{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QUWFIAWQFC6SNH36JKX7VCTFCX","short_pith_number":"pith:QUWFIAWQ","schema_version":"1.0","canonical_sha256":"852c5402d028bd269f7e4aaffa8a6515f53042c5d5c32ec16669355d581f3769","source":{"kind":"arxiv","id":"2112.08663","version":1},"attestation_state":"computed","paper":{"title":"MAVE: A Product Dataset for Multi-source Attribute Value Extraction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Anand Kulkarni, Bhargav Kanagal, Bin Shu, Jon Elsas, Li Yang, Qifan Wang, Sumit Sanghai, Zac Yu","submitted_at":"2021-12-16T06:48:31Z","abstract_excerpt":"Attribute value extraction refers to the task of identifying values of an attribute of interest from product information. Product attribute values are essential in many e-commerce scenarios, such as customer service robots, product ranking, retrieval and recommendations. While in the real world, the attribute values of a product are usually incomplete and vary over time, which greatly hinders the practical applications. In this paper, we introduce MAVE, a new dataset to better facilitate research on product attribute value extraction. MAVE is composed of a curated set of 2.2 million products f"},"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":"2112.08663","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-16T06:48:31Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"a33c9995859baeffc4189852a85cece6a93d8b75a029652e2dd4e96bbb344dd7","abstract_canon_sha256":"577ecf68032ad06d3a70f606b006cab828f7ee565c6d66a4c76a75de0faa95a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:41:31.579967Z","signature_b64":"SdprkH2eMmalMgSEr35IhhoT3wr+2BeoPXY0PiYFsqrK8o9ToS/1dktAYmfduBCbUNYFXuHN8+nppsS0shM6Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"852c5402d028bd269f7e4aaffa8a6515f53042c5d5c32ec16669355d581f3769","last_reissued_at":"2026-07-05T03:41:31.579529Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:41:31.579529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MAVE: A Product Dataset for Multi-source Attribute Value Extraction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Anand Kulkarni, Bhargav Kanagal, Bin Shu, Jon Elsas, Li Yang, Qifan Wang, Sumit Sanghai, Zac Yu","submitted_at":"2021-12-16T06:48:31Z","abstract_excerpt":"Attribute value extraction refers to the task of identifying values of an attribute of interest from product information. Product attribute values are essential in many e-commerce scenarios, such as customer service robots, product ranking, retrieval and recommendations. While in the real world, the attribute values of a product are usually incomplete and vary over time, which greatly hinders the practical applications. In this paper, we introduce MAVE, a new dataset to better facilitate research on product attribute value extraction. MAVE is composed of a curated set of 2.2 million products f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08663","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/2112.08663/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":"2112.08663","created_at":"2026-07-05T03:41:31.579578+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.08663v1","created_at":"2026-07-05T03:41:31.579578+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08663","created_at":"2026-07-05T03:41:31.579578+00:00"},{"alias_kind":"pith_short_12","alias_value":"QUWFIAWQFC6S","created_at":"2026-07-05T03:41:31.579578+00:00"},{"alias_kind":"pith_short_16","alias_value":"QUWFIAWQFC6SNH36","created_at":"2026-07-05T03:41:31.579578+00:00"},{"alias_kind":"pith_short_8","alias_value":"QUWFIAWQ","created_at":"2026-07-05T03:41:31.579578+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/QUWFIAWQFC6SNH36JKX7VCTFCX","json":"https://pith.science/pith/QUWFIAWQFC6SNH36JKX7VCTFCX.json","graph_json":"https://pith.science/api/pith-number/QUWFIAWQFC6SNH36JKX7VCTFCX/graph.json","events_json":"https://pith.science/api/pith-number/QUWFIAWQFC6SNH36JKX7VCTFCX/events.json","paper":"https://pith.science/paper/QUWFIAWQ"},"agent_actions":{"view_html":"https://pith.science/pith/QUWFIAWQFC6SNH36JKX7VCTFCX","download_json":"https://pith.science/pith/QUWFIAWQFC6SNH36JKX7VCTFCX.json","view_paper":"https://pith.science/paper/QUWFIAWQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.08663&json=true","fetch_graph":"https://pith.science/api/pith-number/QUWFIAWQFC6SNH36JKX7VCTFCX/graph.json","fetch_events":"https://pith.science/api/pith-number/QUWFIAWQFC6SNH36JKX7VCTFCX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QUWFIAWQFC6SNH36JKX7VCTFCX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QUWFIAWQFC6SNH36JKX7VCTFCX/action/storage_attestation","attest_author":"https://pith.science/pith/QUWFIAWQFC6SNH36JKX7VCTFCX/action/author_attestation","sign_citation":"https://pith.science/pith/QUWFIAWQFC6SNH36JKX7VCTFCX/action/citation_signature","submit_replication":"https://pith.science/pith/QUWFIAWQFC6SNH36JKX7VCTFCX/action/replication_record"}},"created_at":"2026-07-05T03:41:31.579578+00:00","updated_at":"2026-07-05T03:41:31.579578+00:00"}