{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:NOY2CZ6OG7VEVBLKSMT54NHDEX","short_pith_number":"pith:NOY2CZ6O","schema_version":"1.0","canonical_sha256":"6bb1a167ce37ea4a856a9327de34e325de171db3cb425394ee31b0d3ba39ca3c","source":{"kind":"arxiv","id":"1210.6113","version":1},"attestation_state":"computed","paper":{"title":"Using the DOM Tree for Content Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"David Insa (Universitat Polit\\`ecnica de Val\\`encia), Josep Silva (Universitat Polit\\`ecnica de Val\\`encia), Sergio L\\'opez (Universitat Polit\\`ecnica de Val\\`encia)","submitted_at":"2012-10-23T02:55:06Z","abstract_excerpt":"The main information of a webpage is usually mixed between menus, advertisements, panels, and other not necessarily related information; and it is often difficult to automatically isolate this information. This is precisely the objective of content extraction, a research area of widely interest due to its many applications. Content extraction is useful not only for the final human user, but it is also frequently used as a preprocessing stage of different systems that need to extract the main content in a web document to avoid the treatment and processing of other useless information. Other int"},"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":"1210.6113","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2012-10-23T02:55:06Z","cross_cats_sorted":[],"title_canon_sha256":"2841aacf5c939e6fe114cb05ec0d333c296161eebc622a539a65d9976cce3ea8","abstract_canon_sha256":"416b85605c2cc3057d7014fbba78a170498c6dd29b44773366fa7f508f75933e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:42:33.246105Z","signature_b64":"dsJkJnCb90ZOmoOHHMGFHIXAb06f3Wm/JAn5nH1P5YSrEQrJR3/u7xYC3SUTxSSSV7PUe/IIeFKRuDFL/Tg5Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6bb1a167ce37ea4a856a9327de34e325de171db3cb425394ee31b0d3ba39ca3c","last_reissued_at":"2026-05-18T03:42:33.245299Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:42:33.245299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using the DOM Tree for Content Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"David Insa (Universitat Polit\\`ecnica de Val\\`encia), Josep Silva (Universitat Polit\\`ecnica de Val\\`encia), Sergio L\\'opez (Universitat Polit\\`ecnica de Val\\`encia)","submitted_at":"2012-10-23T02:55:06Z","abstract_excerpt":"The main information of a webpage is usually mixed between menus, advertisements, panels, and other not necessarily related information; and it is often difficult to automatically isolate this information. This is precisely the objective of content extraction, a research area of widely interest due to its many applications. Content extraction is useful not only for the final human user, but it is also frequently used as a preprocessing stage of different systems that need to extract the main content in a web document to avoid the treatment and processing of other useless information. Other int"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1210.6113","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":"1210.6113","created_at":"2026-05-18T03:42:33.245444+00:00"},{"alias_kind":"arxiv_version","alias_value":"1210.6113v1","created_at":"2026-05-18T03:42:33.245444+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1210.6113","created_at":"2026-05-18T03:42:33.245444+00:00"},{"alias_kind":"pith_short_12","alias_value":"NOY2CZ6OG7VE","created_at":"2026-05-18T12:27:16.716162+00:00"},{"alias_kind":"pith_short_16","alias_value":"NOY2CZ6OG7VEVBLK","created_at":"2026-05-18T12:27:16.716162+00:00"},{"alias_kind":"pith_short_8","alias_value":"NOY2CZ6O","created_at":"2026-05-18T12:27:16.716162+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/NOY2CZ6OG7VEVBLKSMT54NHDEX","json":"https://pith.science/pith/NOY2CZ6OG7VEVBLKSMT54NHDEX.json","graph_json":"https://pith.science/api/pith-number/NOY2CZ6OG7VEVBLKSMT54NHDEX/graph.json","events_json":"https://pith.science/api/pith-number/NOY2CZ6OG7VEVBLKSMT54NHDEX/events.json","paper":"https://pith.science/paper/NOY2CZ6O"},"agent_actions":{"view_html":"https://pith.science/pith/NOY2CZ6OG7VEVBLKSMT54NHDEX","download_json":"https://pith.science/pith/NOY2CZ6OG7VEVBLKSMT54NHDEX.json","view_paper":"https://pith.science/paper/NOY2CZ6O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1210.6113&json=true","fetch_graph":"https://pith.science/api/pith-number/NOY2CZ6OG7VEVBLKSMT54NHDEX/graph.json","fetch_events":"https://pith.science/api/pith-number/NOY2CZ6OG7VEVBLKSMT54NHDEX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NOY2CZ6OG7VEVBLKSMT54NHDEX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NOY2CZ6OG7VEVBLKSMT54NHDEX/action/storage_attestation","attest_author":"https://pith.science/pith/NOY2CZ6OG7VEVBLKSMT54NHDEX/action/author_attestation","sign_citation":"https://pith.science/pith/NOY2CZ6OG7VEVBLKSMT54NHDEX/action/citation_signature","submit_replication":"https://pith.science/pith/NOY2CZ6OG7VEVBLKSMT54NHDEX/action/replication_record"}},"created_at":"2026-05-18T03:42:33.245444+00:00","updated_at":"2026-05-18T03:42:33.245444+00:00"}