{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CRJGZJRVA4U55HUFSZG3EF6QKK","short_pith_number":"pith:CRJGZJRV","schema_version":"1.0","canonical_sha256":"14526ca6350729de9e85964db217d052a8c047fbbd2bab3fe52d7456cb101820","source":{"kind":"arxiv","id":"2504.14928","version":3},"attestation_state":"computed","paper":{"title":"EducationQ: Evaluating LLMs' Teaching Capabilities Through Multi-Agent Dialogue Framework","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CE","cs.CL","cs.CY","cs.HC"],"primary_cat":"cs.AI","authors_text":"Rongkeng Liang, Yao Shi, Yong Xu","submitted_at":"2025-04-21T07:48:20Z","abstract_excerpt":"Large language models (LLMs) increasingly serve as educational tools, yet evaluating their teaching capabilities remains challenging due to the resource-intensive, context-dependent, and methodologically complex nature of teacher-student interactions. We introduce EducationQ, a multi-agent dialogue framework that efficiently assesses teaching capabilities through simulated dynamic educational scenarios, featuring specialized agents for teaching, learning, and evaluation. Testing 14 LLMs across major AI Organizations (OpenAI, Meta, Google, Anthropic, and others) on 1,498 questions spanning 13 d"},"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":"2504.14928","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-21T07:48:20Z","cross_cats_sorted":["cs.CE","cs.CL","cs.CY","cs.HC"],"title_canon_sha256":"d091e2db7fe772ed04b554db460d4bce4e2e0f466549658064a9c1406319ec73","abstract_canon_sha256":"e38c331dfa86e54568ab6f9fc1764919e45cf0ce254393fe1de2d3ba50c0eeab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:57.532826Z","signature_b64":"ND8XQ1+lV5p7rhrulCNw+/AwpbyD/B0Px+G/c6+7+UMCU63L0BzyvfzQOR1Sir+Yke+vGNU09mv0hD53m2u/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14526ca6350729de9e85964db217d052a8c047fbbd2bab3fe52d7456cb101820","last_reissued_at":"2026-07-05T11:45:57.532280Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:57.532280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EducationQ: Evaluating LLMs' Teaching Capabilities Through Multi-Agent Dialogue Framework","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CE","cs.CL","cs.CY","cs.HC"],"primary_cat":"cs.AI","authors_text":"Rongkeng Liang, Yao Shi, Yong Xu","submitted_at":"2025-04-21T07:48:20Z","abstract_excerpt":"Large language models (LLMs) increasingly serve as educational tools, yet evaluating their teaching capabilities remains challenging due to the resource-intensive, context-dependent, and methodologically complex nature of teacher-student interactions. We introduce EducationQ, a multi-agent dialogue framework that efficiently assesses teaching capabilities through simulated dynamic educational scenarios, featuring specialized agents for teaching, learning, and evaluation. Testing 14 LLMs across major AI Organizations (OpenAI, Meta, Google, Anthropic, and others) on 1,498 questions spanning 13 d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14928","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/2504.14928/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":"2504.14928","created_at":"2026-07-05T11:45:57.532351+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.14928v3","created_at":"2026-07-05T11:45:57.532351+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14928","created_at":"2026-07-05T11:45:57.532351+00:00"},{"alias_kind":"pith_short_12","alias_value":"CRJGZJRVA4U5","created_at":"2026-07-05T11:45:57.532351+00:00"},{"alias_kind":"pith_short_16","alias_value":"CRJGZJRVA4U55HUF","created_at":"2026-07-05T11:45:57.532351+00:00"},{"alias_kind":"pith_short_8","alias_value":"CRJGZJRV","created_at":"2026-07-05T11:45:57.532351+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CRJGZJRVA4U55HUFSZG3EF6QKK","json":"https://pith.science/pith/CRJGZJRVA4U55HUFSZG3EF6QKK.json","graph_json":"https://pith.science/api/pith-number/CRJGZJRVA4U55HUFSZG3EF6QKK/graph.json","events_json":"https://pith.science/api/pith-number/CRJGZJRVA4U55HUFSZG3EF6QKK/events.json","paper":"https://pith.science/paper/CRJGZJRV"},"agent_actions":{"view_html":"https://pith.science/pith/CRJGZJRVA4U55HUFSZG3EF6QKK","download_json":"https://pith.science/pith/CRJGZJRVA4U55HUFSZG3EF6QKK.json","view_paper":"https://pith.science/paper/CRJGZJRV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.14928&json=true","fetch_graph":"https://pith.science/api/pith-number/CRJGZJRVA4U55HUFSZG3EF6QKK/graph.json","fetch_events":"https://pith.science/api/pith-number/CRJGZJRVA4U55HUFSZG3EF6QKK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CRJGZJRVA4U55HUFSZG3EF6QKK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CRJGZJRVA4U55HUFSZG3EF6QKK/action/storage_attestation","attest_author":"https://pith.science/pith/CRJGZJRVA4U55HUFSZG3EF6QKK/action/author_attestation","sign_citation":"https://pith.science/pith/CRJGZJRVA4U55HUFSZG3EF6QKK/action/citation_signature","submit_replication":"https://pith.science/pith/CRJGZJRVA4U55HUFSZG3EF6QKK/action/replication_record"}},"created_at":"2026-07-05T11:45:57.532351+00:00","updated_at":"2026-07-05T11:45:57.532351+00:00"}