{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WBPNAK5FICICDDAJVQ26EHU7VI","short_pith_number":"pith:WBPNAK5F","schema_version":"1.0","canonical_sha256":"b05ed02ba54090218c09ac35e21e9faa02f5c0ffc8e0468b05244ecc27c22ca9","source":{"kind":"arxiv","id":"2211.11772","version":2},"attestation_state":"computed","paper":{"title":"The NCTE Transcripts: A Dataset of Elementary Math Classroom Transcripts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dorottya Demszky, Heather Hill","submitted_at":"2022-11-21T19:00:01Z","abstract_excerpt":"Classroom discourse is a core medium of instruction - analyzing it can provide a window into teaching and learning as well as driving the development of new tools for improving instruction. We introduce the largest dataset of mathematics classroom transcripts available to researchers, and demonstrate how this data can help improve instruction. The dataset consists of 1,660 45-60 minute long 4th and 5th grade elementary mathematics observations collected by the National Center for Teacher Effectiveness (NCTE) between 2010-2013. The anonymized transcripts represent data from 317 teachers across "},"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":"2211.11772","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-21T19:00:01Z","cross_cats_sorted":[],"title_canon_sha256":"2318013dae2083cecb8c5ff672335fba9a1e197358b98c138d20a51da17e09c4","abstract_canon_sha256":"06a62cab57273b71031367a0e63c844aa29109747556a6c3ca8e44cd63595138"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:37.398942Z","signature_b64":"yFam9AnEUf24JXfR9IUM6UvoI8m3l9chQRn+R3SsXNRKpp2yvJ7f5q0MBUyXs4sTz7S6+vuvegfCiQFSp7FwCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b05ed02ba54090218c09ac35e21e9faa02f5c0ffc8e0468b05244ecc27c22ca9","last_reissued_at":"2026-07-05T06:13:37.398438Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:37.398438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The NCTE Transcripts: A Dataset of Elementary Math Classroom Transcripts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dorottya Demszky, Heather Hill","submitted_at":"2022-11-21T19:00:01Z","abstract_excerpt":"Classroom discourse is a core medium of instruction - analyzing it can provide a window into teaching and learning as well as driving the development of new tools for improving instruction. We introduce the largest dataset of mathematics classroom transcripts available to researchers, and demonstrate how this data can help improve instruction. The dataset consists of 1,660 45-60 minute long 4th and 5th grade elementary mathematics observations collected by the National Center for Teacher Effectiveness (NCTE) between 2010-2013. The anonymized transcripts represent data from 317 teachers across "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.11772","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/2211.11772/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":"2211.11772","created_at":"2026-07-05T06:13:37.398501+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.11772v2","created_at":"2026-07-05T06:13:37.398501+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.11772","created_at":"2026-07-05T06:13:37.398501+00:00"},{"alias_kind":"pith_short_12","alias_value":"WBPNAK5FICIC","created_at":"2026-07-05T06:13:37.398501+00:00"},{"alias_kind":"pith_short_16","alias_value":"WBPNAK5FICICDDAJ","created_at":"2026-07-05T06:13:37.398501+00:00"},{"alias_kind":"pith_short_8","alias_value":"WBPNAK5F","created_at":"2026-07-05T06:13:37.398501+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12422","citing_title":"Creating and Evaluating K-12 GenAI Assessment Graders Through Context Engineering","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30673","citing_title":"TeachObs: A Human-Validated Benchmark for Multimodal Teaching Observation and Model Evaluation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2403.03920","citing_title":"Enhancing Instructional Quality: Leveraging Computer-Assisted Textual Analysis to Generate In-Depth Insights from Educational Artifacts","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02585","citing_title":"Mitigating LLM biases toward spurious social contexts using direct preference optimization","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WBPNAK5FICICDDAJVQ26EHU7VI","json":"https://pith.science/pith/WBPNAK5FICICDDAJVQ26EHU7VI.json","graph_json":"https://pith.science/api/pith-number/WBPNAK5FICICDDAJVQ26EHU7VI/graph.json","events_json":"https://pith.science/api/pith-number/WBPNAK5FICICDDAJVQ26EHU7VI/events.json","paper":"https://pith.science/paper/WBPNAK5F"},"agent_actions":{"view_html":"https://pith.science/pith/WBPNAK5FICICDDAJVQ26EHU7VI","download_json":"https://pith.science/pith/WBPNAK5FICICDDAJVQ26EHU7VI.json","view_paper":"https://pith.science/paper/WBPNAK5F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.11772&json=true","fetch_graph":"https://pith.science/api/pith-number/WBPNAK5FICICDDAJVQ26EHU7VI/graph.json","fetch_events":"https://pith.science/api/pith-number/WBPNAK5FICICDDAJVQ26EHU7VI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WBPNAK5FICICDDAJVQ26EHU7VI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WBPNAK5FICICDDAJVQ26EHU7VI/action/storage_attestation","attest_author":"https://pith.science/pith/WBPNAK5FICICDDAJVQ26EHU7VI/action/author_attestation","sign_citation":"https://pith.science/pith/WBPNAK5FICICDDAJVQ26EHU7VI/action/citation_signature","submit_replication":"https://pith.science/pith/WBPNAK5FICICDDAJVQ26EHU7VI/action/replication_record"}},"created_at":"2026-07-05T06:13:37.398501+00:00","updated_at":"2026-07-05T06:13:37.398501+00:00"}