{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:LBELC7ZMXZJ6LDZUB7CNT552JB","short_pith_number":"pith:LBELC7ZM","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"},"canonical_sha256":"5848b17f2cbe53e58f340fc4d9f7ba4848d6b11d6641e0ce52cb5e25d193d60c","source":{"kind":"arxiv","id":"1703.10350","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.10350","created_at":"2026-05-18T00:47:37Z"},{"alias_kind":"arxiv_version","alias_value":"1703.10350v1","created_at":"2026-05-18T00:47:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.10350","created_at":"2026-05-18T00:47:37Z"},{"alias_kind":"pith_short_12","alias_value":"LBELC7ZMXZJ6","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"LBELC7ZMXZJ6LDZU","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"LBELC7ZM","created_at":"2026-05-18T12:31:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:LBELC7ZMXZJ6LDZUB7CNT552JB","target":"record","payload":{"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"},"canonical_sha256":"5848b17f2cbe53e58f340fc4d9f7ba4848d6b11d6641e0ce52cb5e25d193d60c","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"},"source_kind":"arxiv","source_id":"1703.10350","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:47:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3VT/mVrHOpOzAr8TTYtAwPU7TyAXm8sH+vi6G1hjxwlyj4dyaYkkzhaNOJtAFNBM4O6Llun+zq4mPcugVozNDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T14:03:44.328756Z"},"content_sha256":"4e44a25e7eec93ea34dde2ebdcff2ba0e92f45f0505d42983448fb04aa894ddd","schema_version":"1.0","event_id":"sha256:4e44a25e7eec93ea34dde2ebdcff2ba0e92f45f0505d42983448fb04aa894ddd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:LBELC7ZMXZJ6LDZUB7CNT552JB","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:47:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EF43yM15iR+SFiGrGnDu+laZJIWn1PzSJGtpRg0MMUTiNDnJMH/D7ubnjt1gtW4L83hes4ntq+NmTedoDflhBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T14:03:44.329108Z"},"content_sha256":"c55805b955442a80fd44fb9c1fb40b2509745ae499afeefe356c1a1145847a44","schema_version":"1.0","event_id":"sha256:c55805b955442a80fd44fb9c1fb40b2509745ae499afeefe356c1a1145847a44"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LBELC7ZMXZJ6LDZUB7CNT552JB/bundle.json","state_url":"https://pith.science/pith/LBELC7ZMXZJ6LDZUB7CNT552JB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LBELC7ZMXZJ6LDZUB7CNT552JB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-05T14:03:44Z","links":{"resolver":"https://pith.science/pith/LBELC7ZMXZJ6LDZUB7CNT552JB","bundle":"https://pith.science/pith/LBELC7ZMXZJ6LDZUB7CNT552JB/bundle.json","state":"https://pith.science/pith/LBELC7ZMXZJ6LDZUB7CNT552JB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LBELC7ZMXZJ6LDZUB7CNT552JB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:LBELC7ZMXZJ6LDZUB7CNT552JB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e1524b4505a96e9fb440808fd4410d1e78c20df2bb862a110e491a8f3bf17183","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-03-30T08:27:11Z","title_canon_sha256":"a5298c5c1ef742b11bce887b9ccf291fc87dbf40129f5651c695e377dc87432f"},"schema_version":"1.0","source":{"id":"1703.10350","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.10350","created_at":"2026-05-18T00:47:37Z"},{"alias_kind":"arxiv_version","alias_value":"1703.10350v1","created_at":"2026-05-18T00:47:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.10350","created_at":"2026-05-18T00:47:37Z"},{"alias_kind":"pith_short_12","alias_value":"LBELC7ZMXZJ6","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"LBELC7ZMXZJ6LDZU","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"LBELC7ZM","created_at":"2026-05-18T12:31:28Z"}],"graph_snapshots":[{"event_id":"sha256:c55805b955442a80fd44fb9c1fb40b2509745ae499afeefe356c1a1145847a44","target":"graph","created_at":"2026-05-18T00:47:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Benny Kimelfeld, Dominik D. Freydenberger, Liat Peterfreund","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-03-30T08:27:11Z","title":"Joining Extractions of Regular Expressions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.10350","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4e44a25e7eec93ea34dde2ebdcff2ba0e92f45f0505d42983448fb04aa894ddd","target":"record","created_at":"2026-05-18T00:47:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e1524b4505a96e9fb440808fd4410d1e78c20df2bb862a110e491a8f3bf17183","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-03-30T08:27:11Z","title_canon_sha256":"a5298c5c1ef742b11bce887b9ccf291fc87dbf40129f5651c695e377dc87432f"},"schema_version":"1.0","source":{"id":"1703.10350","kind":"arxiv","version":1}},"canonical_sha256":"5848b17f2cbe53e58f340fc4d9f7ba4848d6b11d6641e0ce52cb5e25d193d60c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5848b17f2cbe53e58f340fc4d9f7ba4848d6b11d6641e0ce52cb5e25d193d60c","first_computed_at":"2026-05-18T00:47:37.257463Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:47:37.257463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LmEWIq4P4dy4qO7CaRawTGY05Oh55092EO+C231z64+zvRi81OFOZRu5MEgSmfgho4VghjIbMGCCQE67CIAGDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:47:37.258005Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.10350","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e44a25e7eec93ea34dde2ebdcff2ba0e92f45f0505d42983448fb04aa894ddd","sha256:c55805b955442a80fd44fb9c1fb40b2509745ae499afeefe356c1a1145847a44"],"state_sha256":"fed47e327afab343f896e2867a7eaf8cc125f9b5cf740c95cf01ff99ba61ac97"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wV1dELdQpO51Gr5Jpl1p8Lvsfn1rSTagDhr5brT2KRLb0uuVz9XLP2w4YnxEGzNcbuCF6nS4wW5M+sdfZpOeCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T14:03:44.330963Z","bundle_sha256":"6df52f2d5ceba6d696702832a8e7c88b923c240c2389bf3a2f8eb26a0b5f2b5c"}}