{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NZ4TGI6VGILG64PGJXAUD6XI6T","short_pith_number":"pith:NZ4TGI6V","schema_version":"1.0","canonical_sha256":"6e793323d532166f71e64dc141fae8f4d5a6257688b180bbd0eccc1cc0274a24","source":{"kind":"arxiv","id":"2606.11267","version":1},"attestation_state":"computed","paper":{"title":"A prior-free blind detection of information leakage from model predictions","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Laurence A. Jacobs","submitted_at":"2026-06-09T05:13:03Z","abstract_excerpt":"Data leakage -- contamination of a model with information unavailable at baseline -- is the dominant reproducibility failure in machine-learning-based science, yet detection tools require training code, external data, or domain expertise. None operates on the artifact an auditor most often holds: the model's output. We ask what can be decided about leakage from predictions and outcomes alone. We give a decision-theoretic framework in which leakage diagnostics are functionals of the predicted-risk/outcome law, parameterized by a threshold-weighting linked to proper scoring rules and decision-cu"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.11267","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T05:13:03Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"a8b145b57115a40bda03387da71ec7289689a65f8024dbc3b2e5f10f61b8fdb5","abstract_canon_sha256":"ea95c19db73a3b55c5602f59d7588061f07cdc247a9812767ea541a2242e5711"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T00:08:15.652135Z","signature_b64":"GKUBmmYyKsnQzgfUT49wmIy/DtOsiLvhZLnbNZhKOkknd6+uQDICF5ZU7B9k2LwQUzjzYigQRA2aGr3EQHPQAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e793323d532166f71e64dc141fae8f4d5a6257688b180bbd0eccc1cc0274a24","last_reissued_at":"2026-06-11T00:08:15.651303Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T00:08:15.651303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A prior-free blind detection of information leakage from model predictions","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Laurence A. Jacobs","submitted_at":"2026-06-09T05:13:03Z","abstract_excerpt":"Data leakage -- contamination of a model with information unavailable at baseline -- is the dominant reproducibility failure in machine-learning-based science, yet detection tools require training code, external data, or domain expertise. None operates on the artifact an auditor most often holds: the model's output. We ask what can be decided about leakage from predictions and outcomes alone. We give a decision-theoretic framework in which leakage diagnostics are functionals of the predicted-risk/outcome law, parameterized by a threshold-weighting linked to proper scoring rules and decision-cu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11267","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/2606.11267/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.11267","created_at":"2026-06-11T00:08:15.651449+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.11267v1","created_at":"2026-06-11T00:08:15.651449+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11267","created_at":"2026-06-11T00:08:15.651449+00:00"},{"alias_kind":"pith_short_12","alias_value":"NZ4TGI6VGILG","created_at":"2026-06-11T00:08:15.651449+00:00"},{"alias_kind":"pith_short_16","alias_value":"NZ4TGI6VGILG64PG","created_at":"2026-06-11T00:08:15.651449+00:00"},{"alias_kind":"pith_short_8","alias_value":"NZ4TGI6V","created_at":"2026-06-11T00:08:15.651449+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NZ4TGI6VGILG64PGJXAUD6XI6T","json":"https://pith.science/pith/NZ4TGI6VGILG64PGJXAUD6XI6T.json","graph_json":"https://pith.science/api/pith-number/NZ4TGI6VGILG64PGJXAUD6XI6T/graph.json","events_json":"https://pith.science/api/pith-number/NZ4TGI6VGILG64PGJXAUD6XI6T/events.json","paper":"https://pith.science/paper/NZ4TGI6V"},"agent_actions":{"view_html":"https://pith.science/pith/NZ4TGI6VGILG64PGJXAUD6XI6T","download_json":"https://pith.science/pith/NZ4TGI6VGILG64PGJXAUD6XI6T.json","view_paper":"https://pith.science/paper/NZ4TGI6V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.11267&json=true","fetch_graph":"https://pith.science/api/pith-number/NZ4TGI6VGILG64PGJXAUD6XI6T/graph.json","fetch_events":"https://pith.science/api/pith-number/NZ4TGI6VGILG64PGJXAUD6XI6T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NZ4TGI6VGILG64PGJXAUD6XI6T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NZ4TGI6VGILG64PGJXAUD6XI6T/action/storage_attestation","attest_author":"https://pith.science/pith/NZ4TGI6VGILG64PGJXAUD6XI6T/action/author_attestation","sign_citation":"https://pith.science/pith/NZ4TGI6VGILG64PGJXAUD6XI6T/action/citation_signature","submit_replication":"https://pith.science/pith/NZ4TGI6VGILG64PGJXAUD6XI6T/action/replication_record"}},"created_at":"2026-06-11T00:08:15.651449+00:00","updated_at":"2026-06-11T00:08:15.651449+00:00"}