{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VHV3YR7K6FQ4FT2KNNEP5C3GD2","short_pith_number":"pith:VHV3YR7K","schema_version":"1.0","canonical_sha256":"a9ebbc47eaf161c2cf4a6b48fe8b661e81f59f043c030a871e72ce55f170c211","source":{"kind":"arxiv","id":"2207.07517","version":2},"attestation_state":"computed","paper":{"title":"On the Usefulness of Deep Ensemble Diversity for Out-of-Distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Christos-Savvas Bouganis, Guoxuan Xia","submitted_at":"2022-07-15T15:02:38Z","abstract_excerpt":"The ability to detect Out-of-Distribution (OOD) data is important in safety-critical applications of deep learning. The aim is to separate In-Distribution (ID) data drawn from the training distribution from OOD data using a measure of uncertainty extracted from a deep neural network. Deep Ensembles are a well-established method of improving the quality of uncertainty estimates produced by deep neural networks, and have been shown to have superior OOD detection performance compared to single models. An existing intuition in the literature is that the diversity of Deep Ensemble predictions indic"},"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":"2207.07517","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-15T15:02:38Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"2fac11805c4695b7d3a4efedde837db4c7bf5707199da66cc6dad0d005e796be","abstract_canon_sha256":"7e517963740ed5e66bbb30d93c13ef503740e5b00456a872a33a98239114a341"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:59:28.187811Z","signature_b64":"MDbKyCA/Xp+2VQ/xDdxfV2HGjxNn3/ywSSxCpAwMmUrj1UMLyP3BoLPDDEb3RI5Z6O51Zb3qAE5VZuIzmzQNDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9ebbc47eaf161c2cf4a6b48fe8b661e81f59f043c030a871e72ce55f170c211","last_reissued_at":"2026-07-05T04:59:28.187390Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:59:28.187390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Usefulness of Deep Ensemble Diversity for Out-of-Distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Christos-Savvas Bouganis, Guoxuan Xia","submitted_at":"2022-07-15T15:02:38Z","abstract_excerpt":"The ability to detect Out-of-Distribution (OOD) data is important in safety-critical applications of deep learning. The aim is to separate In-Distribution (ID) data drawn from the training distribution from OOD data using a measure of uncertainty extracted from a deep neural network. Deep Ensembles are a well-established method of improving the quality of uncertainty estimates produced by deep neural networks, and have been shown to have superior OOD detection performance compared to single models. An existing intuition in the literature is that the diversity of Deep Ensemble predictions indic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.07517","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/2207.07517/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":"2207.07517","created_at":"2026-07-05T04:59:28.187449+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.07517v2","created_at":"2026-07-05T04:59:28.187449+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.07517","created_at":"2026-07-05T04:59:28.187449+00:00"},{"alias_kind":"pith_short_12","alias_value":"VHV3YR7K6FQ4","created_at":"2026-07-05T04:59:28.187449+00:00"},{"alias_kind":"pith_short_16","alias_value":"VHV3YR7K6FQ4FT2K","created_at":"2026-07-05T04:59:28.187449+00:00"},{"alias_kind":"pith_short_8","alias_value":"VHV3YR7K","created_at":"2026-07-05T04:59:28.187449+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08574","citing_title":"Post-hoc Selective Classification for Reliable Synthetic Image Detection","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VHV3YR7K6FQ4FT2KNNEP5C3GD2","json":"https://pith.science/pith/VHV3YR7K6FQ4FT2KNNEP5C3GD2.json","graph_json":"https://pith.science/api/pith-number/VHV3YR7K6FQ4FT2KNNEP5C3GD2/graph.json","events_json":"https://pith.science/api/pith-number/VHV3YR7K6FQ4FT2KNNEP5C3GD2/events.json","paper":"https://pith.science/paper/VHV3YR7K"},"agent_actions":{"view_html":"https://pith.science/pith/VHV3YR7K6FQ4FT2KNNEP5C3GD2","download_json":"https://pith.science/pith/VHV3YR7K6FQ4FT2KNNEP5C3GD2.json","view_paper":"https://pith.science/paper/VHV3YR7K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.07517&json=true","fetch_graph":"https://pith.science/api/pith-number/VHV3YR7K6FQ4FT2KNNEP5C3GD2/graph.json","fetch_events":"https://pith.science/api/pith-number/VHV3YR7K6FQ4FT2KNNEP5C3GD2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VHV3YR7K6FQ4FT2KNNEP5C3GD2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VHV3YR7K6FQ4FT2KNNEP5C3GD2/action/storage_attestation","attest_author":"https://pith.science/pith/VHV3YR7K6FQ4FT2KNNEP5C3GD2/action/author_attestation","sign_citation":"https://pith.science/pith/VHV3YR7K6FQ4FT2KNNEP5C3GD2/action/citation_signature","submit_replication":"https://pith.science/pith/VHV3YR7K6FQ4FT2KNNEP5C3GD2/action/replication_record"}},"created_at":"2026-07-05T04:59:28.187449+00:00","updated_at":"2026-07-05T04:59:28.187449+00:00"}