{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:OUSIUEBMPNERQDPX4YFLO5IRHC","short_pith_number":"pith:OUSIUEBM","canonical_record":{"source":{"id":"2102.12967","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-25T16:14:47Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"11816d9e123508370d74e3d98347d766f5768c282e9043ea781ffe1669958bf2","abstract_canon_sha256":"1e3effdb3d253dc97fdd7e6361e0456dd5f2d0da19f7a43a241c1cf3e4ac6a54"},"schema_version":"1.0"},"canonical_sha256":"75248a102c7b49180df7e60ab775113896cbb73eb5f44dc3c44298475c81827b","source":{"kind":"arxiv","id":"2102.12967","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.12967","created_at":"2026-07-05T04:10:21Z"},{"alias_kind":"arxiv_version","alias_value":"2102.12967v3","created_at":"2026-07-05T04:10:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.12967","created_at":"2026-07-05T04:10:21Z"},{"alias_kind":"pith_short_12","alias_value":"OUSIUEBMPNER","created_at":"2026-07-05T04:10:21Z"},{"alias_kind":"pith_short_16","alias_value":"OUSIUEBMPNERQDPX","created_at":"2026-07-05T04:10:21Z"},{"alias_kind":"pith_short_8","alias_value":"OUSIUEBM","created_at":"2026-07-05T04:10:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:OUSIUEBMPNERQDPX4YFLO5IRHC","target":"record","payload":{"canonical_record":{"source":{"id":"2102.12967","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-25T16:14:47Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"11816d9e123508370d74e3d98347d766f5768c282e9043ea781ffe1669958bf2","abstract_canon_sha256":"1e3effdb3d253dc97fdd7e6361e0456dd5f2d0da19f7a43a241c1cf3e4ac6a54"},"schema_version":"1.0"},"canonical_sha256":"75248a102c7b49180df7e60ab775113896cbb73eb5f44dc3c44298475c81827b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:10:21.792793Z","signature_b64":"RJkn/OsHRa5D+wHd44A2xyPdDVvIChi4ZVqIdDJL27KExfJPD3lbRCUY/Rp4nJL609nlAVK0mEa0JgZPGGKmCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75248a102c7b49180df7e60ab775113896cbb73eb5f44dc3c44298475c81827b","last_reissued_at":"2026-07-05T04:10:21.792292Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:10:21.792292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.12967","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:10:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rs8GvKAsClKU1JDGJsOjFSCmfRDq0q3ySH84FTwSrwywUyt7zhBCLAGdbSISyIJJtxnYEbpESRio0wNdrPPLAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T23:03:13.954796Z"},"content_sha256":"100c311142897a7986115b63550dcf19a8f0f30d5e28621a365fa06572bae84d","schema_version":"1.0","event_id":"sha256:100c311142897a7986115b63550dcf19a8f0f30d5e28621a365fa06572bae84d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:OUSIUEBMPNERQDPX4YFLO5IRHC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A statistical framework for efficient out of distribution detection in deep neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Soudry, Matan Haroush, Ruth Heller, Tzviel Frostig","submitted_at":"2021-02-25T16:14:47Z","abstract_excerpt":"Background. Commonly, Deep Neural Networks (DNNs) generalize well on samples drawn from a distribution similar to that of the training set. However, DNNs' predictions are brittle and unreliable when the test samples are drawn from a dissimilar distribution. This is a major concern for deployment in real-world applications, where such behavior may come at a considerable cost, such as industrial production lines, autonomous vehicles, or healthcare applications. Contributions. We frame Out Of Distribution (OOD) detection in DNNs as a statistical hypothesis testing problem. Tests generated within "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.12967","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/2102.12967/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:10:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"grGnA1yUUoW9wfSsE8oHAyKhvDf8OOTNTMnFSNoKaddnIObWmvZRzpVrl0DzJT2/p2t8UVPhtIts6WrwvgqVBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T23:03:13.955301Z"},"content_sha256":"b2797cfa4b021921f51f499ea07408d368321169e2626f5b770a3e89d30b069b","schema_version":"1.0","event_id":"sha256:b2797cfa4b021921f51f499ea07408d368321169e2626f5b770a3e89d30b069b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OUSIUEBMPNERQDPX4YFLO5IRHC/bundle.json","state_url":"https://pith.science