{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ONWFPYM5OSJ4AAX2ULPYUUFQAA","short_pith_number":"pith:ONWFPYM5","schema_version":"1.0","canonical_sha256":"736c57e19d7493c002faa2df8a50b00028cfe3fb72a70abcc4cd8361293fd25f","source":{"kind":"arxiv","id":"2403.10403","version":1},"attestation_state":"computed","paper":{"title":"Energy Correction Model in the Feature Space for Out-of-Distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Cl\\'ement Rambour, Marc Lafon, Nicolas Thome","submitted_at":"2024-03-15T15:37:04Z","abstract_excerpt":"In this work, we study the out-of-distribution (OOD) detection problem through the use of the feature space of a pre-trained deep classifier. We show that learning the density of in-distribution (ID) features with an energy-based models (EBM) leads to competitive detection results. However, we found that the non-mixing of MCMC sampling during the EBM's training undermines its detection performance. To overcome this an energy-based correction of a mixture of class-conditional Gaussian distributions. We obtains favorable results when compared to a strong baseline like the KNN detector on the CIF"},"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":"2403.10403","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-15T15:37:04Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1a9e245bfe0f4440fb473f437f9f8f6c3227695e09ff267b17bb38e6d7d76d61","abstract_canon_sha256":"1396b895ad23dcc44b50da53afbf0c4cab87641e76ac79e748f08be3234d6b89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:34.937362Z","signature_b64":"6YXklwgH04+PpeuQ/Lvtk+31ZRUdE5UiAB6f0GdL/bapflYjffh+18Br9NpQBJ3J4PuGwbPq3RdoV2ZnNcWFDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"736c57e19d7493c002faa2df8a50b00028cfe3fb72a70abcc4cd8361293fd25f","last_reissued_at":"2026-07-05T07:56:34.936852Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:34.936852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Energy Correction Model in the Feature Space for Out-of-Distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Cl\\'ement Rambour, Marc Lafon, Nicolas Thome","submitted_at":"2024-03-15T15:37:04Z","abstract_excerpt":"In this work, we study the out-of-distribution (OOD) detection problem through the use of the feature space of a pre-trained deep classifier. We show that learning the density of in-distribution (ID) features with an energy-based models (EBM) leads to competitive detection results. However, we found that the non-mixing of MCMC sampling during the EBM's training undermines its detection performance. To overcome this an energy-based correction of a mixture of class-conditional Gaussian distributions. We obtains favorable results when compared to a strong baseline like the KNN detector on the CIF"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10403","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/2403.10403/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":"2403.10403","created_at":"2026-07-05T07:56:34.936911+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.10403v1","created_at":"2026-07-05T07:56:34.936911+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10403","created_at":"2026-07-05T07:56:34.936911+00:00"},{"alias_kind":"pith_short_12","alias_value":"ONWFPYM5OSJ4","created_at":"2026-07-05T07:56:34.936911+00:00"},{"alias_kind":"pith_short_16","alias_value":"ONWFPYM5OSJ4AAX2","created_at":"2026-07-05T07:56:34.936911+00:00"},{"alias_kind":"pith_short_8","alias_value":"ONWFPYM5","created_at":"2026-07-05T07:56:34.936911+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/ONWFPYM5OSJ4AAX2ULPYUUFQAA","json":"https://pith.science/pith/ONWFPYM5OSJ4AAX2ULPYUUFQAA.json","graph_json":"https://pith.science/api/pith-number/ONWFPYM5OSJ4AAX2ULPYUUFQAA/graph.json","events_json":"https://pith.science/api/pith-number/ONWFPYM5OSJ4AAX2ULPYUUFQAA/events.json","paper":"https://pith.science/paper/ONWFPYM5"},"agent_actions":{"view_html":"https://pith.science/pith/ONWFPYM5OSJ4AAX2ULPYUUFQAA","download_json":"https://pith.science/pith/ONWFPYM5OSJ4AAX2ULPYUUFQAA.json","view_paper":"https://pith.science/paper/ONWFPYM5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.10403&json=true","fetch_graph":"https://pith.science/api/pith-number/ONWFPYM5OSJ4AAX2ULPYUUFQAA/graph.json","fetch_events":"https://pith.science/api/pith-number/ONWFPYM5OSJ4AAX2ULPYUUFQAA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ONWFPYM5OSJ4AAX2ULPYUUFQAA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ONWFPYM5OSJ4AAX2ULPYUUFQAA/action/storage_attestation","attest_author":"https://pith.science/pith/ONWFPYM5OSJ4AAX2ULPYUUFQAA/action/author_attestation","sign_citation":"https://pith.science/pith/ONWFPYM5OSJ4AAX2ULPYUUFQAA/action/citation_signature","submit_replication":"https://pith.science/pith/ONWFPYM5OSJ4AAX2ULPYUUFQAA/action/replication_record"}},"created_at":"2026-07-05T07:56:34.936911+00:00","updated_at":"2026-07-05T07:56:34.936911+00:00"}