{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:RCTTN2ZJL3O3ETTADQFDKXLNVP","short_pith_number":"pith:RCTTN2ZJ","canonical_record":{"source":{"id":"2311.04179","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-07T18:06:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"640d7e59e5ee410e1dfba28b8ae961785b1e3f06c6dd5d9567f330328940ecd9","abstract_canon_sha256":"30dd9269cced59d556f6f7bc66b851c44c6b167b44deb4bc08c788a2531092ea"},"schema_version":"1.0"},"canonical_sha256":"88a736eb295eddb24e601c0a355d6dabd46ebbf07795309cde9774bc49ee04b7","source":{"kind":"arxiv","id":"2311.04179","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.04179","created_at":"2026-07-05T11:50:25Z"},{"alias_kind":"arxiv_version","alias_value":"2311.04179v2","created_at":"2026-07-05T11:50:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.04179","created_at":"2026-07-05T11:50:25Z"},{"alias_kind":"pith_short_12","alias_value":"RCTTN2ZJL3O3","created_at":"2026-07-05T11:50:25Z"},{"alias_kind":"pith_short_16","alias_value":"RCTTN2ZJL3O3ETTA","created_at":"2026-07-05T11:50:25Z"},{"alias_kind":"pith_short_8","alias_value":"RCTTN2ZJ","created_at":"2026-07-05T11:50:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:RCTTN2ZJL3O3ETTADQFDKXLNVP","target":"record","payload":{"canonical_record":{"source":{"id":"2311.04179","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-07T18:06:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"640d7e59e5ee410e1dfba28b8ae961785b1e3f06c6dd5d9567f330328940ecd9","abstract_canon_sha256":"30dd9269cced59d556f6f7bc66b851c44c6b167b44deb4bc08c788a2531092ea"},"schema_version":"1.0"},"canonical_sha256":"88a736eb295eddb24e601c0a355d6dabd46ebbf07795309cde9774bc49ee04b7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:25.056020Z","signature_b64":"iMg+6KTd9uX3kmTPD59+VrFAVWthDILFLawLykxkEidY2hE88W8PSqhoTFFr9liDzCy4Z/dWaSEfeZuomViEAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88a736eb295eddb24e601c0a355d6dabd46ebbf07795309cde9774bc49ee04b7","last_reissued_at":"2026-07-05T11:50:25.055492Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:25.055492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.04179","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":"2026-07-05T11:50:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8U94vC7K3KOhgCMxvn0WpN4TgCOMRGJHclrDNeXPTE8iG2yIHAY7tBoDXgE26v8suBumPAJIp3r4z41sm2kBAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:51:26.662077Z"},"content_sha256":"b5317dbc097c6c739a1f5922fcc654e4b7a209f34ccb88261dbece0f616b596d","schema_version":"1.0","event_id":"sha256:b5317dbc097c6c739a1f5922fcc654e4b7a209f34ccb88261dbece0f616b596d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:RCTTN2ZJL3O3ETTADQFDKXLNVP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On Leakage in Machine Learning Pipelines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Abhijit Kulkarni, Bradley C. Love, Eliana Nicolaisen-Sobesky, Federico Raimondo, Juergen Dukart, Juha Lahnakoski, Kaustubh R. Patil, Leonard Sasse, Michael G\\\"otz, Sami Hamdan, Simon B. Eickhoff, Vera Komeyer","submitted_at":"2023-11-07T18:06:29Z","abstract_excerpt":"Machine learning (ML) provides powerful tools for predictive modeling. ML's popularity stems from the promise of sample-level prediction with applications across a variety of fields from physics and marketing to healthcare. However, if not properly implemented and evaluated, ML pipelines may contain leakage typically resulting in overoptimistic performance estimates and failure to generalize to new data. This can have severe negative financial and societal implications. Our aim is to expand understanding associated with causes leading to leakage when designing, implementing, and evaluating ML "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.04179","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/2311.04179/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":"2026-07-05T11:50:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h2I5SZ4KA5nWcfJRCa2iheDcXQW9OaXQWUBGIS+qprdImTfkJdVfjME5FFLzDhE6YPlq5D2GqMIsDiXU0mNsAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:51:26.662462Z"},"content_sha256":"9ccc11c2ac98e9a2e17bbb609129a1b7d774239c7bbf606c61ad40c1336f80a1","schema_version":"1.0","event_id":"sha256:9ccc11c2ac98e9a2e17bbb609129a1b7d774239c7bbf606c61ad40c1336f80a1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RCTTN2ZJL3O3ETTADQFDKXLNVP/bundle.json","state_url":"https://pith