{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:BBRGDNDYC6EFFP7ANJEKOUIUZZ","short_pith_number":"pith:BBRGDNDY","schema_version":"1.0","canonical_sha256":"086261b478178852bfe06a48a75114ce5e6d6fd0823eef0e78f284bc722ef0e3","source":{"kind":"arxiv","id":"1908.11511","version":4},"attestation_state":"computed","paper":{"title":"DCMN+: Dual Co-Matching Network for Multi-choice Reading Comprehension","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hai Zhao, Shuailiang Zhang, Xiang Zhou, Xi Zhou, Yuwei Wu, Zhuosheng Zhang","submitted_at":"2019-08-30T02:30:28Z","abstract_excerpt":"Multi-choice reading comprehension is a challenging task to select an answer from a set of candidate options when given passage and question. Previous approaches usually only calculate question-aware passage representation and ignore passage-aware question representation when modeling the relationship between passage and question, which obviously cannot take the best of information between passage and question. In this work, we propose dual co-matching network (DCMN) which models the relationship among passage, question and answer options bidirectionally. Besides, inspired by how human solve m"},"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":"1908.11511","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-30T02:30:28Z","cross_cats_sorted":[],"title_canon_sha256":"4f58d53104fa90541e59ec8612586706e4059cb54bca45e2e2f53ac2c5c8f8e5","abstract_canon_sha256":"df1d4019abb1e0a88b4662c0931700129f272e905287c2c0f0785d07b08b0d40"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:33:44.169381Z","signature_b64":"ZFmM2gmYSYQe4Af4M127648Ir1hQ1VK9NneTVjTrBbtJwopx3HcRMmV4of/3h/g6CalW6VVgZA1r1ViXBRmpCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"086261b478178852bfe06a48a75114ce5e6d6fd0823eef0e78f284bc722ef0e3","last_reissued_at":"2026-07-05T00:33:44.168866Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:33:44.168866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DCMN+: Dual Co-Matching Network for Multi-choice Reading Comprehension","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hai Zhao, Shuailiang Zhang, Xiang Zhou, Xi Zhou, Yuwei Wu, Zhuosheng Zhang","submitted_at":"2019-08-30T02:30:28Z","abstract_excerpt":"Multi-choice reading comprehension is a challenging task to select an answer from a set of candidate options when given passage and question. Previous approaches usually only calculate question-aware passage representation and ignore passage-aware question representation when modeling the relationship between passage and question, which obviously cannot take the best of information between passage and question. In this work, we propose dual co-matching network (DCMN) which models the relationship among passage, question and answer options bidirectionally. Besides, inspired by how human solve m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.11511","kind":"arxiv","version":4},"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/1908.11511/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":"1908.11511","created_at":"2026-07-05T00:33:44.168932+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.11511v4","created_at":"2026-07-05T00:33:44.168932+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.11511","created_at":"2026-07-05T00:33:44.168932+00:00"},{"alias_kind":"pith_short_12","alias_value":"BBRGDNDYC6EF","created_at":"2026-07-05T00:33:44.168932+00:00"},{"alias_kind":"pith_short_16","alias_value":"BBRGDNDYC6EFFP7A","created_at":"2026-07-05T00:33:44.168932+00:00"},{"alias_kind":"pith_short_8","alias_value":"BBRGDNDY","created_at":"2026-07-05T00:33:44.168932+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1909.11942","citing_title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BBRGDNDYC6EFFP7ANJEKOUIUZZ","json":"https://pith.science/pith/BBRGDNDYC6EFFP7ANJEKOUIUZZ.json","graph_json":"https://pith.science/api/pith-number/BBRGDNDYC6EFFP7ANJEKOUIUZZ/graph.json","events_json":"https://pith.science/api/pith-number/BBRGDNDYC6EFFP7ANJEKOUIUZZ/events.json","paper":"https://pith.science/paper/BBRGDNDY"},"agent_actions":{"view_html":"https://pith.science/pith/BBRGDNDYC6EFFP7ANJEKOUIUZZ","download_json":"https://pith.science/pith/BBRGDNDYC6EFFP7ANJEKOUIUZZ.json","view_paper":"https://pith.science/paper/BBRGDNDY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.11511&json=true","fetch_graph":"https://pith.science/api/pith-number/BBRGDNDYC6EFFP7ANJEKOUIUZZ/graph.json","fetch_events":"https://pith.science/api/pith-number/BBRGDNDYC6EFFP7ANJEKOUIUZZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BBRGDNDYC6EFFP7ANJEKOUIUZZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BBRGDNDYC6EFFP7ANJEKOUIUZZ/action/storage_attestation","attest_author":"https://pith.science/pith/BBRGDNDYC6EFFP7ANJEKOUIUZZ/action/author_attestation","sign_citation":"https://pith.science/pith/BBRGDNDYC6EFFP7ANJEKOUIUZZ/action/citation_signature","submit_replication":"https://pith.science/pith/BBRGDNDYC6EFFP7ANJEKOUIUZZ/action/replication_record"}},"created_at":"2026-07-05T00:33:44.168932+00:00","updated_at":"2026-07-05T00:33:44.168932+00:00"}