{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LBUE6WJT3BX3JBMBWNB5P77JXJ","short_pith_number":"pith:LBUE6WJT","schema_version":"1.0","canonical_sha256":"58684f5933d86fb48581b343d7ffe9ba59a22dff193cebc285d8d03a47083e53","source":{"kind":"arxiv","id":"2505.20350","version":1},"attestation_state":"computed","paper":{"title":"Decision Flow Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dacheng Tao, Hechang Chen, Jifeng Hu, Lichao Sun, Li Shen, Sili Huang, Siyuan Guo, Yi Chang, Zhaogeng Liu","submitted_at":"2025-05-26T03:42:20Z","abstract_excerpt":"In recent years, generative models have shown remarkable capabilities across diverse fields, including images, videos, language, and decision-making. By applying powerful generative models such as flow-based models to reinforcement learning, we can effectively model complex multi-modal action distributions and achieve superior robotic control in continuous action spaces, surpassing the limitations of single-modal action distributions with traditional Gaussian-based policies. Previous methods usually adopt the generative models as behavior models to fit state-conditioned action distributions fr"},"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":"2505.20350","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T03:42:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c2003174f9036bbdebbde68eb4894acc6af6b7048e1cb727989c1d988b13c5e8","abstract_canon_sha256":"6b55fd0c3b8fd8b531112b08d3c99c5a3b038e3216837d337c031f1957a2dc06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:11.637879Z","signature_b64":"zpWBai2aBdcRcIKG4lyHFBXLYUEGQHXlXzYBNkly24T4R5/ma+aLt2sfzqS9cueRF30eUzK5gYS6sozhGDbWAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58684f5933d86fb48581b343d7ffe9ba59a22dff193cebc285d8d03a47083e53","last_reissued_at":"2026-07-05T11:10:11.637339Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:11.637339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decision Flow Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dacheng Tao, Hechang Chen, Jifeng Hu, Lichao Sun, Li Shen, Sili Huang, Siyuan Guo, Yi Chang, Zhaogeng Liu","submitted_at":"2025-05-26T03:42:20Z","abstract_excerpt":"In recent years, generative models have shown remarkable capabilities across diverse fields, including images, videos, language, and decision-making. By applying powerful generative models such as flow-based models to reinforcement learning, we can effectively model complex multi-modal action distributions and achieve superior robotic control in continuous action spaces, surpassing the limitations of single-modal action distributions with traditional Gaussian-based policies. Previous methods usually adopt the generative models as behavior models to fit state-conditioned action distributions fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20350","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/2505.20350/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":"2505.20350","created_at":"2026-07-05T11:10:11.637407+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20350v1","created_at":"2026-07-05T11:10:11.637407+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20350","created_at":"2026-07-05T11:10:11.637407+00:00"},{"alias_kind":"pith_short_12","alias_value":"LBUE6WJT3BX3","created_at":"2026-07-05T11:10:11.637407+00:00"},{"alias_kind":"pith_short_16","alias_value":"LBUE6WJT3BX3JBMB","created_at":"2026-07-05T11:10:11.637407+00:00"},{"alias_kind":"pith_short_8","alias_value":"LBUE6WJT","created_at":"2026-07-05T11:10:11.637407+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LBUE6WJT3BX3JBMBWNB5P77JXJ","json":"https://pith.science/pith/LBUE6WJT3BX3JBMBWNB5P77JXJ.json","graph_json":"https://pith.science/api/pith-number/LBUE6WJT3BX3JBMBWNB5P77JXJ/graph.json","events_json":"https://pith.science/api/pith-number/LBUE6WJT3BX3JBMBWNB5P77JXJ/events.json","paper":"https://pith.science/paper/LBUE6WJT"},"agent_actions":{"view_html":"https://pith.science/pith/LBUE6WJT3BX3JBMBWNB5P77JXJ","download_json":"https://pith.science/pith/LBUE6WJT3BX3JBMBWNB5P77JXJ.json","view_paper":"https://pith.science/paper/LBUE6WJT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20350&json=true","fetch_graph":"https://pith.science/api/pith-number/LBUE6WJT3BX3JBMBWNB5P77JXJ/graph.json","fetch_events":"https://pith.science/api/pith-number/LBUE6WJT3BX3JBMBWNB5P77JXJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LBUE6WJT3BX3JBMBWNB5P77JXJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LBUE6WJT3BX3JBMBWNB5P77JXJ/action/storage_attestation","attest_author":"https://pith.science/pith/LBUE6WJT3BX3JBMBWNB5P77JXJ/action/author_attestation","sign_citation":"https://pith.science/pith/LBUE6WJT3BX3JBMBWNB5P77JXJ/action/citation_signature","submit_replication":"https://pith.science/pith/LBUE6WJT3BX3JBMBWNB5P77JXJ/action/replication_record"}},"created_at":"2026-07-05T11:10:11.637407+00:00","updated_at":"2026-07-05T11:10:11.637407+00:00"}