{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:LBELC7ZMXZJ6LDZUB7CNT552JB","short_pith_number":"pith:LBELC7ZM","schema_version":"1.0","canonical_sha256":"5848b17f2cbe53e58f340fc4d9f7ba4848d6b11d6641e0ce52cb5e25d193d60c","source":{"kind":"arxiv","id":"1703.10350","version":1},"attestation_state":"computed","paper":{"title":"Joining Extractions of Regular Expressions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Benny Kimelfeld, Dominik D. Freydenberger, Liat Peterfreund","submitted_at":"2017-03-30T08:27:11Z","abstract_excerpt":"Regular expressions with capture variables, also known as \"regex formulas,\" extract relations of spans (interval positions) from text. These relations can be further manipulated via Relational Algebra as studied in the context of document spanners, Fagin et al.'s formal framework for information extraction. We investigate the complexity of querying text by Conjunctive Queries (CQs) and Unions of CQs (UCQs) on top of regex formulas. We show that the lower bounds (NP-completeness and W[1]-hardness) from the relational world also hold in our setting; in particular, hardness hits already single-ch"},"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":"1703.10350","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-03-30T08:27:11Z","cross_cats_sorted":[],"title_canon_sha256":"a5298c5c1ef742b11bce887b9ccf291fc87dbf40129f5651c695e377dc87432f","abstract_canon_sha256":"e1524b4505a96e9fb440808fd4410d1e78c20df2bb862a110e491a8f3bf17183"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:47:37.258005Z","signature_b64":"LmEWIq4P4dy4qO7CaRawTGY05Oh55092EO+C231z64+zvRi81OFOZRu5MEgSmfgho4VghjIbMGCCQE67CIAGDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5848b17f2cbe53e58f340fc4d9f7ba4848d6b11d6641e0ce52cb5e25d193d60c","last_reissued_at":"2026-05-18T00:47:37.257463Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:47:37.257463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Joining Extractions of Regular Expressions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Benny Kimelfeld, Dominik D. Freydenberger, Liat Peterfreund","submitted_at":"2017-03-30T08:27:11Z","abstract_excerpt":"Regular expressions with capture variables, also known as \"regex formulas,\" extract relations of spans (interval positions) from text. These relations can be further manipulated via Relational Algebra as studied in the context of document spanners, Fagin et al.'s formal framework for information extraction. We investigate the complexity of querying text by Conjunctive Queries (CQs) and Unions of CQs (UCQs) on top of regex formulas. We show that the lower bounds (NP-completeness and W[1]-hardness) from the relational world also hold in our setting; in particular, hardness hits already single-ch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.10350","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":""},"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":"1703.10350","created_at":"2026-05-18T00:47:37.257539+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.10350v1","created_at":"2026-05-18T00:47:37.257539+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.10350","created_at":"2026-05-18T00:47:37.257539+00:00"},{"alias_kind":"pith_short_12","alias_value":"LBELC7ZMXZJ6","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"LBELC7ZMXZJ6LDZU","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"LBELC7ZM","created_at":"2026-05-18T12:31:28.150371+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/LBELC7ZMXZJ6LDZUB7CNT552JB","json":"https://pith.science/pith/LBELC7ZMXZJ6LDZUB7CNT552JB.json","graph_json":"https://pith.science/api/pith-number/LBELC7ZMXZJ6LDZUB7CNT552JB/graph.json","events_json":"https://pith.science/api/pith-number/LBELC7ZMXZJ6LDZUB7CNT552JB/events.json","paper":"https://pith.science/paper/LBELC7ZM"},"agent_actions":{"view_html":"https://pith.science/pith/LBELC7ZMXZJ6LDZUB7CNT552JB","download_json":"https://pith.science/pith/LBELC7ZMXZJ6LDZUB7CNT552JB.json","view_paper":"https://pith.science/paper/LBELC7ZM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.10350&json=true","fetch_graph":"https://pith.science/api/pith-number/LBELC7ZMXZJ6LDZUB7CNT552JB/graph.json","fetch_events":"https://pith.science/api/pith-number/LBELC7ZMXZJ6LDZUB7CNT552JB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LBELC7ZMXZJ6LDZUB7CNT552JB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LBELC7ZMXZJ6LDZUB7CNT552JB/action/storage_attestation","attest_author":"https://pith.science/pith/LBELC7ZMXZJ6LDZUB7CNT552JB/action/author_attestation","sign_citation":"https://pith.science/pith/LBELC7ZMXZJ6LDZUB7CNT552JB/action/citation_signature","submit_replication":"https://pith.science/pith/LBELC7ZMXZJ6LDZUB7CNT552JB/action/replication_record"}},"created_at":"2026-05-18T00:47:37.257539+00:00","updated_at":"2026-05-18T00:47:37.257539+00:00"}