{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:26NI6V4TP2XNUWGWUUEITVQ3I6","short_pith_number":"pith:26NI6V4T","canonical_record":{"source":{"id":"2112.02597","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-05T15:29:59Z","cross_cats_sorted":[],"title_canon_sha256":"c5d85e47dd8b53097aff5b5405b33f74b5eca4286a507a8f5354c59c9df5f068","abstract_canon_sha256":"801e1531d185aac4884735a4613f24c58a478f9ca4ae99153dab38dc5b6a8320"},"schema_version":"1.0"},"canonical_sha256":"d79a8f57937eaeda58d6a50889d61b47947f67f68c6bb50ca1c37841f4bca0c8","source":{"kind":"arxiv","id":"2112.02597","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.02597","created_at":"2026-07-05T04:17:18Z"},{"alias_kind":"arxiv_version","alias_value":"2112.02597v2","created_at":"2026-07-05T04:17:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.02597","created_at":"2026-07-05T04:17:18Z"},{"alias_kind":"pith_short_12","alias_value":"26NI6V4TP2XN","created_at":"2026-07-05T04:17:18Z"},{"alias_kind":"pith_short_16","alias_value":"26NI6V4TP2XNUWGW","created_at":"2026-07-05T04:17:18Z"},{"alias_kind":"pith_short_8","alias_value":"26NI6V4T","created_at":"2026-07-05T04:17:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:26NI6V4TP2XNUWGWUUEITVQ3I6","target":"record","payload":{"canonical_record":{"source":{"id":"2112.02597","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-05T15:29:59Z","cross_cats_sorted":[],"title_canon_sha256":"c5d85e47dd8b53097aff5b5405b33f74b5eca4286a507a8f5354c59c9df5f068","abstract_canon_sha256":"801e1531d185aac4884735a4613f24c58a478f9ca4ae99153dab38dc5b6a8320"},"schema_version":"1.0"},"canonical_sha256":"d79a8f57937eaeda58d6a50889d61b47947f67f68c6bb50ca1c37841f4bca0c8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:17:18.922820Z","signature_b64":"JSthqL7BpzubOFYRO8VUAS6weII279xTfozuZP6xAMM4gA8LSelkJNVg1zT+OGVFaZlhtlhA3QA4XrTuyKRiDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d79a8f57937eaeda58d6a50889d61b47947f67f68c6bb50ca1c37841f4bca0c8","last_reissued_at":"2026-07-05T04:17:18.922342Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:17:18.922342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.02597","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":"2026-07-05T04:17:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sdC9j6pxsrDsnWi9r85wO/Nq16PMkL2qZR35LiHGLnE3WPjrRNCS77fTR9b7he8Wmc8X7uucpYtJLDLJZsIJCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T14:52:14.791161Z"},"content_sha256":"d0ae0b079cef5dd0379baa5311267c47ed07c2d0a062fac2e89875b1ebe39905","schema_version":"1.0","event_id":"sha256:d0ae0b079cef5dd0379baa5311267c47ed07c2d0a062fac2e89875b1ebe39905"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:26NI6V4TP2XNUWGWUUEITVQ3I6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Constrained Adaptive Projection with Pretrained Features for Anomaly Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Di Wu, Shicai Fan, Xingtai Gui, Yang Chang","submitted_at":"2021-12-05T15:29:59Z","abstract_excerpt":"Anomaly detection aims to separate anomalies from normal samples, and the pretrained network is promising for anomaly detection. However, adapting the pretrained features would be confronted with the risk of pattern collapse when finetuning on one-class training data. In this paper, we propose an anomaly detection framework called constrained adaptive projection with pretrained features (CAP). Combined with pretrained features, a simple linear projection head applied on a specific input and its k most similar pretrained normal representations is designed for feature adaptation, and a reformed "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.02597","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/2112.02597/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":"2026-07-05T04:17:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rJTQRFVJVnyAb/PNeMMWNQl+9nYvp8CyHYBPjtfMPRFKAA+C3teQmEQRLJ/Nwrylm+0UYB/cIKDYKjrv3RZhBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T14:52:14.791648Z"},"content_sha256":"edc2dbf04598587426e3d407475c7515e8eb4a16accb3fd5aa359e7187f6af6d","schema_version":"1.0","event_id":"sha256:edc2dbf04598587426e3d407475c7515e8eb4a16accb3fd5aa359e7187f6af6d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/26NI6V4TP2XNUWGWUUEITVQ3I6/bundle.json","state_url":"https://pith.science/pith/26NI6V4TP2XNUWGWUUEITVQ3I6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/26NI6V4TP2XNUWGWUUEITVQ3I6/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":"2026-08-21T14:52:14Z","links":{"resolver":"https://pith.science/pith/26NI6V4TP2XNUWGWUUEITVQ3I6","bundle":"https://pith.science/pith/26NI6V4TP2XNUWGWUUEITVQ3I6/bundle.json","state":"https://pith.science/pith/26NI6V4TP2XNUWGWUUEITVQ3I6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/26NI6V4TP2XNUWGWUUEITVQ3I6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:26NI6V4TP2XNUWGWUUEITVQ3I6","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":"801e1531d185aac4884735a4613f24c58a478f9ca4ae99153dab38dc5b6a8320","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-05T15:29:59Z","title_canon_sha256":"c5d85e47dd8b53097aff5b5405b33f74b5eca4286a507a8f5354c59c9df5f068"},"schema_version":"1.0","source":{"id":"2112.02597","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.02597","created_at":"2026-07-05T04:17:18Z"},{"alias_kind":"arxiv_version","alias_value":"2112.02597v2","created_at":"2026-07-05T04:17:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.02597","created_at":"2026-07-05T04:17:18Z"},{"alias_kind":"pith_short_12","alias_value":"26NI6V4TP2XN","created_at":"2026-07-05T04:17:18Z"},{"alias_kind":"pith_short_16","alias_value":"26NI6V4TP2XNUWGW","created_at":"2026-07-05T04:17:18Z"},{"alias_kind":"pith_short_8","alias_value":"26NI6V4T","created_at":"2026-07-05T04:17:18Z"}],"graph_snapshots":[{"event_id":"sha256:edc2dbf04598587426e3d407475c7515e8eb4a16accb3fd5aa359e7187f6af6d","target":"graph","created_at":"2026-07-05T04:17:18Z","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/2112.02597/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Anomaly detection aims to separate anomalies from normal samples, and the pretrained network is promising for anomaly detection. However, adapting the pretrained features would be confronted with the risk of pattern collapse when finetuning on one-class training data. In this paper, we propose an anomaly detection framework called constrained adaptive projection with pretrained features (CAP). Combined with pretrained features, a simple linear projection head applied on a specific input and its k most similar pretrained normal representations is designed for feature adaptation, and a reformed ","authors_text":"Di Wu, Shicai Fan, Xingtai Gui, Yang Chang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-05T15:29:59Z","title":"Constrained Adaptive Projection with Pretrained Features for Anomaly Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.02597","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:d0ae0b079cef5dd0379baa5311267c47ed07c2d0a062fac2e89875b1ebe39905","target":"record","created_at":"2026-07-05T04:17:18Z","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":"801e1531d185aac4884735a4613f24c58a478f9ca4ae99153dab38dc5b6a8320","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-05T15:29:59Z","title_canon_sha256":"c5d85e47dd8b53097aff5b5405b33f74b5eca4286a507a8f5354c59c9df5f068"},"schema_version":"1.0","source":{"id":"2112.02597","kind":"arxiv","version":2}},"canonical_sha256":"d79a8f57937eaeda58d6a50889d61b47947f67f68c6bb50ca1c37841f4bca0c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d79a8f57937eaeda58d6a50889d61b47947f67f68c6bb50ca1c37841f4bca0c8","first_computed_at":"2026-07-05T04:17:18.922342Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:17:18.922342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JSthqL7BpzubOFYRO8VUAS6weII279xTfozuZP6xAMM4gA8LSelkJNVg1zT+OGVFaZlhtlhA3QA4XrTuyKRiDw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:17:18.922820Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.02597","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d0ae0b079cef5dd0379baa5311267c47ed07c2d0a062fac2e89875b1ebe39905","sha256:edc2dbf04598587426e3d407475c7515e8eb4a16accb3fd5aa359e7187f6af6d"],"state_sha256":"5689a2c915e6d47415f5f493ec535e2b1259eb09f0158d7e9978abb9a9820d1d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HyuzGj+Ehe0nVkgN1BKZnSNiAJ9Q1AKxnwFIaatpaClgnQiVHK4tH4QlkiFqnWuKaNuxS32dK8X0h1ZYm1I3AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T14:52:14.795434Z","bundle_sha256":"89828b68289d642113e41022d28944b22cd081b0001785a94b2ad271630e0609"}}