{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:R6TCYVAWSLMSCQPZ7IEWRUGEVX","short_pith_number":"pith:R6TCYVAW","schema_version":"1.0","canonical_sha256":"8fa62c541692d92141f9fa0968d0c4adfb971e0c2520cd21b1d85e21083e9894","source":{"kind":"arxiv","id":"2201.02896","version":1},"attestation_state":"computed","paper":{"title":"Extraction of Product Specifications from the Web -- Going Beyond Tables and Lists","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Ashish Kulkarni, Govind Krishnan Gangadhar","submitted_at":"2022-01-08T22:25:32Z","abstract_excerpt":"E-commerce product pages on the web often present product specification data in structured tabular blocks. Extraction of these product attribute-value specifications has benefited applications like product catalogue curation, search, question answering, and others. However, across different Websites, there is a wide variety of HTML elements (like <table>, <ul>, <div>, <span>, <dl> etc.) typically used to render these blocks that makes their automatic extraction a challenge. Most of the current research has focused on extracting product specifications from tables and lists and, therefore, suffe"},"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":"2201.02896","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-01-08T22:25:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ca3a766069fa9ac724145fbdc40cd57f419f8d487177b8c3ca4fe014616fde63","abstract_canon_sha256":"14f1200eaf1196d43588c66f677056819c699a4022bd8c4e7b432148c31f06c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:46:49.781687Z","signature_b64":"nMbdGZytScHLEuUmU7BadbtnpoHz0kRLSxJZ8jB0audxAZG2qUWtbUY3yicbWsc+pkeu0guB0MIplnePEoDzAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fa62c541692d92141f9fa0968d0c4adfb971e0c2520cd21b1d85e21083e9894","last_reissued_at":"2026-07-05T03:46:49.781266Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:46:49.781266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Extraction of Product Specifications from the Web -- Going Beyond Tables and Lists","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Ashish Kulkarni, Govind Krishnan Gangadhar","submitted_at":"2022-01-08T22:25:32Z","abstract_excerpt":"E-commerce product pages on the web often present product specification data in structured tabular blocks. Extraction of these product attribute-value specifications has benefited applications like product catalogue curation, search, question answering, and others. However, across different Websites, there is a wide variety of HTML elements (like <table>, <ul>, <div>, <span>, <dl> etc.) typically used to render these blocks that makes their automatic extraction a challenge. Most of the current research has focused on extracting product specifications from tables and lists and, therefore, suffe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.02896","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/2201.02896/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":"2201.02896","created_at":"2026-07-05T03:46:49.781328+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.02896v1","created_at":"2026-07-05T03:46:49.781328+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.02896","created_at":"2026-07-05T03:46:49.781328+00:00"},{"alias_kind":"pith_short_12","alias_value":"R6TCYVAWSLMS","created_at":"2026-07-05T03:46:49.781328+00:00"},{"alias_kind":"pith_short_16","alias_value":"R6TCYVAWSLMSCQPZ","created_at":"2026-07-05T03:46:49.781328+00:00"},{"alias_kind":"pith_short_8","alias_value":"R6TCYVAW","created_at":"2026-07-05T03:46:49.781328+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/R6TCYVAWSLMSCQPZ7IEWRUGEVX","json":"https://pith.science/pith/R6TCYVAWSLMSCQPZ7IEWRUGEVX.json","graph_json":"https://pith.science/api/pith-number/R6TCYVAWSLMSCQPZ7IEWRUGEVX/graph.json","events_json":"https://pith.science/api/pith-number/R6TCYVAWSLMSCQPZ7IEWRUGEVX/events.json","paper":"https://pith.science/paper/R6TCYVAW"},"agent_actions":{"view_html":"https://pith.science/pith/R6TCYVAWSLMSCQPZ7IEWRUGEVX","download_json":"https://pith.science/pith/R6TCYVAWSLMSCQPZ7IEWRUGEVX.json","view_paper":"https://pith.science/paper/R6TCYVAW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.02896&json=true","fetch_graph":"https://pith.science/api/pith-number/R6TCYVAWSLMSCQPZ7IEWRUGEVX/graph.json","fetch_events":"https://pith.science/api/pith-number/R6TCYVAWSLMSCQPZ7IEWRUGEVX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R6TCYVAWSLMSCQPZ7IEWRUGEVX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R6TCYVAWSLMSCQPZ7IEWRUGEVX/action/storage_attestation","attest_author":"https://pith.science/pith/R6TCYVAWSLMSCQPZ7IEWRUGEVX/action/author_attestation","sign_citation":"https://pith.science/pith/R6TCYVAWSLMSCQPZ7IEWRUGEVX/action/citation_signature","submit_replication":"https://pith.science/pith/R6TCYVAWSLMSCQPZ7IEWRUGEVX/action/replication_record"}},"created_at":"2026-07-05T03:46:49.781328+00:00","updated_at":"2026-07-05T03:46:49.781328+00:00"}