{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PPA2S7JNYF2PZTOE6WGQ2QAMF2","short_pith_number":"pith:PPA2S7JN","schema_version":"1.0","canonical_sha256":"7bc1a97d2dc174fccdc4f58d0d400c2ea928df9d1b65ef288a4752e610220a91","source":{"kind":"arxiv","id":"2606.07723","version":1},"attestation_state":"computed","paper":{"title":"VoLo: A Physical Orchestrator for Open-Vocabulary Long-Horizon Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Alex Zook, Chan Hee Song, Erwin Coumans, Faisal Ladhak, Hugo Hadfield, Jonathan Tremblay, Mikaela Angelina Uy, Qing Qu, Siyi Chen, Stan Birchfield, Valts Blukis, Xuning Yang","submitted_at":"2026-06-05T16:21:27Z","abstract_excerpt":"Open-vocabulary long-horizon manipulation requires robots to reason over flexible instructions and complex multi-object scenes while adaptively planning, executing, monitoring, and recovering from failures. We address these demands with a closed agent loop in which a VLM orchestrates heterogeneous robot capabilities as interruptible tools. Unlike in virtual AI agents, the timing of decisions, actions and tool calls is important in a physical world that does not pause for reasoning. We refer to this setting as Physical Orchestration, and propose VoLoAgent, a VLM that plans, monitors, and recove"},"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":"2606.07723","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-05T16:21:27Z","cross_cats_sorted":[],"title_canon_sha256":"33c3eb4446fd3b1372cb65f3bf83d7fa63c8264be0ebcfc3575ac5f46571bdc3","abstract_canon_sha256":"72ec33970f0f939c1415f1bb52a7a2e408b9d77f282deab1801b180016fe4363"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:04:50.363653Z","signature_b64":"/KyZRsHOtB/xRo85z84jXO49iU3F7hfuBXdzdwcRWk59h3DxdaIbkSsJRcyWjFNcN1uEBuXok7y7FcYtcLKwCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bc1a97d2dc174fccdc4f58d0d400c2ea928df9d1b65ef288a4752e610220a91","last_reissued_at":"2026-06-09T01:04:50.363240Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:04:50.363240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VoLo: A Physical Orchestrator for Open-Vocabulary Long-Horizon Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Alex Zook, Chan Hee Song, Erwin Coumans, Faisal Ladhak, Hugo Hadfield, Jonathan Tremblay, Mikaela Angelina Uy, Qing Qu, Siyi Chen, Stan Birchfield, Valts Blukis, Xuning Yang","submitted_at":"2026-06-05T16:21:27Z","abstract_excerpt":"Open-vocabulary long-horizon manipulation requires robots to reason over flexible instructions and complex multi-object scenes while adaptively planning, executing, monitoring, and recovering from failures. We address these demands with a closed agent loop in which a VLM orchestrates heterogeneous robot capabilities as interruptible tools. Unlike in virtual AI agents, the timing of decisions, actions and tool calls is important in a physical world that does not pause for reasoning. We refer to this setting as Physical Orchestration, and propose VoLoAgent, a VLM that plans, monitors, and recove"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07723","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/2606.07723/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":"2606.07723","created_at":"2026-06-09T01:04:50.363298+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07723v1","created_at":"2026-06-09T01:04:50.363298+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07723","created_at":"2026-06-09T01:04:50.363298+00:00"},{"alias_kind":"pith_short_12","alias_value":"PPA2S7JNYF2P","created_at":"2026-06-09T01:04:50.363298+00:00"},{"alias_kind":"pith_short_16","alias_value":"PPA2S7JNYF2PZTOE","created_at":"2026-06-09T01:04:50.363298+00:00"},{"alias_kind":"pith_short_8","alias_value":"PPA2S7JN","created_at":"2026-06-09T01:04:50.363298+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/PPA2S7JNYF2PZTOE6WGQ2QAMF2","json":"https://pith.science/pith/PPA2S7JNYF2PZTOE6WGQ2QAMF2.json","graph_json":"https://pith.science/api/pith-number/PPA2S7JNYF2PZTOE6WGQ2QAMF2/graph.json","events_json":"https://pith.science/api/pith-number/PPA2S7JNYF2PZTOE6WGQ2QAMF2/events.json","paper":"https://pith.science/paper/PPA2S7JN"},"agent_actions":{"view_html":"https://pith.science/pith/PPA2S7JNYF2PZTOE6WGQ2QAMF2","download_json":"https://pith.science/pith/PPA2S7JNYF2PZTOE6WGQ2QAMF2.json","view_paper":"https://pith.science/paper/PPA2S7JN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07723&json=true","fetch_graph":"https://pith.science/api/pith-number/PPA2S7JNYF2PZTOE6WGQ2QAMF2/graph.json","fetch_events":"https://pith.science/api/pith-number/PPA2S7JNYF2PZTOE6WGQ2QAMF2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PPA2S7JNYF2PZTOE6WGQ2QAMF2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PPA2S7JNYF2PZTOE6WGQ2QAMF2/action/storage_attestation","attest_author":"https://pith.science/pith/PPA2S7JNYF2PZTOE6WGQ2QAMF2/action/author_attestation","sign_citation":"https://pith.science/pith/PPA2S7JNYF2PZTOE6WGQ2QAMF2/action/citation_signature","submit_replication":"https://pith.science/pith/PPA2S7JNYF2PZTOE6WGQ2QAMF2/action/replication_record"}},"created_at":"2026-06-09T01:04:50.363298+00:00","updated_at":"2026-06-09T01:04:50.363298+00:00"}