{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QFHJ5KZRRLEMJDD5G3OQWEAVLB","short_pith_number":"pith:QFHJ5KZR","canonical_record":{"source":{"id":"2403.01698","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-04T03:21:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e577ddf7f4700c4fdc7bab061b6c9bb95c963810cfd9c9c549de0ee42d171ce2","abstract_canon_sha256":"01ad2047bbd705ede06878ba708f7fea8803fb66aedcd43361eb73faeb77e8bb"},"schema_version":"1.0"},"canonical_sha256":"814e9eab318ac8c48c7d36dd0b1015586020abb3e651376582ed1d29b541d621","source":{"kind":"arxiv","id":"2403.01698","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.01698","created_at":"2026-07-05T07:51:50Z"},{"alias_kind":"arxiv_version","alias_value":"2403.01698v1","created_at":"2026-07-05T07:51:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01698","created_at":"2026-07-05T07:51:50Z"},{"alias_kind":"pith_short_12","alias_value":"QFHJ5KZRRLEM","created_at":"2026-07-05T07:51:50Z"},{"alias_kind":"pith_short_16","alias_value":"QFHJ5KZRRLEMJDD5","created_at":"2026-07-05T07:51:50Z"},{"alias_kind":"pith_short_8","alias_value":"QFHJ5KZR","created_at":"2026-07-05T07:51:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QFHJ5KZRRLEMJDD5G3OQWEAVLB","target":"record","payload":{"canonical_record":{"source":{"id":"2403.01698","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-04T03:21:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e577ddf7f4700c4fdc7bab061b6c9bb95c963810cfd9c9c549de0ee42d171ce2","abstract_canon_sha256":"01ad2047bbd705ede06878ba708f7fea8803fb66aedcd43361eb73faeb77e8bb"},"schema_version":"1.0"},"canonical_sha256":"814e9eab318ac8c48c7d36dd0b1015586020abb3e651376582ed1d29b541d621","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:50.563223Z","signature_b64":"uOXblrMmHooRGOegwUfecDD7dcYgwBFus9UGGvVwkz67DXo5LI44E34pLS6Uc/SoaKnuMRZQBejGyXXkG1vODA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"814e9eab318ac8c48c7d36dd0b1015586020abb3e651376582ed1d29b541d621","last_reissued_at":"2026-07-05T07:51:50.562826Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:50.562826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.01698","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":"2026-07-05T07:51:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IaaaFBcH+mdjEZqDJnbHyqEUt+/40oxiYsRF/B8QaF5WJnyGF9sg27DLOdfa9nw15eG+pqZ0IVgCurOwdZHIDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:32:43.773452Z"},"content_sha256":"f8608d9e40c90809e04b198714fd4408745bf64ffa9c1b96c3a53b689ad654ca","schema_version":"1.0","event_id":"sha256:f8608d9e40c90809e04b198714fd4408745bf64ffa9c1b96c3a53b689ad654ca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QFHJ5KZRRLEMJDD5G3OQWEAVLB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hypertext Entity Extraction in Webpage","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bo Shao, Daxin Jiang, Hai Zhao, Linjun Shou, Ming Gong, Tianqiao Liu, Yifei Yang","submitted_at":"2024-03-04T03:21:40Z","abstract_excerpt":"Webpage entity extraction is a fundamental natural language processing task in both research and applications. Nowadays, the majority of webpage entity extraction models are trained on structured datasets which strive to retain textual content and its structure information. However, existing datasets all overlook the rich hypertext features (e.g., font color, font size) which show their effectiveness in previous works. To this end, we first collect a \\textbf{H}ypertext \\textbf{E}ntity \\textbf{E}xtraction \\textbf{D}ataset (\\textit{HEED}) from the e-commerce domains, scraping both the text and t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01698","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2403.01698/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T07:51:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NvBLxV/G31ekmwbn/38nKyaSRs81PrbU+ageLSkd3V/7Sfa16D0ZXZZurQM82QCwAkdJ7HFXiPrPStNu/XReAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:32:43.774093Z"},"content_sha256":"8ee489e929a9ef496c8c59ad2d53def8b809d5d447ff2b68e2662ca92156016b","schema_version":"1.0","event_id":"sha256:8ee489e929a9ef496c8c59ad2d53def8b809d5d447ff2b68e2662ca92156016b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QFHJ5KZRRLEMJDD5G3OQWEAVLB/bundle.json","state_url":"https://pith.science