{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YCIZILVCKW6XYMG6VDUOUUGBA4","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":"d7baa5f5cfa0572cb65e763d04e686e8cb1defcf8570d8e5fbcc0be56303b428","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T04:52:22Z","title_canon_sha256":"66a594e4f2c41aaf3897b91e7c5a4dfd06d9bd2899b2c163078c3229c516f6e8"},"schema_version":"1.0","source":{"id":"2606.20728","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.20728","created_at":"2026-06-23T00:11:54Z"},{"alias_kind":"arxiv_version","alias_value":"2606.20728v1","created_at":"2026-06-23T00:11:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20728","created_at":"2026-06-23T00:11:54Z"},{"alias_kind":"pith_short_12","alias_value":"YCIZILVCKW6X","created_at":"2026-06-23T00:11:54Z"},{"alias_kind":"pith_short_16","alias_value":"YCIZILVCKW6XYMG6","created_at":"2026-06-23T00:11:54Z"},{"alias_kind":"pith_short_8","alias_value":"YCIZILVC","created_at":"2026-06-23T00:11:54Z"}],"graph_snapshots":[{"event_id":"sha256:737f461ae9e027e7600d348c86dac50dd30d8009b6e066bbf43e0f59e414d6c0","target":"graph","created_at":"2026-06-23T00:11:54Z","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/2606.20728/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision foundation tools such as open-vocabulary detectors, segmentation models, and post-processing operators are powerful building blocks for computer vision, but their effectiveness depends heavily on how they are orchestrated: which tools are used, in what order, with what parameters, and under what visual conditions. Existing visual-programming agents typically generate a fixed solution pipeline, making them brittle under dense objects, occlusion, small targets, and domain shift. We introduce VTOS (Vision Tools Orchestration Search), a framework for adaptive visual tool orchestration throu","authors_text":"Jinchao Ge, Lei Wang, Lingqiao Liu, Shuwen Zhao","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T04:52:22Z","title":"VTOS: Learning to Orchestrate Vision Tools by Co-Searching Solutions and Observers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20728","kind":"arxiv","version":1},"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:fbd644b6cb27d8d64d87f7051a8d27abfd161cf9cb2b4d202cc23a17b60a47c6","target":"record","created_at":"2026-06-23T00:11:54Z","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":"d7baa5f5cfa0572cb65e763d04e686e8cb1defcf8570d8e5fbcc0be56303b428","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T04:52:22Z","title_canon_sha256":"66a594e4f2c41aaf3897b91e7c5a4dfd06d9bd2899b2c163078c3229c516f6e8"},"schema_version":"1.0","source":{"id":"2606.20728","kind":"arxiv","version":1}},"canonical_sha256":"c091942ea255bd7c30dea8e8ea50c1070de68b3b1be043ff5ad26a10986a335e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c091942ea255bd7c30dea8e8ea50c1070de68b3b1be043ff5ad26a10986a335e","first_computed_at":"2026-06-23T00:11:54.911777Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T00:11:54.911777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hQAJZxtXhwlsIHGYqCAMV+bCsrwXVnTQ1PQvLjtFGR04TkW33L62K+PJkWqvYXCMF3sraIaiH5AO96R/lMlJDw==","signature_status":"signed_v1","signed_at":"2026-06-23T00:11:54.912171Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.20728","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fbd644b6cb27d8d64d87f7051a8d27abfd161cf9cb2b4d202cc23a17b60a47c6","sha256:737f461ae9e027e7600d348c86dac50dd30d8009b6e066bbf43e0f59e414d6c0"],"state_sha256":"88dd7e3f93a877c3967afacbf587675726b7b3b5442d46992f4781cd4675703d"}