Skip to content

Sources: Avanti AI coach plan

Every work cited in the AI coach papers (META_ANALYSIS.md, WHAT_WORKS.md, COACH_WALKTHROUGH.md) and literature/*.md was downloaded and read in an archived copy, fetched 2026-10-26 to 2026-10-29. Archive: gs://avantifellows-research-sources/ai-coach/<strand>/<file>. The links open only for avantifellows.org Google accounts; the source URL serves everyone else.

Learning with generative AI: tutors and coaches

Section titled “Learning with generative AI: tutors and coaches”
Key Citation Source URL Archived file Bytes SHA-256
bastani2025 Bastani, Bastani, Sungu, Ge, Kabakci, Mariman (2025). Generative AI without guardrails can harm learning: Evidence from high school mathematics. PNAS 122(26): e2422633122. https://doi.org/10.1073/pnas.2422633122 ai_tutors/bastani2025_pnas.xml 93968 d3b61ee92873f2ac…
liu2026 Liu, Sweet, Chen, Engelberg, Masters, Clark, Persaud, Lancaster, Hollingsworth, Rice (2026). The effects of course-integrated AI tutoring on student performance and engagement: A randomized university trial. EdWorkingPaper 26-1598. https://edworkingpapers.com/sites/default/files/ai26-1598.pdf ai_tutors/courseai2026_undergrad.pdf 4203961 11865055a44e9bf4…
kestin2025 Kestin, Miller, Klales, Milbourne, Ponti (2025). AI tutoring outperforms in-class active learning. Scientific Reports 15:17458. https://doi.org/10.1038/s41598-025-97652-6 ai_tutors/kestin2025_physics_tutor.pdf 1376057 afa6965dfd885fcc…
desimone2025 De Simone, Tiberti, Barron Rodriguez, Manolio, Mosuro, Dikoru (2025). From Chalkboards to Chatbots: Evaluating the Impact of Generative AI on Learning Outcomes in Nigeria. World Bank PRWP 11125. https://openknowledge.worldbank.org/server/api/core/bitstreams/8fcccf10-83c9-4295-b01c-5a68aac83b06/content india_context/desimone2025_nigeria.pdf 28294549 62cd8dcc1b7cf3e3…
henkel2024 Henkel, Horne-Robinson, Kozhakhmetova, Lee (2024). Effective and scalable math support: Experimental evidence on the impact of an AI-math tutor in Ghana. arXiv:2402.09809. https://arxiv.org/abs/2402.09809 india_context/henkel2024_rori_ghana.pdf 1331625 3b84457e3fd680d1…
oreopoulos_low2026 Oreopoulos and Low (2026). One click away: AI tutoring with Khanmigo in a two-year school experiment. EdWorkingPaper 26-1551. https://edworkingpapers.com/sites/default/files/ai26-1551.pdf ai_tutors/khanmigo2026_twoyear.pdf 1413072 395562aefe66aaa8…
oreopoulos2026_numi Oreopoulos, Liut, Sungu, Low (2026). Making AI tutoring productive: Evidence from a mastery-based math practice experiment. EdWorkingPaper 26-1552 / NBER WP 35621. https://edworkingpapers.com/sites/default/files/ai26-1552.pdf ai_tutors/oreopoulos2026_numi_mastery.pdf 4805329 6a3702549e1c493d…
learnlm2025 LearnLM Team, Google and Eedi (2025). AI tutoring can safely and effectively support students: An exploratory RCT in UK classrooms. arXiv:2512.23633. https://arxiv.org/abs/2512.23633 ai_tutors/learnlm2025_eedi_rct.pdf 4228199 a0ee40ce7e3b52a7…
learnlm2026 LearnLM Team, Google and Eedi (2026). Measuring the impact of AI tutoring, from near transfer to standardised tests: An expanded RCT in UK mathematics classrooms. Technical report. Added 2026-11-02, after the sweep. https://services.google.com/fh/files/misc/learnlm_oct26.pdf meta_review/ai_tutoring/learnlm_eedi2026_ukrct.pdf 3927399 c0aa30c31f65c99c…
lehmann2025 Lehmann, Cornelius, Sting (2025). AI meets the classroom: When do large language models harm learning? arXiv:2409.09047v2. https://arxiv.org/abs/2409.09047 ai_tutors/lehmann2024_llm_harm.pdf 1491847 de776c0b49dd72ba…
fan2024 Fan, Tang, Le, Shen, Tan, Zhao, Shen, Li, Gasevic (2024). Beware of metacognitive laziness. arXiv:2412.09315. https://arxiv.org/abs/2412.09315 ai_tutors/fan2024_metacog_laziness.pdf 6729517 2b997a39c00fdaf7…
pardos2024 Pardos and Bhandari (2024). ChatGPT-generated help produces learning gains equivalent to human tutor-authored help on mathematics skills. PLOS ONE 19(5): e0304013. https://doi.org/10.1371/journal.pone.0304013 ai_tutors/pardos2024_chatgpt_hints.pdf 1308462 1525207b57c6f4f3…
wang2024 Wang, Ribeiro, Robinson, Loeb, Demszky (2024; v3 2026). Tutor CoPilot: A human-AI approach for scaling real-time expertise. arXiv:2410.03017. https://arxiv.org/abs/2410.03017 ai_tutors/wang2024_tutorcopilot.pdf 1993820 90274f5c23ea01d4…
harrison2026 Harrison, Khowaja, Dobson, Uwimpuhwe, Higgins (2026). Evaluating AI tutoring at the speed of innovation: Practitioner-led micro-randomised trials of an AI tutoring platform in GCSE science. arXiv:2609.14789. https://arxiv.org/abs/2609.14789 ai_tutors/gcse2026_microrandomised.pdf 313374 36cb1b0fd1d8e10c…
huntingtonklein2026 Huntington-Klein (2026). Little impact of ChatGPT on high school test scores. arXiv:2605.08812v3. https://arxiv.org/abs/2605.08812 ai_tutors/highschool2026_little_impact.pdf 267143 0d67f7c86444e7de…
kosmyna2025 Kosmyna et al. (2025). Your brain on ChatGPT: Accumulation of cognitive debt when using an AI assistant for essay writing task. arXiv:2506.08872. https://arxiv.org/abs/2506.08872 ai_tutors/kosmyna2025_brain_chatgpt.pdf 38177802 9b84e8dff3e5a9ea…

Not obtained (leads, not references):

  • Stromberg, Lei and Wu (2026), the generative AI learning penalty in Chinese secondary education (SSRN 6868618 / CEPR DP 21577). I tried the SSRN Delivery.cfm link, the VoxEU column (curl and WebFetch) and the VoxDev column; all three returned a Cloudflare bot-check or a 403. This is the most relevant missing source.
  • Kumar, Rothschild, Goldstein and Hofman (2023), Math education with LLMs: peril or promise? (SSRN 4641653). arXiv ID 2310.13615 turned out to be a different paper (Yen and Hsu), which I deleted. The Microsoft Research record had no PDF link, and SSRN blocks automated access.
  • Futterer et al. (2026), Educational Psychology Review RCT on GenAI support for self-regulated learning (371 students, grades 7-9). OpenAlex lists it as open access, but the Springer PDF and HTML both returned bot-check pages.
  • Darvishi et al. (2024), Computers & Education, on AI assistance and student agency. Paywalled. The sci-hub fallback was refused by the permission classifier, and I did not try to work around that.
  • Barcaui (2025), ‘ChatGPT as a cognitive crutch’ (Social Sciences & Humanities Open, 120 undergraduates, 45-day retention test). Found only in search snippets; OpenAlex search did not return the record.
  • Sungu, Lira and Duckworth (2026), ‘Generative AI can harm teaching’. Cited in Liu et al. 2026; not retrieved; belongs to the teacher-AI strand.
  • Khan Academy’s claimed Uttar Pradesh trial (0.45 effect size): blog claim only; no primary report found.
  • Indian registered trials (Rajasthan custom-GPT revision RCT ended March 2026; Gemini Guided Learning junior-school science, ends Feb 2027): registry entries only, no results.
  • Wang and Fan (2025) meta-analysis of ChatGPT and learning performance: cited in Liu et al. 2026; not retrieved.
  • stromberg2026: Stromberg, Lei, Wu (2026). The generative AI learning penalty: Evidence from Chinese secondary education. SSRN 6868618 / CEPR DP 21577. (listed, not opened)
  • kumar2023: Kumar, Rothschild, Goldstein, Hofman (2023). Math education with large language models: Peril or promise? SSRN 4641653. (listed, not opened)
  • futterer2026: Futterer, Bardach, Kuhn, Keller, Gerjets (2026). Enhancing school students’ self-regulated learning through generative AI support: A randomized controlled trial. Educational Psychology Review 38. (listed, not opened)

Teacher-student-AI interfacing and coaching (hybrid human-AI models, tutoring dosage, teacher dashboards and briefs, coaching/mentoring, nudges, early warning)

