Claims: I 2

A 1 · A 2 · A 3 · A 4 · A 5 · A 6 · A 7 · A 8 · B 1 · B 2 · C 1 · C 2 · C 3 · C 4 · C 5 · C 6 · D 1 · D 2 · D 3 · E 1 · E 2 · E 3 · E 4 · F 1 · F 2 · F 3 · G 1 · G 2 · H 1 · H 2 · I 1 · I 2 · I 3 · I 4 · I 5 · J · K · L 1 · L 2 · L 3 · M 1 · M 2 · M 3 · M 4 · N 1 · N 2 · O 1 · O 2 · P 1 · P 2 · P 3 · P 4 · P 5 · Q · R 1 · R 2 · R 3 · S 1 · S 2 · S 3 · S 4 · S 5 · S 6 · S 7 · S 8 · T 1 · T 2 · T 3 · T 4 · T 5 · T 6 · T 7 · T 8 · T 9 · T 10 · U · V · W 1 · W 2 · X · Y · Z · 0-9

• In an independent seventh-grade sample, stereotype endorsement predicted lower academic self-concept at average and high racial centrality but not at low centrality (Study 2 replication) - In an independent seventh-grade sample, stereotype endorsement predicted lower academic self-concept at average and high racial centrality but not at low centrality (Study 2 replication)
• In an initial eye-tracking study, time on action predicted self-explanation (16-second threshold) and gaze shifts were most reliable at detecting its absence - In an initial eye-tracking study, time on action predicted self-explanation (16-second threshold) and gaze shifts were most reliable at detecting its absence
• In an observational path model of at-risk readers, first-grade attention had no significant direct path to third-grade reading comprehension but a significant indirect path through word reading, not listening comprehension - In an observational path model of at-risk readers, first-grade attention had no significant direct path to third-grade reading comprehension but a significant indirect path through word reading, not l
• In an OLS regression, explicit finish lines in teacher prompts were associated with smaller DOK gaps, while explain-reasoning epistemic framing was associated with larger gaps - In an OLS regression, explicit finish lines in teacher prompts were associated with smaller DOK gaps, while explain-reasoning epistemic framing was associated with larger gaps
• In an online case-based course, students perceive cognitive presence as highest and least variable, and teaching presence as the most variable, among the CoI presences and metacognition dimensions - In an online case-based course, students perceive cognitive presence as highest and least variable, and teaching presence as the most variable, among the CoI presences and metacognition dimensions
• In an open simulation game with wide scope and low distance, second-order interventions effectively elicited second-order responses - In an open simulation game with wide scope and low distance, second-order interventions effectively elicited second-order responses
• In an open simulation game, third-order interventions effectively evoked third-order responses - In an open simulation game, third-order interventions effectively evoked third-order responses
• In an out-of-school lab for social sciences, the authenticity level of the learning activity (Productive Failure vs. Direct Instruction) did not affect students' perceived authenticity or situational interest - In an out-of-school lab for social sciences, the authenticity level of the learning activity (Productive Failure vs.
• In an out-of-the-box evaluation, 60% of parents accessed video clips and 52% accessed activities without prompting or instruction - In an out-of-the-box evaluation, 60% of parents accessed video clips and 52% accessed activities without prompting or instruction
• In an RCT, DCMP significantly increased completion of the developmental math sequence and passing of college-level math - In an RCT, DCMP significantly increased completion of the developmental math sequence and passing of college-level math
• In an unrestricted university course, only a minority of students (23 of 68, 34%) reported using LLMs, averaging 12% of discussion-point and 11% of critical-summary submissions - In an unrestricted university course, only a minority of students (23 of 68, 34%) reported using LLMs, averaging 12% of discussion-point and 11% of critical-summary submissions
• In an unscaffolded GenAI-permitted instructional design course, the control group outperformed the experimental group on posttest instructional design performance - In an unscaffolded GenAI-permitted instructional design course, the control group outperformed the experimental group on posttest instructional design performance
• In an urban district facing shrinking enrollment, student achievement was incorporated as a factor in deciding which schools to close, and the study examined whether student outcomes depended on which schools were closed - In an urban district facing shrinking enrollment, student achievement was incorporated as a factor in deciding which schools to close, and the study examined whether student outcomes depended on which
• In applied settings, the beneficial effect of random practice on retention is almost negligible, as the competing meta-analysis itself reports - In applied settings, the beneficial effect of random practice on retention is almost negligible, as the competing meta-analysis itself reports
• In AQUALAB gameplay logs, the estimated RLMM person parameter is positively associated with cumulative trajectory reward (Pearson 0.5842, Spearman 0.5760) - In AQUALAB gameplay logs, the estimated RLMM person parameter is positively associated with cumulative trajectory reward (Pearson 0.5842, Spearman 0.5760)
• In AQUALAB, estimated β is ordered across episode completion status (means 1.181, 1.506, 2.343; Kruskal–Wallis p = 8.62×10−29) and higher-β quintiles complete more content more efficiently - In AQUALAB, estimated β is ordered across episode completion status (means 1.181, 1.506, 2.343; Kruskal–Wallis p = 8.62×10−29) and higher-β quintiles complete more content more efficiently
• In archived sessions, no operator code changes or quantum-logic corrections were needed; eight of nine notebook executions only required one permitted fix of a missing visualization dependency - In archived sessions, no operator code changes or quantum-logic corrections were needed; eight of nine notebook executions only required one permitted fix of a missing visualization dependency
• In artificial action logs, "answer requested" yields the lowest average predicted probability of a correct end-of-unit response, below even "wrong response" - In artificial action logs, "answer requested" yields the lowest average predicted probability of a correct end-of-unit response, below even "wrong response"
• In ASR-assisted college English speaking instruction, corrective feedback and reflection tasks each significantly predict reflective behavior - In ASR-assisted college English speaking instruction, corrective feedback and reflection tasks each significantly predict reflective behavior
• In association-rule mining of survey data from 530 college students in online courses, goal setting, environment structuring and time management were the strategies most often associated with lower digital distraction - In association-rule mining of survey data from 530 college students in online courses, goal setting, environment structuring and time management were the strategies most often associated with lower di
• In authentic undergraduate courses, taking more voluntary practice tests predicts higher final-exam performance, with and without corrective feedback - In authentic undergraduate courses, taking more voluntary practice tests predicts higher final-exam performance, with and without corrective feedback
• In automated evaluation, equivalence with the human baseline depended on the evaluator model: DeepSeek V3 met equivalence for all rubric sources while GPT-4.1 and GPT-4o scored below the baseline - In automated evaluation, equivalence with the human baseline depended on the evaluator model: DeepSeek V3 met equivalence for all rubric sources while GPT-4.1 and GPT-4o scored below the baseline
• In bilingual education, scaffolding denotes support that allows learners to engage with content in a language they only partially know - In bilingual education, scaffolding denotes support that allows learners to engage with content in a language they only partially know
• In BioWorld, confidence was tied to final diagnostic accuracy but not to the first hypothesis - In BioWorld, confidence was tied to final diagnostic accuracy but not to the first hypothesis
• In BioWorld, expert-like initial problem representation and library use correlate with expert-like evidence collection and diagnostic-test ordering - In BioWorld, expert-like initial problem representation and library use correlate with expert-like evidence collection and diagnostic-test ordering
• In bivariate analyses, children sleeping <9 hours/day at ages 5-7 had higher mother- and teacher-reported BRIEF and SDQ scores than those sleeping ≥10 hours/day - In bivariate analyses, children sleeping <9 hours/day at ages 5-7 had higher mother- and teacher-reported BRIEF and SDQ scores than those sleeping ≥10 hours/day
• In blind A/B comparison, raters prefer personalised (Adaptive) questions over non-personalised (Random-topic) questions about 68–69% of the time in Biology and Chemistry - In blind A/B comparison, raters prefer personalised (Adaptive) questions over non-personalised (Random-topic) questions about 68–69% of the time in Biology and Chemistry
• In blind verification, model selection matters more than source type: Bradley-Terry ranking interleaves human coders and LLMs, with per-model win rates spanning significant human advantage to numerical LLM advantage - In blind verification, model selection matters more than source type: Bradley-Terry ranking interleaves human coders and LLMs, with per-model win rates spanning significant human advantage to numerica
• In both analysis years and all tested grades, EL students reach a 50 percent chance of SBAC ELA proficiency within ELPAC overall PL 4 - In both analysis years and all tested grades, EL students reach a 50 percent chance of SBAC ELA proficiency within ELPAC overall PL 4
• In both Colorado and Washington, youth in foster care and youth experiencing homelessness are consistently prioritized in policy and practice, while migrant and justice-involved youth remain less reliably supported - In both Colorado and Washington, youth in foster care and youth experiencing homelessness are consistently prioritized in policy and practice, while migrant and justice-involved youth remain less reli
• In both high school and college groups, learners with negotiation of meaning scored higher on the delayed post-vocabulary test than learners with pre-modified input only - In both high school and college groups, learners with negotiation of meaning scored higher on the delayed post-vocabulary test than learners with pre-modified input only
• In both interaction-log and think-aloud records from a GenAI-assisted instructional-design task, regulation was the most frequent operational label and monitoring the least frequent - In both interaction-log and think-aloud records from a GenAI-assisted instructional-design task, regulation was the most frequent operational label and monitoring the least frequent
• In both TBL formats, tRAT and iSAT scores significantly improve over preceding iRAT scores - In both TBL formats, tRAT and iSAT scores significantly improve over preceding iRAT scores
• In bottom-quartile schools the School Improvement Plan is largely not implemented, with most teachers negative or mixed - In bottom-quartile schools the School Improvement Plan is largely not implemented, with most teachers negative or mixed
• In Case 1, sustained self-critique by the focal teacher led colleagues to attribute students' mathematics failure to parenting and parental lack of authority - In Case 1, sustained self-critique by the focal teacher led colleagues to attribute students' mathematics failure to parenting and parental lack of authority
• In Case 2, persistent strong negative self-critique led teachers to assign deficit narratives to students as having missed opportunities, serving as foils for teachers - In Case 2, persistent strong negative self-critique led teachers to assign deficit narratives to students as having missed opportunities, serving as foils for teachers
• In case examples, leaders and team members showed markedly different average peaks-per-segment EDA values during the same simulation segments - In case examples, leaders and team members showed markedly different average peaks-per-segment EDA values during the same simulation segments
• In case-study courses that shifted to remote instruction, few instructors offered collaborative learning activities, and some dropped ones used before - In case-study courses that shifted to remote instruction, few instructors offered collaborative learning activities, and some dropped ones used before
• In catch trials, large numbers elicit greater right-hemisphere P300 positivity than small numbers - In catch trials, large numbers elicit greater right-hemisphere P300 positivity than small numbers
• In chemistry cycle 1, students actively engaged in experimentation still did worse on the volume-rate item, with correct answers falling 6% from pre-test to post-test - In chemistry cycle 1, students actively engaged in experimentation still did worse on the volume-rate item, with correct answers falling 6% from pre-test to post-test
• In children with cochlear implants, hearing age correlates with fewer non-table multiplication errors and faster borrow subtraction, unlike in hearing peers - In children with cochlear implants, hearing age correlates with fewer non-table multiplication errors and faster borrow subtraction, unlike in hearing peers
• In children, shifting is a more powerful predictor of creativity than fluid and crystallized intelligence - In children, shifting is a more powerful predictor of creativity than fluid and crystallized intelligence
• In children, the BOLD numerical ratio effect correlates with individual differences in the behavioral ratio effect in right OTC, left superior parietal cortex, and bilateral IFG; no such correlation reaches significance in adults - In children, the BOLD numerical ratio effect correlates with individual differences in the behavioral ratio effect in right OTC, left superior parietal cortex, and bilateral IFG; no such correlation r
• In Chinese children aged 10-12, oral word reading efficiency is positively correlated with cortical thickness in the LSTG, LITG, LSMG and RSTG - In Chinese children aged 10-12, oral word reading efficiency is positively correlated with cortical thickness in the LSTG, LITG, LSMG and RSTG
• In Chinese children aged 10-12, silent sentence reading comprehension is positively correlated with cortical thickness in the left parahippocampus and right calcarine fissure - In Chinese children aged 10-12, silent sentence reading comprehension is positively correlated with cortical thickness in the left parahippocampus and right calcarine fissure
• In CHSRI small high schools, strong freshman course performance is associated with the combination of developmental practices, deep principal leadership, and teacher influence - In CHSRI small high schools, strong freshman course performance is associated with the combination of developmental practices, deep principal leadership, and teacher influence
• In Chun and Plass's CyberBuch studies, the text + picture annotation group significantly outperformed text-definition and text + video groups on a vocabulary test - In Chun and Plass's CyberBuch studies, the text + picture annotation group significantly outperformed text-definition and text + video groups on a vocabulary test
• In cities with individually targeted grant activities, more than three-quarters of grant participants collaborated across sectors - In cities with individually targeted grant activities, more than three-quarters of grant participants collaborated across sectors
• In Clark County, One-Star designation significantly raises math and ELA scores for all students - In Clark County, One-Star designation significantly raises math and ELA scores for all students
