{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:X6T6AVYO46UFIQDSLSPZ2TIC2V","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"27e8b8636337ee755ec953a94d2bcaebe127394ccaaa5c274c55918b025f50b9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-05T02:00:53Z","title_canon_sha256":"9befc34ffa2256212dc5daef1ea902d29959e5f8f0e5857b4945031b9120638d"},"schema_version":"1.0","source":{"id":"2603.04727","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.04727","created_at":"2026-05-20T00:05:42Z"},{"alias_kind":"arxiv_version","alias_value":"2603.04727v2","created_at":"2026-05-20T00:05:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.04727","created_at":"2026-05-20T00:05:42Z"},{"alias_kind":"pith_short_12","alias_value":"X6T6AVYO46UF","created_at":"2026-05-20T00:05:42Z"},{"alias_kind":"pith_short_16","alias_value":"X6T6AVYO46UFIQDS","created_at":"2026-05-20T00:05:42Z"},{"alias_kind":"pith_short_8","alias_value":"X6T6AVYO","created_at":"2026-05-20T00:05:42Z"}],"graph_snapshots":[{"event_id":"sha256:33efcf8a47dbf3835af7ba7710d50697d1753bfab09cac38fbad87c8964ca028","target":"graph","created_at":"2026-05-20T00:05:42Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2603.04727/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) have demonstrated impressive general competence in video understanding, yet their reliability for real-world Video Anomaly Detection (VAD) remains largely unexplored. Unlike conventional pipelines relying on reconstruction or pose-based cues, MLLMs enable a paradigm shift: treating anomaly detection as a language-guided reasoning task. In this work, we systematically evaluate state-of-the-art MLLMs on the ShanghaiTech and CHAD benchmarks by reformulating VAD as a binary classification task under weak temporal supervision. We investigate how prompt speci","authors_text":"Armin Danesh Pazho, Hamed Tabkhi, Narges Rashvand, Shanle Yao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-05T02:00:53Z","title":"Are Multimodal LLMs Ready for Surveillance? A Reality Check on Zero-Shot Anomaly Detection in the Wild"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.04727","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:66753c8d6c11495b4a33517839d55a12c2c8f4d9754581f3cae852a382e08f84","target":"record","created_at":"2026-05-20T00:05:42Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"27e8b8636337ee755ec953a94d2bcaebe127394ccaaa5c274c55918b025f50b9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-05T02:00:53Z","title_canon_sha256":"9befc34ffa2256212dc5daef1ea902d29959e5f8f0e5857b4945031b9120638d"},"schema_version":"1.0","source":{"id":"2603.04727","kind":"arxiv","version":2}},"canonical_sha256":"bfa7e0570ee7a85440725c9f9d4d02d55e08c21bfddd379becb0553626bf7d34","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bfa7e0570ee7a85440725c9f9d4d02d55e08c21bfddd379becb0553626bf7d34","first_computed_at":"2026-05-20T00:05:42.787635Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:05:42.787635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VrzjjBzV1UcF/Ww8Rz8ZZhdCfxcxb9mjVLOoyc8hg89cwRE7UaxdYYM+JUJ91B4gSAThNR+8NGiWw4w5xKD5DA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:05:42.788135Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.04727","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:66753c8d6c11495b4a33517839d55a12c2c8f4d9754581f3cae852a382e08f84","sha256:33efcf8a47dbf3835af7ba7710d50697d1753bfab09cac38fbad87c8964ca028"],"state_sha256":"62118b432dfcd2a2c4727fd150869e6ff5d6c1a7b1caa4f59a51435ffbb4077d"}