{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CHORUGPRLYMIL466E7WSQZZ3PT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3949e5d71a8128cc30c56d94d5ccdda925e291fb5147cecded9d52619895239e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-09T13:59:50Z","title_canon_sha256":"80e185a0c55dce03ee549eeb16c4013801fcd9a55bcde5732ac9ab8a89dbf9f8"},"schema_version":"1.0","source":{"id":"2510.08233","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.08233","created_at":"2026-07-14T01:20:46Z"},{"alias_kind":"arxiv_version","alias_value":"2510.08233v3","created_at":"2026-07-14T01:20:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.08233","created_at":"2026-07-14T01:20:46Z"},{"alias_kind":"pith_short_12","alias_value":"CHORUGPRLYMI","created_at":"2026-07-14T01:20:46Z"},{"alias_kind":"pith_short_16","alias_value":"CHORUGPRLYMIL466","created_at":"2026-07-14T01:20:46Z"},{"alias_kind":"pith_short_8","alias_value":"CHORUGPR","created_at":"2026-07-14T01:20:46Z"}],"graph_snapshots":[{"event_id":"sha256:bfe250e21781ca608b20c62212dab874e0b6afa87a1947f3060c4ac964357dcd","target":"graph","created_at":"2026-07-14T01:20:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2510.08233/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion large language models (dLLMs) are promising alternatives to autoregressive large language models (AR-LLMs), as they potentially allow higher inference throughput. Reinforcement learning (RL) is crucial to enabling dLLMs to achieve performance comparable to that of AR-LLMs on important tasks, such as reasoning. However, RL algorithms well-suited to dLLMs' unique characteristics have yet to be developed. This paper proposes Distribution Matching Policy Optimization (DMPO), a principled and theoretically grounded RL fine-tuning method specifically designed to enhance the reasoning capab","authors_text":"Bo Yuan, Jaemoo Choi, Molei Tao, Petr Molodyk, Wei Guo, Yongxin Chen, Yuchen Zhu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-09T13:59:50Z","title":"Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.08233","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:284b6191d41a9588f6946e8cd89a469c5d76decd8a51b680637c03cc41f369ae","target":"record","created_at":"2026-07-14T01:20:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3949e5d71a8128cc30c56d94d5ccdda925e291fb5147cecded9d52619895239e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-09T13:59:50Z","title_canon_sha256":"80e185a0c55dce03ee549eeb16c4013801fcd9a55bcde5732ac9ab8a89dbf9f8"},"schema_version":"1.0","source":{"id":"2510.08233","kind":"arxiv","version":3}},"canonical_sha256":"11dd1a19f15e1885f3de27ed28673b7cfc7cfc28f02d25deed2307d39d6abe5b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"11dd1a19f15e1885f3de27ed28673b7cfc7cfc28f02d25deed2307d39d6abe5b","first_computed_at":"2026-07-14T01:20:46.820912Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-14T01:20:46.820912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6rkAWGMtN87oG4hDfWyEIyNjFTZnYgWYLZ+ITNaEW9udDNIAWba2HdsBzLC36M1Wii9JkEax9/EzBxvJbR7hAg==","signature_status":"signed_v1","signed_at":"2026-07-14T01:20:46.821917Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.08233","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:284b6191d41a9588f6946e8cd89a469c5d76decd8a51b680637c03cc41f369ae","sha256:bfe250e21781ca608b20c62212dab874e0b6afa87a1947f3060c4ac964357dcd"],"state_sha256":"ed80a67594b7d0272a75b122a7e18ee335ee04b56333d8fe6349a5eae296e551"}