.science/pith/RCTTN2ZJL3O3ETTADQFDKXLNVP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RCTTN2ZJL3O3ETTADQFDKXLNVP/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":"2026-07-07T15:51:26Z","links":{"resolver":"https://pith.science/pith/RCTTN2ZJL3O3ETTADQFDKXLNVP","bundle":"https://pith.science/pith/RCTTN2ZJL3O3ETTADQFDKXLNVP/bundle.json","state":"https://pith.science/pith/RCTTN2ZJL3O3ETTADQFDKXLNVP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RCTTN2ZJL3O3ETTADQFDKXLNVP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RCTTN2ZJL3O3ETTADQFDKXLNVP","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":"30dd9269cced59d556f6f7bc66b851c44c6b167b44deb4bc08c788a2531092ea","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-07T18:06:29Z","title_canon_sha256":"640d7e59e5ee410e1dfba28b8ae961785b1e3f06c6dd5d9567f330328940ecd9"},"schema_version":"1.0","source":{"id":"2311.04179","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.04179","created_at":"2026-07-05T11:50:25Z"},{"alias_kind":"arxiv_version","alias_value":"2311.04179v2","created_at":"2026-07-05T11:50:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.04179","created_at":"2026-07-05T11:50:25Z"},{"alias_kind":"pith_short_12","alias_value":"RCTTN2ZJL3O3","created_at":"2026-07-05T11:50:25Z"},{"alias_kind":"pith_short_16","alias_value":"RCTTN2ZJL3O3ETTA","created_at":"2026-07-05T11:50:25Z"},{"alias_kind":"pith_short_8","alias_value":"RCTTN2ZJ","created_at":"2026-07-05T11:50:25Z"}],"graph_snapshots":[{"event_id":"sha256:9ccc11c2ac98e9a2e17bbb609129a1b7d774239c7bbf606c61ad40c1336f80a1","target":"graph","created_at":"2026-07-05T11:50:25Z","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/2311.04179/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine learning (ML) provides powerful tools for predictive modeling. ML's popularity stems from the promise of sample-level prediction with applications across a variety of fields from physics and marketing to healthcare. However, if not properly implemented and evaluated, ML pipelines may contain leakage typically resulting in overoptimistic performance estimates and failure to generalize to new data. This can have severe negative financial and societal implications. Our aim is to expand understanding associated with causes leading to leakage when designing, implementing, and evaluating ML ","authors_text":"Abhijit Kulkarni, Bradley C. Love, Eliana Nicolaisen-Sobesky, Federico Raimondo, Juergen Dukart, Juha Lahnakoski, Kaustubh R. Patil, Leonard Sasse, Michael G\\\"otz, Sami Hamdan, Simon B. Eickhoff, Vera Komeyer","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-07T18:06:29Z","title":"On Leakage in Machine Learning Pipelines"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.04179","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:b5317dbc097c6c739a1f5922fcc654e4b7a209f34ccb88261dbece0f616b596d","target":"record","created_at":"2026-07-05T11:50:25Z","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":"30dd9269cced59d556f6f7bc66b851c44c6b167b44deb4bc08c788a2531092ea","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-07T18:06:29Z","title_canon_sha256":"640d7e59e5ee410e1dfba28b8ae961785b1e3f06c6dd5d9567f330328940ecd9"},"schema_version":"1.0","source":{"id":"2311.04179","kind":"arxiv","version":2}},"canonical_sha256":"88a736eb295eddb24e601c0a355d6dabd46ebbf07795309cde9774bc49ee04b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88a736eb295eddb24e601c0a355d6dabd46ebbf07795309cde9774bc49ee04b7","first_computed_at":"2026-07-05T11:50:25.055492Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:50:25.055492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iMg+6KTd9uX3kmTPD59+VrFAVWthDILFLawLykxkEidY2hE88W8PSqhoTFFr9liDzCy4Z/dWaSEfeZuomViEAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:50:25.056020Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.04179","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5317dbc097c6c739a1f5922fcc654e4b7a209f34ccb88261dbece0f616b596d","sha256:9ccc11c2ac98e9a2e17bbb609129a1b7d774239c7bbf606c61ad40c1336f80a1"],"state_sha256":"20675df273fbd1bda8dddf4351d5d492f0a65456791941ea71364bbbb85ebc82"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h6agaMKh721oPaX4VoBVd+qdfKOs7EhDsjF8veEhqbE217FU1kHV9DsxuvC1t9X27i70CTiMQpd/ElvY7O8BBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T15:51:26.664500Z","bundle_sha256":"4891e754b4c89b48a5bb5a72f840dac30be2627bd1569c3a234c94e5446bb00b"}}