{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:E3SFBV73NEE6CJKQR73ZY6QQSH","short_pith_number":"pith:E3SFBV73","canonical_record":{"source":{"id":"2308.12885","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-22T18:01:27Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"9e6995b55e172aa133931f1d07acca4480521ed10f0e6db6ec0272d9a7ea793f","abstract_canon_sha256":"34de9d1b4e36e265d62b9ba1db1f2529d9d2806318003193cb5df6ce2fe02947"},"schema_version":"1.0"},"canonical_sha256":"26e450d7fb6909e125508ff79c7a1091d1c330ad35c829a023525712786dc9c7","source":{"kind":"arxiv","id":"2308.12885","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.12885","created_at":"2026-07-05T06:54:55Z"},{"alias_kind":"arxiv_version","alias_value":"2308.12885v2","created_at":"2026-07-05T06:54:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.12885","created_at":"2026-07-05T06:54:55Z"},{"alias_kind":"pith_short_12","alias_value":"E3SFBV73NEE6","created_at":"2026-07-05T06:54:55Z"},{"alias_kind":"pith_short_16","alias_value":"E3SFBV73NEE6CJKQ","created_at":"2026-07-05T06:54:55Z"},{"alias_kind":"pith_short_8","alias_value":"E3SFBV73","created_at":"2026-07-05T06:54:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:E3SFBV73NEE6CJKQR73ZY6QQSH","target":"record","payload":{"canonical_record":{"source":{"id":"2308.12885","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-22T18:01:27Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"9e6995b55e172aa133931f1d07acca4480521ed10f0e6db6ec0272d9a7ea793f","abstract_canon_sha256":"34de9d1b4e36e265d62b9ba1db1f2529d9d2806318003193cb5df6ce2fe02947"},"schema_version":"1.0"},"canonical_sha256":"26e450d7fb6909e125508ff79c7a1091d1c330ad35c829a023525712786dc9c7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:54:55.043677Z","signature_b64":"+hAkg4y7L4rTuyR2/zrfEELCvhxj+pyPxNj9dso2iS9wmjA8C03DK91LRIGfShLO/VivfiQCev+JVsH+nFkmDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26e450d7fb6909e125508ff79c7a1091d1c330ad35c829a023525712786dc9c7","last_reissued_at":"2026-07-05T06:54:55.043209Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:54:55.043209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.12885","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:54:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cC48BuUS5gyhcZWhs1os1WodUj8wi8yFjvRqCifhk9k+nhn8L0v9uZzBnmsPg8iXsrrS2bxGOV63439lOKzvCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T11:57:46.003209Z"},"content_sha256":"a913fcc68c43971ea0fb763583e536c4279c3b0ce501c9389355859a0d961561","schema_version":"1.0","event_id":"sha256:a913fcc68c43971ea0fb763583e536c4279c3b0ce501c9389355859a0d961561"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:E3SFBV73NEE6CJKQR73ZY6QQSH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Collect, Measure, Repeat: Reliability Factors for Responsible AI Data Collection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.LG","authors_text":"Lora Aroyo, Oana Inel, Tim Draws","submitted_at":"2023-08-22T18:01:27Z","abstract_excerpt":"The rapid entry of machine learning approaches in our daily activities and high-stakes domains demands transparency and scrutiny of their fairness and reliability. To help gauge machine learning models' robustness, research typically focuses on the massive datasets used for their deployment, e.g., creating and maintaining documentation for understanding their origin, process of development, and ethical considerations. However, data collection for AI is still typically a one-off practice, and oftentimes datasets collected for a certain purpose or application are reused for a different problem. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.12885","kind":"arxiv","version":2},"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/2308.12885/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":"2026-07-05T06:54:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M6YS1w7w7M+L1NPHxPbgM8BmxTRnr5MxL5be/AzRCn4APFj5lHd0TkIgutbVwmT0GnQeAYUfhA/rvt85f0dvDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T11:57:46.003599Z"},"content_sha256":"3e268425b2f511b652d51c8dd2956cf45cd6f54476e71344338ba107e4b8ee36","schema_version":"1.0","event_id":"sha256:3e268425b2f511b652d51c8dd2956cf45cd6f54476e71344338ba107e4b8ee36"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E3SFBV73NEE6CJKQR73ZY6QQSH/bundle.json","state_url":"https://pith.science