{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QY5VNWX6C2UHKSE2XTSD2UCLVJ","short_pith_number":"pith:QY5VNWX6","schema_version":"1.0","canonical_sha256":"863b56dafe16a875489abce43d504baa45ab0c1950f904942a96c61e5f64ade8","source":{"kind":"arxiv","id":"2106.04612","version":1},"attestation_state":"computed","paper":{"title":"Neural Extractive Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Hillel Taub-Tabib, Shauli Ravfogel, Yoav Goldberg","submitted_at":"2021-06-08T18:03:31Z","abstract_excerpt":"Domain experts often need to extract structured information from large corpora. We advocate for a search paradigm called ``extractive search'', in which a search query is enriched with capture-slots, to allow for such rapid extraction. Such an extractive search system can be built around syntactic structures, resulting in high-precision, low-recall results. We show how the recall can be improved using neural retrieval and alignment. The goals of this paper are to concisely introduce the extractive-search paradigm; and to demonstrate a prototype neural retrieval system for extractive search and"},"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":"2106.04612","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-08T18:03:31Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"46c84a127bbe59c1a463565f9fbdf42bce62e3a981ca3c69897c91f750cff00d","abstract_canon_sha256":"e75c42b8e8a8c9d86e834462932183abdd4dfdd8518011cca94e38186af8f127"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:47:47.189656Z","signature_b64":"c5qB2LfHThKvUhkIk+ZODMbOKXi2VrpqiktlgBqGpXKAIrw+O/cQ/n8vRXC0YpLvhWIwWHlgnpP86a5iU/LmDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"863b56dafe16a875489abce43d504baa45ab0c1950f904942a96c61e5f64ade8","last_reissued_at":"2026-07-05T02:47:47.189163Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:47:47.189163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Extractive Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Hillel Taub-Tabib, Shauli Ravfogel, Yoav Goldberg","submitted_at":"2021-06-08T18:03:31Z","abstract_excerpt":"Domain experts often need to extract structured information from large corpora. We advocate for a search paradigm called ``extractive search'', in which a search query is enriched with capture-slots, to allow for such rapid extraction. Such an extractive search system can be built around syntactic structures, resulting in high-precision, low-recall results. We show how the recall can be improved using neural retrieval and alignment. The goals of this paper are to concisely introduce the extractive-search paradigm; and to demonstrate a prototype neural retrieval system for extractive search and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.04612","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/2106.04612/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":"2106.04612","created_at":"2026-07-05T02:47:47.189221+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.04612v1","created_at":"2026-07-05T02:47:47.189221+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.04612","created_at":"2026-07-05T02:47:47.189221+00:00"},{"alias_kind":"pith_short_12","alias_value":"QY5VNWX6C2UH","created_at":"2026-07-05T02:47:47.189221+00:00"},{"alias_kind":"pith_short_16","alias_value":"QY5VNWX6C2UHKSE2","created_at":"2026-07-05T02:47:47.189221+00:00"},{"alias_kind":"pith_short_8","alias_value":"QY5VNWX6","created_at":"2026-07-05T02:47:47.189221+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QY5VNWX6C2UHKSE2XTSD2UCLVJ","json":"https://pith.science/pith/QY5VNWX6C2UHKSE2XTSD2UCLVJ.json","graph_json":"https://pith.science/api/pith-number/QY5VNWX6C2UHKSE2XTSD2UCLVJ/graph.json","events_json":"https://pith.science/api/pith-number/QY5VNWX6C2UHKSE2XTSD2UCLVJ/events.json","paper":"https://pith.science/paper/QY5VNWX6"},"agent_actions":{"view_html":"https://pith.science/pith/QY5VNWX6C2UHKSE2XTSD2UCLVJ","download_json":"https://pith.science/pith/QY5VNWX6C2UHKSE2XTSD2UCLVJ.json","view_paper":"https://pith.science/paper/QY5VNWX6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.04612&json=true","fetch_graph":"https://pith.science/api/pith-number/QY5VNWX6C2UHKSE2XTSD2UCLVJ/graph.json","fetch_events":"https://pith.science/api/pith-number/QY5VNWX6C2UHKSE2XTSD2UCLVJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QY5VNWX6C2UHKSE2XTSD2UCLVJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QY5VNWX6C2UHKSE2XTSD2UCLVJ/action/storage_attestation","attest_author":"https://pith.science/pith/QY5VNWX6C2UHKSE2XTSD2UCLVJ/action/author_attestation","sign_citation":"https://pith.science/pith/QY5VNWX6C2UHKSE2XTSD2UCLVJ/action/citation_signature","submit_replication":"https://pith.science/pith/QY5VNWX6C2UHKSE2XTSD2UCLVJ/action/replication_record"}},"created_at":"2026-07-05T02:47:47.189221+00:00","updated_at":"2026-07-05T02:47:47.189221+00:00"}