{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:KWQBFBKHHKBVI37JLHC27Z5FTI","short_pith_number":"pith:KWQBFBKH","schema_version":"1.0","canonical_sha256":"55a01285473a83546fe959c5afe7a59a034478bd8d2e605e4711298a3ce8d118","source":{"kind":"arxiv","id":"2010.03759","version":4},"attestation_state":"computed","paper":{"title":"Energy-based Out-of-distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"John D. Owens, Weitang Liu, Xiaoyun Wang, Yixuan Li","submitted_at":"2020-10-08T04:42:17Z","abstract_excerpt":"Determining whether inputs are out-of-distribution (OOD) is an essential building block for safely deploying machine learning models in the open world. However, previous methods relying on the softmax confidence score suffer from overconfident posterior distributions for OOD data. We propose a unified framework for OOD detection that uses an energy score. We show that energy scores better distinguish in- and out-of-distribution samples than the traditional approach using the softmax scores. Unlike softmax confidence scores, energy scores are theoretically aligned with the probability density o"},"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":"2010.03759","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-08T04:42:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d7e53f57a23c80de65a408b0893d2af01cf3c16a1bec5f1e91d13814ed3f8036","abstract_canon_sha256":"886807436f7f2977d85acabf12201cd85ae4dc9a2c439aaef6787fdaa4494259"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:34:42.492608Z","signature_b64":"D06TxJfB4UgXYDf4PPLLtgoV4DkZrJ/oTn9Nf0Isu1cNhBZkgis8nzZee4mtUu5NXNUq9Audn59yjqvyEVrXDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55a01285473a83546fe959c5afe7a59a034478bd8d2e605e4711298a3ce8d118","last_reissued_at":"2026-07-05T02:34:42.492109Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:34:42.492109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Energy-based Out-of-distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"John D. Owens, Weitang Liu, Xiaoyun Wang, Yixuan Li","submitted_at":"2020-10-08T04:42:17Z","abstract_excerpt":"Determining whether inputs are out-of-distribution (OOD) is an essential building block for safely deploying machine learning models in the open world. However, previous methods relying on the softmax confidence score suffer from overconfident posterior distributions for OOD data. We propose a unified framework for OOD detection that uses an energy score. We show that energy scores better distinguish in- and out-of-distribution samples than the traditional approach using the softmax scores. Unlike softmax confidence scores, energy scores are theoretically aligned with the probability density o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.03759","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/2010.03759/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":"2010.03759","created_at":"2026-07-05T02:34:42.492165+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.03759v4","created_at":"2026-07-05T02:34:42.492165+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.03759","created_at":"2026-07-05T02:34:42.492165+00:00"},{"alias_kind":"pith_short_12","alias_value":"KWQBFBKHHKBV","created_at":"2026-07-05T02:34:42.492165+00:00"},{"alias_kind":"pith_short_16","alias_value":"KWQBFBKHHKBVI37J","created_at":"2026-07-05T02:34:42.492165+00:00"},{"alias_kind":"pith_short_8","alias_value":"KWQBFBKH","created_at":"2026-07-05T02:34:42.492165+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12718","citing_title":"Out-of-Distribution (OOD) Detectors for Open-Set RF Fingerprinting","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KWQBFBKHHKBVI37JLHC27Z5FTI","json":"https://pith.science/pith/KWQBFBKHHKBVI37JLHC27Z5FTI.json","graph_json":"https://pith.science/api/pith-number/KWQBFBKHHKBVI37JLHC27Z5FTI/graph.json","events_json":"https://pith.science/api/pith-number/KWQBFBKHHKBVI37JLHC27Z5FTI/events.json","paper":"https://pith.science/paper/KWQBFBKH"},"agent_actions":{"view_html":"https://pith.science/pith/KWQBFBKHHKBVI37JLHC27Z5FTI","download_json":"https://pith.science/pith/KWQBFBKHHKBVI37JLHC27Z5FTI.json","view_paper":"https://pith.science/paper/KWQBFBKH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.03759&json=true","fetch_graph":"https://pith.science/api/pith-number/KWQBFBKHHKBVI37JLHC27Z5FTI/graph.json","fetch_events":"https://pith.science/api/pith-number/KWQBFBKHHKBVI37JLHC27Z5FTI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KWQBFBKHHKBVI37JLHC27Z5FTI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KWQBFBKHHKBVI37JLHC27Z5FTI/action/storage_attestation","attest_author":"https://pith.science/pith/KWQBFBKHHKBVI37JLHC27Z5FTI/action/author_attestation","sign_citation":"https://pith.science/pith/KWQBFBKHHKBVI37JLHC27Z5FTI/action/citation_signature","submit_replication":"https://pith.science/pith/KWQBFBKHHKBVI37JLHC27Z5FTI/action/replication_record"}},"created_at":"2026-07-05T02:34:42.492165+00:00","updated_at":"2026-07-05T02:34:42.492165+00:00"}