{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:N7WX2I5S2CI3EQJ26GVLPEUDSL","short_pith_number":"pith:N7WX2I5S","schema_version":"1.0","canonical_sha256":"6fed7d23b2d091b2413af1aab7928392f3c5324ec52c710871348928f3609f9a","source":{"kind":"arxiv","id":"2508.08386","version":1},"attestation_state":"computed","paper":{"title":"CoDAE: Adapting Large Language Models for Education via Chain-of-Thought Data Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ercong Nie, Hardik Ghoshal, Michael F\\\"arber, Shuzhou Yuan, William LaCroix","submitted_at":"2025-08-11T18:13:31Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly employed as AI tutors due to their scalability and potential for personalized instruction. However, off-the-shelf LLMs often underperform in educational settings: they frequently reveal answers too readily, fail to adapt their responses to student uncertainty, and remain vulnerable to emotionally manipulative prompts. To address these challenges, we introduce CoDAE, a framework that adapts LLMs for educational use through Chain-of-Thought (CoT) data augmentation. We collect real-world dialogues between students and a ChatGPT-based tutor and enrich "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2508.08386","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-11T18:13:31Z","cross_cats_sorted":[],"title_canon_sha256":"9b7a95ac65c5d694320b2328f146409f94a091b9f18d788706226d84f6fdbf88","abstract_canon_sha256":"5d4a9a1eb7cd2d34f4287d58a25335dc9166c3f180439915a36bcde3907ab427"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:27.174928Z","signature_b64":"a/QM8W5//qQwoUcHvpmwNxmuGsqGj4Av+Cb9N0xgMZKAoTjCvnwVsctL4IMWHr1NoNphd+JZDDVm61ZNNOYYDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fed7d23b2d091b2413af1aab7928392f3c5324ec52c710871348928f3609f9a","last_reissued_at":"2026-07-05T11:52:27.174311Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:27.174311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoDAE: Adapting Large Language Models for Education via Chain-of-Thought Data Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ercong Nie, Hardik Ghoshal, Michael F\\\"arber, Shuzhou Yuan, William LaCroix","submitted_at":"2025-08-11T18:13:31Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly employed as AI tutors due to their scalability and potential for personalized instruction. However, off-the-shelf LLMs often underperform in educational settings: they frequently reveal answers too readily, fail to adapt their responses to student uncertainty, and remain vulnerable to emotionally manipulative prompts. To address these challenges, we introduce CoDAE, a framework that adapts LLMs for educational use through Chain-of-Thought (CoT) data augmentation. We collect real-world dialogues between students and a ChatGPT-based tutor and enrich "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.08386","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2508.08386/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2508.08386","created_at":"2026-07-05T11:52:27.174412+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.08386v1","created_at":"2026-07-05T11:52:27.174412+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.08386","created_at":"2026-07-05T11:52:27.174412+00:00"},{"alias_kind":"pith_short_12","alias_value":"N7WX2I5S2CI3","created_at":"2026-07-05T11:52:27.174412+00:00"},{"alias_kind":"pith_short_16","alias_value":"N7WX2I5S2CI3EQJ2","created_at":"2026-07-05T11:52:27.174412+00:00"},{"alias_kind":"pith_short_8","alias_value":"N7WX2I5S","created_at":"2026-07-05T11:52:27.174412+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.18660","citing_title":"Evaluating Answer Leakage Robustness of LLM Tutors against Adversarial Student Attacks","ref_index":91,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N7WX2I5S2CI3EQJ26GVLPEUDSL","json":"https://pith.science/pith/N7WX2I5S2CI3EQJ26GVLPEUDSL.json","graph_json":"https://pith.science/api/pith-number/N7WX2I5S2CI3EQJ26GVLPEUDSL/graph.json","events_json":"https://pith.science/api/pith-number/N7WX2I5S2CI3EQJ26GVLPEUDSL/events.json","paper":"https://pith.science/paper/N7WX2I5S"},"agent_actions":{"view_html":"https://pith.science/pith/N7WX2I5S2CI3EQJ26GVLPEUDSL","download_json":"https://pith.science/pith/N7WX2I5S2CI3EQJ26GVLPEUDSL.json","view_paper":"https://pith.science/paper/N7WX2I5S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.08386&json=true","fetch_graph":"https://pith.science/api/pith-number/N7WX2I5S2CI3EQJ26GVLPEUDSL/graph.json","fetch_events":"https://pith.science/api/pith-number/N7WX2I5S2CI3EQJ26GVLPEUDSL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N7WX2I5S2CI3EQJ26GVLPEUDSL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N7WX2I5S2CI3EQJ26GVLPEUDSL/action/storage_attestation","attest_author":"https://pith.science/pith/N7WX2I5S2CI3EQJ26GVLPEUDSL/action/author_attestation","sign_citation":"https://pith.science/pith/N7WX2I5S2CI3EQJ26GVLPEUDSL/action/citation_signature","submit_replication":"https://pith.science/pith/N7WX2I5S2CI3EQJ26GVLPEUDSL/action/replication_record"}},"created_at":"2026-07-05T11:52:27.174412+00:00","updated_at":"2026-07-05T11:52:27.174412+00:00"}