{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:UNKCTDX5AX7X34N5OK2H7TGEGB","short_pith_number":"pith:UNKCTDX5","canonical_record":{"source":{"id":"1904.09483","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-04-20T19:12:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9fe48957e94b60182e7c9eec707684ebc76ded55843e43ebf69f90d002a170f7","abstract_canon_sha256":"208c43fd1e40ee12320bfb62c86052db4e65b16bad1d49672644b9f309b0b66f"},"schema_version":"1.0"},"canonical_sha256":"a354298efd05ff7df1bd72b47fccc43068a3df1e0023eaefe521c5ca4783e7f7","source":{"kind":"arxiv","id":"1904.09483","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.09483","created_at":"2026-07-05T02:29:07Z"},{"alias_kind":"arxiv_version","alias_value":"1904.09483v3","created_at":"2026-07-05T02:29:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.09483","created_at":"2026-07-05T02:29:07Z"},{"alias_kind":"pith_short_12","alias_value":"UNKCTDX5AX7X","created_at":"2026-07-05T02:29:07Z"},{"alias_kind":"pith_short_16","alias_value":"UNKCTDX5AX7X34N5","created_at":"2026-07-05T02:29:07Z"},{"alias_kind":"pith_short_8","alias_value":"UNKCTDX5","created_at":"2026-07-05T02:29:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:UNKCTDX5AX7X34N5OK2H7TGEGB","target":"record","payload":{"canonical_record":{"source":{"id":"1904.09483","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-04-20T19:12:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9fe48957e94b60182e7c9eec707684ebc76ded55843e43ebf69f90d002a170f7","abstract_canon_sha256":"208c43fd1e40ee12320bfb62c86052db4e65b16bad1d49672644b9f309b0b66f"},"schema_version":"1.0"},"canonical_sha256":"a354298efd05ff7df1bd72b47fccc43068a3df1e0023eaefe521c5ca4783e7f7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:29:07.914291Z","signature_b64":"iRMPoc6ewsaw/qLfZtZy72nV+KgyKfYHl2UiQbPkz0KRHP7A+uhtQ15LXy/JI17eTuekgLgVdNzd4lc6Dt3CDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a354298efd05ff7df1bd72b47fccc43068a3df1e0023eaefe521c5ca4783e7f7","last_reissued_at":"2026-07-05T02:29:07.913762Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:29:07.913762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.09483","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:29:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UnaOQl+cOm3kcxwXPvPNTk60S69lfQVO9GH3Mumdgbn/hlTZ7WH3h0N8Z76XwYJSY/QHV5FfSnZceSYbB9EIAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:58:10.284732Z"},"content_sha256":"d3fbc29a5944c160f0aa3ca56c5a26208ed2e9d9de4a398a8b6929a01b21cf1d","schema_version":"1.0","event_id":"sha256:d3fbc29a5944c160f0aa3ca56c5a26208ed2e9d9de4a398a8b6929a01b21cf1d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:UNKCTDX5AX7X34N5OK2H7TGEGB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CleanML: A Study for Evaluating the Impact of Data Cleaning on ML Classification Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"Ce Zhang, Jennifer Blase, Peng Li, Xi Rao, Xu Chu, Yue Zhang","submitted_at":"2019-04-20T19:12:03Z","abstract_excerpt":"Data quality affects machine learning (ML) model performances, and data scientists spend considerable amount of time on data cleaning before model training. However, to date, there does not exist a rigorous study on how exactly cleaning affects ML -- ML community usually focuses on developing ML algorithms that are robust to some particular noise types of certain distributions, while database (DB) community has been mostly studying the problem of data cleaning alone without considering how data is consumed by downstream ML analytics. We propose a CleanML study that systematically investigates "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.09483","kind":"arxiv","version":3},"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/1904.09483/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":"2026-07-05T02:29:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DiHnQjTHAlWPoROl8xRsddVc0CXwDu8EE7TcrRAPROFZfJ7Tx4w9sA7c+AEOyze3Qv6iFS8UKeIXb5R2+2bNAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:58:10.287085Z"},"content_sha256":"0cb354d4b61d309bdbd079d52f88f126b9a737edd72e30312b6c9266af9de948","schema_version":"1.0","event_id":"sha256:0cb354d4b61d309bdbd079d52f88f126b9a737edd72e30312b6c9266af9de948"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UNKCTDX5AX7X34N5OK2H7TGEGB/bundle.json","state_url":"https://pith