{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EXGIKTSKS7ET2CQEOTG3LEDOXN","short_pith_number":"pith:EXGIKTSK","schema_version":"1.0","canonical_sha256":"25cc854e4a97c93d0a0474cdb5906ebb5ec544cbcc1a8e366464cdfe51c1ee24","source":{"kind":"arxiv","id":"2502.06194","version":1},"attestation_state":"computed","paper":{"title":"Multimodal Task Representation Memory Bank vs. Catastrophic Forgetting in Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deyu Zeng, Jiangshan Zhao, Weixiang Liu, You Zhou, Zongze Wu, Zuo Zuo","submitted_at":"2025-02-10T06:49:54Z","abstract_excerpt":"Unsupervised Continuous Anomaly Detection (UCAD) faces significant challenges in multi-task representation learning, with existing methods suffering from incomplete representation and catastrophic forgetting. Unlike supervised models, unsupervised scenarios lack prior information, making it difficult to effectively distinguish redundant and complementary multimodal features. To address this, we propose the Multimodal Task Representation Memory Bank (MTRMB) method through two key technical innovations: A Key-Prompt-Multimodal Knowledge (KPMK) mechanism that uses concise key prompts to guide cro"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2502.06194","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-10T06:49:54Z","cross_cats_sorted":[],"title_canon_sha256":"a0baec196f822d270408d855ac88a5ee8cc501c95a4e193c00bfd977f2fd6c5d","abstract_canon_sha256":"f55d2f97e29da161aad4aa1e3d8c58d9e12466f240952c9cf07c196cbf50e801"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:48.881732Z","signature_b64":"rvvU0RDpgFJXCEvTabCJvzM4MiUXg0dwBI0B84lu5ufYqv9/iMp7iht5ZGRKWg9Zz3q/dnkc841/4cmlzhFcDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25cc854e4a97c93d0a0474cdb5906ebb5ec544cbcc1a8e366464cdfe51c1ee24","last_reissued_at":"2026-07-05T10:11:48.881241Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:48.881241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Task Representation Memory Bank vs. Catastrophic Forgetting in Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deyu Zeng, Jiangshan Zhao, Weixiang Liu, You Zhou, Zongze Wu, Zuo Zuo","submitted_at":"2025-02-10T06:49:54Z","abstract_excerpt":"Unsupervised Continuous Anomaly Detection (UCAD) faces significant challenges in multi-task representation learning, with existing methods suffering from incomplete representation and catastrophic forgetting. Unlike supervised models, unsupervised scenarios lack prior information, making it difficult to effectively distinguish redundant and complementary multimodal features. To address this, we propose the Multimodal Task Representation Memory Bank (MTRMB) method through two key technical innovations: A Key-Prompt-Multimodal Knowledge (KPMK) mechanism that uses concise key prompts to guide cro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06194","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/2502.06194/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2502.06194","created_at":"2026-07-05T10:11:48.881294+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.06194v1","created_at":"2026-07-05T10:11:48.881294+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06194","created_at":"2026-07-05T10:11:48.881294+00:00"},{"alias_kind":"pith_short_12","alias_value":"EXGIKTSKS7ET","created_at":"2026-07-05T10:11:48.881294+00:00"},{"alias_kind":"pith_short_16","alias_value":"EXGIKTSKS7ET2CQE","created_at":"2026-07-05T10:11:48.881294+00:00"},{"alias_kind":"pith_short_8","alias_value":"EXGIKTSK","created_at":"2026-07-05T10:11:48.881294+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26687","citing_title":"DeCoFlow: Structural Decomposition of Normalizing Flows for Continual Anomaly Detection","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EXGIKTSKS7ET2CQEOTG3LEDOXN","json":"https://pith.science/pith/EXGIKTSKS7ET2CQEOTG3LEDOXN.json","graph_json":"https://pith.science/api/pith-number/EXGIKTSKS7ET2CQEOTG3LEDOXN/graph.json","events_json":"https://pith.science/api/pith-number/EXGIKTSKS7ET2CQEOTG3LEDOXN/events.json","paper":"https://pith.science/paper/EXGIKTSK"},"agent_actions":{"view_html":"https://pith.science/pith/EXGIKTSKS7ET2CQEOTG3LEDOXN","download_json":"https://pith.science/pith/EXGIKTSKS7ET2CQEOTG3LEDOXN.json","view_paper":"https://pith.science/paper/EXGIKTSK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.06194&json=true","fetch_graph":"https://pith.science/api/pith-number/EXGIKTSKS7ET2CQEOTG3LEDOXN/graph.json","fetch_events":"https://pith.science/api/pith-number/EXGIKTSKS7ET2CQEOTG3LEDOXN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EXGIKTSKS7ET2CQEOTG3LEDOXN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EXGIKTSKS7ET2CQEOTG3LEDOXN/action/storage_attestation","attest_author":"https://pith.science/pith/EXGIKTSKS7ET2CQEOTG3LEDOXN/action/author_attestation","sign_citation":"https://pith.science/pith/EXGIKTSKS7ET2CQEOTG3LEDOXN/action/citation_signature","submit_replication":"https://pith.science/pith/EXGIKTSKS7ET2CQEOTG3LEDOXN/action/replication_record"}},"created_at":"2026-07-05T10:11:48.881294+00:00","updated_at":"2026-07-05T10:11:48.881294+00:00"}