{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:AOZF3CD7VPIH4VFNHQAIVJM325","short_pith_number":"pith:AOZF3CD7","schema_version":"1.0","canonical_sha256":"03b25d887fabd07e54ad3c008aa59bd74ce67582a009a23ddbe4bd2199995704","source":{"kind":"arxiv","id":"1912.12510","version":2},"attestation_state":"computed","paper":{"title":"Detecting Out-of-Distribution Examples with In-distribution Examples and Gram Matrices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chandramouli Shama Sastry, Sageev Oore","submitted_at":"2019-12-28T19:44:03Z","abstract_excerpt":"When presented with Out-of-Distribution (OOD) examples, deep neural networks yield confident, incorrect predictions. Detecting OOD examples is challenging, and the potential risks are high. In this paper, we propose to detect OOD examples by identifying inconsistencies between activity patterns and class predicted. We find that characterizing activity patterns by Gram matrices and identifying anomalies in gram matrix values can yield high OOD detection rates. We identify anomalies in the gram matrices by simply comparing each value with its respective range observed over the training data. Unl"},"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":"1912.12510","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-28T19:44:03Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"f912f32e5d5758b1cbc273d8f9c12118e3041536ce8d61dd0b3936b59ddfc586","abstract_canon_sha256":"d38442c2616b8496b2ba29b3f3cc2191757f8f089bb43187ae7be69aee8434a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:32:31.527540Z","signature_b64":"4EO/X2V/gxBj+7CceP4adOGFbSp4u4cGH5UlBMQaHB4ubgmBUe7kwhTClnNX8HukwaKdVNGqHb24vdT0ojkOCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03b25d887fabd07e54ad3c008aa59bd74ce67582a009a23ddbe4bd2199995704","last_reissued_at":"2026-07-05T00:32:31.527113Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:32:31.527113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Detecting Out-of-Distribution Examples with In-distribution Examples and Gram Matrices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chandramouli Shama Sastry, Sageev Oore","submitted_at":"2019-12-28T19:44:03Z","abstract_excerpt":"When presented with Out-of-Distribution (OOD) examples, deep neural networks yield confident, incorrect predictions. Detecting OOD examples is challenging, and the potential risks are high. In this paper, we propose to detect OOD examples by identifying inconsistencies between activity patterns and class predicted. We find that characterizing activity patterns by Gram matrices and identifying anomalies in gram matrix values can yield high OOD detection rates. We identify anomalies in the gram matrices by simply comparing each value with its respective range observed over the training data. Unl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.12510","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/1912.12510/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":"1912.12510","created_at":"2026-07-05T00:32:31.527167+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.12510v2","created_at":"2026-07-05T00:32:31.527167+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.12510","created_at":"2026-07-05T00:32:31.527167+00:00"},{"alias_kind":"pith_short_12","alias_value":"AOZF3CD7VPIH","created_at":"2026-07-05T00:32:31.527167+00:00"},{"alias_kind":"pith_short_16","alias_value":"AOZF3CD7VPIH4VFN","created_at":"2026-07-05T00:32:31.527167+00:00"},{"alias_kind":"pith_short_8","alias_value":"AOZF3CD7","created_at":"2026-07-05T00:32:31.527167+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/AOZF3CD7VPIH4VFNHQAIVJM325","json":"https://pith.science/pith/AOZF3CD7VPIH4VFNHQAIVJM325.json","graph_json":"https://pith.science/api/pith-number/AOZF3CD7VPIH4VFNHQAIVJM325/graph.json","events_json":"https://pith.science/api/pith-number/AOZF3CD7VPIH4VFNHQAIVJM325/events.json","paper":"https://pith.science/paper/AOZF3CD7"},"agent_actions":{"view_html":"https://pith.science/pith/AOZF3CD7VPIH4VFNHQAIVJM325","download_json":"https://pith.science/pith/AOZF3CD7VPIH4VFNHQAIVJM325.json","view_paper":"https://pith.science/paper/AOZF3CD7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.12510&json=true","fetch_graph":"https://pith.science/api/pith-number/AOZF3CD7VPIH4VFNHQAIVJM325/graph.json","fetch_events":"https://pith.science/api/pith-number/AOZF3CD7VPIH4VFNHQAIVJM325/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AOZF3CD7VPIH4VFNHQAIVJM325/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AOZF3CD7VPIH4VFNHQAIVJM325/action/storage_attestation","attest_author":"https://pith.science/pith/AOZF3CD7VPIH4VFNHQAIVJM325/action/author_attestation","sign_citation":"https://pith.science/pith/AOZF3CD7VPIH4VFNHQAIVJM325/action/citation_signature","submit_replication":"https://pith.science/pith/AOZF3CD7VPIH4VFNHQAIVJM325/action/replication_record"}},"created_at":"2026-07-05T00:32:31.527167+00:00","updated_at":"2026-07-05T00:32:31.527167+00:00"}