{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:L7VODS5OQ52SNMZJVGKAHAJBOU","short_pith_number":"pith:L7VODS5O","schema_version":"1.0","canonical_sha256":"5feae1cbae877526b329a9940381217510a18e6b07ecff7cdc0e7bd40bbf868d","source":{"kind":"arxiv","id":"2402.05000","version":3},"attestation_state":"computed","paper":{"title":"Pedagogical Alignment of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kangqi Ni, Richard G. Baraniuk, Sapana Chaudhary, Shashank Sonkar","submitted_at":"2024-02-07T16:15:59Z","abstract_excerpt":"Large Language Models (LLMs), when used in educational settings without pedagogical fine-tuning, often provide immediate answers rather than guiding students through the problem-solving process. This approach falls short of pedagogically best practices and limits their effectiveness as educational tools. We term the objective of training LLMs to emulate effective teaching strategies as `pedagogical alignment.' In this paper, we investigate Learning from Human Preferences (LHP) algorithms to achieve this alignment objective. A key challenge in this process is the scarcity of high-quality prefer"},"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":"2402.05000","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-07T16:15:59Z","cross_cats_sorted":[],"title_canon_sha256":"c135f8f17ea2043bf6cacf206c10918ce4ea7d106af8e4b156ec177abcc69a94","abstract_canon_sha256":"b4e95d29c8668837d0ecdc0a2ff7011731125b83a42b07968d9076893af54f62"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:12.455955Z","signature_b64":"r3ndRPn2R7XEaIZYhWypZUpLZ98YIjDM+cvTz2m3dj81QOHFdJCM+1bql+8zxbtRlmpba2vwJlaU0rcY4WKLCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5feae1cbae877526b329a9940381217510a18e6b07ecff7cdc0e7bd40bbf868d","last_reissued_at":"2026-07-05T09:16:12.455481Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:12.455481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pedagogical Alignment of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kangqi Ni, Richard G. Baraniuk, Sapana Chaudhary, Shashank Sonkar","submitted_at":"2024-02-07T16:15:59Z","abstract_excerpt":"Large Language Models (LLMs), when used in educational settings without pedagogical fine-tuning, often provide immediate answers rather than guiding students through the problem-solving process. This approach falls short of pedagogically best practices and limits their effectiveness as educational tools. We term the objective of training LLMs to emulate effective teaching strategies as `pedagogical alignment.' In this paper, we investigate Learning from Human Preferences (LHP) algorithms to achieve this alignment objective. A key challenge in this process is the scarcity of high-quality prefer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05000","kind":"arxiv","version":3},"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/2402.05000/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":"2402.05000","created_at":"2026-07-05T09:16:12.455534+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.05000v3","created_at":"2026-07-05T09:16:12.455534+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05000","created_at":"2026-07-05T09:16:12.455534+00:00"},{"alias_kind":"pith_short_12","alias_value":"L7VODS5OQ52S","created_at":"2026-07-05T09:16:12.455534+00:00"},{"alias_kind":"pith_short_16","alias_value":"L7VODS5OQ52SNMZJ","created_at":"2026-07-05T09:16:12.455534+00:00"},{"alias_kind":"pith_short_8","alias_value":"L7VODS5O","created_at":"2026-07-05T09:16:12.455534+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.08386","citing_title":"CoDAE: Adapting Large Language Models for Education via Chain-of-Thought Data Augmentation","ref_index":7517,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L7VODS5OQ52SNMZJVGKAHAJBOU","json":"https://pith.science/pith/L7VODS5OQ52SNMZJVGKAHAJBOU.json","graph_json":"https://pith.science/api/pith-number/L7VODS5OQ52SNMZJVGKAHAJBOU/graph.json","events_json":"https://pith.science/api/pith-number/L7VODS5OQ52SNMZJVGKAHAJBOU/events.json","paper":"https://pith.science/paper/L7VODS5O"},"agent_actions":{"view_html":"https://pith.science/pith/L7VODS5OQ52SNMZJVGKAHAJBOU","download_json":"https://pith.science/pith/L7VODS5OQ52SNMZJVGKAHAJBOU.json","view_paper":"https://pith.science/paper/L7VODS5O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.05000&json=true","fetch_graph":"https://pith.science/api/pith-number/L7VODS5OQ52SNMZJVGKAHAJBOU/graph.json","fetch_events":"https://pith.science/api/pith-number/L7VODS5OQ52SNMZJVGKAHAJBOU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L7VODS5OQ52SNMZJVGKAHAJBOU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L7VODS5OQ52SNMZJVGKAHAJBOU/action/storage_attestation","attest_author":"https://pith.science/pith/L7VODS5OQ52SNMZJVGKAHAJBOU/action/author_attestation","sign_citation":"https://pith.science/pith/L7VODS5OQ52SNMZJVGKAHAJBOU/action/citation_signature","submit_replication":"https://pith.science/pith/L7VODS5OQ52SNMZJVGKAHAJBOU/action/replication_record"}},"created_at":"2026-07-05T09:16:12.455534+00:00","updated_at":"2026-07-05T09:16:12.455534+00:00"}