Section titled “Teacher-student-AI interfacing and coaching (hybrid human-AI models, tutoring dosage, teacher dashboards and briefs, coaching/mentoring, nudges, early warning)”
Key Citation Source URL Archived file Bytes SHA-256
guryan2021 Guryan, Ludwig, Bhatt, Cook, Davis, Dodge, Farkas, Fryer, Mayer, Pollack, Steinberg (2021). Not Too Late: Improving Academic Outcomes Among Adolescents. NBER WP 28531. https://www.nber.org/papers/w28531 hybrid_human_ai/guryan2023_saga_tutoring.pdf 971745 58d03613fc68c9fd…
nickow2020 Nickow, Oreopoulos, Quan (2020). The Impressive Effects of Tutoring on PreK-12 Learning. NBER WP 27476. https://www.nber.org/papers/w27476 hybrid_human_ai/nickow2020_tutoring_meta.pdf 820093 64dd755f2d6264b0…
kraft2024 Kraft, Schueler, Falken (2024). What Impacts Should We Expect from Tutoring at Scale? EdWorkingPaper 24-1031. https://edworkingpapers.com/sites/default/files/ai24-1031.pdf hybrid_human_ai/kraft2024_tutoring_at_scale.pdf 1876838 4f40740e847132bd…
wang2024 Wang, Ribeiro, Robinson, Loeb, Demszky (2024). Tutor CoPilot: A Human-AI Approach for Scaling Real-Time Expertise. arXiv:2410.03017. https://arxiv.org/abs/2410.03017 hybrid_human_ai/wang2024_tutor_copilot.pdf 1993820 90274f5c23ea01d4…
thomas2024 Thomas et al. (2024). Improving Student Learning with Hybrid Human-AI Tutoring: A Three-Study Quasi-Experimental Investigation. LAK ’24. https://arxiv.org/abs/2312.11274 hybrid_human_ai/thomas2024_hybrid_tutoring.pdf 1788129 73c4c2a89c2c33f6…
holstein2018 Holstein, McLaren, Aleven (2018). Student Learning Benefits of a Mixed-Reality Teacher Awareness Tool in AI-Enhanced Classrooms. AIED 2018. https://www.cs.cmu.edu/~bmclaren/pubs/HolsteinMcLarenAleven-StudentLearningBenefitsMixedRealityTeacherAwarnessTool-AIED2018.pdf hybrid_human_ai/holstein2018_lumilo.pdf 2394265 1837c6b66510b954…
holstein2021 Holstein, Aleven (2021). Designing for human-AI complementarity in K-12 education. arXiv:2104.01266. https://arxiv.org/abs/2104.01266 hybrid_human_ai/holstein2021_complementarity.pdf 640474 ea370c1a1fc9c4a2…
roy2024 Roy, Poet, Staunton, Aston, Thomas (2024). ChatGPT in Lesson Preparation: A Teacher Choices Trial. EEF/NFER Evaluation Report. https://files.eric.ed.gov/fulltext/ED680921.pdf hybrid_human_ai/roy2024_eef_chatgpt_lesson_prep.pdf 1986148 adc5d7759f7f7702…
bettinger2011 Bettinger, Baker (2011). The Effects of Student Coaching in College: An Evaluation of a Randomized Experiment in Student Mentoring. NBER WP 16881. https://www.nber.org/papers/w16881 hybrid_human_ai/bettinger2014_insidetrack_coaching.pdf 182647 482dd6bcf0edb466…
oreopoulos2016 Oreopoulos, Petronijevic (2016). Student Coaching: How Far Can Technology Go? NBER WP 22630. https://www.nber.org/papers/w22630 hybrid_human_ai/oreopoulos2018_coaching_technology.pdf 745155 d2c83f2f37ec5f60…
oreopoulos2019 Oreopoulos, Petronijevic (2019). The Remarkable Unresponsiveness of College Students to Nudging and What We Can Learn from It. NBER WP 26059. https://www.nber.org/papers/w26059 hybrid_human_ai/oreopoulos2019_unresponsive_nudging.pdf 707953 391f10a77303ca51…
carrell2013 Carrell, Sacerdote (2013). Why Do College Going Interventions Work? NBER WP 19031. https://www.nber.org/papers/w19031 hybrid_human_ai/carrell2017_college_going_mentoring.pdf 1048151 aafa80fd09ebbb4e…
clark2017 Clark, Gill, Prowse, Rush (2017). Using Goals to Motivate College Students: Theory and Evidence from Field Experiments. NBER WP 23638. https://www.nber.org/papers/w23638 hybrid_human_ai/clark2020_goals_college.pdf 888186 3144c3e032400bf0…
bird2019 Bird, Castleman, Denning, Goodman, Lamberton, Rosinger (2019). Nudging at Scale: Experimental Evidence from FAFSA Completion Campaigns. NBER WP 26158. https://www.nber.org/papers/w26158 hybrid_human_ai/bird2021_nudging_at_scale.pdf 503532 aedfba2a099cadd5…
page2017 Page, Gehlbach (2017). How an Artificially Intelligent Virtual Assistant Helps Students Navigate the Road to College. AERA Open 3(4). https://doi.org/10.1177/2332858417749220 hybrid_human_ai/page2017_chatbot_summer_melt.pdf 94903 d02b2abe78d9e970…
faria2017 Faria et al. (2017). Getting students on track for graduation: Impacts of the Early Warning Intervention and Monitoring System after one year (REL 2017-272). https://ies.ed.gov/sites/default/files/migrated/rel/regions/midwest/pdf/REL_2017272.pdf hybrid_human_ai/faria2017_ewims.pdf 895402 c740e99623b1f177…
fang2025 Fang et al. (2025). How AI and Human Behaviors Shape Psychosocial Effects of Extended Chatbot Use: A Longitudinal Randomized Controlled Study. arXiv:2503.17473. https://arxiv.org/abs/2503.17473 hybrid_human_ai/fang2025_chatbot_psychosocial.pdf 3042099 c26e783264416b90…

Not obtained (leads, not references):

  • Gehlbach et al. 2016, Creating birds of similar feathers (J Educ Psych, doi:10.1037/edu0000042): Harvard DASH links from OpenAlex returned empty files.
  • Bergman 2021, Parent-Child Information Frictions (JPE, doi:10.1086/711410): CESifo WP 5391 link returned HTML, not PDF.
  • Bergman and Chan 2021, Leveraging Parents through Low-Cost Technology (JHR): no OA copy found.
  • Holstein et al. 2018 via sci-hub mirror was blocked by the permission classifier; obtained instead from the CMU author page (so not a gap).
  • EEF project page blocked by Cloudflare (403); report obtained from ERIC instead.
  • Demszky et al. automated feedback to instructors RCT: not attempted.
  • The 82-study hybrid systematic review and the ‘35% GPA’ mentoring study cited in Pritam’s review: primary sources not identified.
  • Avery et al. national vs school-counsellor texting campaign (cited in Bird et al.): not located.
  • gehlbach2016: Gehlbach et al. (2016). Creating birds of similar feathers. Journal of Educational Psychology. (listed, not opened)
  • bergman2021: Bergman (2021). Parent-Child Information Frictions and Human Capital Investment. JPE. (listed, not opened)

