{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EBK3T2JZ6XMYGWO4A2DJ7PG5LC","short_pith_number":"pith:EBK3T2JZ","schema_version":"1.0","canonical_sha256":"2055b9e939f5d98359dc06869fbcdd5885ebb19ec66e081d4f5a65866ccd55d0","source":{"kind":"arxiv","id":"2309.05528","version":2},"attestation_state":"computed","paper":{"title":"On the detection of Out-Of-Distribution samples in Multiple Instance Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fabrice Andr\\'e, Hugues Talbot, Lo\\\"ic Le Bescond, Maria Vakalopoulou, Stergios Christodoulidis","submitted_at":"2023-09-11T15:12:05Z","abstract_excerpt":"The deployment of machine learning solutions in real-world scenarios often involves addressing the challenge of out-of-distribution (OOD) detection. While significant efforts have been devoted to OOD detection in classical supervised settings, the context of weakly supervised learning, particularly the Multiple Instance Learning (MIL) framework, remains under-explored. In this study, we tackle this challenge by adapting post-hoc OOD detection methods to the MIL setting while introducing a novel benchmark specifically designed to assess OOD detection performance in weakly supervised scenarios. "},"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":"2309.05528","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-11T15:12:05Z","cross_cats_sorted":[],"title_canon_sha256":"bab4fdf696d5670d406ac21fe68fdb184e9a64499cc499cab7a430f2d32ba12a","abstract_canon_sha256":"81d1b08e224fbe73470ea4eebf58999eb7229b0c1cecfc8f11e10b9ee07e5287"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:10:49.799996Z","signature_b64":"OWwtUkO0bk7nMclN3QtQ9bs/vy0A11F0uleu8XJ9RYBVBp65veI2vVC7h3gRUKFchhZQG4ZZNU9xbXyS31j5Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2055b9e939f5d98359dc06869fbcdd5885ebb19ec66e081d4f5a65866ccd55d0","last_reissued_at":"2026-07-05T07:10:49.799493Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:10:49.799493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the detection of Out-Of-Distribution samples in Multiple Instance Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fabrice Andr\\'e, Hugues Talbot, Lo\\\"ic Le Bescond, Maria Vakalopoulou, Stergios Christodoulidis","submitted_at":"2023-09-11T15:12:05Z","abstract_excerpt":"The deployment of machine learning solutions in real-world scenarios often involves addressing the challenge of out-of-distribution (OOD) detection. While significant efforts have been devoted to OOD detection in classical supervised settings, the context of weakly supervised learning, particularly the Multiple Instance Learning (MIL) framework, remains under-explored. In this study, we tackle this challenge by adapting post-hoc OOD detection methods to the MIL setting while introducing a novel benchmark specifically designed to assess OOD detection performance in weakly supervised scenarios. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.05528","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/2309.05528/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":"2309.05528","created_at":"2026-07-05T07:10:49.799551+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.05528v2","created_at":"2026-07-05T07:10:49.799551+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.05528","created_at":"2026-07-05T07:10:49.799551+00:00"},{"alias_kind":"pith_short_12","alias_value":"EBK3T2JZ6XMY","created_at":"2026-07-05T07:10:49.799551+00:00"},{"alias_kind":"pith_short_16","alias_value":"EBK3T2JZ6XMYGWO4","created_at":"2026-07-05T07:10:49.799551+00:00"},{"alias_kind":"pith_short_8","alias_value":"EBK3T2JZ","created_at":"2026-07-05T07:10:49.799551+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/EBK3T2JZ6XMYGWO4A2DJ7PG5LC","json":"https://pith.science/pith/EBK3T2JZ6XMYGWO4A2DJ7PG5LC.json","graph_json":"https://pith.science/api/pith-number/EBK3T2JZ6XMYGWO4A2DJ7PG5LC/graph.json","events_json":"https://pith.science/api/pith-number/EBK3T2JZ6XMYGWO4A2DJ7PG5LC/events.json","paper":"https://pith.science/paper/EBK3T2JZ"},"agent_actions":{"view_html":"https://pith.science/pith/EBK3T2JZ6XMYGWO4A2DJ7PG5LC","download_json":"https://pith.science/pith/EBK3T2JZ6XMYGWO4A2DJ7PG5LC.json","view_paper":"https://pith.science/paper/EBK3T2JZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.05528&json=true","fetch_graph":"https://pith.science/api/pith-number/EBK3T2JZ6XMYGWO4A2DJ7PG5LC/graph.json","fetch_events":"https://pith.science/api/pith-number/EBK3T2JZ6XMYGWO4A2DJ7PG5LC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EBK3T2JZ6XMYGWO4A2DJ7PG5LC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EBK3T2JZ6XMYGWO4A2DJ7PG5LC/action/storage_attestation","attest_author":"https://pith.science/pith/EBK3T2JZ6XMYGWO4A2DJ7PG5LC/action/author_attestation","sign_citation":"https://pith.science/pith/EBK3T2JZ6XMYGWO4A2DJ7PG5LC/action/citation_signature","submit_replication":"https://pith.science/pith/EBK3T2JZ6XMYGWO4A2DJ7PG5LC/action/replication_record"}},"created_at":"2026-07-05T07:10:49.799551+00:00","updated_at":"2026-07-05T07:10:49.799551+00:00"}