{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RE2U5VN6VYLIWHDOQAKO64RHSU","short_pith_number":"pith:RE2U5VN6","schema_version":"1.0","canonical_sha256":"89354ed5beae168b1c6e8014ef7227952ddd0ce6e6dfdce2f869d8ba07f1bba1","source":{"kind":"arxiv","id":"2305.16966","version":3},"attestation_state":"computed","paper":{"title":"Hybrid Energy Based Model in the Feature Space for Out-of-Distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cl\\'ement Rambour, Elias Ramzi, Marc Lafon, Nicolas Thome","submitted_at":"2023-05-26T14:21:39Z","abstract_excerpt":"Out-of-distribution (OOD) detection is a critical requirement for the deployment of deep neural networks. This paper introduces the HEAT model, a new post-hoc OOD detection method estimating the density of in-distribution (ID) samples using hybrid energy-based models (EBM) in the feature space of a pre-trained backbone. HEAT complements prior density estimators of the ID density, e.g. parametric models like the Gaussian Mixture Model (GMM), to provide an accurate yet robust density estimation. A second contribution is to leverage the EBM framework to provide a unified density estimation and to"},"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":"2305.16966","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-26T14:21:39Z","cross_cats_sorted":[],"title_canon_sha256":"2fee122842d7993d050cb803d9458bf9da3279bbb8cdef5a763329275397819f","abstract_canon_sha256":"5f71fa57add0fecf7bb66a30f9259f29ef785ed0890fcf6947fe4e6cbdad5f2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:42:06.061204Z","signature_b64":"eHS2tVtWly+MJM6Q/XhTY5ATvqYnlka8wzYHf01e3whlJkB5HvtqcBjWG+OhN3x9roWKPMWKPhYwk0yT8jF9Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89354ed5beae168b1c6e8014ef7227952ddd0ce6e6dfdce2f869d8ba07f1bba1","last_reissued_at":"2026-07-05T06:42:06.060718Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:42:06.060718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hybrid Energy Based Model in the Feature Space for Out-of-Distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cl\\'ement Rambour, Elias Ramzi, Marc Lafon, Nicolas Thome","submitted_at":"2023-05-26T14:21:39Z","abstract_excerpt":"Out-of-distribution (OOD) detection is a critical requirement for the deployment of deep neural networks. This paper introduces the HEAT model, a new post-hoc OOD detection method estimating the density of in-distribution (ID) samples using hybrid energy-based models (EBM) in the feature space of a pre-trained backbone. HEAT complements prior density estimators of the ID density, e.g. parametric models like the Gaussian Mixture Model (GMM), to provide an accurate yet robust density estimation. A second contribution is to leverage the EBM framework to provide a unified density estimation and to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16966","kind":"arxiv","version":3},"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/2305.16966/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":"2305.16966","created_at":"2026-07-05T06:42:06.060776+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.16966v3","created_at":"2026-07-05T06:42:06.060776+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16966","created_at":"2026-07-05T06:42:06.060776+00:00"},{"alias_kind":"pith_short_12","alias_value":"RE2U5VN6VYLI","created_at":"2026-07-05T06:42:06.060776+00:00"},{"alias_kind":"pith_short_16","alias_value":"RE2U5VN6VYLIWHDO","created_at":"2026-07-05T06:42:06.060776+00:00"},{"alias_kind":"pith_short_8","alias_value":"RE2U5VN6","created_at":"2026-07-05T06:42:06.060776+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.01111","citing_title":"Incorporating Inductive Biases to Energy-based Generative Models","ref_index":2021,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RE2U5VN6VYLIWHDOQAKO64RHSU","json":"https://pith.science/pith/RE2U5VN6VYLIWHDOQAKO64RHSU.json","graph_json":"https://pith.science/api/pith-number/RE2U5VN6VYLIWHDOQAKO64RHSU/graph.json","events_json":"https://pith.science/api/pith-number/RE2U5VN6VYLIWHDOQAKO64RHSU/events.json","paper":"https://pith.science/paper/RE2U5VN6"},"agent_actions":{"view_html":"https://pith.science/pith/RE2U5VN6VYLIWHDOQAKO64RHSU","download_json":"https://pith.science/pith/RE2U5VN6VYLIWHDOQAKO64RHSU.json","view_paper":"https://pith.science/paper/RE2U5VN6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.16966&json=true","fetch_graph":"https://pith.science/api/pith-number/RE2U5VN6VYLIWHDOQAKO64RHSU/graph.json","fetch_events":"https://pith.science/api/pith-number/RE2U5VN6VYLIWHDOQAKO64RHSU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RE2U5VN6VYLIWHDOQAKO64RHSU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RE2U5VN6VYLIWHDOQAKO64RHSU/action/storage_attestation","attest_author":"https://pith.science/pith/RE2U5VN6VYLIWHDOQAKO64RHSU/action/author_attestation","sign_citation":"https://pith.science/pith/RE2U5VN6VYLIWHDOQAKO64RHSU/action/citation_signature","submit_replication":"https://pith.science/pith/RE2U5VN6VYLIWHDOQAKO64RHSU/action/replication_record"}},"created_at":"2026-07-05T06:42:06.060776+00:00","updated_at":"2026-07-05T06:42:06.060776+00:00"}