India context, safety, policy and evaluation

Section titled “India context, safety, policy and evaluation”
Key Citation Source URL Archived file Bytes SHA-256
chiplunkar2020 Chiplunkar, Dhar and Nagesh (2020). Too little, too late: Improving post-primary learning outcomes in India. Working paper. gs://avantifellows-research-sources/avanti-impact-paper/chiplunkar_dhar_nagesh_2020.pdf india_context/dhar2020_toolittle.pdf 463002 799b2ac06d809dd4…
muralidharan2017 Muralidharan, Singh and Ganimian (2017). Disrupting education? NBER WP 22923 (AER 2019). https://www.nber.org/papers/w22923 india_context/muralidharan2019_mindspark.pdf 1668164 5f3efac6f7a4266f…
muralidharan2025 Muralidharan and Singh (2025). Adapting for scale. NBER WP 34205. https://www.nber.org/system/files/working_papers/w34205/w34205.pdf india_context/muralidharan2025_adapting.pdf 6086338 6bf913ef4a11d3b5…
banerjee2017 Banerjee et al. (2017). From proof of concept to scalable policies. NBER WP 22931 / JEP. gs://avantifellows-research-sources/talent-identification/level_pace__tarl2017jep.pdf india_context/banerjee2017_tarl_jep.pdf 251714 e61ffa65977c031c…
rodriguezsegura2021 Rodriguez-Segura (2021). EdTech in developing countries: a review of the evidence. Author draft of WBRO 2022. https://www.ictworks.org/wp-content/uploads/2023/03/Edutech-developing-countries.pdf india_context/rodriguezsegura2021_edtech_draft.pdf 303041 1722bbdea088fa78…
desimone2025 De Simone et al. (2025). From chalkboards to chatbots. World Bank PRWP 11125. https://documents1.worldbank.org/curated/en/099548105192529324/pdf/IDU-c09f40d8-9ff8-42dc-b315-591157499be7.pdf india_context/desimone2025_nigeria.pdf 28294549 62cd8dcc1b7cf3e3…
henkel2024 Henkel et al. (2024). Effective and scalable math support: AI math tutor in Ghana. arXiv 2402.09809. https://arxiv.org/pdf/2402.09809 india_context/henkel2024_rori_ghana.pdf 1331625 3b84457e3fd680d1…
verma2025 Verma et al. (2025). MILU: A multi-task Indic language understanding benchmark. arXiv 2411.02538 v3. https://arxiv.org/pdf/2411.02538 india_context/milu2024_indic.pdf 1020081 a862d7eb687765fd…
fang2018 Fang et al. (2018). The big-fish-little-pond effect on academic self-concept: A meta-analysis. Frontiers in Psychology 9:1569. https://doi.org/10.3389/fpsyg.2018.01569 india_context/fang2018_bflpe.pdf 816427 682e675b55427e16…
azmat2016 Azmat, Bagues, Cabrales and Iriberri (2016). What you don’t know… can’t hurt you? IZA DP 9853 (Management Science 2019). https://docs.iza.org/dp9853.pdf india_context/azmat2019_rankfeedback.pdf 744801 6e113ecd1c56cc4b…
murphy2013 Murphy and Weinhardt (2013). Top of the class: The importance of ordinal rank. CEP DP 1241 (REStud 2020). https://cep.lse.ac.uk/pubs/download/dp1241.pdf india_context/murphy2020_rank.pdf 1066747 7aea6197c11ecda6…
evansyuan2020 Evans and Yuan (2020). How big are effect sizes in international education studies? CGD WP 545. https://www.cgdev.org/sites/default/files/how-big-are-effect-sizes-international-education-studies.pdf india_context/evansyuan2022_effectsizes.pdf 615463 462493686985cf39…
kraft2019 Kraft (2019). Interpreting effect sizes of education interventions. EdWorkingPaper 19-10. https://edworkingpapers.com/sites/default/files/Interpreting%20Effect%20Sizes%20-%20August%2019%20FINAL_0.pdf india_context/kraft2019_effectsizes.pdf 861239 05eeeb964facff83…
duflo2007 Duflo, Glennerster and Kremer (2007). Using randomization in development economics research: A toolkit. NBER TWP 333. https://www.nber.org/system/files/working_papers/t0333/t0333.pdf india_context/duflo2007_toolkit.pdf 1092099 e55eba9e33c45156…
anthropic_consumer_terms Anthropic Consumer Terms of Service, effective 8 Oct 2025. https://www.anthropic.com/legal/consumer-terms india_context/anthropic_consumer_terms.html 541478 40f5e7932603b394…
anthropic_age_assurance Anthropic, Age assurance on Claude (help centre, 18 May 2026). https://support.claude.com/en/articles/15171100-age-assurance-on-claude india_context/anthropic_age_assurance.html 195193 71d8bcc040d55ca8…
anthropic_min_age Anthropic, Minimum age requirement access restriction (help centre, 16 Mar 2026). https://support.claude.com/en/articles/13117299-minimum-age-requirement-access-restriction india_context/anthropic_min_age.html 196103 938c72aa43ca0c2b…
anthropic_minors Anthropic, Guidelines for organizations serving minors (16 Mar 2026). https://support.claude.com/en/articles/9307344-responsible-use-of-anthropic-s-models-guidelines-for-organizations-serving-minors india_context/anthropic_minors_helpcenter.html 201403 e2fa12053273240c…
anthropic_aup Anthropic Usage Policy (page states effective 12 Nov 2026). https://www.anthropic.com/legal/aup india_context/anthropic_aup.html 1023063 e2d15cbb5d3fa9f8…
anthropic_k12 Anthropic U.S. K-12 Terms of Service and DPA, effective 28 Aug 2026. https://www.anthropic.com/legal/k12-terms india_context/anthropic_k12_terms.html 345166 32ead7624e5d6dbc…
anthropic_commercial Anthropic Commercial Terms of Service, effective 17 Jun 2025. https://www.anthropic.com/legal/commercial-terms india_context/anthropic_commercial_terms.html 243521 7215dbf7985f650a…
anthropic_education Anthropic, Claude for Education and Claude for Teachers pages. https://claude.com/solutions/education india_context/anthropic_education.html 602504 b9d74019432f7a28…
dpdp_act Digital Personal Data Protection Act, 2023 (No. 22 of 2023). https://www.meity.gov.in/static/uploads/2024/06/2bf1f0e9f04e6fb4f8fef35e82c42aa5.pdf india_context/dpdp_act_2023.pdf 182082 4deb23981d3010c8…
dpdp_rules DPDP Rules, 2025, G.S.R. 846(E), 13 Nov 2025. https://www.meity.gov.in/static/uploads/2025/11/53450e6e5dc0bfa85ebd78686cadad39.pdf india_context/dpdp_rules_2025_gsr846.pdf 2492944 eabc7d05e0131446…
dpdp_commencement MeitY notification G.S.R. 843(E), 13 Nov 2025, commencement dates. https://www.meity.gov.in/static/uploads/2025/11/c56ceae6c383460ca69577428d36828b.pdf india_context/dpdp_commencement_gsr843.pdf 1869005 6df25cd8c76ac8eb…
nta_calendar NTA Examination Calendar, December 2026 cycle onwards (revised). https://nta.ac.in/Download/Notice/ExamcalendarRevised.pdf india_context/nta_exam_calendar.pdf 25400 8f66c1f0e5920930…
avanti_retest_query Avanti warehouse own query: test-retest correlation of z-scored major tests, JNV CoE G12 engineering, 2025-2026. file:///Users/akshay/avanti-data/jnv_coe_g12_major_test_retest_r2_2025_26.csv Avanti warehouse query (aggregate result, not archived: rerun from BigQuery)

Not obtained (leads, not references):

  • Rodriguez-Segura (2022) WBRO published version (DOI 10.1093/wbro/lkab011): the publisher PDF and the UVA working paper returned 403, the IIEP mirror failed on SSL, and the sci-hub fallback was denied by the permission classifier. I used the author’s June 2021 draft instead.
  • Mindspark AER 2019 published version: not opened. I used the NBER WP 22923 numbers (0.36/0.22 SD); the framework’s 0.37/0.23 SD is unverified.
  • Azmat and Iriberri (2010) and Tran and Zeckhauser (2012), both on positive rank-feedback effects: known only as cited in Azmat et al. 2016, not opened.
  • Code-mixed (Hinglish/Marathi-English) math or physics reasoning benchmarks: CodeMixBench (arXiv 2505.05063) and MathMist seen in search results only.
  • Reports of a MeitY proposal to shorten the DPDP compliance window to 12 months (SS Rana, Feb 2026; Takshashila, Jan 2026): not opened, and I found no notified amendment.
  • Any Anthropic statement on whether under-18 users may hold Team or Enterprise seats: not found on any page opened. A direct question to Anthropic is needed.
  • Brilliant.org and Art of Problem Solving terms on users under 18 and data collection: not checked.
  • Kraft 2020 Educational Researcher published version: the EdWorkingPaper URL first tried returned 404. I used the August 2019 working paper.

