{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:O267LUJOGN5IYWUY7BDZMZDJ4J","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":"24094a30e136f8fab56359222a55aad40dbd45abc41db9627be03ed5847c7edb","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-25T09:39:13Z","title_canon_sha256":"c089989a5b55d15a8f4eb6090a3b6b910ab16ef582bd500af2ff23ca904c00fa"},"schema_version":"1.0","source":{"id":"2605.25638","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.25638","created_at":"2026-05-26T02:04:47Z"},{"alias_kind":"arxiv_version","alias_value":"2605.25638v1","created_at":"2026-05-26T02:04:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25638","created_at":"2026-05-26T02:04:47Z"},{"alias_kind":"pith_short_12","alias_value":"O267LUJOGN5I","created_at":"2026-05-26T02:04:47Z"},{"alias_kind":"pith_short_16","alias_value":"O267LUJOGN5IYWUY","created_at":"2026-05-26T02:04:47Z"},{"alias_kind":"pith_short_8","alias_value":"O267LUJO","created_at":"2026-05-26T02:04:47Z"}],"graph_snapshots":[{"event_id":"sha256:d599006db65ff0afdd000ebbc67e89ef42d2a10a18ea0df41acabd6d485ce6f9","target":"graph","created_at":"2026-05-26T02:04:47Z","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/2605.25638/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Policy loss estimation remains a fundamental and long-standing challenge in reinforcement learning (RL) for diffusion language models (dLLMs). We introduce Reinforcement Learning from Denoising Feedback (RLDF), a novel training paradigm that leverages feedback obtained from rollout and training processes to facilitate accurate and efficient policy loss estimation. To balance the trade-off between computational efficiency and estimation effectiveness, RLDF optimizes the model toward the clipped clean state $\\hat{x}_0$ from intermediate noisy states $x_t$, combined with weighted timestep samplin","authors_text":"Baojian Zhou, Huan Chen, Huijia Zhu, Qi He, Ya Guo, Yi R. Fung","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-25T09:39:13Z","title":"Reinforcement Learning from Denoising Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25638","kind":"arxiv","version":1},"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:ce6d31f26d8bba9de41607ae163c63cb148a851d9720a9a8a8a4f4b3e7e2a689","target":"record","created_at":"2026-05-26T02:04:47Z","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":"24094a30e136f8fab56359222a55aad40dbd45abc41db9627be03ed5847c7edb","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-25T09:39:13Z","title_canon_sha256":"c089989a5b55d15a8f4eb6090a3b6b910ab16ef582bd500af2ff23ca904c00fa"},"schema_version":"1.0","source":{"id":"2605.25638","kind":"arxiv","version":1}},"canonical_sha256":"76bdf5d12e337a8c5a98f847966469e2505648a00cc70e9faacb40db893e8baa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"76bdf5d12e337a8c5a98f847966469e2505648a00cc70e9faacb40db893e8baa","first_computed_at":"2026-05-26T02:04:47.643614Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:04:47.643614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vAP/K8T8aDwK7+BK3Od9aOkepIxm0MVRuZx6excQySEg6BZ7FKUAKnjSCT5P7JqFRrW7YLrp163qZVHhHm6GCQ==","signature_status":"signed_v1","signed_at":"2026-05-26T02:04:47.644228Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.25638","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce6d31f26d8bba9de41607ae163c63cb148a851d9720a9a8a8a4f4b3e7e2a689","sha256:d599006db65ff0afdd000ebbc67e89ef42d2a10a18ea0df41acabd6d485ce6f9"],"state_sha256":"a1804fc8764057699fd412495cdf2098629b3f302704fd83d07a7d72c5b793b3"}