{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:V3OY7J4UIISOY2UL3F5DB2G3W6","short_pith_number":"pith:V3OY7J4U","schema_version":"1.0","canonical_sha256":"aedd8fa7944224ec6a8bd97a30e8dbb7bc555e2342e4e1143345c14a5328c37a","source":{"kind":"arxiv","id":"2402.06559","version":2},"attestation_state":"computed","paper":{"title":"Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous Driving and Zero-Shot Instruction Following","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.RO"],"primary_cat":"cs.LG","authors_text":"Ayush Jain, Brian Yang, Huangyuan Su, Jeff Schneider, Katerina Fragkiadaki, Nikolaos Gkanatsios, Tsung-Wei Ke","submitted_at":"2024-02-09T17:18:33Z","abstract_excerpt":"Diffusion models excel at modeling complex and multimodal trajectory distributions for decision-making and control. Reward-gradient guided denoising has been recently proposed to generate trajectories that maximize both a differentiable reward function and the likelihood under the data distribution captured by a diffusion model. Reward-gradient guided denoising requires a differentiable reward function fitted to both clean and noised samples, limiting its applicability as a general trajectory optimizer. In this paper, we propose DiffusionES, a method that combines gradient-free optimization wi"},"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":"2402.06559","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-09T17:18:33Z","cross_cats_sorted":["cs.AI","cs.CL","cs.RO"],"title_canon_sha256":"3fd8233022a6f3a95236d04dbee79cfa31152e1b056c9ab11d82bd7f2c66d5b1","abstract_canon_sha256":"97da7a0bae9af7edd4247736f92f3e1a5c1d977c85b86877e3b7db5edb54f5ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:50.877643Z","signature_b64":"pluQm5ZeDU4hPZ0xIwL2HJHMFKpPlwjhHe5wF0tCIPL4TMFWycLINRAIoMJylB7QKTdG4wZpf5oMlJmI6ezIAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aedd8fa7944224ec6a8bd97a30e8dbb7bc555e2342e4e1143345c14a5328c37a","last_reissued_at":"2026-07-05T08:44:50.877209Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:50.877209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous Driving and Zero-Shot Instruction Following","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.RO"],"primary_cat":"cs.LG","authors_text":"Ayush Jain, Brian Yang, Huangyuan Su, Jeff Schneider, Katerina Fragkiadaki, Nikolaos Gkanatsios, Tsung-Wei Ke","submitted_at":"2024-02-09T17:18:33Z","abstract_excerpt":"Diffusion models excel at modeling complex and multimodal trajectory distributions for decision-making and control. Reward-gradient guided denoising has been recently proposed to generate trajectories that maximize both a differentiable reward function and the likelihood under the data distribution captured by a diffusion model. Reward-gradient guided denoising requires a differentiable reward function fitted to both clean and noised samples, limiting its applicability as a general trajectory optimizer. In this paper, we propose DiffusionES, a method that combines gradient-free optimization wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.06559","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/2402.06559/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":"2402.06559","created_at":"2026-07-05T08:44:50.877268+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.06559v2","created_at":"2026-07-05T08:44:50.877268+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.06559","created_at":"2026-07-05T08:44:50.877268+00:00"},{"alias_kind":"pith_short_12","alias_value":"V3OY7J4UIISO","created_at":"2026-07-05T08:44:50.877268+00:00"},{"alias_kind":"pith_short_16","alias_value":"V3OY7J4UIISOY2UL","created_at":"2026-07-05T08:44:50.877268+00:00"},{"alias_kind":"pith_short_8","alias_value":"V3OY7J4U","created_at":"2026-07-05T08:44:50.877268+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07693","citing_title":"Selective Timestep Weighting and Advantage-Based Replay for Sample-Efficient Diffusion RLHF","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2402.10885","citing_title":"3D Diffuser Actor: Policy Diffusion with 3D Scene Representations","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V3OY7J4UIISOY2UL3F5DB2G3W6","json":"https://pith.science/pith/V3OY7J4UIISOY2UL3F5DB2G3W6.json","graph_json":"https://pith.science/api/pith-number/V3OY7J4UIISOY2UL3F5DB2G3W6/graph.json","events_json":"https://pith.science/api/pith-number/V3OY7J4UIISOY2UL3F5DB2G3W6/events.json","paper":"https://pith.science/paper/V3OY7J4U"},"agent_actions":{"view_html":"https://pith.science/pith/V3OY7J4UIISOY2UL3F5DB2G3W6","download_json":"https://pith.science/pith/V3OY7J4UIISOY2UL3F5DB2G3W6.json","view_paper":"https://pith.science/paper/V3OY7J4U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.06559&json=true","fetch_graph":"https://pith.science/api/pith-number/V3OY7J4UIISOY2UL3F5DB2G3W6/graph.json","fetch_events":"https://pith.science/api/pith-number/V3OY7J4UIISOY2UL3F5DB2G3W6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V3OY7J4UIISOY2UL3F5DB2G3W6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V3OY7J4UIISOY2UL3F5DB2G3W6/action/storage_attestation","attest_author":"https://pith.science/pith/V3OY7J4UIISOY2UL3F5DB2G3W6/action/author_attestation","sign_citation":"https://pith.science/pith/V3OY7J4UIISOY2UL3F5DB2G3W6/action/citation_signature","submit_replication":"https://pith.science/pith/V3OY7J4UIISOY2UL3F5DB2G3W6/action/replication_record"}},"created_at":"2026-07-05T08:44:50.877268+00:00","updated_at":"2026-07-05T08:44:50.877268+00:00"}