{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EEYXNS6AQGTHSCCDM6UI4FUEYT","short_pith_number":"pith:EEYXNS6A","schema_version":"1.0","canonical_sha256":"213176cbc081a679084367a88e1684c4e7105955736bb930dcb5b364eb4f1d9a","source":{"kind":"arxiv","id":"2412.03907","version":3},"attestation_state":"computed","paper":{"title":"ONER: Online Experience Replay for Incremental Anomaly Detection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guodong Wang, Jiahui Zhu, Jinjin Zhang, Qingjie Liu, Shiwei Li, Xinyue Liu, Yizhou Jin, Yunhong Wang","submitted_at":"2024-12-05T06:26:32Z","abstract_excerpt":"Incremental anomaly detection aims to sequentially identify defects in industrial product lines but suffers from catastrophic forgetting, primarily due to knowledge overwriting during parameter updates and feature conflicts between tasks. In this work, We propose ONER (ONline Experience Replay), an end-to-end framework that addresses these issues by synergistically integrating two types of experience: (1) decomposed prompts, which dynamically generate image-conditioned prompts from reusable modules to retain prior knowledge thus prevent knowledge overwriting, and (2) semantic prototypes, which"},"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":"2412.03907","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T06:26:32Z","cross_cats_sorted":[],"title_canon_sha256":"45a50d4e0ab34f5a97671a4e641c10d3edcb7c4a01d641b6376e32abe72be9d0","abstract_canon_sha256":"b809135ae618c48be330eaf7915b2b9af6156db5dde3cc41c23f3ef9a1aa918b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:23.943338Z","signature_b64":"POVIEH3pncghOlroTWmI/jPnSJRRncYjf3jnK6mXy27aZQwwQq59697DEJdzkPpFzEyVlGPY5p74EvZf/2znCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"213176cbc081a679084367a88e1684c4e7105955736bb930dcb5b364eb4f1d9a","last_reissued_at":"2026-07-05T10:39:23.942848Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:23.942848Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ONER: Online Experience Replay for Incremental Anomaly Detection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guodong Wang, Jiahui Zhu, Jinjin Zhang, Qingjie Liu, Shiwei Li, Xinyue Liu, Yizhou Jin, Yunhong Wang","submitted_at":"2024-12-05T06:26:32Z","abstract_excerpt":"Incremental anomaly detection aims to sequentially identify defects in industrial product lines but suffers from catastrophic forgetting, primarily due to knowledge overwriting during parameter updates and feature conflicts between tasks. In this work, We propose ONER (ONline Experience Replay), an end-to-end framework that addresses these issues by synergistically integrating two types of experience: (1) decomposed prompts, which dynamically generate image-conditioned prompts from reusable modules to retain prior knowledge thus prevent knowledge overwriting, and (2) semantic prototypes, which"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03907","kind":"arxiv","version":3},"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/2412.03907/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":"2412.03907","created_at":"2026-07-05T10:39:23.942903+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.03907v3","created_at":"2026-07-05T10:39:23.942903+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03907","created_at":"2026-07-05T10:39:23.942903+00:00"},{"alias_kind":"pith_short_12","alias_value":"EEYXNS6AQGTH","created_at":"2026-07-05T10:39:23.942903+00:00"},{"alias_kind":"pith_short_16","alias_value":"EEYXNS6AQGTHSCCD","created_at":"2026-07-05T10:39:23.942903+00:00"},{"alias_kind":"pith_short_8","alias_value":"EEYXNS6A","created_at":"2026-07-05T10:39:23.942903+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.12049","citing_title":"MoViAD: A Modular Library for Visual Anomaly Detection","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EEYXNS6AQGTHSCCDM6UI4FUEYT","json":"https://pith.science/pith/EEYXNS6AQGTHSCCDM6UI4FUEYT.json","graph_json":"https://pith.science/api/pith-number/EEYXNS6AQGTHSCCDM6UI4FUEYT/graph.json","events_json":"https://pith.science/api/pith-number/EEYXNS6AQGTHSCCDM6UI4FUEYT/events.json","paper":"https://pith.science/paper/EEYXNS6A"},"agent_actions":{"view_html":"https://pith.science/pith/EEYXNS6AQGTHSCCDM6UI4FUEYT","download_json":"https://pith.science/pith/EEYXNS6AQGTHSCCDM6UI4FUEYT.json","view_paper":"https://pith.science/paper/EEYXNS6A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.03907&json=true","fetch_graph":"https://pith.science/api/pith-number/EEYXNS6AQGTHSCCDM6UI4FUEYT/graph.json","fetch_events":"https://pith.science/api/pith-number/EEYXNS6AQGTHSCCDM6UI4FUEYT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EEYXNS6AQGTHSCCDM6UI4FUEYT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EEYXNS6AQGTHSCCDM6UI4FUEYT/action/storage_attestation","attest_author":"https://pith.science/pith/EEYXNS6AQGTHSCCDM6UI4FUEYT/action/author_attestation","sign_citation":"https://pith.science/pith/EEYXNS6AQGTHSCCDM6UI4FUEYT/action/citation_signature","submit_replication":"https://pith.science/pith/EEYXNS6AQGTHSCCDM6UI4FUEYT/action/replication_record"}},"created_at":"2026-07-05T10:39:23.942903+00:00","updated_at":"2026-07-05T10:39:23.942903+00:00"}