{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:FJW6EBOWJCXVNUZYBJAEGZBQ6X","short_pith_number":"pith:FJW6EBOW","canonical_record":{"source":{"id":"2207.10062","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-20T17:47:54Z","cross_cats_sorted":[],"title_canon_sha256":"7451a2ab6143f9f92c4b22f61f158d2b3642a1b9bf55d017d6a39be0d4e73e8c","abstract_canon_sha256":"6e9573ac953019e8f83964ae51d0f96910036813f1bdfed620ad270a884e187e"},"schema_version":"1.0"},"canonical_sha256":"2a6de205d648af56d3380a40436430f5e905dc788508bba3becb7245187e9248","source":{"kind":"arxiv","id":"2207.10062","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.10062","created_at":"2026-07-05T07:00:19Z"},{"alias_kind":"arxiv_version","alias_value":"2207.10062v4","created_at":"2026-07-05T07:00:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.10062","created_at":"2026-07-05T07:00:19Z"},{"alias_kind":"pith_short_12","alias_value":"FJW6EBOWJCXV","created_at":"2026-07-05T07:00:19Z"},{"alias_kind":"pith_short_16","alias_value":"FJW6EBOWJCXVNUZY","created_at":"2026-07-05T07:00:19Z"},{"alias_kind":"pith_short_8","alias_value":"FJW6EBOW","created_at":"2026-07-05T07:00:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:FJW6EBOWJCXVNUZYBJAEGZBQ6X","target":"record","payload":{"canonical_record":{"source":{"id":"2207.10062","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-20T17:47:54Z","cross_cats_sorted":[],"title_canon_sha256":"7451a2ab6143f9f92c4b22f61f158d2b3642a1b9bf55d017d6a39be0d4e73e8c","abstract_canon_sha256":"6e9573ac953019e8f83964ae51d0f96910036813f1bdfed620ad270a884e187e"},"schema_version":"1.0"},"canonical_sha256":"2a6de205d648af56d3380a40436430f5e905dc788508bba3becb7245187e9248","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:19.365554Z","signature_b64":"JHyHLOncgu0Bu38jnEjXz3rwMje053Q+k+J+ugdiezzMWez+9lA/1/MKyyOnRVkHHT9PT8Z6aglMXlE/D3aVCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a6de205d648af56d3380a40436430f5e905dc788508bba3becb7245187e9248","last_reissued_at":"2026-07-05T07:00:19.364996Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:19.364996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.10062","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:00:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7s3DeWiNW2N5/wVRMmAfg4bLlGJhPmf2XxZiIWDedWxDlFyxL6l7vXC6rFE9hqWojCkk1Jc4fOfMNBgii3nrBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T12:04:43.525213Z"},"content_sha256":"a43edfef4975ca01c97ec33c3a142a084a1f59160d015e2e1b93afeb9b83322f","schema_version":"1.0","event_id":"sha256:a43edfef4975ca01c97ec33c3a142a084a1f59160d015e2e1b93afeb9b83322f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:FJW6EBOWJCXVNUZYBJAEGZBQ6X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DataPerf: Benchmarks for Data-Centric AI Development","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adina Williams, Alicia Parrish, Amirata Ghorbani, Andrew Ng, Bilge Acun, Bojan Karla\\v{s}, Carole-Jean Wu, Ce Zhang, Charvi Rastogi, Christine R. Kirkpatrick, Cody Coleman, Colby Banbury, David Jurado, David Kanter, Douwe Kiela, Emmett Goodman, Greg Diamos, Hannah Rose Kirk, James Zou, Jessica Quaye, Joaquin Vanschoren, Jonas Mueller, Juan Ciro, Lilith Bat-Leah, Lingjiao Chen, Lora Aroyo, Lynn He, Margaret Warren, Mark Mazumder, Max Bartolo, Mehul Smriti Raje, Newsha Ardalani, Oana Inel, Peter Mattson, Praveen Paritosh, Rafael Mosquera, Sabri Eyuboglu, Serena Yeung, Sudnya Diamos, Tariq Kane, Tristan Thrush, Tzu-Sheng Kuo, Vijay Janapa Reddi, William Gaviria Rojas, Xiaozhe Yao","submitted_at":"2022-07-20T17:47:54Z","abstract_excerpt":"Machine learning research has long focused on models rather than datasets, and prominent datasets are used for common ML tasks without regard to the breadth, difficulty, and faithfulness of the underlying problems. Neglecting the fundamental importance of data has given rise to inaccuracy, bias, and fragility in real-world applications, and research is hindered by saturation across existing dataset benchmarks. In response, we present DataPerf, a community-led benchmark suite for evaluating ML datasets and data-centric algorithms. We aim to foster innovation in data-centric AI through competiti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.10062","kind":"arxiv","version":4},"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/2207.10062/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":"2026-07-05T07:00:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WT8kracxfa5JcevBJOkkjI8MgJDWH7am3eteQCYISlFxOVEQHvml1YJ5uxH0EFYlxeei9ealQQ8j8xDZ7QGDAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T12:04:43.526155Z"},"content_sha256":"43d153f50f17a0def842e7a0a16d74d34599b9f5ed039fbf1b970f50748c49d1","schema_version":"1.0","event_id":"sha256:43d153f50f17a0def842e7a0a16d74d34599b9f5ed039fbf1b970f50748c49d1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FJW6EBOWJCXVNUZYBJAEGZBQ6X/bundle.json","state_url":"https://pith.science