{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IFF6JKDUIBLBUUUTLRWX5WYVJT","short_pith_number":"pith:IFF6JKDU","schema_version":"1.0","canonical_sha256":"414be4a87440561a52935c6d7edb154ce0e700c90a1e3e2ab7e95f3d5c038bc7","source":{"kind":"arxiv","id":"2305.14536","version":2},"attestation_state":"computed","paper":{"title":"MathDial: A Dialogue Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Iryna Gurevych, Jakub Macina, Manu Kapur, Mrinmaya Sachan, Nico Daheim, Sankalan Pal Chowdhury, Tanmay Sinha","submitted_at":"2023-05-23T21:44:56Z","abstract_excerpt":"While automatic dialogue tutors hold great potential in making education personalized and more accessible, research on such systems has been hampered by a lack of sufficiently large and high-quality datasets. Collecting such datasets remains challenging, as recording tutoring sessions raises privacy concerns and crowdsourcing leads to insufficient data quality. To address this, we propose a framework to generate such dialogues by pairing human teachers with a Large Language Model (LLM) prompted to represent common student errors. We describe how we use this framework to collect MathDial, a dat"},"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":"2305.14536","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T21:44:56Z","cross_cats_sorted":[],"title_canon_sha256":"527d67fc58d149e08c123001e19a31ee8466d53f6ff3bd261018212e45896286","abstract_canon_sha256":"40444eddce40774d280a5c1b1a54fbde059f0b5607e6a81eb51a6659ba11684b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:59.154977Z","signature_b64":"8zjnMq3mnuEX6x43U3wKpCQ4NjyIW0EJ4pmoJhYYkIF5QTRuFjAXxFicTawKfRUJyd41bxUDNNCykNQEMv57CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"414be4a87440561a52935c6d7edb154ce0e700c90a1e3e2ab7e95f3d5c038bc7","last_reissued_at":"2026-07-05T07:03:59.154502Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:59.154502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MathDial: A Dialogue Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Iryna Gurevych, Jakub Macina, Manu Kapur, Mrinmaya Sachan, Nico Daheim, Sankalan Pal Chowdhury, Tanmay Sinha","submitted_at":"2023-05-23T21:44:56Z","abstract_excerpt":"While automatic dialogue tutors hold great potential in making education personalized and more accessible, research on such systems has been hampered by a lack of sufficiently large and high-quality datasets. Collecting such datasets remains challenging, as recording tutoring sessions raises privacy concerns and crowdsourcing leads to insufficient data quality. To address this, we propose a framework to generate such dialogues by pairing human teachers with a Large Language Model (LLM) prompted to represent common student errors. We describe how we use this framework to collect MathDial, a dat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14536","kind":"arxiv","version":2},"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/2305.14536/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":"2305.14536","created_at":"2026-07-05T07:03:59.154560+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14536v2","created_at":"2026-07-05T07:03:59.154560+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14536","created_at":"2026-07-05T07:03:59.154560+00:00"},{"alias_kind":"pith_short_12","alias_value":"IFF6JKDUIBLB","created_at":"2026-07-05T07:03:59.154560+00:00"},{"alias_kind":"pith_short_16","alias_value":"IFF6JKDUIBLBUUUT","created_at":"2026-07-05T07:03:59.154560+00:00"},{"alias_kind":"pith_short_8","alias_value":"IFF6JKDU","created_at":"2026-07-05T07:03:59.154560+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21502","citing_title":"Towards Pedagogically Aligned LLM Tutors for Math Mistake Remediation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2508.03085","citing_title":"When AI Evaluates Its Own Work: Validating Learner-Initiated, AI-Generated Physics Practice Problems","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IFF6JKDUIBLBUUUTLRWX5WYVJT","json":"https://pith.science/pith/IFF6JKDUIBLBUUUTLRWX5WYVJT.json","graph_json":"https://pith.science/api/pith-number/IFF6JKDUIBLBUUUTLRWX5WYVJT/graph.json","events_json":"https://pith.science/api/pith-number/IFF6JKDUIBLBUUUTLRWX5WYVJT/events.json","paper":"https://pith.science/paper/IFF6JKDU"},"agent_actions":{"view_html":"https://pith.science/pith/IFF6JKDUIBLBUUUTLRWX5WYVJT","download_json":"https://pith.science/pith/IFF6JKDUIBLBUUUTLRWX5WYVJT.json","view_paper":"https://pith.science/paper/IFF6JKDU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14536&json=true","fetch_graph":"https://pith.science/api/pith-number/IFF6JKDUIBLBUUUTLRWX5WYVJT/graph.json","fetch_events":"https://pith.science/api/pith-number/IFF6JKDUIBLBUUUTLRWX5WYVJT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IFF6JKDUIBLBUUUTLRWX5WYVJT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IFF6JKDUIBLBUUUTLRWX5WYVJT/action/storage_attestation","attest_author":"https://pith.science/pith/IFF6JKDUIBLBUUUTLRWX5WYVJT/action/author_attestation","sign_citation":"https://pith.science/pith/IFF6JKDUIBLBUUUTLRWX5WYVJT/action/citation_signature","submit_replication":"https://pith.science/pith/IFF6JKDUIBLBUUUTLRWX5WYVJT/action/replication_record"}},"created_at":"2026-07-05T07:03:59.154560+00:00","updated_at":"2026-07-05T07:03:59.154560+00:00"}