{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6Z5RRGFM332ONHQZVDEEGS642O","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":"efbbdfc7a28e25ef1c855fe6587059c150e48de3c8a7e0fd55e5e4426f7fa66e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-06T06:59:28Z","title_canon_sha256":"46ca4618ee18801ced1bd632a133d2bc867615cc1840e7dd4d74851826e99ee7"},"schema_version":"1.0","source":{"id":"2505.03233","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.03233","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"arxiv_version","alias_value":"2505.03233v3","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03233","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"pith_short_12","alias_value":"6Z5RRGFM332O","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"6Z5RRGFM332ONHQZ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"6Z5RRGFM","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:7c90b8d5cfa4686594a7f4632f23be0fe65d5ae43ce0bd8e05a47f420ec2581f","target":"graph","created_at":"2026-05-17T23:38:13Z","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":"GraspVLA integrates autoregressive perception tasks and flow-matching-based action generation into a unified Chain-of-Thought process, enabling joint training on synthetic action data and Internet semantics data to achieve open-vocabulary generalization in grasping."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That photorealistic rendering plus extensive domain randomization in simulation, combined with the CoT architecture, is sufficient to close the sim-to-real gap so that actions learned on synthetic data transfer effectively to physical robots on unseen objects."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"GraspVLA shows that pretraining a grasping model on a billion synthetic action frames enables zero-shot open-vocabulary performance and sim-to-real transfer."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A grasping model pretrained entirely on a billion-frame synthetic dataset achieves open-vocabulary generalization to real robots by unifying perception and action in one chain-of-thought sequence."}],"snapshot_sha256":"188944180b282cc6da36a10847252afadf58f39f68815391e810cf3bdbe88d8d"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"44a23072815f53252a63d673ee7d458ebdc8aa6fc2aa549dcd376c9f1dd6c8e2"},"paper":{"abstract_excerpt":"Embodied foundation models are gaining increasing attention for their zero-shot generalization, scalability, and adaptability to new tasks through few-shot post-training. However, existing models rely heavily on real-world data, which is costly and labor-intensive to collect. Synthetic data offers a cost-effective alternative, yet its potential remains largely underexplored. To bridge this gap, we explore the feasibility of training Vision-Language-Action models entirely with large-scale synthetic action data. We curate SynGrasp-1B, a billion-frame robotic grasping dataset generated in simulat","authors_text":"Haixin Ma, Heming Cui, He Wang, Jiayi Chen, Mi Yan, Shengliang Deng, Songlin Wei, Taoyu Yang, Wenhao Zhang, Xuheng Zhang, Yuxin Yang, Zhiqi Zhang, Zhizheng Zhang","cross_cats":[],"headline":"A grasping model pretrained entirely on a billion-frame synthetic dataset achieves open-vocabulary generalization to real robots by unifying perception and action in one chain-of-thought sequence.","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-06T06:59:28Z","title":"GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data"},"references":{"count":90,"internal_anchors":35,"resolved_work":90,"sample":[{"cited_arxiv_id":"2302.13971","doi":"","is_internal_anchor":true,"ref_index":1,"title":"LLaMA: Open and Efficient Foundation Language Models","work_id":"c018fc23-6f3f-4035-9d02-28a2173b2b9d","year":2023},{"cited_arxiv_id":"2304.02643","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Segment Anything","work_id":"2bbf46ca-720a-45a1-8e9c-10c33fbeada0","year":2023},{"cited_arxiv_id":"2103.00020","doi":"","is_internal_anchor":true,"ref_index":3,"title":"Learning Transferable Visual Models From Natural Language Supervision","work_id":"6de86bb5-27bd-4d5c-8b89-967ebfc52659","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Chatgpt: Jan 17 version","work_id":"e752cccc-4880-4947-bff8-1b4c3e4bb107","year":2023},{"cited_arxiv_id":"2307.15818","doi":"","is_internal_anchor":true,"ref_index":5,"title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","work_id":"ff438a8a-8003-4fae-9131-acd418b3597b","year":2023}],"snapshot_sha256":"5cb778e1a6f55163ff9301275a3d0b10174854280aee400a6581d29cf1ba97af"},"source":{"id":"2505.03233","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-17T20:51:38.996102Z","id":"9dec9f6d-eea2-43b3-aec4-9d4bdd3e3b29","model_set":{"reader":"grok-4.3"},"one_line_summary":"GraspVLA shows that pretraining a grasping model on a billion synthetic action frames enables zero-shot open-vocabulary performance and sim-to-real transfer.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A grasping model pretrained entirely on a billion-frame synthetic dataset achieves open-vocabulary generalization to real robots by unifying perception and action in one chain-of-thought sequence.","strongest_claim":"GraspVLA integrates autoregressive perception tasks and flow-matching-based action generation into a unified Chain-of-Thought process, enabling joint training on synthetic action data and Internet semantics data to achieve open-vocabulary generalization in grasping.","weakest_assumption":"That photorealistic rendering plus extensive domain randomization in simulation, combined with the CoT architecture, is sufficient to close the sim-to-real gap so that actions learned on synthetic data transfer effectively to physical robots on unseen objects."}},"verdict_id":"9dec9f6d-eea2-43b3-aec4-9d4bdd3e3b29"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:80e54924b4b4918538ad602ca8c843c1e709ab7e4f3e242dada4184ed5e2a3c9","target":"record","created_at":"2026-05-17T23:38:13Z","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":"efbbdfc7a28e25ef1c855fe6587059c150e48de3c8a7e0fd55e5e4426f7fa66e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-06T06:59:28Z","title_canon_sha256":"46ca4618ee18801ced1bd632a133d2bc867615cc1840e7dd4d74851826e99ee7"},"schema_version":"1.0","source":{"id":"2505.03233","kind":"arxiv","version":3}},"canonical_sha256":"f67b1898acdef4e69e19a8c8434bdcd39e9e70b9d9b5a0221c04811458bb201c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f67b1898acdef4e69e19a8c8434bdcd39e9e70b9d9b5a0221c04811458bb201c","first_computed_at":"2026-05-17T23:38:13.102573Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:13.102573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UudoqpFAFVxwENMhXSjhM5G3NNNs7lONHnKtXitR6xugjbBBfZLV4sgGV0YSQDe+z235ipfM+XCLv67zVLUpBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:13.103225Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.03233","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80e54924b4b4918538ad602ca8c843c1e709ab7e4f3e242dada4184ed5e2a3c9","sha256:7c90b8d5cfa4686594a7f4632f23be0fe65d5ae43ce0bd8e05a47f420ec2581f"],"state_sha256":"c114e716aa86968cb56ce4532affecd7a944e6621616417f1a5541016b744064"}