{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:UO3WF663VKBUKUCAY5ZYDILQ6R","short_pith_number":"pith:UO3WF663","canonical_record":{"source":{"id":"2209.03345","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2022-09-07T17:59:42Z","cross_cats_sorted":[],"title_canon_sha256":"a304ed65dfa12a7c9531ed8257cfe100846372e5a283b3e586449c2ebd1734f3","abstract_canon_sha256":"facccac5b22ef01a10a9cf48e190626a2d7edd0ace070998ac535c3bf0e6578f"},"schema_version":"1.0"},"canonical_sha256":"a3b762fbdbaa83455040c77381a170f468c3f63b88eedb731b667153125e0d6a","source":{"kind":"arxiv","id":"2209.03345","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.03345","created_at":"2026-07-05T04:55:34Z"},{"alias_kind":"arxiv_version","alias_value":"2209.03345v1","created_at":"2026-07-05T04:55:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.03345","created_at":"2026-07-05T04:55:34Z"},{"alias_kind":"pith_short_12","alias_value":"UO3WF663VKBU","created_at":"2026-07-05T04:55:34Z"},{"alias_kind":"pith_short_16","alias_value":"UO3WF663VKBUKUCA","created_at":"2026-07-05T04:55:34Z"},{"alias_kind":"pith_short_8","alias_value":"UO3WF663","created_at":"2026-07-05T04:55:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:UO3WF663VKBUKUCAY5ZYDILQ6R","target":"record","payload":{"canonical_record":{"source":{"id":"2209.03345","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2022-09-07T17:59:42Z","cross_cats_sorted":[],"title_canon_sha256":"a304ed65dfa12a7c9531ed8257cfe100846372e5a283b3e586449c2ebd1734f3","abstract_canon_sha256":"facccac5b22ef01a10a9cf48e190626a2d7edd0ace070998ac535c3bf0e6578f"},"schema_version":"1.0"},"canonical_sha256":"a3b762fbdbaa83455040c77381a170f468c3f63b88eedb731b667153125e0d6a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:55:34.251806Z","signature_b64":"+LvSDG0uSMWsgFP3TyGXDKPTORif17mMesPHAxFbO/Xsh7mFN7VpPS4oxXMeSAnnbh/QE6kNYB0AzDTbO/vFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3b762fbdbaa83455040c77381a170f468c3f63b88eedb731b667153125e0d6a","last_reissued_at":"2026-07-05T04:55:34.251340Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:55:34.251340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.03345","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":"2026-07-05T04:55:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xrpxbmSo6qiRLqzJPKhm2rUNLLGTMaDrt9UO+ukG2IJFPCTEcejcV4+hmIowteM60LMFuhTqkKFDAyw66EmYDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:14:00.139813Z"},"content_sha256":"040136d17ba8721a62f6076412ca1bf9d6db6365b5d238292d3274d43e9501f3","schema_version":"1.0","event_id":"sha256:040136d17ba8721a62f6076412ca1bf9d6db6365b5d238292d3274d43e9501f3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:UO3WF663VKBUKUCAY5ZYDILQ6R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Leakage in Notebooks: Static Detection and Better Processes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Chenyang Yang, Christian K\\\"astner, Grace A. Lewis, Rachel A Brower-Sinning","submitted_at":"2022-09-07T17:59:42Z","abstract_excerpt":"Data science pipelines to train and evaluate models with machine learning may contain bugs just like any other code. Leakage between training and test data can lead to overestimating the model's accuracy during offline evaluations, possibly leading to deployment of low-quality models in production. Such leakage can happen easily by mistake or by following poor practices, but may be tedious and challenging to detect manually. We develop a static analysis approach to detect common forms of data leakage in data science code. Our evaluation shows that our analysis accurately detects data leakage a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.03345","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/2209.03345/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":"2026-07-05T04:55:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8MVdyo+h5Kb69CQM2YgY8Cv6xbIqiNuOANwT94k8r/X6ybrp+lMJyTAWkjSikKAAIISxvnsSqwwnMqin8uWsAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:14:00.140389Z"},"content_sha256":"ffc1b7836536adba98a35b9720a5928f01f76b9616ec8e4eb46d6610bffa55b3","schema_version":"1.0","event_id":"sha256:ffc1b7836536adba98a35b9720a5928f01f76b9616ec8e4eb46d6610bffa55b3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UO3WF663VKBUKUCAY5ZYDILQ6R/bundle.json","state_url":"https://pith.science