{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:AM2O32YGYVL5JVFABVHJQVJTZE","short_pith_number":"pith:AM2O32YG","canonical_record":{"source":{"id":"2503.11366","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2025-03-14T13:04:39Z","cross_cats_sorted":[],"title_canon_sha256":"b9176fd91d7eacc64151ae571fd268b9bdf31672dd2f0a036836cfe877c13998","abstract_canon_sha256":"636767f2ade05ad5b1d2ebec6b7f83ed3337563246ab00a8559d367f2b181edb"},"schema_version":"1.0"},"canonical_sha256":"0334edeb06c557d4d4a00d4e985533c90e91ae004515c2969b84141966a31515","source":{"kind":"arxiv","id":"2503.11366","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.11366","created_at":"2026-07-05T10:31:29Z"},{"alias_kind":"arxiv_version","alias_value":"2503.11366v1","created_at":"2026-07-05T10:31:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.11366","created_at":"2026-07-05T10:31:29Z"},{"alias_kind":"pith_short_12","alias_value":"AM2O32YGYVL5","created_at":"2026-07-05T10:31:29Z"},{"alias_kind":"pith_short_16","alias_value":"AM2O32YGYVL5JVFA","created_at":"2026-07-05T10:31:29Z"},{"alias_kind":"pith_short_8","alias_value":"AM2O32YG","created_at":"2026-07-05T10:31:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:AM2O32YGYVL5JVFABVHJQVJTZE","target":"record","payload":{"canonical_record":{"source":{"id":"2503.11366","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2025-03-14T13:04:39Z","cross_cats_sorted":[],"title_canon_sha256":"b9176fd91d7eacc64151ae571fd268b9bdf31672dd2f0a036836cfe877c13998","abstract_canon_sha256":"636767f2ade05ad5b1d2ebec6b7f83ed3337563246ab00a8559d367f2b181edb"},"schema_version":"1.0"},"canonical_sha256":"0334edeb06c557d4d4a00d4e985533c90e91ae004515c2969b84141966a31515","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:29.948960Z","signature_b64":"7iFrovj3Uqx62sRzc1f1AiZVJKPmR0yJuf+hzcKiU5m3W7gsMp6ADKclOi1p40maGXijA4RFG1xqcLMWvEd/Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0334edeb06c557d4d4a00d4e985533c90e91ae004515c2969b84141966a31515","last_reissued_at":"2026-07-05T10:31:29.948023Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:29.948023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.11366","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":"2026-07-05T10:31:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M+2MRWL/pgUL1Z8fPzb5X69qPTLoEoq59HlhL84e4fUnCXR/oFk/tFuSKNNu1csaCf9jnFU71bLbqi5uoLvpCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T19:23:06.616893Z"},"content_sha256":"00b2ed4721b1d38a8ae842a2ff375895134822227c648f9322f83917ee740c1e","schema_version":"1.0","event_id":"sha256:00b2ed4721b1d38a8ae842a2ff375895134822227c648f9322f83917ee740c1e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:AM2O32YGYVL5JVFABVHJQVJTZE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Step-by-Step Data Cleaning Recommendations to Improve ML Prediction Accuracy","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Felix Naumann, Hazar Harmouch, Sedir Mohammed","submitted_at":"2025-03-14T13:04:39Z","abstract_excerpt":"Data quality is crucial in machine learning (ML) applications, as errors in the data can significantly impact the prediction accuracy of the underlying ML model. Therefore, data cleaning is an integral component of any ML pipeline. However, in practical scenarios, data cleaning incurs significant costs, as it often involves domain experts for configuring and executing the cleaning process. Thus, efficient resource allocation during data cleaning can enhance ML prediction accuracy while controlling expenses.\n  This paper presents COMET, a system designed to optimize data cleaning efforts for ML"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.11366","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/2503.11366/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":"2026-07-05T10:31:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+bst91yyCD3e8zQkg/zImVMado6lNO0iE9tEmYBqrt86TV/sLwVZID47qoDkQ8dy2G3j3gRPq+2jPdhrmcAsAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T19:23:06.617428Z"},"content_sha256":"d933e680bed850ad4669aefc28cafc916d0d72f6058e5766c6a30353591bbaef","schema_version":"1.0","event_id":"sha256:d933e680bed850ad4669aefc28cafc916d0d72f6058e5766c6a30353591bbaef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AM2O32YGYVL5JVFABVHJQVJTZE/bundle.json","state_url":"https://pith.science