{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BWUVATSDI4GMSMAJDSJRAG7ADW","short_pith_number":"pith:BWUVATSD","schema_version":"1.0","canonical_sha256":"0da9504e43470cc930091c93101be01db5ecbd17d36998c2d51d554f3c7ccc54","source":{"kind":"arxiv","id":"2606.10825","version":1},"attestation_state":"computed","paper":{"title":"MODIP: Efficient Model-Based Optimization for Diffusion Policies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Nicolas Thome, Olivier Sigaud, Philippe Gratias-Quiquandon, Zakariae El Asri","submitted_at":"2026-06-09T13:09:21Z","abstract_excerpt":"Diffusion policies (DPs) have emerged as expressive policy representations for robot learning, often used with imitation learning methods such as behavioral cloning (BC). However, while their success has largely been confined to BC, direct reinforcement learning (RL) fine-tuning remains challenging because actions are generated through a multi-step denoising process. In this work, we propose MODIP, a framework for the offline-to-online fine-tuning of DPs. Rather than directly applying RL to the DPs, MODIP leverages a world model (WM) to guide policy adaptation and keeps the simplicity and stab"},"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":"2606.10825","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T13:09:21Z","cross_cats_sorted":[],"title_canon_sha256":"1820731c49e1b7de05bd805a602c4f192b6425248fe6bca261cfdd4259105d89","abstract_canon_sha256":"e07d7f94a730e936f78d5d3ac27d7b0613c7ec40232078f2263765a75fb88c0e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:42.595709Z","signature_b64":"rZy+njjNeXm/riaSHh8kyk2VaufAVStD9uNMrHRZMWAi8+KuOVc04HxHh4905ymIu4kW2cozUPreaNNvtKqbAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0da9504e43470cc930091c93101be01db5ecbd17d36998c2d51d554f3c7ccc54","last_reissued_at":"2026-06-10T01:10:42.594914Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:42.594914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MODIP: Efficient Model-Based Optimization for Diffusion Policies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Nicolas Thome, Olivier Sigaud, Philippe Gratias-Quiquandon, Zakariae El Asri","submitted_at":"2026-06-09T13:09:21Z","abstract_excerpt":"Diffusion policies (DPs) have emerged as expressive policy representations for robot learning, often used with imitation learning methods such as behavioral cloning (BC). However, while their success has largely been confined to BC, direct reinforcement learning (RL) fine-tuning remains challenging because actions are generated through a multi-step denoising process. In this work, we propose MODIP, a framework for the offline-to-online fine-tuning of DPs. Rather than directly applying RL to the DPs, MODIP leverages a world model (WM) to guide policy adaptation and keeps the simplicity and stab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10825","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/2606.10825/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":"2606.10825","created_at":"2026-06-10T01:10:42.595018+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10825v1","created_at":"2026-06-10T01:10:42.595018+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10825","created_at":"2026-06-10T01:10:42.595018+00:00"},{"alias_kind":"pith_short_12","alias_value":"BWUVATSDI4GM","created_at":"2026-06-10T01:10:42.595018+00:00"},{"alias_kind":"pith_short_16","alias_value":"BWUVATSDI4GMSMAJ","created_at":"2026-06-10T01:10:42.595018+00:00"},{"alias_kind":"pith_short_8","alias_value":"BWUVATSD","created_at":"2026-06-10T01:10:42.595018+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/BWUVATSDI4GMSMAJDSJRAG7ADW","json":"https://pith.science/pith/BWUVATSDI4GMSMAJDSJRAG7ADW.json","graph_json":"https://pith.science/api/pith-number/BWUVATSDI4GMSMAJDSJRAG7ADW/graph.json","events_json":"https://pith.science/api/pith-number/BWUVATSDI4GMSMAJDSJRAG7ADW/events.json","paper":"https://pith.science/paper/BWUVATSD"},"agent_actions":{"view_html":"https://pith.science/pith/BWUVATSDI4GMSMAJDSJRAG7ADW","download_json":"https://pith.science/pith/BWUVATSDI4GMSMAJDSJRAG7ADW.json","view_paper":"https://pith.science/paper/BWUVATSD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10825&json=true","fetch_graph":"https://pith.science/api/pith-number/BWUVATSDI4GMSMAJDSJRAG7ADW/graph.json","fetch_events":"https://pith.science/api/pith-number/BWUVATSDI4GMSMAJDSJRAG7ADW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BWUVATSDI4GMSMAJDSJRAG7ADW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BWUVATSDI4GMSMAJDSJRAG7ADW/action/storage_attestation","attest_author":"https://pith.science/pith/BWUVATSDI4GMSMAJDSJRAG7ADW/action/author_attestation","sign_citation":"https://pith.science/pith/BWUVATSDI4GMSMAJDSJRAG7ADW/action/citation_signature","submit_replication":"https://pith.science/pith/BWUVATSDI4GMSMAJDSJRAG7ADW/action/replication_record"}},"created_at":"2026-06-10T01:10:42.595018+00:00","updated_at":"2026-06-10T01:10:42.595018+00:00"}