{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:N2FRBV56TROXFTCWTPIGOS6HCI","short_pith_number":"pith:N2FRBV56","canonical_record":{"source":{"id":"2605.16342","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-08T01:02:31Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"dfc5bc991983809445c4c9288496665c82d5f42837fa7185f7552ddff4b3790f","abstract_canon_sha256":"854d1cc9ef29c643f3d276e058250d57ea58a4955fe3f4d963927b08b793b1d6"},"schema_version":"1.0"},"canonical_sha256":"6e8b10d7be9c5d72cc569bd0674bc712168a303e65054b363e66a017b48faa80","source":{"kind":"arxiv","id":"2605.16342","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:N2FRBV56TROXFTCWTPIGOS6HCI","target":"record","payload":{"canonical_record":{"source":{"id":"2605.16342","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-08T01:02:31Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"dfc5bc991983809445c4c9288496665c82d5f42837fa7185f7552ddff4b3790f","abstract_canon_sha256":"854d1cc9ef29c643f3d276e058250d57ea58a4955fe3f4d963927b08b793b1d6"},"schema_version":"1.0"},"canonical_sha256":"6e8b10d7be9c5d72cc569bd0674bc712168a303e65054b363e66a017b48faa80","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:17.554268Z","signature_b64":"Al2W4ijOcapPIxN2boosmihu+6ys1gYoG/QUw/dwR/BBZIx2+RYMEyVnYWtfWIbfuHRZpVM7/cMEOiTWbtjLAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e8b10d7be9c5d72cc569bd0674bc712168a303e65054b363e66a017b48faa80","last_reissued_at":"2026-05-20T00:02:17.553671Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:17.553671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.16342","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:02:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"34tkQCYwQs4oke4pMx35XX2aP1mmBUIoq9ccZbnj9J0fdx1pnCVi1dpeWNJb4QUU7iqM/j2I5y54bVZ9m6qlCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T14:41:55.200904Z"},"content_sha256":"32ec5497dc3cd56dfbc9eef85dbf3dd5b31247d71b0662c4dae367e99bee6071","schema_version":"1.0","event_id":"sha256:32ec5497dc3cd56dfbc9eef85dbf3dd5b31247d71b0662c4dae367e99bee6071"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:N2FRBV56TROXFTCWTPIGOS6HCI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DACA-GRPO: Denoising-Aware Credit Assignment for Reinforcement Learning in Diffusion Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Amin Karimi Monsefi, Dominic Culver, Irina Belousova, Lokesh Boominathan, Manuel R. Ciosici, Nikhil Bhendawade, Yizhe Zhang","submitted_at":"2026-05-08T01:02:31Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16342","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/2605.16342/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:02:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"So3TH7l2pYB1OLPrNa4tWr9e6xiMKKm1P6EASKUrEQh13UtZ7FoBY760soaqfmXOvm7oxeLmf1DYJsvo9WLFBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T14:41:55.201603Z"},"content_sha256":"8279bf06f907e5e431114b6cfd77fc8d76e0fe6cb220e9b40d0625b5f11e9b6f","schema_version":"1.0","event_id":"sha256:8279bf06f907e5e431114b6cfd77fc8d76e0fe6cb220e9b40d0625b5f11e9b6f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N2FRBV56TROXFTCWTPIGOS6HCI/bundle.json","state_url":"https://pith.science/pith/N2FRBV56TROXFTCWTPIGOS6HCI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N2FRBV56TROXFTCWTPIGOS6HCI/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-25T14:41:55Z","links":{"resolver":"https://pith.science/pith/N2FRBV56TROXFTCWTPIGOS6HCI","bundle":"https://pith.science/pith/N2FRBV56TROXFTCWTPIGOS6HCI/bundle.json","state":"https://pith.science/pith/N2FRBV56TROXFTCWTPIGOS6HCI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N2FRBV56TROXFTCWTPIGOS6HCI/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8f6U4awrgwxBC3EzIYOiP4DRUuCCGMRl2M9ju3nxjFgsrokbzvmJewGfOLzkBfsdZ1r0JUBsD0n27/FgYSjTAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T14:41:55.205338Z","bundle_sha256":"8476df49090ec7d6be2b4a9ec3a4925beb9764977ec1d1f000d3f771b186e4c1"}}