{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LTSPTYUWQT3YETW43MC6QP2PT4","short_pith_number":"pith:LTSPTYUW","schema_version":"1.0","canonical_sha256":"5ce4f9e29684f7824edcdb05e83f4f9f13db0fd9732dc9096130e83302db27d1","source":{"kind":"arxiv","id":"2503.00535","version":1},"attestation_state":"computed","paper":{"title":"What Makes a Good Diffusion Planner for Decision Making?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dongqi Han, Dongsheng Li, Haofei Lu, Yifei Shen","submitted_at":"2025-03-01T15:31:14Z","abstract_excerpt":"Diffusion models have recently shown significant potential in solving decision-making problems, particularly in generating behavior plans -- also known as diffusion planning. While numerous studies have demonstrated the impressive performance of diffusion planning, the mechanisms behind the key components of a good diffusion planner remain unclear and the design choices are highly inconsistent in existing studies. In this work, we address this issue through systematic empirical experiments on diffusion planning in an offline reinforcement learning (RL) setting, providing practical insights int"},"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":"2503.00535","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-01T15:31:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c7a3e172a5d6baa4ff709eb38c981e8b746bf5d7cdd031c0edf33e23844ef33a","abstract_canon_sha256":"42c06f03175842c43e48e250337b100e8ca5783230c4b3459ccddc59c61dbc49"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:24.688489Z","signature_b64":"TVXgh4VD5ptSP7fCo23SOKEJxZjxxZ7DWyK59bRuN9/1mXYlFp3JLbU8bNnsZu4Wjv2vr2ITaONt4syys9SVBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ce4f9e29684f7824edcdb05e83f4f9f13db0fd9732dc9096130e83302db27d1","last_reissued_at":"2026-07-05T10:22:24.687961Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:24.687961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What Makes a Good Diffusion Planner for Decision Making?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dongqi Han, Dongsheng Li, Haofei Lu, Yifei Shen","submitted_at":"2025-03-01T15:31:14Z","abstract_excerpt":"Diffusion models have recently shown significant potential in solving decision-making problems, particularly in generating behavior plans -- also known as diffusion planning. While numerous studies have demonstrated the impressive performance of diffusion planning, the mechanisms behind the key components of a good diffusion planner remain unclear and the design choices are highly inconsistent in existing studies. In this work, we address this issue through systematic empirical experiments on diffusion planning in an offline reinforcement learning (RL) setting, providing practical insights int"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00535","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/2503.00535/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":"2503.00535","created_at":"2026-07-05T10:22:24.688022+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.00535v1","created_at":"2026-07-05T10:22:24.688022+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00535","created_at":"2026-07-05T10:22:24.688022+00:00"},{"alias_kind":"pith_short_12","alias_value":"LTSPTYUWQT3Y","created_at":"2026-07-05T10:22:24.688022+00:00"},{"alias_kind":"pith_short_16","alias_value":"LTSPTYUWQT3YETW4","created_at":"2026-07-05T10:22:24.688022+00:00"},{"alias_kind":"pith_short_8","alias_value":"LTSPTYUW","created_at":"2026-07-05T10:22:24.688022+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10613","citing_title":"Fast and Highly Expressive Policy Learning for Offline Reinforcement Learning via Bootstrapped Flow Q-Learning","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29398","citing_title":"GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19457","citing_title":"Generative Auto-Bidding with Unified Modeling and Exploration","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09999","citing_title":"Muninn: Your Trajectory Diffusion Model But Faster","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LTSPTYUWQT3YETW43MC6QP2PT4","json":"https://pith.science/pith/LTSPTYUWQT3YETW43MC6QP2PT4.json","graph_json":"https://pith.science/api/pith-number/LTSPTYUWQT3YETW43MC6QP2PT4/graph.json","events_json":"https://pith.science/api/pith-number/LTSPTYUWQT3YETW43MC6QP2PT4/events.json","paper":"https://pith.science/paper/LTSPTYUW"},"agent_actions":{"view_html":"https://pith.science/pith/LTSPTYUWQT3YETW43MC6QP2PT4","download_json":"https://pith.science/pith/LTSPTYUWQT3YETW43MC6QP2PT4.json","view_paper":"https://pith.science/paper/LTSPTYUW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.00535&json=true","fetch_graph":"https://pith.science/api/pith-number/LTSPTYUWQT3YETW43MC6QP2PT4/graph.json","fetch_events":"https://pith.science/api/pith-number/LTSPTYUWQT3YETW43MC6QP2PT4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LTSPTYUWQT3YETW43MC6QP2PT4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LTSPTYUWQT3YETW43MC6QP2PT4/action/storage_attestation","attest_author":"https://pith.science/pith/LTSPTYUWQT3YETW43MC6QP2PT4/action/author_attestation","sign_citation":"https://pith.science/pith/LTSPTYUWQT3YETW43MC6QP2PT4/action/citation_signature","submit_replication":"https://pith.science/pith/LTSPTYUWQT3YETW43MC6QP2PT4/action/replication_record"}},"created_at":"2026-07-05T10:22:24.688022+00:00","updated_at":"2026-07-05T10:22:24.688022+00:00"}