{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:ZNEFWMYSWZ4E4MRPJQC4ATK2EK","short_pith_number":"pith:ZNEFWMYS","canonical_record":{"source":{"id":"1909.11786","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-09-25T21:41:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"014e30bdfb10cf22d08281b18a3cfd393dc74b390867fb7122d68494b52aa480","abstract_canon_sha256":"dcaead1986f599be2853f68ae65170f5fa3ca9784c1a9749fbc44184c7990864"},"schema_version":"1.0"},"canonical_sha256":"cb485b3312b6784e322f4c05c04d5a22a7d0939088318a4851afd3c9a316dad2","source":{"kind":"arxiv","id":"1909.11786","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.11786","created_at":"2026-07-05T00:07:27Z"},{"alias_kind":"arxiv_version","alias_value":"1909.11786v1","created_at":"2026-07-05T00:07:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.11786","created_at":"2026-07-05T00:07:27Z"},{"alias_kind":"pith_short_12","alias_value":"ZNEFWMYSWZ4E","created_at":"2026-07-05T00:07:27Z"},{"alias_kind":"pith_short_16","alias_value":"ZNEFWMYSWZ4E4MRP","created_at":"2026-07-05T00:07:27Z"},{"alias_kind":"pith_short_8","alias_value":"ZNEFWMYS","created_at":"2026-07-05T00:07:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:ZNEFWMYSWZ4E4MRPJQC4ATK2EK","target":"record","payload":{"canonical_record":{"source":{"id":"1909.11786","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-09-25T21:41:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"014e30bdfb10cf22d08281b18a3cfd393dc74b390867fb7122d68494b52aa480","abstract_canon_sha256":"dcaead1986f599be2853f68ae65170f5fa3ca9784c1a9749fbc44184c7990864"},"schema_version":"1.0"},"canonical_sha256":"cb485b3312b6784e322f4c05c04d5a22a7d0939088318a4851afd3c9a316dad2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:07:27.905977Z","signature_b64":"jJtja0CcKDUSLlTF6qv/xhaE/P28IL86+GfHRjOSusN8cEXIThysLllYsvBToZ3wqn12KxElDAX2UU8dBjHABw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb485b3312b6784e322f4c05c04d5a22a7d0939088318a4851afd3c9a316dad2","last_reissued_at":"2026-07-05T00:07:27.905485Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:07:27.905485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.11786","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:07:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"84QjZywSIqp1KuFeE/oABdhqBbh3FIcWAw9KXc+nFb6IeWnFHQ9xHhmO9xN3GV4+kVafweDqDneCLPPD4Hd1Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T04:37:16.385379Z"},"content_sha256":"2d6c37fe257c877378af012bf9d919c3d50aca74e157dbde4f064db7d8b4e40b","schema_version":"1.0","event_id":"sha256:2d6c37fe257c877378af012bf9d919c3d50aca74e157dbde4f064db7d8b4e40b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:ZNEFWMYSWZ4E4MRPJQC4ATK2EK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Probabilistic Modeling of Deep Features for Out-of-Distribution and Adversarial Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Ibrahima Ndiour, Nilesh A. Ahuja, Omesh Tickoo, Trushant Kalyanpur","submitted_at":"2019-09-25T21:41:56Z","abstract_excerpt":"We present a principled approach for detecting out-of-distribution (OOD) and adversarial samples in deep neural networks. Our approach consists in modeling the outputs of the various layers (deep features) with parametric probability distributions once training is completed. At inference, the likelihoods of the deep features w.r.t the previously learnt distributions are calculated and used to derive uncertainty estimates that can discriminate in-distribution samples from OOD samples. We explore the use of two classes of multivariate distributions for modeling the deep features - Gaussian and G"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.11786","kind":"arxiv","version":1},"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/1909.11786/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":"2026-07-05T00:07:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SW6xG2OA3lHKnVpwoJla9F7HLkQWpewPtCokg49bUzVTVwalT55tfLw/Ow+tjqEOEi7P1dfiviNrshrlhkvcAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T04:37:16.385760Z"},"content_sha256":"92d9ec5e3c0833235000985751b5ccb594ac8dae56df08c5abfd97e3112fe2e5","schema_version":"1.0","event_id":"sha256:92d9ec5e3c0833235000985751b5ccb594ac8dae56df08c5abfd97e3112fe2e5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZNEFWMYSWZ4E4MRPJQC4ATK2EK/bundle.json","state_url":"https://pith.science