{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JCNLFONENEST6JD5ZGA5W5UQH2","short_pith_number":"pith:JCNLFONE","canonical_record":{"source":{"id":"2605.13632","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-13T14:58:29Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"3a0179fe064ee1dd6e92a15e7a2ee2102c754f687ca4ccf0f0a3a554fc5fd5f6","abstract_canon_sha256":"075dfc62fc83e16389d80508c1df17daceeea30b9f27618ea1709c58b3a5ed60"},"schema_version":"1.0"},"canonical_sha256":"489ab2b9a469253f247dc981db76903e88c59eacaeb830a297e9b5ff1219c761","source":{"kind":"arxiv","id":"2605.13632","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13632","created_at":"2026-05-18T02:44:17Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13632v1","created_at":"2026-05-18T02:44:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13632","created_at":"2026-05-18T02:44:17Z"},{"alias_kind":"pith_short_12","alias_value":"JCNLFONENEST","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"JCNLFONENEST6JD5","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"JCNLFONE","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JCNLFONENEST6JD5ZGA5W5UQH2","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13632","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-13T14:58:29Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"3a0179fe064ee1dd6e92a15e7a2ee2102c754f687ca4ccf0f0a3a554fc5fd5f6","abstract_canon_sha256":"075dfc62fc83e16389d80508c1df17daceeea30b9f27618ea1709c58b3a5ed60"},"schema_version":"1.0"},"canonical_sha256":"489ab2b9a469253f247dc981db76903e88c59eacaeb830a297e9b5ff1219c761","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:17.743033Z","signature_b64":"WZHtwE1tJmbP7yDOLwyqVeMpGqa1zpBnwT1cwR5HTc48JtmYw6MAgTkcAWAniezUuzGRe0l6ZZA4l+PcU+ykDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"489ab2b9a469253f247dc981db76903e88c59eacaeb830a297e9b5ff1219c761","last_reissued_at":"2026-05-18T02:44:17.742606Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:17.742606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13632","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":"2026-05-18T02:44:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MH9KsZnUlUyYRMo9lIPvIXuOAijH7/AZ93IzsmWY7ZmrzfqBrItVm+eA8XE73k4LTJSmLvHG8XKGmafMwQNFDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T23:06:55.063495Z"},"content_sha256":"50509086b75ef34d66c972b0b0ba3c754bb24f37ab5cd07f85aa319cc38a4b29","schema_version":"1.0","event_id":"sha256:50509086b75ef34d66c972b0b0ba3c754bb24f37ab5cd07f85aa319cc38a4b29"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JCNLFONENEST6JD5ZGA5W5UQH2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Guide, Think, Act: Interactive Embodied Reasoning in Vision-Language-Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"GTA-VLA lets users steer vision-language-action models with explicit spatial visual cues for better robot control.","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Chuanxiu Liu, Jie Liu, Jinghang Li, Lei Zhang, Qing Jiang, Qing Lian, Tianming Zhang, Xiaoke Jiang, Yiran Ling","submitted_at":"2026-05-13T14:58:29Z","abstract_excerpt":"In this paper, we propose GTA-VLA(Guide, Think, Act), an interactive Vision-Language-Action (VLA) framework that enables spatially steerable embodied reasoning by allowing users to guide robot policies with explicit visual cues. Existing VLA models learn a direct \"Sense-to-Act\" mapping from multimodal observations to robot actions. While effective within the training distribution, such tightly coupled policies are brittle under out-of-domain (OOD) shifts and difficult to correct when failures occur. Although recent embodied Chain-of-Thought (CoT) approaches expose intermediate reasoning, they "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"On the in-domain SimplerEnv WidowX benchmark, our framework achieves a state-of-the-art 81.2% success rate. Under OOD visual shifts and spatial ambiguities, a single visual interaction substantially improves task success over existing methods.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That users will supply accurate, task-relevant spatial priors (points, boxes, traces) that the model can reliably integrate without introducing new errors or ambiguities.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"GTA-VLA conditions VLA models on user spatial priors to produce a unified spatial-visual chain-of-thought, reaching 81.2% success on SimplerEnv WidowX and improving performance under out-of-distribution shifts.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"GTA-VLA lets users steer vision-language-action models with explicit spatial visual cues for better robot control.