{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GNU7P364VA2YN7BL76C7OTL6P7","short_pith_number":"pith:GNU7P364","schema_version":"1.0","canonical_sha256":"3369f7efdca83586fc2bff85f74d7e7ffbb5275fdc245afdba09e60c1eeda0f1","source":{"kind":"arxiv","id":"2110.12320","version":1},"attestation_state":"computed","paper":{"title":"CoVA: Context-aware Visual Attention for Webpage Information Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.HC","cs.IR"],"primary_cat":"cs.CV","authors_text":"Alexander Schwing, Anurendra Kumar, Jingjin Wang, Keval Morabia, Kevin Chen-Chuan Chang","submitted_at":"2021-10-24T00:21:46Z","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"},"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":"2110.12320","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-24T00:21:46Z","cross_cats_sorted":["cs.AI","cs.CL","cs.HC","cs.IR"],"title_canon_sha256":"b58330408ac4fc20797e82b9cf2191edecd71721750d27903fa45f7764c657bc","abstract_canon_sha256":"3b64c0ba459d30485464bbae0bef2e58a99d0e8eccaf96bd4ebefd1fc2a6796c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:46:12.474002Z","signature_b64":"UMzbvzkAEMqk+jN0cHiEuq4ChQ7LEYdeM+/0PkaxFTyAtgypO9H9Lpg+Z6Q1YHyXo8+BWCd9YERZtXu1fWwtAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3369f7efdca83586fc2bff85f74d7e7ffbb5275fdc245afdba09e60c1eeda0f1","last_reissued_at":"2026-07-05T04:46:12.473583Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:46:12.473583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoVA: Context-aware Visual Attention for Webpage Information Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.HC","cs.IR"],"primary_cat":"cs.CV","authors_text":"Alexander Schwing, Anurendra Kumar, Jingjin Wang, Keval Morabia, Kevin Chen-Chuan Chang","submitted_at":"2021-10-24T00:21:46Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.12320","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/2110.12320/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2110.12320","created_at":"2026-07-05T04:46:12.473637+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.12320v1","created_at":"2026-07-05T04:46:12.473637+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.12320","created_at":"2026-07-05T04:46:12.473637+00:00"},{"alias_kind":"pith_short_12","alias_value":"GNU7P364VA2Y","created_at":"2026-07-05T04:46:12.473637+00:00"},{"alias_kind":"pith_short_16","alias_value":"GNU7P364VA2YN7BL","created_at":"2026-07-05T04:46:12.473637+00:00"},{"alias_kind":"pith_short_8","alias_value":"GNU7P364","created_at":"2026-07-05T04:46:12.473637+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.02167","citing_title":"Multilingual Attribute Extraction from News Web Pages","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GNU7P364VA2YN7BL76C7OTL6P7","json":"https://pith.science/pith/GNU7P364VA2YN7BL76C7OTL6P7.json","graph_json":"https://pith.science/api/pith-number/GNU7P364VA2YN7BL76C7OTL6P7/graph.json","events_json":"https://pith.science/api/pith-number/GNU7P364VA2YN7BL76C7OTL6P7/events.json","paper":"https://pith.science/paper/GNU7P364"},"agent_actions":{"view_html":"https://pith.science/pith/GNU7P364VA2YN7BL76C7OTL6P7","download_json":"https://pith.science/pith/GNU7P364VA2YN7BL76C7OTL6P7.json","view_paper":"https://pith.science/paper/GNU7P364","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.12320&json=true","fetch_graph":"https://pith.science/api/pith-number/GNU7P364VA2YN7BL76C7OTL6P7/graph.json","fetch_events":"https://pith.science/api/pith-number/GNU7P364VA2YN7BL76C7OTL6P7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GNU7P364VA2YN7BL76C7OTL6P7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GNU7P364VA2YN7BL76C7OTL6P7/action/storage_attestation","attest_author":"https://pith.science/pith/GNU7P364VA2YN7BL76C7OTL6P7/action/author_attestation","sign_citation":"https://pith.science/pith/GNU7P364VA2YN7BL76C7OTL6P7/action/citation_signature","submit_replication":"https://pith.science/pith/GNU7P364VA2YN7BL76C7OTL6P7/action/replication_record"}},"created_at":"2026-07-05T04:46:12.473637+00:00","updated_at":"2026-07-05T04:46:12.473637+00:00"}