{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:PWSTSHIVOMDRNARHUEY32DTTFU","short_pith_number":"pith:PWSTSHIV","schema_version":"1.0","canonical_sha256":"7da5391d157307168227a131bd0e732d26e6cfbb793af6d9feb18ea9f710323a","source":{"kind":"arxiv","id":"1908.05441","version":1},"attestation_state":"computed","paper":{"title":"Multi-class Hierarchical Question Classification for Multiple Choice Science Exams","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dongfang Xu, Harish Tayyar Madabushi, Jaycie Martin, Oyvind Tafjord, Peter Clark, Peter Jansen, Vikas Yadav, Zhengnan Xie","submitted_at":"2019-08-15T07:00:16Z","abstract_excerpt":"Prior work has demonstrated that question classification (QC), recognizing the problem domain of a question, can help answer it more accurately. However, developing strong QC algorithms has been hindered by the limited size and complexity of annotated data available. To address this, we present the largest challenge dataset for QC, containing 7,787 science exam questions paired with detailed classification labels from a fine-grained hierarchical taxonomy of 406 problem domains. We then show that a BERT-based model trained on this dataset achieves a large (+0.12 MAP) gain compared with previous"},"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":"1908.05441","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-15T07:00:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7d4be4bebc1e13056a895601fc0d16169bf92197e4d2abcbd48f8a622fbf51d0","abstract_canon_sha256":"3bb6165e98b638fe2201c7cfed1361c96dcf82208a65891a2dbfc0fb1e3e0d67"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:56:52.007576Z","signature_b64":"7pagVxgjSJRLiTexn9zlu+3DJHqB58X8Qjf+0qqY8SIHU6F7M7/RhQmpT6/UTTivrD9k1RSYljI4Jff21UIiDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7da5391d157307168227a131bd0e732d26e6cfbb793af6d9feb18ea9f710323a","last_reissued_at":"2026-07-04T23:56:52.007163Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:56:52.007163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-class Hierarchical Question Classification for Multiple Choice Science Exams","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dongfang Xu, Harish Tayyar Madabushi, Jaycie Martin, Oyvind Tafjord, Peter Clark, Peter Jansen, Vikas Yadav, Zhengnan Xie","submitted_at":"2019-08-15T07:00:16Z","abstract_excerpt":"Prior work has demonstrated that question classification (QC), recognizing the problem domain of a question, can help answer it more accurately. However, developing strong QC algorithms has been hindered by the limited size and complexity of annotated data available. To address this, we present the largest challenge dataset for QC, containing 7,787 science exam questions paired with detailed classification labels from a fine-grained hierarchical taxonomy of 406 problem domains. We then show that a BERT-based model trained on this dataset achieves a large (+0.12 MAP) gain compared with previous"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.05441","kind":"arxiv","version":1},"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/1908.05441/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":"1908.05441","created_at":"2026-07-04T23:56:52.007220+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.05441v1","created_at":"2026-07-04T23:56:52.007220+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.05441","created_at":"2026-07-04T23:56:52.007220+00:00"},{"alias_kind":"pith_short_12","alias_value":"PWSTSHIVOMDR","created_at":"2026-07-04T23:56:52.007220+00:00"},{"alias_kind":"pith_short_16","alias_value":"PWSTSHIVOMDRNARH","created_at":"2026-07-04T23:56:52.007220+00:00"},{"alias_kind":"pith_short_8","alias_value":"PWSTSHIV","created_at":"2026-07-04T23:56:52.007220+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.05441","citing_title":"Multi-class Hierarchical Question Classification for Multiple Choice Science Exams","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PWSTSHIVOMDRNARHUEY32DTTFU","json":"https://pith.science/pith/PWSTSHIVOMDRNARHUEY32DTTFU.json","graph_json":"https://pith.science/api/pith-number/PWSTSHIVOMDRNARHUEY32DTTFU/graph.json","events_json":"https://pith.science/api/pith-number/PWSTSHIVOMDRNARHUEY32DTTFU/events.json","paper":"https://pith.science/paper/PWSTSHIV"},"agent_actions":{"view_html":"https://pith.science/pith/PWSTSHIVOMDRNARHUEY32DTTFU","download_json":"https://pith.science/pith/PWSTSHIVOMDRNARHUEY32DTTFU.json","view_paper":"https://pith.science/paper/PWSTSHIV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.05441&json=true","fetch_graph":"https://pith.science/api/pith-number/PWSTSHIVOMDRNARHUEY32DTTFU/graph.json","fetch_events":"https://pith.science/api/pith-number/PWSTSHIVOMDRNARHUEY32DTTFU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PWSTSHIVOMDRNARHUEY32DTTFU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PWSTSHIVOMDRNARHUEY32DTTFU/action/storage_attestation","attest_author":"https://pith.science/pith/PWSTSHIVOMDRNARHUEY32DTTFU/action/author_attestation","sign_citation":"https://pith.science/pith/PWSTSHIVOMDRNARHUEY32DTTFU/action/citation_signature","submit_replication":"https://pith.science/pith/PWSTSHIVOMDRNARHUEY32DTTFU/action/replication_record"}},"created_at":"2026-07-04T23:56:52.007220+00:00","updated_at":"2026-07-04T23:56:52.007220+00:00"}