{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VLPOZMR6B2TU54GALN6T4DOHIB","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":"2406b1fb10a6281c6c1a02338f8ba600882961dcf7132257532b92aaee7546ab","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-27T08:37:35Z","title_canon_sha256":"153514f450defd65d67933b804e59679f8a7c0b535df3ee9e8ebbab199c5af64"},"schema_version":"1.0","source":{"id":"2607.24159","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.24159","created_at":"2026-07-28T01:23:47Z"},{"alias_kind":"arxiv_version","alias_value":"2607.24159v1","created_at":"2026-07-28T01:23:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24159","created_at":"2026-07-28T01:23:47Z"},{"alias_kind":"pith_short_12","alias_value":"VLPOZMR6B2TU","created_at":"2026-07-28T01:23:47Z"},{"alias_kind":"pith_short_16","alias_value":"VLPOZMR6B2TU54GA","created_at":"2026-07-28T01:23:47Z"},{"alias_kind":"pith_short_8","alias_value":"VLPOZMR6","created_at":"2026-07-28T01:23:47Z"}],"graph_snapshots":[{"event_id":"sha256:0453a4c8e9cff49af410a711b675522ea1133bb3907e758f5135cb5656a04f43","target":"graph","created_at":"2026-07-28T01:23:47Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.24159/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generalizable robot manipulation requires policies that can anticipate how visual scenes evolve while executing language instructions. While recent Vision-Language-Action models benefit from large-scale pretraining, their predominantly static pretraining objectives provide limited supervision for physical dynamics and temporal causality, leaving control-relevant knowledge to be learned from downstream robot demonstrations. Video generative models offer a promising foundation by encoding rich spatiotemporal priors through future predictions. However, existing Video-Action Models either couple v","authors_text":"Judy Hoffman, Mengqi Zhang, Sahil Khose, Simar Kareer, Unnat Jain, Yuchen Song","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-27T08:37:35Z","title":"DeVA: Decoupled Video-Action Model with physical guidance for robot policy learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24159","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f11b473feae036b1789bcf708e3b662c61e5ca6be24ed05917094c171a971f98","target":"record","created_at":"2026-07-28T01:23:47Z","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":"2406b1fb10a6281c6c1a02338f8ba600882961dcf7132257532b92aaee7546ab","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-27T08:37:35Z","title_canon_sha256":"153514f450defd65d67933b804e59679f8a7c0b535df3ee9e8ebbab199c5af64"},"schema_version":"1.0","source":{"id":"2607.24159","kind":"arxiv","version":1}},"canonical_sha256":"aadeecb23e0ea74ef0c05b7d3e0dc74041c1b7c8ed3a413708d33b2e401d2cb4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aadeecb23e0ea74ef0c05b7d3e0dc74041c1b7c8ed3a413708d33b2e401d2cb4","first_computed_at":"2026-07-28T01:23:47.914973Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T01:23:47.914973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uBHT2YPotmLPGOcw575bm13djk7GHa5CMLepUyWnAt3PSuxbGgByz52ryLWmjsiy1MdzSwDyDNwnW/7bA1GrCA==","signature_status":"signed_v1","signed_at":"2026-07-28T01:23:47.915840Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.24159","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f11b473feae036b1789bcf708e3b662c61e5ca6be24ed05917094c171a971f98","sha256:0453a4c8e9cff49af410a711b675522ea1133bb3907e758f5135cb5656a04f43"],"state_sha256":"0510b9fd4b697369c6678426bfaa2912e045208468ac311d54a2d7c7e624778c"}