/pith/UO3WF663VKBUKUCAY5ZYDILQ6R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UO3WF663VKBUKUCAY5ZYDILQ6R/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":"2026-08-06T01:14:00Z","links":{"resolver":"https://pith.science/pith/UO3WF663VKBUKUCAY5ZYDILQ6R","bundle":"https://pith.science/pith/UO3WF663VKBUKUCAY5ZYDILQ6R/bundle.json","state":"https://pith.science/pith/UO3WF663VKBUKUCAY5ZYDILQ6R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UO3WF663VKBUKUCAY5ZYDILQ6R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:UO3WF663VKBUKUCAY5ZYDILQ6R","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":"facccac5b22ef01a10a9cf48e190626a2d7edd0ace070998ac535c3bf0e6578f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2022-09-07T17:59:42Z","title_canon_sha256":"a304ed65dfa12a7c9531ed8257cfe100846372e5a283b3e586449c2ebd1734f3"},"schema_version":"1.0","source":{"id":"2209.03345","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.03345","created_at":"2026-07-05T04:55:34Z"},{"alias_kind":"arxiv_version","alias_value":"2209.03345v1","created_at":"2026-07-05T04:55:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.03345","created_at":"2026-07-05T04:55:34Z"},{"alias_kind":"pith_short_12","alias_value":"UO3WF663VKBU","created_at":"2026-07-05T04:55:34Z"},{"alias_kind":"pith_short_16","alias_value":"UO3WF663VKBUKUCA","created_at":"2026-07-05T04:55:34Z"},{"alias_kind":"pith_short_8","alias_value":"UO3WF663","created_at":"2026-07-05T04:55:34Z"}],"graph_snapshots":[{"event_id":"sha256:ffc1b7836536adba98a35b9720a5928f01f76b9616ec8e4eb46d6610bffa55b3","target":"graph","created_at":"2026-07-05T04:55:34Z","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/2209.03345/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data science pipelines to train and evaluate models with machine learning may contain bugs just like any other code. Leakage between training and test data can lead to overestimating the model's accuracy during offline evaluations, possibly leading to deployment of low-quality models in production. Such leakage can happen easily by mistake or by following poor practices, but may be tedious and challenging to detect manually. We develop a static analysis approach to detect common forms of data leakage in data science code. Our evaluation shows that our analysis accurately detects data leakage a","authors_text":"Chenyang Yang, Christian K\\\"astner, Grace A. Lewis, Rachel A Brower-Sinning","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2022-09-07T17:59:42Z","title":"Data Leakage in Notebooks: Static Detection and Better Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.03345","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":"sha256:040136d17ba8721a62f6076412ca1bf9d6db6365b5d238292d3274d43e9501f3","target":"record","created_at":"2026-07-05T04:55:34Z","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":"facccac5b22ef01a10a9cf48e190626a2d7edd0ace070998ac535c3bf0e6578f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2022-09-07T17:59:42Z","title_canon_sha256":"a304ed65dfa12a7c9531ed8257cfe100846372e5a283b3e586449c2ebd1734f3"},"schema_version":"1.0","source":{"id":"2209.03345","kind":"arxiv","version":1}},"canonical_sha256":"a3b762fbdbaa83455040c77381a170f468c3f63b88eedb731b667153125e0d6a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3b762fbdbaa83455040c77381a170f468c3f63b88eedb731b667153125e0d6a","first_computed_at":"2026-07-05T04:55:34.251340Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:55:34.251340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+LvSDG0uSMWsgFP3TyGXDKPTORif17mMesPHAxFbO/Xsh7mFN7VpPS4oxXMeSAnnbh/QE6kNYB0AzDTbO/vFDw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:55:34.251806Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.03345","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:040136d17ba8721a62f6076412ca1bf9d6db6365b5d238292d3274d43e9501f3","sha256:ffc1b7836536adba98a35b9720a5928f01f76b9616ec8e4eb46d6610bffa55b3"],"state_sha256":"6569db687e27e3b4e33d55c8fe1213c76ca1ab48083d3284fc3324511dbc1a33"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DR7hCjb/FILcqKQ+/MalaFETuxc+aihls6lX5AX4BrF3XXeAEuVJYffACAgzKcXQ5149rRXZ3Ws2Dw5r3sKKDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T01:14:00.145580Z","bundle_sha256":"67fe9ddbf69b37f6bdf38b2d24bec5a9e31ee81ff19de4e9ea849f119c385870"}}