{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VLPOZMR6B2TU54GALN6T4DOHIB","short_pith_number":"pith:VLPOZMR6","schema_version":"1.0","canonical_sha256":"aadeecb23e0ea74ef0c05b7d3e0dc74041c1b7c8ed3a413708d33b2e401d2cb4","source":{"kind":"arxiv","id":"2607.24159","version":1},"attestation_state":"computed","paper":{"title":"DeVA: Decoupled Video-Action Model with physical guidance for robot policy learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Judy Hoffman, Mengqi Zhang, Sahil Khose, Simar Kareer, Unnat Jain, Yuchen Song","submitted_at":"2026-07-27T08:37:35Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.24159","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-27T08:37:35Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"153514f450defd65d67933b804e59679f8a7c0b535df3ee9e8ebbab199c5af64","abstract_canon_sha256":"2406b1fb10a6281c6c1a02338f8ba600882961dcf7132257532b92aaee7546ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:23:47.915840Z","signature_b64":"uBHT2YPotmLPGOcw575bm13djk7GHa5CMLepUyWnAt3PSuxbGgByz52ryLWmjsiy1MdzSwDyDNwnW/7bA1GrCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aadeecb23e0ea74ef0c05b7d3e0dc74041c1b7c8ed3a413708d33b2e401d2cb4","last_reissued_at":"2026-07-28T01:23:47.914973Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:23:47.914973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeVA: Decoupled Video-Action Model with physical guidance for robot policy learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Judy Hoffman, Mengqi Zhang, Sahil Khose, Simar Kareer, Unnat Jain, Yuchen Song","submitted_at":"2026-07-27T08:37:35Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24159","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.24159/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.24159","created_at":"2026-07-28T01:23:47.915417+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.24159v1","created_at":"2026-07-28T01:23:47.915417+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24159","created_at":"2026-07-28T01:23:47.915417+00:00"},{"alias_kind":"pith_short_12","alias_value":"VLPOZMR6B2TU","created_at":"2026-07-28T01:23:47.915417+00:00"},{"alias_kind":"pith_short_16","alias_value":"VLPOZMR6B2TU54GA","created_at":"2026-07-28T01:23:47.915417+00:00"},{"alias_kind":"pith_short_8","alias_value":"VLPOZMR6","created_at":"2026-07-28T01:23:47.915417+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VLPOZMR6B2TU54GALN6T4DOHIB","json":"https://pith.science/pith/VLPOZMR6B2TU54GALN6T4DOHIB.json","graph_json":"https://pith.science/api/pith-number/VLPOZMR6B2TU54GALN6T4DOHIB/graph.json","events_json":"https://pith.science/api/pith-number/VLPOZMR6B2TU54GALN6T4DOHIB/events.json","paper":"https://pith.science/paper/VLPOZMR6"},"agent_actions":{"view_html":"https://pith.science/pith/VLPOZMR6B2TU54GALN6T4DOHIB","download_json":"https://pith.science/pith/VLPOZMR6B2TU54GALN6T4DOHIB.json","view_paper":"https://pith.science/paper/VLPOZMR6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.24159&json=true","fetch_graph":"https://pith.science/api/pith-number/VLPOZMR6B2TU54GALN6T4DOHIB/graph.json","fetch_events":"https://pith.science/api/pith-number/VLPOZMR6B2TU54GALN6T4DOHIB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VLPOZMR6B2TU54GALN6T4DOHIB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VLPOZMR6B2TU54GALN6T4DOHIB/action/storage_attestation","attest_author":"https://pith.science/pith/VLPOZMR6B2TU54GALN6T4DOHIB/action/author_attestation","sign_citation":"https://pith.science/pith/VLPOZMR6B2TU54GALN6T4DOHIB/action/citation_signature","submit_replication":"https://pith.science/pith/VLPOZMR6B2TU54GALN6T4DOHIB/action/replication_record"}},"created_at":"2026-07-28T01:23:47.915417+00:00","updated_at":"2026-07-28T01:23:47.915417+00:00"}