{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6XAIUR2GYONFPTZCI4R7XQDBSB","short_pith_number":"pith:6XAIUR2G","schema_version":"1.0","canonical_sha256":"f5c08a4746c39a57cf224723fbc061904754c270534347d31de2c1010049c53d","source":{"kind":"arxiv","id":"2605.14274","version":1},"attestation_state":"computed","paper":{"title":"CreFlow: Corrective Reflow for Sparse-Reward Embodied Video Diffusion RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"CreFlow uses automatically generated Linear Temporal Logic rewards plus corrective reflow to align video diffusion rollouts with embodied task rules and lift downstream success 23.8 points.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Minshuo Chen, Philip Torr, Qi Zhu, Ruochen Jiao, Simon Sinong Zhan, Sipeng Chen, Yijiang Li, Zhaoran Wang, Zhenfei Yin, Zhenyang Ni","submitted_at":"2026-05-14T02:18:58Z","abstract_excerpt":"Video generation models trained on heterogeneous data with likelihood-surrogate objectives can produce visually plausible rollouts that violate physical constraints in embodied manipulation. Although reinforcement-learning post-training offers a natural route to adapting VGMs, existing video-RL rewards often reduce each rollout to a low-level visual metric, whereas manipulation video evaluation requires logic-based verification of whether the rollout satisfies a compositional task specification. To fill this gap, we introduce a compositional constraint-based reward model for post-training embo"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.14274","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T02:18:58Z","cross_cats_sorted":[],"title_canon_sha256":"1b215cebce7d0e38ab236f9d44487c275a2e490f5694c52f84d4a62268eba5b7","abstract_canon_sha256":"37ec7e054359b823a87cddfe110a26171fcb72f316bcafd8535a8a9165226c43"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:10.362867Z","signature_b64":"1uOy3fas62FfRGgehF44zZbuFBaRK8bMArkAjSGH25mxFaxpYBzT3jJ32crAZ6qpWm0hcuG4apieGcRN+YZ1Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5c08a4746c39a57cf224723fbc061904754c270534347d31de2c1010049c53d","last_reissued_at":"2026-05-17T23:39:10.362385Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:10.362385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CreFlow: Corrective Reflow for Sparse-Reward Embodied Video Diffusion RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"CreFlow uses automatically generated Linear Temporal Logic rewards plus corrective reflow to align video diffusion rollouts with embodied task rules and lift downstream success 23.8 points.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Minshuo Chen, Philip Torr, Qi Zhu, Ruochen Jiao, Simon Sinong Zhan, Sipeng Chen, Yijiang Li, Zhaoran Wang, Zhenfei Yin, Zhenyang Ni","submitted_at":"2026-05-14T02:18:58Z","abstract_excerpt":"Video generation models trained on heterogeneous data with likelihood-surrogate objectives can produce visually plausible rollouts that violate physical constraints in embodied manipulation. Although reinforcement-learning post-training offers a natural route to adapting VGMs, existing video-RL rewards often reduce each rollout to a low-level visual metric, whereas manipulation video evaluation requires logic-based verification of whether the rollout satisfies a compositional task specification. To fill this gap, we introduce a compositional constraint-based reward model for post-training embo"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"CreFlow yields reward judgments better aligned with human and simulator success labels than existing methods and improves downstream execution success by 23.8 percentage points across eight bimanual manipulation tasks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the automatically formulated LTL constraints provide faithful, localized rewards without significant manual engineering or domain-specific tuning, and that the corrective reflow loss reliably stabilizes high-dimensional video diffusion updates in practice.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CreFlow combines LTL compositional rewards with credit-aware NFT and corrective reflow losses in online RL to improve embodied video diffusion models, raising downstream task success by 23.8 percentage points on eight bimanual manipulation tasks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"CreFlow uses automatically generated Linear Temporal Logic rewards plus corrective reflow to align video diffusion rollouts with embodied task rules and lift downstream success 23.8 points.