{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2Y4XBD6FM4CCNV5MLD6SMYMJP7","short_pith_number":"pith:2Y4XBD6F","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"},"canonical_sha256":"d639708fc5670426d7ac58fd2661897ffa2ff3a93eab5fbf3de73973b50ec5d2","source":{"kind":"arxiv","id":"2403.02130","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.02130","created_at":"2026-07-05T09:01:30Z"},{"alias_kind":"arxiv_version","alias_value":"2403.02130v4","created_at":"2026-07-05T09:01:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.02130","created_at":"2026-07-05T09:01:30Z"},{"alias_kind":"pith_short_12","alias_value":"2Y4XBD6FM4CC","created_at":"2026-07-05T09:01:30Z"},{"alias_kind":"pith_short_16","alias_value":"2Y4XBD6FM4CCNV5M","created_at":"2026-07-05T09:01:30Z"},{"alias_kind":"pith_short_8","alias_value":"2Y4XBD6F","created_at":"2026-07-05T09:01:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2Y4XBD6FM4CCNV5MLD6SMYMJP7","target":"record","payload":{"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"},"canonical_sha256":"d639708fc5670426d7ac58fd2661897ffa2ff3a93eab5fbf3de73973b50ec5d2","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"},"source_kind":"arxiv","source_id":"2403.02130","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:01:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tOGsbaEzhGyQL4cIfMi54lTSp+NRMuL65WlajecgMCVeRnDc0HTjAL53yuCm4TKo8stu1m5+/ULCU4iOcplvCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T13:31:36.203576Z"},"content_sha256":"8a07ec21c1b61058411aa506d57ef3dff8a7f59a06120464ed25e70bcfc7f9ab","schema_version":"1.0","event_id":"sha256:8a07ec21c1b61058411aa506d57ef3dff8a7f59a06120464ed25e70bcfc7f9ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2Y4XBD6FM4CCNV5MLD6SMYMJP7","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:01:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DQEZSFZy2LV/rLV4+HH8oAtESvIIjr29iNN75W2px0EZZw+s0gLC7T44r122S9C6xPIhMn4/RYJu6RjbTzatCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T13:31:36.204404Z"},"content_sha256":"05e91503bb1cc77810c70566c40cbefc28f75c607c163ded790d96a097625fb6","schema_version":"1.0","event_id":"sha256:05e91503bb1cc77810c70566c40cbefc28f75c607c163ded790d96a097625fb6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2Y4XBD6FM4CCNV5MLD6SMYMJP7/bundle.json","state_url":"https://pith.science/pith/2Y4XBD6FM4CCNV5MLD6SMYMJP7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2Y4XBD6FM4CCNV5MLD6SMYMJP7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-20T13:31:36Z","links":{"resolver":"https://pith.science/pith/2Y4XBD6FM4CCNV5MLD6SMYMJP7","bundle":"https://pith.science/pith/2Y4XBD6FM4CCNV5MLD6SMYMJP7/bundle.json","state":"https://pith.science/pith/2Y4XBD6FM4CCNV5MLD6SMYMJP7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2Y4XBD6FM4CCNV5MLD6SMYMJP7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2Y4XBD6FM4CCNV5MLD6SMYMJP7","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":"9eff1c7646ce07aca0969772f4cb0e2b24aeec1403cf61f3bba4793128d92d02","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-04T15:39:59Z","title_canon_sha256":"28a2735f330637156c393020619f42681b4bd7c099cba284d174b34e12083a3e"},"schema_version":"1.0","source":{"id":"2403.02130","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.02130","created_at":"2026-07-05T09:01:30Z"},{"alias_kind":"arxiv_version","alias_value":"2403.02130v4","created_at":"2026-07-05T09:01:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.02130","created_at":"2026-07-05T09:01:30Z"},{"alias_kind":"pith_short_12","alias_value":"2Y4XBD6FM4CC","created_at":"2026-07-05T09:01:30Z"},{"alias_kind":"pith_short_16","alias_value":"2Y4XBD6FM4CCNV5M","created_at":"2026-07-05T09:01:30Z"},{"alias_kind":"pith_short_8","alias_value":"2Y4XBD6F","created_at":"2026-07-05T09:01:30Z"}],"graph_snapshots":[{"event_id":"sha256:05e91503bb1cc77810c70566c40cbefc28f75c607c163ded790d96a097625fb6","target":"graph","created_at":"2026-07-05T09:01:30Z","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/2403.02130/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Alexander Brinkmann, Christian Bizer, Nick Baumann","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-04T15:39:59Z","title":"Using LLMs for the Extraction and Normalization of Product Attribute Values"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.02130","kind":"arxiv","version":4},"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":"sha256:8a07ec21c1b61058411aa506d57ef3dff8a7f59a06120464ed25e70bcfc7f9ab","target":"record","created_at":"2026-07-05T09:01:30Z","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":"9eff1c7646ce07aca0969772f4cb0e2b24aeec1403cf61f3bba4793128d92d02","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-04T15:39:59Z","title_canon_sha256":"28a2735f330637156c393020619f42681b4bd7c099cba284d174b34e12083a3e"},"schema_version":"1.0","source":{"id":"2403.02130","kind":"arxiv","version":4}},"canonical_sha256":"d639708fc5670426d7ac58fd2661897ffa2ff3a93eab5fbf3de73973b50ec5d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d639708fc5670426d7ac58fd2661897ffa2ff3a93eab5fbf3de73973b50ec5d2","first_computed_at":"2026-07-05T09:01:30.603377Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:01:30.603377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ElyhpEiPTUTgdZel8lzu4hygfMIvgIy1MiZkKXgIyLTSsGGkTi4QJKQ9dHVKkjUz+3JPCJie2QrBNW618lSMCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:01:30.603857Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.02130","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a07ec21c1b61058411aa506d57ef3dff8a7f59a06120464ed25e70bcfc7f9ab","sha256:05e91503bb1cc77810c70566c40cbefc28f75c607c163ded790d96a097625fb6"],"state_sha256":"cfc1ceffa91523a0175180f5f72128c70467eb6e502090f0711ce41fe8edcb11"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OD+bTdpkR+A55sQyTQACzWb1Et5musXRAD9z08WyBwlhofPj+Fl3EvMIq5CWhVICmvlMcYS2wQctYUPnS0SaDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T13:31:36.208773Z","bundle_sha256":"030436b5f601ebb390318ee935445bfbd096c1562567f8c4a92902bc2ff96310"}}