/pith/E3SFBV73NEE6CJKQR73ZY6QQSH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E3SFBV73NEE6CJKQR73ZY6QQSH/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":"2026-07-05T11:57:46Z","links":{"resolver":"https://pith.science/pith/E3SFBV73NEE6CJKQR73ZY6QQSH","bundle":"https://pith.science/pith/E3SFBV73NEE6CJKQR73ZY6QQSH/bundle.json","state":"https://pith.science/pith/E3SFBV73NEE6CJKQR73ZY6QQSH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E3SFBV73NEE6CJKQR73ZY6QQSH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:E3SFBV73NEE6CJKQR73ZY6QQSH","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":"34de9d1b4e36e265d62b9ba1db1f2529d9d2806318003193cb5df6ce2fe02947","cross_cats_sorted":["cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-22T18:01:27Z","title_canon_sha256":"9e6995b55e172aa133931f1d07acca4480521ed10f0e6db6ec0272d9a7ea793f"},"schema_version":"1.0","source":{"id":"2308.12885","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.12885","created_at":"2026-07-05T06:54:55Z"},{"alias_kind":"arxiv_version","alias_value":"2308.12885v2","created_at":"2026-07-05T06:54:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.12885","created_at":"2026-07-05T06:54:55Z"},{"alias_kind":"pith_short_12","alias_value":"E3SFBV73NEE6","created_at":"2026-07-05T06:54:55Z"},{"alias_kind":"pith_short_16","alias_value":"E3SFBV73NEE6CJKQ","created_at":"2026-07-05T06:54:55Z"},{"alias_kind":"pith_short_8","alias_value":"E3SFBV73","created_at":"2026-07-05T06:54:55Z"}],"graph_snapshots":[{"event_id":"sha256:3e268425b2f511b652d51c8dd2956cf45cd6f54476e71344338ba107e4b8ee36","target":"graph","created_at":"2026-07-05T06:54:55Z","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/2308.12885/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid entry of machine learning approaches in our daily activities and high-stakes domains demands transparency and scrutiny of their fairness and reliability. To help gauge machine learning models' robustness, research typically focuses on the massive datasets used for their deployment, e.g., creating and maintaining documentation for understanding their origin, process of development, and ethical considerations. However, data collection for AI is still typically a one-off practice, and oftentimes datasets collected for a certain purpose or application are reused for a different problem. ","authors_text":"Lora Aroyo, Oana Inel, Tim Draws","cross_cats":["cs.HC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-22T18:01:27Z","title":"Collect, Measure, Repeat: Reliability Factors for Responsible AI Data Collection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.12885","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:a913fcc68c43971ea0fb763583e536c4279c3b0ce501c9389355859a0d961561","target":"record","created_at":"2026-07-05T06:54:55Z","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":"34de9d1b4e36e265d62b9ba1db1f2529d9d2806318003193cb5df6ce2fe02947","cross_cats_sorted":["cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-22T18:01:27Z","title_canon_sha256":"9e6995b55e172aa133931f1d07acca4480521ed10f0e6db6ec0272d9a7ea793f"},"schema_version":"1.0","source":{"id":"2308.12885","kind":"arxiv","version":2}},"canonical_sha256":"26e450d7fb6909e125508ff79c7a1091d1c330ad35c829a023525712786dc9c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"26e450d7fb6909e125508ff79c7a1091d1c330ad35c829a023525712786dc9c7","first_computed_at":"2026-07-05T06:54:55.043209Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:54:55.043209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+hAkg4y7L4rTuyR2/zrfEELCvhxj+pyPxNj9dso2iS9wmjA8C03DK91LRIGfShLO/VivfiQCev+JVsH+nFkmDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:54:55.043677Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.12885","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a913fcc68c43971ea0fb763583e536c4279c3b0ce501c9389355859a0d961561","sha256:3e268425b2f511b652d51c8dd2956cf45cd6f54476e71344338ba107e4b8ee36"],"state_sha256":"9e21686a4cc57da6ffa06fc4433b0b5c94ac091a61b55d725a2de8856312dc72"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"drEi1BDxNRpiyVL0pbQnmAUMXyM+67T8WciUI7ij6VDqDMm381NBaNfHw/jOv+Vu4IweoOWxdpS3JD9Z0/sGAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T11:57:46.005725Z","bundle_sha256":"48a4985a5ccb328f58dfdde97f759f1506c99f136db18cc7e0f34e2b854dc036"}}