Adaptive platforms and the pedagogy behind each tool

Section titled “Adaptive platforms and the pedagogy behind each tool”
Key Citation Source URL Archived file Bytes SHA-256
MSG2017 Muralidharan, K., Singh, A., & Ganimian, A. J. (2017). Disrupting education? Experimental evidence on technology-aided instruction in India. NBER Working Paper 22923. https://www.nber.org/papers/w22923 adaptive_platforms/MSG2019_mindspark.pdf 1668164 5f3efac6f7a4266f…
OKA2026 Oreopoulos, P., Keyes-Krysakowski, O., & Agarwal, D. (2026). How in-school supervised ed-tech support produces massive learning gains: a Khan Academy field experiment in India. NBER Working Paper 34683. https://www.nber.org/papers/w34683 adaptive_platforms/NBER_w34683.pdf 6676004 6d38a81cb6fd978f…
OL2026 Oreopoulos, P., & Low, N. (2026). One click away: AI tutoring with Khanmigo in a two-year school experiment. NBER Working Paper 35620. https://www.nber.org/papers/w35620 adaptive_platforms/NBER_w35620.pdf 991227 55a8689cc89190db…
OGJP2024 Oreopoulos, P., Gibbs, C., Jensen, M., & Price, J. (2024). Teaching teachers to use computer assisted learning effectively. NBER Working Paper 32388. https://www.nber.org/papers/w32388 adaptive_platforms/NBER_w32388.pdf 1083990 da9c8f2b58cbf221…
GWH2022 Grimaldi, P., Weatherholtz, K., & Hill, K. M. (2022). Estimating the causal effects of Khan Academy MAP Accelerator across demographic subgroups. EDM 2022, 839-846. https://educationaldatamining.org/EDM2022/proceedings/2022.EDM-industry-track.112/2022.EDM-industry-track.112.pdf adaptive_platforms/KHAN2022_edm_mapaccel.pdf 1905611 e094e62075471bf5…
YB2024 Yamkovenko, B., & Bergstrom, A. (2024). Khan Academy efficacy results, November 2024. Khan Academy Blog. https://blog.khanacademy.org/?p=18194 adaptive_platforms/KHAN2024_efficacy_blog.html 114019 0a5a30ecd4df71e9…
KHANBLOG Khan Academy (n.d.). Multiple studies show Khan Academy drives learning gains. Khan Academy Blog. https://blog.khanacademy.org/multiple-studies-show-khan-academy-drives-learning-gains-evidence-for-our-platforms-effectiveness/ adaptive_platforms/KHAN_multiple_studies_blog.html 100310 5b614f0408b16cec…
SRI2014 Murphy, R., Gallagher, L., Krumm, A., Mislevy, J., & Hafter, A. (2014). Research on the use of Khan Academy in schools. SRI Education. gs://avantifellows-research-sources/nvs-lakshya/sri_khan_2014.pdf adaptive_platforms/SRI2014_khan.pdf 3475436 8acd89159646d008…
RFMM2016 Roschelle, J., Feng, M., Murphy, R. F., & Mason, C. A. (2016). Online mathematics homework increases student achievement. AERA Open, 2(4). https://files.eric.ed.gov/fulltext/EJ1194398.pdf adaptive_platforms/RFMM2016_assistments.pdf 483956 04385d8c856c93e7…
SP2017 Sales, A. C., & Pane, J. F. (2017/2018). The role of mastery learning in an intelligent tutoring system: principal stratification on a latent variable. arXiv:1707.09308. https://arxiv.org/abs/1707.09308 adaptive_platforms/SP2017_mastery_cta1_arxiv.pdf 3660937 174dccc58a16de35…
ISP2018 Israni, A., Sales, A. C., & Pane, J. F. (2018). Mastery learning in practice: log data from the Cognitive Tutor Algebra I effectiveness trial. arXiv:1802.08616. https://arxiv.org/abs/1802.08616 adaptive_platforms/SP2018_mastery_logdata_arxiv.pdf 437226 5d7d740d4347ecf3…
V2011 VanLehn, K. (2011). The relative effectiveness of human tutoring, intelligent tutoring systems, and other tutoring systems. Educational Psychologist, 46(4), 197-221. https://doi.org/10.1080/00461520.2011.611369 adaptive_platforms/V2011_tutoring.pdf 602280 1b353bd1e6fdf2ed…
KF2012 Kulik, J. A., & Fletcher, J. D. (2012). Effectiveness of intelligent tutoring systems. IDA Document D-4664. https://www.ida.org/-/media/feature/publications/e/ef/effectiveness-of-intelligent-tutoring-systems/d-4664.ashx adaptive_platforms/KF2016_its_meta.pdf 617323 023577255d7a2b08…
MANL2014 Ma, W., Adesope, O. O., Nesbit, J. C., & Liu, Q. (2014). Intelligent tutoring systems and learning outcomes: a meta-analysis. Journal of Educational Psychology, 106. https://www.cs.uky.edu/~sgware/reading/papers/ma2014intelligent.pdf adaptive_platforms/MANL2014_its_meta.pdf 230851 e6d990913e57eeb7…
LEITE2025 Leite, W. L., et al. (2025). Do intelligent tutoring systems benefit K-12 students? A meta-analysis… arXiv:2511.04997. https://arxiv.org/abs/2511.04997 adaptive_platforms/ITS2025_k12_meta_arxiv.pdf 793908 73297c3352b894f0…
EQNO2017 Escueta, M., Quan, V., Nickow, A. J., & Oreopoulos, P. (2017). Education technology: an evidence-based review. NBER Working Paper 23744. https://www.nber.org/papers/w23744 adaptive_platforms/EQNO2017_edtech_nber.pdf 869272 1034c37ec458205b…
RS2021 Rodriguez-Segura, D. (2021 draft; WBRO 2022). Educational technology in developing countries: a review of the evidence. https://www.ictworks.org/wp-content/uploads/2023/03/Edutech-developing-countries.pdf adaptive_platforms/RS2022_ictworks.pdf 303041 1722bbdea088fa78…
ALPHAMAP2025 Alpha School (2025). NWEA MAP Student Growth Summary Report, Spring 2024-2025 (self-generated). https://go.alpha.school/hubfs/MAP%20Results%20-%2024%2025/2025%20NWEA%20MAP%20results.pdf adaptive_platforms/ALPHA2025_map_results.pdf 201712 2e8af2bccfe5201a…
ALPHASITES Alpha School and 2 Hour Learning homepages and results page. https://alpha.school/ ; https://2hourlearning.com/ ; https://2hourlearning.com/results/ adaptive_platforms/ALPHA_site_home.html; adaptive_platforms/ALPHA_2hourlearning_home.html; adaptive_platforms/ALPHA_2hl_results.html 921295 25578ec91dac7d6c…; 5b60249d2f53c54f…; 45608af1ddb47388…
ACX2025 Anonymous ACX reader (2025). Your Review: Alpha School. Astral Codex Ten. https://www.astralcodexten.com/p/your-review-alpha-school adaptive_platforms/ACX2025_alpha_parent_review.html 442454 9554c059bfe163b8…
SCHOALES2026 Schoales, V. (2026). Alpha School’s Theranos problem. Fordham Institute Flypaper. https://fordhaminstitute.org/national/commentary/alpha-schools-theranos-problem adaptive_platforms/FORD2025_alpha_theranos.html 87439 5aeb72d99de77ba1…
ALDEMAN2026 Aldeman, C. (2026). What public schools and parents can learn from a $40,000-a-year private school. The 74. https://www.the74million.org/article/what-public-schools-and-parents-can-learn-from-a-40000-a-year-private-school/ adaptive_platforms/T74_alpha.html 94869 755f7d9a2a71c692…
SQAI2019 Cui, W., Xue, Z., & Thai, K.-P. (2019). Performance comparison of an AI-based adaptive learning system in China. arXiv:1901.10268. https://arxiv.org/abs/1901.10268 adaptive_platforms/SQAI2019_arxiv_company.pdf 509623 8c1317e0964637e2…
SRISQ SRI International publication page for Wang et al. (2020), Squirrel AI RCT. https://sri.com/publication/education-learning-pubs/when-adaptive-learning-is-effective-learning-comparison-of-an-adaptive-learning-system-to-teacher-led-instruction adaptive_platforms/SRI_squirrel_page.html 139702 e3f647b9c964e68f…
AOPS Art of Problem Solving. Alcumus: a peek under the hood of our adaptive learning tool (blog). https://artofproblemsolving.com/blog/articles/alcumus-a-peek-under-the-hood-of-our-adaptive-learning-tool adaptive_platforms/AOPS_alcumus_underhood.html 107149 34eb12474e93bf87…
WESTED2022 Gibney, T. T., & Bojorquez, J. C. (2022). Evaluation of Beast Academy in Mankato Area Public Schools. WestEd for AoPS. https://beastacademy.com/u/pdfs/marketing/WestEd%20Beast%20Academy%20Evaluation%20Technical%20Report%20Final.pdf adaptive_platforms/WESTED2022_beastacademy.pdf 629429 31c7ea4364bedce7…
BRIL2023 de la Puente, M., & Perez, H. (2023). Assessing the impact of Brilliant.org… a quasi-experimental study (protocol). Mathematics Teaching Research Journal 15(2). https://files.eric.ed.gov/fulltext/EJ1394390.pdf adaptive_platforms/BRIL_eric_protocol.pdf 382471 3070408036389c20…
BRILSITE Brilliant.org homepage. https://brilliant.org/ adaptive_platforms/BRIL_site_home.html 373365 f8de56439dd2c2a1…

Not obtained (leads, not references):

  • Muralidharan, Singh & Ganimian 2019 AER (published Mindspark version, 0.37/0.23 SD): paywalled; used NBER w22923 (2017) from Avanti archive instead.
  • Muralidharan & Singh 2025, Mindspark in UP government schools (0.22 SD over 18 months per Oreopoulos et al. 2026): not located.
  • Pane, Griffin, McCaffrey & Karam 2014 EEPA 36(2): ERIC has no full text, RAND WR-984 blocked automated download (403/HTML); results taken from Sales & Pane arXiv restatement co-authored by Pane.
  • Kulik & Fletcher 2016 RER 86(1): paywalled; DTIC returned HTML; used 2012 IDA report D-4664.
  • Escueta, Nickow, Oreopoulos & Quan 2020 JEL 58(4): AEA PDF routes returned HTML; used 2017 NBER w23744.
  • Wang et al. 2020 Interactive Learning Environments, SRI Squirrel AI RCT: paywalled; only SRI abstract page opened.
  • Reich & Ruiperez-Valiente 2019 Science ‘The MOOC pivot’: MIT DSpace bitstream returned server error 500.
  • Hirshleifer 2016, Bettinger et al. 2020, Ma et al. 2020, Linden 2008: cited only via Rodriguez-Segura 2021 draft, not opened.
  • Eames et al. 2026 PNAS, Ferman et al. 2019, Buchel et al. 2019, Snipes et al. 2015 (Khan Academy studies listed on Khan blog): not opened.
  • Any outcome evaluation of Alcumus or Brilliant.org: none found via ERIC API, web search or company sites.
  • sci-hub fallback for paywalled DOIs was refused by the session permission classifier, so those DOIs remain leads.
  • PANE2014: Pane, J. F., Griffin, B. A., McCaffrey, D. F., & Karam, R. (2014). Effectiveness of Cognitive Tutor Algebra I at scale. EEPA 36(2), 127-144. (listed, not opened)
  • KF2016: Kulik, J. A., & Fletcher, J. D. (2016). Effectiveness of intelligent tutoring systems: a meta-analytic review. RER 86(1), 42-78. (listed, not opened)
  • EQNO2020: Escueta, M., Nickow, A., Oreopoulos, P., & Quan, V. (2020). Upgrading education with technology. JEL 58(4). (listed, not opened)
  • WANG2020: Wang, S., et al. (2020). When adaptive learning is effective learning. Interactive Learning Environments. (listed, not opened)
  • RRV2019: Reich, J., & Ruiperez-Valiente, J. A. (2019). The MOOC pivot. Science 363(6423). (listed, not opened)

