{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2007:QRRE7SYCVO5GVNM4WALJ4IU4FO","short_pith_number":"pith:QRRE7SYC","schema_version":"1.0","canonical_sha256":"84624fcb02abba6ab59cb0169e229c2b931e6f9de219675b213dd8b231559f51","source":{"kind":"arxiv","id":"0707.1913","version":3},"attestation_state":"computed","paper":{"title":"Removing Manually-Generated Boilerplate from Electronic Texts: Experiments with Project Gutenberg e-Books","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.DL","authors_text":"Daniel Lemire, Owen Kaser","submitted_at":"2007-07-13T02:30:10Z","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"},"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":"0707.1913","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2007-07-13T02:30:10Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"8f63fb00512e69659cc579cbeb0d68fc71e8c68841bf0d2bbf402063907b6dba","abstract_canon_sha256":"e964f58358ed92e102201200eb631ce0739717d68071e7057b9802886c06cb54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:08:21.789920Z","signature_b64":"1V4Xf+VDBvIcxSKo9lXShHE+DHJo0tg7wsJnbtak5ptU+Z9E3rGBPMIVA0qKMX8HU/Tz/bBseQCZph9fHed6AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84624fcb02abba6ab59cb0169e229c2b931e6f9de219675b213dd8b231559f51","last_reissued_at":"2026-05-18T01:08:21.789290Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:08:21.789290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Removing Manually-Generated Boilerplate from Electronic Texts: Experiments with Project Gutenberg e-Books","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.DL","authors_text":"Daniel Lemire, Owen Kaser","submitted_at":"2007-07-13T02:30:10Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"0707.1913","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":"0707.1913","created_at":"2026-05-18T01:08:21.789398+00:00"},{"alias_kind":"arxiv_version","alias_value":"0707.1913v3","created_at":"2026-05-18T01:08:21.789398+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.0707.1913","created_at":"2026-05-18T01:08:21.789398+00:00"},{"alias_kind":"pith_short_12","alias_value":"QRRE7SYCVO5G","created_at":"2026-05-18T12:25:56.245647+00:00"},{"alias_kind":"pith_short_16","alias_value":"QRRE7SYCVO5GVNM4","created_at":"2026-05-18T12:25:56.245647+00:00"},{"alias_kind":"pith_short_8","alias_value":"QRRE7SYC","created_at":"2026-05-18T12:25:56.245647+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/QRRE7SYCVO5GVNM4WALJ4IU4FO","json":"https://pith.science/pith/QRRE7SYCVO5GVNM4WALJ4IU4FO.json","graph_json":"https://pith.science/api/pith-number/QRRE7SYCVO5GVNM4WALJ4IU4FO/graph.json","events_json":"https://pith.science/api/pith-number/QRRE7SYCVO5GVNM4WALJ4IU4FO/events.json","paper":"https://pith.science/paper/QRRE7SYC"},"agent_actions":{"view_html":"https://pith.science/pith/QRRE7SYCVO5GVNM4WALJ4IU4FO","download_json":"https://pith.science/pith/QRRE7SYCVO5GVNM4WALJ4IU4FO.json","view_paper":"https://pith.science/paper/QRRE7SYC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=0707.1913&json=true","fetch_graph":"https://pith.science/api/pith-number/QRRE7SYCVO5GVNM4WALJ4IU4FO/graph.json","fetch_events":"https://pith.science/api/pith-number/QRRE7SYCVO5GVNM4WALJ4IU4FO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QRRE7SYCVO5GVNM4WALJ4IU4FO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QRRE7SYCVO5GVNM4WALJ4IU4FO/action/storage_attestation","attest_author":"https://pith.science/pith/QRRE7SYCVO5GVNM4WALJ4IU4FO/action/author_attestation","sign_citation":"https://pith.science/pith/QRRE7SYCVO5GVNM4WALJ4IU4FO/action/citation_signature","submit_replication":"https://pith.science/pith/QRRE7SYCVO5GVNM4WALJ4IU4FO/action/replication_record"}},"created_at":"2026-05-18T01:08:21.789398+00:00","updated_at":"2026-05-18T01:08:21.789398+00:00"}