• In classroom video labeling, high raw agreement (often exceeding 90%) co-occurred with low chance-corrected κ due to temporal misalignment - In classroom video labeling, high raw agreement (often exceeding 90%) co-occurred with low chance-corrected κ due to temporal misalignment
• In CLIL, teachers perceive conceptual hollowing, a bilingual bluff, translation dependency, and a synthesis illusion - In CLIL, teachers perceive conceptual hollowing, a bilingual bluff, translation dependency, and a synthesis illusion
• In CLL, teachers perceive a trust erosion cycle, AI dominance in groups, collaborative hollowing, and a counselor's dilemma - In CLL, teachers perceive a trust erosion cycle, AI dominance in groups, collaborative hollowing, and a counselor's dilemma
• In CLT, teachers perceive an authenticity crisis, risk-free fluency, a confidence mirage, and pragmatic blindness - In CLT, teachers perceive an authenticity crisis, risk-free fluency, a confidence mirage, and pragmatic blindness
• In Coach Wright, Asset-mindset participants noticed Jeremy's positive behaviors while Deficit-mindset participants framed behavior as rule compliance, and strength language sometimes appeared without referencing actual strengths - In Coach Wright, Asset-mindset participants noticed Jeremy's positive behaviors while Deficit-mindset participants framed behavior as rule compliance, and strength language sometimes appeared without
• In collaborative inquiry learning, dyads use more team regulation than task regulation in all support conditions - In collaborative inquiry learning, dyads use more team regulation than task regulation in all support conditions
• In college groups, negotiation of meaning made no difference to comprehensible input obtained in the match task - In college groups, negotiation of meaning made no difference to comprehensible input obtained in the match task
• In college groups, no correlation was found between frequency of negotiation of meaning and vocabulary score - In college groups, no correlation was found between frequency of negotiation of meaning and vocabulary score
• In compulsory secondary education PE, anger and fear predominated, driven mainly by physical fitness testing, grading pressures and “exposed body” experiences - In compulsory secondary education PE, anger and fear predominated, driven mainly by physical fitness testing, grading pressures and “exposed body” experiences
• In computer-mediated problem solving, students may attribute their problems to the technology rather than to their own work, complicating how they frame the problem context - In computer-mediated problem solving, students may attribute their problems to the technology rather than to their own work, complicating how they frame the problem context
• In continuous recognition memory, the lag function is inverted U-shaped after a short retention interval and monotonically increasing after a long retention interval - In continuous recognition memory, the lag function is inverted U-shaped after a short retention interval and monotonically increasing after a long retention interval
• In CPS dialogues, low-achievers requested more support while high-achievers provided more support and reminders, though group differences were not statistically significant - In CPS dialogues, low-achievers requested more support while high-achievers provided more support and reminders, though group differences were not statistically significant
• In CPS ninth-grade math sections using mastery-based or weekly grading, those categories determined nearly all of the final grade; otherwise assessments carried the highest weight, with a median of 60 percent exceeding the CPS/CTU 50 percent recommendation - In CPS ninth-grade math sections using mastery-based or weekly grading, those categories determined nearly all of the final grade; otherwise assessments carried the highest weight, with a median of 60
• In CPS, student teachers were disproportionately placed in North Side schools and in more socioeconomically advantaged schools with stronger organizational ratings - In CPS, student teachers were disproportionately placed in North Side schools and in more socioeconomically advantaged schools with stronger organizational ratings
• In CSCL history inquiry, regulation of social activities predicts group performance while social activities are negatively related to group performance - In CSCL history inquiry, regulation of social activities predicts group performance while social activities are negatively related to group performance
• In CSCL written civic discussions, gaps exist between a composer's emotion labeling and others' emotion recognition - In CSCL written civic discussions, gaps exist between a composer's emotion labeling and others' emotion recognition
• In delayed recall, the random procedure reversed the pattern, exceeding the orderly procedure by 16.4% fewer errors - In delayed recall, the random procedure reversed the pattern, exceeding the orderly procedure by 16.4% fewer errors
• In deployment, 13% of sampled LLM agent responses were faulty and 37% very useful, with response quality improving over weeks of use - In deployment, 13% of sampled LLM agent responses were faulty and 37% very useful, with response quality improving over weeks of use
• In Desktop-VR, interaction format (object movement vs. camera movement vs. no interaction) showed no significant main effect on learning outcomes - In Desktop-VR, interaction format (object movement vs.
• In directional manual testing, reward hardening halved unusable interactive pages (25%→10%) and eliminated page-entry failures (2/24→0/30) - In directional manual testing, reward hardening halved unusable interactive pages (25%→10%) and eliminated page-entry failures (2/24→0/30)
• In disagreement cases, blinded educators more frequently prefer CLARA developmental estimates over publisher recommendations - In disagreement cases, blinded educators more frequently prefer CLARA developmental estimates over publisher recommendations
• In discipline-specific exploratory regressions, neither Stroop RT cost nor complex No-Go accuracy significantly predicted science or maths misconception measures separately - In discipline-specific exploratory regressions, neither Stroop RT cost nor complex No-Go accuracy significantly predicted science or maths misconception measures separately
• In e-learning text comprehension, higher working memory and lower self-reported navigation behavior predict better comprehension - In e-learning text comprehension, higher working memory and lower self-reported navigation behavior predict better comprehension
• In early online implementations of the Skyline Data Path course, Filipino students' success rates exceeded the course average while Latino students' fell below it - In early online implementations of the Skyline Data Path course, Filipino students' success rates exceeded the course average while Latino students' fell below it
• In early prototype testing, AI-generated visuals were the main barrier to real-world readiness, rated lower than text and narration - In early prototype testing, AI-generated visuals were the main barrier to real-world readiness, rated lower than text and narration
• In ECEC research, engagement is typically defined as behaviors and interactions with the environment while involvement is described as an internal experience - In ECEC research, engagement is typically defined as behaviors and interactions with the environment while involvement is described as an internal experience
• In EERs, autonomy, competence, and relatedness are each supported by specific design features per self-determination theory - In EERs, autonomy, competence, and relatedness are each supported by specific design features per self-determination theory
• In elementary book talk, students spent significantly more time interacting with a fixed-role AI peer than with their homeroom teacher in both grades - In elementary book talk, students spent significantly more time interacting with a fixed-role AI peer than with their homeroom teacher in both grades
• In elementary grades, students in schools with extensive standards-related professional development reported significantly larger improvements in academic demand, rigor, instructional clarity, and teacher support than students in schools with limited professional development - In elementary grades, students in schools with extensive standards-related professional development reported significantly larger improvements in academic demand, rigor, instructional clarity, and tea
• In elementary school students, short-term green breaks restore attention and working memory, with effects on inhibition mixed - In elementary school students, short-term green breaks restore attention and working memory, with effects on inhibition mixed
• In elite STEM graduate students, educational acceleration did not covary with age-50 well-being, with small correlations if anything positive - In elite STEM graduate students, educational acceleration did not covary with age-50 well-being, with small correlations if anything positive
• In encounters where both client and worker are predominantly defensive, the learning cycle stalls before implementing, reflecting and consolidating actions - In encounters where both client and worker are predominantly defensive, the learning cycle stalls before implementing, reflecting and consolidating actions
• In encounters where both parties are predominantly expansive, early cycle actions such as questioning and modeling are typically absent and the focus is on implementing and consolidating - In encounters where both parties are predominantly expansive, early cycle actions such as questioning and modeling are typically absent and the focus is on implementing and consolidating
• In eSpark quests requiring three post-quiz attempts, students reached the 80 percent mastery criterion only 14 percent of the time - In eSpark quests requiring three post-quiz attempts, students reached the 80 percent mastery criterion only 14 percent of the time
• In every district, more educators agree than disagree that they share a common language for the SLO process - In every district, more educators agree than disagree that they share a common language for the SLO process
• In examination weeks, students revisited prior topics and used exercises, whose deadlines had passed, as formative practice for the exams - In examination weeks, students revisited prior topics and used exercises, whose deadlines had passed, as formative practice for the exams
• In experience sampling during lessons, tired was the only feeling rated above the scale midpoint, and positive feelings (calm, happy, relaxed) ranked second to fourth, ahead of stressed and bored - In experience sampling during lessons, tired was the only feeling rated above the scale midpoint, and positive feelings (calm, happy, relaxed) ranked second to fourth, ahead of stressed and bored
• In Experiment 1, a five-trial metacognitive prediction-plus-feedback intervention significantly reduced reminder bias, producing more optimal reminder-setting behaviour - In Experiment 1, a five-trial metacognitive prediction-plus-feedback intervention significantly reduced reminder bias, producing more optimal reminder-setting behaviour
• In Experiment 1, abstract representations produced better symbol learning than multiple concrete representations, but only for children who completed the concrete condition first - In Experiment 1, abstract representations produced better symbol learning than multiple concrete representations, but only for children who completed the concrete condition first
• In Experiment 1, cue-only JOLs produced significantly better Phase B memory and transfer than restudy, while overt retrieval's memory advantage over restudy was only marginal - In Experiment 1, cue-only JOLs produced significantly better Phase B memory and transfer than restudy, while overt retrieval's memory advantage over restudy was only marginal
• In Experiment 1, diagnosis scores were better for the liver cirrhosis case than the pheochromocytoma case, but not among experts - In Experiment 1, diagnosis scores were better for the liver cirrhosis case than the pheochromocytoma case, but not among experts
• In Experiment 1, differences-matter instruction shifted learners' self-reported effort allocation toward detecting differences and away from detecting commonalities - In Experiment 1, differences-matter instruction shifted learners' self-reported effort allocation toward detecting differences and away from detecting commonalities
• In Experiment 1, dyads that more often chose maximum CSCL scaffolding had lower post-test socio-discursive MAS - In Experiment 1, dyads that more often chose maximum CSCL scaffolding had lower post-test socio-discursive MAS
• In Experiment 1, general self-assessment feedback during a learning phase led to less accurate self-assessment in a subsequent no-feedback test phase than receiving no feedback at all - In Experiment 1, general self-assessment feedback during a learning phase led to less accurate self-assessment in a subsequent no-feedback test phase than receiving no feedback at all
• In Experiment 1, I-PS students solved the initial problem better but PS-I students learned more from the subsequent instructional video - In Experiment 1, I-PS students solved the initial problem better but PS-I students learned more from the subsequent instructional video
• In Experiment 1, interim tasks with high retrieval probability (overt retrieval, cue-only JOLs) enhanced new inductive learning more than low-retrieval tasks (cue–target JOLs, restudy) on both memory and transfer - In Experiment 1, interim tasks with high retrieval probability (overt retrieval, cue-only JOLs) enhanced new inductive learning more than low-retrieval tasks (cue–target JOLs, restudy) on both memory
• In Experiment 1, learners interleaved more only when high utility value of distinguishing was combined with instruction that differences matter, with the two factors interacting rather than showing main effects - In Experiment 1, learners interleaved more only when high utility value of distinguishing was combined with instruction that differences matter, with the two factors interacting rather than showing ma
• In Experiment 1, lower confidence predicted greater offloading beyond objective performance in the no-feedback group, but not in the feedback group - In Experiment 1, lower confidence predicted greater offloading beyond objective performance in the no-feedback group, but not in the feedback group
• In Experiment 1, mental effort was negatively related to perceived effectiveness and (via perceived effectiveness) willingness to use interleaved studying, with a more influential role for interleaved than blocked studying - In Experiment 1, mental effort was negatively related to perceived effectiveness and (via perceived effectiveness) willingness to use interleaved studying, with a more influential role for interleaved
• In Experiment 1, metacognitive preference for interleaving showed main effects of utility value and differences-matter instruction without an interaction - In Experiment 1, metacognitive preference for interleaving showed main effects of utility value and differences-matter instruction without an interaction
• In Experiment 1, model concepts increase monotonically with expertise while detailed biomedical concepts show an inverted U, confirming knowledge encapsulation - In Experiment 1, model concepts increase monotonically with expertise while detailed biomedical concepts show an inverted U, confirming knowledge encapsulation
• In Experiment 1, overall final-test recall was lower in the blocked 50% group than in the random 25% group (d = 0.40), an exploratory between-groups difference. - In Experiment 1, overall final-test recall was lower in the blocked 50% group than in the random 25% group (d = 0.40), an exploratory between-groups difference.
