{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HV4DE7724GXOBHSCOGD4DSLCJY","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":"75c87d0353aa617513a8e230238e6ff17f833ca768c758642b6ec35391fa8cce","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T17:59:17Z","title_canon_sha256":"6d4fa7d73198168034b8420872212384d1dbd6c59a15dcede1989b4626a33ee0"},"schema_version":"1.0","source":{"id":"2505.20289","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20289","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20289v2","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20289","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"pith_short_12","alias_value":"HV4DE7724GXO","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"pith_short_16","alias_value":"HV4DE7724GXOBHSC","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"pith_short_8","alias_value":"HV4DE772","created_at":"2026-07-05T11:39:54Z"}],"graph_snapshots":[{"event_id":"sha256:77fc4a7f0dd6dda3262aab0b655cc9d7d1147196e2c5b10b4f0b784b19823aa0","target":"graph","created_at":"2026-07-05T11:39:54Z","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/2505.20289/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce VisTA, a new reinforcement learning framework that empowers visual agents to dynamically explore, select, and combine tools from a diverse library based on empirical performance. Existing methods for tool-augmented reasoning either rely on training-free prompting or large-scale fine-tuning; both lack active tool exploration and typically assume limited tool diversity, and fine-tuning methods additionally demand extensive human supervision. In contrast, VisTA leverages end-to-end reinforcement learning to iteratively refine sophisticated, query-specific tool selection strategies, u","authors_text":"Anirudh Sundara Rajan, Haohan Wang, Junjie Hu, Wen Xiao, Yong Jae Lee, Yuyang Ji, Zefan Cai, Zeyi Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T17:59:17Z","title":"VisualToolAgent (VisTA): A Reinforcement Learning Framework for Visual Tool Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20289","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:d897e272891cc859829ce2a1b70ef83aad94f500bc01448f8a322028dabbce03","target":"record","created_at":"2026-07-05T11:39:54Z","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":"75c87d0353aa617513a8e230238e6ff17f833ca768c758642b6ec35391fa8cce","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T17:59:17Z","title_canon_sha256":"6d4fa7d73198168034b8420872212384d1dbd6c59a15dcede1989b4626a33ee0"},"schema_version":"1.0","source":{"id":"2505.20289","kind":"arxiv","version":2}},"canonical_sha256":"3d78327ffae1aee09e427187c1c9624e0938aedb42163f57facc5f613077e830","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d78327ffae1aee09e427187c1c9624e0938aedb42163f57facc5f613077e830","first_computed_at":"2026-07-05T11:39:54.367857Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:39:54.367857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6xLQU2ZtojAZa2UB7HqaVPCHSgxclUViCwn0CiT6zq9KhxHN5uFLGrEMM7Kph+ly/RvESGtkUHFzASY4QjmPBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:39:54.368398Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.20289","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d897e272891cc859829ce2a1b70ef83aad94f500bc01448f8a322028dabbce03","sha256:77fc4a7f0dd6dda3262aab0b655cc9d7d1147196e2c5b10b4f0b784b19823aa0"],"state_sha256":"a252f80bb2c25f837c3bdd150f2395f940edf634f8f558f7a0ce37c5e5d54d9a"}