/pith/AM2O32YGYVL5JVFABVHJQVJTZE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AM2O32YGYVL5JVFABVHJQVJTZE/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":"2026-08-22T19:23:06Z","links":{"resolver":"https://pith.science/pith/AM2O32YGYVL5JVFABVHJQVJTZE","bundle":"https://pith.science/pith/AM2O32YGYVL5JVFABVHJQVJTZE/bundle.json","state":"https://pith.science/pith/AM2O32YGYVL5JVFABVHJQVJTZE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AM2O32YGYVL5JVFABVHJQVJTZE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AM2O32YGYVL5JVFABVHJQVJTZE","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":"636767f2ade05ad5b1d2ebec6b7f83ed3337563246ab00a8559d367f2b181edb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2025-03-14T13:04:39Z","title_canon_sha256":"b9176fd91d7eacc64151ae571fd268b9bdf31672dd2f0a036836cfe877c13998"},"schema_version":"1.0","source":{"id":"2503.11366","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.11366","created_at":"2026-07-05T10:31:29Z"},{"alias_kind":"arxiv_version","alias_value":"2503.11366v1","created_at":"2026-07-05T10:31:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.11366","created_at":"2026-07-05T10:31:29Z"},{"alias_kind":"pith_short_12","alias_value":"AM2O32YGYVL5","created_at":"2026-07-05T10:31:29Z"},{"alias_kind":"pith_short_16","alias_value":"AM2O32YGYVL5JVFA","created_at":"2026-07-05T10:31:29Z"},{"alias_kind":"pith_short_8","alias_value":"AM2O32YG","created_at":"2026-07-05T10:31:29Z"}],"graph_snapshots":[{"event_id":"sha256:d933e680bed850ad4669aefc28cafc916d0d72f6058e5766c6a30353591bbaef","target":"graph","created_at":"2026-07-05T10:31:29Z","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/2503.11366/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data quality is crucial in machine learning (ML) applications, as errors in the data can significantly impact the prediction accuracy of the underlying ML model. Therefore, data cleaning is an integral component of any ML pipeline. However, in practical scenarios, data cleaning incurs significant costs, as it often involves domain experts for configuring and executing the cleaning process. Thus, efficient resource allocation during data cleaning can enhance ML prediction accuracy while controlling expenses.\n  This paper presents COMET, a system designed to optimize data cleaning efforts for ML","authors_text":"Felix Naumann, Hazar Harmouch, Sedir Mohammed","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2025-03-14T13:04:39Z","title":"Step-by-Step Data Cleaning Recommendations to Improve ML Prediction Accuracy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.11366","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":"sha256:00b2ed4721b1d38a8ae842a2ff375895134822227c648f9322f83917ee740c1e","target":"record","created_at":"2026-07-05T10:31:29Z","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":"636767f2ade05ad5b1d2ebec6b7f83ed3337563246ab00a8559d367f2b181edb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2025-03-14T13:04:39Z","title_canon_sha256":"b9176fd91d7eacc64151ae571fd268b9bdf31672dd2f0a036836cfe877c13998"},"schema_version":"1.0","source":{"id":"2503.11366","kind":"arxiv","version":1}},"canonical_sha256":"0334edeb06c557d4d4a00d4e985533c90e91ae004515c2969b84141966a31515","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0334edeb06c557d4d4a00d4e985533c90e91ae004515c2969b84141966a31515","first_computed_at":"2026-07-05T10:31:29.948023Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:31:29.948023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7iFrovj3Uqx62sRzc1f1AiZVJKPmR0yJuf+hzcKiU5m3W7gsMp6ADKclOi1p40maGXijA4RFG1xqcLMWvEd/Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:31:29.948960Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.11366","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:00b2ed4721b1d38a8ae842a2ff375895134822227c648f9322f83917ee740c1e","sha256:d933e680bed850ad4669aefc28cafc916d0d72f6058e5766c6a30353591bbaef"],"state_sha256":"c0243c351b0a086b149c1a140af3bb1628950288d9aec91d7e2a6ab72dc10f6a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8pvnEWxDYEp6a5wfA9YCPmODHZuPONDMxdWUiCLDTO7gkLQHnt1fNB9PYmYLk3nuamG6TPooDvQ0eZeEgaCEBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T19:23:06.621823Z","bundle_sha256":"b659d993dafe017dc806b66d464d076cd86b40322992f3bff5c64390531f9257"}}