{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XV2NSX4WCNMUIZWXFZDZBC2CFV","short_pith_number":"pith:XV2NSX4W","schema_version":"1.0","canonical_sha256":"bd74d95f9613594466d72e47908b422d7d5164c961094137c88393c962b7ad75","source":{"kind":"arxiv","id":"2211.16073","version":2},"attestation_state":"computed","paper":{"title":"Abstract Interpretation-Based Data Leakage Static Analysis","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.PL","authors_text":"Caterina Urban, Filip Drobnjakovi\\'c, Pavle Suboti\\'c","submitted_at":"2022-11-29T10:30:40Z","abstract_excerpt":"Data leakage is a well-known problem in machine learning. Data leakage occurs when information from outside the training dataset is used to create a model. This phenomenon renders a model excessively optimistic or even useless in the real world since the model tends to leverage greatly on the unfairly acquired information. To date, detection of data leakages occurs post-mortem using run-time methods. However, due to the insidious nature of data leakage, it may not be apparent to a data scientist that a data leakage has occurred in the first place. For this reason, it is advantageous to detect "},"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":"2211.16073","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.PL","submitted_at":"2022-11-29T10:30:40Z","cross_cats_sorted":[],"title_canon_sha256":"b7bc12bc23cf53b7d2ed0e689c1ae2c3739d1ca92c1c783ec9b292f729075192","abstract_canon_sha256":"1861f630ef19d3cc9e19d17c9e1bf433efa3032cefec1a487602bfdf124b4c27"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:23.395573Z","signature_b64":"g9LD02UvE9++PQFRz76gopFJjr17g1o2bKPtp+J6g2F0ut257Pf+BXLrHK5VduIGXZI2k9WuCM8wP3pkFA+bBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd74d95f9613594466d72e47908b422d7d5164c961094137c88393c962b7ad75","last_reissued_at":"2026-07-05T08:52:23.395109Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:23.395109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Abstract Interpretation-Based Data Leakage Static Analysis","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.PL","authors_text":"Caterina Urban, Filip Drobnjakovi\\'c, Pavle Suboti\\'c","submitted_at":"2022-11-29T10:30:40Z","abstract_excerpt":"Data leakage is a well-known problem in machine learning. Data leakage occurs when information from outside the training dataset is used to create a model. This phenomenon renders a model excessively optimistic or even useless in the real world since the model tends to leverage greatly on the unfairly acquired information. To date, detection of data leakages occurs post-mortem using run-time methods. However, due to the insidious nature of data leakage, it may not be apparent to a data scientist that a data leakage has occurred in the first place. For this reason, it is advantageous to detect "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.16073","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/2211.16073/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":"2211.16073","created_at":"2026-07-05T08:52:23.395167+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.16073v2","created_at":"2026-07-05T08:52:23.395167+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.16073","created_at":"2026-07-05T08:52:23.395167+00:00"},{"alias_kind":"pith_short_12","alias_value":"XV2NSX4WCNMU","created_at":"2026-07-05T08:52:23.395167+00:00"},{"alias_kind":"pith_short_16","alias_value":"XV2NSX4WCNMUIZWX","created_at":"2026-07-05T08:52:23.395167+00:00"},{"alias_kind":"pith_short_8","alias_value":"XV2NSX4W","created_at":"2026-07-05T08:52:23.395167+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/XV2NSX4WCNMUIZWXFZDZBC2CFV","json":"https://pith.science/pith/XV2NSX4WCNMUIZWXFZDZBC2CFV.json","graph_json":"https://pith.science/api/pith-number/XV2NSX4WCNMUIZWXFZDZBC2CFV/graph.json","events_json":"https://pith.science/api/pith-number/XV2NSX4WCNMUIZWXFZDZBC2CFV/events.json","paper":"https://pith.science/paper/XV2NSX4W"},"agent_actions":{"view_html":"https://pith.science/pith/XV2NSX4WCNMUIZWXFZDZBC2CFV","download_json":"https://pith.science/pith/XV2NSX4WCNMUIZWXFZDZBC2CFV.json","view_paper":"https://pith.science/paper/XV2NSX4W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.16073&json=true","fetch_graph":"https://pith.science/api/pith-number/XV2NSX4WCNMUIZWXFZDZBC2CFV/graph.json","fetch_events":"https://pith.science/api/pith-number/XV2NSX4WCNMUIZWXFZDZBC2CFV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XV2NSX4WCNMUIZWXFZDZBC2CFV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XV2NSX4WCNMUIZWXFZDZBC2CFV/action/storage_attestation","attest_author":"https://pith.science/pith/XV2NSX4WCNMUIZWXFZDZBC2CFV/action/author_attestation","sign_citation":"https://pith.science/pith/XV2NSX4WCNMUIZWXFZDZBC2CFV/action/citation_signature","submit_replication":"https://pith.science/pith/XV2NSX4WCNMUIZWXFZDZBC2CFV/action/replication_record"}},"created_at":"2026-07-05T08:52:23.395167+00:00","updated_at":"2026-07-05T08:52:23.395167+00:00"}