/pith/ZNEFWMYSWZ4E4MRPJQC4ATK2EK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZNEFWMYSWZ4E4MRPJQC4ATK2EK/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":"2026-07-05T04:37:16Z","links":{"resolver":"https://pith.science/pith/ZNEFWMYSWZ4E4MRPJQC4ATK2EK","bundle":"https://pith.science/pith/ZNEFWMYSWZ4E4MRPJQC4ATK2EK/bundle.json","state":"https://pith.science/pith/ZNEFWMYSWZ4E4MRPJQC4ATK2EK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZNEFWMYSWZ4E4MRPJQC4ATK2EK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ZNEFWMYSWZ4E4MRPJQC4ATK2EK","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":"dcaead1986f599be2853f68ae65170f5fa3ca9784c1a9749fbc44184c7990864","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-09-25T21:41:56Z","title_canon_sha256":"014e30bdfb10cf22d08281b18a3cfd393dc74b390867fb7122d68494b52aa480"},"schema_version":"1.0","source":{"id":"1909.11786","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.11786","created_at":"2026-07-05T00:07:27Z"},{"alias_kind":"arxiv_version","alias_value":"1909.11786v1","created_at":"2026-07-05T00:07:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.11786","created_at":"2026-07-05T00:07:27Z"},{"alias_kind":"pith_short_12","alias_value":"ZNEFWMYSWZ4E","created_at":"2026-07-05T00:07:27Z"},{"alias_kind":"pith_short_16","alias_value":"ZNEFWMYSWZ4E4MRP","created_at":"2026-07-05T00:07:27Z"},{"alias_kind":"pith_short_8","alias_value":"ZNEFWMYS","created_at":"2026-07-05T00:07:27Z"}],"graph_snapshots":[{"event_id":"sha256:92d9ec5e3c0833235000985751b5ccb594ac8dae56df08c5abfd97e3112fe2e5","target":"graph","created_at":"2026-07-05T00:07:27Z","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/1909.11786/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a principled approach for detecting out-of-distribution (OOD) and adversarial samples in deep neural networks. Our approach consists in modeling the outputs of the various layers (deep features) with parametric probability distributions once training is completed. At inference, the likelihoods of the deep features w.r.t the previously learnt distributions are calculated and used to derive uncertainty estimates that can discriminate in-distribution samples from OOD samples. We explore the use of two classes of multivariate distributions for modeling the deep features - Gaussian and G","authors_text":"Ibrahima Ndiour, Nilesh A. Ahuja, Omesh Tickoo, Trushant Kalyanpur","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-09-25T21:41:56Z","title":"Probabilistic Modeling of Deep Features for Out-of-Distribution and Adversarial Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.11786","kind":"arxiv","version":1},"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":"sha256:2d6c37fe257c877378af012bf9d919c3d50aca74e157dbde4f064db7d8b4e40b","target":"record","created_at":"2026-07-05T00:07:27Z","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":"dcaead1986f599be2853f68ae65170f5fa3ca9784c1a9749fbc44184c7990864","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-09-25T21:41:56Z","title_canon_sha256":"014e30bdfb10cf22d08281b18a3cfd393dc74b390867fb7122d68494b52aa480"},"schema_version":"1.0","source":{"id":"1909.11786","kind":"arxiv","version":1}},"canonical_sha256":"cb485b3312b6784e322f4c05c04d5a22a7d0939088318a4851afd3c9a316dad2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb485b3312b6784e322f4c05c04d5a22a7d0939088318a4851afd3c9a316dad2","first_computed_at":"2026-07-05T00:07:27.905485Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:07:27.905485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jJtja0CcKDUSLlTF6qv/xhaE/P28IL86+GfHRjOSusN8cEXIThysLllYsvBToZ3wqn12KxElDAX2UU8dBjHABw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:07:27.905977Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.11786","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d6c37fe257c877378af012bf9d919c3d50aca74e157dbde4f064db7d8b4e40b","sha256:92d9ec5e3c0833235000985751b5ccb594ac8dae56df08c5abfd97e3112fe2e5"],"state_sha256":"a9202a444bbbca0a85e8f7d2ec3c63f0a0cd97a6a88bf3731bf274f620b66cd3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ooAdzRaXGMYVMGiu0FNwQRADnGiUIVLsFCppZBRLRK1RnG7RILeNVgdRWbg68iScC2UsZwRpwwpnNVNhpniIBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T04:37:16.387823Z","bundle_sha256":"18984b1d82969d2ecd8930813234872c9b98dc928cb34c108495e7a75a6bc2d8"}}