• In Experiment 1, participants in both groups were significantly biased towards excessive reminder use relative to the optimal strategy - In Experiment 1, participants in both groups were significantly biased towards excessive reminder use relative to the optimal strategy
• In Experiment 1, participants predicted masked speech (speech in pink noise) to be more distracting than pure speech, even predicting pure speech to be slightly helpful - In Experiment 1, participants predicted masked speech (speech in pink noise) to be more distracting than pure speech, even predicting pure speech to be slightly helpful
• In Experiment 1, participants were objectively less distracted by masked speech than by pure speech in serial recall, although both types caused significant distraction relative to quiet - In Experiment 1, participants were objectively less distracted by masked speech than by pure speech in serial recall, although both types caused significant distraction relative to quiet
• In Experiment 1, personalized feedback after the test made students significantly more positive about interleaved studying, yet they still did not consider it more effective or desirable than blocked studying - In Experiment 1, personalized feedback after the test made students significantly more positive about interleaved studying, yet they still did not consider it more effective or desirable than blocked
• In Experiment 1, receiving self-assessment feedback during the learning phase led to less accurate task selection than no feedback, despite feedback stating actual performance - In Experiment 1, receiving self-assessment feedback during the learning phase led to less accurate task selection than no feedback, despite feedback stating actual performance
• In Experiment 1, retrospective judgments after firsthand experience still showed the metacognitive illusion, and it was amplified in participants who had earlier given prospective judgments - In Experiment 1, retrospective judgments after firsthand experience still showed the metacognitive illusion, and it was amplified in participants who had earlier given prospective judgments
• In Experiment 1, self-regulation skills significantly predicted socio-discursive MAS only in the adaptable CSCL script condition - In Experiment 1, self-regulation skills significantly predicted socio-discursive MAS only in the adaptable CSCL script condition
• In Experiment 1, students' prospective judgments of learning were higher for blocked studying even though actual test performance was higher for interleaved studying - In Experiment 1, students' prospective judgments of learning were higher for blocked studying even though actual test performance was higher for interleaved studying
• In Experiment 1, task-selection accuracy during the no-feedback test phase did not differ between feedback and control conditions - In Experiment 1, task-selection accuracy during the no-feedback test phase did not differ between feedback and control conditions
• In Experiment 1, the Confirmatory-Only condition learned the target category faster than the Complete condition after the category switch. - In Experiment 1, the Confirmatory-Only condition learned the target category faster than the Complete condition after the category switch.
• In Experiment 1, the CSCL script condition significantly affected domain-specific MAS, with only the maximal script significantly outperforming the minimal script - In Experiment 1, the CSCL script condition significantly affected domain-specific MAS, with only the maximal script significantly outperforming the minimal script
• In Experiment 1, the extent of informative interleaving did not correlate with category assignment performance, which the authors interpret as a utilization deficiency - In Experiment 1, the extent of informative interleaving did not correlate with category assignment performance, which the authors interpret as a utilization deficiency
• In Experiment 1, the feedback group showed significantly lower absolute (unsigned) metacognitive bias than the no-feedback group at both pre-task and post-task - In Experiment 1, the feedback group showed significantly lower absolute (unsigned) metacognitive bias than the no-feedback group at both pre-task and post-task
• In Experiment 1, the feedback intervention reduced pre-task signed metacognitive bias (underconfidence) but the group difference did not persist at post-task - In Experiment 1, the feedback intervention reduced pre-task signed metacognitive bias (underconfidence) but the group difference did not persist at post-task
• In Experiment 1, the interim learning task did not affect Phase A posttest performance, indicating the forward benefit was not due to improved prior learning - In Experiment 1, the interim learning task did not affect Phase A posttest performance, indicating the forward benefit was not due to improved prior learning
• In Experiment 1, the numerical comparison group was more accurate on symbolic arithmetic than the line-length addition group, the only pairwise accuracy difference - In Experiment 1, the numerical comparison group was more accurate on symbolic arithmetic than the line-length addition group, the only pairwise accuracy difference
• In Experiment 1, the total number of concepts used in pathophysiological case explanations shows an inverted U-shaped relation with level of medical expertise - In Experiment 1, the total number of concepts used in pathophysiological case explanations shows an inverted U-shaped relation with level of medical expertise
• In Experiment 1, the type-of-recall by varied-constant by distribution interaction was significant, with a massed-distributed effect only in constant cued recall and a distribution effect in both free-recall conditions - In Experiment 1, the type-of-recall by varied-constant by distribution interaction was significant, with a massed-distributed effect only in constant cued recall and a distribution effect in both free
• In Experiment 1, unlearning of the initial category and re-learning of the target category proceeded in parallel rather than unlearning preceding re-learning. - In Experiment 1, unlearning of the initial category and re-learning of the target category proceeded in parallel rather than unlearning preceding re-learning.
• In Experiment 2 the authentic-setting effect on retention did not replicate and reinstating the setting as a test background produced no context effects - In Experiment 2 the authentic-setting effect on retention did not replicate and reinstating the setting as a test background produced no context effects
• In Experiment 2 with speech babble masking, participants again predicted masked speech to be more distracting than pure speech while being objectively less distracted by it, replicating Experiment 1 - In Experiment 2 with speech babble masking, participants again predicted masked speech to be more distracting than pure speech while being objectively less distracted by it, replicating Experiment 1
• In Experiment 2, absolute metacognitive bias decreased linearly across the four additive intervention groups, and the full intervention group was significantly less biased than control - In Experiment 2, absolute metacognitive bias decreased linearly across the four additive intervention groups, and the full intervention group was significantly less biased than control
• In Experiment 2, actual regulation of adaptable heuristic worked examples showed no significant correlation with self-regulation skills or MAS outcomes - In Experiment 2, actual regulation of adaptable heuristic worked examples showed no significant correlation with self-regulation skills or MAS outcomes
• In Experiment 2, an interaction between probe and expertise shows intermediates' enabling-condition knowledge is not yet integrated into their illness scripts - In Experiment 2, an interaction between probe and expertise shows intermediates' enabling-condition knowledge is not yet integrated into their illness scripts
• In Experiment 2, children's confidence-task performance correlated with Winner and Ask choices but not Endorse choices, controlling for age - In Experiment 2, children's confidence-task performance correlated with Winner and Ask choices but not Endorse choices, controlling for age
• In Experiment 2, I-PS students outperformed PS-I students on problem-solving, idea generation, and embedded video quizzes - In Experiment 2, I-PS students outperformed PS-I students on problem-solving, idea generation, and embedded video quizzes
• In Experiment 2, making metacognitive predictions alone did not improve calibration, performance feedback was sufficient, and explicit metacognitive feedback added no significant benefit - In Experiment 2, making metacognitive predictions alone did not improve calibration, performance feedback was sufficient, and explicit metacognitive feedback added no significant benefit
• In Experiment 2, mental effort over time interacted with condition: the feedback + contrast condition increased effort from learning to test phase while other conditions decreased - In Experiment 2, mental effort over time interacted with condition: the feedback + contrast condition increased effort from learning to test phase while other conditions decreased
• In Experiment 2, neither self-assessment feedback plus correct answers nor plus contrasting own with correct answers improved test-phase self-assessment accuracy - In Experiment 2, neither self-assessment feedback plus correct answers nor plus contrasting own with correct answers improved test-phase self-assessment accuracy
• In Experiment 2, self-regulation skills significantly positively predicted domain-specific MAS only in the minimal heuristic worked examples condition - In Experiment 2, self-regulation skills significantly positively predicted domain-specific MAS only in the minimal heuristic worked examples condition
• In Experiment 2, signed metacognitive bias scores showed no significant group effect or linear trend, failing to replicate the Experiment 1 signed-bias finding - In Experiment 2, signed metacognitive bias scores showed no significant group effect or linear trend, failing to replicate the Experiment 1 signed-bias finding
• In Experiment 2, task-selection accuracy during the learning phase did not differ between feedback and control conditions, unlike Experiment 1 - In Experiment 2, task-selection accuracy during the learning phase did not differ between feedback and control conditions, unlike Experiment 1
• In Experiment 2, the heuristic worked examples condition significantly affected socio-discursive MAS, with maximal worked examples descriptively best and no significant post-hoc differences - In Experiment 2, the heuristic worked examples condition significantly affected socio-discursive MAS, with maximal worked examples descriptively best and no significant post-hoc differences
• In Experiment 2, the interleaving benefit on actual test outcomes was not statistically significant, unlike in Experiment 1 - In Experiment 2, the interleaving benefit on actual test outcomes was not statistically significant, unlike in Experiment 1
• In Experiment 2, the native language × frequency interaction is significant, with both groups responding faster to high-frequency items - In Experiment 2, the native language × frequency interaction is significant, with both groups responding faster to high-frequency items
• In Experiment 2, the proportion of fault (pathophysiological) statements decreased monotonically with expertise regardless of probe - In Experiment 2, the proportion of fault (pathophysiological) statements decreased monotonically with expertise regardless of probe
• In Experiment 3, individual learners showed greater forgetting over 24 hours than paired learners - In Experiment 3, individual learners showed greater forgetting over 24 hours than paired learners
• In exploratory between-subject analyses, embodied learning showed larger effects against passive non-embodied controls (g = 0.43) than against active non-embodied controls (g = 0.86) - In exploratory between-subject analyses, embodied learning showed larger effects against passive non-embodied controls (g = 0.43) than against active non-embodied controls (g = 0.86)
• In exploratory synthetic control analyses, two GEO no-deadlines programs received 120 to 130 fewer proposals relative to their synthetic counterfactuals - In exploratory synthetic control analyses, two GEO no-deadlines programs received 120 to 130 fewer proposals relative to their synthetic counterfactuals
• In fabric manipulation, the algorithmic performance was contingent on repeated combinations of components paired with steps of the craft - In fabric manipulation, the algorithmic performance was contingent on repeated combinations of components paired with steps of the craft
• In fall 1998, five percent of children were repeating kindergarten and six percent were attending kindergarten for the first time despite being age-eligible a year earlier - In fall 1998, five percent of children were repeating kindergarten and six percent were attending kindergarten for the first time despite being age-eligible a year earlier
• In Ferentino (1991), social skills training produced a large significant effect on teacher-rated Vineland Socialization but not on four other social-emotional measures - In Ferentino (1991), social skills training produced a large significant effect on teacher-rated Vineland Socialization but not on four other social-emotional measures
• In fifth-grade mathematics, ITBS scores declined while ISAT scores rose, a statistically significant difference in opposing trends - In fifth-grade mathematics, ITBS scores declined while ISAT scores rose, a statistically significant difference in opposing trends
• In fifth-grade reading, ITBS scores declined significantly more than ISAT scores from 1999 to 2002 - In fifth-grade reading, ITBS scores declined significantly more than ISAT scores from 1999 to 2002
• In first-year GenAI adoption in business higher education, curriculum-integrated modules reported enhanced student engagement, performance and employability, while fragmented approaches were more susceptible to ethical concerns, overreliance and inequality - In first-year GenAI adoption in business higher education, curriculum-integrated modules reported enhanced student engagement, performance and employability, while fragmented approaches were more susc
• In five scaled early learning coaching systems, coach-to-site ratios averaged about 1 coach per 22 sites, dosage varied widely, and participants perceived benefits in educator satisfaction, practice, and program quality - In five scaled early learning coaching systems, coach-to-site ratios averaged about 1 coach per 22 sites, dosage varied widely, and participants perceived benefits in educator satisfaction, practice,
• In fixed-duration conditions, accuracy rises faster with presentation duration in VGPs, confirming greater sensory integration and ruling out non-decision-time accounts - In fixed-duration conditions, accuracy rises faster with presentation duration in VGPs, confirming greater sensory integration and ruling out non-decision-time accounts
• In four-year private institutions, white and Asian students had nearly identical persistence rates (89.8 and 89.6 percent), but Asian students were more likely to continue at their starting institution (82.5 percent) - In four-year private institutions, white and Asian students had nearly identical persistence rates (89.8 and 89.6 percent), but Asian students were more likely to continue at their starting institutio
• In French first-graders, a three-factor structure distinguishing lower level language skills from discourse skills fits better than a two-factor oral language structure at both the beginning and end of first grade - In French first-graders, a three-factor structure distinguishing lower level language skills from discourse skills fits better than a two-factor oral language structure at both the beginning and end o
