{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:5U74EUVDXJGQXMKHLM6VHO435E","short_pith_number":"pith:5U74EUVD","canonical_record":{"source":{"id":"1805.03677","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-05-09T18:10:02Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"5ededf99a2811c89b044df4580f1148ac1b0d066da6a879f430249c41cd93223","abstract_canon_sha256":"2a46b5a724386a8d0f34c1580f799fdee26a959c25d9e778874e7d1af59152a7"},"schema_version":"1.0"},"canonical_sha256":"ed3fc252a3ba4d0bb1475b3d53bb9be9157a1b634a287cfd5fcad8d68faa165b","source":{"kind":"arxiv","id":"1805.03677","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.03677","created_at":"2026-05-18T00:16:19Z"},{"alias_kind":"arxiv_version","alias_value":"1805.03677v1","created_at":"2026-05-18T00:16:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.03677","created_at":"2026-05-18T00:16:19Z"},{"alias_kind":"pith_short_12","alias_value":"5U74EUVDXJGQ","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5U74EUVDXJGQXMKH","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5U74EUVD","created_at":"2026-05-18T12:32:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:5U74EUVDXJGQXMKHLM6VHO435E","target":"record","payload":{"canonical_record":{"source":{"id":"1805.03677","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-05-09T18:10:02Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"5ededf99a2811c89b044df4580f1148ac1b0d066da6a879f430249c41cd93223","abstract_canon_sha256":"2a46b5a724386a8d0f34c1580f799fdee26a959c25d9e778874e7d1af59152a7"},"schema_version":"1.0"},"canonical_sha256":"ed3fc252a3ba4d0bb1475b3d53bb9be9157a1b634a287cfd5fcad8d68faa165b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:16:19.016040Z","signature_b64":"zFDfFq9SSOPEdHMDqpuhuxZmIni7IQzCGKOLhYJfRa+ch5eoz/Z7pxSfVWtqd2Qwel8B6GJV6Jgo2/qzO+q1Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed3fc252a3ba4d0bb1475b3d53bb9be9157a1b634a287cfd5fcad8d68faa165b","last_reissued_at":"2026-05-18T00:16:19.015452Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:16:19.015452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.03677","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":"2026-05-18T00:16:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RPYtPnV/FtwRk/TKxyOatZm63oTy/UaVasFq+KZ1Jxt6R7Mj/PffUOfKkYsPnzDtJkNT3kjyy9rI5FTF+QEdBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T01:50:32.802825Z"},"content_sha256":"41d570cdc4e47014c001280e1927c7a7d89fa09591b74aa552512ae15e3079e2","schema_version":"1.0","event_id":"sha256:41d570cdc4e47014c001280e1927c7a7d89fa09591b74aa552512ae15e3079e2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:5U74EUVDXJGQXMKHLM6VHO435E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Dataset Nutrition Label: A Framework To Drive Higher Data Quality Standards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.DB","authors_text":"Ahmed Hosny, Joshua Joseph, Kasia Chmielinski, Sarah Holland, Sarah Newman","submitted_at":"2018-05-09T18:10:02Z","abstract_excerpt":"Artificial intelligence (AI) systems built on incomplete or biased data will often exhibit problematic outcomes. Current methods of data analysis, particularly before model development, are costly and not standardized. The Dataset Nutrition Label (the Label) is a diagnostic framework that lowers the barrier to standardized data analysis by providing a distilled yet comprehensive overview of dataset \"ingredients\" before AI model development. Building a Label that can be applied across domains and data types requires that the framework itself be flexible and adaptable; as such, the Label is comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.03677","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":""},"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":"2026-05-18T00:16:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RuQpHEsQ39iwkkOxlWvRfwQjE+teGm8Agh8TE1mrZ6IN8KLgbT/0CIkQ4yaxgfy5/mPVja4xUiwiYwAFR5zVBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T01:50:32.803430Z"},"content_sha256":"b011ed240b3e56ca3b78f3266228788e8a7a014d63624c786dd8a1cf0f494591","schema_version":"1.0","event_id":"sha256:b011ed240b3e56ca3b78f3266228788e8a7a014d63624c786dd8a1cf0f494591"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5U74EUVDXJGQXMKHLM6VHO435E/bundle.json","state_url":"https://pith.science