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"5405d3fb8d76c379c503dbd93c2b52aef0705e2d5dd43454a5346bafcef8f514"},"source":{"id":"2605.14274","kind":"arxiv","version":1},"verdict":{"id":"aef9cafb-2caf-4f66-bc8b-d1974185da61","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T02:39:41.086820Z","strongest_claim":"CreFlow yields reward judgments better aligned with human and simulator success labels than existing methods and improves downstream execution success by 23.8 percentage points across eight bimanual manipulation tasks.","one_line_summary":"CreFlow combines LTL compositional rewards with credit-aware NFT and corrective reflow losses in online RL to improve embodied video diffusion models, raising downstream task success by 23.8 percentage points on eight bimanual manipulation tasks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the automatically formulated LTL constraints provide faithful, localized rewards without significant manual engineering or domain-specific tuning, and that the corrective reflow loss reliably stabilizes high-dimensional video diffusion updates in practice.","pith_extraction_headline":"CreFlow uses automatically generated Linear Temporal Logic rewards plus corrective reflow to align video diffusion rollouts with embodied task rules and lift downstream success 23.8 points."},"references":{"count":45,"sample":[{"doi":"","year":2025,"title":"Cosmos World Foundation Model Platform for Physical AI","work_id":"a2dba24c-318d-476a-8b21-4289c265810c","ref_index":1,"cited_arxiv_id":"2501.03575","is_internal_anchor":true},{"doi":"","year":2024,"title":"Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation","work_id":"a3bde288-aace-40db-8067-3ae6656f9509","ref_index":2,"cited_arxiv_id":"2409.16283","is_internal_anchor":true},{"doi":"","year":2025,"title":"Motus: A Unified Latent Action World Model","work_id":"d0b2d257-524d-4d67-9daf-5fb43e5e977a","ref_index":3,"cited_arxiv_id":"2512.13030","is_internal_anchor":true},{"doi":"","year":2025,"title":"$\\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization","work_id":"d1ad7304-d09a-49bc-809e-846439f6aff9","ref_index":4,"cited_arxiv_id":"2504.16054","is_internal_anchor":true},{"doi":"","year":2025,"title":"SAM 3: Segment Anything with Concepts","work_id":"4a72a006-2592-4554-aad0-a9c41a9f952d","ref_index":5,"cited_arxiv_id":"2511.16719","is_internal_anchor":true}],"resolved_work":45,"snapshot_sha256":"be34ede198d7cb0d7c3623048847cb2d8608395687bd45f9d6bafc3afd597210","internal_anchors":22},"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":"2605.14274","created_at":"2026-05-17T23:39:10.362464+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14274v1","created_at":"2026-05-17T23:39:10.362464+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14274","created_at":"2026-05-17T23:39:10.362464+00:00"},{"alias_kind":"pith_short_12","alias_value":"6XAIUR2GYONF","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"6XAIUR2GYONFPTZC","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"6XAIUR2G","created_at":"2026-05-18T12:33:37.589309+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/6XAIUR2GYONFPTZCI4R7XQDBSB","json":"https://pith.science/pith/6XAIUR2GYONFPTZCI4R7XQDBSB.json","graph_json":"https://pith.science/api/pith-number/6XAIUR2GYONFPTZCI4R7XQDBSB/graph.json","events_json":"https://pith.science/api/pith-number/6XAIUR2GYONFPTZCI4R7XQDBSB/events.json","paper":"https://pith.science/paper/6XAIUR2G"},"agent_actions":{"view_html":"https://pith.science/pith/6XAIUR2GYONFPTZCI4R7XQDBSB","download_json":"https://pith.science/pith/6XAIUR2GYONFPTZCI4R7XQDBSB.json","view_paper":"https://pith.science/paper/6XAIUR2G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14274&json=true","fetch_graph":"https://pith.science/api/pith-number/6XAIUR2GYONFPTZCI4R7XQDBSB/graph.json","fetch_events":"https://pith.science/api/pith-number/6XAIUR2GYONFPTZCI4R7XQDBSB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6XAIUR2GYONFPTZCI4R7XQDBSB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6XAIUR2GYONFPTZCI4R7XQDBSB/action/storage_attestation","attest_author":"https://pith.science/pith/6XAIUR2GYONFPTZCI4R7XQDBSB/action/author_attestation","sign_citation":"https://pith.science/pith/6XAIUR2GYONFPTZCI4R7XQDBSB/action/citation_signature","submit_replication":"https://pith.science/pith/6XAIUR2GYONFPTZCI4R7XQDBSB/action/replication_record"}},"created_at":"2026-05-17T23:39:10.362464+00:00","updated_at":"2026-05-17T23:39:10.362464+00:00"}