{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CT4T3DUPU5UBAEE7Z2KEAJYZYZ","short_pith_number":"pith:CT4T3DUP","schema_version":"1.0","canonical_sha256":"14f93d8e8fa76810109fce94402719c64edbf75491eda6ca6b1b180e2de40474","source":{"kind":"arxiv","id":"2306.09483","version":1},"attestation_state":"computed","paper":{"title":"R2-Diff: Denoising by diffusion as a refinement of retrieved motion for image-based motion prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Norimichi Ukita, Takeru Oba","submitted_at":"2023-06-15T20:27:06Z","abstract_excerpt":"Image-based motion prediction is one of the essential techniques for robot manipulation. Among the various prediction models, we focus on diffusion models because they have achieved state-of-the-art performance in various applications. In image-based motion prediction, diffusion models stochastically predict contextually appropriate motion by gradually denoising random Gaussian noise based on the image context. While diffusion models are able to predict various motions by changing the random noise, they sometimes fail to predict a contextually appropriate motion based on the image because the "},"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":"2306.09483","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-15T20:27:06Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"5ba054cab7392876fcd4c72dbb5d7153918cf855039af1b0a8d17b21fa826832","abstract_canon_sha256":"2c60fb4bc453421cc121ed5fb579df81ecc5f8e764f733a3dc650c2e83c5d7c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:21:20.444617Z","signature_b64":"+P8OOJMEYcJ5fYwaABTr+p8FLr+128qV5jZNudwclTkvHCUtotpXQfFnuTZ3ED7jT0sS7XWOwbPKRIkYQ9iBAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14f93d8e8fa76810109fce94402719c64edbf75491eda6ca6b1b180e2de40474","last_reissued_at":"2026-07-05T06:21:20.444218Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:21:20.444218Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"R2-Diff: Denoising by diffusion as a refinement of retrieved motion for image-based motion prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Norimichi Ukita, Takeru Oba","submitted_at":"2023-06-15T20:27:06Z","abstract_excerpt":"Image-based motion prediction is one of the essential techniques for robot manipulation. Among the various prediction models, we focus on diffusion models because they have achieved state-of-the-art performance in various applications. In image-based motion prediction, diffusion models stochastically predict contextually appropriate motion by gradually denoising random Gaussian noise based on the image context. While diffusion models are able to predict various motions by changing the random noise, they sometimes fail to predict a contextually appropriate motion based on the image because the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09483","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/2306.09483/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":"2306.09483","created_at":"2026-07-05T06:21:20.444271+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.09483v1","created_at":"2026-07-05T06:21:20.444271+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09483","created_at":"2026-07-05T06:21:20.444271+00:00"},{"alias_kind":"pith_short_12","alias_value":"CT4T3DUPU5UB","created_at":"2026-07-05T06:21:20.444271+00:00"},{"alias_kind":"pith_short_16","alias_value":"CT4T3DUPU5UBAEE7","created_at":"2026-07-05T06:21:20.444271+00:00"},{"alias_kind":"pith_short_8","alias_value":"CT4T3DUP","created_at":"2026-07-05T06:21:20.444271+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.21452","citing_title":"Retrieve-Augmented Generation for Speeding up Diffusion Policy without Additional Training","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CT4T3DUPU5UBAEE7Z2KEAJYZYZ","json":"https://pith.science/pith/CT4T3DUPU5UBAEE7Z2KEAJYZYZ.json","graph_json":"https://pith.science/api/pith-number/CT4T3DUPU5UBAEE7Z2KEAJYZYZ/graph.json","events_json":"https://pith.science/api/pith-number/CT4T3DUPU5UBAEE7Z2KEAJYZYZ/events.json","paper":"https://pith.science/paper/CT4T3DUP"},"agent_actions":{"view_html":"https://pith.science/pith/CT4T3DUPU5UBAEE7Z2KEAJYZYZ","download_json":"https://pith.science/pith/CT4T3DUPU5UBAEE7Z2KEAJYZYZ.json","view_paper":"https://pith.science/paper/CT4T3DUP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.09483&json=true","fetch_graph":"https://pith.science/api/pith-number/CT4T3DUPU5UBAEE7Z2KEAJYZYZ/graph.json","fetch_events":"https://pith.science/api/pith-number/CT4T3DUPU5UBAEE7Z2KEAJYZYZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CT4T3DUPU5UBAEE7Z2KEAJYZYZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CT4T3DUPU5UBAEE7Z2KEAJYZYZ/action/storage_attestation","attest_author":"https://pith.science/pith/CT4T3DUPU5UBAEE7Z2KEAJYZYZ/action/author_attestation","sign_citation":"https://pith.science/pith/CT4T3DUPU5UBAEE7Z2KEAJYZYZ/action/citation_signature","submit_replication":"https://pith.science/pith/CT4T3DUPU5UBAEE7Z2KEAJYZYZ/action/replication_record"}},"created_at":"2026-07-05T06:21:20.444271+00:00","updated_at":"2026-07-05T06:21:20.444271+00:00"}