{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:GVBYYX35QEPHGZHWYKFLGOJ3SR","short_pith_number":"pith:GVBYYX35","schema_version":"1.0","canonical_sha256":"35438c5f7d811e7364f6c28ab3393b94759a831c1fe3f81413f0bf3c28ee08bd","source":{"kind":"arxiv","id":"1704.00051","version":2},"attestation_state":"computed","paper":{"title":"Reading Wikipedia to Answer Open-Domain Questions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adam Fisch, Antoine Bordes, Danqi Chen, Jason Weston","submitted_at":"2017-03-31T20:39:10Z","abstract_excerpt":"This paper proposes to tackle open- domain question answering using Wikipedia as the unique knowledge source: the answer to any factoid question is a text span in a Wikipedia article. This task of machine reading at scale combines the challenges of document retrieval (finding the relevant articles) with that of machine comprehension of text (identifying the answer spans from those articles). Our approach combines a search component based on bigram hashing and TF-IDF matching with a multi-layer recurrent neural network model trained to detect answers in Wikipedia paragraphs. Our experiments on "},"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":"1704.00051","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-31T20:39:10Z","cross_cats_sorted":[],"title_canon_sha256":"452900c20db179ecaa3225a07ce3d7d70614b3915b29ae64091696f6649e2413","abstract_canon_sha256":"ee226f4dd68d8aaa0735baf4b77ec3c4c27e1be8b73ba4242545a91eb69eec17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:45:25.596411Z","signature_b64":"Uby6kVrxEcecfGzTyBUcYUUVKwm8FXvvTq1mCbZuPUn6usIRK8cIQxkenvG1iU4vZk3z9cbaY0CdNbdfe4+6BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35438c5f7d811e7364f6c28ab3393b94759a831c1fe3f81413f0bf3c28ee08bd","last_reissued_at":"2026-05-18T00:45:25.595855Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:45:25.595855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reading Wikipedia to Answer Open-Domain Questions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adam Fisch, Antoine Bordes, Danqi Chen, Jason Weston","submitted_at":"2017-03-31T20:39:10Z","abstract_excerpt":"This paper proposes to tackle open- domain question answering using Wikipedia as the unique knowledge source: the answer to any factoid question is a text span in a Wikipedia article. This task of machine reading at scale combines the challenges of document retrieval (finding the relevant articles) with that of machine comprehension of text (identifying the answer spans from those articles). Our approach combines a search component based on bigram hashing and TF-IDF matching with a multi-layer recurrent neural network model trained to detect answers in Wikipedia paragraphs. Our experiments on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.00051","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":""},"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":"1704.00051","created_at":"2026-05-18T00:45:25.595938+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.00051v2","created_at":"2026-05-18T00:45:25.595938+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.00051","created_at":"2026-05-18T00:45:25.595938+00:00"},{"alias_kind":"pith_short_12","alias_value":"GVBYYX35QEPH","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"GVBYYX35QEPHGZHW","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"GVBYYX35","created_at":"2026-05-18T12:31:18.294218+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":7,"sample":[{"citing_arxiv_id":"2410.15761","citing_title":"Optimal Query Allocation in Extractive QA with LLMs: A Learning-to-Defer Framework with Theoretical Guarantees","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2504.02181","citing_title":"A Survey of Scaling in Large Language Model Reasoning","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12340","citing_title":"Online Learning-to-Defer with Varying Experts","ref_index":79,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17187","citing_title":"PluRule: A Benchmark for Moderating Pluralistic Communities on Social Media","ref_index":271,"is_internal_anchor":true},{"citing_arxiv_id":"2401.03568","citing_title":"Agent AI: Surveying the Horizons of Multimodal Interaction","ref_index":92,"is_internal_anchor":true},{"citing_arxiv_id":"2309.02427","citing_title":"Cognitive Architectures for Language Agents","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2002.08910","citing_title":"How Much Knowledge Can You Pack Into the Parameters of a Language Model?","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12340","citing_title":"Online Learning-to-Defer with Varying Experts","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06216","citing_title":"TIDE: Every Layer Knows the Token Beneath the Context","ref_index":101,"is_internal_anchor":false},{"citing_arxiv_id":"1901.04085","citing_title":"Passage Re-ranking with BERT","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08519","citing_title":"Cram Less to Fit More: Training Data Pruning Improves Memorization of Facts","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06279","citing_title":"Plasma GraphRAG: Physics-Grounded Parameter Selection for Gyrokinetic Simulations","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GVBYYX35QEPHGZHWYKFLGOJ3SR","json":"https://pith.science/pith/GVBYYX35QEPHGZHWYKFLGOJ3SR.json","graph_json":"https://pith.science/api/pith-number/GVBYYX35QEPHGZHWYKFLGOJ3SR/graph.json","events_json":"https://pith.science/api/pith-number/GVBYYX35QEPHGZHWYKFLGOJ3SR/events.json","paper":"https://pith.science/paper/GVBYYX35"},"agent_actions":{"view_html":"https://pith.science/pith/GVBYYX35QEPHGZHWYKFLGOJ3SR","download_json":"https://pith.science/pith/GVBYYX35QEPHGZHWYKFLGOJ3SR.json","view_paper":"https://pith.science/paper/GVBYYX35","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.00051&json=true","fetch_graph":"https://pith.science/api/pith-number/GVBYYX35QEPHGZHWYKFLGOJ3SR/graph.json","fetch_events":"https://pith.science/api/pith-number/GVBYYX35QEPHGZHWYKFLGOJ3SR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GVBYYX35QEPHGZHWYKFLGOJ3SR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GVBYYX35QEPHGZHWYKFLGOJ3SR/action/storage_attestation","attest_author":"https://pith.science/pith/GVBYYX35QEPHGZHWYKFLGOJ3SR/action/author_attestation","sign_citation":"https://pith.science/pith/GVBYYX35QEPHGZHWYKFLGOJ3SR/action/citation_signature","submit_replication":"https://pith.science/pith/GVBYYX35QEPHGZHWYKFLGOJ3SR/action/replication_record"}},"created_at":"2026-05-18T00:45:25.595938+00:00","updated_at":"2026-05-18T00:45:25.595938+00:00"}