{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZMUD7654HRBG52ZUP5XFSY2BBN","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":"b1718add8d88efea68bb2bb792747efcfee8e0b20f4fb8662470b6cc4bf4d48e","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-28T15:13:53Z","title_canon_sha256":"8c3a8f0c96552877f5d52406da942292322033e5f233b437978d033b3d6b1ae7"},"schema_version":"1.0","source":{"id":"2410.21113","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.21113","created_at":"2026-07-05T10:33:38Z"},{"alias_kind":"arxiv_version","alias_value":"2410.21113v2","created_at":"2026-07-05T10:33:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.21113","created_at":"2026-07-05T10:33:38Z"},{"alias_kind":"pith_short_12","alias_value":"ZMUD7654HRBG","created_at":"2026-07-05T10:33:38Z"},{"alias_kind":"pith_short_16","alias_value":"ZMUD7654HRBG52ZU","created_at":"2026-07-05T10:33:38Z"},{"alias_kind":"pith_short_8","alias_value":"ZMUD7654","created_at":"2026-07-05T10:33:38Z"}],"graph_snapshots":[{"event_id":"sha256:b72827ced25a1592d01db92554a75dbbc2599b2fc839ff68eed6bcfe902265c8","target":"graph","created_at":"2026-07-05T10:33:38Z","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/2410.21113/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The growing demand for surveillance in public spaces presents significant challenges due to the shortage of human resources. Current AI-based video surveillance systems heavily rely on core computer vision models that require extensive finetuning, which is particularly difficult in surveillance settings due to limited datasets and difficult setting (viewpoint, low quality, etc.). In this work, we propose leveraging Large Vision-Language Models (LVLMs), known for their strong zero and few-shot generalization, to tackle video understanding tasks in surveillance. Specifically, we explore VideoLLa","authors_text":"David Semedo, Joao Neves, Joao Pereira, Vasco Lopes","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-28T15:13:53Z","title":"Zero-Shot Action Recognition in Surveillance Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.21113","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":"sha256:724b3593484742bbf17f85363b7968be43e6a5032da3ae5771da741b4e92a4ab","target":"record","created_at":"2026-07-05T10:33:38Z","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":"b1718add8d88efea68bb2bb792747efcfee8e0b20f4fb8662470b6cc4bf4d48e","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-28T15:13:53Z","title_canon_sha256":"8c3a8f0c96552877f5d52406da942292322033e5f233b437978d033b3d6b1ae7"},"schema_version":"1.0","source":{"id":"2410.21113","kind":"arxiv","version":2}},"canonical_sha256":"cb283ffbbc3c426eeb347f6e5963410b61a5901e5800375365271b528ae90d02","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb283ffbbc3c426eeb347f6e5963410b61a5901e5800375365271b528ae90d02","first_computed_at":"2026-07-05T10:33:38.901580Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:33:38.901580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7LJzzuWGO9x+2B71cQ+9T7MyGC7RLdkJWB1tHPdQLwa49TsafWPv2o+R2utL28ebvZcgmosdbZa1R72xEq8ZDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:33:38.902187Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.21113","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:724b3593484742bbf17f85363b7968be43e6a5032da3ae5771da741b4e92a4ab","sha256:b72827ced25a1592d01db92554a75dbbc2599b2fc839ff68eed6bcfe902265c8"],"state_sha256":"935342a7c6cbbe75976318582293bd3a1d2d683d1866f86bd314eec8648a3df9"}