{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6TZWRJYXWSIQ4TEN5OZYTQF27J","short_pith_number":"pith:6TZWRJYX","canonical_record":{"source":{"id":"2503.13463","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DL","submitted_at":"2025-02-10T12:31:42Z","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"title_canon_sha256":"870458f93ae5e7e0460e1d4d066d0211ce533e746c1910f1cc395bda744a7702","abstract_canon_sha256":"040ee7de7edf7be9657e7ba4f73c7ad20eeef59b304505cd7e338eb97fb90474"},"schema_version":"1.0"},"canonical_sha256":"f4f368a717b4910e4c8debb389c0bafa5473f365c9423f86d841e1244cd4fbf9","source":{"kind":"arxiv","id":"2503.13463","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.13463","created_at":"2026-07-05T10:33:10Z"},{"alias_kind":"arxiv_version","alias_value":"2503.13463v1","created_at":"2026-07-05T10:33:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13463","created_at":"2026-07-05T10:33:10Z"},{"alias_kind":"pith_short_12","alias_value":"6TZWRJYXWSIQ","created_at":"2026-07-05T10:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"6TZWRJYXWSIQ4TEN","created_at":"2026-07-05T10:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"6TZWRJYX","created_at":"2026-07-05T10:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6TZWRJYXWSIQ4TEN5OZYTQF27J","target":"record","payload":{"canonical_record":{"source":{"id":"2503.13463","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DL","submitted_at":"2025-02-10T12:31:42Z","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"title_canon_sha256":"870458f93ae5e7e0460e1d4d066d0211ce533e746c1910f1cc395bda744a7702","abstract_canon_sha256":"040ee7de7edf7be9657e7ba4f73c7ad20eeef59b304505cd7e338eb97fb90474"},"schema_version":"1.0"},"canonical_sha256":"f4f368a717b4910e4c8debb389c0bafa5473f365c9423f86d841e1244cd4fbf9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:33:10.572694Z","signature_b64":"fYAsHv+A2wr2vzHez+O22HVFQgjZA7Lz4ucae6K3Hgdu2ExTEdqILszRM+Y+3wVEftitYIkNNKoPjB6dD1gHAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4f368a717b4910e4c8debb389c0bafa5473f365c9423f86d841e1244cd4fbf9","last_reissued_at":"2026-07-05T10:33:10.572073Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:33:10.572073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.13463","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":"2026-07-05T10:33:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PGUUOzqbI99SIqMdUfY/8Bd3NXKP+ZAJI2DifqkpzqXmHRg3Qj7gNa4QnbftOsGCx0aH10hKubdkWednoAtsBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T23:38:58.122992Z"},"content_sha256":"80fda9879f7fad523740cc49c029e197b5de4d5d365ce2b8ed1a990269462808","schema_version":"1.0","event_id":"sha256:80fda9879f7fad523740cc49c029e197b5de4d5d365ce2b8ed1a990269462808"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6TZWRJYXWSIQ4TEN5OZYTQF27J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Completeness of Datasets Documentation on ML/AI repositories: an Empirical Investigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"cs.DL","authors_text":"Antonio Vetr\\`o, Juan Carlos De Martin, Marco Rondina","submitted_at":"2025-02-10T12:31:42Z","abstract_excerpt":"ML/AI is the field of computer science and computer engineering that arguably received the most attention and funding over the last decade. Data is the key element of ML/AI, so it is becoming increasingly important to ensure that users are fully aware of the quality of the datasets that they use, and of the process generating them, so that possible negative impacts on downstream effects can be tracked, analysed, and, where possible, mitigated. One of the tools that can be useful in this perspective is dataset documentation. The aim of this work is to investigate the state of dataset documentat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.13463","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/2503.13463/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":"2026-07-05T10:33:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zTmTtm32wwpaojlnXg4H1XE0CyY2Z3mMD6HCLGZ5kqx3pKql7gHN0+36l2G54ZypWyqoTOUWKdOu7pbWm684BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T23:38:58.127191Z"},"content_sha256":"25d05c14b98b1e1b928c53ab436cd105751c0bf09fcc461da4c15aa7995f26f7","schema_version":"1.0","event_id":"sha256:25d05c14b98b1e1b928c53ab436cd105751c0bf09fcc461da4c15aa7995f26f7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6TZWRJYXWSIQ4TEN5OZYTQF27J/bundle.json","state_url":"https://pith.science/pith/6TZWRJYXWSIQ4TEN5OZYTQF27J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6TZWRJYXWSIQ4TEN5OZYTQF27J/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":"2026-08-21T23:38:58Z","links":{"resolver":"https://pith.science/pith/6TZWRJYXWSIQ4TEN5OZYTQF27J","bundle":"https://pith.science/pith/6TZWRJYXWSIQ4TEN5OZYTQF27J/bundle.json","state":"https://pith.science/pith/6TZWRJYXWSIQ4TEN5OZYTQF27J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6TZWRJYXWSIQ4TEN5OZYTQF27J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6TZWRJYXWSIQ4TEN5OZYTQF27J","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":"040ee7de7edf7be9657e7ba4f73c7ad20eeef59b304505cd7e338eb97fb90474","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DL","submitted_at":"2025-02-10T12:31:42Z","title_canon_sha256":"870458f93ae5e7e0460e1d4d066d0211ce533e746c1910f1cc395bda744a7702"},"schema_version":"1.0","source":{"id":"2503.13463","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.13463","created_at":"2026-07-05T10:33:10Z"},{"alias_kind":"arxiv_version","alias_value":"2503.13463v1","created_at":"2026-07-05T10:33:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13463","created_at":"2026-07-05T10:33:10Z"},{"alias_kind":"pith_short_12","alias_value":"6TZWRJYXWSIQ","created_at":"2026-07-05T10:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"6TZWRJYXWSIQ4TEN","created_at":"2026-07-05T10:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"6TZWRJYX","created_at":"2026-07-05T10:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:25d05c14b98b1e1b928c53ab436cd105751c0bf09fcc461da4c15aa7995f26f7","target":"graph","created_at":"2026-07-05T10:33:10Z","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/2503.13463/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"ML/AI is the field of computer science and computer engineering that arguably received the most attention and funding over the last decade. Data is the key element of ML/AI, so it is becoming increasingly important to ensure that users are fully aware of the quality of the datasets that they use, and of the process generating them, so that possible negative impacts on downstream effects can be tracked, analysed, and, where possible, mitigated. One of the tools that can be useful in this perspective is dataset documentation. The aim of this work is to investigate the state of dataset documentat","authors_text":"Antonio Vetr\\`o, Juan Carlos De Martin, Marco Rondina","cross_cats":["cs.AI","cs.HC","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DL","submitted_at":"2025-02-10T12:31:42Z","title":"Completeness of Datasets Documentation on ML/AI repositories: an Empirical Investigation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.13463","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":"sha256:80fda9879f7fad523740cc49c029e197b5de4d5d365ce2b8ed1a990269462808","target":"record","created_at":"2026-07-05T10:33:10Z","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":"040ee7de7edf7be9657e7ba4f73c7ad20eeef59b304505cd7e338eb97fb90474","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DL","submitted_at":"2025-02-10T12:31:42Z","title_canon_sha256":"870458f93ae5e7e0460e1d4d066d0211ce533e746c1910f1cc395bda744a7702"},"schema_version":"1.0","source":{"id":"2503.13463","kind":"arxiv","version":1}},"canonical_sha256":"f4f368a717b4910e4c8debb389c0bafa5473f365c9423f86d841e1244cd4fbf9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f4f368a717b4910e4c8debb389c0bafa5473f365c9423f86d841e1244cd4fbf9","first_computed_at":"2026-07-05T10:33:10.572073Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:33:10.572073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fYAsHv+A2wr2vzHez+O22HVFQgjZA7Lz4ucae6K3Hgdu2ExTEdqILszRM+Y+3wVEftitYIkNNKoPjB6dD1gHAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:33:10.572694Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.13463","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80fda9879f7fad523740cc49c029e197b5de4d5d365ce2b8ed1a990269462808","sha256:25d05c14b98b1e1b928c53ab436cd105751c0bf09fcc461da4c15aa7995f26f7"],"state_sha256":"c12bd5dec3c0388b585f37a0781a9096e18b4065ec08b709b58729fd9853abca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h2VHCANFDkgnt/I66bCtNtO/Q7/FzkfdQDL2FYlByLdSQXAZr7GSo5qQgdB1wcvpBMYj+sfVOvSMU4S/Rj5WAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T23:38:58.134359Z","bundle_sha256":"af4954723c8f5d797f859fef0b1bfdd10bfe1041d8a3560fabf680bdb8333282"}}