• In French first-graders, T1 decoding precursors directly predicted T2 reading comprehension above their contribution through decoding skills - In French first-graders, T1 decoding precursors directly predicted T2 reading comprehension above their contribution through decoding skills
• In frequency-based models, Argue, Discuss, Evaluate, and Socialize show significant positive associations with grades, but no interaction type is significant in the full model - In frequency-based models, Argue, Discuss, Evaluate, and Socialize show significant positive associations with grades, but no interaction type is significant in the full model
• In gamers' interview reports, sustained gaming engagement appeared closely related to controlling an optimal level of challenge: games too hard were often abandoned and games too easy lost their interest - In gamers' interview reports, sustained gaming engagement appeared closely related to controlling an optimal level of challenge: games too hard were often abandoned and games too easy lost their inter
• In Georgia, a two-month accelerated manufacturing program with micro-credentials led to recent high school graduates being hired, including employers making an exception to their under-21 hiring practice - In Georgia, a two-month accelerated manufacturing program with micro-credentials led to recent high school graduates being hired, including employers making an exception to their under-21 hiring pract
• In German secondary-school mathematics, effects of self-concept on achievement are lagged (lag1) whereas effects of achievement on self-concept are more contemporaneous (lag0) - In German secondary-school mathematics, effects of self-concept on achievement are lagged (lag1) whereas effects of achievement on self-concept are more contemporaneous (lag0)
• In Goddard's Vineland examination of 1547 pupils, only about half of mentally over-age and under-age pupils show corresponding advancement or retardation in school grading - In Goddard's Vineland examination of 1547 pupils, only about half of mentally over-age and under-age pupils show corresponding advancement or retardation in school grading
• In good adult writers, maximum speed within an arc rises with radial length (Spearman rank correlation 0.96 across 33 segments), approaching a fixed limit; poorer writers and children show much lower correlation - In good adult writers, maximum speed within an arc rises with radial length (Spearman rank correlation 0.96 across 33 segments), approaching a fixed limit; poorer writers and children show much lower
• In Grade 3, both problem solving and arithmetical facts are predicted by the preschool WM–flexibility component - In Grade 3, both problem solving and arithmetical facts are predicted by the preschool WM–flexibility component
• In Grade 4, reading comprehension gains were statistically comparable between the mental simulation training group and the control training group - In Grade 4, reading comprehension gains were statistically comparable between the mental simulation training group and the control training group
• In Grade 9, fewer problems during distance learning were associated with better verbal achievement, summer school attendance was associated with lower reading and listening achievement, and learning-condition relations did not differ between student groups - In Grade 9, fewer problems during distance learning were associated with better verbal achievement, summer school attendance was associated with lower reading and listening achievement, and learning-c
• In Grade 9, negative achievement trends emerged for non-SEN and SEN-L-R students in all domains, and SEN-L-R trends were always significantly more pronounced than for non-SEN peers - In Grade 9, negative achievement trends emerged for non-SEN and SEN-L-R students in all domains, and SEN-L-R trends were always significantly more pronounced than for non-SEN peers
• In Grossman's case study, English teachers without formal teacher education adopted text-centered instruction, while teacher education graduates adopted student-centered instruction - In Grossman's case study, English teachers without formal teacher education adopted text-centered instruction, while teacher education graduates adopted student-centered instruction
• In group B, usage of I–we gradually increased and peaked in the final stage during critical evaluation, suggesting intrapersonal collective voice drives critical evaluation of evidence - In group B, usage of I–we gradually increased and peaked in the final stage during critical evaluation, suggesting intrapersonal collective voice drives critical evaluation of evidence
• In group design studies, effects of family-implemented literacy interventions vary by outcome type: meaning-focused outcomes (g = 0.41) show larger effects than code-focused outcomes (g = 0.28) - In group design studies, effects of family-implemented literacy interventions vary by outcome type: meaning-focused outcomes (g = 0.41) show larger effects than code-focused outcomes (g = 0.28)
• In groups with pre-established positive collaborative relationships, NGI clusters aligned with high positive emotions and frequent group synchronisation during collaborative DGBL - In groups with pre-established positive collaborative relationships, NGI clusters aligned with high positive emotions and frequent group synchronisation during collaborative DGBL
• In Guglielmo and Tryon (2001), social skills training plus reinforcement increased sharing behaviors significantly more than reinforcement alone, while effects on being in a group were positive but not significant - In Guglielmo and Tryon (2001), social skills training plus reinforcement increased sharing behaviors significantly more than reinforcement alone, while effects on being in a group were positive but no
• In Gunn (1996), LiPS effects on word accuracy/fluency and phonemic decoding were negative and substantively important but not statistically significant - In Gunn (1996), LiPS effects on word accuracy/fluency and phonemic decoding were negative and substantively important but not statistically significant
• In Han students, higher initial metacognitive knowledge predicted both a higher starting point and a faster growth rate of vocabulary breadth - In Han students, higher initial metacognitive knowledge predicted both a higher starting point and a faster growth rate of vocabulary breadth
• In Harvard's introductory physics course, average FCI posttest scores and normalized gain rose sharply in the year it switched from traditional lectures to Peer Instruction - In Harvard's introductory physics course, average FCI posttest scores and normalized gain rose sharply in the year it switched from traditional lectures to Peer Instruction
• In healthy controls, the processing speed–SAS-II association is not significant once IQ is accounted for - In healthy controls, the processing speed–SAS-II association is not significant once IQ is accounted for
• In held-out pairwise judge evaluation, combining Edu-QuRater and answer-structure GRPO rewards yields the highest pedagogical-quality win rate (81.08%) while retaining instruction-following above parity (68.24%) against the Qwen3-4B base model - In held-out pairwise judge evaluation, combining Edu-QuRater and answer-structure GRPO rewards yields the highest pedagogical-quality win rate (81.08%) while retaining instruction-following above pari
• In hierarchical regression, gender and LD status contributed 6.4% to science achievements, and auditory learning preference contributed a further significant 3.1% beyond them - In hierarchical regression, gender and LD status contributed 6.4% to science achievements, and auditory learning preference contributed a further significant 3.1% beyond them
• In high school groups, frequency of negotiation of meaning correlates positively with vocabulary score (r = 0.761) and with comprehensible input (r = 0.310) - In high school groups, frequency of negotiation of meaning correlates positively with vocabulary score (r = 0.761) and with comprehensible input (r = 0.310)
• In high school groups, learners with negotiation of meaning obtained more comprehensible input in the match task than learners with pre-modified input only - In high school groups, learners with negotiation of meaning obtained more comprehensible input in the match task than learners with pre-modified input only
• In high schools, extensive-PD schools started with significantly lower rigor and teacher support but closed the gap by early implementation, while academic demand and clarity improved at rates comparable to limited-PD schools - In high schools, extensive-PD schools started with significantly lower rigor and teacher support but closed the gap by early implementation, while academic demand and clarity improved at rates compara
• In high-stakes homework settings, answer-first checking functions as a rational self-regulation strategy and diagnostic checkpoint rather than shortcutting - In high-stakes homework settings, answer-first checking functions as a rational self-regulation strategy and diagnostic checkpoint rather than shortcutting
• In higher education, the purported Silicon Valley revolution is undermined by detrimental effects on academic integrity and erosion of evidence-based pedagogical practices, compounded by the prevailing crisis of higher education - In higher education, the purported Silicon Valley revolution is undermined by detrimental effects on academic integrity and erosion of evidence-based pedagogical practices, compounded by the prevailin
• In human evaluation, abstraction preference was associated with perceived response quality, and more complex questions generally received lower ratings - In human evaluation, abstraction preference was associated with perceived response quality, and more complex questions generally received lower ratings
• In hunter-gatherer communities, children themselves generally decide whether to attend school, reflecting the cultural value of childhood autonomy - In hunter-gatherer communities, children themselves generally decide whether to attend school, reflecting the cultural value of childhood autonomy
• In hypothetical scenarios, 5- and 6-year-olds most often suggest goal reinstatement and goal substitution, and their strategies do not differ for sadness versus anger - In hypothetical scenarios, 5- and 6-year-olds most often suggest goal reinstatement and goal substitution, and their strategies do not differ for sadness versus anger
• In immediate recall by school pupils, objects shown are remembered better than written words, and written words better than spoken words - In immediate recall by school pupils, objects shown are remembered better than written words, and written words better than spoken words
• In immediate recall, an orderly (fixed spatial-temporal) procedure for spelling word groups produced fewer errors than a random procedure, by 9.4% - In immediate recall, an orderly (fixed spatial-temporal) procedure for spelling word groups produced fewer errors than a random procedure, by 9.4%
• In individual dialogue patterns, the dominant speaker learns more than the listening partner, potentially explaining null collaboration findings - In individual dialogue patterns, the dominant speaker learns more than the listening partner, potentially explaining null collaboration findings
• In ineffective CL teams, belongingness goals are negatively related to socially oriented task engagement, and no other goal domain relates significantly to engagement - In ineffective CL teams, belongingness goals are negatively related to socially oriented task engagement, and no other goal domain relates significantly to engagement
• In informal social scenes, AgentSchool generates plausible traces of peripheral participation, clique formation, aggressor-induced cohesion, and opinion-leader emergence consistent with classroom social theories - In informal social scenes, AgentSchool generates plausible traces of peripheral participation, clique formation, aggressor-induced cohesion, and opinion-leader emergence consistent with classroom soci
• In inquiry learning of combinatorics, learners given a Text + Arithmetic representation outperformed learners given tree diagrams on total post-test scores - In inquiry learning of combinatorics, learners given a Text + Arithmetic representation outperformed learners given tree diagrams on total post-test scores
• In interviews with 25 engineering students at one Swedish university, students described GenAI as acceptable when it stimulates reflection and directly copying its outputs as cheating, and one used its fallibility as a prompt to double-check - In interviews with 25 engineering students at one Swedish university, students described GenAI as acceptable when it stimulates reflection and directly copying its outputs as cheating, and one used it
• In interviews, families who used the app's features more extensively seemed to have better internalized its purpose, and those who explored it most reported stronger self-reported changes in joint media engagement and science - In interviews, families who used the app's features more extensively seemed to have better internalized its purpose, and those who explored it most reported stronger self-reported changes in joint med
• In Irving ISD, 56% of educators who served as program coaches since 2017 were promoted to new positions - In Irving ISD, 56% of educators who served as program coaches since 2017 were promoted to new positions
• In its first 3-year grant cycle, 21CSLA served approximately 8,300 California leaders through 333 communities of practice and localized professional learning offerings plus coaching for hundreds of leaders - In its first 3-year grant cycle, 21CSLA served approximately 8,300 California leaders through 333 communities of practice and localized professional learning offerings plus coaching for hundreds of le
• In its traditional treatment, germane cognitive load is essentially indistinguishable from intrinsic load and may be a redundant concept - In its traditional treatment, germane cognitive load is essentially indistinguishable from intrinsic load and may be a redundant concept
• In JEU SERAI, questionnaire-like in-game items (diary ordering, mini game ranking, narrative questionnaires) correlated best with RIASEC questionnaire results, while other item types correlated poorly - In JEU SERAI, questionnaire-like in-game items (diary ordering, mini game ranking, narrative questionnaires) correlated best with RIASEC questionnaire results, while other item types correlated poorly
• In joint analysis, Practice codes correlate most strongly with AI pedagogical orientation, while Epistemic codes show a weaker positive association - In joint analysis, Practice codes correlate most strongly with AI pedagogical orientation, while Epistemic codes show a weaker positive association
• In Kentucky, educators used micro-credentials to advance from Rank II to Rank I, increasing their yearly salaries - In Kentucky, educators used micro-credentials to advance from Rank II to Rank I, increasing their yearly salaries
• In kindergarteners, trait beliefs and goal orientations form two separate but related factors rather than a coherent growth/fixed mindset - In kindergarteners, trait beliefs and goal orientations form two separate but related factors rather than a coherent growth/fixed mindset
• In Knowledge Forum discourse, three components (connecting knowledge, transactivity, authority) dominated notes, and cognitive openness components predicted follow-up while social openness components predicted slightly reduced follow-up - In Knowledge Forum discourse, three components (connecting knowledge, transactivity, authority) dominated notes, and cognitive openness components predicted follow-up while social openness components
• In knowledge-construction content analysis data from discussion groups, the largest share of variance lies at the message level, with only small between-group and between-student variance. - In knowledge-construction content analysis data from discussion groups, the largest share of variance lies at the message level, with only small between-group and between-student variance.