/pith/FJW6EBOWJCXVNUZYBJAEGZBQ6X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FJW6EBOWJCXVNUZYBJAEGZBQ6X/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":"2026-08-06T12:04:43Z","links":{"resolver":"https://pith.science/pith/FJW6EBOWJCXVNUZYBJAEGZBQ6X","bundle":"https://pith.science/pith/FJW6EBOWJCXVNUZYBJAEGZBQ6X/bundle.json","state":"https://pith.science/pith/FJW6EBOWJCXVNUZYBJAEGZBQ6X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FJW6EBOWJCXVNUZYBJAEGZBQ6X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:FJW6EBOWJCXVNUZYBJAEGZBQ6X","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":"6e9573ac953019e8f83964ae51d0f96910036813f1bdfed620ad270a884e187e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-20T17:47:54Z","title_canon_sha256":"7451a2ab6143f9f92c4b22f61f158d2b3642a1b9bf55d017d6a39be0d4e73e8c"},"schema_version":"1.0","source":{"id":"2207.10062","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.10062","created_at":"2026-07-05T07:00:19Z"},{"alias_kind":"arxiv_version","alias_value":"2207.10062v4","created_at":"2026-07-05T07:00:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.10062","created_at":"2026-07-05T07:00:19Z"},{"alias_kind":"pith_short_12","alias_value":"FJW6EBOWJCXV","created_at":"2026-07-05T07:00:19Z"},{"alias_kind":"pith_short_16","alias_value":"FJW6EBOWJCXVNUZY","created_at":"2026-07-05T07:00:19Z"},{"alias_kind":"pith_short_8","alias_value":"FJW6EBOW","created_at":"2026-07-05T07:00:19Z"}],"graph_snapshots":[{"event_id":"sha256:43d153f50f17a0def842e7a0a16d74d34599b9f5ed039fbf1b970f50748c49d1","target":"graph","created_at":"2026-07-05T07:00:19Z","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/2207.10062/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine learning research has long focused on models rather than datasets, and prominent datasets are used for common ML tasks without regard to the breadth, difficulty, and faithfulness of the underlying problems. Neglecting the fundamental importance of data has given rise to inaccuracy, bias, and fragility in real-world applications, and research is hindered by saturation across existing dataset benchmarks. In response, we present DataPerf, a community-led benchmark suite for evaluating ML datasets and data-centric algorithms. We aim to foster innovation in data-centric AI through competiti","authors_text":"Adina Williams, Alicia Parrish, Amirata Ghorbani, Andrew Ng, Bilge Acun, Bojan Karla\\v{s}, Carole-Jean Wu, Ce Zhang, Charvi Rastogi, Christine R. Kirkpatrick, Cody Coleman, Colby Banbury, David Jurado, David Kanter, Douwe Kiela, Emmett Goodman, Greg Diamos, Hannah Rose Kirk, James Zou, Jessica Quaye, Joaquin Vanschoren, Jonas Mueller, Juan Ciro, Lilith Bat-Leah, Lingjiao Chen, Lora Aroyo, Lynn He, Margaret Warren, Mark Mazumder, Max Bartolo, Mehul Smriti Raje, Newsha Ardalani, Oana Inel, Peter Mattson, Praveen Paritosh, Rafael Mosquera, Sabri Eyuboglu, Serena Yeung, Sudnya Diamos, Tariq Kane, Tristan Thrush, Tzu-Sheng Kuo, Vijay Janapa Reddi, William Gaviria Rojas, Xiaozhe Yao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-20T17:47:54Z","title":"DataPerf: Benchmarks for Data-Centric AI Development"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.10062","kind":"arxiv","version":4},"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:a43edfef4975ca01c97ec33c3a142a084a1f59160d015e2e1b93afeb9b83322f","target":"record","created_at":"2026-07-05T07:00:19Z","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":"6e9573ac953019e8f83964ae51d0f96910036813f1bdfed620ad270a884e187e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-20T17:47:54Z","title_canon_sha256":"7451a2ab6143f9f92c4b22f61f158d2b3642a1b9bf55d017d6a39be0d4e73e8c"},"schema_version":"1.0","source":{"id":"2207.10062","kind":"arxiv","version":4}},"canonical_sha256":"2a6de205d648af56d3380a40436430f5e905dc788508bba3becb7245187e9248","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a6de205d648af56d3380a40436430f5e905dc788508bba3becb7245187e9248","first_computed_at":"2026-07-05T07:00:19.364996Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:00:19.364996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JHyHLOncgu0Bu38jnEjXz3rwMje053Q+k+J+ugdiezzMWez+9lA/1/MKyyOnRVkHHT9PT8Z6aglMXlE/D3aVCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:00:19.365554Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.10062","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a43edfef4975ca01c97ec33c3a142a084a1f59160d015e2e1b93afeb9b83322f","sha256:43d153f50f17a0def842e7a0a16d74d34599b9f5ed039fbf1b970f50748c49d1"],"state_sha256":"a1d9385e53a92e1e80778bf3d3564400e7d8654a9eedd5d059dddbc6a6cf55fd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1a7zpeiQduGm3/Z09RFUGuZidSD18v2VJx0U88VflCLh22o7VPI5R2A0khs5nQi+4+SDmIqIEOwnniV/CaOoBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T12:04:43.530601Z","bundle_sha256":"3a8d8ce67b1a57075a06e5995170f6f00dc606cce6e9e2135709a92c31f938ad"}}