{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VE6VE7G6N4Z2AFHGWTK4KR2BMX","short_pith_number":"pith:VE6VE7G6","schema_version":"1.0","canonical_sha256":"a93d527cde6f33a014e6b4d5c5474165d7e403128d593f8bb82a650298f8f91f","source":{"kind":"arxiv","id":"2405.18196","version":1},"attestation_state":"computed","paper":{"title":"Render and Diffuse: Aligning Image and Action Spaces for Diffusion-based Behaviour Cloning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Jafar Uru\\c{c}, Stephen James, Vitalis Vosylius, Younggyo Seo","submitted_at":"2024-05-28T14:06:10Z","abstract_excerpt":"In the field of Robot Learning, the complex mapping between high-dimensional observations such as RGB images and low-level robotic actions, two inherently very different spaces, constitutes a complex learning problem, especially with limited amounts of data. In this work, we introduce Render and Diffuse (R&D) a method that unifies low-level robot actions and RGB observations within the image space using virtual renders of the 3D model of the robot. Using this joint observation-action representation it computes low-level robot actions using a learnt diffusion process that iteratively updates th"},"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":"2405.18196","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-05-28T14:06:10Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"fd20288aea782d5b24a7c8b7219372caf001724da5a3ef9cc7e0938eb2e65a63","abstract_canon_sha256":"8e6f119a867fff50ae183a23662aa74e2d0c0b0397442f1ba307abd047d582f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:16.953436Z","signature_b64":"3z5Y+STCA+3qxghedd3zpwvHM35HtkLSQo24ml88d/mqqwR7GFMUKQBJA+V5rZ9H/roKbbzF8wGvp+94mgeWAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a93d527cde6f33a014e6b4d5c5474165d7e403128d593f8bb82a650298f8f91f","last_reissued_at":"2026-07-05T08:24:16.952993Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:16.952993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Render and Diffuse: Aligning Image and Action Spaces for Diffusion-based Behaviour Cloning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Jafar Uru\\c{c}, Stephen James, Vitalis Vosylius, Younggyo Seo","submitted_at":"2024-05-28T14:06:10Z","abstract_excerpt":"In the field of Robot Learning, the complex mapping between high-dimensional observations such as RGB images and low-level robotic actions, two inherently very different spaces, constitutes a complex learning problem, especially with limited amounts of data. In this work, we introduce Render and Diffuse (R&D) a method that unifies low-level robot actions and RGB observations within the image space using virtual renders of the 3D model of the robot. Using this joint observation-action representation it computes low-level robot actions using a learnt diffusion process that iteratively updates th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18196","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/2405.18196/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":"2405.18196","created_at":"2026-07-05T08:24:16.953050+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.18196v1","created_at":"2026-07-05T08:24:16.953050+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18196","created_at":"2026-07-05T08:24:16.953050+00:00"},{"alias_kind":"pith_short_12","alias_value":"VE6VE7G6N4Z2","created_at":"2026-07-05T08:24:16.953050+00:00"},{"alias_kind":"pith_short_16","alias_value":"VE6VE7G6N4Z2AFHG","created_at":"2026-07-05T08:24:16.953050+00:00"},{"alias_kind":"pith_short_8","alias_value":"VE6VE7G6","created_at":"2026-07-05T08:24:16.953050+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.14135","citing_title":"GAF: Gaussian Action Field as a 4D Representation for Dynamic World Modeling in Robotic Manipulation","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06192","citing_title":"EA-WM: Event-Aware Generative World Model with Structured Kinematic-to-Visual Action Fields","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VE6VE7G6N4Z2AFHGWTK4KR2BMX","json":"https://pith.science/pith/VE6VE7G6N4Z2AFHGWTK4KR2BMX.json","graph_json":"https://pith.science/api/pith-number/VE6VE7G6N4Z2AFHGWTK4KR2BMX/graph.json","events_json":"https://pith.science/api/pith-number/VE6VE7G6N4Z2AFHGWTK4KR2BMX/events.json","paper":"https://pith.science/paper/VE6VE7G6"},"agent_actions":{"view_html":"https://pith.science/pith/VE6VE7G6N4Z2AFHGWTK4KR2BMX","download_json":"https://pith.science/pith/VE6VE7G6N4Z2AFHGWTK4KR2BMX.json","view_paper":"https://pith.science/paper/VE6VE7G6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.18196&json=true","fetch_graph":"https://pith.science/api/pith-number/VE6VE7G6N4Z2AFHGWTK4KR2BMX/graph.json","fetch_events":"https://pith.science/api/pith-number/VE6VE7G6N4Z2AFHGWTK4KR2BMX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VE6VE7G6N4Z2AFHGWTK4KR2BMX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VE6VE7G6N4Z2AFHGWTK4KR2BMX/action/storage_attestation","attest_author":"https://pith.science/pith/VE6VE7G6N4Z2AFHGWTK4KR2BMX/action/author_attestation","sign_citation":"https://pith.science/pith/VE6VE7G6N4Z2AFHGWTK4KR2BMX/action/citation_signature","submit_replication":"https://pith.science/pith/VE6VE7G6N4Z2AFHGWTK4KR2BMX/action/replication_record"}},"created_at":"2026-07-05T08:24:16.953050+00:00","updated_at":"2026-07-05T08:24:16.953050+00:00"}