{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:5ZML44CAPZLT6PUN3M7YSWARC3","short_pith_number":"pith:5ZML44CA","schema_version":"1.0","canonical_sha256":"ee58be70407e573f3e8ddb3f89581116fa42ac6680faf462984658f67a79df16","source":{"kind":"arxiv","id":"1409.2590","version":1},"attestation_state":"computed","paper":{"title":"Automatic Detection of Webpages that Share the Same Web Template","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, Juli\\'an Alarte (Universitat Polit\\`ecnica de Val\\`encia, Madrid, Salvador Tamarit (Universidad Polit\\'ecnica de Madrid, Spain), Valencia","submitted_at":"2014-09-09T04:12:36Z","abstract_excerpt":"Template extraction is the process of isolating the template of a given webpage. It is widely used in several disciplines, including webpages development, content extraction, block detection, and webpages indexing. One of the main goals of template extraction is identifying a set of webpages with the same template without having to load and analyze too many webpages prior to identifying the template. This work introduces a new technique to automatically discover a reduced set of webpages in a website that implement the template. This set is computed with an hyperlink analysis that computes a v"},"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":"1409.2590","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2014-09-09T04:12:36Z","cross_cats_sorted":[],"title_canon_sha256":"60300718f46a388ab0259d703d8b01ada08df040f52028a194682d4ce4c37de6","abstract_canon_sha256":"5d9364d36af42057b6e3b0d851b35e4c930baa22c2c1ce8fabbbc5a91e4ff663"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:43:10.216480Z","signature_b64":"p8NMnv+JP/K8Djl/vJhkisp50c/K3H+k5NtEgGR7veV4H6FJipHhs9Z7iDQ10aw+HPUGrsClm/8SM62Qmn3wCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee58be70407e573f3e8ddb3f89581116fa42ac6680faf462984658f67a79df16","last_reissued_at":"2026-05-18T02:43:10.216006Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:43:10.216006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatic Detection of Webpages that Share the Same Web Template","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, Juli\\'an Alarte (Universitat Polit\\`ecnica de Val\\`encia, Madrid, Salvador Tamarit (Universidad Polit\\'ecnica de Madrid, Spain), Valencia","submitted_at":"2014-09-09T04:12:36Z","abstract_excerpt":"Template extraction is the process of isolating the template of a given webpage. It is widely used in several disciplines, including webpages development, content extraction, block detection, and webpages indexing. One of the main goals of template extraction is identifying a set of webpages with the same template without having to load and analyze too many webpages prior to identifying the template. This work introduces a new technique to automatically discover a reduced set of webpages in a website that implement the template. This set is computed with an hyperlink analysis that computes a v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1409.2590","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":"1409.2590","created_at":"2026-05-18T02:43:10.216079+00:00"},{"alias_kind":"arxiv_version","alias_value":"1409.2590v1","created_at":"2026-05-18T02:43:10.216079+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1409.2590","created_at":"2026-05-18T02:43:10.216079+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ZML44CAPZLT","created_at":"2026-05-18T12:28:16.859392+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ZML44CAPZLT6PUN","created_at":"2026-05-18T12:28:16.859392+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ZML44CA","created_at":"2026-05-18T12:28:16.859392+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/5ZML44CAPZLT6PUN3M7YSWARC3","json":"https://pith.science/pith/5ZML44CAPZLT6PUN3M7YSWARC3.json","graph_json":"https://pith.science/api/pith-number/5ZML44CAPZLT6PUN3M7YSWARC3/graph.json","events_json":"https://pith.science/api/pith-number/5ZML44CAPZLT6PUN3M7YSWARC3/events.json","paper":"https://pith.science/paper/5ZML44CA"},"agent_actions":{"view_html":"https://pith.science/pith/5ZML44CAPZLT6PUN3M7YSWARC3","download_json":"https://pith.science/pith/5ZML44CAPZLT6PUN3M7YSWARC3.json","view_paper":"https://pith.science/paper/5ZML44CA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1409.2590&json=true","fetch_graph":"https://pith.science/api/pith-number/5ZML44CAPZLT6PUN3M7YSWARC3/graph.json","fetch_events":"https://pith.science/api/pith-number/5ZML44CAPZLT6PUN3M7YSWARC3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ZML44CAPZLT6PUN3M7YSWARC3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ZML44CAPZLT6PUN3M7YSWARC3/action/storage_attestation","attest_author":"https://pith.science/pith/5ZML44CAPZLT6PUN3M7YSWARC3/action/author_attestation","sign_citation":"https://pith.science/pith/5ZML44CAPZLT6PUN3M7YSWARC3/action/citation_signature","submit_replication":"https://pith.science/pith/5ZML44CAPZLT6PUN3M7YSWARC3/action/replication_record"}},"created_at":"2026-05-18T02:43:10.216079+00:00","updated_at":"2026-05-18T02:43:10.216079+00:00"}