{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3PRNFZTZNZEPTQQPC23DGS63K3","short_pith_number":"pith:3PRNFZTZ","schema_version":"1.0","canonical_sha256":"dbe2d2e6796e48f9c20f16b6334bdb56fc5b0917da5e4c80e9473f71220ceafe","source":{"kind":"arxiv","id":"2405.10918","version":2},"attestation_state":"computed","paper":{"title":"A Framework for Leveraging Partially-Labeled Data for Product Attribute-Value Identification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"D. Subhalingam, Keshav Kolluru, Mausam, Saurabh Singal","submitted_at":"2024-05-17T17:09:45Z","abstract_excerpt":"In the e-commerce domain, the accurate extraction of attribute-value pairs (e.g., Brand: Apple) from product titles and user search queries is crucial for enhancing search and recommendation systems. A major challenge with neural models for this task is the lack of high-quality training data, as the annotations for attribute-value pairs in the available datasets are often incomplete. To address this, we introduce GenToC, a model designed for training directly with partially-labeled data, eliminating the necessity for a fully annotated dataset. GenToC employs a marker-augmented generative model"},"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":"2405.10918","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-17T17:09:45Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"17ca5cd2ea220917acd5185573a1279485e24fdd0fa3b3dd9f9da98ba338c793","abstract_canon_sha256":"e306ba115d8e602d4d694db93d13d7921835feb15c91b488e8767a0a20a203eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:40.907452Z","signature_b64":"BbvZfINmnQ7wZ/veX/dFglF//o6tra1PhTS4xsEqPN522OYEDQKbZP+mkiJ6eRS0K9nayKz/wU3JwVloeYSvBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbe2d2e6796e48f9c20f16b6334bdb56fc5b0917da5e4c80e9473f71220ceafe","last_reissued_at":"2026-07-05T09:36:40.906918Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:40.906918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Framework for Leveraging Partially-Labeled Data for Product Attribute-Value Identification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"D. Subhalingam, Keshav Kolluru, Mausam, Saurabh Singal","submitted_at":"2024-05-17T17:09:45Z","abstract_excerpt":"In the e-commerce domain, the accurate extraction of attribute-value pairs (e.g., Brand: Apple) from product titles and user search queries is crucial for enhancing search and recommendation systems. A major challenge with neural models for this task is the lack of high-quality training data, as the annotations for attribute-value pairs in the available datasets are often incomplete. To address this, we introduce GenToC, a model designed for training directly with partially-labeled data, eliminating the necessity for a fully annotated dataset. GenToC employs a marker-augmented generative model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.10918","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/2405.10918/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":"2405.10918","created_at":"2026-07-05T09:36:40.906989+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.10918v2","created_at":"2026-07-05T09:36:40.906989+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.10918","created_at":"2026-07-05T09:36:40.906989+00:00"},{"alias_kind":"pith_short_12","alias_value":"3PRNFZTZNZEP","created_at":"2026-07-05T09:36:40.906989+00:00"},{"alias_kind":"pith_short_16","alias_value":"3PRNFZTZNZEPTQQP","created_at":"2026-07-05T09:36:40.906989+00:00"},{"alias_kind":"pith_short_8","alias_value":"3PRNFZTZ","created_at":"2026-07-05T09:36:40.906989+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/3PRNFZTZNZEPTQQPC23DGS63K3","json":"https://pith.science/pith/3PRNFZTZNZEPTQQPC23DGS63K3.json","graph_json":"https://pith.science/api/pith-number/3PRNFZTZNZEPTQQPC23DGS63K3/graph.json","events_json":"https://pith.science/api/pith-number/3PRNFZTZNZEPTQQPC23DGS63K3/events.json","paper":"https://pith.science/paper/3PRNFZTZ"},"agent_actions":{"view_html":"https://pith.science/pith/3PRNFZTZNZEPTQQPC23DGS63K3","download_json":"https://pith.science/pith/3PRNFZTZNZEPTQQPC23DGS63K3.json","view_paper":"https://pith.science/paper/3PRNFZTZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.10918&json=true","fetch_graph":"https://pith.science/api/pith-number/3PRNFZTZNZEPTQQPC23DGS63K3/graph.json","fetch_events":"https://pith.science/api/pith-number/3PRNFZTZNZEPTQQPC23DGS63K3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3PRNFZTZNZEPTQQPC23DGS63K3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3PRNFZTZNZEPTQQPC23DGS63K3/action/storage_attestation","attest_author":"https://pith.science/pith/3PRNFZTZNZEPTQQPC23DGS63K3/action/author_attestation","sign_citation":"https://pith.science/pith/3PRNFZTZNZEPTQQPC23DGS63K3/action/citation_signature","submit_replication":"https://pith.science/pith/3PRNFZTZNZEPTQQPC23DGS63K3/action/replication_record"}},"created_at":"2026-07-05T09:36:40.906989+00:00","updated_at":"2026-07-05T09:36:40.906989+00:00"}