{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LFKECIKKSMYDI4AUVXTDGIDDDG","short_pith_number":"pith:LFKECIKK","schema_version":"1.0","canonical_sha256":"595441214a9330347014ade633206319b4cfd2b0cf2c7c4a6894fe7901343c00","source":{"kind":"arxiv","id":"2406.06370","version":2},"attestation_state":"computed","paper":{"title":"UMAD: Unsupervised Mask-Level Anomaly Detection for Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Daniel Bogdoll, J. Marius Z\\\"ollner, No\\\"el Ollick, Svetlana Pavlitska, Tim Joseph","submitted_at":"2024-06-10T15:32:16Z","abstract_excerpt":"Dealing with atypical traffic scenarios remains a challenging task in autonomous driving. However, most anomaly detection approaches cannot be trained on raw sensor data but require exposure to outlier data and powerful semantic segmentation models trained in a supervised fashion. This limits the representation of normality to labeled data, which does not scale well. In this work, we revisit unsupervised anomaly detection and present UMAD, leveraging generative world models and unsupervised image segmentation. Our method outperforms state-of-the-art unsupervised anomaly detection."},"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":"2406.06370","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-10T15:32:16Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"a05703c567400551fa49fa97c998cfc871bec2ef002ee6c886bf3571fd6c5a3d","abstract_canon_sha256":"6e2002ee3f5309e84426da1c999aa892c50f5450b21f27869722562e68f49ab0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:53.631061Z","signature_b64":"Og3RC8XWO1uY0ZUyXkaD7pJaw0gtllIhdyqVBPVFrGycQHIU/GdzwzdoLBUgYO+XlJtGKwy7JrPhege/bkBMBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"595441214a9330347014ade633206319b4cfd2b0cf2c7c4a6894fe7901343c00","last_reissued_at":"2026-07-05T09:13:53.630570Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:53.630570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UMAD: Unsupervised Mask-Level Anomaly Detection for Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Daniel Bogdoll, J. Marius Z\\\"ollner, No\\\"el Ollick, Svetlana Pavlitska, Tim Joseph","submitted_at":"2024-06-10T15:32:16Z","abstract_excerpt":"Dealing with atypical traffic scenarios remains a challenging task in autonomous driving. However, most anomaly detection approaches cannot be trained on raw sensor data but require exposure to outlier data and powerful semantic segmentation models trained in a supervised fashion. This limits the representation of normality to labeled data, which does not scale well. In this work, we revisit unsupervised anomaly detection and present UMAD, leveraging generative world models and unsupervised image segmentation. Our method outperforms state-of-the-art unsupervised anomaly detection."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06370","kind":"arxiv","version":2},"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/2406.06370/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":"2406.06370","created_at":"2026-07-05T09:13:53.630629+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.06370v2","created_at":"2026-07-05T09:13:53.630629+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06370","created_at":"2026-07-05T09:13:53.630629+00:00"},{"alias_kind":"pith_short_12","alias_value":"LFKECIKKSMYD","created_at":"2026-07-05T09:13:53.630629+00:00"},{"alias_kind":"pith_short_16","alias_value":"LFKECIKKSMYDI4AU","created_at":"2026-07-05T09:13:53.630629+00:00"},{"alias_kind":"pith_short_8","alias_value":"LFKECIKK","created_at":"2026-07-05T09:13:53.630629+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.04776","citing_title":"NSF-HRPT: Neural Semantic Field meets Hierarchical Risk Perception Tree for Safety-Critical Scenario Assessment","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LFKECIKKSMYDI4AUVXTDGIDDDG","json":"https://pith.science/pith/LFKECIKKSMYDI4AUVXTDGIDDDG.json","graph_json":"https://pith.science/api/pith-number/LFKECIKKSMYDI4AUVXTDGIDDDG/graph.json","events_json":"https://pith.science/api/pith-number/LFKECIKKSMYDI4AUVXTDGIDDDG/events.json","paper":"https://pith.science/paper/LFKECIKK"},"agent_actions":{"view_html":"https://pith.science/pith/LFKECIKKSMYDI4AUVXTDGIDDDG","download_json":"https://pith.science/pith/LFKECIKKSMYDI4AUVXTDGIDDDG.json","view_paper":"https://pith.science/paper/LFKECIKK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.06370&json=true","fetch_graph":"https://pith.science/api/pith-number/LFKECIKKSMYDI4AUVXTDGIDDDG/graph.json","fetch_events":"https://pith.science/api/pith-number/LFKECIKKSMYDI4AUVXTDGIDDDG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LFKECIKKSMYDI4AUVXTDGIDDDG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LFKECIKKSMYDI4AUVXTDGIDDDG/action/storage_attestation","attest_author":"https://pith.science/pith/LFKECIKKSMYDI4AUVXTDGIDDDG/action/author_attestation","sign_citation":"https://pith.science/pith/LFKECIKKSMYDI4AUVXTDGIDDDG/action/citation_signature","submit_replication":"https://pith.science/pith/LFKECIKKSMYDI4AUVXTDGIDDDG/action/replication_record"}},"created_at":"2026-07-05T09:13:53.630629+00:00","updated_at":"2026-07-05T09:13:53.630629+00:00"}