{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZIMSZ76EAAQUTPM3FS2QHI4YWC","short_pith_number":"pith:ZIMSZ76E","schema_version":"1.0","canonical_sha256":"ca192cffc4002149bd9b2cb503a398b09f5b554f6b88c2749ef67f38bee32357","source":{"kind":"arxiv","id":"2411.18179","version":1},"attestation_state":"computed","paper":{"title":"Prediction with Action: Visual Policy Learning via Joint Denoising Process","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Chaochao Lu, Jianke Zhang, Jianyu Chen, Xiaoyu Chen, Yanjiang Guo, Yen-Jen Wang, Yucheng Hu","submitted_at":"2024-11-27T09:54:58Z","abstract_excerpt":"Diffusion models have demonstrated remarkable capabilities in image generation tasks, including image editing and video creation, representing a good understanding of the physical world. On the other line, diffusion models have also shown promise in robotic control tasks by denoising actions, known as diffusion policy. Although the diffusion generative model and diffusion policy exhibit distinct capabilities--image prediction and robotic action, respectively--they technically follow a similar denoising process. In robotic tasks, the ability to predict future images and generate actions is high"},"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":"2411.18179","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-11-27T09:54:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"054f1ae7eeb97ac235b22d2b7e4702ad78b0d8cfda9eb31b7d92ab0ebd514b76","abstract_canon_sha256":"d8ef8bc4865ea5ea375cf9040da1933800fbe34ae44a8ccc30b3f95268aecaed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:13.019383Z","signature_b64":"o70niRRie+Ij/PaNgsU8BeHICh7OzLTFVCTdKVs4VhrnDiZK5oLE26zsgj5z77BFgvOX+DlP4vzgeA/1ac+VDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca192cffc4002149bd9b2cb503a398b09f5b554f6b88c2749ef67f38bee32357","last_reissued_at":"2026-07-05T09:41:13.018900Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:13.018900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prediction with Action: Visual Policy Learning via Joint Denoising Process","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Chaochao Lu, Jianke Zhang, Jianyu Chen, Xiaoyu Chen, Yanjiang Guo, Yen-Jen Wang, Yucheng Hu","submitted_at":"2024-11-27T09:54:58Z","abstract_excerpt":"Diffusion models have demonstrated remarkable capabilities in image generation tasks, including image editing and video creation, representing a good understanding of the physical world. On the other line, diffusion models have also shown promise in robotic control tasks by denoising actions, known as diffusion policy. Although the diffusion generative model and diffusion policy exhibit distinct capabilities--image prediction and robotic action, respectively--they technically follow a similar denoising process. In robotic tasks, the ability to predict future images and generate actions is high"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18179","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/2411.18179/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":"2411.18179","created_at":"2026-07-05T09:41:13.018959+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.18179v1","created_at":"2026-07-05T09:41:13.018959+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18179","created_at":"2026-07-05T09:41:13.018959+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZIMSZ76EAAQU","created_at":"2026-07-05T09:41:13.018959+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZIMSZ76EAAQUTPM3","created_at":"2026-07-05T09:41:13.018959+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZIMSZ76E","created_at":"2026-07-05T09:41:13.018959+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07217","citing_title":"Robotic Policy Adaptation via Weight-Space Meta-Learning","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04974","citing_title":"From Video to Control: A Survey of Learning Manipulation Interfaces from Temporal Visual Data","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZIMSZ76EAAQUTPM3FS2QHI4YWC","json":"https://pith.science/pith/ZIMSZ76EAAQUTPM3FS2QHI4YWC.json","graph_json":"https://pith.science/api/pith-number/ZIMSZ76EAAQUTPM3FS2QHI4YWC/graph.json","events_json":"https://pith.science/api/pith-number/ZIMSZ76EAAQUTPM3FS2QHI4YWC/events.json","paper":"https://pith.science/paper/ZIMSZ76E"},"agent_actions":{"view_html":"https://pith.science/pith/ZIMSZ76EAAQUTPM3FS2QHI4YWC","download_json":"https://pith.science/pith/ZIMSZ76EAAQUTPM3FS2QHI4YWC.json","view_paper":"https://pith.science/paper/ZIMSZ76E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.18179&json=true","fetch_graph":"https://pith.science/api/pith-number/ZIMSZ76EAAQUTPM3FS2QHI4YWC/graph.json","fetch_events":"https://pith.science/api/pith-number/ZIMSZ76EAAQUTPM3FS2QHI4YWC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZIMSZ76EAAQUTPM3FS2QHI4YWC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZIMSZ76EAAQUTPM3FS2QHI4YWC/action/storage_attestation","attest_author":"https://pith.science/pith/ZIMSZ76EAAQUTPM3FS2QHI4YWC/action/author_attestation","sign_citation":"https://pith.science/pith/ZIMSZ76EAAQUTPM3FS2QHI4YWC/action/citation_signature","submit_replication":"https://pith.science/pith/ZIMSZ76EAAQUTPM3FS2QHI4YWC/action/replication_record"}},"created_at":"2026-07-05T09:41:13.018959+00:00","updated_at":"2026-07-05T09:41:13.018959+00:00"}