{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4BBRYHH66YYYVN2VJPOB2MX3UN","short_pith_number":"pith:4BBRYHH6","schema_version":"1.0","canonical_sha256":"e0431c1cfef6318ab7554bdc1d32fba3799843d8cab4176b4e73a5b7a7541a8f","source":{"kind":"arxiv","id":"2302.01877","version":2},"attestation_state":"computed","paper":{"title":"AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fei Ni, Masayoshi Tomizuka, Mingyu Ding, Ping Luo, Yao Mu, Zhixuan Liang","submitted_at":"2023-02-03T17:28:59Z","abstract_excerpt":"Diffusion models have demonstrated their powerful generative capability in many tasks, with great potential to serve as a paradigm for offline reinforcement learning. However, the quality of the diffusion model is limited by the insufficient diversity of training data, which hinders the performance of planning and the generalizability to new tasks. This paper introduces AdaptDiffuser, an evolutionary planning method with diffusion that can self-evolve to improve the diffusion model hence a better planner, not only for seen tasks but can also adapt to unseen tasks. AdaptDiffuser enables the gen"},"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":"2302.01877","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-03T17:28:59Z","cross_cats_sorted":[],"title_canon_sha256":"cca2db377e91083f7daf01658251cf8cb46e0a5bbff461b3bfcaf9cc20a9a817","abstract_canon_sha256":"cf3a25f1f7357fad9f712f93cffae56e9152a1bfccab26f5a4d6575d962e69fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:09:33.389791Z","signature_b64":"Hnrgyo0vgBKxteYx8EuNjVjSOnZ9eyPzjdATqkzlVJt5GbCj6XlqG/cvN879G9jc4YAZ9S7+APfE+2lfJXMHAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0431c1cfef6318ab7554bdc1d32fba3799843d8cab4176b4e73a5b7a7541a8f","last_reissued_at":"2026-07-05T06:09:33.389242Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:09:33.389242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fei Ni, Masayoshi Tomizuka, Mingyu Ding, Ping Luo, Yao Mu, Zhixuan Liang","submitted_at":"2023-02-03T17:28:59Z","abstract_excerpt":"Diffusion models have demonstrated their powerful generative capability in many tasks, with great potential to serve as a paradigm for offline reinforcement learning. However, the quality of the diffusion model is limited by the insufficient diversity of training data, which hinders the performance of planning and the generalizability to new tasks. This paper introduces AdaptDiffuser, an evolutionary planning method with diffusion that can self-evolve to improve the diffusion model hence a better planner, not only for seen tasks but can also adapt to unseen tasks. AdaptDiffuser enables the gen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.01877","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/2302.01877/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":"2302.01877","created_at":"2026-07-05T06:09:33.389301+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.01877v2","created_at":"2026-07-05T06:09:33.389301+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.01877","created_at":"2026-07-05T06:09:33.389301+00:00"},{"alias_kind":"pith_short_12","alias_value":"4BBRYHH66YYY","created_at":"2026-07-05T06:09:33.389301+00:00"},{"alias_kind":"pith_short_16","alias_value":"4BBRYHH66YYYVN2V","created_at":"2026-07-05T06:09:33.389301+00:00"},{"alias_kind":"pith_short_8","alias_value":"4BBRYHH6","created_at":"2026-07-05T06:09:33.389301+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16054","citing_title":"Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Making","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16520","citing_title":"Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing","ref_index":133,"is_internal_anchor":false},{"citing_arxiv_id":"2506.15799","citing_title":"Steering Your Diffusion Policy with Latent Space Reinforcement Learning","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2409.00588","citing_title":"Diffusion Policy Policy Optimization","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09999","citing_title":"Muninn: Your Trajectory Diffusion Model But Faster","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09035","citing_title":"Advantage-Guided Diffusion for Model-Based Reinforcement Learning","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08960","citing_title":"Efficient Hierarchical Implicit Flow Q-learning for Offline Goal-conditioned Reinforcement Learning","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4BBRYHH66YYYVN2VJPOB2MX3UN","json":"https://pith.science/pith/4BBRYHH66YYYVN2VJPOB2MX3UN.json","graph_json":"https://pith.science/api/pith-number/4BBRYHH66YYYVN2VJPOB2MX3UN/graph.json","events_json":"https://pith.science/api/pith-number/4BBRYHH66YYYVN2VJPOB2MX3UN/events.json","paper":"https://pith.science/paper/4BBRYHH6"},"agent_actions":{"view_html":"https://pith.science/pith/4BBRYHH66YYYVN2VJPOB2MX3UN","download_json":"https://pith.science/pith/4BBRYHH66YYYVN2VJPOB2MX3UN.json","view_paper":"https://pith.science/paper/4BBRYHH6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.01877&json=true","fetch_graph":"https://pith.science/api/pith-number/4BBRYHH66YYYVN2VJPOB2MX3UN/graph.json","fetch_events":"https://pith.science/api/pith-number/4BBRYHH66YYYVN2VJPOB2MX3UN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4BBRYHH66YYYVN2VJPOB2MX3UN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4BBRYHH66YYYVN2VJPOB2MX3UN/action/storage_attestation","attest_author":"https://pith.science/pith/4BBRYHH66YYYVN2VJPOB2MX3UN/action/author_attestation","sign_citation":"https://pith.science/pith/4BBRYHH66YYYVN2VJPOB2MX3UN/action/citation_signature","submit_replication":"https://pith.science/pith/4BBRYHH66YYYVN2VJPOB2MX3UN/action/replication_record"}},"created_at":"2026-07-05T06:09:33.389301+00:00","updated_at":"2026-07-05T06:09:33.389301+00:00"}