{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CZATSXJUT3NUAJVDS5BP7ZE3R3","short_pith_number":"pith:CZATSXJU","schema_version":"1.0","canonical_sha256":"1641395d349edb4026a39742ffe49b8eec0f2dbc86b7bdb0bd03f84d6a268c51","source":{"kind":"arxiv","id":"2504.03442","version":1},"attestation_state":"computed","paper":{"title":"Pyramid-based Mamba Multi-class Unsupervised Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Nasar Iqbal, Niki Martinel","submitted_at":"2025-04-04T13:33:59Z","abstract_excerpt":"Recent advances in convolutional neural networks (CNNs) and transformer-based methods have improved anomaly detection and localization, but challenges persist in precisely localizing small anomalies. While CNNs face limitations in capturing long-range dependencies, transformer architectures often suffer from substantial computational overheads. We introduce a state space model (SSM)-based Pyramidal Scanning Strategy (PSS) for multi-class anomaly detection and localization--a novel approach designed to address the challenge of small anomaly localization. Our method captures fine-grained details"},"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":"2504.03442","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-04T13:33:59Z","cross_cats_sorted":[],"title_canon_sha256":"3bbe2b7b5efadf3621e7101d323bf8c4426622c87e2f31c67b636dcf826a6e4e","abstract_canon_sha256":"ef9105c38dd719d8da5a9f3d413245bec02f12e8eedcffaef9225fc2ad3e6cab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:32.314713Z","signature_b64":"Vk0g/6tqWPL17MX+gl9/JE7OASTk3ZUgFAHgqb+lHsNTXEKrBQdUNbHcwhvKAFrN8lpVwUiRo25CoEBRh3HqBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1641395d349edb4026a39742ffe49b8eec0f2dbc86b7bdb0bd03f84d6a268c51","last_reissued_at":"2026-07-05T10:44:32.314236Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:32.314236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pyramid-based Mamba Multi-class Unsupervised Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Nasar Iqbal, Niki Martinel","submitted_at":"2025-04-04T13:33:59Z","abstract_excerpt":"Recent advances in convolutional neural networks (CNNs) and transformer-based methods have improved anomaly detection and localization, but challenges persist in precisely localizing small anomalies. While CNNs face limitations in capturing long-range dependencies, transformer architectures often suffer from substantial computational overheads. We introduce a state space model (SSM)-based Pyramidal Scanning Strategy (PSS) for multi-class anomaly detection and localization--a novel approach designed to address the challenge of small anomaly localization. Our method captures fine-grained details"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.03442","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/2504.03442/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":"2504.03442","created_at":"2026-07-05T10:44:32.314291+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.03442v1","created_at":"2026-07-05T10:44:32.314291+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.03442","created_at":"2026-07-05T10:44:32.314291+00:00"},{"alias_kind":"pith_short_12","alias_value":"CZATSXJUT3NU","created_at":"2026-07-05T10:44:32.314291+00:00"},{"alias_kind":"pith_short_16","alias_value":"CZATSXJUT3NUAJVD","created_at":"2026-07-05T10:44:32.314291+00:00"},{"alias_kind":"pith_short_8","alias_value":"CZATSXJU","created_at":"2026-07-05T10:44:32.314291+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.01591","citing_title":"Self-Navigated Residual Mamba for Universal Industrial Anomaly Detection","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CZATSXJUT3NUAJVDS5BP7ZE3R3","json":"https://pith.science/pith/CZATSXJUT3NUAJVDS5BP7ZE3R3.json","graph_json":"https://pith.science/api/pith-number/CZATSXJUT3NUAJVDS5BP7ZE3R3/graph.json","events_json":"https://pith.science/api/pith-number/CZATSXJUT3NUAJVDS5BP7ZE3R3/events.json","paper":"https://pith.science/paper/CZATSXJU"},"agent_actions":{"view_html":"https://pith.science/pith/CZATSXJUT3NUAJVDS5BP7ZE3R3","download_json":"https://pith.science/pith/CZATSXJUT3NUAJVDS5BP7ZE3R3.json","view_paper":"https://pith.science/paper/CZATSXJU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.03442&json=true","fetch_graph":"https://pith.science/api/pith-number/CZATSXJUT3NUAJVDS5BP7ZE3R3/graph.json","fetch_events":"https://pith.science/api/pith-number/CZATSXJUT3NUAJVDS5BP7ZE3R3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CZATSXJUT3NUAJVDS5BP7ZE3R3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CZATSXJUT3NUAJVDS5BP7ZE3R3/action/storage_attestation","attest_author":"https://pith.science/pith/CZATSXJUT3NUAJVDS5BP7ZE3R3/action/author_attestation","sign_citation":"https://pith.science/pith/CZATSXJUT3NUAJVDS5BP7ZE3R3/action/citation_signature","submit_replication":"https://pith.science/pith/CZATSXJUT3NUAJVDS5BP7ZE3R3/action/replication_record"}},"created_at":"2026-07-05T10:44:32.314291+00:00","updated_at":"2026-07-05T10:44:32.314291+00:00"}