{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3PRNFZTZNZEPTQQPC23DGS63K3","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":"e306ba115d8e602d4d694db93d13d7921835feb15c91b488e8767a0a20a203eb","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-17T17:09:45Z","title_canon_sha256":"17ca5cd2ea220917acd5185573a1279485e24fdd0fa3b3dd9f9da98ba338c793"},"schema_version":"1.0","source":{"id":"2405.10918","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.10918","created_at":"2026-07-05T09:36:40Z"},{"alias_kind":"arxiv_version","alias_value":"2405.10918v2","created_at":"2026-07-05T09:36:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.10918","created_at":"2026-07-05T09:36:40Z"},{"alias_kind":"pith_short_12","alias_value":"3PRNFZTZNZEP","created_at":"2026-07-05T09:36:40Z"},{"alias_kind":"pith_short_16","alias_value":"3PRNFZTZNZEPTQQP","created_at":"2026-07-05T09:36:40Z"},{"alias_kind":"pith_short_8","alias_value":"3PRNFZTZ","created_at":"2026-07-05T09:36:40Z"}],"graph_snapshots":[{"event_id":"sha256:d7f5dc6f6a8dfab689fb68b86fcd6e1e01b2e1c47bf0fc3c9df57e7fa2f5ab58","target":"graph","created_at":"2026-07-05T09:36:40Z","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/2405.10918/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"D. Subhalingam, Keshav Kolluru, Mausam, Saurabh Singal","cross_cats":["cs.AI","cs.IR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-17T17:09:45Z","title":"A Framework for Leveraging Partially-Labeled Data for Product Attribute-Value Identification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.10918","kind":"arxiv","version":2},"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":"sha256:16013f9ac7e65213b6b2908822007d755a9325f88f86cbcc6122004031a5c47b","target":"record","created_at":"2026-07-05T09:36:40Z","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":"e306ba115d8e602d4d694db93d13d7921835feb15c91b488e8767a0a20a203eb","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-17T17:09:45Z","title_canon_sha256":"17ca5cd2ea220917acd5185573a1279485e24fdd0fa3b3dd9f9da98ba338c793"},"schema_version":"1.0","source":{"id":"2405.10918","kind":"arxiv","version":2}},"canonical_sha256":"dbe2d2e6796e48f9c20f16b6334bdb56fc5b0917da5e4c80e9473f71220ceafe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dbe2d2e6796e48f9c20f16b6334bdb56fc5b0917da5e4c80e9473f71220ceafe","first_computed_at":"2026-07-05T09:36:40.906918Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:36:40.906918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BbvZfINmnQ7wZ/veX/dFglF//o6tra1PhTS4xsEqPN522OYEDQKbZP+mkiJ6eRS0K9nayKz/wU3JwVloeYSvBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:36:40.907452Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.10918","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16013f9ac7e65213b6b2908822007d755a9325f88f86cbcc6122004031a5c47b","sha256:d7f5dc6f6a8dfab689fb68b86fcd6e1e01b2e1c47bf0fc3c9df57e7fa2f5ab58"],"state_sha256":"3aefa745f343de440c06823ce10614121d9d76a1136e7d160a74b4d221516481"}