{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XWR3HY4R63WXARVJBBE3KP3PQ5","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":"e0d5f68d11feba92f0d5cc4636c6164c479c12c5155cd641402809cf223bf8da","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-12-17T18:47:31Z","title_canon_sha256":"0412f0ff8a4ed450487be639acf053b40c333f1fd4bc4b5d02d74e264d01b310"},"schema_version":"1.0","source":{"id":"2512.15692","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.15692","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"arxiv_version","alias_value":"2512.15692v2","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.15692","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"pith_short_12","alias_value":"XWR3HY4R63WX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"XWR3HY4R63WXARVJ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"XWR3HY4R","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:43eca102a4275e336dcf8732eb804a6c422f73ec9c5372f9bad70c3a05084af8","target":"graph","created_at":"2026-05-17T23:38:52Z","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 extensive evaluation shows that our approach achieves state-of-the-art performance on simulated and real-world robotic manipulation tasks, improving sample efficiency by 10x and convergence speed by 2x compared to traditional VLA architectures."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That a pretrained internet video model already captures sufficient physical causality and temporal dynamics so that the remaining task reduces cleanly to low-level control via the flow-matching decoder."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"mimic-video combines internet video pretraining with a flow-matching decoder to achieve state-of-the-art robotic manipulation performance with 10x better sample efficiency than vision-language-action models."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Pretrained video models plus a flow-matching decoder let robots learn manipulation with far less data than vision-language-action models."}],"snapshot_sha256":"91dedd1877388b6d03a9e70fdf923b5d2854898cf737ce91e32b10ed4fa5f0b8"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"48ee4a283a4e41a2e0a0249d42b1a3eab7bd9a69359fe66ac8c678785db4eb0b"},"paper":{"abstract_excerpt":"Prevailing Vision-Language-Action Models (VLAs) for robotic manipulation are built upon vision-language backbones pretrained on large-scale, but disconnected static web data. As a result, despite improved semantic generalization, the policy must implicitly infer complex physical dynamics and temporal dependencies solely from robot trajectories. This reliance creates an unsustainable data burden, necessitating continuous, large-scale expert data collection to compensate for the lack of innate physical understanding. We contend that while vision-language pretraining effectively captures semantic","authors_text":"Benedek Forrai, Elvis Nava, Jonas Pai, Liam Achenbach, Oier Mees, Victoriano Montesinos","cross_cats":["cs.AI","cs.CV","cs.LG"],"headline":"Pretrained video models plus a flow-matching decoder let robots learn manipulation with far less data than vision-language-action models.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-12-17T18:47:31Z","title":"mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs"},"references":{"count":64,"internal_anchors":35,"resolved_work":64,"sample":[{"cited_arxiv_id":"2506.09985","doi":"","is_internal_anchor":true,"ref_index":1,"title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","work_id":"a9c28401-f16a-4933-89f0-788e2f94e52b","year":2025},{"cited_arxiv_id":"2407.07726","doi":"","is_internal_anchor":true,"ref_index":2,"title":"PaliGemma: A versatile 3B VLM for transfer","work_id":"df6f48b3-5792-47c7-9614-cb856ea31ad9","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":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"RoboCat : A self-improving foundation agent for robotic manipulation","work_id":"143e7731-0488-4088-8e23-63f9d4140118","year":2023},{"cited_arxiv_id":"2104.14294","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Emerging Properties in Self-Supervised Vision Transformers","work_id":"6b124bd1-c9f1-4251-96c1-2683f7f17a64","year":2021}],"snapshot_sha256":"e667f1ad075990562f559a60638d466104c24301e241d90a6aba90e8135b6df8"},"source":{"id":"2512.15692","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-15T10:35:14.719280Z","id":"7803f969-855a-4ac9-8d9b-e11480a9afb5","model_set":{"reader":"grok-4.3"},"one_line_summary":"mimic-video combines internet video pretraining with a flow-matching decoder to achieve state-of-the-art robotic manipulation performance with 10x better sample efficiency than vision-language-action models.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Pretrained video models plus a flow-matching decoder let robots learn manipulation with far less data than vision-language-action models.","strongest_claim":"Our extensive evaluation shows that our approach achieves state-of-the-art performance on simulated and real-world robotic manipulation tasks, improving sample efficiency by 10x and convergence speed by 2x compared to traditional VLA architectures.","weakest_assumption":"That a pretrained internet video model already captures sufficient physical causality and temporal dynamics so that the remaining task reduces cleanly to low-level control via the flow-matching decoder."}},"verdict_id":"7803f969-855a-4ac9-8d9b-e11480a9afb5"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3f2a68ddbc671274a3745d4d359063cc5f8af96e6e71a69020f4e4495974c278","target":"record","created_at":"2026-05-17T23:38:52Z","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":"e0d5f68d11feba92f0d5cc4636c6164c479c12c5155cd641402809cf223bf8da","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-12-17T18:47:31Z","title_canon_sha256":"0412f0ff8a4ed450487be639acf053b40c333f1fd4bc4b5d02d74e264d01b310"},"schema_version":"1.0","source":{"id":"2512.15692","kind":"arxiv","version":2}},"canonical_sha256":"bda3b3e391f6ed7046a90849b53f6f8773a77ed8908f7f8ad73ae49c2ede6ab2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bda3b3e391f6ed7046a90849b53f6f8773a77ed8908f7f8ad73ae49c2ede6ab2","first_computed_at":"2026-05-17T23:38:52.754552Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:52.754552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5qVzNn0TKKuW2VJoruoyV23uPa1/6Pp7lgikI2DBdtZDoH1235uKR1ZxHQUtprADQVeCHXPJOHylKqEfEAw0Aw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:52.755032Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.15692","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f2a68ddbc671274a3745d4d359063cc5f8af96e6e71a69020f4e4495974c278","sha256:43eca102a4275e336dcf8732eb804a6c422f73ec9c5372f9bad70c3a05084af8"],"state_sha256":"ffe0a53b6c10056befff7aa0d8bd30bc9d862755fcfdbb7073c470ca5f3dd6a7"}