{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YCIZILVCKW6XYMG6VDUOUUGBA4","short_pith_number":"pith:YCIZILVC","schema_version":"1.0","canonical_sha256":"c091942ea255bd7c30dea8e8ea50c1070de68b3b1be043ff5ad26a10986a335e","source":{"kind":"arxiv","id":"2606.20728","version":1},"attestation_state":"computed","paper":{"title":"VTOS: Learning to Orchestrate Vision Tools by Co-Searching Solutions and Observers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Jinchao Ge, Lei Wang, Lingqiao Liu, Shuwen Zhao","submitted_at":"2026-06-17T04:52:22Z","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"},"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":"2606.20728","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T04:52:22Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"66a594e4f2c41aaf3897b91e7c5a4dfd06d9bd2899b2c163078c3229c516f6e8","abstract_canon_sha256":"d7baa5f5cfa0572cb65e763d04e686e8cb1defcf8570d8e5fbcc0be56303b428"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T00:11:54.912171Z","signature_b64":"hQAJZxtXhwlsIHGYqCAMV+bCsrwXVnTQ1PQvLjtFGR04TkW33L62K+PJkWqvYXCMF3sraIaiH5AO96R/lMlJDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c091942ea255bd7c30dea8e8ea50c1070de68b3b1be043ff5ad26a10986a335e","last_reissued_at":"2026-06-23T00:11:54.911777Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T00:11:54.911777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VTOS: Learning to Orchestrate Vision Tools by Co-Searching Solutions and Observers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Jinchao Ge, Lei Wang, Lingqiao Liu, Shuwen Zhao","submitted_at":"2026-06-17T04:52:22Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20728","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/2606.20728/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":"2606.20728","created_at":"2026-06-23T00:11:54.911835+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.20728v1","created_at":"2026-06-23T00:11:54.911835+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20728","created_at":"2026-06-23T00:11:54.911835+00:00"},{"alias_kind":"pith_short_12","alias_value":"YCIZILVCKW6X","created_at":"2026-06-23T00:11:54.911835+00:00"},{"alias_kind":"pith_short_16","alias_value":"YCIZILVCKW6XYMG6","created_at":"2026-06-23T00:11:54.911835+00:00"},{"alias_kind":"pith_short_8","alias_value":"YCIZILVC","created_at":"2026-06-23T00:11:54.911835+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/YCIZILVCKW6XYMG6VDUOUUGBA4","json":"https://pith.science/pith/YCIZILVCKW6XYMG6VDUOUUGBA4.json","graph_json":"https://pith.science/api/pith-number/YCIZILVCKW6XYMG6VDUOUUGBA4/graph.json","events_json":"https://pith.science/api/pith-number/YCIZILVCKW6XYMG6VDUOUUGBA4/events.json","paper":"https://pith.science/paper/YCIZILVC"},"agent_actions":{"view_html":"https://pith.science/pith/YCIZILVCKW6XYMG6VDUOUUGBA4","download_json":"https://pith.science/pith/YCIZILVCKW6XYMG6VDUOUUGBA4.json","view_paper":"https://pith.science/paper/YCIZILVC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.20728&json=true","fetch_graph":"https://pith.science/api/pith-number/YCIZILVCKW6XYMG6VDUOUUGBA4/graph.json","fetch_events":"https://pith.science/api/pith-number/YCIZILVCKW6XYMG6VDUOUUGBA4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YCIZILVCKW6XYMG6VDUOUUGBA4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YCIZILVCKW6XYMG6VDUOUUGBA4/action/storage_attestation","attest_author":"https://pith.science/pith/YCIZILVCKW6XYMG6VDUOUUGBA4/action/author_attestation","sign_citation":"https://pith.science/pith/YCIZILVCKW6XYMG6VDUOUUGBA4/action/citation_signature","submit_replication":"https://pith.science/pith/YCIZILVCKW6XYMG6VDUOUUGBA4/action/replication_record"}},"created_at":"2026-06-23T00:11:54.911835+00:00","updated_at":"2026-06-23T00:11:54.911835+00:00"}