• In latent-variable SEM models, intelligence — not working memory — is the significant direct predictor of academic outcomes in both childhood and early adulthood - In latent-variable SEM models, intelligence — not working memory — is the significant direct predictor of academic outcomes in both childhood and early adulthood
• In Layers, Context-Centered-mindset participants drew on students' communities and home lives while Context-Neutral-mindset participants adapted content without students' out-of-school experiences - In Layers, Context-Centered-mindset participants drew on students' communities and home lives while Context-Neutral-mindset participants adapted content without students' out-of-school experiences
• In literature teaching, a method using a sympathetic approach with opportunity for picturing and imaging the experiences in the selection was found superior to one stressing technique, analysis and factual detail - In literature teaching, a method using a sympathetic approach with opportunity for picturing and imaging the experiences in the selection was found superior to one stressing technique, analysis and fa
• In LLM-assisted team formation with name-only personas, male students are significantly less likely than female students to be assigned to Interface Design and Quality Assurance teams relative to Core Development - In LLM-assisted team formation with name-only personas, male students are significantly less likely than female students to be assigned to Interface Design and Quality Assurance teams relative to Core
• In LLM-assisted team formation, class standing strongly drives assignments: seniors are far less likely than freshmen to be assigned to Interface Design relative to Core Development - In LLM-assisted team formation, class standing strongly drives assignments: seniors are far less likely than freshmen to be assigned to Interface Design relative to Core Development
• In LLM-assisted team formation, persona nationality systematically shifts assignments, with Nigerian names favored for Quality Assurance and South Korean names for Interface Design relative to Chinese names - In LLM-assisted team formation, persona nationality systematically shifts assignments, with Nigerian names favored for Quality Assurance and South Korean names for Interface Design relative to Chinese
• In LLM-simulated subjects with known skill levels, the Executive LLM yields better skill-level recovery (lower MAE) than Independent Agents - In LLM-simulated subjects with known skill levels, the Executive LLM yields better skill-level recovery (lower MAE) than Independent Agents
• In Lomicka's think-aloud study, no statistical differences emerged among no-gloss, single-gloss, and multiple-gloss groups despite apparent vocabulary gains from multiple annotations - In Lomicka's think-aloud study, no statistical differences emerged among no-gloss, single-gloss, and multiple-gloss groups despite apparent vocabulary gains from multiple annotations
• In long-term assessments, personnel reporting high combat exposure have higher odds of screening positive for PTSD and depression than personnel reporting lower exposure - In long-term assessments, personnel reporting high combat exposure have higher odds of screening positive for PTSD and depression than personnel reporting lower exposure
• In Lonigan et al. (2003), DaisyQuest effects were statistically significant on four of eight phonological processing outcomes and not significant on the others - In Lonigan et al.
• In low challenge dyads the metacognitive activities are closely interconnected, whereas in high challenge dyads monitoring is disconnected from other metacognitive activities - In low challenge dyads the metacognitive activities are closely interconnected, whereas in high challenge dyads monitoring is disconnected from other metacognitive activities
• In Lynwood Unified, chronic absence fell from 37.1% to 24.5% and average daily attendance rose from 87.4% to 91.5% during the first two years of districtwide community schools implementation. - In Lynwood Unified, chronic absence fell from 37.1% to 24.5% and average daily attendance rose from 87.4% to 91.5% during the first two years of districtwide community schools implementation.
• In many large districts, secondary students lost more than a year of instruction per 100 enrolled, up to 416 days in Grand Rapids, MI - In many large districts, secondary students lost more than a year of instruction per 100 enrolled, up to 416 days in Grand Rapids, MI
• In many NCLB waiver states, performance against improvement and gap-closing goals does not factor into school accountability ratings - In many NCLB waiver states, performance against improvement and gap-closing goals does not factor into school accountability ratings
• In Maryland, disciplinary removals (out-of-school suspensions and expulsions) declined over the past 10 years while discipline disparities persisted - In Maryland, disciplinary removals (out-of-school suspensions and expulsions) declined over the past 10 years while discipline disparities persisted
• In Massachusetts K-3 screening data, roughly one quarter to one third of students are significantly below benchmark at any given period and 16 to 19 percent are below benchmark in all three periods, rates consistent over three years - In Massachusetts K-3 screening data, roughly one quarter to one third of students are significantly below benchmark at any given period and 16 to 19 percent are below benchmark in all three periods, r
• In matched single-run 1B pre-training comparisons, all Edu-QuRating-based mixtures reach higher observed aggregate accuracy at 30k steps than the FineWeb-Edu baseline, with gains concentrated in specific tasks - In matched single-run 1B pre-training comparisons, all Edu-QuRating-based mixtures reach higher observed aggregate accuracy at 30k steps than the FineWeb-Edu baseline, with gains concentrated in speci
• In math problem solving, a tutor LLM alone significantly improved unassisted test accuracy over no-agent control, while peer-like error agents alone did not reach significance - In math problem solving, a tutor LLM alone significantly improved unassisted test accuracy over no-agent control, while peer-like error agents alone did not reach significance
• In math problem solving, a tutor-plus-peers LLM arrangement produced the strongest unassisted post-task test accuracy, with accuracy increasing monotonically from Control to Tutor + Peers - In math problem solving, a tutor-plus-peers LLM arrangement produced the strongest unassisted post-task test accuracy, with accuracy increasing monotonically from Control to Tutor + Peers
• In math, EL groups grew more than never-ELs during academic years but lost more during summers - In math, EL groups grew more than never-ELs during academic years but lost more during summers
• In math, ELs grew more than never-ELs during academic years but lost more during summers - In math, ELs grew more than never-ELs during academic years but lost more during summers
• In math, meeting the PARCC college-readiness standard predicts higher college performance than meeting the MCAS proficiency standard - In math, meeting the PARCC college-readiness standard predicts higher college performance than meeting the MCAS proficiency standard
• In math, students meeting the PARCC college-ready standard are less likely to need remediation than students meeting the MCAS proficient standard - In math, students meeting the PARCC college-ready standard are less likely to need remediation than students meeting the MCAS proficient standard
• In math, students meeting the PARCC college-ready standard are less likely to need remediation than students meeting the MCAS proficient standard; in ELA the standards are not statistically distinguishable - In math, students meeting the PARCC college-ready standard are less likely to need remediation than students meeting the MCAS proficient standard; in ELA the standards are not statistically distinguis
• In math, the PARCC college-ready standard predicts higher college performance than the MCAS proficient standard, while in ELA the standards are similar - In math, the PARCC college-ready standard predicts higher college performance than the MCAS proficient standard, while in ELA the standards are similar
• In mathematics, personalized-learning students in the lowest baseline quintile were the most likely to out-grow their matched comparison students - In mathematics, personalized-learning students in the lowest baseline quintile were the most likely to out-grow their matched comparison students
• In mathematics, students meeting the PARCC college-ready standard are less likely to need remediation than students meeting the MCAS proficient standard; in English language arts the standards are not statistically distinguishable - In mathematics, students meeting the PARCC college-ready standard are less likely to need remediation than students meeting the MCAS proficient standard; in English language arts the standards are not
• In Mead's lectures, meanings grow out of social intercourse and the child constructs meanings only in social process - In Mead's lectures, meanings grow out of social intercourse and the child constructs meanings only in social process
• In medical and dental education, a deep learning approach is associated with high(er) or no-difference academic performance and never with low(er) performance - In medical and dental education, a deep learning approach is associated with high(er) or no-difference academic performance and never with low(er) performance
• In medical simulation training, socially shared regulation relates to subsequent emotional stabilization, with electrodermal activity modeled as a dependent variable - In medical simulation training, socially shared regulation relates to subsequent emotional stabilization, with electrodermal activity modeled as a dependent variable
• In Miami-Dade County, Cognitive Tutor Algebra I students significantly outscored peers on the 2003 FCAT, with especially large pass-rate differences for Exceptional Student Education and limited-English-proficiency students - In Miami-Dade County, Cognitive Tutor Algebra I students significantly outscored peers on the 2003 FCAT, with especially large pass-rate differences for Exceptional Student Education and limited-Engli
• In middle school, academic-year growth in math was comparable across Catholic and public school sectors - In middle school, academic-year growth in math was comparable across Catholic and public school sectors
• In Mnemosyne flashcard log data, adding a delay term improves the recall-prediction performance of exponential forgetting curve memory models. - In Mnemosyne flashcard log data, adding a delay term improves the recall-prediction performance of exponential forgetting curve memory models.
• In Mnemosyne log data, exponential forgetting curve models that include a delay term perform comparably to 1PL-IRT, the best-performing benchmark model. - In Mnemosyne log data, exponential forgetting curve models that include a delay term perform comparably to 1PL-IRT, the best-performing benchmark model.
• In Mnemosyne log data, item-specific difficulty parameters outperform a global difficulty for lower and higher Leitner decks, while global difficulty performs better for intermediate decks. - In Mnemosyne log data, item-specific difficulty parameters outperform a global difficulty for lower and higher Leitner decks, while global difficulty performs better for intermediate decks.
• In Mnemosyne log data, setting memory strength equal to an item's Leitner deck position predicts recall better than number of past reviews, which beats constant strength. - In Mnemosyne log data, setting memory strength equal to an item's Leitner deck position predicts recall better than number of past reviews, which beats constant strength.
• In more competitive school environments, lower-SES students perform better academically than their more advantaged peers, narrowing SES achievement gaps - In more competitive school environments, lower-SES students perform better academically than their more advantaged peers, narrowing SES achievement gaps
• In more competitive school environments, students from lower SES backgrounds report more positive self-views than their more advantaged peers, narrowing SES gaps in self-views - In more competitive school environments, students from lower SES backgrounds report more positive self-views than their more advantaged peers, narrowing SES gaps in self-views
• In Morris et al. (2012), the phonological (phonics-including) intervention alone showed no significant reading benefits, while conditions adding orthographic and semantic instruction did - In Morris et al.
