{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:SNQCGZRNYQRLEZ2DJMDLUNAYJC","short_pith_number":"pith:SNQCGZRN","schema_version":"1.0","canonical_sha256":"936023662dc422b267434b06ba34184891d3c40d161c5126583fde681fbdb6e3","source":{"kind":"arxiv","id":"1810.06683","version":3},"attestation_state":"computed","paper":{"title":"FlowQA: Grasping Flow in History for Conversational Machine Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Eunsol Choi, Hsin-Yuan Huang, Wen-tau Yih","submitted_at":"2018-10-06T20:46:49Z","abstract_excerpt":"Conversational machine comprehension requires the understanding of the conversation history, such as previous question/answer pairs, the document context, and the current question. To enable traditional, single-turn models to encode the history comprehensively, we introduce Flow, a mechanism that can incorporate intermediate representations generated during the process of answering previous questions, through an alternating parallel processing structure. Compared to approaches that concatenate previous questions/answers as input, Flow integrates the latent semantics of the conversation history"},"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":"1810.06683","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-06T20:46:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8edf48286187618d6daf9e8820fbb274d4d0375cbe8e9be134280a4f75f08b01","abstract_canon_sha256":"c6b9ec176b49e58b4ed5cf18f40eef70a35849b4eb5677f2537cd0283dfdec0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:31.866418Z","signature_b64":"xqOoqDRuRXz3qiPIM9GoseV1j1TFFnSJHsnUhU2NVmhLj05WeNA5gMoGCCTtf45m+tqcUa1+zVHILbd/W3y3Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"936023662dc422b267434b06ba34184891d3c40d161c5126583fde681fbdb6e3","last_reissued_at":"2026-05-17T23:48:31.865901Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:31.865901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FlowQA: Grasping Flow in History for Conversational Machine Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Eunsol Choi, Hsin-Yuan Huang, Wen-tau Yih","submitted_at":"2018-10-06T20:46:49Z","abstract_excerpt":"Conversational machine comprehension requires the understanding of the conversation history, such as previous question/answer pairs, the document context, and the current question. To enable traditional, single-turn models to encode the history comprehensively, we introduce Flow, a mechanism that can incorporate intermediate representations generated during the process of answering previous questions, through an alternating parallel processing structure. Compared to approaches that concatenate previous questions/answers as input, Flow integrates the latent semantics of the conversation history"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.06683","kind":"arxiv","version":3},"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":"1810.06683","created_at":"2026-05-17T23:48:31.865974+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.06683v3","created_at":"2026-05-17T23:48:31.865974+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.06683","created_at":"2026-05-17T23:48:31.865974+00:00"},{"alias_kind":"pith_short_12","alias_value":"SNQCGZRNYQRL","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"SNQCGZRNYQRLEZ2D","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"SNQCGZRN","created_at":"2026-05-18T12:32:53.628368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2402.06196","citing_title":"Large Language Models: A Survey","ref_index":205,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SNQCGZRNYQRLEZ2DJMDLUNAYJC","json":"https://pith.science/pith/SNQCGZRNYQRLEZ2DJMDLUNAYJC.json","graph_json":"https://pith.science/api/pith-number/SNQCGZRNYQRLEZ2DJMDLUNAYJC/graph.json","events_json":"https://pith.science/api/pith-number/SNQCGZRNYQRLEZ2DJMDLUNAYJC/events.json","paper":"https://pith.science/paper/SNQCGZRN"},"agent_actions":{"view_html":"https://pith.science/pith/SNQCGZRNYQRLEZ2DJMDLUNAYJC","download_json":"https://pith.science/pith/SNQCGZRNYQRLEZ2DJMDLUNAYJC.json","view_paper":"https://pith.science/paper/SNQCGZRN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.06683&json=true","fetch_graph":"https://pith.science/api/pith-number/SNQCGZRNYQRLEZ2DJMDLUNAYJC/graph.json","fetch_events":"https://pith.science/api/pith-number/SNQCGZRNYQRLEZ2DJMDLUNAYJC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SNQCGZRNYQRLEZ2DJMDLUNAYJC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SNQCGZRNYQRLEZ2DJMDLUNAYJC/action/storage_attestation","attest_author":"https://pith.science/pith/SNQCGZRNYQRLEZ2DJMDLUNAYJC/action/author_attestation","sign_citation":"https://pith.science/pith/SNQCGZRNYQRLEZ2DJMDLUNAYJC/action/citation_signature","submit_replication":"https://pith.science/pith/SNQCGZRNYQRLEZ2DJMDLUNAYJC/action/replication_record"}},"created_at":"2026-05-17T23:48:31.865974+00:00","updated_at":"2026-05-17T23:48:31.865974+00:00"}