{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:G22HECE4TQIPHI26LLTRZN2IYM","short_pith_number":"pith:G22HECE4","schema_version":"1.0","canonical_sha256":"36b472089c9c10f3a35e5ae71cb748c30c5c41964e98d87bc215d0e3066d8d07","source":{"kind":"arxiv","id":"2501.01237","version":2},"attestation_state":"computed","paper":{"title":"Self-Refinement Strategies for LLM-based Product Attribute Value Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Brinkmann, Christian Bizer","submitted_at":"2025-01-02T12:55:27Z","abstract_excerpt":"Structured product data, in the form of attribute-value pairs, is essential for e-commerce platforms to support features such as faceted product search and attribute-based product comparison. However, vendors often provide unstructured product descriptions, making attribute value extraction necessary to ensure data consistency and usability. Large language models (LLMs) have demonstrated their potential for product attribute value extraction in few-shot scenarios. Recent research has shown that self-refinement techniques can improve the performance of LLMs on tasks such as code generation and "},"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":"2501.01237","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-02T12:55:27Z","cross_cats_sorted":[],"title_canon_sha256":"8e207d6e8278599abaf6b3cace5e2188db4a937e1d4a1d6cce00aee8421b7a5b","abstract_canon_sha256":"88bccc79671457a43d3105175789162bddc2706ec597d79f997a57db0fd5aace"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:25.641268Z","signature_b64":"PBp4B+ncMrNJs2o29gfvoZ2kqIAFaWCY2d8gQ5omZBP/V7e/uMNZh2jrGdZyuRpjLeuP8NCIV7fpiKmYhL8pAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36b472089c9c10f3a35e5ae71cb748c30c5c41964e98d87bc215d0e3066d8d07","last_reissued_at":"2026-07-05T10:14:25.640770Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:25.640770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Refinement Strategies for LLM-based Product Attribute Value Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Brinkmann, Christian Bizer","submitted_at":"2025-01-02T12:55:27Z","abstract_excerpt":"Structured product data, in the form of attribute-value pairs, is essential for e-commerce platforms to support features such as faceted product search and attribute-based product comparison. However, vendors often provide unstructured product descriptions, making attribute value extraction necessary to ensure data consistency and usability. Large language models (LLMs) have demonstrated their potential for product attribute value extraction in few-shot scenarios. Recent research has shown that self-refinement techniques can improve the performance of LLMs on tasks such as code generation and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01237","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2501.01237/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":"2501.01237","created_at":"2026-07-05T10:14:25.640831+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.01237v2","created_at":"2026-07-05T10:14:25.640831+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01237","created_at":"2026-07-05T10:14:25.640831+00:00"},{"alias_kind":"pith_short_12","alias_value":"G22HECE4TQIP","created_at":"2026-07-05T10:14:25.640831+00:00"},{"alias_kind":"pith_short_16","alias_value":"G22HECE4TQIPHI26","created_at":"2026-07-05T10:14:25.640831+00:00"},{"alias_kind":"pith_short_8","alias_value":"G22HECE4","created_at":"2026-07-05T10:14:25.640831+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24655","citing_title":"AI-PAVE-Br: Leveraging Large Language Models for Enhanced Product Attribute Value Extraction through a Golden Set Approach","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G22HECE4TQIPHI26LLTRZN2IYM","json":"https://pith.science/pith/G22HECE4TQIPHI26LLTRZN2IYM.json","graph_json":"https://pith.science/api/pith-number/G22HECE4TQIPHI26LLTRZN2IYM/graph.json","events_json":"https://pith.science/api/pith-number/G22HECE4TQIPHI26LLTRZN2IYM/events.json","paper":"https://pith.science/paper/G22HECE4"},"agent_actions":{"view_html":"https://pith.science/pith/G22HECE4TQIPHI26LLTRZN2IYM","download_json":"https://pith.science/pith/G22HECE4TQIPHI26LLTRZN2IYM.json","view_paper":"https://pith.science/paper/G22HECE4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.01237&json=true","fetch_graph":"https://pith.science/api/pith-number/G22HECE4TQIPHI26LLTRZN2IYM/graph.json","fetch_events":"https://pith.science/api/pith-number/G22HECE4TQIPHI26LLTRZN2IYM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G22HECE4TQIPHI26LLTRZN2IYM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G22HECE4TQIPHI26LLTRZN2IYM/action/storage_attestation","attest_author":"https://pith.science/pith/G22HECE4TQIPHI26LLTRZN2IYM/action/author_attestation","sign_citation":"https://pith.science/pith/G22HECE4TQIPHI26LLTRZN2IYM/action/citation_signature","submit_replication":"https://pith.science/pith/G22HECE4TQIPHI26LLTRZN2IYM/action/replication_record"}},"created_at":"2026-07-05T10:14:25.640831+00:00","updated_at":"2026-07-05T10:14:25.640831+00:00"}