• In most blended learning designs the instructor, not the learner, controls the realization of the blend - In most blended learning designs the instructor, not the learner, controls the realization of the blend
• In most included studies, AI tool use is preceded by a preparatory phase, but its configuration varies between technology-first and content-first approaches - In most included studies, AI tool use is preceded by a preparatory phase, but its configuration varies between technology-first and content-first approaches
• In most of the reported collaborative experiments, the accuracy of the partner model A built about B was correlated with the accuracy of the model B built about A - In most of the reported collaborative experiments, the accuracy of the partner model A built about B was correlated with the accuracy of the model B built about A
• In multimodal collaboration, the whiteboard primarily represents the state of problem solving while chat grounds whiteboard content, contrary to the expectation that schemata on the whiteboard would disambiguate chat utterances - In multimodal collaboration, the whiteboard primarily represents the state of problem solving while chat grounds whiteboard content, contrary to the expectation that schemata on the whiteboard would d
• In multiple regression, the percentage of exploratory experiments was the strongest predictor of performance success, negatively related to it - In multiple regression, the percentage of exploratory experiments was the strongest predictor of performance success, negatively related to it
• In NAEP regression discontinuity estimates, exceeding the state threshold increases math achievement by 2.6 points (9.1% of a standard deviation) and reading achievement by 4.4 points (12.2% of a standard deviation) - In NAEP regression discontinuity estimates, exceeding the state threshold increases math achievement by 2.6 points (9.1% of a standard deviation) and reading achievement by 4.4 points (12.2% of a stan
• In natural learning, elemental and higher-order habits develop together, so the most economic method is to practice with the highest-order habits possible - In natural learning, elemental and higher-order habits develop together, so the most economic method is to practice with the highest-order habits possible
• In non-randomised controlled trials, teacher programs show moderate effects on stress (g=0.50) and small effects on anxiety and wellbeing (g=0.38 each) at post-intervention, with non-significant effects at short-term follow-up - In non-randomised controlled trials, teacher programs show moderate effects on stress (g=0.50) and small effects on anxiety and wellbeing (g=0.38 each) at post-intervention, with non-significant effec
• In nonrandom studies where both trait and state variables influence instruction, neither approach reports an unbiased instruction effect - In nonrandom studies where both trait and state variables influence instruction, neither approach reports an unbiased instruction effect
• In nonrandom studies where state-specific variables influence instruction, neither the ANCOVA nor the CHANGE approach reports the correct instruction effect - In nonrandom studies where state-specific variables influence instruction, neither the ANCOVA nor the CHANGE approach reports the correct instruction effect
• In nonrandom studies where trait variables influence instruction, the CHANGE approach is unbiased when change is unrelated to stable skill differences, the ANCOVA overestimates, and neither is unbiased when change depends on the trait - In nonrandom studies where trait variables influence instruction, the CHANGE approach is unbiased when change is unrelated to stable skill differences, the ANCOVA overestimates, and neither is unbiase
• In object counting, deaf and hearing children make similar attention and principle errors, but deaf children make more number-string errors - In object counting, deaf and hearing children make similar attention and principle errors, but deaf children make more number-string errors
• In observed Australian secondary classrooms, only a minority of lesson tasks stimulated Constructive or Interactive engagement - In observed Australian secondary classrooms, only a minority of lesson tasks stimulated Constructive or Interactive engagement
• In observed groups, Reactions to Children's Emotions was the most common scaffolding subscale, and ECERS-R Interactions rated high while Activities rated low - In observed groups, Reactions to Children's Emotions was the most common scaffolding subscale, and ECERS-R Interactions rated high while Activities rated low
• In Oceanside, teachers' successes in supporting student academic discourse diminished when teachers followed newly adopted instructional materials too closely - In Oceanside, teachers' successes in supporting student academic discourse diminished when teachers followed newly adopted instructional materials too closely
• In offline evaluation on NSMQ Riddles, closed LLMs generally outperform open models and higher reasoning settings improve performance - In offline evaluation on NSMQ Riddles, closed LLMs generally outperform open models and higher reasoning settings improve performance
• In offline validation, combined relevance-based secondary-AOI selection matched children's next attended AOI more often than random or single-distance selection - In offline validation, combined relevance-based secondary-AOI selection matched children's next attended AOI more often than random or single-distance selection
• In offline validation, the HMM timing model detected children's attention moments more accurately than fixed-interval and dwell-time triggers - In offline validation, the HMM timing model detected children's attention moments more accurately than fixed-interval and dwell-time triggers
• In Ohio, charter schools authorized by nonprofits are less effective in promoting student achievement than other charter schools - In Ohio, charter schools authorized by nonprofits are less effective in promoting student achievement than other charter schools
• In Oklahoma A and B schools, FRL students scored lower in reading than Non-FRL students, with the gap widening in 2014 - In Oklahoma A and B schools, FRL students scored lower in reading than Non-FRL students, with the gap widening in 2014
• In one 12-week trial, balance and relaxation training did not detectably differ in their effects on cardiorespiratory fitness, Stroop interference, or psychopathological symptoms - In one 12-week trial, balance and relaxation training did not detectably differ in their effects on cardiorespiratory fitness, Stroop interference, or psychopathological symptoms
• In one 2×2 experiment with 120 undergraduates, an Assessment-Performance Calibration Activity (APCA) gave the most accurate self-assessment and least overconfidence, and adding a feedback-literacy script did not improve calibration further - In one 2×2 experiment with 120 undergraduates, an Assessment-Performance Calibration Activity (APCA) gave the most accurate self-assessment and least overconfidence, and adding a feedback-literacy scr
• In one 30-student study of high-school English learners (Lu 2008, reported in a review), vocabulary learned by mobile phone showed greater gains than vocabulary learned from print - In one 30-student study of high-school English learners (Lu 2008, reported in a review), vocabulary learned by mobile phone showed greater gains than vocabulary learned from print
• In one 37-student classroom experiment, recall and retention differ across media combinations in the direction Dual Coding Theory predicts
• In one 51-learner experiment on help formats in computer-based electrical engineering instruction, far-transfer scores were at the floor in every condition, and time spent on instruction did not differ significantly between conditions - In one 51-learner experiment on help formats in computer-based electrical engineering instruction, far-transfer scores were at the floor in every condition, and time spent on instruction did not diffe
• In one accounting classroom experiment, self-generated elaboration scored marginally above instructor-assisted elaboration on intellectual skills (p = .06, omnibus test not significant) and no higher than a combined strategy - In one accounting classroom experiment, self-generated elaboration scored marginally above instructor-assisted elaboration on intellectual skills (p = .06, omnibus test not significant) and no higher
• In one author's classroom media experiments, intuitive learners tended to score above sensing learners, though not in every format comparison
• In one case-study school, a principal's lack of Framework knowledge and inability to rate practice led teachers to perceive the new evaluation as subjective, undermining buy-in - In one case-study school, a principal's lack of Framework knowledge and inability to rate practice led teachers to perceive the new evaluation as subjective, undermining buy-in
• In one Chicago study, above-norm students' post-policy algebra test gains were partly explained by higher peer ability and by having classmates who took support algebra - In one Chicago study, above-norm students' post-policy algebra test gains were partly explained by higher peer ability and by having classmates who took support algebra
• In one class of 13-year-old boys, memory scores were kept to a steady rank order by repeated practice (successive tests correlating +.87 to +.90) before fatigue testing began - In one class of 13-year-old boys, memory scores were kept to a steady rank order by repeated practice (successive tests correlating +.87 to +.90) before fatigue testing began
• In one class of 14 non-science majors, preliminary explicit instruction in scientific reasoning patterns (e.g., IAT statement construction) was followed by a larger average normalized LCTSR gain (68%) than in earlier courses without it (11%, n=42) - In one class of 14 non-science majors, preliminary explicit instruction in scientific reasoning patterns (e.g., IAT statement construction) was followed by a larger average normalized LCTSR gain (68%)
• In one community-college lab class, six scorers rating six teams with an engineering rubric differed by a mean of 1.2 of 9 points, which the authors read as a sign the rubric may not be reliable - In one community-college lab class, six scorers rating six teams with an engineering rubric differed by a mean of 1.2 of 9 points, which the authors read as a sign the rubric may not be reliable
• In one design report on 25 cybersecurity tabletop exercises, the authors observed that trainees consistently wanted more debriefing time than the schedule allowed - In one design report on 25 cybersecurity tabletop exercises, the authors observed that trainees consistently wanted more debriefing time than the schedule allowed
• In one essay-feedback system, fine-tuned models produced no usable deep-level feedback output, so only directly prompted LLMs were evaluated; the authors suggest prompting may be more effective than supervised fine-tuning for this task - In one essay-feedback system, fine-tuned models produced no usable deep-level feedback output, so only directly prompted LLMs were evaluated; the authors suggest prompting may be more effective than s
• In one experiment with 256 undergraduates, computer-based lesson versions that included practice produced significantly higher posttest scores than versions without practice - In one experiment with 256 undergraduates, computer-based lesson versions that included practice produced significantly higher posttest scores than versions without practice
• In one experiment with undergraduate business majors in asynchronous online small groups, reward interdependence raised agreement that group work was beneficial and generated better ideas - In one experiment with undergraduate business majors in asynchronous online small groups, reward interdependence raised agreement that group work was beneficial and generated better ideas
• In one experiment, refutational text (misbelief stated first, then fact) enhanced free recall relative to traditional text and free and cued recall relative to inverted refutational text, but its reported 14-day recognition advantage was over inverted refutational text only - In one experiment, refutational text (misbelief stated first, then fact) enhanced free recall relative to traditional text and free and cued recall relative to inverted refutational text, but its repo
• In one experiment, students who generated their own underlining did not score significantly higher on tests than students given experimenter-generated underlining
• In one extreme case, two sixth-graders with a choice-rich, ungraded STEAM infrastructure extended a game-design challenge into a year-long self-directed project well beyond its designed scope
• In one eye-tracking experiment, revising math-relevant visuals changes fixation length on them differently by prior knowledge group, with shorter fixations under the revised visuals for low prior knowledge students - In one eye-tracking experiment, revising math-relevant visuals changes fixation length on them differently by prior knowledge group, with shorter fixations under the revised visuals for low prior know
• In one first-year composition class, stylistic analysis of a president's letter served critical pedagogy goals - In one first-year composition class, stylistic analysis of a president's letter served critical pedagogy goals
• In one flipped calculus study, prior achievement level had no significant main effect on self-efficacy, although it interacted with teaching method - In one flipped calculus study, prior achievement level had no significant main effect on self-efficacy, although it interacted with teaching method
• In one flipped calculus study, teaching method (peer-teaching versus conventional flipped classroom) and prior achievement level interact on self-efficacy - In one flipped calculus study, teaching method (peer-teaching versus conventional flipped classroom) and prior achievement level interact on self-efficacy
• In one informal tournament survey, coaches and students listed partly different strengths and weaknesses of parliamentary debate - In one informal tournament survey, coaches and students listed partly different strengths and weaknesses of parliamentary debate
• In one introductory accounting experiment, self-generated elaboration scored above instructor-assisted elaboration on procedural knowledge at the p = .05 boundary, and not significantly above a combined strategy - In one introductory accounting experiment, self-generated elaboration scored above instructor-assisted elaboration on procedural knowledge at the p = .05 boundary, and not significantly above a combin
• In one keystroke-logging study, spontaneous sentence production under minimal planning is associated with gains in writers' self-rated understanding and with lower initial text quality
• In one meta-analysis, modality-effect studies using virtual reality head-mounted displays show larger effects than studies using computer screens or audio-tapes - In one meta-analysis, modality-effect studies using virtual reality head-mounted displays show larger effects than studies using computer screens or audio-tapes
• In one meta-regression, the PS-I fidelity benefit tended to shrink for interventions spanning only a few hours, a marginal interaction (p = .055) - In one meta-regression, the PS-I fidelity benefit tended to shrink for interventions spanning only a few hours, a marginal interaction (p = .055)
• In one middle-school quasi-experiment on electricity, spoken-text groups outperform written-text groups with both abstract and concrete animation (d = .35) - The modality effect holds for middle school students learning electricity with multimedia animation in real school settings: spoken-text groups significantly outperform written-text groups with both a
• In one middle-school quasi-experiment, adding written text to spoken narration makes no significant difference to achievement with either abstract or concrete animation - In one middle-school quasi-experiment, adding written text to spoken narration makes no significant difference to achievement with either abstract or concrete animation
• In one mixed-methods study of university students, reported in a review, gamified vocabulary learning gave better test results, motivation and satisfaction than traditional instruction - In one mixed-methods study of university students, reported in a review, gamified vocabulary learning gave better test results, motivation and satisfaction than traditional instruction
• In one MMLA nursing simulation study, 11 of 14 interviewed students preferred opt-out over opt-in consent, but most did not fully read the explanatory statement - In one MMLA nursing simulation study, 11 of 14 interviewed students preferred opt-out over opt-in consent, but most did not fully read the explanatory statement
• In one nonequivalent-groups study of pre-school prospective teachers, the group taught with formative assessment embedded in explicit-reflective instruction scored higher on post-test NOS and SK than the group taught with explicit-reflective instruction alone - In one nonequivalent-groups study of pre-school prospective teachers, the group taught with formative assessment embedded in explicit-reflective instruction scored higher on post-test NOS and SK than
• In one NVCC summer bridge cohort, 100 percent of students continued to the next semester, described as much higher than normal retention rates - In one NVCC summer bridge cohort, 100 percent of students continued to the next semester, described as much higher than normal retention rates
• In one participatory budgeting case, Latino immigrant participation lapsed under outreach with interpretation and was sustained only after the activity structure was redesigned
