{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UI6QCF73AJX3YE25JAUAQHH2LH","short_pith_number":"pith:UI6QCF73","canonical_record":{"source":{"id":"2504.21294","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-30T03:59:58Z","cross_cats_sorted":[],"title_canon_sha256":"21c1ac6b24f411de54a6a0d1789e14b7dcc85ee3d0b98ce18c96f601e28eeb8b","abstract_canon_sha256":"d18cd97b067bcbbcdead5237866833a9daa65085457ebca47b8072c01137c34d"},"schema_version":"1.0"},"canonical_sha256":"a23d0117fb026fbc135d4828081cfa59f49786322a1e4eecd5bab3dbe8632d4d","source":{"kind":"arxiv","id":"2504.21294","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.21294","created_at":"2026-07-05T10:56:21Z"},{"alias_kind":"arxiv_version","alias_value":"2504.21294v1","created_at":"2026-07-05T10:56:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21294","created_at":"2026-07-05T10:56:21Z"},{"alias_kind":"pith_short_12","alias_value":"UI6QCF73AJX3","created_at":"2026-07-05T10:56:21Z"},{"alias_kind":"pith_short_16","alias_value":"UI6QCF73AJX3YE25","created_at":"2026-07-05T10:56:21Z"},{"alias_kind":"pith_short_8","alias_value":"UI6QCF73","created_at":"2026-07-05T10:56:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UI6QCF73AJX3YE25JAUAQHH2LH","target":"record","payload":{"canonical_record":{"source":{"id":"2504.21294","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-30T03:59:58Z","cross_cats_sorted":[],"title_canon_sha256":"21c1ac6b24f411de54a6a0d1789e14b7dcc85ee3d0b98ce18c96f601e28eeb8b","abstract_canon_sha256":"d18cd97b067bcbbcdead5237866833a9daa65085457ebca47b8072c01137c34d"},"schema_version":"1.0"},"canonical_sha256":"a23d0117fb026fbc135d4828081cfa59f49786322a1e4eecd5bab3dbe8632d4d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:56:21.686331Z","signature_b64":"lF4bNwhYIahcsE7pgf1za0k6VVrrEfAIZhMqFflSTeMxyd0phfgQnsZu+V+pAk6Frbi5YFx2IkUeBDaNoPLyDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a23d0117fb026fbc135d4828081cfa59f49786322a1e4eecd5bab3dbe8632d4d","last_reissued_at":"2026-07-05T10:56:21.685811Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:56:21.685811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.21294","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":"2026-07-05T10:56:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"De8lQnj+NYd7nsdKgPnnKMfUp9mkQJtoyQWl2BjMn6uk475XRL0XelAhalZR7cnBZ8a03yNhhw9IiGH8N4wrBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T22:45:22.887933Z"},"content_sha256":"21d1cdd5342a83e63e86891d38f92006217f1fe5c3baa5e3067ed051846adbf2","schema_version":"1.0","event_id":"sha256:21d1cdd5342a83e63e86891d38f92006217f1fe5c3baa5e3067ed051846adbf2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UI6QCF73AJX3YE25JAUAQHH2LH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Multi-view Multi-class Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qianzi Yu, Yang Cao, Yu Kang","submitted_at":"2025-04-30T03:59:58Z","abstract_excerpt":"The latest trend in anomaly detection is to train a unified model instead of training a separate model for each category. However, existing multi-class anomaly detection (MCAD) models perform poorly in multi-view scenarios because they often fail to effectively model the relationships and complementary information among different views. In this paper, we introduce a Multi-View Multi-Class Anomaly Detection model (MVMCAD), which integrates information from multiple views to accurately identify anomalies. Specifically, we propose a semi-frozen encoder, where a pre-encoder prior enhancement mecha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.21294","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/2504.21294/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":"2026-07-05T10:56:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iG3KWSQS/2N8gDXMsniPmCWdTCEXD959waBGZ4SnQFyQHGuga2tIMhqDRpMfkaDWlysuPWNtF50vp+vOVhTsAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T22:45:22.888412Z"},"content_sha256":"e7dca845922085072e1eb656710b5b981bb62d2670e8e93ae5a41eb34c31bd2f","schema_version":"1.0","event_id":"sha256:e7dca845922085072e1eb656710b5b981bb62d2670e8e93ae5a41eb34c31bd2f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UI6QCF73AJX3YE25JAUAQHH2LH/bundle.json","state_url":"https://pith.science