{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TYQ44CJXN3XN4Q7CF6SXOGVGGH","short_pith_number":"pith:TYQ44CJX","schema_version":"1.0","canonical_sha256":"9e21ce09376eeede43e22fa5771aa631dda754a49eb9331980b8fafd6792f213","source":{"kind":"arxiv","id":"2406.00990","version":1},"attestation_state":"computed","paper":{"title":"Constraint-Aware Diffusion Models for Trajectory Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Adji Bousso Dieng, Anjian Li, Ryne Beeson, Zihan Ding","submitted_at":"2024-06-03T04:53:20Z","abstract_excerpt":"The diffusion model has shown success in generating high-quality and diverse solutions to trajectory optimization problems. However, diffusion models with neural networks inevitably make prediction errors, which leads to constraint violations such as unmet goals or collisions. This paper presents a novel constraint-aware diffusion model for trajectory optimization. We introduce a novel hybrid loss function for training that minimizes the constraint violation of diffusion samples compared to the groundtruth while recovering the original data distribution. Our model is demonstrated on tabletop m"},"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":"2406.00990","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-03T04:53:20Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"695d142a9bab44e536e67ec6ed5415d6c47ef1302ff3c6b4fe32296fac5b5076","abstract_canon_sha256":"0bdc1177da2dd385cec9e803a44dba27c04d14b93891ab72805c8f7d682d84e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:33.556334Z","signature_b64":"nbJ8jIBUk+8/Xub0ROPGUZswmd8O+PH7m77rkiEqzhEUorDfQusWMP1/Y+wfYslh7DeOVHMRtpBXb44bR0fFDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e21ce09376eeede43e22fa5771aa631dda754a49eb9331980b8fafd6792f213","last_reissued_at":"2026-07-05T08:26:33.555871Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:33.555871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Constraint-Aware Diffusion Models for Trajectory Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Adji Bousso Dieng, Anjian Li, Ryne Beeson, Zihan Ding","submitted_at":"2024-06-03T04:53:20Z","abstract_excerpt":"The diffusion model has shown success in generating high-quality and diverse solutions to trajectory optimization problems. However, diffusion models with neural networks inevitably make prediction errors, which leads to constraint violations such as unmet goals or collisions. This paper presents a novel constraint-aware diffusion model for trajectory optimization. We introduce a novel hybrid loss function for training that minimizes the constraint violation of diffusion samples compared to the groundtruth while recovering the original data distribution. Our model is demonstrated on tabletop m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00990","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/2406.00990/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":"2406.00990","created_at":"2026-07-05T08:26:33.555945+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.00990v1","created_at":"2026-07-05T08:26:33.555945+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00990","created_at":"2026-07-05T08:26:33.555945+00:00"},{"alias_kind":"pith_short_12","alias_value":"TYQ44CJXN3XN","created_at":"2026-07-05T08:26:33.555945+00:00"},{"alias_kind":"pith_short_16","alias_value":"TYQ44CJXN3XN4Q7C","created_at":"2026-07-05T08:26:33.555945+00:00"},{"alias_kind":"pith_short_8","alias_value":"TYQ44CJX","created_at":"2026-07-05T08:26:33.555945+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.08775","citing_title":"Joint Model-based Model-free Diffusion for Planning with Constraints","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TYQ44CJXN3XN4Q7CF6SXOGVGGH","json":"https://pith.science/pith/TYQ44CJXN3XN4Q7CF6SXOGVGGH.json","graph_json":"https://pith.science/api/pith-number/TYQ44CJXN3XN4Q7CF6SXOGVGGH/graph.json","events_json":"https://pith.science/api/pith-number/TYQ44CJXN3XN4Q7CF6SXOGVGGH/events.json","paper":"https://pith.science/paper/TYQ44CJX"},"agent_actions":{"view_html":"https://pith.science/pith/TYQ44CJXN3XN4Q7CF6SXOGVGGH","download_json":"https://pith.science/pith/TYQ44CJXN3XN4Q7CF6SXOGVGGH.json","view_paper":"https://pith.science/paper/TYQ44CJX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.00990&json=true","fetch_graph":"https://pith.science/api/pith-number/TYQ44CJXN3XN4Q7CF6SXOGVGGH/graph.json","fetch_events":"https://pith.science/api/pith-number/TYQ44CJXN3XN4Q7CF6SXOGVGGH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TYQ44CJXN3XN4Q7CF6SXOGVGGH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TYQ44CJXN3XN4Q7CF6SXOGVGGH/action/storage_attestation","attest_author":"https://pith.science/pith/TYQ44CJXN3XN4Q7CF6SXOGVGGH/action/author_attestation","sign_citation":"https://pith.science/pith/TYQ44CJXN3XN4Q7CF6SXOGVGGH/action/citation_signature","submit_replication":"https://pith.science/pith/TYQ44CJXN3XN4Q7CF6SXOGVGGH/action/replication_record"}},"created_at":"2026-07-05T08:26:33.555945+00:00","updated_at":"2026-07-05T08:26:33.555945+00:00"}