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"eaace184c0009b135198d08d3f0b278033038f551a69e5f68779487dc984677a"},"source":{"id":"2605.13632","kind":"arxiv","version":1},"verdict":{"id":"2527139b-5c9b-4368-a56b-41cd91fd7d10","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T18:27:09.637078Z","strongest_claim":"On the in-domain SimplerEnv WidowX benchmark, our framework achieves a state-of-the-art 81.2% success rate. Under OOD visual shifts and spatial ambiguities, a single visual interaction substantially improves task success over existing methods.","one_line_summary":"GTA-VLA conditions VLA models on user spatial priors to produce a unified spatial-visual chain-of-thought, reaching 81.2% success on SimplerEnv WidowX and improving performance under out-of-distribution shifts.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That users will supply accurate, task-relevant spatial priors (points, boxes, traces) that the model can reliably integrate without introducing new errors or ambiguities.","pith_extraction_headline":"GTA-VLA lets users steer vision-language-action models with explicit spatial visual cues for better robot control."},"references":{"count":39,"sample":[{"doi":"","year":2025,"title":"Qwen3-VL Technical Report","work_id":"1fe243aa-e3c0-4da6-b391-4cbcfc88d5c0","ref_index":1,"cited_arxiv_id":"2511.21631","is_internal_anchor":true},{"doi":"","year":2024,"title":"RT-H: Action Hierarchies Using Language","work_id":"ecf7cf18-c1a8-4a6b-bc2a-fb165643aa0d","ref_index":2,"cited_arxiv_id":"2403.01823","is_internal_anchor":true},{"doi":"","year":2024,"title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","work_id":"f790abdc-a796-482f-a40d-f8ee035ecfc2","ref_index":3,"cited_arxiv_id":"2410.24164","is_internal_anchor":true},{"doi":"","year":2025,"title":"$\\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization","work_id":"d1ad7304-d09a-49bc-809e-846439f6aff9","ref_index":4,"cited_arxiv_id":"2504.16054","is_internal_anchor":true},{"doi":"","year":2025,"title":"SAM 3: Segment Anything with Concepts","work_id":"4a72a006-2592-4554-aad0-a9c41a9f952d","ref_index":5,"cited_arxiv_id":"2511.16719","is_internal_anchor":true}],"resolved_work":39,"snapshot_sha256":"22cd1f886b762cf19ce42cf5c43a1180b6db3330ac088ce97e4e4366502c125a","internal_anchors":18},"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":"2527139b-5c9b-4368-a56b-41cd91fd7d10"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jpVtqY99uXMQ84RMUsdJnHNGpCOcxfiE3IbfDNw3wWVKNp3F+CXcHeYPs9/I3WX9diKjIUkJM64N/mgUpoiLBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T23:06:55.064022Z"},"content_sha256":"754860394dbf32875c1e52af0d596616b661a1dbc0229d22b4e9cd1c58ea77f2","schema_version":"1.0","event_id":"sha256:754860394dbf32875c1e52af0d596616b661a1dbc0229d22b4e9cd1c58ea77f2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JCNLFONENEST6JD5ZGA5W5UQH2/bundle.json","state_url":"https://pith.science/pith/JCNLFONENEST6JD5ZGA5W5UQH2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JCNLFONENEST6JD5ZGA5W5UQH2/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":"2026-06-02T23:06:55Z","links":{"resolver":"https://pith.science/pith/JCNLFONENEST6JD5ZGA5W5UQH2","bundle":"https://pith.science/pith/JCNLFONENEST6JD5ZGA5W5UQH2/bundle.json","state":"https://pith.science/pith/JCNLFONENEST6JD5ZGA5W5UQH2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JCNLFONENEST6JD5ZGA5W5UQH2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JCNLFONENEST6JD5ZGA5W5UQH2","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":"075dfc62fc83e16389d80508c1df17daceeea30b9f27618ea1709c58b3a5ed60","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-13T14:58:29Z","title_canon_sha256":"3a0179fe064ee1dd6e92a15e7a2ee2102c754f687ca4ccf0f0a3a554fc5fd5f6"},"schema_version":"1.0","source":{"id":"2605.13632","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13632","created_at":"2026-05-18T02:44:17Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13632v1","created_at":"2026-05-18T02:44:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13632","created_at":"2026-05-18T02:44:17Z"},{"alias_kind":"pith_short_12","alias_value":"JCNLFONENEST","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"JCNLFONENEST6JD5","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"JCNLFONE","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:754860394dbf32875c1e52af0d596616b661a1dbc0229d22b4e9cd1c58ea77f2","target":"graph","created_at":"2026-05-18T02:44:17Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"On the in-domain SimplerEnv WidowX benchmark, our framework achieves a state-of-the-art 81.2% success rate. Under OOD visual shifts and spatial ambiguities, a single visual interaction substantially improves task success over existing methods."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That users will supply accurate, task-relevant spatial priors (points, boxes, traces) that the model can reliably integrate without introducing new errors or ambiguities."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"GTA-VLA conditions VLA models on user spatial priors to produce a unified spatial-visual chain-of-thought, reaching 81.2% success on SimplerEnv WidowX and improving performance under out-of-distribution shifts."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"GTA-VLA lets users steer vision-language-action models with explicit spatial visual cues for better robot control."