{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2QTHUPPS6L7O275HC4UQZCSNN5","short_pith_number":"pith:2QTHUPPS","schema_version":"1.0","canonical_sha256":"d4267a3df2f2feed7fa717290c8a4d6f566f100c6c9fc613baa52dcd4368b102","source":{"kind":"arxiv","id":"2307.08643","version":4},"attestation_state":"computed","paper":{"title":"Corruptions of Supervised Learning Problems: Typology and Mitigations","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Laura Iacovissi, Nan Lu, Robert C. Williamson","submitted_at":"2023-07-17T16:57:01Z","abstract_excerpt":"Corruption is notoriously widespread in data collection. Despite extensive research, the existing literature predominantly focuses on specific settings and learning scenarios, lacking a unified view of corruption modelization and mitigation. In this work, we develop a general theory of corruption, which incorporates all modifications to a supervised learning problem, including changes in model class and loss. Focusing on changes to the underlying probability distributions via Markov kernels, our approach leads to three novel opportunities. First, it enables the construction of a novel, provabl"},"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":"2307.08643","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-17T16:57:01Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"680b2f9d7fe7e07941ccd874f307d44eccf93f4f9a503e3fe65132841c28c47d","abstract_canon_sha256":"5cc9440645d2fda949c1822222658afc3c05abc8e1c587a38457014f6e0d66b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:24.489761Z","signature_b64":"LD4DzvxE5eMk7n7saohJBzMLqKEbkuMlGl4kYfAQNWfSeaWLELjO+UsyGH/TqDQpMo8yBHqwOOBMRy8FiUNXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4267a3df2f2feed7fa717290c8a4d6f566f100c6c9fc613baa52dcd4368b102","last_reissued_at":"2026-05-20T00:05:24.489049Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:24.489049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Corruptions of Supervised Learning Problems: Typology and Mitigations","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Laura Iacovissi, Nan Lu, Robert C. Williamson","submitted_at":"2023-07-17T16:57:01Z","abstract_excerpt":"Corruption is notoriously widespread in data collection. Despite extensive research, the existing literature predominantly focuses on specific settings and learning scenarios, lacking a unified view of corruption modelization and mitigation. In this work, we develop a general theory of corruption, which incorporates all modifications to a supervised learning problem, including changes in model class and loss. Focusing on changes to the underlying probability distributions via Markov kernels, our approach leads to three novel opportunities. First, it enables the construction of a novel, provabl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.08643","kind":"arxiv","version":4},"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/2307.08643/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":"2307.08643","created_at":"2026-05-20T00:05:24.489148+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.08643v4","created_at":"2026-05-20T00:05:24.489148+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.08643","created_at":"2026-05-20T00:05:24.489148+00:00"},{"alias_kind":"pith_short_12","alias_value":"2QTHUPPS6L7O","created_at":"2026-05-20T00:05:24.489148+00:00"},{"alias_kind":"pith_short_16","alias_value":"2QTHUPPS6L7O275H","created_at":"2026-05-20T00:05:24.489148+00:00"},{"alias_kind":"pith_short_8","alias_value":"2QTHUPPS","created_at":"2026-05-20T00:05:24.489148+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/2QTHUPPS6L7O275HC4UQZCSNN5","json":"https://pith.science/pith/2QTHUPPS6L7O275HC4UQZCSNN5.json","graph_json":"https://pith.science/api/pith-number/2QTHUPPS6L7O275HC4UQZCSNN5/graph.json","events_json":"https://pith.science/api/pith-number/2QTHUPPS6L7O275HC4UQZCSNN5/events.json","paper":"https://pith.science/paper/2QTHUPPS"},"agent_actions":{"view_html":"https://pith.science/pith/2QTHUPPS6L7O275HC4UQZCSNN5","download_json":"https://pith.science/pith/2QTHUPPS6L7O275HC4UQZCSNN5.json","view_paper":"https://pith.science/paper/2QTHUPPS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.08643&json=true","fetch_graph":"https://pith.science/api/pith-number/2QTHUPPS6L7O275HC4UQZCSNN5/graph.json","fetch_events":"https://pith.science/api/pith-number/2QTHUPPS6L7O275HC4UQZCSNN5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2QTHUPPS6L7O275HC4UQZCSNN5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2QTHUPPS6L7O275HC4UQZCSNN5/action/storage_attestation","attest_author":"https://pith.science/pith/2QTHUPPS6L7O275HC4UQZCSNN5/action/author_attestation","sign_citation":"https://pith.science/pith/2QTHUPPS6L7O275HC4UQZCSNN5/action/citation_signature","submit_replication":"https://pith.science/pith/2QTHUPPS6L7O275HC4UQZCSNN5/action/replication_record"}},"created_at":"2026-05-20T00:05:24.489148+00:00","updated_at":"2026-05-20T00:05:24.489148+00:00"}