{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:QUWFIAWQFC6SNH36JKX7VCTFCX","short_pith_number":"pith:QUWFIAWQ","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"},"canonical_sha256":"852c5402d028bd269f7e4aaffa8a6515f53042c5d5c32ec16669355d581f3769","source":{"kind":"arxiv","id":"2112.08663","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.08663","created_at":"2026-07-05T03:41:31Z"},{"alias_kind":"arxiv_version","alias_value":"2112.08663v1","created_at":"2026-07-05T03:41:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08663","created_at":"2026-07-05T03:41:31Z"},{"alias_kind":"pith_short_12","alias_value":"QUWFIAWQFC6S","created_at":"2026-07-05T03:41:31Z"},{"alias_kind":"pith_short_16","alias_value":"QUWFIAWQFC6SNH36","created_at":"2026-07-05T03:41:31Z"},{"alias_kind":"pith_short_8","alias_value":"QUWFIAWQ","created_at":"2026-07-05T03:41:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:QUWFIAWQFC6SNH36JKX7VCTFCX","target":"record","payload":{"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"},"canonical_sha256":"852c5402d028bd269f7e4aaffa8a6515f53042c5d5c32ec16669355d581f3769","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"},"source_kind":"arxiv","source_id":"2112.08663","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:41:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"po7X1KtAq7jDOZVoXW9jwT/+LiQSVh297AaMObcMmfvaFS26d/a0k8bSQ1BaRZt8zn5sqmSrfK2ddqC2ngJRBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:19:20.937106Z"},"content_sha256":"cdf1096f22a6989d7a7e7a0dc6cddad3acadf96c275e13541899379cc4741a21","schema_version":"1.0","event_id":"sha256:cdf1096f22a6989d7a7e7a0dc6cddad3acadf96c275e13541899379cc4741a21"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:QUWFIAWQFC6SNH36JKX7VCTFCX","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:41:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X5m62NwYpdtKLz+oLzrxsCNT4xzSkzHMJSeHfQBvVfwwSWbssqdFxbayEV9ni/bgZVTsYZy55UWm3uKdBMzSDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:19:20.937491Z"},"content_sha256":"7065087498370b08e72c6a0bdc45d3c791de67578636d82f70718ceb5eaec144","schema_version":"1.0","event_id":"sha256:7065087498370b08e72c6a0bdc45d3c791de67578636d82f70718ceb5eaec144"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QUWFIAWQFC6SNH36JKX7VCTFCX/bundle.json","state_url":"https://pith.science/pith/QUWFIAWQFC6SNH36JKX7VCTFCX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QUWFIAWQFC6SNH36JKX7VCTFCX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T06:19:20Z","links":{"resolver":"https://pith.science/pith/QUWFIAWQFC6SNH36JKX7VCTFCX","bundle":"https://pith.science/pith/QUWFIAWQFC6SNH36JKX7VCTFCX/bundle.json","state":"https://pith.science/pith/QUWFIAWQFC6SNH36JKX7VCTFCX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QUWFIAWQFC6SNH36JKX7VCTFCX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:QUWFIAWQFC6SNH36JKX7VCTFCX","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":"577ecf68032ad06d3a70f606b006cab828f7ee565c6d66a4c76a75de0faa95a9","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-16T06:48:31Z","title_canon_sha256":"a33c9995859baeffc4189852a85cece6a93d8b75a029652e2dd4e96bbb344dd7"},"schema_version":"1.0","source":{"id":"2112.08663","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.08663","created_at":"2026-07-05T03:41:31Z"},{"alias_kind":"arxiv_version","alias_value":"2112.08663v1","created_at":"2026-07-05T03:41:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08663","created_at":"2026-07-05T03:41:31Z"},{"alias_kind":"pith_short_12","alias_value":"QUWFIAWQFC6S","created_at":"2026-07-05T03:41:31Z"},{"alias_kind":"pith_short_16","alias_value":"QUWFIAWQFC6SNH36","created_at":"2026-07-05T03:41:31Z"},{"alias_kind":"pith_short_8","alias_value":"QUWFIAWQ","created_at":"2026-07-05T03:41:31Z"}],"graph_snapshots":[{"event_id":"sha256:7065087498370b08e72c6a0bdc45d3c791de67578636d82f70718ceb5eaec144","target":"graph","created_at":"2026-07-05T03:41:31Z","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/2112.08663/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Anand Kulkarni, Bhargav Kanagal, Bin Shu, Jon Elsas, Li Yang, Qifan Wang, Sumit Sanghai, Zac Yu","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-16T06:48:31Z","title":"MAVE: A Product Dataset for Multi-source Attribute Value Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08663","kind":"arxiv","version":1},"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:cdf1096f22a6989d7a7e7a0dc6cddad3acadf96c275e13541899379cc4741a21","target":"record","created_at":"2026-07-05T03:41:31Z","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":"577ecf68032ad06d3a70f606b006cab828f7ee565c6d66a4c76a75de0faa95a9","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-16T06:48:31Z","title_canon_sha256":"a33c9995859baeffc4189852a85cece6a93d8b75a029652e2dd4e96bbb344dd7"},"schema_version":"1.0","source":{"id":"2112.08663","kind":"arxiv","version":1}},"canonical_sha256":"852c5402d028bd269f7e4aaffa8a6515f53042c5d5c32ec16669355d581f3769","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"852c5402d028bd269f7e4aaffa8a6515f53042c5d5c32ec16669355d581f3769","first_computed_at":"2026-07-05T03:41:31.579529Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:41:31.579529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SdprkH2eMmalMgSEr35IhhoT3wr+2BeoPXY0PiYFsqrK8o9ToS/1dktAYmfduBCbUNYFXuHN8+nppsS0shM6Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:41:31.579967Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.08663","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cdf1096f22a6989d7a7e7a0dc6cddad3acadf96c275e13541899379cc4741a21","sha256:7065087498370b08e72c6a0bdc45d3c791de67578636d82f70718ceb5eaec144"],"state_sha256":"04857d08b020ca1a350968d4bdc53037827229339576d2dd7be453539a0a7e07"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oG9Hm6Xs03jW/EuCS1+Uwp8+F6tLJoGa4oPllgxa2E6pBiKcztfzkj8gaT5XQrd00+sljgBrdeTeKSs5eLJ/BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T06:19:20.939457Z","bundle_sha256":"8b6a7cad01bd78877e2fd583500a3b9c785565da77c3039f08f2ff7ee8d15930"}}