• In one practitioner's report on her own older-beginner Step One class, with no comparison group, students gained an average of 128 BEST Plus points over 6 months and two former absolute beginners passed the citizenship test - In one practitioner's report on her own older-beginner Step One class, with no comparison group, students gained an average of 128 BEST Plus points over 6 months and two former absolute beginners pass
• In one preregistered experiment, metacognitive feedback on learners' own LLM use lowered the odds of answer offloading and raised the odds of a correct unaided answer on one-sided tests, with 95% intervals reaching no effect - In one preregistered experiment, metacognitive feedback on learners' own LLM use lowered the odds of answer offloading and raised the odds of a correct unaided answer on one-sided tests, with 95% inte
• In one qualitative interview study, science teachers report that AI tools let students experience risky or inaccessible phenomena and practise virtually before real lab work - In one qualitative interview study, science teachers report that AI tools let students experience risky or inaccessible phenomena and practise virtually before real lab work
• In one quasi-experiment in EFL writing classes, students given AI-peer integrated feedback reported higher posttest cognitive engagement than students given conventional peer feedback - In one quasi-experiment in EFL writing classes, students given AI-peer integrated feedback reported higher posttest cognitive engagement than students given conventional peer feedback
• In one quasi-experimental study of Chicago teachers, a classroom one SD higher on a quality index raised the same teacher's observation scores by 0.07 SD and student survey ratings by 0.13 SD - In one quasi-experimental study of Chicago teachers, a classroom one SD higher on a quality index raised the same teacher's observation scores by 0.07 SD and student survey ratings by 0.13 SD
• In one quasi-experimental VR shooting study (n = 50), reported in a review, rule-based dynamic difficulty outperformed progressive difficulty - In one quasi-experimental VR shooting study (n = 50), reported in a review, rule-based dynamic difficulty outperformed progressive difficulty
• In one randomized working-paper experiment, conceptual-map scaffolding gave LLM-using novices marginally higher scores (p < .10) and lower score variance, with a marginal benefit concentrated among low-AIC novices - In one randomized working-paper experiment, conceptual-map scaffolding gave LLM-using novices marginally higher scores (p < .10) and lower score variance, with a marginal benefit concentrated among lo
• In one RCT, a content-rich prompt-engineered generative AI chat tutor improved performance and engagement in a Harvard physics course - In one RCT, a content-rich prompt-engineered generative AI chat tutor improved performance and engagement in a Harvard physics course
• In one reviewed study, Anatomage virtual dissection increased medical student engagement by 34% over cadaver-based practice, constrained by equipment costs exceeding $72,000 per station - In one reviewed study, Anatomage virtual dissection increased medical student engagement by 34% over cadaver-based practice, constrained by equipment costs exceeding $72,000 per station
• In one reviewed study, flipped classrooms using AI tools raised cognitive and emotional engagement but behavioral engagement showed no significant difference from traditional methods - In one reviewed study, flipped classrooms using AI tools raised cognitive and emotional engagement but behavioral engagement showed no significant difference from traditional methods
• In one reviewed study, GPT-4 automated essay scoring showed score inflation, with AI–human rating discrepancies exceeding 1.5 standard deviations in 38% of graduate-level bibliographies - In one reviewed study, GPT-4 automated essay scoring showed score inflation, with AI–human rating discrepancies exceeding 1.5 standard deviations in 38% of graduate-level bibliographies
• In one reviewed study, students who first collaborate and then complete an activity individually in the VRL are more successful than students who complete an individual task first and then collaborate - In one reviewed study, students who first collaborate and then complete an activity individually in the VRL are more successful than students who complete an individual task first and then collaborate
• In one school, well-defined instructional priorities plus deliberate leadership facilitated sustained developmental practices - In one school, well-defined instructional priorities plus deliberate leadership facilitated sustained developmental practices
• In one study of 37 thermodynamics freshmen, a CLT-based instructional design yields higher retention and transfer scores than lecturer-designed instruction, controlling for prior knowledge and memory span - In one study of 37 thermodynamics freshmen, a CLT-based instructional design yields higher retention and transfer scores than lecturer-designed instruction, controlling for prior knowledge and memory
• In one study of five LLMs scoring 60 undergraduate essays on IELTS rubric dimensions, systematic underestimation of human scores was the dominant bias trend, with some models also compressing scores into a narrow range - In one study of five LLMs scoring 60 undergraduate essays on IELTS rubric dimensions, systematic underestimation of human scores was the dominant bias trend, with some models also compressing scores i
• In one study of repeated LLM scoring of 60 IELTS essays, Gemini 2.5 Flash was moderately reliable (ICC 0.63-0.75) while Claude Sonnet 4 and DeepSeek R1 stayed below 0.70 in most dimensions - In one study of repeated LLM scoring of 60 IELTS essays, Gemini 2.5 Flash was moderately reliable (ICC 0.63-0.75) while Claude Sonnet 4 and DeepSeek R1 stayed below 0.70 in most dimensions
• In one study of undergraduate business majors in asynchronous online small groups, learners with high affiliation motive agreed more than low-affiliation learners with six of twelve attitude statements about group work - In one study of undergraduate business majors in asynchronous online small groups, learners with high affiliation motive agreed more than low-affiliation learners with six of twelve attitude statement
• In one study summarised in a policy brief, students and teachers who learned their commonalities through getting-to-know-you surveys reported more positive relationships, students earned higher grades, and achievement gaps for Black and Latinx students closed by more than 60% - In one study summarised in a policy brief, students and teachers who learned their commonalities through getting-to-know-you surveys reported more positive relationships, students earned higher grades
• In one study, feedback quality significantly predicts revised essay quality under teacher feedback but not under either GenAI feedback condition, though the conditions are not compared directly - In one study, feedback quality significantly predicts revised essay quality under teacher feedback but not under either GenAI feedback condition, though the conditions are not compared directly
• In one survey, coached teachers more often report sustained, followed-up professional development than non-coached peers, and more than 81% received at least 30 minutes of one-on-one coaching a week - In a survey of Dynamic Learning Project teachers, 47% of coached versus 30% of non-coached core-subject teachers reported sustained PD with follow-up; more than 81% of coached teachers got at least 30
• In one synthesis of group-based mastery learning, five observational studies found more time-on-task in mastery classes and one community-college evaluation found lower attrition in seven of eight disciplines - In one synthesis of group-based mastery learning, five observational studies found more time-on-task in mastery classes and one community-college evaluation found lower attrition in seven of eight dis
• In one thermodynamics study, retention and transfer scores tended to be lower on topics of higher element interactivity, a descriptive pattern with several sessions that did not fit it - In one thermodynamics study, retention and transfer scores tended to be lower on topics of higher element interactivity, a descriptive pattern with several sessions that did not fit it
• In one trial, task-centered Entrepreneur course students analyzed a new business as well as completed business majors - In one trial, task-centered Entrepreneur course students analyzed a new business as well as completed business majors
• In one university's records, minority students visit a drop-in tutoring center more often than Caucasian students, while first-generation and other students do not differ in visits - In one university's records, minority students visit a drop-in tutoring center more often than Caucasian students, while first-generation and other students do not differ in visits
• In one very poor neighborhood school the exception occurred: the earlier-working group improved more rapidly than the later-working group - In one very poor neighborhood school the exception occurred: the earlier-working group improved more rapidly than the later-working group
• In one video study of Betty's Brain, 77% of the feedback delivered by the agents was ignored by students. - In one video study of Betty's Brain, 77% of the feedback delivered by the agents was ignored by students.
• In one word-problem study, females gained significantly when the formatted procedural plan came after an unformatted test, and scored lower when the formatted test came first - In one word-problem study, females gained significantly when the formatted procedural plan came after an unformatted test, and scored lower when the formatted test came first
• In open-ended constructivist activities, task success or failure is not a reliable indicator of learning, so learner models based only on performance risk misjudging learners - In open-ended constructivist activities, task success or failure is not a reliable indicator of learning, so learner models based only on performance risk misjudging learners
• In open-ended responses to a national survey, about three-quarters of the feelings US high school students reported about school were negative, with tired, stressed, and bored the most frequent - In open-ended responses to a national survey, about three-quarters of the feelings US high school students reported about school were negative, with tired, stressed, and bored the most frequent
• In open-ended writing, both single-generalist and role-specialized duo LLM assistance improved essay quality over no-AI control, with no significant difference between them - In open-ended writing, both single-generalist and role-specialized duo LLM assistance improved essay quality over no-AI control, with no significant difference between them
• In operational reading-test data, ignoring local dependence inflates reliability estimates, with passage-based alpha 2.3%-4.9% lower than item-based alpha across six test forms - In operational reading-test data, ignoring local dependence inflates reliability estimates, with passage-based alpha 2.3%-4.9% lower than item-based alpha across six test forms
• In operational reading-test data, item parameter estimates from a standard 2PL/GPCM that ignores local dependence closely match those from the testlet model (average correlations 0.9893 and 0.9978) - In operational reading-test data, item parameter estimates from a standard 2PL/GPCM that ignores local dependence closely match those from the testlet model (average correlations 0.9893 and 0.9978)
• In OUSD dual enrollment courses, students most often identify the point person as their main source of support, at higher rates than the instructor, peers, or family - In OUSD dual enrollment courses, students most often identify the point person as their main source of support, at higher rates than the instructor, peers, or family
• In over 60% of inquiry threads of low-achieving students, curiosity was followed by confusion, and joy or confusion by curiosity (sequential patterns, not shown causes) - In over 60% of inquiry threads of low-achieving students, curiosity was followed by confusion, and joy or confusion by curiosity (sequential patterns, not shown causes)
• In paired-associate paradigms, the lag function is decreasing at very short retention intervals, inverted U-shaped at slightly longer intervals, and monotonically increasing at long intervals - In paired-associate paradigms, the lag function is decreasing at very short retention intervals, inverted U-shaped at slightly longer intervals, and monotonically increasing at long intervals
• In pairwise A/B preference tests, raters preferred XTTS and Orpheus over CSM, and preferred female voices across all models - In pairwise A/B preference tests, raters preferred XTTS and Orpheus over CSM, and preferred female voices across all models
• In pairwise LLM-judge comparisons PsyScore-AEF wins over 90% in Actionability against GPT-4o and Llama, and removing the psychometric module reduces Adaptivity and Tone wins with PsyScore retaining above 75% - In pairwise LLM-judge comparisons PsyScore-AEF wins over 90% in Actionability against GPT-4o and Llama, and removing the psychometric module reduces Adaptivity and Tone wins with PsyScore retaining ab
• In pairwise WD analyses, learner trajectory similarity dominates variation in percentage-overlap values (57.90% of variation) while remaining design factors are essentially zero - In pairwise WD analyses, learner trajectory similarity dominates variation in percentage-overlap values (57.90% of variation) while remaining design factors are essentially zero
• In peg-solitaire simulations with known true abilities, the RLMM attains lower RMSE of log βj than the MDP-MM on all four original boards - In peg-solitaire simulations with known true abilities, the RLMM attains lower RMSE of log βj than the MDP-MM on all four original boards
• In Pennsylvania districts using hybrid instruction with precautions in fall 2020, increases in student and staff infections were no greater than community increases outside school - In Pennsylvania districts using hybrid instruction with precautions in fall 2020, increases in student and staff infections were no greater than community increases outside school
• In physics-based courses for non-science majors taught with active-engagement pedagogy, normalized gains were 0.38–0.42 on content tests but 0.06 on a scientific-reasoning test - In physics-based courses for non-science majors taught with active-engagement pedagogy, normalized gains were 0.38–0.42 on content tests but 0.06 on a scientific-reasoning test
• In Pilot District 3, majorities of students agreed that Compact Writing Assignments gave them topic choice and that autonomy and varied expression formats improved engagement and writing quality - In Pilot District 3, majorities of students agreed that Compact Writing Assignments gave them topic choice and that autonomy and varied expression formats improved engagement and writing quality
• In Pilot District 4, student-led Small Writing Groups showed growing attendance and increased writing confidence among participating students, per Core Team reflections - In Pilot District 4, student-led Small Writing Groups showed growing attendance and increased writing confidence among participating students, per Core Team reflections
• In points-based GoCPS programs, students were admitted strictly in order of application score within priority groups - In points-based GoCPS programs, students were admitted strictly in order of application score within priority groups
• In post-wargaming debriefings, teachers and students delineate tactics from related areas of military competence such as teamwork, communication, and technology - In post-wargaming debriefings, teachers and students delineate tactics from related areas of military competence such as teamwork, communication, and technology
• In predicting the change in achievement from 3rd to 4th grade, IQ is positively and study habits negatively associated with change, together predicting 12% - In predicting the change in achievement from 3rd to 4th grade, IQ is positively and study habits negatively associated with change, together predicting 12%
• In preliminary user acceptance testing, 84% of participants rated Taklif.AI's personalization feature as beneficial - In preliminary user acceptance testing, 84% of participants rated Taklif.AI's personalization feature as beneficial
• In pretend play the child behaves beyond her average age and daily behaviour - In pretend play the child behaves beyond her average age and daily behaviour
• In primary grades, lower order writing and lower order mathematics skills show the strongest relation (r = 0.59); in adulthood the higher order pair is weak (r = 0.26) - In primary grades, lower order writing and lower order mathematics skills show the strongest relation (r = 0.59); in adulthood the higher order pair is weak (r = 0.26)
• In primary school children learning javelin throwing, PS-I did not outperform I-PS on throwing distance or movement-feature execution - In primary school children learning javelin throwing, PS-I did not outperform I-PS on throwing distance or movement-feature execution
• In PS-I, prompting students to generate multiple strategies during the initial phase generally outperformed inventing one strategy or I-PS - In PS-I, prompting students to generate multiple strategies during the initial phase generally outperformed inventing one strategy or I-PS
• In pure developmental dyscalculia with normal reading and verbal IQ, verbal short-term and working memory are intact - In pure developmental dyscalculia with normal reading and verbal IQ, verbal short-term and working memory are intact
• In Quantitative AI sessions, faster AI replies were associated with more engagement, more correct practice, and larger learning gains; these associations were not significant in Verbal - In Quantitative AI sessions, faster AI replies were associated with more engagement, more correct practice, and larger learning gains; these associations were not significant in Verbal
