{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:5ZML44CAPZLT6PUN3M7YSWARC3","short_pith_number":"pith:5ZML44CA","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"},"canonical_sha256":"ee58be70407e573f3e8ddb3f89581116fa42ac6680faf462984658f67a79df16","source":{"kind":"arxiv","id":"1409.2590","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1409.2590","created_at":"2026-05-18T02:43:10Z"},{"alias_kind":"arxiv_version","alias_value":"1409.2590v1","created_at":"2026-05-18T02:43:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1409.2590","created_at":"2026-05-18T02:43:10Z"},{"alias_kind":"pith_short_12","alias_value":"5ZML44CAPZLT","created_at":"2026-05-18T12:28:16Z"},{"alias_kind":"pith_short_16","alias_value":"5ZML44CAPZLT6PUN","created_at":"2026-05-18T12:28:16Z"},{"alias_kind":"pith_short_8","alias_value":"5ZML44CA","created_at":"2026-05-18T12:28:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:5ZML44CAPZLT6PUN3M7YSWARC3","target":"record","payload":{"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"},"canonical_sha256":"ee58be70407e573f3e8ddb3f89581116fa42ac6680faf462984658f67a79df16","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"},"source_kind":"arxiv","source_id":"1409.2590","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:43:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+lcuqoGqePSSmO/Vg7o+eCkwavUE7YDrF1a+HAphrg6YyvVRMTrUgpF9Ga9XnfGS5HPtkfIGUXg2Fj/g7plOCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T16:45:15.307854Z"},"content_sha256":"b49d0ca8be56bf9ad88a16b23bad1c735914173221f1d71b00008f0196025d16","schema_version":"1.0","event_id":"sha256:b49d0ca8be56bf9ad88a16b23bad1c735914173221f1d71b00008f0196025d16"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:5ZML44CAPZLT6PUN3M7YSWARC3","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:43:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+8SSaNBD0TAj8Qq1ZkrE+AA8fhToSAzIgZynNUJW0ViQ8XHwPjin9yv0C7kyuewHa1vBQWqUameznNRxMCmnAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T16:45:15.308200Z"},"content_sha256":"1c73fa0bf04e94a0d655ef583a9f03070de0a48094fc782b882e7234447d8c53","schema_version":"1.0","event_id":"sha256:1c73fa0bf04e94a0d655ef583a9f03070de0a48094fc782b882e7234447d8c53"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5ZML44CAPZLT6PUN3M7YSWARC3/bundle.json","state_url":"https://pith.science/pith/5ZML44CAPZLT6PUN3M7YSWARC3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5ZML44CAPZLT6PUN3M7YSWARC3/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-01T16:45:15Z","links":{"resolver":"https://pith.science/pith/5ZML44CAPZLT6PUN3M7YSWARC3","bundle":"https://pith.science/pith/5ZML44CAPZLT6PUN3M7YSWARC3/bundle.json","state":"https://pith.science/pith/5ZML44CAPZLT6PUN3M7YSWARC3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5ZML44CAPZLT6PUN3M7YSWARC3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:5ZML44CAPZLT6PUN3M7YSWARC3","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":"5d9364d36af42057b6e3b0d851b35e4c930baa22c2c1ce8fabbbc5a91e4ff663","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2014-09-09T04:12:36Z","title_canon_sha256":"60300718f46a388ab0259d703d8b01ada08df040f52028a194682d4ce4c37de6"},"schema_version":"1.0","source":{"id":"1409.2590","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1409.2590","created_at":"2026-05-18T02:43:10Z"},{"alias_kind":"arxiv_version","alias_value":"1409.2590v1","created_at":"2026-05-18T02:43:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1409.2590","created_at":"2026-05-18T02:43:10Z"},{"alias_kind":"pith_short_12","alias_value":"5ZML44CAPZLT","created_at":"2026-05-18T12:28:16Z"},{"alias_kind":"pith_short_16","alias_value":"5ZML44CAPZLT6PUN","created_at":"2026-05-18T12:28:16Z"},{"alias_kind":"pith_short_8","alias_value":"5ZML44CA","created_at":"2026-05-18T12:28:16Z"}],"graph_snapshots":[{"event_id":"sha256:1c73fa0bf04e94a0d655ef583a9f03070de0a48094fc782b882e7234447d8c53","target":"graph","created_at":"2026-05-18T02:43:10Z","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":"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","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","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2014-09-09T04:12:36Z","title":"Automatic Detection of Webpages that Share the Same Web Template"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1409.2590","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:b49d0ca8be56bf9ad88a16b23bad1c735914173221f1d71b00008f0196025d16","target":"record","created_at":"2026-05-18T02:43:10Z","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":"5d9364d36af42057b6e3b0d851b35e4c930baa22c2c1ce8fabbbc5a91e4ff663","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2014-09-09T04:12:36Z","title_canon_sha256":"60300718f46a388ab0259d703d8b01ada08df040f52028a194682d4ce4c37de6"},"schema_version":"1.0","source":{"id":"1409.2590","kind":"arxiv","version":1}},"canonical_sha256":"ee58be70407e573f3e8ddb3f89581116fa42ac6680faf462984658f67a79df16","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee58be70407e573f3e8ddb3f89581116fa42ac6680faf462984658f67a79df16","first_computed_at":"2026-05-18T02:43:10.216006Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:43:10.216006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p8NMnv+JP/K8Djl/vJhkisp50c/K3H+k5NtEgGR7veV4H6FJipHhs9Z7iDQ10aw+HPUGrsClm/8SM62Qmn3wCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:43:10.216480Z","signed_message":"canonical_sha256_bytes"},"source_id":"1409.2590","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b49d0ca8be56bf9ad88a16b23bad1c735914173221f1d71b00008f0196025d16","sha256:1c73fa0bf04e94a0d655ef583a9f03070de0a48094fc782b882e7234447d8c53"],"state_sha256":"f91fa38eec4097b4f0b405b56bd89bbed7616487f9cf4aa0ed0c6d960977b3fb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7t4NUfXy303fiPy1b8JcN654IqltxxKCwqfU96nNSsIpH+Pdj+i758EdxIJzeKlfpWuFzkmC7dRUOAn3XjB9Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T16:45:15.310138Z","bundle_sha256":"48236feb3ef17aa277a0acea2e84bcc60fb37cc81b4652bfbd56456826637248"}}