{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2007:QRRE7SYCVO5GVNM4WALJ4IU4FO","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":"e964f58358ed92e102201200eb631ce0739717d68071e7057b9802886c06cb54","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2007-07-13T02:30:10Z","title_canon_sha256":"8f63fb00512e69659cc579cbeb0d68fc71e8c68841bf0d2bbf402063907b6dba"},"schema_version":"1.0","source":{"id":"0707.1913","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"0707.1913","created_at":"2026-05-18T01:08:21Z"},{"alias_kind":"arxiv_version","alias_value":"0707.1913v3","created_at":"2026-05-18T01:08:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.0707.1913","created_at":"2026-05-18T01:08:21Z"},{"alias_kind":"pith_short_12","alias_value":"QRRE7SYCVO5G","created_at":"2026-05-18T12:25:56Z"},{"alias_kind":"pith_short_16","alias_value":"QRRE7SYCVO5GVNM4","created_at":"2026-05-18T12:25:56Z"},{"alias_kind":"pith_short_8","alias_value":"QRRE7SYC","created_at":"2026-05-18T12:25:56Z"}],"graph_snapshots":[{"event_id":"sha256:e94a6da9535f0a7f4c0204e84cc42312f1184d5fea7165281580675408958fc4","target":"graph","created_at":"2026-05-18T01:08:21Z","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":"Collaborative work on unstructured or semi-structured documents, such as in literature corpora or source code, often involves agreed upon templates containing metadata. These templates are not consistent across users and over time. Rule-based parsing of these templates is expensive to maintain and tends to fail as new documents are added. Statistical techniques based on frequent occurrences have the potential to identify automatically a large fraction of the templates, thus reducing the burden on the programmers. We investigate the case of the Project Gutenberg corpus, where most documents are","authors_text":"Daniel Lemire, Owen Kaser","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2007-07-13T02:30:10Z","title":"Removing Manually-Generated Boilerplate from Electronic Texts: Experiments with Project Gutenberg e-Books"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"0707.1913","kind":"arxiv","version":3},"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:ca1c6c1bb452542afa6031353526f17f40c49a6043518375106d428f9897d863","target":"record","created_at":"2026-05-18T01:08:21Z","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":"e964f58358ed92e102201200eb631ce0739717d68071e7057b9802886c06cb54","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2007-07-13T02:30:10Z","title_canon_sha256":"8f63fb00512e69659cc579cbeb0d68fc71e8c68841bf0d2bbf402063907b6dba"},"schema_version":"1.0","source":{"id":"0707.1913","kind":"arxiv","version":3}},"canonical_sha256":"84624fcb02abba6ab59cb0169e229c2b931e6f9de219675b213dd8b231559f51","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"84624fcb02abba6ab59cb0169e229c2b931e6f9de219675b213dd8b231559f51","first_computed_at":"2026-05-18T01:08:21.789290Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:08:21.789290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1V4Xf+VDBvIcxSKo9lXShHE+DHJo0tg7wsJnbtak5ptU+Z9E3rGBPMIVA0qKMX8HU/Tz/bBseQCZph9fHed6AA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:08:21.789920Z","signed_message":"canonical_sha256_bytes"},"source_id":"0707.1913","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca1c6c1bb452542afa6031353526f17f40c49a6043518375106d428f9897d863","sha256:e94a6da9535f0a7f4c0204e84cc42312f1184d5fea7165281580675408958fc4"],"state_sha256":"660e53c7837e5ccdd084d193484cacf82f1c881aca40589a71d32c00f1dd8471"}