Techniques that work, checked for high-ability JEE students (learning science)

Section titled “Techniques that work, checked for high-ability JEE students (learning science)”
Key Citation Source URL Archived file Bytes SHA-256
dunlosky2013 Dunlosky, Rawson, Marsh, Nathan and Willingham (2013). Improving students’ learning with effective learning techniques. Psychological Science in the Public Interest 14(1), 4-58. https://doi.org/10.1177/1529100612453266 learning_science/dunlosky2013_pspi.pdf 1618194 f551a6008f7bd8f3…
roediger2006 Roediger and Karpicke (2006). Test-enhanced learning. Psychological Science 17(3). https://doi.org/10.1111/j.1467-9280.2006.01693.x learning_science/roediger2006_testing.pdf 119037 00ecdeb3510075cb…
rowland2014 Rowland (2014). The effect of testing versus restudy on retention: a meta-analytic review. Psychological Bulletin 140(6), 1432-1463. https://doi.org/10.1037/a0037559 learning_science/rowland2014_meta.pdf 22970149 f9a6171b8cda48ad…
adesope2017 Adesope, Trevisan and Sundararajan (2017). Rethinking the use of tests: a meta-analysis of practice testing. Review of Educational Research 87(3), 659-701. https://doi.org/10.3102/0034654316689306 learning_science/adesope2017_meta.pdf 701305 8e02477c7b6a8707…
agarwal2012 Agarwal, Bain and Chamberlain (2012). The value of applied research: retrieval practice improves classroom learning. Educational Psychology Review 24, 437-448. https://doi.org/10.1007/s10648-012-9210-2 learning_science/agarwal2012.pdf 374748 7e702a619d60a783…
vangog2015 van Gog and Sweller (2015). Not new, but nearly forgotten: the testing effect decreases or even disappears as the complexity of learning materials increases. Educational Psychology Review 27, 247-264. https://repub.eur.nl/pub/92178/REPUB_92178-OA.pdf learning_science/vangog2015_testing_complexity.pdf 359856 bae53c64888c274b…
cepeda2008 Cepeda, Vul, Rohrer, Wixted and Pashler (2008). Spacing effects in learning: a temporal ridgeline of optimal retention. Psychological Science 19(11), 1095-1102. https://escholarship.org/uc/item/0kp5q19x learning_science/cepeda2008_ridgeline.pdf 234347 5e6829111626409d…
bego2024 Bego, Lyle et al. (2024). Single-paper meta-analyses of the effects of spaced retrieval practice in nine introductory STEM courses. International Journal of STEM Education 11. https://doi.org/10.1186/s40594-024-00468-5 learning_science/bego2024_spaced_retrieval_stem_excerpt.txt 1894 6a527286c63a31db…
rohrer2015 Rohrer, Dedrick and Stershic (2015). Interleaved practice improves mathematics learning. Journal of Educational Psychology (advance online 2014). ERIC ED557355. https://files.eric.ed.gov/fulltext/ED557355.pdf learning_science/rohrer2015_interleaved.pdf 241205 74b771e0104c676c…
rohrer2020 Rohrer, Dedrick, Hartwig and Cheung (2020). A randomized controlled trial of interleaved mathematics practice. Journal of Educational Psychology 112(1), 40-52. ERIC ED595322. https://files.eric.ed.gov/fulltext/ED595322.pdf learning_science/rohrer2020_interleaved_rct.pdf 354324 ba6adb172f16ddbb…
vanderhaar2023 van der Haar, Gray-Lobe, Kremer and de Laat (2023). The long-term distributional impacts of a full-year interleaving math program in Nigeria. EdWorkingPaper 23-876. https://files.eric.ed.gov/fulltext/ED672238.pdf learning_science/vanderhaar2023_nigeria_interleaving.pdf 1201510 7aceb8b82aa5119e…
kalyuga2007 Kalyuga (2007). Expertise reversal effect and its implications for learner-tailored instruction. Educational Psychology Review 19, 509-539. https://www.uky.edu/~gmswan3/EDC608/Kalyuga2007_Article_ExpertiseReversalEffectAndItsI.pdf learning_science/kalyuga2007_reversal_review.pdf 385775 acbd290d5478168a…
wisniewski2020 Wisniewski, Zierer and Hattie (2020). The power of feedback revisited: a meta-analysis. Frontiers in Psychology 10, 3087. https://doi.org/10.3389/fpsyg.2019.03087 learning_science/wisniewski2020_feedback.pdf 1933587 1fe0c0b1da12d7d7…
schroeder2022 Schroeder and Kucera (2022). Refutation text facilitates learning: a meta-analysis of between-subjects experiments. Educational Psychology Review 34(2), 957-987. https://doi.org/10.1007/s10648-021-09656-z learning_science/schroeder2022_refutation_meta.xml 180411 5a411a8cefc453ba…
sadler2016 Sadler and Sonnert (2016). Understanding misconceptions: teaching and learning in middle school physical science. American Educator, Spring 2016. ERIC EJ1094278. https://files.eric.ed.gov/fulltext/EJ1094278.pdf learning_science/sadler2016_misconceptions_ameducator.pdf 215722 da9a9403d7adc901…
bloom1984 Bloom (1984). The 2 sigma problem. Educational Researcher 13(6). https://doi.org/10.3102/0013189X013006004 learning_science/bloom1984_2sigma.pdf 2569660 583630e3fd54ca89…
vonhippel2024 von Hippel (2024). Two-sigma tutoring: separating science fiction from science fact. Education Next 24(2). https://www.educationnext.org/two-sigma-tutoring-separating-science-fiction-from-science-fact/ learning_science/vonhippel2024_twosigma.html 197672 db4d36a40965122c…
slavin1987 Slavin (1987). Mastery learning reconsidered. Report No. 7, CREMS. ERIC ED294891. https://files.eric.ed.gov/fulltext/ED294891.pdf learning_science/slavin1987_mastery_reconsidered.pdf 964275 b05e4448dd1d7bed…
nickow2020 Nickow, Oreopoulos and Quan (2020). The impressive effects of tutoring on preK-12 learning. NBER WP 27476. https://www.nber.org/papers/w27476 learning_science/nickow2020_tutoring.pdf 820093 64dd755f2d6264b0…
kraft2020 Kraft (2020). Interpreting effect sizes of education interventions. Educational Researcher (EdWorkingPaper 19-10). https://doi.org/10.3102/0013189X20912798 learning_science/kraft2020_effectsizes.pdf 861239 05eeeb964facff83…
muralidharan2019 Muralidharan, Singh and Ganimian (2019). Disrupting education? AER 109(4) (working-paper copy). https://econweb.ucsd.edu/~kamurali/papers/Working%20Papers/Disrupting%20Education%20(Current%20WP).pdf india_context/muralidharan2019_mindspark.pdf 1668164 5f3efac6f7a4266f…
akyol2016 Akyol, Key and Krishna (2016). Hit or miss? Test taking behavior in multiple choice exams. NBER WP 22401. https://www.nber.org/papers/w22401 learning_science/akyol2016_hitormiss.pdf 624542 0058b7eb589d0636…
krishna2025 Krishna, Akyol and Ozer (2025). Do time-constraints matter? How, why, and for whom? NBER WP 33679. https://www.nber.org/papers/w33679 learning_science/akyol_krishna2025_timeconstraints.pdf 1519133 842ebacefd2fa690…
baldiga2014 Baldiga (2014). Gender differences in willingness to guess. Management Science (working-paper copy). https://doi.org/10.1287/mnsc.2013.1776 learning_science/baldiga2014_guess.pdf 302044 b9e269c459a667e6…
pekkarinen2014 Pekkarinen (2014). Gender differences in strategic behaviour under competitive pressure: omission patterns in university entrance examinations. IZA DP 8018. https://docs.iza.org/dp8018.pdf learning_science/pekkarinen2015_omission.pdf 589350 13b8d35e12905553…
nta2027bulletin National Testing Agency (2026). Information Bulletin, JEE (Main) 2027. https://cdnbbsr.s3waas.gov.in/s3f8e59f4b2fe7c5705bf878bbd494ccdf/uploads/2026/10/202610241890224107.pdf learning_science/nta_jeemain2027_bulletin.pdf 6576588 c2532df2a228836e…
nta2026paper National Testing Agency (2026). JEE (Main) B.Tech question paper, 2 April 2026 Shift 1. https://cdnbbsr.s3waas.gov.in/s3f8e59f4b2fe7c5705bf878bbd494ccdf/uploads/2026/04/202604092096865379.pdf learning_science/nta_jeemain2026_apr02_s1_paper.pdf 2463315 ba8b5256533e0a29…

