{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:X6PKHSYKS4FL242C2656HCPTYC","short_pith_number":"pith:X6PKHSYK","schema_version":"1.0","canonical_sha256":"bf9ea3cb0a970abd7342d7bbe389f3c085d68ea45b2a7486904dc92bccb245c2","source":{"kind":"arxiv","id":"2409.00942","version":1},"attestation_state":"computed","paper":{"title":"VQ-Flow: Taming Normalizing Flows for Multi-Class Anomaly Detection via Hierarchical Vector Quantization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrzej Cichocki, Heng Tao Shen, Jingkuan Song, Xing Xu, Yixuan Zhou, Zhe Sun","submitted_at":"2024-09-02T05:01:41Z","abstract_excerpt":"Normalizing flows, a category of probabilistic models famed for their capabilities in modeling complex data distributions, have exhibited remarkable efficacy in unsupervised anomaly detection. This paper explores the potential of normalizing flows in multi-class anomaly detection, wherein the normal data is compounded with multiple classes without providing class labels. Through the integration of vector quantization (VQ), we empower the flow models to distinguish different concepts of multi-class normal data in an unsupervised manner, resulting in a novel flow-based unified method, named VQ-F"},"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":"2409.00942","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-02T05:01:41Z","cross_cats_sorted":[],"title_canon_sha256":"8baee84b9b9416f6375e2f89b65c8929bc9950715474e4601b72440ed85b5987","abstract_canon_sha256":"f05ef26ea5b2375c829c481badff23b6f80da6d2995f6fdcda5a0e72a5412dc6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:01:55.642089Z","signature_b64":"rFl1kFh1VfBPHGrcIMVIPtewoXchfUxeNrofSm/rmi1q0mzfgEUGo/C3qCoOOvxRF2eko7YJDHmhwfNxoD7LCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf9ea3cb0a970abd7342d7bbe389f3c085d68ea45b2a7486904dc92bccb245c2","last_reissued_at":"2026-07-05T09:01:55.641625Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:01:55.641625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VQ-Flow: Taming Normalizing Flows for Multi-Class Anomaly Detection via Hierarchical Vector Quantization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrzej Cichocki, Heng Tao Shen, Jingkuan Song, Xing Xu, Yixuan Zhou, Zhe Sun","submitted_at":"2024-09-02T05:01:41Z","abstract_excerpt":"Normalizing flows, a category of probabilistic models famed for their capabilities in modeling complex data distributions, have exhibited remarkable efficacy in unsupervised anomaly detection. This paper explores the potential of normalizing flows in multi-class anomaly detection, wherein the normal data is compounded with multiple classes without providing class labels. Through the integration of vector quantization (VQ), we empower the flow models to distinguish different concepts of multi-class normal data in an unsupervised manner, resulting in a novel flow-based unified method, named VQ-F"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.00942","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/2409.00942/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":"2409.00942","created_at":"2026-07-05T09:01:55.641683+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.00942v1","created_at":"2026-07-05T09:01:55.641683+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.00942","created_at":"2026-07-05T09:01:55.641683+00:00"},{"alias_kind":"pith_short_12","alias_value":"X6PKHSYKS4FL","created_at":"2026-07-05T09:01:55.641683+00:00"},{"alias_kind":"pith_short_16","alias_value":"X6PKHSYKS4FL242C","created_at":"2026-07-05T09:01:55.641683+00:00"},{"alias_kind":"pith_short_8","alias_value":"X6PKHSYK","created_at":"2026-07-05T09:01:55.641683+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":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X6PKHSYKS4FL242C2656HCPTYC","json":"https://pith.science/pith/X6PKHSYKS4FL242C2656HCPTYC.json","graph_json":"https://pith.science/api/pith-number/X6PKHSYKS4FL242C2656HCPTYC/graph.json","events_json":"https://pith.science/api/pith-number/X6PKHSYKS4FL242C2656HCPTYC/events.json","paper":"https://pith.science/paper/X6PKHSYK"},"agent_actions":{"view_html":"https://pith.science/pith/X6PKHSYKS4FL242C2656HCPTYC","download_json":"https://pith.science/pith/X6PKHSYKS4FL242C2656HCPTYC.json","view_paper":"https://pith.science/paper/X6PKHSYK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.00942&json=true","fetch_graph":"https://pith.science/api/pith-number/X6PKHSYKS4FL242C2656HCPTYC/graph.json","fetch_events":"https://pith.science/api/pith-number/X6PKHSYKS4FL242C2656HCPTYC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X6PKHSYKS4FL242C2656HCPTYC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X6PKHSYKS4FL242C2656HCPTYC/action/storage_attestation","attest_author":"https://pith.science/pith/X6PKHSYKS4FL242C2656HCPTYC/action/author_attestation","sign_citation":"https://pith.science/pith/X6PKHSYKS4FL242C2656HCPTYC/action/citation_signature","submit_replication":"https://pith.science/pith/X6PKHSYKS4FL242C2656HCPTYC/action/replication_record"}},"created_at":"2026-07-05T09:01:55.641683+00:00","updated_at":"2026-07-05T09:01:55.641683+00:00"}