{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2Y4XBD6FM4CCNV5MLD6SMYMJP7","short_pith_number":"pith:2Y4XBD6F","schema_version":"1.0","canonical_sha256":"d639708fc5670426d7ac58fd2661897ffa2ff3a93eab5fbf3de73973b50ec5d2","source":{"kind":"arxiv","id":"2403.02130","version":4},"attestation_state":"computed","paper":{"title":"Using LLMs for the Extraction and Normalization of Product Attribute Values","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Brinkmann, Christian Bizer, Nick Baumann","submitted_at":"2024-03-04T15:39:59Z","abstract_excerpt":"Product offers on e-commerce websites often consist of a product title and a textual product description. In order to enable features such as faceted product search or to generate product comparison tables, it is necessary to extract structured attribute-value pairs from the unstructured product titles and descriptions and to normalize the extracted values to a single, unified scale for each attribute. This paper explores the potential of using large language models (LLMs), such as GPT-3.5 and GPT-4, to extract and normalize attribute values from product titles and descriptions. We experiment "},"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":"2403.02130","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-04T15:39:59Z","cross_cats_sorted":[],"title_canon_sha256":"28a2735f330637156c393020619f42681b4bd7c099cba284d174b34e12083a3e","abstract_canon_sha256":"9eff1c7646ce07aca0969772f4cb0e2b24aeec1403cf61f3bba4793128d92d02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:01:30.603857Z","signature_b64":"ElyhpEiPTUTgdZel8lzu4hygfMIvgIy1MiZkKXgIyLTSsGGkTi4QJKQ9dHVKkjUz+3JPCJie2QrBNW618lSMCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d639708fc5670426d7ac58fd2661897ffa2ff3a93eab5fbf3de73973b50ec5d2","last_reissued_at":"2026-07-05T09:01:30.603377Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:01:30.603377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using LLMs for the Extraction and Normalization of Product Attribute Values","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Brinkmann, Christian Bizer, Nick Baumann","submitted_at":"2024-03-04T15:39:59Z","abstract_excerpt":"Product offers on e-commerce websites often consist of a product title and a textual product description. In order to enable features such as faceted product search or to generate product comparison tables, it is necessary to extract structured attribute-value pairs from the unstructured product titles and descriptions and to normalize the extracted values to a single, unified scale for each attribute. This paper explores the potential of using large language models (LLMs), such as GPT-3.5 and GPT-4, to extract and normalize attribute values from product titles and descriptions. We experiment "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.02130","kind":"arxiv","version":4},"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/2403.02130/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":"2403.02130","created_at":"2026-07-05T09:01:30.603443+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.02130v4","created_at":"2026-07-05T09:01:30.603443+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.02130","created_at":"2026-07-05T09:01:30.603443+00:00"},{"alias_kind":"pith_short_12","alias_value":"2Y4XBD6FM4CC","created_at":"2026-07-05T09:01:30.603443+00:00"},{"alias_kind":"pith_short_16","alias_value":"2Y4XBD6FM4CCNV5M","created_at":"2026-07-05T09:01:30.603443+00:00"},{"alias_kind":"pith_short_8","alias_value":"2Y4XBD6F","created_at":"2026-07-05T09:01:30.603443+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/2Y4XBD6FM4CCNV5MLD6SMYMJP7","json":"https://pith.science/pith/2Y4XBD6FM4CCNV5MLD6SMYMJP7.json","graph_json":"https://pith.science/api/pith-number/2Y4XBD6FM4CCNV5MLD6SMYMJP7/graph.json","events_json":"https://pith.science/api/pith-number/2Y4XBD6FM4CCNV5MLD6SMYMJP7/events.json","paper":"https://pith.science/paper/2Y4XBD6F"},"agent_actions":{"view_html":"https://pith.science/pith/2Y4XBD6FM4CCNV5MLD6SMYMJP7","download_json":"https://pith.science/pith/2Y4XBD6FM4CCNV5MLD6SMYMJP7.json","view_paper":"https://pith.science/paper/2Y4XBD6F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.02130&json=true","fetch_graph":"https://pith.science/api/pith-number/2Y4XBD6FM4CCNV5MLD6SMYMJP7/graph.json","fetch_events":"https://pith.science/api/pith-number/2Y4XBD6FM4CCNV5MLD6SMYMJP7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2Y4XBD6FM4CCNV5MLD6SMYMJP7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2Y4XBD6FM4CCNV5MLD6SMYMJP7/action/storage_attestation","attest_author":"https://pith.science/pith/2Y4XBD6FM4CCNV5MLD6SMYMJP7/action/author_attestation","sign_citation":"https://pith.science/pith/2Y4XBD6FM4CCNV5MLD6SMYMJP7/action/citation_signature","submit_replication":"https://pith.science/pith/2Y4XBD6FM4CCNV5MLD6SMYMJP7/action/replication_record"}},"created_at":"2026-07-05T09:01:30.603443+00:00","updated_at":"2026-07-05T09:01:30.603443+00:00"}