{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:Y5NEIOEVK2MBQ7I533BHFOKVNQ","short_pith_number":"pith:Y5NEIOEV","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"},"canonical_sha256":"c75a4438955698187d1ddec272b9556c022a8bf8841eb7a4d3080233a0bf99f5","source":{"kind":"arxiv","id":"2606.07107","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07107","created_at":"2026-06-08T01:04:46Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07107v1","created_at":"2026-06-08T01:04:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07107","created_at":"2026-06-08T01:04:46Z"},{"alias_kind":"pith_short_12","alias_value":"Y5NEIOEVK2MB","created_at":"2026-06-08T01:04:46Z"},{"alias_kind":"pith_short_16","alias_value":"Y5NEIOEVK2MBQ7I5","created_at":"2026-06-08T01:04:46Z"},{"alias_kind":"pith_short_8","alias_value":"Y5NEIOEV","created_at":"2026-06-08T01:04:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:Y5NEIOEVK2MBQ7I533BHFOKVNQ","target":"record","payload":{"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"},"canonical_sha256":"c75a4438955698187d1ddec272b9556c022a8bf8841eb7a4d3080233a0bf99f5","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"},"source_kind":"arxiv","source_id":"2606.07107","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-08T01:04:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0F3bLIfeqzdvQ2MHX77Jc8bkenHKM55T2ltfUiBi3TqDVYQzY+Rgr/MaxeFq7+Okp/1lhP2VYrMjE/BEyBpdDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T20:44:05.894286Z"},"content_sha256":"aa196106fb5d4275c0dcecf39c7418184d109eae38adff8bddcac790f1290682","schema_version":"1.0","event_id":"sha256:aa196106fb5d4275c0dcecf39c7418184d109eae38adff8bddcac790f1290682"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:Y5NEIOEVK2MBQ7I533BHFOKVNQ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-08T01:04:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OM0NSFu1Yg5tPNMMa5C9S8R0739JvcHT9oCLAUtCoWRvvOmxV7h6IMmrogXoAGDE9PQutvmu8egbmY1RLlVyBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T20:44:05.894655Z"},"content_sha256":"b43f913f0bbef3251a1425b9d0ca40e513a4a6e76fdbace0ab8763afea3f2d38","schema_version":"1.0","event_id":"sha256:b43f913f0bbef3251a1425b9d0ca40e513a4a6e76fdbace0ab8763afea3f2d38"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y5NEIOEVK2MBQ7I533BHFOKVNQ/bundle.json","state_url":"https://pith.science/pith/Y5NEIOEVK2MBQ7I533BHFOKVNQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y5NEIOEVK2MBQ7I533BHFOKVNQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-29T20:44:05Z","links":{"resolver":"https://pith.science/pith/Y5NEIOEVK2MBQ7I533BHFOKVNQ","bundle":"https://pith.science/pith/Y5NEIOEVK2MBQ7I533BHFOKVNQ/bundle.json","state":"https://pith.science/pith/Y5NEIOEVK2MBQ7I533BHFOKVNQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y5NEIOEVK2MBQ7I533BHFOKVNQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Y5NEIOEVK2MBQ7I533BHFOKVNQ","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":"25f8a5632fc7216d7087fa450e4aebba2b6b2a5633a0fdcf724b67d158a9e22c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-05T10:01:37Z","title_canon_sha256":"1c49433d30fb2c2143c7252cea85691a0dd8338fcbbf233e455c60ef75682fef"},"schema_version":"1.0","source":{"id":"2606.07107","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07107","created_at":"2026-06-08T01:04:46Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07107v1","created_at":"2026-06-08T01:04:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07107","created_at":"2026-06-08T01:04:46Z"},{"alias_kind":"pith_short_12","alias_value":"Y5NEIOEVK2MB","created_at":"2026-06-08T01:04:46Z"},{"alias_kind":"pith_short_16","alias_value":"Y5NEIOEVK2MBQ7I5","created_at":"2026-06-08T01:04:46Z"},{"alias_kind":"pith_short_8","alias_value":"Y5NEIOEV","created_at":"2026-06-08T01:04:46Z"}],"graph_snapshots":[{"event_id":"sha256:b43f913f0bbef3251a1425b9d0ca40e513a4a6e76fdbace0ab8763afea3f2d38","target":"graph","created_at":"2026-06-08T01:04:46Z","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/2606.07107/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-05T10:01:37Z","title":"Coarse-to-Control: Action-Token Planning for Vision-Language-Action Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07107","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:aa196106fb5d4275c0dcecf39c7418184d109eae38adff8bddcac790f1290682","target":"record","created_at":"2026-06-08T01:04:46Z","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":"25f8a5632fc7216d7087fa450e4aebba2b6b2a5633a0fdcf724b67d158a9e22c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-05T10:01:37Z","title_canon_sha256":"1c49433d30fb2c2143c7252cea85691a0dd8338fcbbf233e455c60ef75682fef"},"schema_version":"1.0","source":{"id":"2606.07107","kind":"arxiv","version":1}},"canonical_sha256":"c75a4438955698187d1ddec272b9556c022a8bf8841eb7a4d3080233a0bf99f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c75a4438955698187d1ddec272b9556c022a8bf8841eb7a4d3080233a0bf99f5","first_computed_at":"2026-06-08T01:04:46.695877Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:04:46.695877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LdYFeJHGDM62UwBLNoM8JgNFMorP6yJi/ai+v/JmDs2cvo+Ti4gyRR999uxZrfdVUX+G12rTjzjcl/V96C2pAg==","signature_status":"signed_v1","signed_at":"2026-06-08T01:04:46.696707Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.07107","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa196106fb5d4275c0dcecf39c7418184d109eae38adff8bddcac790f1290682","sha256:b43f913f0bbef3251a1425b9d0ca40e513a4a6e76fdbace0ab8763afea3f2d38"],"state_sha256":"3dba311d72c0e56c8354c3bcef8ca4300104048576b27472278d328558a5df5d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YPOc5Ugn77cVap/oMCTZNzk0KYpdXHfVi5nkUnOgDISp1vb4SXkGSY1s2ZErC+YfCySMImmnxuosM5e2yr6CBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T20:44:05.896537Z","bundle_sha256":"687f4be8cad676b131022f6e30fdfcbbdbe869257e948ad17fb585739a05c078"}}