.science/pith/UNKCTDX5AX7X34N5OK2H7TGEGB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UNKCTDX5AX7X34N5OK2H7TGEGB/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":"2026-08-09T13:58:10Z","links":{"resolver":"https://pith.science/pith/UNKCTDX5AX7X34N5OK2H7TGEGB","bundle":"https://pith.science/pith/UNKCTDX5AX7X34N5OK2H7TGEGB/bundle.json","state":"https://pith.science/pith/UNKCTDX5AX7X34N5OK2H7TGEGB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UNKCTDX5AX7X34N5OK2H7TGEGB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:UNKCTDX5AX7X34N5OK2H7TGEGB","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":"208c43fd1e40ee12320bfb62c86052db4e65b16bad1d49672644b9f309b0b66f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-04-20T19:12:03Z","title_canon_sha256":"9fe48957e94b60182e7c9eec707684ebc76ded55843e43ebf69f90d002a170f7"},"schema_version":"1.0","source":{"id":"1904.09483","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.09483","created_at":"2026-07-05T02:29:07Z"},{"alias_kind":"arxiv_version","alias_value":"1904.09483v3","created_at":"2026-07-05T02:29:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.09483","created_at":"2026-07-05T02:29:07Z"},{"alias_kind":"pith_short_12","alias_value":"UNKCTDX5AX7X","created_at":"2026-07-05T02:29:07Z"},{"alias_kind":"pith_short_16","alias_value":"UNKCTDX5AX7X34N5","created_at":"2026-07-05T02:29:07Z"},{"alias_kind":"pith_short_8","alias_value":"UNKCTDX5","created_at":"2026-07-05T02:29:07Z"}],"graph_snapshots":[{"event_id":"sha256:0cb354d4b61d309bdbd079d52f88f126b9a737edd72e30312b6c9266af9de948","target":"graph","created_at":"2026-07-05T02:29:07Z","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/1904.09483/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data quality affects machine learning (ML) model performances, and data scientists spend considerable amount of time on data cleaning before model training. However, to date, there does not exist a rigorous study on how exactly cleaning affects ML -- ML community usually focuses on developing ML algorithms that are robust to some particular noise types of certain distributions, while database (DB) community has been mostly studying the problem of data cleaning alone without considering how data is consumed by downstream ML analytics. We propose a CleanML study that systematically investigates ","authors_text":"Ce Zhang, Jennifer Blase, Peng Li, Xi Rao, Xu Chu, Yue Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-04-20T19:12:03Z","title":"CleanML: A Study for Evaluating the Impact of Data Cleaning on ML Classification Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.09483","kind":"arxiv","version":3},"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:d3fbc29a5944c160f0aa3ca56c5a26208ed2e9d9de4a398a8b6929a01b21cf1d","target":"record","created_at":"2026-07-05T02:29:07Z","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":"208c43fd1e40ee12320bfb62c86052db4e65b16bad1d49672644b9f309b0b66f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-04-20T19:12:03Z","title_canon_sha256":"9fe48957e94b60182e7c9eec707684ebc76ded55843e43ebf69f90d002a170f7"},"schema_version":"1.0","source":{"id":"1904.09483","kind":"arxiv","version":3}},"canonical_sha256":"a354298efd05ff7df1bd72b47fccc43068a3df1e0023eaefe521c5ca4783e7f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a354298efd05ff7df1bd72b47fccc43068a3df1e0023eaefe521c5ca4783e7f7","first_computed_at":"2026-07-05T02:29:07.913762Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:29:07.913762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iRMPoc6ewsaw/qLfZtZy72nV+KgyKfYHl2UiQbPkz0KRHP7A+uhtQ15LXy/JI17eTuekgLgVdNzd4lc6Dt3CDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:29:07.914291Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.09483","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d3fbc29a5944c160f0aa3ca56c5a26208ed2e9d9de4a398a8b6929a01b21cf1d","sha256:0cb354d4b61d309bdbd079d52f88f126b9a737edd72e30312b6c9266af9de948"],"state_sha256":"e49b89cb5c5951955c232a95d8379436c5a49ebdeb76f673d93345258a83fc75"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q/Q99QJ8RCWc5xUFxAnTmaQl/gfQrOakdcj99Dvx44pid75DIhvdBVxvb6v/shgnyxyhBZkY3UdfRWiovHaPDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T13:58:10.294639Z","bundle_sha256":"acac2342c51b2503db9174cc953af8cab31ec95efc0e00f357fe72eb2b279136"}}