{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:EFSNMKTI5I3AS6NUCPO3DZSTUY","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":"05a554f9c88a23aed9a61bd47870d188fda8710667fb44939ff1a8cc5426af29","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2012-06-05T12:36:09Z","title_canon_sha256":"aad65c4898667f6d1d89659bfd51fd5e4106395dafdad6445b48e944d87e7d11"},"schema_version":"1.0","source":{"id":"1206.0905","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1206.0905","created_at":"2026-05-18T03:54:15Z"},{"alias_kind":"arxiv_version","alias_value":"1206.0905v1","created_at":"2026-05-18T03:54:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1206.0905","created_at":"2026-05-18T03:54:15Z"},{"alias_kind":"pith_short_12","alias_value":"EFSNMKTI5I3A","created_at":"2026-05-18T12:27:04Z"},{"alias_kind":"pith_short_16","alias_value":"EFSNMKTI5I3AS6NU","created_at":"2026-05-18T12:27:04Z"},{"alias_kind":"pith_short_8","alias_value":"EFSNMKTI","created_at":"2026-05-18T12:27:04Z"}],"graph_snapshots":[{"event_id":"sha256:a4a4c2faf1c90aa13aec0f7fa6494aa77449e8035df46cad1c399e8281c354e4","target":"graph","created_at":"2026-05-18T03:54:15Z","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":"Recent work in machine learning for information extraction has focused on two distinct sub-problems: the conventional problem of filling template slots from natural language text, and the problem of wrapper induction, learning simple extraction procedures (\"wrappers\") for highly structured text such as Web pages. For suitable regular domains, existing wrapper induction algorithms can efficiently learn wrappers that are simple and highly accurate, but the regularity bias of these algorithms makes them unsuitable for most conventional information extraction tasks. This paper describes a new appr","authors_text":"Habib Youssef, Mohamed Nazih Omri, Radhouane Boughamoura","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2012-06-05T12:36:09Z","title":"A Fuzzy Approach for Pertinent Information Extraction from Web Resources"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1206.0905","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":"sha256:8dafde3c4f1899253a44093de9fdc7aeee3f24a8fde286624b1af82ff0aaa635","target":"record","created_at":"2026-05-18T03:54:15Z","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":"05a554f9c88a23aed9a61bd47870d188fda8710667fb44939ff1a8cc5426af29","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2012-06-05T12:36:09Z","title_canon_sha256":"aad65c4898667f6d1d89659bfd51fd5e4106395dafdad6445b48e944d87e7d11"},"schema_version":"1.0","source":{"id":"1206.0905","kind":"arxiv","version":1}},"canonical_sha256":"2164d62a68ea360979b413ddb1e653a6259d350832c8fcc45bdb57a589a99fef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2164d62a68ea360979b413ddb1e653a6259d350832c8fcc45bdb57a589a99fef","first_computed_at":"2026-05-18T03:54:15.727569Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:54:15.727569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XbDt2PAMKsHD2SdeqAAX9CZS7C9MXHHDTInt+w80WKvr3nyRNWZRNRQi56iXSNlKbT5PDMkff+Iff0fNHr/QCg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:54:15.728173Z","signed_message":"canonical_sha256_bytes"},"source_id":"1206.0905","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8dafde3c4f1899253a44093de9fdc7aeee3f24a8fde286624b1af82ff0aaa635","sha256:a4a4c2faf1c90aa13aec0f7fa6494aa77449e8035df46cad1c399e8281c354e4"],"state_sha256":"d2e369775fb044f9c6e2e16f345f36f045dbe2b6f4365eb3ef567c8c8f9d64f4"}