{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:F6GNC4ZFRZWYMANCLK5Q4HZY6Z","short_pith_number":"pith:F6GNC4ZF","canonical_record":{"source":{"id":"2506.01789","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T15:31:52Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","eess.AS"],"title_canon_sha256":"4c094cd537583ad354f0d39faf9008e51fc761bece2b059e7402d55e01e5de52","abstract_canon_sha256":"06357229cb96d9aabe4aa96f8a83a6a4c992c9663a266249bde7a095765952d7"},"schema_version":"1.0"},"canonical_sha256":"2f8cd173258e6d8601a25abb0e1f38f6403f08b85e5cf2db2d9e77099cc0569c","source":{"kind":"arxiv","id":"2506.01789","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01789","created_at":"2026-07-05T11:14:30Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01789v2","created_at":"2026-07-05T11:14:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01789","created_at":"2026-07-05T11:14:30Z"},{"alias_kind":"pith_short_12","alias_value":"F6GNC4ZFRZWY","created_at":"2026-07-05T11:14:30Z"},{"alias_kind":"pith_short_16","alias_value":"F6GNC4ZFRZWYMANC","created_at":"2026-07-05T11:14:30Z"},{"alias_kind":"pith_short_8","alias_value":"F6GNC4ZF","created_at":"2026-07-05T11:14:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:F6GNC4ZFRZWYMANCLK5Q4HZY6Z","target":"record","payload":{"canonical_record":{"source":{"id":"2506.01789","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T15:31:52Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","eess.AS"],"title_canon_sha256":"4c094cd537583ad354f0d39faf9008e51fc761bece2b059e7402d55e01e5de52","abstract_canon_sha256":"06357229cb96d9aabe4aa96f8a83a6a4c992c9663a266249bde7a095765952d7"},"schema_version":"1.0"},"canonical_sha256":"2f8cd173258e6d8601a25abb0e1f38f6403f08b85e5cf2db2d9e77099cc0569c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:30.090494Z","signature_b64":"mJLtuX62ZnDvQ4+U2QgFaOdfY4Dl6D2qKnXYrwo0uUwqP9mZ3Ii/XU/oNfG+cmf3A8y13/k65Y2HAtuwSI7xCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f8cd173258e6d8601a25abb0e1f38f6403f08b85e5cf2db2d9e77099cc0569c","last_reissued_at":"2026-07-05T11:14:30.090044Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:30.090044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.01789","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":"2026-07-05T11:14:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i+V/5W/3EOFgOBtnbIQpueZbxzJH1jEefhZ75kzc5X0FYoyh00kQ4s0v8oU6ozrXTtBwqMbHtwNhNSg8xu79Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T15:08:33.274804Z"},"content_sha256":"6d78ddd719a58f28e7684448570586b4dda96b21df4f086a5320014e623e3b85","schema_version":"1.0","event_id":"sha256:6d78ddd719a58f28e7684448570586b4dda96b21df4f086a5320014e623e3b85"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:F6GNC4ZFRZWYMANCLK5Q4HZY6Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Datasheets Aren't Enough: DataRubrics for Automated Quality Metrics and Accountability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","eess.AS"],"primary_cat":"cs.LG","authors_text":"Aditya Parashar, Alham Fikri Aji, Ayu Purwarianti, David Anugraha, Derry Tanti Wijaya, Emmy Liu, En-Shiun Annie Lee, Genta Indra Winata, Hanyang Zhao, Jan Christian Blaise Cruz, Kezia Erina Suryoraharjo, M. Farid Adilazuarda, Monojit Choudhury, Niklas Muennighoff, Patrick Amadeus Irawan, Ruochen Zhang, Seungone Kim, Shou-Yi Hung, Sudipta Kar, Zheng-Xin Yong","submitted_at":"2025-06-02T15:31:52Z","abstract_excerpt":"High-quality datasets are fundamental to training and evaluating machine learning models, yet their creation-especially with accurate human annotations-remains a significant challenge. Many dataset paper submissions lack originality, diversity, or rigorous quality control, and these shortcomings are often overlooked during peer review. Submissions also frequently omit essential details about dataset construction and properties. While existing tools such as datasheets aim to promote transparency, they are largely descriptive and do not provide standardized, measurable methods for evaluating