{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:LGEXVP6GEHJLS2AQVH26IRN6HM","short_pith_number":"pith:LGEXVP6G","schema_version":"1.0","canonical_sha256":"59897abfc621d2b96810a9f5e445be3b2d52e137e6e922bf4fe40808745739f6","source":{"kind":"arxiv","id":"1506.08454","version":2},"attestation_state":"computed","paper":{"title":"WYSIWYE: An Algebra for Expressing Spatial and Textual Rules for Visual Information Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","cs.IR"],"primary_cat":"cs.CL","authors_text":"Knut Stolze, Prasad M Desphande, Raghu Krishnapuram, Ramakrishna Varadarajan, Vijil Chenthamarakshan","submitted_at":"2015-06-28T21:17:26Z","abstract_excerpt":"The visual layout of a webpage can provide valuable clues for certain types of Information Extraction (IE) tasks. In traditional rule based IE frameworks, these layout cues are mapped to rules that operate on the HTML source of the webpages. In contrast, we have developed a framework in which the rules can be specified directly at the layout level. This has many advantages, since the higher level of abstraction leads to simpler extraction rules that are largely independent of the source code of the page, and, therefore, more robust. It can also enable specification of new types of rules that a"},"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":"1506.08454","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-06-28T21:17:26Z","cross_cats_sorted":["cs.DB","cs.IR"],"title_canon_sha256":"51a4e971d14a90354149d44016a42e1489c7e763d42c8091eb6298ad066594d9","abstract_canon_sha256":"1eabdd2a0e2cc3028e3866fc1189cbd07fe691f216b00558f78dc295cf411aba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:03:53.055805Z","signature_b64":"HaDs8OeZG/nuF19zfSbtCgm4es5uvA3eQXkV4rQz5Nz1Cto1JXTBAGVXRJ2CkGs+oaAhlcCO/hAzSrHecv5PBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59897abfc621d2b96810a9f5e445be3b2d52e137e6e922bf4fe40808745739f6","last_reissued_at":"2026-05-18T01:03:53.054990Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:03:53.054990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WYSIWYE: An Algebra for Expressing Spatial and Textual Rules for Visual Information Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","cs.IR"],"primary_cat":"cs.CL","authors_text":"Knut Stolze, Prasad M Desphande, Raghu Krishnapuram, Ramakrishna Varadarajan, Vijil Chenthamarakshan","submitted_at":"2015-06-28T21:17:26Z","abstract_excerpt":"The visual layout of a webpage can provide valuable clues for certain types of Information Extraction (IE) tasks. In traditional rule based IE frameworks, these layout cues are mapped to rules that operate on the HTML source of the webpages. In contrast, we have developed a framework in which the rules can be specified directly at the layout level. This has many advantages, since the higher level of abstraction leads to simpler extraction rules that are largely independent of the source code of the page, and, therefore, more robust. It can also enable specification of new types of rules that a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.08454","kind":"arxiv","version":2},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1506.08454","created_at":"2026-05-18T01:03:53.055114+00:00"},{"alias_kind":"arxiv_version","alias_value":"1506.08454v2","created_at":"2026-05-18T01:03:53.055114+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.08454","created_at":"2026-05-18T01:03:53.055114+00:00"},{"alias_kind":"pith_short_12","alias_value":"LGEXVP6GEHJL","created_at":"2026-05-18T12:29:29.992203+00:00"},{"alias_kind":"pith_short_16","alias_value":"LGEXVP6GEHJLS2AQ","created_at":"2026-05-18T12:29:29.992203+00:00"},{"alias_kind":"pith_short_8","alias_value":"LGEXVP6G","created_at":"2026-05-18T12:29:29.992203+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LGEXVP6GEHJLS2AQVH26IRN6HM","json":"https://pith.science/pith/LGEXVP6GEHJLS2AQVH26IRN6HM.json","graph_json":"https://pith.science/api/pith-number/LGEXVP6GEHJLS2AQVH26IRN6HM/graph.json","events_json":"https://pith.science/api/pith-number/LGEXVP6GEHJLS2AQVH26IRN6HM/events.json","paper":"https://pith.science/paper/LGEXVP6G"},"agent_actions":{"view_html":"https://pith.science/pith/LGEXVP6GEHJLS2AQVH26IRN6HM","download_json":"https://pith.science/pith/LGEXVP6GEHJLS2AQVH26IRN6HM.json","view_paper":"https://pith.science/paper/LGEXVP6G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1506.08454&json=true","fetch_graph":"https://pith.science/api/pith-number/LGEXVP6GEHJLS2AQVH26IRN6HM/graph.json","fetch_events":"https://pith.science/api/pith-number/LGEXVP6GEHJLS2AQVH26IRN6HM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LGEXVP6GEHJLS2AQVH26IRN6HM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LGEXVP6GEHJLS2AQVH26IRN6HM/action/storage_attestation","attest_author":"https://pith.science/pith/LGEXVP6GEHJLS2AQVH26IRN6HM/action/author_attestation","sign_citation":"https://pith.science/pith/LGEXVP6GEHJLS2AQVH26IRN6HM/action/citation_signature","submit_replication":"https://pith.science/pith/LGEXVP6GEHJLS2AQVH26IRN6HM/action/replication_record"}},"created_at":"2026-05-18T01:03:53.055114+00:00","updated_at":"2026-05-18T01:03:53.055114+00:00"}