{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:NGB76MZMLZNSNTBT3TTAHITTH7","short_pith_number":"pith:NGB76MZM","schema_version":"1.0","canonical_sha256":"6983ff332c5e5b26cc33dce603a2733fd94e793a55d589616e758269c87cddca","source":{"kind":"arxiv","id":"1712.08198","version":3},"attestation_state":"computed","paper":{"title":"Recursive Programs for Document Spanners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Balder ten Cate, Benny Kimelfeld, Liat Peterfreund, Ronald Fagin","submitted_at":"2017-12-21T20:22:47Z","abstract_excerpt":"A document spanner models a program for Information Extraction (IE) as a function that takes as input a text document (string over a finite alphabet) and produces a relation of spans (intervals in the document) over a predefined schema. A well studied language for expressing spanners is that of the regular spanners: relational algebra over regex formulas, which are obtained by adding capture variables to regular expressions. Equivalently, the regular spanners are the ones expressible in non-recursive Datalog over regex formulas (extracting relations that play the role of EDBs from the input do"},"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":"1712.08198","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-12-21T20:22:47Z","cross_cats_sorted":[],"title_canon_sha256":"8f0e9ed6f67093c280cc55c7ad52d0b2651c1704c97c97e7633fec32615af7fa","abstract_canon_sha256":"7c0e9b2d762eae0fdbcf9d9721b8e1dcda7c9c4bc71a85e21995226f3ed71a4f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:09.907788Z","signature_b64":"jy2LmXXEczd83iKVF7pvBshmRkiLdscbTdvepzlESVPIX4lZYDt0vYeMcXunqGjEf89Za0hdaJO569B/ZQouDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6983ff332c5e5b26cc33dce603a2733fd94e793a55d589616e758269c87cddca","last_reissued_at":"2026-05-18T00:15:09.907089Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:09.907089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recursive Programs for Document Spanners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Balder ten Cate, Benny Kimelfeld, Liat Peterfreund, Ronald Fagin","submitted_at":"2017-12-21T20:22:47Z","abstract_excerpt":"A document spanner models a program for Information Extraction (IE) as a function that takes as input a text document (string over a finite alphabet) and produces a relation of spans (intervals in the document) over a predefined schema. A well studied language for expressing spanners is that of the regular spanners: relational algebra over regex formulas, which are obtained by adding capture variables to regular expressions. Equivalently, the regular spanners are the ones expressible in non-recursive Datalog over regex formulas (extracting relations that play the role of EDBs from the input do"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.08198","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":"1712.08198","created_at":"2026-05-18T00:15:09.907185+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.08198v3","created_at":"2026-05-18T00:15:09.907185+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.08198","created_at":"2026-05-18T00:15:09.907185+00:00"},{"alias_kind":"pith_short_12","alias_value":"NGB76MZMLZNS","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_16","alias_value":"NGB76MZMLZNSNTBT","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_8","alias_value":"NGB76MZM","created_at":"2026-05-18T12:31:31.346846+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/NGB76MZMLZNSNTBT3TTAHITTH7","json":"https://pith.science/pith/NGB76MZMLZNSNTBT3TTAHITTH7.json","graph_json":"https://pith.science/api/pith-number/NGB76MZMLZNSNTBT3TTAHITTH7/graph.json","events_json":"https://pith.science/api/pith-number/NGB76MZMLZNSNTBT3TTAHITTH7/events.json","paper":"https://pith.science/paper/NGB76MZM"},"agent_actions":{"view_html":"https://pith.science/pith/NGB76MZMLZNSNTBT3TTAHITTH7","download_json":"https://pith.science/pith/NGB76MZMLZNSNTBT3TTAHITTH7.json","view_paper":"https://pith.science/paper/NGB76MZM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.08198&json=true","fetch_graph":"https://pith.science/api/pith-number/NGB76MZMLZNSNTBT3TTAHITTH7/graph.json","fetch_events":"https://pith.science/api/pith-number/NGB76MZMLZNSNTBT3TTAHITTH7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NGB76MZMLZNSNTBT3TTAHITTH7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NGB76MZMLZNSNTBT3TTAHITTH7/action/storage_attestation","attest_author":"https://pith.science/pith/NGB76MZMLZNSNTBT3TTAHITTH7/action/author_attestation","sign_citation":"https://pith.science/pith/NGB76MZMLZNSNTBT3TTAHITTH7/action/citation_signature","submit_replication":"https://pith.science/pith/NGB76MZMLZNSNTBT3TTAHITTH7/action/replication_record"}},"created_at":"2026-05-18T00:15:09.907185+00:00","updated_at":"2026-05-18T00:15:09.907185+00:00"}