{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PPQJJRR6JS2EFMGIQSOLSRDKHW","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":"facb64202c82213c7e5ffa87cf5850af1e79e6f349e74b2fb30c6e601c2a1d0c","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-13T17:59:52Z","title_canon_sha256":"3547a3a9f5d9e60b9a2fdd4375a5e12e48215603b741ba11840c7c6c0f109329"},"schema_version":"1.0","source":{"id":"2503.10631","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.10631","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"arxiv_version","alias_value":"2503.10631v3","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10631","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"pith_short_12","alias_value":"PPQJJRR6JS2E","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"PPQJJRR6JS2EFMGI","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"PPQJJRR6","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:3fc919903313cd3a8af27197f31635c8e5adc2d38dd3481767ecfa7e57988446","target":"graph","created_at":"2026-05-17T23:38:50Z","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":"HybridVLA outperforms previous state-of-the-art VLA methods by 14% and 19% in mean success rate on simulation and real-world tasks, respectively, while demonstrating stable manipulation in unseen configurations."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The collaborative training recipe successfully prevents interference between diffusion denoising and next-token prediction while allowing the two paradigms to reinforce each other across tasks."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"HybridVLA unifies diffusion and autoregression in a single VLA model via collaborative training and ensemble to raise robot manipulation success rates by 14% in simulation and 19% in real-world tasks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"HybridVLA unifies diffusion for continuous actions and autoregression for reasoning inside one vision-language-action model."}],"snapshot_sha256":"f60d62d555cb87ba1712b6516e4b2f2529fa7f4897ada1c2047204adbd6a44dd"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"A fundamental objective of manipulation policy design is to endow robots to comprehend human instructions, reason about scene cues, and execute generalized actions in dynamic environments. Recent autoregressive vision-language-action (VLA) methods inherit common-sense reasoning capabilities from vision-language models (VLMs) for next action-token prediction. However, these methods quantize actions into discrete bins, which disrupts the continuity required for precise control. In contrast, existing diffusion-based VLA methods incorporate an additional diffusion head to predict continuous action","authors_text":"Chengkai Hou, Chenyang Gu, Hao Chen, Jiaming Liu, KC alex Zhou, Mengdi Zhao, Mengzhen Liu, Pengju An, Pheng-Ann Heng, Renrui Zhang, Shanghang Zhang, Sixiang Chen, Xiaoqi Li, Zhuoyang Liu, Ziyu Guo","cross_cats":["cs.RO"],"headline":"HybridVLA unifies diffusion for continuous actions and autoregression for reasoning inside one vision-language-action model.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-13T17:59:52Z","title":"HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model"},"references":{"count":127,"internal_anchors":42,"resolved_work":127,"sample":[{"cited_arxiv_id":"2303.03378","doi":"","is_internal_anchor":true,"ref_index":1,"title":"PaLM-E: An Embodied Multimodal Language Model","work_id":"5b99811a-1d93-47e2-9d59-f4045a0b74a2","year":2023},{"cited_arxiv_id":"2204.01691","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","work_id":"037320f1-b0a9-4cbe-a639-bfb25409ce71","year":2022},{"cited_arxiv_id":"2307.05973","doi":"","is_internal_anchor":true,"ref_index":3,"title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","work_id":"5a5edf95-2538-4e2b-8dfa-da39cec89f22","year":2023},{"cited_arxiv_id":"2412.14058","doi":"","is_internal_anchor":true,"ref_index":4,"title":"What Matters in Building Vision-Language-Action Models for Generalist Robots","work_id":"972ba6c7-a312-404e-bd8d-851850b28fc9","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Visual instruction tuning","work_id":"a2628f23-eb28-4e09-a098-bce23f22dee1","year":2024}],"snapshot_sha256":"6828e62d3c65ce92fbd7fb78972eb241f48387976896d9433f37739a35edf8b1"},"source":{"id":"2503.10631","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-15T21:57:10.964919Z","id":"17f48075-055a-45b6-b90c-25bba68fbb29","model_set":{"reader":"grok-4.3"},"one_line_summary":"HybridVLA unifies diffusion and autoregression in a single VLA model via collaborative training and ensemble to raise robot manipulation success rates by 14% in simulation and 19% in real-world tasks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"HybridVLA unifies diffusion for continuous actions and autoregression for reasoning inside one vision-language-action model.","strongest_claim":"HybridVLA outperforms previous state-of-the-art VLA methods by 14% and 19% in mean success rate on simulation and real-world tasks, respectively, while demonstrating stable manipulation in unseen configurations.","weakest_assumption":"The collaborative training recipe successfully prevents interference between diffusion denoising and next-token prediction while allowing the two paradigms to reinforce each other across tasks."}},"verdict_id":"17f48075-055a-45b6-b90c-25bba68fbb29"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d7527f93895e01fb2bb505236ebba30fb817d521158b048ad528ffe1e9f0b3a4","target":"record","created_at":"2026-05-17T23:38:50Z","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":"facb64202c82213c7e5ffa87cf5850af1e79e6f349e74b2fb30c6e601c2a1d0c","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-13T17:59:52Z","title_canon_sha256":"3547a3a9f5d9e60b9a2fdd4375a5e12e48215603b741ba11840c7c6c0f109329"},"schema_version":"1.0","source":{"id":"2503.10631","kind":"arxiv","version":3}},"canonical_sha256":"7be094c63e4cb442b0c8849cb9446a3db7f263eb3cb1311bf4768c02971e3b80","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7be094c63e4cb442b0c8849cb9446a3db7f263eb3cb1311bf4768c02971e3b80","first_computed_at":"2026-05-17T23:38:50.020884Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:50.020884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v+kpGRtOFWqpZLw9ZUMbwpSTkI6bq0JPUWP+PLZdy4JRixVTH+JAtqo20FfHF5ZOamw+gw1jWTqaOSzsf7VXAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:50.021385Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.10631","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d7527f93895e01fb2bb505236ebba30fb817d521158b048ad528ffe1e9f0b3a4","sha256:3fc919903313cd3a8af27197f31635c8e5adc2d38dd3481767ecfa7e57988446"],"state_sha256":"080d61de97806d8941beb6fcc36d5536128b60079fff78a291e59f72f24502da"}