/pith/QFHJ5KZRRLEMJDD5G3OQWEAVLB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QFHJ5KZRRLEMJDD5G3OQWEAVLB/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":"2026-08-05T10:32:43Z","links":{"resolver":"https://pith.science/pith/QFHJ5KZRRLEMJDD5G3OQWEAVLB","bundle":"https://pith.science/pith/QFHJ5KZRRLEMJDD5G3OQWEAVLB/bundle.json","state":"https://pith.science/pith/QFHJ5KZRRLEMJDD5G3OQWEAVLB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QFHJ5KZRRLEMJDD5G3OQWEAVLB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QFHJ5KZRRLEMJDD5G3OQWEAVLB","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":"01ad2047bbd705ede06878ba708f7fea8803fb66aedcd43361eb73faeb77e8bb","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-04T03:21:40Z","title_canon_sha256":"e577ddf7f4700c4fdc7bab061b6c9bb95c963810cfd9c9c549de0ee42d171ce2"},"schema_version":"1.0","source":{"id":"2403.01698","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.01698","created_at":"2026-07-05T07:51:50Z"},{"alias_kind":"arxiv_version","alias_value":"2403.01698v1","created_at":"2026-07-05T07:51:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01698","created_at":"2026-07-05T07:51:50Z"},{"alias_kind":"pith_short_12","alias_value":"QFHJ5KZRRLEM","created_at":"2026-07-05T07:51:50Z"},{"alias_kind":"pith_short_16","alias_value":"QFHJ5KZRRLEMJDD5","created_at":"2026-07-05T07:51:50Z"},{"alias_kind":"pith_short_8","alias_value":"QFHJ5KZR","created_at":"2026-07-05T07:51:50Z"}],"graph_snapshots":[{"event_id":"sha256:8ee489e929a9ef496c8c59ad2d53def8b809d5d447ff2b68e2662ca92156016b","target":"graph","created_at":"2026-07-05T07:51:50Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2403.01698/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Webpage entity extraction is a fundamental natural language processing task in both research and applications. Nowadays, the majority of webpage entity extraction models are trained on structured datasets which strive to retain textual content and its structure information. However, existing datasets all overlook the rich hypertext features (e.g., font color, font size) which show their effectiveness in previous works. To this end, we first collect a \\textbf{H}ypertext \\textbf{E}ntity \\textbf{E}xtraction \\textbf{D}ataset (\\textit{HEED}) from the e-commerce domains, scraping both the text and t","authors_text":"Bo Shao, Daxin Jiang, Hai Zhao, Linjun Shou, Ming Gong, Tianqiao Liu, Yifei Yang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-04T03:21:40Z","title":"Hypertext Entity Extraction in Webpage"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01698","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:f8608d9e40c90809e04b198714fd4408745bf64ffa9c1b96c3a53b689ad654ca","target":"record","created_at":"2026-07-05T07:51:50Z","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":"01ad2047bbd705ede06878ba708f7fea8803fb66aedcd43361eb73faeb77e8bb","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-04T03:21:40Z","title_canon_sha256":"e577ddf7f4700c4fdc7bab061b6c9bb95c963810cfd9c9c549de0ee42d171ce2"},"schema_version":"1.0","source":{"id":"2403.01698","kind":"arxiv","version":1}},"canonical_sha256":"814e9eab318ac8c48c7d36dd0b1015586020abb3e651376582ed1d29b541d621","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"814e9eab318ac8c48c7d36dd0b1015586020abb3e651376582ed1d29b541d621","first_computed_at":"2026-07-05T07:51:50.562826Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:51:50.562826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uOXblrMmHooRGOegwUfecDD7dcYgwBFus9UGGvVwkz67DXo5LI44E34pLS6Uc/SoaKnuMRZQBejGyXXkG1vODA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:51:50.563223Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.01698","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8608d9e40c90809e04b198714fd4408745bf64ffa9c1b96c3a53b689ad654ca","sha256:8ee489e929a9ef496c8c59ad2d53def8b809d5d447ff2b68e2662ca92156016b"],"state_sha256":"5dba17e0cefc8ddf4fa56974e74f6188cd2aa60227cb225fff940859959e20c5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GmsuUK+jqNoyX4TiPBwGZF/N3MEPkxKKmfJYGrW6O1GqwakPE7fb6T47Ewe+e1ce2vUxQ+EXUlg+XPPjOJR6Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T10:32:43.781164Z","bundle_sha256":"a3ec8324a32042b3b1bdbd957389e2430baef6f64d78953c0acdb7a7914729a1"}}