{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QVSGI4HQA2UR34I2Y3FJPQOGSW","short_pith_number":"pith:QVSGI4HQ","schema_version":"1.0","canonical_sha256":"85646470f006a91df11ac6ca97c1c695892622c06cd842b26d8f83e37500a3da","source":{"kind":"arxiv","id":"2606.19340","version":1},"attestation_state":"computed","paper":{"title":"Zero-Shot Long-Horizon Dexterous Manipulation via Multi-View 3D-Grounded VLM Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Hanbyul Joo, Jisoo Kim, Junyoung Lee, Mingi Choi, Sangwon Baik, Sungjoo Kim, Taeksoo Kim","submitted_at":"2026-06-17T17:59:56Z","abstract_excerpt":"We present a zero-shot framework for long-horizon dexterous manipulation that grounds language instructions into executable 3D task plans from calibrated multi-view RGB images. Rather than training an end-to-end policy, our system uses a vision-language model (VLM) to produce reference-frame task grounding and primitive-level 2D keypoints, then lifts them into 3D via multi-view fusion. This lifting combines triangulation of view-wise VLM groundings with reference-view ray voting, which searches along a semantic camera ray for geometrically consistent candidates across neighboring views. The re"},"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":"2606.19340","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-17T17:59:56Z","cross_cats_sorted":[],"title_canon_sha256":"605a7e881afee7f5812c0299498f6a094d48d8eb65528a75f38cdb6b9666c769","abstract_canon_sha256":"254fdf55c3a52ea7667802fc0d56505901df072d3dbee22ce5183961e08f1039"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:11.641447Z","signature_b64":"PDs84wMGBdVbID3UavNkyshPfk61BgSc1XQvxDOxOKgYUfoXXGWKkooT9Yay1iGN02j5xk91gi8IcSA2AbuiAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85646470f006a91df11ac6ca97c1c695892622c06cd842b26d8f83e37500a3da","last_reissued_at":"2026-06-19T16:12:11.641105Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:11.641105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Long-Horizon Dexterous Manipulation via Multi-View 3D-Grounded VLM Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Hanbyul Joo, Jisoo Kim, Junyoung Lee, Mingi Choi, Sangwon Baik, Sungjoo Kim, Taeksoo Kim","submitted_at":"2026-06-17T17:59:56Z","abstract_excerpt":"We present a zero-shot framework for long-horizon dexterous manipulation that grounds language instructions into executable 3D task plans from calibrated multi-view RGB images. Rather than training an end-to-end policy, our system uses a vision-language model (VLM) to produce reference-frame task grounding and primitive-level 2D keypoints, then lifts them into 3D via multi-view fusion. This lifting combines triangulation of view-wise VLM groundings with reference-view ray voting, which searches along a semantic camera ray for geometrically consistent candidates across neighboring views. The re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19340","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/2606.19340/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":"2606.19340","created_at":"2026-06-19T16:12:11.641157+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.19340v1","created_at":"2026-06-19T16:12:11.641157+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19340","created_at":"2026-06-19T16:12:11.641157+00:00"},{"alias_kind":"pith_short_12","alias_value":"QVSGI4HQA2UR","created_at":"2026-06-19T16:12:11.641157+00:00"},{"alias_kind":"pith_short_16","alias_value":"QVSGI4HQA2UR34I2","created_at":"2026-06-19T16:12:11.641157+00:00"},{"alias_kind":"pith_short_8","alias_value":"QVSGI4HQ","created_at":"2026-06-19T16:12:11.641157+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/QVSGI4HQA2UR34I2Y3FJPQOGSW","json":"https://pith.science/pith/QVSGI4HQA2UR34I2Y3FJPQOGSW.json","graph_json":"https://pith.science/api/pith-number/QVSGI4HQA2UR34I2Y3FJPQOGSW/graph.json","events_json":"https://pith.science/api/pith-number/QVSGI4HQA2UR34I2Y3FJPQOGSW/events.json","paper":"https://pith.science/paper/QVSGI4HQ"},"agent_actions":{"view_html":"https://pith.science/pith/QVSGI4HQA2UR34I2Y3FJPQOGSW","download_json":"https://pith.science/pith/QVSGI4HQA2UR34I2Y3FJPQOGSW.json","view_paper":"https://pith.science/paper/QVSGI4HQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.19340&json=true","fetch_graph":"https://pith.science/api/pith-number/QVSGI4HQA2UR34I2Y3FJPQOGSW/graph.json","fetch_events":"https://pith.science/api/pith-number/QVSGI4HQA2UR34I2Y3FJPQOGSW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QVSGI4HQA2UR34I2Y3FJPQOGSW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QVSGI4HQA2UR34I2Y3FJPQOGSW/action/storage_attestation","attest_author":"https://pith.science/pith/QVSGI4HQA2UR34I2Y3FJPQOGSW/action/author_attestation","sign_citation":"https://pith.science/pith/QVSGI4HQA2UR34I2Y3FJPQOGSW/action/citation_signature","submit_replication":"https://pith.science/pith/QVSGI4HQA2UR34I2Y3FJPQOGSW/action/replication_record"}},"created_at":"2026-06-19T16:12:11.641157+00:00","updated_at":"2026-06-19T16:12:11.641157+00:00"}