{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:N2FRBV56TROXFTCWTPIGOS6HCI","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":"854d1cc9ef29c643f3d276e058250d57ea58a4955fe3f4d963927b08b793b1d6","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-08T01:02:31Z","title_canon_sha256":"dfc5bc991983809445c4c9288496665c82d5f42837fa7185f7552ddff4b3790f"},"schema_version":"1.0","source":{"id":"2605.16342","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16342","created_at":"2026-05-20T00:02:17Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16342v1","created_at":"2026-05-20T00:02:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16342","created_at":"2026-05-20T00:02:17Z"},{"alias_kind":"pith_short_12","alias_value":"N2FRBV56TROX","created_at":"2026-05-20T00:02:17Z"},{"alias_kind":"pith_short_16","alias_value":"N2FRBV56TROXFTCW","created_at":"2026-05-20T00:02:17Z"},{"alias_kind":"pith_short_8","alias_value":"N2FRBV56","created_at":"2026-05-20T00:02:17Z"}],"graph_snapshots":[{"event_id":"sha256:8279bf06f907e5e431114b6cfd77fc8d76e0fe6cb220e9b40d0625b5f11e9b6f","target":"graph","created_at":"2026-05-20T00:02:17Z","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/2605.16342/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion large language models are a compelling alternative to autoregressive models, yet existing RL methods for diffusion treat all denoising steps as equally important and rely on biased, high-variance likelihood estimates. We identify two fundamental weaknesses: the absence of temporal credit assignment across the denoising trajectory, and the systematic bias of mean-field likelihood estimates used for policy optimization. To address these, we propose Denoising-Aware Credit Assignment for GRPO (DACA-GRPO), a lightweight, plug-and-play enhancement for any GRPO-style trainer. DACA-GRPO intr","authors_text":"Amin Karimi Monsefi, Dominic Culver, Irina Belousova, Lokesh Boominathan, Manuel R. Ciosici, Nikhil Bhendawade, Yizhe Zhang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-08T01:02:31Z","title":"DACA-GRPO: Denoising-Aware Credit Assignment for Reinforcement Learning in Diffusion Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16342","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":"sha256:32ec5497dc3cd56dfbc9eef85dbf3dd5b31247d71b0662c4dae367e99bee6071","target":"record","created_at":"2026-05-20T00:02:17Z","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":"854d1cc9ef29c643f3d276e058250d57ea58a4955fe3f4d963927b08b793b1d6","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-08T01:02:31Z","title_canon_sha256":"dfc5bc991983809445c4c9288496665c82d5f42837fa7185f7552ddff4b3790f"},"schema_version":"1.0","source":{"id":"2605.16342","kind":"arxiv","version":1}},"canonical_sha256":"6e8b10d7be9c5d72cc569bd0674bc712168a303e65054b363e66a017b48faa80","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e8b10d7be9c5d72cc569bd0674bc712168a303e65054b363e66a017b48faa80","first_computed_at":"2026-05-20T00:02:17.553671Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:02:17.553671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Al2W4ijOcapPIxN2boosmihu+6ys1gYoG/QUw/dwR/BBZIx2+RYMEyVnYWtfWIbfuHRZpVM7/cMEOiTWbtjLAg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:02:17.554268Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16342","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:32ec5497dc3cd56dfbc9eef85dbf3dd5b31247d71b0662c4dae367e99bee6071","sha256:8279bf06f907e5e431114b6cfd77fc8d76e0fe6cb220e9b40d0625b5f11e9b6f"],"state_sha256":"788e78fa00277e0703a10b5471e1014681b5de79d2468b80b7a1eeeafe4c4bad"}