{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4CXTBTJ4TNN5FREDAZL4D3WVVT","short_pith_number":"pith:4CXTBTJ4","schema_version":"1.0","canonical_sha256":"e0af30cd3c9b5bd2c4830657c1eed5acf2d441ac7ebdae266bca6fc99d8ebb56","source":{"kind":"arxiv","id":"2608.08219","version":1},"attestation_state":"computed","paper":{"title":"VTO: Visual Tool Orchestration for Video Anomaly Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Mengshi Qi, Rui Wang, Xianling Zhang, Yeteng Wu","submitted_at":"2026-08-08T16:28:36Z","abstract_excerpt":"Video anomaly detection (VAD) is a critical yet challenging task due to the complex and diverse nature of real-world scenarios. Traditional deep learning approaches are fundamentally limited by poor generalization across diverse scenarios. While multimodal agents offer a promising tool-learning paradigm for VAD, current systems relying on supervised fine-tuning struggle with complex orchestration, and standard reinforcement learning often causes premature termination due to coarse-grained outcome rewards. To address these challenges, we propose VTO, a process-supervised reinforcement learning "},"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":"2608.08219","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-08T16:28:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"07a0407dff778e308e464f154f605760c068cf182eab5188ba091947903fb5cc","abstract_canon_sha256":"69a0051a9712405ea58d838eab626af8f94eed2b0bf3f14dcd38854b891b4089"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T01:22:01.598588Z","signature_b64":"KECbskZeVUtRBmVxNETFCxQIVy3wzaodiXKPtoEF90UJZ540C3HSjDawQGFyQ1z7Z7g6oA5oYqUyMle1CnhOBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0af30cd3c9b5bd2c4830657c1eed5acf2d441ac7ebdae266bca6fc99d8ebb56","last_reissued_at":"2026-08-11T01:22:01.594620Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T01:22:01.594620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VTO: Visual Tool Orchestration for Video Anomaly Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Mengshi Qi, Rui Wang, Xianling Zhang, Yeteng Wu","submitted_at":"2026-08-08T16:28:36Z","abstract_excerpt":"Video anomaly detection (VAD) is a critical yet challenging task due to the complex and diverse nature of real-world scenarios. Traditional deep learning approaches are fundamentally limited by poor generalization across diverse scenarios. While multimodal agents offer a promising tool-learning paradigm for VAD, current systems relying on supervised fine-tuning struggle with complex orchestration, and standard reinforcement learning often causes premature termination due to coarse-grained outcome rewards. To address these challenges, we propose VTO, a process-supervised reinforcement learning "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08219","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/2608.08219/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":"2608.08219","created_at":"2026-08-11T01:22:01.595699+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.08219v1","created_at":"2026-08-11T01:22:01.595699+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08219","created_at":"2026-08-11T01:22:01.595699+00:00"},{"alias_kind":"pith_short_12","alias_value":"4CXTBTJ4TNN5","created_at":"2026-08-11T01:22:01.595699+00:00"},{"alias_kind":"pith_short_16","alias_value":"4CXTBTJ4TNN5FRED","created_at":"2026-08-11T01:22:01.595699+00:00"},{"alias_kind":"pith_short_8","alias_value":"4CXTBTJ4","created_at":"2026-08-11T01:22:01.595699+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4CXTBTJ4TNN5FREDAZL4D3WVVT","json":"https://pith.science/pith/4CXTBTJ4TNN5FREDAZL4D3WVVT.json","graph_json":"https://pith.science/api/pith-number/4CXTBTJ4TNN5FREDAZL4D3WVVT/graph.json","events_json":"https://pith.science/api/pith-number/4CXTBTJ4TNN5FREDAZL4D3WVVT/events.json","paper":"https://pith.science/paper/4CXTBTJ4"},"agent_actions":{"view_html":"https://pith.science/pith/4CXTBTJ4TNN5FREDAZL4D3WVVT","download_json":"https://pith.science/pith/4CXTBTJ4TNN5FREDAZL4D3WVVT.json","view_paper":"https://pith.science/paper/4CXTBTJ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.08219&json=true","fetch_graph":"https://pith.science/api/pith-number/4CXTBTJ4TNN5FREDAZL4D3WVVT/graph.json","fetch_events":"https://pith.science/api/pith-number/4CXTBTJ4TNN5FREDAZL4D3WVVT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4CXTBTJ4TNN5FREDAZL4D3WVVT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4CXTBTJ4TNN5FREDAZL4D3WVVT/action/storage_attestation","attest_author":"https://pith.science/pith/4CXTBTJ4TNN5FREDAZL4D3WVVT/action/author_attestation","sign_citation":"https://pith.science/pith/4CXTBTJ4TNN5FREDAZL4D3WVVT/action/citation_signature","submit_replication":"https://pith.science/pith/4CXTBTJ4TNN5FREDAZL4D3WVVT/action/replication_record"}},"created_at":"2026-08-11T01:22:01.595699+00:00","updated_at":"2026-08-11T01:22:01.595699+00:00"}