{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:P45B75ZK5TG65HJYETDB5WOPHZ","short_pith_number":"pith:P45B75ZK","schema_version":"1.0","canonical_sha256":"7f3a1ff72aeccdee9d3824c61ed9cf3e553b57907e0349bdc13d50a96e664255","source":{"kind":"arxiv","id":"2006.10712","version":4},"attestation_state":"computed","paper":{"title":"Task-agnostic Out-of-Distribution Detection Using Kernel Density Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ender Konukoglu, Ertunc Erdil, Krishna Chaitanya, Neerav Karani","submitted_at":"2020-06-18T17:46:06Z","abstract_excerpt":"In the recent years, researchers proposed a number of successful methods to perform out-of-distribution (OOD) detection in deep neural networks (DNNs). So far the scope of the highly accurate methods has been limited to image level classification tasks. However, attempts for generally applicable methods beyond classification did not attain similar performance. In this paper, we address this limitation by proposing a simple yet effective task-agnostic OOD detection method. We estimate the probability density functions (pdfs) of intermediate features of a pre-trained DNN by performing kernel den"},"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":"2006.10712","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-18T17:46:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"805d218c8547d90a8626c3b5f07e4334847b8164ff59e9a4b9d8cf5cd987aacf","abstract_canon_sha256":"dab2debbf2dce66a98d2020a7074883a7ccaf493c1e3abfcf99299a87dfe6194"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:27:54.404252Z","signature_b64":"XZl0Z3iZLYpcXDp7i4LsyTbpdJQwl7OlAGjwmUobpr0IsEbLF/BhYgGP/qSBTSSvtxSJAZsggKax7Os4gnhlCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f3a1ff72aeccdee9d3824c61ed9cf3e553b57907e0349bdc13d50a96e664255","last_reissued_at":"2026-07-05T02:27:54.403875Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:27:54.403875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Task-agnostic Out-of-Distribution Detection Using Kernel Density Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ender Konukoglu, Ertunc Erdil, Krishna Chaitanya, Neerav Karani","submitted_at":"2020-06-18T17:46:06Z","abstract_excerpt":"In the recent years, researchers proposed a number of successful methods to perform out-of-distribution (OOD) detection in deep neural networks (DNNs). So far the scope of the highly accurate methods has been limited to image level classification tasks. However, attempts for generally applicable methods beyond classification did not attain similar performance. In this paper, we address this limitation by proposing a simple yet effective task-agnostic OOD detection method. We estimate the probability density functions (pdfs) of intermediate features of a pre-trained DNN by performing kernel den"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.10712","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/2006.10712/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":"2006.10712","created_at":"2026-07-05T02:27:54.403944+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.10712v4","created_at":"2026-07-05T02:27:54.403944+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.10712","created_at":"2026-07-05T02:27:54.403944+00:00"},{"alias_kind":"pith_short_12","alias_value":"P45B75ZK5TG6","created_at":"2026-07-05T02:27:54.403944+00:00"},{"alias_kind":"pith_short_16","alias_value":"P45B75ZK5TG65HJY","created_at":"2026-07-05T02:27:54.403944+00:00"},{"alias_kind":"pith_short_8","alias_value":"P45B75ZK","created_at":"2026-07-05T02:27:54.403944+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/P45B75ZK5TG65HJYETDB5WOPHZ","json":"https://pith.science/pith/P45B75ZK5TG65HJYETDB5WOPHZ.json","graph_json":"https://pith.science/api/pith-number/P45B75ZK5TG65HJYETDB5WOPHZ/graph.json","events_json":"https://pith.science/api/pith-number/P45B75ZK5TG65HJYETDB5WOPHZ/events.json","paper":"https://pith.science/paper/P45B75ZK"},"agent_actions":{"view_html":"https://pith.science/pith/P45B75ZK5TG65HJYETDB5WOPHZ","download_json":"https://pith.science/pith/P45B75ZK5TG65HJYETDB5WOPHZ.json","view_paper":"https://pith.science/paper/P45B75ZK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.10712&json=true","fetch_graph":"https://pith.science/api/pith-number/P45B75ZK5TG65HJYETDB5WOPHZ/graph.json","fetch_events":"https://pith.science/api/pith-number/P45B75ZK5TG65HJYETDB5WOPHZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P45B75ZK5TG65HJYETDB5WOPHZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P45B75ZK5TG65HJYETDB5WOPHZ/action/storage_attestation","attest_author":"https://pith.science/pith/P45B75ZK5TG65HJYETDB5WOPHZ/action/author_attestation","sign_citation":"https://pith.science/pith/P45B75ZK5TG65HJYETDB5WOPHZ/action/citation_signature","submit_replication":"https://pith.science/pith/P45B75ZK5TG65HJYETDB5WOPHZ/action/replication_record"}},"created_at":"2026-07-05T02:27:54.403944+00:00","updated_at":"2026-07-05T02:27:54.403944+00:00"}