{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EAPXATCIWTBNRKXTQMRRHTUDKO","short_pith_number":"pith:EAPXATCI","canonical_record":{"source":{"id":"2402.18998","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-29T09:48:19Z","cross_cats_sorted":[],"title_canon_sha256":"a022f29c4f1bbf2cfafb387ceb2750a2cd3e10611fb512bf334995e15f6e441d","abstract_canon_sha256":"0cf46fabafb8089bfd2ac6ebcab85e41e85e606771eb0f19a002b8053234b01c"},"schema_version":"1.0"},"canonical_sha256":"201f704c48b4c2d8aaf3832313ce83539fef4326b9aa3597e73f4a76746112fa","source":{"kind":"arxiv","id":"2402.18998","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.18998","created_at":"2026-07-05T07:50:31Z"},{"alias_kind":"arxiv_version","alias_value":"2402.18998v1","created_at":"2026-07-05T07:50:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18998","created_at":"2026-07-05T07:50:31Z"},{"alias_kind":"pith_short_12","alias_value":"EAPXATCIWTBN","created_at":"2026-07-05T07:50:31Z"},{"alias_kind":"pith_short_16","alias_value":"EAPXATCIWTBNRKXT","created_at":"2026-07-05T07:50:31Z"},{"alias_kind":"pith_short_8","alias_value":"EAPXATCI","created_at":"2026-07-05T07:50:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EAPXATCIWTBNRKXTQMRRHTUDKO","target":"record","payload":{"canonical_record":{"source":{"id":"2402.18998","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-29T09:48:19Z","cross_cats_sorted":[],"title_canon_sha256":"a022f29c4f1bbf2cfafb387ceb2750a2cd3e10611fb512bf334995e15f6e441d","abstract_canon_sha256":"0cf46fabafb8089bfd2ac6ebcab85e41e85e606771eb0f19a002b8053234b01c"},"schema_version":"1.0"},"canonical_sha256":"201f704c48b4c2d8aaf3832313ce83539fef4326b9aa3597e73f4a76746112fa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:31.159016Z","signature_b64":"ozLlEPs2sJOKpRzeoe0kYhvaNCnLlMQ3sICF9GvZDojnfd0tRc3PlX9BeMwQW4VOKM/5tiO5N1L97M6pv9lfDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"201f704c48b4c2d8aaf3832313ce83539fef4326b9aa3597e73f4a76746112fa","last_reissued_at":"2026-07-05T07:50:31.158566Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:31.158566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.18998","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":"2026-07-05T07:50:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QH8vbcAaoMG71Tb9eZPkTTmEWTP/K5fpdFsIaiKqBR20gMXe/29NivbJ+CnFPopwwQvfXaSAK5gpO28ipYh6Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:36:19.282878Z"},"content_sha256":"9a85897afd3a2119e26d6532531222cbe4a023308660dce71c952ba585f58d6d","schema_version":"1.0","event_id":"sha256:9a85897afd3a2119e26d6532531222cbe4a023308660dce71c952ba585f58d6d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EAPXATCIWTBNRKXTQMRRHTUDKO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"COFT-AD: COntrastive Fine-Tuning for Few-Shot Anomaly Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adam Goodge, Chuan Sheng Foo, Jingyi Liao, Manh Cuong Nguyen, Xun Xu","submitted_at":"2024-02-29T09:48:19Z","abstract_excerpt":"Existing approaches towards anomaly detection~(AD) often rely on a substantial amount of anomaly-free data to train representation and density models. However, large anomaly-free datasets may not always be available before the inference stage; in which case an anomaly detection model must be trained with only a handful of normal samples, a.k.a. few-shot anomaly detection (FSAD). In this paper, we propose a novel methodology to address the challenge of FSAD which incorporates two important techniques. Firstly, we employ a model pre-trained on a large source dataset to initialize model weights. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18998","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/2402.18998/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":"2026-07-05T07:50:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Va7aWOTzLYdrwSLsOBboCEe2ANHRKqEmc6BSHPsNJjmmepSNqKb52s91uEM/w6xLXEK6/wx6pOsnPciD5N+TBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:36:19.283480Z"},"content_sha256":"158302280720e4d520c486e16755d8f906ed0339b65b232c17b60494b92747de","schema_version":"1.0","event_id":"sha256:158302280720e4d520c486e16755d8f906ed0339b65b232c17b60494b92747de"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EAPXATCIWTBNRKXTQMRRHTUDKO/bundle.json","state_url":"https://pith.science