/pith/OUSIUEBMPNERQDPX4YFLO5IRHC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OUSIUEBMPNERQDPX4YFLO5IRHC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T23:03:13Z","links":{"resolver":"https://pith.science/pith/OUSIUEBMPNERQDPX4YFLO5IRHC","bundle":"https://pith.science/pith/OUSIUEBMPNERQDPX4YFLO5IRHC/bundle.json","state":"https://pith.science/pith/OUSIUEBMPNERQDPX4YFLO5IRHC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OUSIUEBMPNERQDPX4YFLO5IRHC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:OUSIUEBMPNERQDPX4YFLO5IRHC","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1e3effdb3d253dc97fdd7e6361e0456dd5f2d0da19f7a43a241c1cf3e4ac6a54","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-25T16:14:47Z","title_canon_sha256":"11816d9e123508370d74e3d98347d766f5768c282e9043ea781ffe1669958bf2"},"schema_version":"1.0","source":{"id":"2102.12967","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.12967","created_at":"2026-07-05T04:10:21Z"},{"alias_kind":"arxiv_version","alias_value":"2102.12967v3","created_at":"2026-07-05T04:10:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.12967","created_at":"2026-07-05T04:10:21Z"},{"alias_kind":"pith_short_12","alias_value":"OUSIUEBMPNER","created_at":"2026-07-05T04:10:21Z"},{"alias_kind":"pith_short_16","alias_value":"OUSIUEBMPNERQDPX","created_at":"2026-07-05T04:10:21Z"},{"alias_kind":"pith_short_8","alias_value":"OUSIUEBM","created_at":"2026-07-05T04:10:21Z"}],"graph_snapshots":[{"event_id":"sha256:b2797cfa4b021921f51f499ea07408d368321169e2626f5b770a3e89d30b069b","target":"graph","created_at":"2026-07-05T04:10:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2102.12967/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Background. Commonly, Deep Neural Networks (DNNs) generalize well on samples drawn from a distribution similar to that of the training set. However, DNNs' predictions are brittle and unreliable when the test samples are drawn from a dissimilar distribution. This is a major concern for deployment in real-world applications, where such behavior may come at a considerable cost, such as industrial production lines, autonomous vehicles, or healthcare applications. Contributions. We frame Out Of Distribution (OOD) detection in DNNs as a statistical hypothesis testing problem. Tests generated within ","authors_text":"Daniel Soudry, Matan Haroush, Ruth Heller, Tzviel Frostig","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-25T16:14:47Z","title":"A statistical framework for efficient out of distribution detection in deep neural networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.12967","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:100c311142897a7986115b63550dcf19a8f0f30d5e28621a365fa06572bae84d","target":"record","created_at":"2026-07-05T04:10:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1e3effdb3d253dc97fdd7e6361e0456dd5f2d0da19f7a43a241c1cf3e4ac6a54","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-25T16:14:47Z","title_canon_sha256":"11816d9e123508370d74e3d98347d766f5768c282e9043ea781ffe1669958bf2"},"schema_version":"1.0","source":{"id":"2102.12967","kind":"arxiv","version":3}},"canonical_sha256":"75248a102c7b49180df7e60ab775113896cbb73eb5f44dc3c44298475c81827b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"75248a102c7b49180df7e60ab775113896cbb73eb5f44dc3c44298475c81827b","first_computed_at":"2026-07-05T04:10:21.792292Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:10:21.792292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RJkn/OsHRa5D+wHd44A2xyPdDVvIChi4ZVqIdDJL27KExfJPD3lbRCUY/Rp4nJL609nlAVK0mEa0JgZPGGKmCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:10:21.792793Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.12967","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:100c311142897a7986115b63550dcf19a8f0f30d5e28621a365fa06572bae84d","sha256:b2797cfa4b021921f51f499ea07408d368321169e2626f5b770a3e89d30b069b"],"state_sha256":"320c3057257530b13cfa0c98789923da6d1466473d16e7ff5a784cd58b0c28dd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mki8g/62w2pRQiJvl9fawxVX0iEdtkXqSGYxrhpkhTUH7y6VK0tl6QDy4OMcJyCCgt81dtwRrxSELti1UEyqBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T23:03:13.960129Z","bundle_sha256":"8d4c28df4ddd908ec42c9452d6da259bd62feb0a6635bd5cdb31940ee98c5399"}}