{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PEBP4TFO5XRL37FWVRS5A2Q35Y","short_pith_number":"pith:PEBP4TFO","schema_version":"1.0","canonical_sha256":"7902fe4caeede2bdfcb6ac65d06a1bee3be3190dc6b428d4b303493b606df8d6","source":{"kind":"arxiv","id":"2510.18034","version":3},"attestation_state":"computed","paper":{"title":"Can VLMs Unlock Semantic Anomaly Detection? A Framework for Structured Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Structured reasoning framework lets VLMs detect semantic anomalies in driving scenes with 18.5 percent higher recall.","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"David Pop, Johannes Betz, Mattia Piccinini, Roberto Brusnicki, Yuan Gao","submitted_at":"2025-10-20T19:14:29Z","abstract_excerpt":"Autonomous driving systems remain critically vulnerable to the long-tail of rare, out-of-distribution semantic anomalies. While VLMs have emerged as promising tools for perception, their application in anomaly detection remains largely restricted to prompting proprietary models - limiting reliability, reproducibility, and deployment feasibility. To address this gap, we introduce SAVANT (Semantic Anomaly Verification/Analysis Toolkit), a novel model-agnostic reasoning framework that reformulates anomaly detection as a layered semantic consistency verification. By applying SAVANT's two-phase pip"},"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":true},"canonical_record":{"source":{"id":"2510.18034","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-10-20T19:14:29Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"aa1b55cc34fcf2b2d0ea87381c2ee6c38355f7435c3639f9b8b6cb07a037c177","abstract_canon_sha256":"593f05e84dc7ad1f8d210d0208c7e01fd913cc1d269b611aad76b7acca25ea21"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:05:11.176306Z","signature_b64":"fKIjdb15PYV3eV5EhYl4CDt6FOTldCogDrFwF53tzZZ9Dd3/zV4IeqHXS0tpUtwD1pshCDiifvbH9Dkk8eZZAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7902fe4caeede2bdfcb6ac65d06a1bee3be3190dc6b428d4b303493b606df8d6","last_reissued_at":"2026-05-21T01:05:11.175417Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:05:11.175417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can VLMs Unlock Semantic Anomaly Detection? A Framework for Structured Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Structured reasoning framework lets VLMs detect semantic anomalies in driving scenes with 18.5 percent higher recall.","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"David Pop, Johannes Betz, Mattia Piccinini, Roberto Brusnicki, Yuan Gao","submitted_at":"2025-10-20T19:14:29Z","abstract_excerpt":"Autonomous driving systems remain critically vulnerable to the long-tail of rare, out-of-distribution semantic anomalies. While VLMs have emerged as promising tools for perception, their application in anomaly detection remains largely restricted to prompting proprietary models - limiting reliability, reproducibility, and deployment feasibility. To address this gap, we introduce SAVANT (Semantic Anomaly Verification/Analysis Toolkit), a novel model-agnostic reasoning framework that reformulates anomaly detection as a layered semantic consistency verification. By applying SAVANT's two-phase pip"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Applying SAVANT improves VLM's absolute recall by approximately 18.5% compared to prompting baselines, and leveraging the best proprietary model within the framework enables automatic labeling of around 10,000 images to fine-tune a 7B open-source model achieving 90.8% recall and 93.8% accuracy.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The evaluation uses a 'balanced set of real-world driving scenarios' whose selection criteria and representativeness of long-tail anomalies are not specified, which is required to support that the reported recall gains are due to the structured reasoning pipeline rather than dataset construction.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SAVANT boosts VLM recall for semantic anomaly detection in driving images by 18.5% via structured reasoning and enables fine-tuning a 7B open model to 90.8% recall and 93.8% accuracy.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Structured reasoning framework lets VLMs detect semantic anomalies in driving scenes with 18.5 percent higher recall.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e065cd65ec00f8368f1fb3e237ce517ca0d19694fded47e8b3900325c085e044"},"source":{"id":"2510.18034","kind":"arxiv","version":3},"verdict":{"id":"c52c4db2-f984-44e3-963a-df5747e99981","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-18T05:43:04.751411Z","strongest_claim":"Applying SAVANT improves VLM's absolute recall by approximately 18.5% compared to prompting baselines, and leveraging the best proprietary model within the framework enables automatic labeling of around 10,000 images to fine-tune a 7B open-source model achieving 90.8% recall and 93.8% accuracy.","one_line_summary":"SAVANT boosts VLM recall for semantic anomaly detection in driving images by 18.5% via structured reasoning and enables fine-tuning a 7B open model to 90.8% recall and 93.8% accuracy.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The evaluation uses a 'balanced set of real-world driving scenarios' whose selection criteria and representativeness of long-tail anomalies are not specified, which is required to support that the reported recall gains are due to the structured reasoning pipeline rather than dataset construction.","pith_extraction_headline":"Structured reasoning framework lets VLMs detect semantic anomalies in driving scenes with 18.5 percent higher recall."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2510.18034/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":2,"snapshot_sha256":"2fceb3457930879b5343fa37b2737a3e105095b36484eb43a163ae2953f3523f"},"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":"2510.18034","created_at":"2026-05-21T01:05:11.175544+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.18034v3","created_at":"2026-05-21T01:05:11.175544+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.18034","created_at":"2026-05-21T01:05:11.175544+00:00"},{"alias_kind":"pith_short_12","alias_value":"PEBP4TFO5XRL","created_at":"2026-05-21T01:05:11.175544+00:00"},{"alias_kind":"pith_short_16","alias_value":"PEBP4TFO5XRL37FW","created_at":"2026-05-21T01:05:11.175544+00:00"},{"alias_kind":"pith_short_8","alias_value":"PEBP4TFO","created_at":"2026-05-21T01:05:11.175544+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PEBP4TFO5XRL37FWVRS5A2Q35Y","json":"https://pith.science/pith/PEBP4TFO5XRL37FWVRS5A2Q35Y.json","graph_json":"https://pith.science/api/pith-number/PEBP4TFO5XRL37FWVRS5A2Q35Y/graph.json","events_json":"https://pith.science/api/pith-number/PEBP4TFO5XRL37FWVRS5A2Q35Y/events.json","paper":"https://pith.science/paper/PEBP4TFO"},"agent_actions":{"view_html":"https://pith.science/pith/PEBP4TFO5XRL37FWVRS5A2Q35Y","download_json":"https://pith.science/pith/PEBP4TFO5XRL37FWVRS5A2Q35Y.json","view_paper":"https://pith.science/paper/PEBP4TFO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.18034&json=true","fetch_graph":"https://pith.science/api/pith-number/PEBP4TFO5XRL37FWVRS5A2Q35Y/graph.json","fetch_events":"https://pith.science/api/pith-number/PEBP4TFO5XRL37FWVRS5A2Q35Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PEBP4TFO5XRL37FWVRS5A2Q35Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PEBP4TFO5XRL37FWVRS5A2Q35Y/action/storage_attestation","attest_author":"https://pith.science/pith/PEBP4TFO5XRL37FWVRS5A2Q35Y/action/author_attestation","sign_citation":"https://pith.science/pith/PEBP4TFO5XRL37FWVRS5A2Q35Y/action/citation_signature","submit_replication":"https://pith.science/pith/PEBP4TFO5XRL37FWVRS5A2Q35Y/action/replication_record"}},"created_at":"2026-05-21T01:05:11.175544+00:00","updated_at":"2026-05-21T01:05:11.175544+00:00"}