{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Y5NEIOEVK2MBQ7I533BHFOKVNQ","short_pith_number":"pith:Y5NEIOEV","schema_version":"1.0","canonical_sha256":"c75a4438955698187d1ddec272b9556c022a8bf8841eb7a4d3080233a0bf99f5","source":{"kind":"arxiv","id":"2606.07107","version":1},"attestation_state":"computed","paper":{"title":"Coarse-to-Control: Action-Token Planning for Vision-Language-Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Hang Zhao, Jing Huo, Jingjing Gong, Jinhao Wu, Shiduo Zhang, Sixian Li, Siyin Wang, Xiaopeng Yu, Xipeng Qiu, Yang Gao, Yicheng Liu, Yu-Gang Jiang","submitted_at":"2026-06-05T10:01:37Z","abstract_excerpt":"Most vision-language-action (VLA) models map observations directly to actions without explicit intermediate planning, which limits performance on long-horizon tasks where early mistakes compound. We propose Coarse-to-Control, a plan-execute VLA that introduces planning natively in the action-token space. The key idea is to let the policy first predict a compact sequence of coarse action tokens that summarize the intended future trajectory, and then generate executable action tokens conditioned on this plan. Because both planning and execution share a unified discrete action vocabulary, the pla"},"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":"2606.07107","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-05T10:01:37Z","cross_cats_sorted":[],"title_canon_sha256":"1c49433d30fb2c2143c7252cea85691a0dd8338fcbbf233e455c60ef75682fef","abstract_canon_sha256":"25f8a5632fc7216d7087fa450e4aebba2b6b2a5633a0fdcf724b67d158a9e22c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:04:46.696707Z","signature_b64":"LdYFeJHGDM62UwBLNoM8JgNFMorP6yJi/ai+v/JmDs2cvo+Ti4gyRR999uxZrfdVUX+G12rTjzjcl/V96C2pAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c75a4438955698187d1ddec272b9556c022a8bf8841eb7a4d3080233a0bf99f5","last_reissued_at":"2026-06-08T01:04:46.695877Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:04:46.695877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Coarse-to-Control: Action-Token Planning for Vision-Language-Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Hang Zhao, Jing Huo, Jingjing Gong, Jinhao Wu, Shiduo Zhang, Sixian Li, Siyin Wang, Xiaopeng Yu, Xipeng Qiu, Yang Gao, Yicheng Liu, Yu-Gang Jiang","submitted_at":"2026-06-05T10:01:37Z","abstract_excerpt":"Most vision-language-action (VLA) models map observations directly to actions without explicit intermediate planning, which limits performance on long-horizon tasks where early mistakes compound. We propose Coarse-to-Control, a plan-execute VLA that introduces planning natively in the action-token space. The key idea is to let the policy first predict a compact sequence of coarse action tokens that summarize the intended future trajectory, and then generate executable action tokens conditioned on this plan. Because both planning and execution share a unified discrete action vocabulary, the pla"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07107","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/2606.07107/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":"2606.07107","created_at":"2026-06-08T01:04:46.696002+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07107v1","created_at":"2026-06-08T01:04:46.696002+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07107","created_at":"2026-06-08T01:04:46.696002+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y5NEIOEVK2MB","created_at":"2026-06-08T01:04:46.696002+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y5NEIOEVK2MBQ7I5","created_at":"2026-06-08T01:04:46.696002+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y5NEIOEV","created_at":"2026-06-08T01:04:46.696002+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/Y5NEIOEVK2MBQ7I533BHFOKVNQ","json":"https://pith.science/pith/Y5NEIOEVK2MBQ7I533BHFOKVNQ.json","graph_json":"https://pith.science/api/pith-number/Y5NEIOEVK2MBQ7I533BHFOKVNQ/graph.json","events_json":"https://pith.science/api/pith-number/Y5NEIOEVK2MBQ7I533BHFOKVNQ/events.json","paper":"https://pith.science/paper/Y5NEIOEV"},"agent_actions":{"view_html":"https://pith.science/pith/Y5NEIOEVK2MBQ7I533BHFOKVNQ","download_json":"https://pith.science/pith/Y5NEIOEVK2MBQ7I533BHFOKVNQ.json","view_paper":"https://pith.science/paper/Y5NEIOEV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07107&json=true","fetch_graph":"https://pith.science/api/pith-number/Y5NEIOEVK2MBQ7I533BHFOKVNQ/graph.json","fetch_events":"https://pith.science/api/pith-number/Y5NEIOEVK2MBQ7I533BHFOKVNQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y5NEIOEVK2MBQ7I533BHFOKVNQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y5NEIOEVK2MBQ7I533BHFOKVNQ/action/storage_attestation","attest_author":"https://pith.science/pith/Y5NEIOEVK2MBQ7I533BHFOKVNQ/action/author_attestation","sign_citation":"https://pith.science/pith/Y5NEIOEVK2MBQ7I533BHFOKVNQ/action/citation_signature","submit_replication":"https://pith.science/pith/Y5NEIOEVK2MBQ7I533BHFOKVNQ/action/replication_record"}},"created_at":"2026-06-08T01:04:46.696002+00:00","updated_at":"2026-06-08T01:04:46.696002+00:00"}