{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5LJABTGJ7K3BFTPVTGXJZACZCJ","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":"7a75950fedc7665a116cbc335d63c8dd7bb2ed11a6f217ef1d118cc4831d38cd","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-27T22:23:04Z","title_canon_sha256":"dd802464cc0fdd008ca9fd5ca53edf693e63979868d8545f80321fe3dc1c1b6c"},"schema_version":"1.0","source":{"id":"2503.22020","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.22020","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"arxiv_version","alias_value":"2503.22020v1","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.22020","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"pith_short_12","alias_value":"5LJABTGJ7K3B","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"5LJABTGJ7K3BFTPV","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"5LJABTGJ","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:c4f7a419abd18bf7509d36522f04517bb2624a19233c5a930f5db0a55018f73b","target":"graph","created_at":"2026-05-17T23:38:48Z","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":"Our experimental results demonstrate that CoT-VLA achieves strong performance, outperforming the state-of-the-art VLA model by 17% in real-world manipulation tasks and 6% in simulation benchmarks."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That autoregressive prediction of future image frames produces reliable visual goals that meaningfully improve downstream action generation for complex manipulation tasks."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"CoT-VLA is a 7B VLA that generates future visual frames autoregressively as planning goals before actions, outperforming prior VLAs by 17% on real-world tasks and 6% in simulation."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Adding explicit visual chain-of-thought by predicting future image frames before actions improves vision-language-action model performance on complex robot tasks."}],"snapshot_sha256":"3b52b88d2af5ea114c21b3b378c53ee08b402920c61bbf8d8ff99ba3ab2c10d3"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"38c0d167a3af73b21e802bd9b1a98b72fe48248e34edd20fb8a7e992da0f3826"},"paper":{"abstract_excerpt":"Vision-language-action models (VLAs) have shown potential in leveraging pretrained vision-language models and diverse robot demonstrations for learning generalizable sensorimotor control. While this paradigm effectively utilizes large-scale data from both robotic and non-robotic sources, current VLAs primarily focus on direct input--output mappings, lacking the intermediate reasoning steps crucial for complex manipulation tasks. As a result, existing VLAs lack temporal planning or reasoning capabilities. In this paper, we introduce a method that incorporates explicit visual chain-of-thought (C","authors_text":"Ankur Handa, Chelsea Finn, Donglai Xiang, Gordon Wetzstein, Ming-Yu Liu, Moo Jin Kim, Qianli Ma, Qingqing Zhao, Song Han, Tsung-Yi Lin, Yao Lu, Yecheng Wu, Zhaoshuo Li, Zhuoyang Zhang, Zipeng Fu","cross_cats":["cs.AI","cs.LG","cs.RO"],"headline":"Adding explicit visual chain-of-thought by predicting future image frames before actions improves vision-language-action model performance on complex robot tasks.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-27T22:23:04Z","title":"CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models"},"references":{"count":85,"internal_anchors":28,"resolved_work":85,"sample":[{"cited_arxiv_id":"2409.16283","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation","work_id":"a3bde288-aace-40db-8067-3ae6656f9509","year":2024},{"cited_arxiv_id":"2310.10639","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models","work_id":"954b4359-f4ed-4c73-ae5b-f75d486b6fc8","year":2023},{"cited_arxiv_id":"2212.06817","doi":"","is_internal_anchor":true,"ref_index":3,"title":"RT-1: Robotics Transformer for Real-World Control at Scale","work_id":"e11bda85-8531-46bc-a07f-d0ade3643ab1","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Emerg- ing properties in self-supervised vision transformers","work_id":"d783e7b6-6d26-419d-a3e8-aae0948df097","year":2021},{"cited_arxiv_id":"2410.06158","doi":"","is_internal_anchor":true,"ref_index":5,"title":"GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation","work_id":"843ab5eb-2815-4db8-b3bc-890b23fa5ffa","year":2024}],"snapshot_sha256":"ed33a648d307c2bf7df5fb3321c74515d25cf806f5865b17937f09810b96bb56"},"source":{"id":"2503.22020","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-16T05:17:41.158602Z","id":"5fa2ec6f-345f-40fb-a915-12c6d595b5c6","model_set":{"reader":"grok-4.3"},"one_line_summary":"CoT-VLA is a 7B VLA that generates future visual frames autoregressively as planning goals before actions, outperforming prior VLAs by 17% on real-world tasks and 6% in simulation.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Adding explicit visual chain-of-thought by predicting future image frames before actions improves vision-language-action model performance on complex robot tasks.","strongest_claim":"Our experimental results demonstrate that CoT-VLA achieves strong performance, outperforming the state-of-the-art VLA model by 17% in real-world manipulation tasks and 6% in simulation benchmarks.","weakest_assumption":"That autoregressive prediction of future image frames produces reliable visual goals that meaningfully improve downstream action generation for complex manipulation tasks."}},"verdict_id":"5fa2ec6f-345f-40fb-a915-12c6d595b5c6"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2911f66a4b1a4abe2f585bd09a9a01646451dfa7d61e2bed2d09c05289a1d2ec","target":"record","created_at":"2026-05-17T23:38:48Z","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":"7a75950fedc7665a116cbc335d63c8dd7bb2ed11a6f217ef1d118cc4831d38cd","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-27T22:23:04Z","title_canon_sha256":"dd802464cc0fdd008ca9fd5ca53edf693e63979868d8545f80321fe3dc1c1b6c"},"schema_version":"1.0","source":{"id":"2503.22020","kind":"arxiv","version":1}},"canonical_sha256":"ead200ccc9fab612cdf599ae9c8059126dfb74b1d9eb8331e18424a25620f90e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ead200ccc9fab612cdf599ae9c8059126dfb74b1d9eb8331e18424a25620f90e","first_computed_at":"2026-05-17T23:38:48.986037Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:48.986037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vrty8zIArtoQ96oDqqb4XYdQuNZtMNrXuPv+FeyuaFnQ5qPcaJWZktfikN+CmKnpwHGjQ3iy20q4RFWPbbwUDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:48.986650Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.22020","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2911f66a4b1a4abe2f585bd09a9a01646451dfa7d61e2bed2d09c05289a1d2ec","sha256:c4f7a419abd18bf7509d36522f04517bb2624a19233c5a930f5db0a55018f73b"],"state_sha256":"185e0d32b97bd34382df1b5fbd11426ce1879b0dcbf0c961e0255e5175c4ea8c"}