/pith/5U74EUVDXJGQXMKHLM6VHO435E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5U74EUVDXJGQXMKHLM6VHO435E/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":"2026-05-27T01:50:32Z","links":{"resolver":"https://pith.science/pith/5U74EUVDXJGQXMKHLM6VHO435E","bundle":"https://pith.science/pith/5U74EUVDXJGQXMKHLM6VHO435E/bundle.json","state":"https://pith.science/pith/5U74EUVDXJGQXMKHLM6VHO435E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5U74EUVDXJGQXMKHLM6VHO435E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:5U74EUVDXJGQXMKHLM6VHO435E","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":"2a46b5a724386a8d0f34c1580f799fdee26a959c25d9e778874e7d1af59152a7","cross_cats_sorted":["cs.CY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-05-09T18:10:02Z","title_canon_sha256":"5ededf99a2811c89b044df4580f1148ac1b0d066da6a879f430249c41cd93223"},"schema_version":"1.0","source":{"id":"1805.03677","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.03677","created_at":"2026-05-18T00:16:19Z"},{"alias_kind":"arxiv_version","alias_value":"1805.03677v1","created_at":"2026-05-18T00:16:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.03677","created_at":"2026-05-18T00:16:19Z"},{"alias_kind":"pith_short_12","alias_value":"5U74EUVDXJGQ","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5U74EUVDXJGQXMKH","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5U74EUVD","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:b011ed240b3e56ca3b78f3266228788e8a7a014d63624c786dd8a1cf0f494591","target":"graph","created_at":"2026-05-18T00:16:19Z","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"},"paper":{"abstract_excerpt":"Artificial intelligence (AI) systems built on incomplete or biased data will often exhibit problematic outcomes. Current methods of data analysis, particularly before model development, are costly and not standardized. The Dataset Nutrition Label (the Label) is a diagnostic framework that lowers the barrier to standardized data analysis by providing a distilled yet comprehensive overview of dataset \"ingredients\" before AI model development. Building a Label that can be applied across domains and data types requires that the framework itself be flexible and adaptable; as such, the Label is comp","authors_text":"Ahmed Hosny, Joshua Joseph, Kasia Chmielinski, Sarah Holland, Sarah Newman","cross_cats":["cs.CY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-05-09T18:10:02Z","title":"The Dataset Nutrition Label: A Framework To Drive Higher Data Quality Standards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.03677","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":"sha256:41d570cdc4e47014c001280e1927c7a7d89fa09591b74aa552512ae15e3079e2","target":"record","created_at":"2026-05-18T00:16:19Z","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":"2a46b5a724386a8d0f34c1580f799fdee26a959c25d9e778874e7d1af59152a7","cross_cats_sorted":["cs.CY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-05-09T18:10:02Z","title_canon_sha256":"5ededf99a2811c89b044df4580f1148ac1b0d066da6a879f430249c41cd93223"},"schema_version":"1.0","source":{"id":"1805.03677","kind":"arxiv","version":1}},"canonical_sha256":"ed3fc252a3ba4d0bb1475b3d53bb9be9157a1b634a287cfd5fcad8d68faa165b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed3fc252a3ba4d0bb1475b3d53bb9be9157a1b634a287cfd5fcad8d68faa165b","first_computed_at":"2026-05-18T00:16:19.015452Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:16:19.015452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zFDfFq9SSOPEdHMDqpuhuxZmIni7IQzCGKOLhYJfRa+ch5eoz/Z7pxSfVWtqd2Qwel8B6GJV6Jgo2/qzO+q1Bg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:16:19.016040Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.03677","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41d570cdc4e47014c001280e1927c7a7d89fa09591b74aa552512ae15e3079e2","sha256:b011ed240b3e56ca3b78f3266228788e8a7a014d63624c786dd8a1cf0f494591"],"state_sha256":"51efb88d9096b8f1e6b7fa7a8362040e893e23088376706e48df540095760177"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"18BtVeHS869J7KDaKzf414UMYxKZYFkaTpSiZ2rx1z5IVq1dGMu23UqUsJjMkob3o19aWNWIAMOQQkYeGzlHBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T01:50:32.806045Z","bundle_sha256":"7799fb5a1f7341cf38bf7606f85b883f2280fc6b8a20a2da44c72e7655c51d0a"}}