{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:J6KJHU3E4OLGHC3GGMROENRJGQ","short_pith_number":"pith:J6KJHU3E","schema_version":"1.0","canonical_sha256":"4f9493d364e396638b663322e236293410d43aa53c0b20d13710fa2d5f98122c","source":{"kind":"arxiv","id":"2506.18710","version":3},"attestation_state":"computed","paper":{"title":"Benchmarking the Pedagogical Knowledge of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alasdair Mackintosh, Amy Waldock, Jared Lee, Mar\\'ia Jos\\'e Ogando Portela, Maxime Leli\\`evre, Meng Liu, Natalia Vald\\'es Aspillaga, Oliver G. B. Garrod, Paul Atherton, Robin A. A. Ince","submitted_at":"2025-06-23T14:49:01Z","abstract_excerpt":"Benchmarks like Massive Multitask Language Understanding (MMLU) have played a pivotal role in evaluating AI's knowledge and abilities across diverse domains. However, existing benchmarks predominantly focus on content knowledge, leaving a critical gap in assessing models' understanding of pedagogy - the method and practice of teaching. This paper introduces The Pedagogy Benchmark, a novel dataset designed to evaluate large language models on their Cross-Domain Pedagogical Knowledge (CDPK) and Special Education Needs and Disability (SEND) pedagogical knowledge. These benchmarks are built on a c"},"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":"2506.18710","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-23T14:49:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b6f62a8d6ba67e7ff319aa10a189a8db55bf7c3e4fb5c73bf1af416d5b762b85","abstract_canon_sha256":"b60a29fc92e9b0a3b50fb012ee7f3be3e262b418cbf65744b9123f7244aedec9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:02.410590Z","signature_b64":"1BUzMLX5LkCY1gu+pNbI3MnM8tf6bqEMbRJxiAWoKwAsBnwZ2w7L94HvQM8B9Qc4kizwonx3LuZZU89eIpLLAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f9493d364e396638b663322e236293410d43aa53c0b20d13710fa2d5f98122c","last_reissued_at":"2026-07-05T11:30:02.410083Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:02.410083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking the Pedagogical Knowledge of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alasdair Mackintosh, Amy Waldock, Jared Lee, Mar\\'ia Jos\\'e Ogando Portela, Maxime Leli\\`evre, Meng Liu, Natalia Vald\\'es Aspillaga, Oliver G. B. Garrod, Paul Atherton, Robin A. A. Ince","submitted_at":"2025-06-23T14:49:01Z","abstract_excerpt":"Benchmarks like Massive Multitask Language Understanding (MMLU) have played a pivotal role in evaluating AI's knowledge and abilities across diverse domains. However, existing benchmarks predominantly focus on content knowledge, leaving a critical gap in assessing models' understanding of pedagogy - the method and practice of teaching. This paper introduces The Pedagogy Benchmark, a novel dataset designed to evaluate large language models on their Cross-Domain Pedagogical Knowledge (CDPK) and Special Education Needs and Disability (SEND) pedagogical knowledge. These benchmarks are built on a c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18710","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/2506.18710/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":"2506.18710","created_at":"2026-07-05T11:30:02.410141+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.18710v3","created_at":"2026-07-05T11:30:02.410141+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18710","created_at":"2026-07-05T11:30:02.410141+00:00"},{"alias_kind":"pith_short_12","alias_value":"J6KJHU3E4OLG","created_at":"2026-07-05T11:30:02.410141+00:00"},{"alias_kind":"pith_short_16","alias_value":"J6KJHU3E4OLGHC3G","created_at":"2026-07-05T11:30:02.410141+00:00"},{"alias_kind":"pith_short_8","alias_value":"J6KJHU3E","created_at":"2026-07-05T11:30:02.410141+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.06385","citing_title":"Application-Driven Pedagogical Knowledge Optimization of Open-Source LLMs via Reinforcement Learning and Supervised Fine-Tuning","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J6KJHU3E4OLGHC3GGMROENRJGQ","json":"https://pith.science/pith/J6KJHU3E4OLGHC3GGMROENRJGQ.json","graph_json":"https://pith.science/api/pith-number/J6KJHU3E4OLGHC3GGMROENRJGQ/graph.json","events_json":"https://pith.science/api/pith-number/J6KJHU3E4OLGHC3GGMROENRJGQ/events.json","paper":"https://pith.science/paper/J6KJHU3E"},"agent_actions":{"view_html":"https://pith.science/pith/J6KJHU3E4OLGHC3GGMROENRJGQ","download_json":"https://pith.science/pith/J6KJHU3E4OLGHC3GGMROENRJGQ.json","view_paper":"https://pith.science/paper/J6KJHU3E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.18710&json=true","fetch_graph":"https://pith.science/api/pith-number/J6KJHU3E4OLGHC3GGMROENRJGQ/graph.json","fetch_events":"https://pith.science/api/pith-number/J6KJHU3E4OLGHC3GGMROENRJGQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J6KJHU3E4OLGHC3GGMROENRJGQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J6KJHU3E4OLGHC3GGMROENRJGQ/action/storage_attestation","attest_author":"https://pith.science/pith/J6KJHU3E4OLGHC3GGMROENRJGQ/action/author_attestation","sign_citation":"https://pith.science/pith/J6KJHU3E4OLGHC3GGMROENRJGQ/action/citation_signature","submit_replication":"https://pith.science/pith/J6KJHU3E4OLGHC3GGMROENRJGQ/action/replication_record"}},"created_at":"2026-07-05T11:30:02.410141+00:00","updated_at":"2026-07-05T11:30:02.410141+00:00"}