{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DZ4JJS3I6ZEUEI7LLR7EJ2JAQE","short_pith_number":"pith:DZ4JJS3I","schema_version":"1.0","canonical_sha256":"1e7894cb68f6494223eb5c7e44e9208125ecaf63c6b5fc4c26e3ed79df3298b7","source":{"kind":"arxiv","id":"2307.04751","version":1},"attestation_state":"computed","paper":{"title":"Shelving, Stacking, Hanging: Relational Pose Diffusion for Multi-modal Rearrangement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Alberto Rodriguez, Alina Sarmiento, Ankit Goyal, Anthony Simeonov, Dieter Fox, Lin Yen-Chen, Lucas Manuelli, Pulkit Agrawal","submitted_at":"2023-07-10T17:56:06Z","abstract_excerpt":"We propose a system for rearranging objects in a scene to achieve a desired object-scene placing relationship, such as a book inserted in an open slot of a bookshelf. The pipeline generalizes to novel geometries, poses, and layouts of both scenes and objects, and is trained from demonstrations to operate directly on 3D point clouds. Our system overcomes challenges associated with the existence of many geometrically-similar rearrangement solutions for a given scene. By leveraging an iterative pose de-noising training procedure, we can fit multi-modal demonstration data and produce multi-modal o"},"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":"2307.04751","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-07-10T17:56:06Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"4ca206041248ced1479188e37a2d9e484118838384fa5350919d3ec38db8c5c3","abstract_canon_sha256":"577cbf12769fab810bb58c04b6e40c53d1de6de392d30a7edb2ac888cc949ca1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:29:16.917470Z","signature_b64":"QidRgyamcwziPD36gWTs3AO1A9yLmRRGeOi/ysXT1ZLq3klqfyDYihQq7P4HRhChXdDRQKLhfJ8tbecc71WdBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e7894cb68f6494223eb5c7e44e9208125ecaf63c6b5fc4c26e3ed79df3298b7","last_reissued_at":"2026-07-05T06:29:16.916972Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:29:16.916972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Shelving, Stacking, Hanging: Relational Pose Diffusion for Multi-modal Rearrangement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Alberto Rodriguez, Alina Sarmiento, Ankit Goyal, Anthony Simeonov, Dieter Fox, Lin Yen-Chen, Lucas Manuelli, Pulkit Agrawal","submitted_at":"2023-07-10T17:56:06Z","abstract_excerpt":"We propose a system for rearranging objects in a scene to achieve a desired object-scene placing relationship, such as a book inserted in an open slot of a bookshelf. The pipeline generalizes to novel geometries, poses, and layouts of both scenes and objects, and is trained from demonstrations to operate directly on 3D point clouds. Our system overcomes challenges associated with the existence of many geometrically-similar rearrangement solutions for a given scene. By leveraging an iterative pose de-noising training procedure, we can fit multi-modal demonstration data and produce multi-modal o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.04751","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/2307.04751/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":"2307.04751","created_at":"2026-07-05T06:29:16.917031+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.04751v1","created_at":"2026-07-05T06:29:16.917031+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.04751","created_at":"2026-07-05T06:29:16.917031+00:00"},{"alias_kind":"pith_short_12","alias_value":"DZ4JJS3I6ZEU","created_at":"2026-07-05T06:29:16.917031+00:00"},{"alias_kind":"pith_short_16","alias_value":"DZ4JJS3I6ZEUEI7L","created_at":"2026-07-05T06:29:16.917031+00:00"},{"alias_kind":"pith_short_8","alias_value":"DZ4JJS3I","created_at":"2026-07-05T06:29:16.917031+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2402.10885","citing_title":"3D Diffuser Actor: Policy Diffusion with 3D Scene Representations","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2503.10631","citing_title":"HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2403.03954","citing_title":"3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations","ref_index":61,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DZ4JJS3I6ZEUEI7LLR7EJ2JAQE","json":"https://pith.science/pith/DZ4JJS3I6ZEUEI7LLR7EJ2JAQE.json","graph_json":"https://pith.science/api/pith-number/DZ4JJS3I6ZEUEI7LLR7EJ2JAQE/graph.json","events_json":"https://pith.science/api/pith-number/DZ4JJS3I6ZEUEI7LLR7EJ2JAQE/events.json","paper":"https://pith.science/paper/DZ4JJS3I"},"agent_actions":{"view_html":"https://pith.science/pith/DZ4JJS3I6ZEUEI7LLR7EJ2JAQE","download_json":"https://pith.science/pith/DZ4JJS3I6ZEUEI7LLR7EJ2JAQE.json","view_paper":"https://pith.science/paper/DZ4JJS3I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.04751&json=true","fetch_graph":"https://pith.science/api/pith-number/DZ4JJS3I6ZEUEI7LLR7EJ2JAQE/graph.json","fetch_events":"https://pith.science/api/pith-number/DZ4JJS3I6ZEUEI7LLR7EJ2JAQE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DZ4JJS3I6ZEUEI7LLR7EJ2JAQE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DZ4JJS3I6ZEUEI7LLR7EJ2JAQE/action/storage_attestation","attest_author":"https://pith.science/pith/DZ4JJS3I6ZEUEI7LLR7EJ2JAQE/action/author_attestation","sign_citation":"https://pith.science/pith/DZ4JJS3I6ZEUEI7LLR7EJ2JAQE/action/citation_signature","submit_replication":"https://pith.science/pith/DZ4JJS3I6ZEUEI7LLR7EJ2JAQE/action/replication_record"}},"created_at":"2026-07-05T06:29:16.917031+00:00","updated_at":"2026-07-05T06:29:16.917031+00:00"}