/pith/EAPXATCIWTBNRKXTQMRRHTUDKO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EAPXATCIWTBNRKXTQMRRHTUDKO/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":"2026-08-08T10:36:19Z","links":{"resolver":"https://pith.science/pith/EAPXATCIWTBNRKXTQMRRHTUDKO","bundle":"https://pith.science/pith/EAPXATCIWTBNRKXTQMRRHTUDKO/bundle.json","state":"https://pith.science/pith/EAPXATCIWTBNRKXTQMRRHTUDKO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EAPXATCIWTBNRKXTQMRRHTUDKO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EAPXATCIWTBNRKXTQMRRHTUDKO","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":"0cf46fabafb8089bfd2ac6ebcab85e41e85e606771eb0f19a002b8053234b01c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-29T09:48:19Z","title_canon_sha256":"a022f29c4f1bbf2cfafb387ceb2750a2cd3e10611fb512bf334995e15f6e441d"},"schema_version":"1.0","source":{"id":"2402.18998","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.18998","created_at":"2026-07-05T07:50:31Z"},{"alias_kind":"arxiv_version","alias_value":"2402.18998v1","created_at":"2026-07-05T07:50:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18998","created_at":"2026-07-05T07:50:31Z"},{"alias_kind":"pith_short_12","alias_value":"EAPXATCIWTBN","created_at":"2026-07-05T07:50:31Z"},{"alias_kind":"pith_short_16","alias_value":"EAPXATCIWTBNRKXT","created_at":"2026-07-05T07:50:31Z"},{"alias_kind":"pith_short_8","alias_value":"EAPXATCI","created_at":"2026-07-05T07:50:31Z"}],"graph_snapshots":[{"event_id":"sha256:158302280720e4d520c486e16755d8f906ed0339b65b232c17b60494b92747de","target":"graph","created_at":"2026-07-05T07:50:31Z","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/2402.18998/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing approaches towards anomaly detection~(AD) often rely on a substantial amount of anomaly-free data to train representation and density models. However, large anomaly-free datasets may not always be available before the inference stage; in which case an anomaly detection model must be trained with only a handful of normal samples, a.k.a. few-shot anomaly detection (FSAD). In this paper, we propose a novel methodology to address the challenge of FSAD which incorporates two important techniques. Firstly, we employ a model pre-trained on a large source dataset to initialize model weights. ","authors_text":"Adam Goodge, Chuan Sheng Foo, Jingyi Liao, Manh Cuong Nguyen, Xun Xu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-29T09:48:19Z","title":"COFT-AD: COntrastive Fine-Tuning for Few-Shot Anomaly Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18998","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":"sha256:9a85897afd3a2119e26d6532531222cbe4a023308660dce71c952ba585f58d6d","target":"record","created_at":"2026-07-05T07:50:31Z","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":"0cf46fabafb8089bfd2ac6ebcab85e41e85e606771eb0f19a002b8053234b01c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-29T09:48:19Z","title_canon_sha256":"a022f29c4f1bbf2cfafb387ceb2750a2cd3e10611fb512bf334995e15f6e441d"},"schema_version":"1.0","source":{"id":"2402.18998","kind":"arxiv","version":1}},"canonical_sha256":"201f704c48b4c2d8aaf3832313ce83539fef4326b9aa3597e73f4a76746112fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"201f704c48b4c2d8aaf3832313ce83539fef4326b9aa3597e73f4a76746112fa","first_computed_at":"2026-07-05T07:50:31.158566Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:50:31.158566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ozLlEPs2sJOKpRzeoe0kYhvaNCnLlMQ3sICF9GvZDojnfd0tRc3PlX9BeMwQW4VOKM/5tiO5N1L97M6pv9lfDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:50:31.159016Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.18998","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a85897afd3a2119e26d6532531222cbe4a023308660dce71c952ba585f58d6d","sha256:158302280720e4d520c486e16755d8f906ed0339b65b232c17b60494b92747de"],"state_sha256":"410fb751e4eda49bfecc12dcd5b99eb0b9449c3123d466f74e0c8226fa82ddd4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CYBQSodWJyAT/X3/6loTty39KmG/xMagNT2/wB8NA/DI82oOt4hmypbXHZt7TbTrGkpggCOHXmudlBxewnH6Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T10:36:19.287833Z","bundle_sha256":"31c81dff2602f717670088583f03a93fdceb639135fa50b3d4b3acdcf6ed1121"}}