Not obtained (leads, not references):

  • Sinha and Kapur 2021, RER 91(5), productive failure meta-analysis (DOI 10.3102/00346543211019105): CC BY on SAGE but SAGE served a bot-verification page to curl and to the browser; ETH repository handle 20.500.11850/490417 returned errors. Only ERIC abstract seen.
  • Kulik, Kulik and Bangert-Drowns 1990, RER mastery learning meta-analysis: closed per Unpaywall and Semantic Scholar; no ERIC full text.
  • Kulik and Kulik 1988, feedback timing meta-analysis: closed; ERIC abstract only.
  • Mullet et al. 2014 JARMAC (delayed feedback, engineering): closed per Unpaywall.
  • Butler, Karpicke and Roediger 2007 (feedback type and timing on MC tests): no OA copy found.
  • Muller, Bewes, Sharma and Reimann 2008 JCAL 24(2) and Muller 2008 PhD thesis: closed; University of Sydney repository and open-journals download blocked automated access. Crossref metadata confirmed correct citation. A sci-hub fallback was refused by the permission system and not used.
  • Crouch and Mazur 2001 AJP: closed; ComPADRE copy requires login.
  • Smith et al. 2009 Science (peer discussion): closed.
  • Kalyuga, Ayres, Chandler and Sweller 2003 Educational Psychologist: UNSW record metadata only; Kalyuga 2007 review used instead.
  • Riener and Wagner 2017 Economics of Education Review: closed; no working-paper copy found.
  • Brunmair and Richter 2019 Psych Bulletin (interleaving meta): closed.
  • Yang et al. 2021 Psych Bulletin (classroom quizzing meta): closed.
  • Murray, Horner and Gobel 2025 Ed Psych Review (spacing and retrieval for maths meta): paywalled, abstract only.
  • Danielson et al. 2025 Educational Psychologist (refutation meta): closed.
  • sinha2021: Sinha and Kapur (2021). When problem solving followed by instruction works: evidence for productive failure. RER 91(5), 761-798. (listed, not opened)
  • kulik1990: Kulik, Kulik and Bangert-Drowns (1990). Effectiveness of mastery learning programs: a meta-analysis. RER 60(2). (listed, not opened)
  • muller2008: Muller, Bewes, Sharma and Reimann (2008). Saying the wrong thing. JCAL 24(2), 144-155. (listed, not opened)
  • crouch2001: Crouch and Mazur (2001). Peer instruction: ten years of experience and results. AJP 69(9), 970-977. (listed, not opened)
  • kulik1988: Kulik and Kulik (1988). Timing of feedback and verbal learning. RER 58(1). (listed, not opened)
  • riener2017: Riener and Wagner (2017). Shying away from demanding tasks? Economics of Education Review 59, 43-62. (listed, not opened)

Step-based tutoring and problem decomposition

Section titled “Step-based tutoring and problem decomposition”
Key Citation Source URL Archived file Bytes SHA-256
VanLehn2011 VanLehn, K. (2011). The relative effectiveness of human tutoring, intelligent tutoring systems, and other tutoring systems. Educational Psychologist 46(4), 197-221. https://doi.org/10.1080/00461520.2011.611369 step_tutoring/V2011_tutoring.pdf 602280 1b353bd1e6fdf2ed…
VanLehn2005 VanLehn, K., et al. (2005). The Andes physics tutoring system: Lessons learned. IJAIED 15(3), 147-204. https://www.public.asu.edu/~kvanlehn/distrib/AndesLessonsLearnedForWeb.pdf step_tutoring/vanlehn2005_andes.pdf 408902 412bbb9b9bcccda4…
Ma2014 Ma, W., Adesope, O. O., Nesbit, J. C., and Liu, Q. (2014). Intelligent tutoring systems and learning outcomes: A meta-analysis. J Educ Psychol 106(4), 901-918. https://doi.org/10.1037/a0037123 step_tutoring/MANL2014_its_meta.pdf 230851 e6d990913e57eeb7…
SteenbergenHu2013 Steenbergen-Hu, S., and Cooper, H. (2013). A meta-analysis of the effectiveness of ITS on K-12 students’ mathematical learning. J Educ Psychol 105(4), 970-987. https://doi.org/10.1037/a0032447 step_tutoring/steenbergenhu2013_its_k12math.pdf 147055 0195a8600ab140a9…
KulikFletcher2012 Kulik, J. A., and Fletcher, J. D. (2012). Effectiveness of intelligent tutoring systems. IDA Document D-4664. https://www.ida.org/-/media/feature/publications/e/ef/effectiveness-of-intelligent-tutoring-systems/d-4664.ashx step_tutoring/KF2016_its_meta.pdf 617323 023577255d7a2b08…
Koedinger2012 Koedinger, K. R., Corbett, A. T., and Perfetti, C. (2012). The Knowledge-Learning-Instruction framework. Cognitive Science 36(5), 757-798. https://doi.org/10.1111/j.1551-6709.2012.01245.x step_tutoring/koedinger2012_kli.pdf 800334 7f478239b27c6480…
Koedinger2023 Koedinger, K. R., Carvalho, P. F., Liu, R., and McLaughlin, E. A. (2023). An astonishing regularity in student learning rate. PNAS 120(13), e2221311120. https://doi.org/10.1073/pnas.2221311120 step_tutoring/koedinger2023_learning_rate.xml 148718 2c623c204db11214…
Catrambone1998 Catrambone, R. (1998). The subgoal learning model. J Exp Psychol: General 127(4), 355-376. https://doi.org/10.1037/0096-3445.127.4.355 step_tutoring/catrambone1998_subgoal.pdf 2073162 a244d3389091c2e3…
Margulieux2016ICLS Margulieux, L. E., Morrison, B. B., Guzdial, M., and Catrambone, R. (2016). Training learners to self-explain. ICLS 2016 Proceedings Vol. 1. https://hdl.handle.net/20.500.14694/10111 step_tutoring/margulieux2016_selfexplain_training.pdf 908223 5e8737bd81392d2d…
Renkl2000 Renkl, A., Atkinson, R. K., and Maier, U. H. (2000). From example study to problem solving: Smooth transitions help learning. Freiburg Research Report 140. https://www.psycharchives.org/handle/20.500.11780/196 step_tutoring/renkl2000_smooth_transitions_report.pdf 50976 4c12506d2e27508e…
Kalyuga2007 Kalyuga, S. (2007). Expertise reversal effect and its implications for learner-tailored instruction. Educ Psychol Rev 19, 509-539. https://doi.org/10.1007/s10648-007-9054-3 step_tutoring/kalyuga2007_reversal_review.pdf 385775 acbd290d5478168a…
Chi1989 Chi, M. T. H., Bassok, M., Lewis, M. W., Reimann, P., and Glaser, R. (1989). Self-explanations. Cognitive Science 13, 145-182. https://doi.org/10.1207/s15516709cog1302_1 step_tutoring/chi1989_selfexpl.pdf 2749420 65506f4da574c4ff…
Bisra2018 Bisra, K., Liu, Q., Nesbit, J. C., Salimi, F., and Winne, P. H. (2018). Inducing self-explanation: a meta-analysis. Educ Psychol Rev 30, 703-725. https://doi.org/10.1007/s10648-018-9434-x step_tutoring/bisra2018_selfexpl_meta.pdf 545214 82efb34db4ce6db0…
Costa2022 Costa, J. M., Miranda, G., and Melo, M. (2022). The 4C/ID model: A meta-analysis on use and effect. Learning Environments Research 25(2), 445-463. https://doi.org/10.1007/s10984-021-09373-y step_tutoring/costa2022_4cid_meta.pdf 1237041 c3f52fa8e01075e7…
DocktorMestre2014 Docktor, J. L., and Mestre, J. P. (2014). Synthesis of discipline-based education research in physics. PRST-PER 10, 020119. https://doi.org/10.1103/PhysRevSTPER.10.020119 step_tutoring/docktor2014_per_synthesis.pdf 769551 5fb26057bd5e8484…
Singh2023 Singh, C., Maries, A., Heller, K., and Heller, P. (2023). Instructional strategies that foster effective problem-solving. arXiv:2304.05585. https://arxiv.org/abs/2304.05585 step_tutoring/maries2023_ps_strategies_arxiv.pdf 620278 1a2313c3f2df5789…
Pardos2024 Pardos, Z. A., and Bhandari, S. (2024). ChatGPT-generated help produces learning gains equivalent to human tutor-authored help on mathematics skills. PLOS ONE 19(5), e0304013. https://doi.org/10.1371/journal.pone.0304013 ai_authoring/pardos2024_chatgpt_hints.pdf 1308462 1525207b57c6f4f3…

Not obtained (leads, not references):

  • Kulik and Fletcher 2016, RER 86(1). Paywalled; the 2012 IDA report was used instead.
  • Steenbergen-Hu and Cooper 2014, J Educ Psychol 106(2), college ITS. No open copy found.
  • Margulieux and Catrambone 2016, Learning and Instruction 42. The GSU repository returned a different paper.
  • Margulieux, Morrison and Decker 2020, IJ STEM Education 7:19. Open access, but the publisher blocked automated download and the Wayback copy was truncated at 1 MB. Worth opening by hand.
  • Atkinson, Renkl and Merrill 2003, J Educ Psychol 95(4). No open copy found.
  • Renkl and Atkinson 2003, Educational Psychologist 38(1); Renkl et al. 2002, J Exp Educ. The 2000 Freiburg report was used instead.
  • Sweller and Cooper 1985, Cognition and Instruction 2(1). No open copy found.
  • Chi et al. 1994, Cognitive Science 18. Not obtained.
  • Heller, Keith and Anderson 1992 and Heller and Hollabaugh 1992, AJP 60(7). No open copy found; used only through secondary summaries.
  • Barbieri et al. 2023 worked-example meta-analysis, Educ Psychol Rev 35:11. Publisher PDF not retrieved.
  • The sci-hub fallback was refused by this session’s permission system and was not retried.