• In Quebec's Remote Networked School initiative, teacher collaborative design proved to be relevant, feasible, and sustainable despite systemic limits - In Quebec's Remote Networked School initiative, teacher collaborative design proved to be relevant, feasible, and sustainable despite systemic limits
• In Quiet Eye Training literature, the EMME video is typically one component of a larger training package rather than the main manipulation - In Quiet Eye Training literature, the EMME video is typically one component of a larger training package rather than the main manipulation
• In Railside's detracked, Complex Instruction classrooms, students from diverse racial and ethnic backgrounds pursued higher-level math courses and greater interest over five years - In Railside's detracked, Complex Instruction classrooms, students from diverse racial and ethnic backgrounds pursued higher-level math courses and greater interest over five years
• In RAMPUP field trials, English Learners' mathematical language became more monologic, authoritative, and technical within a single 40-minute jigsaw activity - In RAMPUP field trials, English Learners' mathematical language became more monologic, authoritative, and technical within a single 40-minute jigsaw activity
• In random experiments, both the ANCOVA and the CHANGE approach estimate the instruction effect without bias - In random experiments, both the ANCOVA and the CHANGE approach estimate the instruction effect without bias
• In RCTs of interventions to improve student test scores, estimators including late pretests will typically be preferred to estimators excluding them or using other baseline data - In RCTs of interventions to improve student test scores, estimators including late pretests will typically be preferred to estimators excluding them or using other baseline data
• In RCTs, effects on stress (g=1.79) and professional burnout (g=0.82) increased at short-term follow-up, while effects on anxiety, sleep, and wellbeing were non-significant - In RCTs, effects on stress (g=1.79) and professional burnout (g=0.82) increased at short-term follow-up, while effects on anxiety, sleep, and wellbeing were non-significant
• In reading textually constrained period poetry, experts' organized domain knowledge (schemata) is the major factor differentiating them from novices, enabling allusion, contextualization and anticipation. - In reading textually constrained period poetry, experts' organized domain knowledge (schemata) is the major factor differentiating them from novices, enabling allusion, contextualization and anticipat
• In reading, dual language participants grew slightly more slowly during school years but lost less learning during summers, closing the gap with the national average - In reading, dual language participants grew slightly more slowly during school years but lost less learning during summers, closing the gap with the national average
• In reading, ELs grew less than never-ELs in K-1 but more in later grades, with greater summer loss - In reading, ELs grew less than never-ELs in K-1 but more in later grades, with greater summer loss
• In reading-related outcomes, group differences involving RD or RDMD are largest for reading tasks and phonological processing and smallest for RAN - In reading-related outcomes, group differences involving RD or RDMD are largest for reading tasks and phonological processing and smallest for RAN
• In regressions predicting self-reported achievement, elaboration positively (Beta = 0.24) and cramming negatively (Beta = -0.30) predicted achievement, but only effort regulation and engagement remained significant in the combined model - In regressions predicting self-reported achievement, elaboration positively (Beta = 0.24) and cramming negatively (Beta = -0.30) predicted achievement, but only effort regulation and engagement remain
• In replication analyses, the variety conditions were particularly beneficial for students with low prior GPAs, while the same-type-only conditions had negligible effect sizes - In replication analyses, the variety conditions were particularly beneficial for students with low prior GPAs, while the same-type-only conditions had negligible effect sizes
• In research-intensive managerial cultures, teaching and students have been comparatively neglected in favour of research and writing - In research-intensive managerial cultures, teaching and students have been comparatively neglected in favour of research and writing
• In retrospective within-subject comparison, no core metric distinguished synthesized TTS narration from recorded instructor voice, and equivalence testing supported non-inferiority - In retrospective within-subject comparison, no core metric distinguished synthesized TTS narration from recorded instructor voice, and equivalence testing supported non-inferiority
• In rigorous controlled studies, residency graduates retained at significantly higher rates than non-residency peers - In rigorous controlled studies, residency graduates retained at significantly higher rates than non-residency peers
• In Root's study, superior children (IQ 135+ younger, 120+ older) excelled normal children on all administered tests - In Root's study, superior children (IQ 135+ younger, 120+ older) excelled normal children on all administered tests
• In Roster Justice, Avoidant-mindset participants described roster disparities in racially neutral terms while Aware-mindset participants named the racialized nature of the disparity - In Roster Justice, Avoidant-mindset participants described roster disparities in racially neutral terms while Aware-mindset participants named the racialized nature of the disparity
• In Save Patch, different error types were associated with different learning outcomes, attributed to Kerr and Chung (2013b) - In Save Patch, different error types were associated with different learning outcomes, attributed to Kerr and Chung (2013b)
• In SCED studies, family-implemented interventions significantly improve text reading outcomes (g = 1.80) but show a positive, non-significant effect on decoding/word reading outcomes (g = 0.86) - In SCED studies, family-implemented interventions significantly improve text reading outcomes (g = 1.80) but show a positive, non-significant effect on decoding/word reading outcomes (g = 0.86)
• In school racial/ethnic diversity research, mathematical diversity indices operationalizing dual-concept diversity are the dominant measure, with Simpson's D the most widely applied, and most studies assess static diversity at a single timepoint - In school racial/ethnic diversity research, mathematical diversity indices operationalizing dual-concept diversity are the dominant measure, with Simpson's D the most widely applied, and most studies
• In school studies, cooperative and peer-learning methods that reward groups on every member's individual learning raised achievement more than methods without such rewards
• In schools attending fully in person, temporary closures in response to known cases are far less effective than hybrid operation from the start and increase schedule disruption - In schools attending fully in person, temporary closures in response to known cases are far less effective than hybrid operation from the start and increase schedule disruption
• In schools characterized by high relational trust, educators were more likely to experiment with new practices and work together with parents to advance improvements - In schools characterized by high relational trust, educators were more likely to experiment with new practices and work together with parents to advance improvements
• In schools offering both course types, enrollment differs by race/ethnicity, with more White students in single-discipline courses - In schools offering both course types, enrollment differs by race/ethnicity, with more White students in single-discipline courses
• In schools that did not fully implement the district-level suspension reform, peer math achievement declined and attendance decreased - In schools that did not fully implement the district-level suspension reform, peer math achievement declined and attendance decreased
• In schools that eliminated classroom disorder out-of-school suspensions, peer math achievement and attendance were unaffected - In schools that eliminated classroom disorder out-of-school suspensions, peer math achievement and attendance were unaffected
• In schools where students experience peer support for academic work, student learning is more likely - In schools where students experience peer support for academic work, student learning is more likely
• In schoolwide grant-activity cities, about half of surveyed educators collaborated with educators from the opposite sector - In schoolwide grant-activity cities, about half of surveyed educators collaborated with educators from the opposite sector
• In SDPBL with SDD introduced, AI usage varies greatly by team and phase, with all teams using AI in Implementation and Debugging but large team differences in Investigation and Planning - In SDPBL with SDD introduced, AI usage varies greatly by team and phase, with all teams using AI in Implementation and Debugging but large team differences in Investigation and Planning
• In second-language teaching for pupils with special educational needs, Pepper was associated with higher participation than digital tablets - In second-language teaching for pupils with special educational needs, Pepper was associated with higher participation than digital tablets
• In secondary school students, breaks with green views or walks in larger green spaces improve attention performance - In secondary school students, breaks with green views or walks in larger green spaces improve attention performance
• In secondary-school research, cooperative learning beat frontal teaching in 68% of comparisons, with STAD most and Jigsaw least successful - In secondary-school research, cooperative learning beat frontal teaching in 68% of comparisons, with STAD most and Jigsaw least successful
• In selected Chicago schools, external partners sparked documented improvements in instruction, parent involvement, or school climate - In selected Chicago schools, external partners sparked documented improvements in instruction, parent involvement, or school climate
• In self-cued directed forgetting, selected words were better recalled than unselected words regardless of whether they were designated to-be-remembered or to-be-forgotten - In self-cued directed forgetting, selected words were better recalled than unselected words regardless of whether they were designated to-be-remembered or to-be-forgotten
• In SEM, all three self-efficacy dimensions are positively associated with AI use, with Excellence strongest (β = .47), followed by Communication (β = .31) and Attention (β = .22); the model explains 43% of variance - In SEM, all three self-efficacy dimensions are positively associated with AI use, with Excellence strongest (β = .47), followed by Communication (β = .31) and Attention (β = .22); the model explains 4
• In session 4, LLM-to-Brain participants showed weaker neural connectivity and under-engagement of alpha and beta networks, while Brain-to-LLM participants showed higher memory recall and re-engagement of occipito-parietal and prefrontal nodes - In session 4, LLM-to-Brain participants showed weaker neural connectivity and under-engagement of alpha and beta networks, while Brain-to-LLM participants showed higher memory recall and re-engagement
• In simulated epistemic games, the weighted density statistic distinguishes simulated learner types with distinct mastery trajectories, with the expert trajectory showing the largest WD values - In simulated epistemic games, the weighted density statistic distinguishes simulated learner types with distinct mastery trajectories, with the expert trajectory showing the largest WD values
• In simulated learners with forgetting, study-practice yields higher skill gains while practice-only yields higher fact gains, mirroring the human pattern - In simulated learners with forgetting, study-practice yields higher skill gains while practice-only yields higher fact gains, mirroring the human pattern
• In simulated mastery learning, system constraints left most other task-selection strategies' overpractice stable while sharply reducing it under the outlier risk-averse strategy - In simulated mastery learning, system constraints left most other task-selection strategies' overpractice stable while sharply reducing it under the outlier risk-averse strategy
• In simulated online mastery learning, BKT gave the fewest problems, Streak the second fewest, Random the most, and DKT gave almost as many as Random in one problem type and the least in the other two - In simulated online mastery learning, BKT gave the fewest problems, Streak the second fewest, Random the most, and DKT gave almost as many as Random in one problem type and the least in the other two
• In simulation the router matches the empirically optimal subject strategy in 8 of 13 subjects, but retreats to a safe strategy where gains are marginal - In simulation the router matches the empirically optimal subject strategy in 8 of 13 subjects, but retreats to a safe strategy where gains are marginal
• In simulation, AI-assisted students showed increased scores and reduced solving time, attributed to personalized assistance - In simulation, AI-assisted students showed increased scores and reduced solving time, attributed to personalized assistance
• In simulation, an adaptive prompt router outperforms two static prompt baselines on pedagogical score across 390 scenarios - In simulation, an adaptive prompt router outperforms two static prompt baselines on pedagogical score across 390 scenarios
• In simulation, ignoring local dependence overestimates reliability, and the overestimation grows with the size of the testlet effect (17.0%-21.8% decrease under the larger testlet effect vs. 4.8%-7.4% under the small) - In simulation, ignoring local dependence overestimates reliability, and the overestimation grows with the size of the testlet effect (17.0%-21.8% decrease under the larger testlet effect vs.
• In simulation, LEA met or exceeded targets in Chat and Tutor modes while Quiz Mode's KC Alignment Score fell below target - In simulation, LEA met or exceeded targets in Chat and Tutor modes while Quiz Mode's KC Alignment Score fell below target
• In simulation, the mean-recall approximation matches the clocked-delay Leitner Queue Network for small arrival rates, and its phase-transition threshold appears to be a conservative lower bound. - In simulation, the mean-recall approximation matches the clocked-delay Leitner Queue Network for small arrival rates, and its phase-transition threshold appears to be a conservative lower bound.
• In simulations, Bayesian GLASSO estimation outperforms frequentist GLASSO on bias in edge weights, centrality measures, correlation between estimated and true partial correlations, and specificity - In simulations, Bayesian GLASSO estimation outperforms frequentist GLASSO on bias in edge weights, centrality measures, correlation between estimated and true partial correlations, and specificity
• In simulations, increasing the reflection reward produces a sharp threshold-driven transition around r ≈ 1.5, beyond which responsible AI use with meaningful reflection dominates and opportunistic AI use collapses - In simulations, increasing the reflection reward produces a sharp threshold-driven transition around r ≈ 1.5, beyond which responsible AI use with meaningful reflection dominates and opportunistic AI
• In simulations, peer sensitivity (β) moderates how rapidly responsible AI-use norms emerge: strong peer sensitivity yields a sharp tipping-point transition, while weak peer sensitivity yields only gradual, marginal increases - In simulations, peer sensitivity (β) moderates how rapidly responsible AI-use norms emerge: strong peer sensitivity yields a sharp tipping-point transition, while weak peer sensitivity yields only gra
• In simulations, resolution metrics become strongly positively related to knowledge once guessing is possible, even when true resolution is constant - In simulations, resolution metrics become strongly positively related to knowledge once guessing is possible, even when true resolution is constant
• In simulations, responsible AI-use norms emerge only within a constrained design space: when reflection effort is high relative to its reward, opportunistic AI use persists, and near the boundary small changes in reward or effort produce large shifts in responsible-use frequency - In simulations, responsible AI-use norms emerge only within a constrained design space: when reflection effort is high relative to its reward, opportunistic AI use persists, and near the boundary smal
• In simulations, superficial reflection stays at consistently low frequency across all reflection-reward levels, and misuse remains negligible, indicating the main governance challenge is normalised opportunistic AI use rather than overt misconduct - In simulations, superficial reflection stays at consistently low frequency across all reflection-reward levels, and misuse remains negligible, indicating the main governance challenge is normalised op
• In simulations, the Bayesian GLASSO performed better than the Horseshoe prior for estimating symptom networks - In simulations, the Bayesian GLASSO performed better than the Horseshoe prior for estimating symptom networks
• In some cases, Teach For America and Teaching Fellows secondary math teachers are more effective than traditionally certified math teachers - In some cases, Teach For America and Teaching Fellows secondary math teachers are more effective than traditionally certified math teachers
• In spaced practice with post-feedback memory ratings, restudied Swahili–English pairs were recalled better than covertly or overtly retrieved pairs on a delayed final cued-recall test. - In spaced practice with post-feedback memory ratings, restudied Swahili–English pairs were recalled better than covertly or overtly retrieved pairs on a delayed final cued-recall test.