dat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01789","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/2506.01789/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":"2026-07-05T11:14:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XrSjYGJqM8vezedDf3jlVoHhC0e5t+n19LLlpsh8+v6s8r7SysOGAv9yKSptlPOiosfU5x73YUdqZyiqHlq+CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T15:08:33.275341Z"},"content_sha256":"22cc1bf68dcaed4ca517f63607e0aab36ff515f2e8323886b578bc419f5794c9","schema_version":"1.0","event_id":"sha256:22cc1bf68dcaed4ca517f63607e0aab36ff515f2e8323886b578bc419f5794c9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F6GNC4ZFRZWYMANCLK5Q4HZY6Z/bundle.json","state_url":"https://pith.science/pith/F6GNC4ZFRZWYMANCLK5Q4HZY6Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F6GNC4ZFRZWYMANCLK5Q4HZY6Z/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":"2026-08-06T15:08:33Z","links":{"resolver":"https://pith.science/pith/F6GNC4ZFRZWYMANCLK5Q4HZY6Z","bundle":"https://pith.science/pith/F6GNC4ZFRZWYMANCLK5Q4HZY6Z/bundle.json","state":"https://pith.science/pith/F6GNC4ZFRZWYMANCLK5Q4HZY6Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F6GNC4ZFRZWYMANCLK5Q4HZY6Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:F6GNC4ZFRZWYMANCLK5Q4HZY6Z","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":"06357229cb96d9aabe4aa96f8a83a6a4c992c9663a266249bde7a095765952d7","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T15:31:52Z","title_canon_sha256":"4c094cd537583ad354f0d39faf9008e51fc761bece2b059e7402d55e01e5de52"},"schema_version":"1.0","source":{"id":"2506.01789","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01789","created_at":"2026-07-05T11:14:30Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01789v2","created_at":"2026-07-05T11:14:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01789","created_at":"2026-07-05T11:14:30Z"},{"alias_kind":"pith_short_12","alias_value":"F6GNC4ZFRZWY","created_at":"2026-07-05T11:14:30Z"},{"alias_kind":"pith_short_16","alias_value":"F6GNC4ZFRZWYMANC","created_at":"2026-07-05T11:14:30Z"},{"alias_kind":"pith_short_8","alias_value":"F6GNC4ZF","created_at":"2026-07-05T11:14:30Z"}],"graph_snapshots":[{"event_id":"sha256:22cc1bf68dcaed4ca517f63607e0aab36ff515f2e8323886b578bc419f5794c9","target":"graph","created_at":"2026-07-05T11:14:30Z","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/2506.01789/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"High-quality datasets are fundamental to training and evaluating machine learning models, yet their creation-especially with accurate human annotations-remains a significant challenge. Many dataset paper submissions lack originality, diversity, or rigorous quality control, and these shortcomings are often overlooked during peer review. Submissions also frequently omit essential details about dataset construction and properties. While existing tools such as datasheets aim to promote transparency, they are largely descriptive and do not provide standardized, measurable methods for evaluating dat","authors_text":"Aditya Parashar, Alham Fikri Aji, Ayu Purwarianti, David Anugraha, Derry Tanti Wijaya, Emmy Liu, En-Shiun Annie Lee, Genta Indra Winata, Hanyang Zhao, Jan Christian Blaise Cruz, Kezia Erina Suryoraharjo, M. Farid Adilazuarda, Monojit Choudhury, Niklas Muennighoff, Patrick Amadeus Irawan, Ruochen Zhang, Seungone Kim, Shou-Yi Hung, Sudipta Kar, Zheng-Xin Yong","cross_cats":["cs.AI","cs.CL","cs.CV","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T15:31:52Z","title":"Datasheets Aren't Enough: DataRubrics for Automated Quality Metrics and Accountability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01789","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":"sha256:6d78ddd719a58f28e7684448570586b4dda96b21df4f086a5320014e623e3b85","target":"record","created_at":"2026-07-05T11:14:30Z","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":"06357229cb96d9aabe4aa96f8a83a6a4c992c9663a266249bde7a095765952d7","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T15:31:52Z","title_canon_sha256":"4c094cd537583ad354f0d39faf9008e51fc761bece2b059e7402d55e01e5de52"},"schema_version":"1.0","source":{"id":"2506.01789","kind":"arxiv","version":2}},"canonical_sha256":"2f8cd173258e6d8601a25abb0e1f38f6403f08b85e5cf2db2d9e77099cc0569c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f8cd173258e6d8601a25abb0e1f38f6403f08b85e5cf2db2d9e77099cc0569c","first_computed_at":"2026-07-05T11:14:30.090044Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:30.090044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mJLtuX62ZnDvQ4+U2QgFaOdfY4Dl6D2qKnXYrwo0uUwqP9mZ3Ii/XU/oNfG+cmf3A8y13/k65Y2HAtuwSI7xCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:30.090494Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.01789","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d78ddd719a58f28e7684448570586b4dda96b21df4f086a5320014e623e3b85","sha256:22cc1bf68dcaed4ca517f63607e0aab36ff515f2e8323886b578bc419f5794c9"],"state_sha256":"2e933ca6e246e5548e16faf18dddd33adda350b61bfad8e5f0a2330ccc7116f7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R+tkFZCfa0Evowq1u0B1LXyOLuawouLdLU3SnNnnX10+4uNYgXkkffXVfpfJwZTSiDBVDnPtOkJV65tJ4UPwAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T15:08:33.280163Z","bundle_sha256":"634a2b349c5cf27d69eb6ea5d42c2e8b5503a989d68edc1d3b75469b9c2fcf38"}}