{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:OQGVSUKD3PD5NJAHHDQSUAMVNK","short_pith_number":"pith:OQGVSUKD","canonical_record":{"source":{"id":"1606.04429","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2016-06-14T15:44:52Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7fe187184e2e4130425e5a5d3c97e947bc80c949471c471892bba86955052b05","abstract_canon_sha256":"2a161e99c733189109d818bedc3cff41206b1c497ab56fc945105b23c49b1ac1"},"schema_version":"1.0"},"canonical_sha256":"740d595143dbc7d6a40738e12a01956a894156d573a5bdcf084a034c919fdae4","source":{"kind":"arxiv","id":"1606.04429","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.04429","created_at":"2026-05-18T01:12:25Z"},{"alias_kind":"arxiv_version","alias_value":"1606.04429v1","created_at":"2026-05-18T01:12:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.04429","created_at":"2026-05-18T01:12:25Z"},{"alias_kind":"pith_short_12","alias_value":"OQGVSUKD3PD5","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"OQGVSUKD3PD5NJAH","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"OQGVSUKD","created_at":"2026-05-18T12:30:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:OQGVSUKD3PD5NJAHHDQSUAMVNK","target":"record","payload":{"canonical_record":{"source":{"id":"1606.04429","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2016-06-14T15:44:52Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7fe187184e2e4130425e5a5d3c97e947bc80c949471c471892bba86955052b05","abstract_canon_sha256":"2a161e99c733189109d818bedc3cff41206b1c497ab56fc945105b23c49b1ac1"},"schema_version":"1.0"},"canonical_sha256":"740d595143dbc7d6a40738e12a01956a894156d573a5bdcf084a034c919fdae4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:25.617829Z","signature_b64":"2NdPtywNn7SAZpOFVDsjNbjqBMkm/1aZ/g/aMDlyUNKMSQHXiJssCJZH6QmqxuoxuwbcSgIBZkQcgdwTfWHvCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"740d595143dbc7d6a40738e12a01956a894156d573a5bdcf084a034c919fdae4","last_reissued_at":"2026-05-18T01:12:25.617502Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:25.617502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1606.04429","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":"2026-05-18T01:12:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OCADRZbeaBgj/gH3AltcYxG0YvkJzLgcc75gHrJh7btoGtltKRbpn6l5xX3J6Dv1jOst+SttbrvK/XMFoxiUAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T01:40:49.364538Z"},"content_sha256":"733d2c70587cc020f75db2edf694ae20aebd1bb11aba89c067b09b111f34309a","schema_version":"1.0","event_id":"sha256:733d2c70587cc020f75db2edf694ae20aebd1bb11aba89c067b09b111f34309a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:OQGVSUKD3PD5NJAHHDQSUAMVNK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Using Fuzzy Logic to Leverage HTML Markup for Web Page Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Alberto P. Garc\\'ia-Plaza, Arkaitz Zubiaga, Raquel Mart\\'inez, V\\'ictor Fresno","submitted_at":"2016-06-14T15:44:52Z","abstract_excerpt":"The selection of a suitable document representation approach plays a crucial role in the performance of a document clustering task. Being able to pick out representative words within a document can lead to substantial improvements in document clustering. In the case of web documents, the HTML markup that defines the layout of the content provides additional structural information that can be further exploited to identify representative words. In this paper we introduce a fuzzy term weighing approach that makes the most of the HTML structure for document clustering. We set forth and build on th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.04429","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":"2026-05-18T01:12:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+FRjuL+qC5froLrSjmusCqDIIc7Nc9k9euxgdwN1E2Ov7bLuxAOXgcIKl9ql4uviWOaDniU/Fze0Eo+/SeyYAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T01:40:49.364895Z"},"content_sha256":"f61619d8fb486e5207ad08adf6331e6b4fc2f1cf952f64ce652ef96a126bc852","schema_version":"1.0","event_id":"sha256:f61619d8fb486e5207ad08adf6331e6b4fc2f1cf952f64ce652ef96a126bc852"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OQGVSUKD3PD5NJAHHDQSUAMVNK/bundle.json","state_url":"https://pith.science/pith/OQGVSUKD3PD5NJAHHDQSUAMVNK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OQGVSUKD3PD5NJAHHDQSUAMVNK/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":"2026-06-03T01:40:49Z","links":{"resolver":"https://pith.science/pith/OQGVSUKD3PD5NJAHHDQSUAMVNK","bundle":"https://pith.science/pith/OQGVSUKD3PD5NJAHHDQSUAMVNK/bundle.json","state":"https://pith.science/pith/OQGVSUKD3PD5NJAHHDQSUAMVNK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OQGVSUKD3PD5NJAHHDQSUAMVNK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:OQGVSUKD3PD5NJAHHDQSUAMVNK","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":"2a161e99c733189109d818bedc3cff41206b1c497ab56fc945105b23c49b1ac1","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2016-06-14T15:44:52Z","title_canon_sha256":"7fe187184e2e4130425e5a5d3c97e947bc80c949471c471892bba86955052b05"},"schema_version":"1.0","source":{"id":"1606.04429","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.04429","created_at":"2026-05-18T01:12:25Z"},{"alias_kind":"arxiv_version","alias_value":"1606.04429v1","created_at":"2026-05-18T01:12:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.04429","created_at":"2026-05-18T01:12:25Z"},{"alias_kind":"pith_short_12","alias_value":"OQGVSUKD3PD5","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"OQGVSUKD3PD5NJAH","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"OQGVSUKD","created_at":"2026-05-18T12:30:36Z"}],"graph_snapshots":[{"event_id":"sha256:f61619d8fb486e5207ad08adf6331e6b4fc2f1cf952f64ce652ef96a126bc852","target":"graph","created_at":"2026-05-18T01:12:25Z","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":"The selection of a suitable document representation approach plays a crucial role in the performance of a document clustering task. Being able to pick out representative words within a document can lead to substantial improvements in document clustering. In the case of web documents, the HTML markup that defines the layout of the content provides additional structural information that can be further exploited to identify representative words. In this paper we introduce a fuzzy term weighing approach that makes the most of the HTML structure for document clustering. We set forth and build on th","authors_text":"Alberto P. Garc\\'ia-Plaza, Arkaitz Zubiaga, Raquel Mart\\'inez, V\\'ictor Fresno","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2016-06-14T15:44:52Z","title":"Using Fuzzy Logic to Leverage HTML Markup for Web Page Representation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.04429","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":"sha256:733d2c70587cc020f75db2edf694ae20aebd1bb11aba89c067b09b111f34309a","target":"record","created_at":"2026-05-18T01:12:25Z","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":"2a161e99c733189109d818bedc3cff41206b1c497ab56fc945105b23c49b1ac1","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2016-06-14T15:44:52Z","title_canon_sha256":"7fe187184e2e4130425e5a5d3c97e947bc80c949471c471892bba86955052b05"},"schema_version":"1.0","source":{"id":"1606.04429","kind":"arxiv","version":1}},"canonical_sha256":"740d595143dbc7d6a40738e12a01956a894156d573a5bdcf084a034c919fdae4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"740d595143dbc7d6a40738e12a01956a894156d573a5bdcf084a034c919fdae4","first_computed_at":"2026-05-18T01:12:25.617502Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:12:25.617502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2NdPtywNn7SAZpOFVDsjNbjqBMkm/1aZ/g/aMDlyUNKMSQHXiJssCJZH6QmqxuoxuwbcSgIBZkQcgdwTfWHvCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:12:25.617829Z","signed_message":"canonical_sha256_bytes"},"source_id":"1606.04429","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:733d2c70587cc020f75db2edf694ae20aebd1bb11aba89c067b09b111f34309a","sha256:f61619d8fb486e5207ad08adf6331e6b4fc2f1cf952f64ce652ef96a126bc852"],"state_sha256":"32e15078682fbf85df73a98b77cfaa3708510f7fa7fcf823b661e3788dc55376"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iEclx6ZIh5u4aVvzbutkGyFSYLnfIWe3BInAb+Y/k9FpXB24FK4T5w7blcj+Mf74Wkw9APgEGcsP7+p6Yb/NCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T01:40:49.366878Z","bundle_sha256":"373cceb6840bdfa21f97e4e55b20fec5f174d6790d50b02be556109bdc9ee289"}}