{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:HUW4QJCJ4PWYAYEIRP5DSWH4FG","short_pith_number":"pith:HUW4QJCJ","canonical_record":{"source":{"id":"2005.14140","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-05-28T16:43:41Z","cross_cats_sorted":[],"title_canon_sha256":"c1faff8817c36c0d2a5c6f9512adb8e0108a4daf6292e28ae0d98d4aa61e95b6","abstract_canon_sha256":"fe2281eb83a921e6fab9ea82833680f416e6c4f3abaa924a756bb10bd6c34799"},"schema_version":"1.0"},"canonical_sha256":"3d2dc82449e3ed8060888bfa3958fc2990a0024566c4f61ae0089f5b22e1c523","source":{"kind":"arxiv","id":"2005.14140","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.14140","created_at":"2026-07-05T01:45:27Z"},{"alias_kind":"arxiv_version","alias_value":"2005.14140v2","created_at":"2026-07-05T01:45:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.14140","created_at":"2026-07-05T01:45:27Z"},{"alias_kind":"pith_short_12","alias_value":"HUW4QJCJ4PWY","created_at":"2026-07-05T01:45:27Z"},{"alias_kind":"pith_short_16","alias_value":"HUW4QJCJ4PWYAYEI","created_at":"2026-07-05T01:45:27Z"},{"alias_kind":"pith_short_8","alias_value":"HUW4QJCJ","created_at":"2026-07-05T01:45:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:HUW4QJCJ4PWYAYEIRP5DSWH4FG","target":"record","payload":{"canonical_record":{"source":{"id":"2005.14140","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-05-28T16:43:41Z","cross_cats_sorted":[],"title_canon_sha256":"c1faff8817c36c0d2a5c6f9512adb8e0108a4daf6292e28ae0d98d4aa61e95b6","abstract_canon_sha256":"fe2281eb83a921e6fab9ea82833680f416e6c4f3abaa924a756bb10bd6c34799"},"schema_version":"1.0"},"canonical_sha256":"3d2dc82449e3ed8060888bfa3958fc2990a0024566c4f61ae0089f5b22e1c523","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:45:27.250667Z","signature_b64":"TYByuk27v4AbOceVV/EAWeczWj5FDTTRzNZLCFuq8VfPGkIN2fYpdHlETA8Lw8vtHNvSSdob37QY6R4U0zbrCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d2dc82449e3ed8060888bfa3958fc2990a0024566c4f61ae0089f5b22e1c523","last_reissued_at":"2026-07-05T01:45:27.250231Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:45:27.250231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.14140","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:45:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h3AtlprBtz46nKKNOg+V139AR4UIZZTOYb7jUz62kFsOiDA8uE8S9XQ0uSszAhl7AQ25CxySexXCiKr77XPRCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T17:50:00.479093Z"},"content_sha256":"1c95bae7c5c1ac723bea5efcc7087edf53b1c4100bd0d5ea7eecbe166cc8889e","schema_version":"1.0","event_id":"sha256:1c95bae7c5c1ac723bea5efcc7087edf53b1c4100bd0d5ea7eecbe166cc8889e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:HUW4QJCJ4PWYAYEIRP5DSWH4FG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Modeling the Distribution of Normal Data in Pre-Trained Deep Features for Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dorit Merhof, Oliver Rippel, Patrick Mertens","submitted_at":"2020-05-28T16:43:41Z","abstract_excerpt":"Anomaly Detection (AD) in images is a fundamental computer vision problem and refers to identifying images and image substructures that deviate significantly from the norm. Popular AD algorithms commonly try to learn a model of normality from scratch using task specific datasets, but are limited to semi-supervised approaches employing mostly normal data due to the inaccessibility of anomalies on a large scale combined with the ambiguous nature of anomaly appearance.\n  We follow an alternative approach and demonstrate that deep feature representations learned by discriminative models on large n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.14140","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/2005.14140/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":"2026-07-05T01:45:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u1TCU93NRh5dC1UY+/heHf75leGFbqy2NliXYAykRr/7aKTNj7L1CJdcdKosLR5icFyzoAoreZapCGNoZJidDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T17:50:00.480040Z"},"content_sha256":"b03612692bffe7a7e837fec55333fc88c5a33bb1f04580dda98a8343c9e8c38c","schema_version":"1.0","event_id":"sha256:b03612692bffe7a7e837fec55333fc88c5a33bb1f04580dda98a8343c9e8c38c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HUW4QJCJ4PWYAYEIRP5DSWH4FG/bundle.json","state_url":"https://pith.science/pith/HUW4QJCJ4PWYAYEIRP5DSWH4FG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HUW4QJCJ4PWYAYEIRP5DSWH4FG/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":"2026-08-21T17:50:00Z","links":{"resolver":"https://pith.science/pith/HUW4QJCJ4PWYAYEIRP5DSWH4FG","bundle":"https://pith.science/pith/HUW4QJCJ4PWYAYEIRP5DSWH4FG/bundle.json","state":"https://pith.science/pith/HUW4QJCJ4PWYAYEIRP5DSWH4FG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HUW4QJCJ4PWYAYEIRP5DSWH4FG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:HUW4QJCJ4PWYAYEIRP5DSWH4FG","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":"fe2281eb83a921e6fab9ea82833680f416e6c4f3abaa924a756bb10bd6c34799","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-05-28T16:43:41Z","title_canon_sha256":"c1faff8817c36c0d2a5c6f9512adb8e0108a4daf6292e28ae0d98d4aa61e95b6"},"schema_version":"1.0","source":{"id":"2005.14140","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.14140","created_at":"2026-07-05T01:45:27Z"},{"alias_kind":"arxiv_version","alias_value":"2005.14140v2","created_at":"2026-07-05T01:45:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.14140","created_at":"2026-07-05T01:45:27Z"},{"alias_kind":"pith_short_12","alias_value":"HUW4QJCJ4PWY","created_at":"2026-07-05T01:45:27Z"},{"alias_kind":"pith_short_16","alias_value":"HUW4QJCJ4PWYAYEI","created_at":"2026-07-05T01:45:27Z"},{"alias_kind":"pith_short_8","alias_value":"HUW4QJCJ","created_at":"2026-07-05T01:45:27Z"}],"graph_snapshots":[{"event_id":"sha256:b03612692bffe7a7e837fec55333fc88c5a33bb1f04580dda98a8343c9e8c38c","target":"graph","created_at":"2026-07-05T01:45:27Z","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/2005.14140/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Anomaly Detection (AD) in images is a fundamental computer vision problem and refers to identifying images and image substructures that deviate significantly from the norm. Popular AD algorithms commonly try to learn a model of normality from scratch using task specific datasets, but are limited to semi-supervised approaches employing mostly normal data due to the inaccessibility of anomalies on a large scale combined with the ambiguous nature of anomaly appearance.\n  We follow an alternative approach and demonstrate that deep feature representations learned by discriminative models on large n","authors_text":"Dorit Merhof, Oliver Rippel, Patrick Mertens","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-05-28T16:43:41Z","title":"Modeling the Distribution of Normal Data in Pre-Trained Deep Features for Anomaly Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.14140","kind":"arxiv","version":2},"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":"sha256:1c95bae7c5c1ac723bea5efcc7087edf53b1c4100bd0d5ea7eecbe166cc8889e","target":"record","created_at":"2026-07-05T01:45:27Z","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":"fe2281eb83a921e6fab9ea82833680f416e6c4f3abaa924a756bb10bd6c34799","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-05-28T16:43:41Z","title_canon_sha256":"c1faff8817c36c0d2a5c6f9512adb8e0108a4daf6292e28ae0d98d4aa61e95b6"},"schema_version":"1.0","source":{"id":"2005.14140","kind":"arxiv","version":2}},"canonical_sha256":"3d2dc82449e3ed8060888bfa3958fc2990a0024566c4f61ae0089f5b22e1c523","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d2dc82449e3ed8060888bfa3958fc2990a0024566c4f61ae0089f5b22e1c523","first_computed_at":"2026-07-05T01:45:27.250231Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:45:27.250231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TYByuk27v4AbOceVV/EAWeczWj5FDTTRzNZLCFuq8VfPGkIN2fYpdHlETA8Lw8vtHNvSSdob37QY6R4U0zbrCg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:45:27.250667Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.14140","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c95bae7c5c1ac723bea5efcc7087edf53b1c4100bd0d5ea7eecbe166cc8889e","sha256:b03612692bffe7a7e837fec55333fc88c5a33bb1f04580dda98a8343c9e8c38c"],"state_sha256":"6c966bc6a743951d98211dcb61edb56a9c604bfc95e775bda1a1c5f7404a3bca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WOU8MJ0i88jBMJwYqRECIfr+Dpymzp690JfwBiwK98oL+qFTSKeaLq0JKLdjlp5xiRLpDVuWAafY8juihktfBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T17:50:00.484873Z","bundle_sha256":"59f0cb3cddc4094b7b80e929970aacb98eee7b9f14fd9ac8935c5705b0028272"}}