How good is AI at writing lessons, questions, hints and worked solutions? (ai_authoring)

Section titled “How good is AI at writing lessons, questions, hints and worked solutions? (ai_authoring)”
Key Citation Source URL Archived file Bytes SHA-256
arora2023 Arora, D., Singh, H. G., and Mausam (2023). Have LLMs advanced enough? A challenging problem solving benchmark for large language models. arXiv:2305.15074. https://arxiv.org/abs/2305.15074 ai_authoring/arora2023_jeebench.pdf 5515192 8a3a1d92e3da326f…
mukherjee2025 Mukherjee, A., and Ghosh, S. (2025). mmJEE-Eval: A bilingual multimodal benchmark for evaluating scientific reasoning in vision-language models. arXiv:2511.09339. https://arxiv.org/abs/2511.09339 ai_authoring/mukherjee2025_mmjee.pdf 1868408 191f8914c93f6bcb…
kortemeyer2023 Kortemeyer, G. (2023). Could an artificial-intelligence agent pass an introductory physics course? arXiv:2301.12127. https://arxiv.org/abs/2301.12127 ai_authoring/kortemeyer2023_physics_course.pdf 3382093 2f67a83965b7d6f8…
kieser2023 Kieser, F., Wulff, P., Kuhn, J., and Kuchemann, S. (2023). Educational data augmentation in physics education research using ChatGPT. Phys. Rev. PER 19, 020150. https://doi.org/10.1103/PhysRevPhysEducRes.19.020150 ai_authoring/kieser2023_prper_fci_synthetic.pdf 467772 1dfc113fabbf884a…
pardos2024 Pardos, Z. A., and Bhandari, S. (2024). ChatGPT-generated help produces learning gains equivalent to human tutor-authored help on mathematics skills. PLOS ONE 19(5): e0304013. https://doi.org/10.1371/journal.pone.0304013 ai_authoring/pardos2024_chatgpt_hints.pdf 1308462 1525207b57c6f4f3…
learnlm2025 LearnLM Team, Google, and Eedi (2025). AI tutoring can safely and effectively support students: An exploratory RCT in UK classrooms. arXiv:2512.23633. https://arxiv.org/abs/2512.23633 ai_authoring/learnlm2025_eedi_rct.pdf 4228199 a0ee40ce7e3b52a7…
scarlatos2024 Scarlatos, A., Smith, D., Woodhead, S., and Lan, A. (2024). Improving the validity of automatically generated feedback via reinforcement learning. AIED 2024. arXiv:2403.01304. https://arxiv.org/abs/2403.01304 ai_authoring/scarlatos2024_feedback_rl.pdf 217551 f573ad113173f81d…
feng2024 Feng, W., Lee, J., McNichols, H., Scarlatos, A., Smith, D., Woodhead, S., Otero Ornelas, N., and Lan, A. (2024). Exploring automated distractor generation for math multiple-choice questions via large language models. arXiv:2404.02124. https://arxiv.org/abs/2404.02124 ai_authoring/feng2024_distractors.pdf 593867 5ba4e2390d45a468…
fernandez2024 Fernandez, N., Scarlatos, A., Feng, W., Woodhead, S., and Lan, A. (2024). DiVERT: Distractor generation with variational errors represented as text for math multiple-choice questions. arXiv:2406.19356. https://arxiv.org/abs/2406.19356 ai_authoring/fernandez2024_divert.pdf 686704 813d2bd4ee12458f…
bitew2023 Bitew, S. K., Deleu, J., Develder, C., and Demeester, T. (2023). Distractor generation for multiple-choice questions with predictive prompting and large language models. arXiv:2307.16338. https://arxiv.org/abs/2307.16338 ai_authoring/bitew2023_distractors.pdf 373053 21002f8e89f9adb6…
doughty2024 Doughty, J., Wan, Z., Bompelli, A., et al. (2024). A comparative study of AI-generated (GPT-4) and human-crafted MCQs in programming education. ACE 2024. https://doi.org/10.1145/3636243.3636256 ai_authoring/doughty2024_mcq_gpt4.pdf 909946 d162c7e8a2f17f6d…
kuchemann2024 Kuchemann, S., Rau, M., Schmidt, A., and Kuhn, J. (2024). ChatGPT’s quality: Reliability and validity of concept inventory items. Frontiers in Psychology 15: 1426209. https://doi.org/10.3389/fpsyg.2024.1426209 ai_authoring/kuchemann2024_frontiers_ci_items.pdf 1172423 82aafe2ca15d4aba…
muszynski2025 Muszynski, M., Plisiecki, H., Pokropek, A., and Zoltak, T. (2025). Using large language models for automatic item generation: Development and validation for TIMSS Grade 4. IEA R&D final report. https://www.iea.nl/sites/default/files/2025-10/Muszy%C5%84ski%20AIG%20LLM%20Report.pdf ai_authoring/muszynski2025_iea_aig.pdf 3285491 3e8f492442b07204…
geisler2026 Geisler, T., and Kortemeyer, G. (2026). When AI evaluates its own work: Validating learner-initiated, AI-generated physics practice problems. Phys. Rev. PER 22, 010134. https://doi.org/10.1103/9hh9-vt4d ai_authoring/prper2026_9hh9.pdf 2897583 895a5bb47f0a9877…
yaneva2024 Yaneva, V., North, K., Baldwin, P., Ha, L. A., Rezayi, S., Zhou, Y., Ray Choudhury, S., Harik, P., and Clauser, B. (2024). Findings from the first shared task on automated prediction of difficulty and response time for multiple-choice questions. BEA 2024. https://aclanthology.org/2024.bea-1.39.pdf ai_authoring/yaneva2024_bea_difficulty.pdf 155898 bac20ab885a29649…
li2025 Li, M., Chen, H., Xiao, Y., Chen, J., Jiao, H., and Zhou, T. (2025). Can LLMs estimate student struggles? Human-AI difficulty alignment with proficiency simulation for item difficulty prediction. arXiv:2512.18880. https://arxiv.org/abs/2512.18880 ai_authoring/misalign2025_difficulty.pdf 8370418 5a18a5360ec8c11d…
acquaye2026 Acquaye, C., Huang, Y. T., Carpuat, M., and Rudinger, R. (2026). Take out your calculators: Estimating the real difficulty of question items with LLM student simulations. arXiv:2601.09953. https://arxiv.org/abs/2601.09953 ai_authoring/takeout2026_difficulty_sim.pdf 3119462 8582e2cabd738fab…
crossley2026 Crossley, S. A., Rittle-Johnson, B., Adler, R., Burleigh, L., Durkin, K., King, J., and Benner, M. (2026). Automated approaches for scoring math misunderstandings in student self-explanations. AIME-Con 2026, pp. 297-302. https://aclanthology.org/2026.aimecon-main.33.pdf ai_authoring/aimecon2026_33.pdf 296668 caf1fb340c4e517c…
gupta2025 Gupta, V., Pal Chowdhury, S., Zouhar, V., Rooein, D., and Sachan, M. (2025). Are large language models for education reliable for all languages? arXiv:2504.17720. https://arxiv.org/abs/2504.17720 ai_authoring/eth2025_multilingual_edu_tasks.pdf 714169 86fafaec434759fd…
roy2024 Roy, P., Poet, H., Staunton, R., Aston, K., and Thomas, D. (2024). ChatGPT in lesson preparation: A Teacher Choices trial. EEF / NFER. https://files.eric.ed.gov/fulltext/ED680921.pdf ai_authoring/roy2024_eef_chatgpt_lesson_prep.pdf 1986148 adc5d7759f7f7702…
roy2026 Roy, P., Poet, H., Staunton, R., Aston, K., Thomas, D., and Styles, B. (2026). Lesson planning using AI lesson assistant, Aila: A Teacher Choices trial. EEF / NFER, October 2026. https://d2tic4wvo1iusb.cloudfront.net/production/documents/projects/aila-lesson-planning_teacher-choices_evaluation-report.pdf ai_authoring/eef2026_aila_trial.pdf 3895453 726e0ea02324b8b0…
clark2024 Clark, H.-B., Dowland, M., Benton, L., Budai, R., Keskin, I. K., Searle, E., Gregory, M., Hodierne, M., Gayne, W., and Roberts, J. (2024). Auto-evaluation: A critical measure in driving improvements in quality and safety of AI-generated lesson resources. MIT Open Learning AI + Open Education (arXiv:2502.10410). https://aiopeneducation.pubpub.org/pub/i36sncz8 ai_authoring/clark2025_oak_autoeval.pdf 580653 5e3020ffd468face…
eedi2025blog Eedi (2025). From wrong answers to real insights: How we used a Kaggle challenge to map student misconceptions. Blog. https://www.eedi.com/news/from-wrong-answers-to-real-insights-how-we-used-a-kaggle-challenge-to-map-student-misconceptions ai_authoring/eedi2025_kaggle_blog.html 30533 4065a4f9941f6b62…

