{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2VWFERGXU6AVU5WXWE4QRSVOEF","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":"dc17ed531fae1a4806ea140631ac6082ceb972ee833b35df1406fcf825b47c3d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-13T18:40:51Z","title_canon_sha256":"af4e419f6184e6b71787583dac50fceafa88e714c0dda7e7caf84bab110c5241"},"schema_version":"1.0","source":{"id":"2412.10345","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10345","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10345v3","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10345","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"pith_short_12","alias_value":"2VWFERGXU6AV","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"2VWFERGXU6AVU5WX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"2VWFERGX","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:e60c7b3c991ced4a9fbdc6516bb74950d52e4173abc12f458d20ee49992de4c3","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":"Evaluations of TraceVLA across 137 configurations in SimplerEnv and 4 tasks on a physical WidowX robot demonstrate state-of-the-art performance, outperforming OpenVLA by 10% on SimplerEnv and 3.5x on real-robot tasks and exhibiting robust generalization across diverse embodiments and scenarios."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the 150K collected trajectories with visual traces are sufficiently diverse and representative so that the observed gains are not artifacts of the specific data-collection procedure or embodiment distribution."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Visual trace prompting improves spatial-temporal awareness in VLA models, delivering 10% gains on SimplerEnv and 3.5x on real-robot tasks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Visual trace prompting encodes state-action trajectories to improve spatial-temporal awareness in vision-language-action robotic policies."}],"snapshot_sha256":"c77c0fbcb7e18a530d8b2b72a1591ac46f1f42b232f2daeb5a7f84e733169359"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"fe9bb0d287593b52fc679526f4bd9bb96449dcd9a6371a9e28c1cfd8937ea65b"},"paper":{"abstract_excerpt":"Although large vision-language-action (VLA) models pretrained on extensive robot datasets offer promising generalist policies for robotic learning, they still struggle with spatial-temporal dynamics in interactive robotics, making them less effective in handling complex tasks, such as manipulation. In this work, we introduce visual trace prompting, a simple yet effective approach to facilitate VLA models' spatial-temporal awareness for action prediction by encoding state-action trajectories visually. We develop a new TraceVLA model by finetuning OpenVLA on our own collected dataset of 150K rob","authors_text":"Andrey Kolobov, Furong Huang, Hal Daum\\'e III, Jianfeng Gao, Jianwei Yang, Ruijie Zheng, Shuaiyi Huang, Yongyuan Liang","cross_cats":["cs.AI"],"headline":"Visual trace prompting encodes state-action trajectories to improve spatial-temporal awareness in vision-language-action robotic policies.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-13T18:40:51Z","title":"TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies"},"references":{"count":76,"internal_anchors":16,"resolved_work":76,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"8th Annual Conference on Robot Learning , year=","work_id":"ab0d7be5-0e23-4407-8c37-e64bd7900606","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"7th Annual Conference on Robot Learning , year=","work_id":"259382f5-d2cd-4146-84a3-16a0869c4c73","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"8th Annual Conference on Robot Learning , year=","work_id":"a56f212f-d0d7-45a7-b9a4-c56f0b4f87f0","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Scaling Learning Algorithms Towards","work_id":"bb2761cc-98d0-411b-92f6-803773d64460","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":7,"title":"and Osindero, Simon and Teh, Yee Whye , journal =","work_id":"0a5921e3-ac4e-46f1-85ae-866119a87be0","year":null}],"snapshot_sha256":"6588a7990a8ad8d28c798f8e86c4dd816110b76e5983833c22e065e937bc825c"},"source":{"id":"2412.10345","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-15T18:22:47.948121Z","id":"1b13dae1-e6dc-41f4-8401-2489b6b21245","model_set":{"reader":"grok-4.3"},"one_line_summary":"Visual trace prompting improves spatial-temporal awareness in VLA models, delivering 10% gains on SimplerEnv and 3.5x on real-robot tasks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Visual trace prompting encodes state-action trajectories to improve spatial-temporal awareness in vision-language-action robotic policies.","strongest_claim":"Evaluations of TraceVLA across 137 configurations in SimplerEnv and 4 tasks on a physical WidowX robot demonstrate state-of-the-art performance, outperforming OpenVLA by 10% on SimplerEnv and 3.5x on real-robot tasks and exhibiting robust generalization across diverse embodiments and scenarios.","weakest_assumption":"That the 150K collected trajectories with visual traces are sufficiently diverse and representative so that the observed gains are not artifacts of the specific data-collection procedure or embodiment distribution."}},"verdict_id":"1b13dae1-e6dc-41f4-8401-2489b6b21245"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:82a3e6b41a796f8a4eedf9226d28fdb2467ac9505e206aae7fbfd7391792794b","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":"dc17ed531fae1a4806ea140631ac6082ceb972ee833b35df1406fcf825b47c3d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-13T18:40:51Z","title_canon_sha256":"af4e419f6184e6b71787583dac50fceafa88e714c0dda7e7caf84bab110c5241"},"schema_version":"1.0","source":{"id":"2412.10345","kind":"arxiv","version":3}},"canonical_sha256":"d56c5244d7a7815a76d7b13908caae2168512f025d4eb1ade4d2cd320a194744","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d56c5244d7a7815a76d7b13908caae2168512f025d4eb1ade4d2cd320a194744","first_computed_at":"2026-05-17T23:38:50.593974Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:50.593974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PMsgfJs8UvPKC657rQnhjAcedN94QUacaNOEAo8UmDUXhec3qbTfER97QTz67/eLbQ+D/Cp34sQbmiN2SKdzBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:50.594554Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.10345","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:82a3e6b41a796f8a4eedf9226d28fdb2467ac9505e206aae7fbfd7391792794b","sha256:e60c7b3c991ced4a9fbdc6516bb74950d52e4173abc12f458d20ee49992de4c3"],"state_sha256":"4ce6f94df71d32918e58f605e75fba8395ff4d684c49962019dcf03f20c7abc3"}