/pith/UI6QCF73AJX3YE25JAUAQHH2LH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UI6QCF73AJX3YE25JAUAQHH2LH/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":"2026-08-18T22:45:22Z","links":{"resolver":"https://pith.science/pith/UI6QCF73AJX3YE25JAUAQHH2LH","bundle":"https://pith.science/pith/UI6QCF73AJX3YE25JAUAQHH2LH/bundle.json","state":"https://pith.science/pith/UI6QCF73AJX3YE25JAUAQHH2LH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UI6QCF73AJX3YE25JAUAQHH2LH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UI6QCF73AJX3YE25JAUAQHH2LH","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":"d18cd97b067bcbbcdead5237866833a9daa65085457ebca47b8072c01137c34d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-30T03:59:58Z","title_canon_sha256":"21c1ac6b24f411de54a6a0d1789e14b7dcc85ee3d0b98ce18c96f601e28eeb8b"},"schema_version":"1.0","source":{"id":"2504.21294","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.21294","created_at":"2026-07-05T10:56:21Z"},{"alias_kind":"arxiv_version","alias_value":"2504.21294v1","created_at":"2026-07-05T10:56:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21294","created_at":"2026-07-05T10:56:21Z"},{"alias_kind":"pith_short_12","alias_value":"UI6QCF73AJX3","created_at":"2026-07-05T10:56:21Z"},{"alias_kind":"pith_short_16","alias_value":"UI6QCF73AJX3YE25","created_at":"2026-07-05T10:56:21Z"},{"alias_kind":"pith_short_8","alias_value":"UI6QCF73","created_at":"2026-07-05T10:56:21Z"}],"graph_snapshots":[{"event_id":"sha256:e7dca845922085072e1eb656710b5b981bb62d2670e8e93ae5a41eb34c31bd2f","target":"graph","created_at":"2026-07-05T10:56:21Z","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/2504.21294/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The latest trend in anomaly detection is to train a unified model instead of training a separate model for each category. However, existing multi-class anomaly detection (MCAD) models perform poorly in multi-view scenarios because they often fail to effectively model the relationships and complementary information among different views. In this paper, we introduce a Multi-View Multi-Class Anomaly Detection model (MVMCAD), which integrates information from multiple views to accurately identify anomalies. Specifically, we propose a semi-frozen encoder, where a pre-encoder prior enhancement mecha","authors_text":"Qianzi Yu, Yang Cao, Yu Kang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-30T03:59:58Z","title":"Learning Multi-view Multi-class Anomaly Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.21294","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":"sha256:21d1cdd5342a83e63e86891d38f92006217f1fe5c3baa5e3067ed051846adbf2","target":"record","created_at":"2026-07-05T10:56:21Z","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":"d18cd97b067bcbbcdead5237866833a9daa65085457ebca47b8072c01137c34d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-30T03:59:58Z","title_canon_sha256":"21c1ac6b24f411de54a6a0d1789e14b7dcc85ee3d0b98ce18c96f601e28eeb8b"},"schema_version":"1.0","source":{"id":"2504.21294","kind":"arxiv","version":1}},"canonical_sha256":"a23d0117fb026fbc135d4828081cfa59f49786322a1e4eecd5bab3dbe8632d4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a23d0117fb026fbc135d4828081cfa59f49786322a1e4eecd5bab3dbe8632d4d","first_computed_at":"2026-07-05T10:56:21.685811Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:56:21.685811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lF4bNwhYIahcsE7pgf1za0k6VVrrEfAIZhMqFflSTeMxyd0phfgQnsZu+V+pAk6Frbi5YFx2IkUeBDaNoPLyDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:56:21.686331Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.21294","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:21d1cdd5342a83e63e86891d38f92006217f1fe5c3baa5e3067ed051846adbf2","sha256:e7dca845922085072e1eb656710b5b981bb62d2670e8e93ae5a41eb34c31bd2f"],"state_sha256":"9775813914dec652584ab05cf937d2d037c94b6dd0c98e7cfccf7c60e0deebb1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yOADprJgrR2NcICYH/pxMic88EAw6w1ESPPVhpF2aSNvVkKXVrZ6+ALiqTbmA26ZR3j9D4Pv+DkH7qlhqLWeBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T22:45:22.891804Z","bundle_sha256":"fb6713905b946cac07d01a032ca1cc88c5bb37c5adaeed6fa0bec7cefe17f9fb"}}