}],"snapshot_sha256":"eaace184c0009b135198d08d3f0b278033038f551a69e5f68779487dc984677a"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"In this paper, we propose GTA-VLA(Guide, Think, Act), an interactive Vision-Language-Action (VLA) framework that enables spatially steerable embodied reasoning by allowing users to guide robot policies with explicit visual cues. Existing VLA models learn a direct \"Sense-to-Act\" mapping from multimodal observations to robot actions. While effective within the training distribution, such tightly coupled policies are brittle under out-of-domain (OOD) shifts and difficult to correct when failures occur. Although recent embodied Chain-of-Thought (CoT) approaches expose intermediate reasoning, they ","authors_text":"Chuanxiu Liu, Jie Liu, Jinghang Li, Lei Zhang, Qing Jiang, Qing Lian, Tianming Zhang, Xiaoke Jiang, Yiran Ling","cross_cats":["cs.CV"],"headline":"GTA-VLA lets users steer vision-language-action models with explicit spatial visual cues for better robot control.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-13T14:58:29Z","title":"Guide, Think, Act: Interactive Embodied Reasoning in Vision-Language-Action Models"},"references":{"count":39,"internal_anchors":18,"resolved_work":39,"sample":[{"cited_arxiv_id":"2511.21631","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Qwen3-VL Technical Report","work_id":"1fe243aa-e3c0-4da6-b391-4cbcfc88d5c0","year":2025},{"cited_arxiv_id":"2403.01823","doi":"","is_internal_anchor":true,"ref_index":2,"title":"RT-H: Action Hierarchies Using Language","work_id":"ecf7cf18-c1a8-4a6b-bc2a-fb165643aa0d","year":2024},{"cited_arxiv_id":"2410.24164","doi":"","is_internal_anchor":true,"ref_index":3,"title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","work_id":"f790abdc-a796-482f-a40d-f8ee035ecfc2","year":2024},{"cited_arxiv_id":"2504.16054","doi":"","is_internal_anchor":true,"ref_index":4,"title":"$\\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization","work_id":"d1ad7304-d09a-49bc-809e-846439f6aff9","year":2025},{"cited_arxiv_id":"2511.16719","doi":"","is_internal_anchor":true,"ref_index":5,"title":"SAM 3: Segment Anything with Concepts","work_id":"4a72a006-2592-4554-aad0-a9c41a9f952d","year":2025}],"snapshot_sha256":"22cd1f886b762cf19ce42cf5c43a1180b6db3330ac088ce97e4e4366502c125a"},"source":{"id":"2605.13632","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T18:27:09.637078Z","id":"2527139b-5c9b-4368-a56b-41cd91fd7d10","model_set":{"reader":"grok-4.3"},"one_line_summary":"GTA-VLA conditions VLA models on user spatial priors to produce a unified spatial-visual chain-of-thought, reaching 81.2% success on SimplerEnv WidowX and improving performance under out-of-distribution shifts.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"GTA-VLA lets users steer vision-language-action models with explicit spatial visual cues for better robot control.","strongest_claim":"On the in-domain SimplerEnv WidowX benchmark, our framework achieves a state-of-the-art 81.2% success rate. Under OOD visual shifts and spatial ambiguities, a single visual interaction substantially improves task success over existing methods.","weakest_assumption":"That users will supply accurate, task-relevant spatial priors (points, boxes, traces) that the model can reliably integrate without introducing new errors or ambiguities."}},"verdict_id":"2527139b-5c9b-4368-a56b-41cd91fd7d10"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:50509086b75ef34d66c972b0b0ba3c754bb24f37ab5cd07f85aa319cc38a4b29","target":"record","created_at":"2026-05-18T02:44:17Z","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":"075dfc62fc83e16389d80508c1df17daceeea30b9f27618ea1709c58b3a5ed60","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-13T14:58:29Z","title_canon_sha256":"3a0179fe064ee1dd6e92a15e7a2ee2102c754f687ca4ccf0f0a3a554fc5fd5f6"},"schema_version":"1.0","source":{"id":"2605.13632","kind":"arxiv","version":1}},"canonical_sha256":"489ab2b9a469253f247dc981db76903e88c59eacaeb830a297e9b5ff1219c761","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"489ab2b9a469253f247dc981db76903e88c59eacaeb830a297e9b5ff1219c761","first_computed_at":"2026-05-18T02:44:17.742606Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:17.742606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WZHtwE1tJmbP7yDOLwyqVeMpGqa1zpBnwT1cwR5HTc48JtmYw6MAgTkcAWAniezUuzGRe0l6ZZA4l+PcU+ykDA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:17.743033Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13632","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:50509086b75ef34d66c972b0b0ba3c754bb24f37ab5cd07f85aa319cc38a4b29","sha256:754860394dbf32875c1e52af0d596616b661a1dbc0229d22b4e9cd1c58ea77f2"],"state_sha256":"e8ecd8a3a822ada7c76f2b75b22544b13424ed1b549da4046d9b2407fe119ddc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j5/jjzDjTfV8qiQkJdbF18yImwzW8+QTEkQrjEyi5izjk28BAk935YVk+VqCY162lK+udxm9Rd3z6clwEm7CCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T23:06:55.066458Z","bundle_sha256":"aae63aca3f208d4d2d95eacaeffe6deb90a74b1a979df072e2478890c37d7aac"}}