{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:GNU7P364VA2YN7BL76C7OTL6P7","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":"3b64c0ba459d30485464bbae0bef2e58a99d0e8eccaf96bd4ebefd1fc2a6796c","cross_cats_sorted":["cs.AI","cs.CL","cs.HC","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-24T00:21:46Z","title_canon_sha256":"b58330408ac4fc20797e82b9cf2191edecd71721750d27903fa45f7764c657bc"},"schema_version":"1.0","source":{"id":"2110.12320","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.12320","created_at":"2026-07-05T04:46:12Z"},{"alias_kind":"arxiv_version","alias_value":"2110.12320v1","created_at":"2026-07-05T04:46:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.12320","created_at":"2026-07-05T04:46:12Z"},{"alias_kind":"pith_short_12","alias_value":"GNU7P364VA2Y","created_at":"2026-07-05T04:46:12Z"},{"alias_kind":"pith_short_16","alias_value":"GNU7P364VA2YN7BL","created_at":"2026-07-05T04:46:12Z"},{"alias_kind":"pith_short_8","alias_value":"GNU7P364","created_at":"2026-07-05T04:46:12Z"}],"graph_snapshots":[{"event_id":"sha256:ea5a932406c2fcbe923bc56d4347a9e67ebc8dc535cdea1a66e30e54589885b3","target":"graph","created_at":"2026-07-05T04:46:12Z","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/2110.12320/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Webpage information extraction (WIE) is an important step to create knowledge bases. For this, classical WIE methods leverage the Document Object Model (DOM) tree of a website. However, use of the DOM tree poses significant challenges as context and appearance are encoded in an abstract manner. To address this challenge we propose to reformulate WIE as a context-aware Webpage Object Detection task. Specifically, we develop a Context-aware Visual Attention-based (CoVA) detection pipeline which combines appearance features with syntactical structure from the DOM tree. To study the approach we co","authors_text":"Alexander Schwing, Anurendra Kumar, Jingjin Wang, Keval Morabia, Kevin Chen-Chuan Chang","cross_cats":["cs.AI","cs.CL","cs.HC","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-24T00:21:46Z","title":"CoVA: Context-aware Visual Attention for Webpage Information Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.12320","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:ce42d72afa656d03faaadf6f93b491383a879ea239aa174d19b3502a128d7c9d","target":"record","created_at":"2026-07-05T04:46:12Z","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":"3b64c0ba459d30485464bbae0bef2e58a99d0e8eccaf96bd4ebefd1fc2a6796c","cross_cats_sorted":["cs.AI","cs.CL","cs.HC","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-24T00:21:46Z","title_canon_sha256":"b58330408ac4fc20797e82b9cf2191edecd71721750d27903fa45f7764c657bc"},"schema_version":"1.0","source":{"id":"2110.12320","kind":"arxiv","version":1}},"canonical_sha256":"3369f7efdca83586fc2bff85f74d7e7ffbb5275fdc245afdba09e60c1eeda0f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3369f7efdca83586fc2bff85f74d7e7ffbb5275fdc245afdba09e60c1eeda0f1","first_computed_at":"2026-07-05T04:46:12.473583Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:46:12.473583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UMzbvzkAEMqk+jN0cHiEuq4ChQ7LEYdeM+/0PkaxFTyAtgypO9H9Lpg+Z6Q1YHyXo8+BWCd9YERZtXu1fWwtAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:46:12.474002Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.12320","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce42d72afa656d03faaadf6f93b491383a879ea239aa174d19b3502a128d7c9d","sha256:ea5a932406c2fcbe923bc56d4347a9e67ebc8dc535cdea1a66e30e54589885b3"],"state_sha256":"f306a80eedae72e9b068be727e82404262cebc93d105dafee4e4c4f7c7db2ed0"}