{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:LBX6QMUXQZT3U7KJOT3UAY44UH","short_pith_number":"pith:LBX6QMUX","schema_version":"1.0","canonical_sha256":"586fe832978667ba7d4974f740639ca1ffd46be4b2b13db98adfeb74ddb1e0b0","source":{"kind":"arxiv","id":"1611.01603","version":6},"attestation_state":"computed","paper":{"title":"Bidirectional Attention Flow for Machine Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ali Farhadi, Aniruddha Kembhavi, Hannaneh Hajishirzi, Minjoon Seo","submitted_at":"2016-11-05T04:49:00Z","abstract_excerpt":"Machine comprehension (MC), answering a query about a given context paragraph, requires modeling complex interactions between the context and the query. Recently, attention mechanisms have been successfully extended to MC. Typically these methods use attention to focus on a small portion of the context and summarize it with a fixed-size vector, couple attentions temporally, and/or often form a uni-directional attention. In this paper we introduce the Bi-Directional Attention Flow (BIDAF) network, a multi-stage hierarchical process that represents the context at different levels of granularity "},"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":"1611.01603","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-11-05T04:49:00Z","cross_cats_sorted":[],"title_canon_sha256":"ae13249a8b9900de1c1656e7c4d20ab7af8e36c7a12143f66bc81d2ceeb46a66","abstract_canon_sha256":"ccd307f5a69785f2da23ba3e01dc6e6169a44aba898ec366a278ac1ee9edf199"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:45.971583Z","signature_b64":"dOf9WzUGRTPKnYHVQU1KGwRrwI4fVe4t8ARJq4lkXule21lNZLpOkg7clcB31L+hm9g8CMD2gGeTY6CxptphCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"586fe832978667ba7d4974f740639ca1ffd46be4b2b13db98adfeb74ddb1e0b0","last_reissued_at":"2026-05-18T00:12:45.971015Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:45.971015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bidirectional Attention Flow for Machine Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ali Farhadi, Aniruddha Kembhavi, Hannaneh Hajishirzi, Minjoon Seo","submitted_at":"2016-11-05T04:49:00Z","abstract_excerpt":"Machine comprehension (MC), answering a query about a given context paragraph, requires modeling complex interactions between the context and the query. Recently, attention mechanisms have been successfully extended to MC. Typically these methods use attention to focus on a small portion of the context and summarize it with a fixed-size vector, couple attentions temporally, and/or often form a uni-directional attention. In this paper we introduce the Bi-Directional Attention Flow (BIDAF) network, a multi-stage hierarchical process that represents the context at different levels of granularity "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.01603","kind":"arxiv","version":6},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1611.01603","created_at":"2026-05-18T00:12:45.971103+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.01603v6","created_at":"2026-05-18T00:12:45.971103+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.01603","created_at":"2026-05-18T00:12:45.971103+00:00"},{"alias_kind":"pith_short_12","alias_value":"LBX6QMUXQZT3","created_at":"2026-05-18T12:30:29.479603+00:00"},{"alias_kind":"pith_short_16","alias_value":"LBX6QMUXQZT3U7KJ","created_at":"2026-05-18T12:30:29.479603+00:00"},{"alias_kind":"pith_short_8","alias_value":"LBX6QMUX","created_at":"2026-05-18T12:30:29.479603+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":6,"sample":[{"citing_arxiv_id":"1907.00708","citing_title":"EQuANt (Enhanced Question Answer Network)","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"1906.11604","citing_title":"Gated Embeddings in End-to-End Speech Recognition for Conversational-Context Fusion","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"1907.01686","citing_title":"Machine Reading Comprehension: a Literature Review","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"1907.00607","citing_title":"Weak Supervision Enhanced Generative Network for Question Generation","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12340","citing_title":"Online Learning-to-Defer with Varying Experts","ref_index":78,"is_internal_anchor":true},{"citing_arxiv_id":"2401.18059","citing_title":"RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval","ref_index":126,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12340","citing_title":"Online Learning-to-Defer with Varying Experts","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"1611.09268","citing_title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"1901.04085","citing_title":"Passage Re-ranking with BERT","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"1705.03551","citing_title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LBX6QMUXQZT3U7KJOT3UAY44UH","json":"https://pith.science/pith/LBX6QMUXQZT3U7KJOT3UAY44UH.json","graph_json":"https://pith.science/api/pith-number/LBX6QMUXQZT3U7KJOT3UAY44UH/graph.json","events_json":"https://pith.science/api/pith-number/LBX6QMUXQZT3U7KJOT3UAY44UH/events.json","paper":"https://pith.science/paper/LBX6QMUX"},"agent_actions":{"view_html":"https://pith.science/pith/LBX6QMUXQZT3U7KJOT3UAY44UH","download_json":"https://pith.science/pith/LBX6QMUXQZT3U7KJOT3UAY44UH.json","view_paper":"https://pith.science/paper/LBX6QMUX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.01603&json=true","fetch_graph":"https://pith.science/api/pith-number/LBX6QMUXQZT3U7KJOT3UAY44UH/graph.json","fetch_events":"https://pith.science/api/pith-number/LBX6QMUXQZT3U7KJOT3UAY44UH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LBX6QMUXQZT3U7KJOT3UAY44UH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LBX6QMUXQZT3U7KJOT3UAY44UH/action/storage_attestation","attest_author":"https://pith.science/pith/LBX6QMUXQZT3U7KJOT3UAY44UH/action/author_attestation","sign_citation":"https://pith.science/pith/LBX6QMUXQZT3U7KJOT3UAY44UH/action/citation_signature","submit_replication":"https://pith.science/pith/LBX6QMUXQZT3U7KJOT3UAY44UH/action/replication_record"}},"created_at":"2026-05-18T00:12:45.971103+00:00","updated_at":"2026-05-18T00:12:45.971103+00:00"}