{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VZUJOR7ENLV4F5HWRREAC3HFN6","short_pith_number":"pith:VZUJOR7E","schema_version":"1.0","canonical_sha256":"ae689747e46aebc2f4f68c48016ce56f8d2666ada993976d357381d61b9533af","source":{"kind":"arxiv","id":"2509.08775","version":2},"attestation_state":"computed","paper":{"title":"Joint Model-based Model-free Diffusion for Planning with Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Danfei Xu, Nadun Ranawaka Arachchige, Shreyas Kousik, Utkarsh A. Mishra, Wonsuhk Jung, Yongxin Chen","submitted_at":"2025-09-10T17:05:16Z","abstract_excerpt":"Model-free diffusion planners have shown great promise for robot motion planning, but practical robotic systems often require combining them with model-based optimization modules to enforce constraints, such as safety. Naively integrating these modules presents compatibility challenges when diffusion's multi-modal outputs behave adversarially to optimization-based modules. To address this, we introduce Joint Model-based Model-free Diffusion (JM2D), a novel generative modeling framework. JM2D formulates module integration as a joint sampling problem to maximize compatibility via an interaction "},"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":"2509.08775","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-09-10T17:05:16Z","cross_cats_sorted":[],"title_canon_sha256":"c75aa52ef4305d2924f208d6f6e9e11f1aec5e8685cf354ea85fabc88070f019","abstract_canon_sha256":"eda74f3bc3376eafb28f2cd17722a3256a462247bc1df24cdf1058b56c31ccd9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:25.214299Z","signature_b64":"caxAqj3wOzgE4wuKDFVKvYX1ELAecx9+mhfOC4xxo/ABlzDDvi1Dv56/6JYocFLvads1otR8FF+w+a6X7Oo2BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae689747e46aebc2f4f68c48016ce56f8d2666ada993976d357381d61b9533af","last_reissued_at":"2026-07-05T12:09:25.213823Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:25.213823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Joint Model-based Model-free Diffusion for Planning with Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Danfei Xu, Nadun Ranawaka Arachchige, Shreyas Kousik, Utkarsh A. Mishra, Wonsuhk Jung, Yongxin Chen","submitted_at":"2025-09-10T17:05:16Z","abstract_excerpt":"Model-free diffusion planners have shown great promise for robot motion planning, but practical robotic systems often require combining them with model-based optimization modules to enforce constraints, such as safety. Naively integrating these modules presents compatibility challenges when diffusion's multi-modal outputs behave adversarially to optimization-based modules. To address this, we introduce Joint Model-based Model-free Diffusion (JM2D), a novel generative modeling framework. JM2D formulates module integration as a joint sampling problem to maximize compatibility via an interaction "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.08775","kind":"arxiv","version":2},"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/2509.08775/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":"2509.08775","created_at":"2026-07-05T12:09:25.213877+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.08775v2","created_at":"2026-07-05T12:09:25.213877+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.08775","created_at":"2026-07-05T12:09:25.213877+00:00"},{"alias_kind":"pith_short_12","alias_value":"VZUJOR7ENLV4","created_at":"2026-07-05T12:09:25.213877+00:00"},{"alias_kind":"pith_short_16","alias_value":"VZUJOR7ENLV4F5HW","created_at":"2026-07-05T12:09:25.213877+00:00"},{"alias_kind":"pith_short_8","alias_value":"VZUJOR7E","created_at":"2026-07-05T12:09:25.213877+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.24489","citing_title":"Model Predictive Path Integral Control as Preconditioned Gradient Descent","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VZUJOR7ENLV4F5HWRREAC3HFN6","json":"https://pith.science/pith/VZUJOR7ENLV4F5HWRREAC3HFN6.json","graph_json":"https://pith.science/api/pith-number/VZUJOR7ENLV4F5HWRREAC3HFN6/graph.json","events_json":"https://pith.science/api/pith-number/VZUJOR7ENLV4F5HWRREAC3HFN6/events.json","paper":"https://pith.science/paper/VZUJOR7E"},"agent_actions":{"view_html":"https://pith.science/pith/VZUJOR7ENLV4F5HWRREAC3HFN6","download_json":"https://pith.science/pith/VZUJOR7ENLV4F5HWRREAC3HFN6.json","view_paper":"https://pith.science/paper/VZUJOR7E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.08775&json=true","fetch_graph":"https://pith.science/api/pith-number/VZUJOR7ENLV4F5HWRREAC3HFN6/graph.json","fetch_events":"https://pith.science/api/pith-number/VZUJOR7ENLV4F5HWRREAC3HFN6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VZUJOR7ENLV4F5HWRREAC3HFN6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VZUJOR7ENLV4F5HWRREAC3HFN6/action/storage_attestation","attest_author":"https://pith.science/pith/VZUJOR7ENLV4F5HWRREAC3HFN6/action/author_attestation","sign_citation":"https://pith.science/pith/VZUJOR7ENLV4F5HWRREAC3HFN6/action/citation_signature","submit_replication":"https://pith.science/pith/VZUJOR7ENLV4F5HWRREAC3HFN6/action/replication_record"}},"created_at":"2026-07-05T12:09:25.213877+00:00","updated_at":"2026-07-05T12:09:25.213877+00:00"}