{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7UWX354AQ2ARLPIY4SID6EJLPM","short_pith_number":"pith:7UWX354A","schema_version":"1.0","canonical_sha256":"fd2d7df780868115bd18e4903f112b7b1a453982689996c83eb4134be9b76936","source":{"kind":"arxiv","id":"2409.12695","version":1},"attestation_state":"computed","paper":{"title":"Exploring Large Language Models for Product Attribute Value Identification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Barbara Plank, Johann Gamper, Kassem Sabeh, Mouna Kacimi, Robert Litschko","submitted_at":"2024-09-19T12:09:33Z","abstract_excerpt":"Product attribute value identification (PAVI) involves automatically identifying attributes and their values from product information, enabling features like product search, recommendation, and comparison. Existing methods primarily rely on fine-tuning pre-trained language models, such as BART and T5, which require extensive task-specific training data and struggle to generalize to new attributes. This paper explores large language models (LLMs), such as LLaMA and Mistral, as data-efficient and robust alternatives for PAVI. We propose various strategies: comparing one-step and two-step prompt-"},"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":"2409.12695","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-19T12:09:33Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"445d2edb234c8a14a8cab5a97fb0716e0dbb279a2a8ed301b36cb3ffa6db85a5","abstract_canon_sha256":"353861f53f4faddc3747948cc06d2c81044d91e94d1fc99317f485e614bc2e4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:10.833923Z","signature_b64":"6LnZ5SPINEEH1hAa50fj34oniooLB9nJVNTltF8m4frX3YNY814sAIm/mZsvIksgU5C1vEWFfH351VO/7nKSCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd2d7df780868115bd18e4903f112b7b1a453982689996c83eb4134be9b76936","last_reissued_at":"2026-07-05T09:09:10.833485Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:10.833485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Large Language Models for Product Attribute Value Identification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Barbara Plank, Johann Gamper, Kassem Sabeh, Mouna Kacimi, Robert Litschko","submitted_at":"2024-09-19T12:09:33Z","abstract_excerpt":"Product attribute value identification (PAVI) involves automatically identifying attributes and their values from product information, enabling features like product search, recommendation, and comparison. Existing methods primarily rely on fine-tuning pre-trained language models, such as BART and T5, which require extensive task-specific training data and struggle to generalize to new attributes. This paper explores large language models (LLMs), such as LLaMA and Mistral, as data-efficient and robust alternatives for PAVI. We propose various strategies: comparing one-step and two-step prompt-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12695","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/2409.12695/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":"2409.12695","created_at":"2026-07-05T09:09:10.833530+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.12695v1","created_at":"2026-07-05T09:09:10.833530+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12695","created_at":"2026-07-05T09:09:10.833530+00:00"},{"alias_kind":"pith_short_12","alias_value":"7UWX354AQ2AR","created_at":"2026-07-05T09:09:10.833530+00:00"},{"alias_kind":"pith_short_16","alias_value":"7UWX354AQ2ARLPIY","created_at":"2026-07-05T09:09:10.833530+00:00"},{"alias_kind":"pith_short_8","alias_value":"7UWX354A","created_at":"2026-07-05T09:09:10.833530+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":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7UWX354AQ2ARLPIY4SID6EJLPM","json":"https://pith.science/pith/7UWX354AQ2ARLPIY4SID6EJLPM.json","graph_json":"https://pith.science/api/pith-number/7UWX354AQ2ARLPIY4SID6EJLPM/graph.json","events_json":"https://pith.science/api/pith-number/7UWX354AQ2ARLPIY4SID6EJLPM/events.json","paper":"https://pith.science/paper/7UWX354A"},"agent_actions":{"view_html":"https://pith.science/pith/7UWX354AQ2ARLPIY4SID6EJLPM","download_json":"https://pith.science/pith/7UWX354AQ2ARLPIY4SID6EJLPM.json","view_paper":"https://pith.science/paper/7UWX354A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.12695&json=true","fetch_graph":"https://pith.science/api/pith-number/7UWX354AQ2ARLPIY4SID6EJLPM/graph.json","fetch_events":"https://pith.science/api/pith-number/7UWX354AQ2ARLPIY4SID6EJLPM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7UWX354AQ2ARLPIY4SID6EJLPM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7UWX354AQ2ARLPIY4SID6EJLPM/action/storage_attestation","attest_author":"https://pith.science/pith/7UWX354AQ2ARLPIY4SID6EJLPM/action/author_attestation","sign_citation":"https://pith.science/pith/7UWX354AQ2ARLPIY4SID6EJLPM/action/citation_signature","submit_replication":"https://pith.science/pith/7UWX354AQ2ARLPIY4SID6EJLPM/action/replication_record"}},"created_at":"2026-07-05T09:09:10.833530+00:00","updated_at":"2026-07-05T09:09:10.833530+00:00"}