Not obtained (leads, not references):

  • ByteDance Seed technical report on LLMs taking JEE Advanced 2025: only press and blog coverage found, so the primary report could not be checked.
  • Kaggle Eedi ‘Mining Misconceptions in Mathematics’ leaderboard and winning write-ups: Kaggle pages were not retrieved, and Eedi’s blog gives no score.
  • ImpactEd 2024-25 evaluation of Oak National Academy: seen only in search results.
  • arXiv:2602.00034, Synthetic student responses for IRT difficulty estimation: authors not checked, and the figure was seen only in a search summary.
  • arXiv:2602.16467, IndicEval (UPSC/JEE/NEET questions in English and Hindi): not downloaded. This is the best open lead for Hindi.
  • Maity et al. 2024 (arXiv:2405.11579) and IndicGenBench (arXiv:2404.16816): skimmed but not cited and not archived, because they use old models or test general generation tasks.
  • The EEF project page blocked direct access (HTTP 403). The Aila report PDF link was found through the Wayback copy and then downloaded directly.

Designing a lesson around a hard problem: physics education research

Section titled “Designing a lesson around a hard problem: physics education research”
Key Citation Source URL Archived file Bytes SHA-256
hake1998 Hake, R. R. 1998. Interactive-engagement versus traditional methods: A six-thousand-student survey of mechanics test data for introductory physics courses. American Journal of Physics 66(1), 64-74. doi:10.1119/1.18809 https://web.mit.edu/jrankin/www/Active_Learning/hake_active_phys.pdf lesson_design/hake1998_ie.pdf 223774 86ae238ffe122c38…
crouch2001 Crouch, C. H., and Mazur, E. 2001. Peer Instruction: Ten years of experience and results. American Journal of Physics 69(9), 970-977. doi:10.1119/1.1374249 https://ctne.fct.unl.pt/pluginfile.php/256/mod_data/content/4180/peer_instruction.pdf lesson_design/crouch2001_pi.pdf 289692 d83b6d7b95058353…
deslauriers2011 Deslauriers, L., Schelew, E., and Wieman, C. 2011. Improved learning in a large-enrollment physics class. Science 332(6031), 862-864. doi:10.1126/science.1201783 https://cetl.uni.edu/sites/default/files/improved_learning_in_a_large_enrollment_physics_class.pdf lesson_design/deslauriers2011_science.pdf 581250 2fdca5a89b872fe1…
deslauriers2019 Deslauriers, L., McCarty, L. S., Miller, K., Callaghan, K., and Kestin, G. 2019. Measuring actual learning versus feeling of learning in response to being actively engaged in the classroom. PNAS 116(39), 19251-19257. doi:10.1073/pnas.1821936116 https://www.ebi.ac.uk/europepmc/webservices/rest/PMC6765278/fullTextXML lesson_design/deslauriers2019_pnas.xml 88550 7b3d55bb9ee09194…
freeman2014 Freeman, S., et al. 2014. Active learning increases student performance in science, engineering, and mathematics. PNAS 111(23), 8410-8415. doi:10.1073/pnas.1319030111 https://cdn.serc.carleton.edu/files/nagt/profdev/twp/sanbernardino/freeman_et_al._2014.pdf lesson_design/freeman2014_pnas.pdf 3600062 5e37e17c751c831a…
mcdermott2001 McDermott, L. C. 2001. Oersted Medal Lecture 2001: Physics education research, the key to student learning. American Journal of Physics 69(11), 1127-1137. doi:10.1119/1.1389280 (read in UW PEG selected-readings packet, which also reprints Wosilait et al. 1998) https://aapt.org/Conferences/newfaculty/upload/PEG-papers-16-6-for-e-distribution.pdf lesson_design/mcdermott2001_oersted_packet.pdf 4509496 08df5bca53a3b5a9…
etkina2007 Etkina, E., and Van Heuvelen, A. 2007. Investigative Science Learning Environment: A science process approach to learning physics. PER Reviews vol. 1. https://www.per-central.org/per_reviews/media/volume1/ISLE-2007.pdf lesson_design/etkina2007_isle.pdf 1242299 671df696a8e9f6d2…
schwartz1998 Schwartz, D. L., and Bransford, J. D. 1998. A time for telling. Cognition and Instruction 16(4), 475-522. doi:10.1207/s1532690xci1604_4 https://www.wright.edu/sites/www.wright.edu/files/uploads/2017/Feb/event/Schwartz_Bransford_1998_TimeForTelling.pdf lesson_design/schwartz1998_telling.pdf 3203305 2097bb4097bbdb22…
schwartz2011 Schwartz, D. L., Chase, C. C., Oppezzo, M. A., and Chin, D. B. 2011. Practicing versus inventing with contrasting cases. Journal of Educational Psychology 103(4), 759-775. doi:10.1037/a0025140 https://aaalab.stanford.edu/assets/papers/2011/Practicing_versus_inventing.pdf lesson_design/schwartz2011_contrasting.pdf 1735943 c3b46b73955e7c11…
kapurroll2023 Kapur, M., and Roll, I. 2023. Productive failure. In In Their Own Words, APA Division 2. https://www.unh.edu/teaching-learning-resource-hub/sites/default/files/media/2023-06/itow-productive-failure-kapor.pdf lesson_design/kapurroll2023_pf_chapter.pdf 416251 6e397e69a5ec2702…
kirschner2006 Kirschner, P. A., Sweller, J., and Clark, R. E. 2006. Why minimal guidance during instruction does not work. Educational Psychologist 41(2), 75-86. doi:10.1207/s15326985ep4102_1 https://www.davidlewisphd.com/courses/EDD8121/readings/2006-Kirschner_et_al.pdf lesson_design/kirschner2006_minimal.pdf 175718 be00580b2eaeb677…
alfieri2011 Alfieri, L., Brooks, P. J., Aldrich, N. J., and Tenenbaum, H. R. 2011. Does discovery-based instruction enhance learning? Journal of Educational Psychology 103(1), 1-18. doi:10.1037/a0021017 https://www.fisme.science.uu.nl/publicaties/literatuur/2011_alfieri_discovery_learning.pdf lesson_design/alfieri2011_discovery.pdf 155044 163a29d3de4de6d4…
chen2016 Chen, O., Kalyuga, S., and Sweller, J. 2016. When instructional guidance is needed. Educational and Developmental Psychologist 33(2), 149-162. doi:10.1017/edp.2016.16 (accepted manuscript) https://ndownloader.figshare.com/files/22174674 lesson_design/chen2016_guidance.pdf 280667 c6703e396b68b06c…
rittlejohnson2001 Rittle-Johnson, B., Siegler, R. S., and Alibali, M. W. 2001. Developing conceptual understanding and procedural skill in mathematics: An iterative process. Journal of Educational Psychology 93(2), 346-362. doi:10.1037/0022-0663.93.2.346 https://alibali.psych.wisc.edu/wp-content/uploads/sites/371/2018/02/Rittle-JohnsonSieglerAlibali2001.pdf lesson_design/rittlejohnson2001_iterative.pdf 2784387 b727f887da126815…
hestenes1992 Hestenes, D., Wells, M., and Swackhamer, G. 1992. Force Concept Inventory. The Physics Teacher 30(3), 141-158. doi:10.1119/1.2343497 https://gwern.net/doc/science/physics/1992-hestenes.pdf lesson_design/hestenes1992_fci.pdf 4463737 a53aac988ae1e7ee…

Not obtained (leads, not references):

  • Sinha and Kapur 2021 (RER, CC BY): the SAGE PDF hit a bot-check page and the ETH Research Collection bitstream returned ‘Rate Limited’ on four tries. Its figures appear only via the author’s own chapter, Kapur and Roll 2023, and are labelled that way. Retry the ETH link later and archive it, since it is the main productive-failure meta-analysis.
  • Loibl, Roll and Rummel 2017; Rittle-Johnson, Schneider and Star 2015; Ashman, Kalyuga and Sweller 2020; Kapur 2014; Hmelo-Silver et al. 2007; Smith et al. 2009; Etkina et al. 2010; Shaffer and McDermott 1992: closed access, with no open copy found through Unpaywall, OpenAlex or Semantic Scholar.
  • Per the session’s permission policy, I did not use the sci-hub fallback or retry the SAGE page with custom headers. Both attempts were blocked as walled-content or bot-check circumvention.

170 opened sources across 8 strands. All have an archived copy except avanti_retest_query, which is Avanti’s own BigQuery aggregate, rerunnable from the warehouse. policy_safety/ holds the Supreme Court judgment the synthesis added.