{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:CVGV3CCRJL4Y42DJ43RLY7ISHU","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":"3d06f00faf5243a0b4ab803d026c8e8da1e5e011df7ef382dce784e58e24b7bf","cross_cats_sorted":["cs.AI","stat.ME"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-14T16:44:59Z","title_canon_sha256":"529a3f2c0740807242d2c0e4cb49ed18c2f76f030878313ac98972c9b57c9964"},"schema_version":"1.0","source":{"id":"2207.07048","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.07048","created_at":"2026-07-05T04:40:20Z"},{"alias_kind":"arxiv_version","alias_value":"2207.07048v1","created_at":"2026-07-05T04:40:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.07048","created_at":"2026-07-05T04:40:20Z"},{"alias_kind":"pith_short_12","alias_value":"CVGV3CCRJL4Y","created_at":"2026-07-05T04:40:20Z"},{"alias_kind":"pith_short_16","alias_value":"CVGV3CCRJL4Y42DJ","created_at":"2026-07-05T04:40:20Z"},{"alias_kind":"pith_short_8","alias_value":"CVGV3CCR","created_at":"2026-07-05T04:40:20Z"}],"graph_snapshots":[{"event_id":"sha256:3d19f0a23cf16e3d39f759b9b6b064644a5515f2352b50a25944deac84b4670b","target":"graph","created_at":"2026-07-05T04:40:20Z","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/2207.07048/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The use of machine learning (ML) methods for prediction and forecasting has become widespread across the quantitative sciences. However, there are many known methodological pitfalls, including data leakage, in ML-based science. In this paper, we systematically investigate reproducibility issues in ML-based science. We show that data leakage is indeed a widespread problem and has led to severe reproducibility failures. Specifically, through a survey of literature in research communities that adopted ML methods, we find 17 fields where errors have been found, collectively affecting 329 papers an","authors_text":"Arvind Narayanan, Sayash Kapoor","cross_cats":["cs.AI","stat.ME"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-14T16:44:59Z","title":"Leakage and the Reproducibility Crisis in ML-based Science"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.07048","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":"sha256:4fb76d3a02b5c95f668015f4d33ab2ec120c8f662d5607a0306079e6fb7179d3","target":"record","created_at":"2026-07-05T04:40:20Z","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":"3d06f00faf5243a0b4ab803d026c8e8da1e5e011df7ef382dce784e58e24b7bf","cross_cats_sorted":["cs.AI","stat.ME"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-14T16:44:59Z","title_canon_sha256":"529a3f2c0740807242d2c0e4cb49ed18c2f76f030878313ac98972c9b57c9964"},"schema_version":"1.0","source":{"id":"2207.07048","kind":"arxiv","version":1}},"canonical_sha256":"154d5d88514af98e6869e6e2bc7d123d10f8ec46c3c82ea0503555cc5c4943a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"154d5d88514af98e6869e6e2bc7d123d10f8ec46c3c82ea0503555cc5c4943a6","first_computed_at":"2026-07-05T04:40:20.375180Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:40:20.375180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HJT+tATFRdsMMLsZT1XtEX8V1NHUQQSAnKn5AkMDdZi4mf35CvJGsHmwk4c9DEq2BvZR+kISdE4vt5JksZPTDg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:40:20.375618Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.07048","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fb76d3a02b5c95f668015f4d33ab2ec120c8f662d5607a0306079e6fb7179d3","sha256:3d19f0a23cf16e3d39f759b9b6b064644a5515f2352b50a25944deac84b4670b"],"state_sha256":"3b0152b7a76cad0e7bf934ff46806efe3eb7aab18d8ffe5bbdf8589932d78655"}