{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PNEOTERX6UN55LNL3OMF7RBQYE","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":"cf35a7296f385eca049c5623057a2e5e0b125c92f332d0db480939aa4b6be7d9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T16:57:34Z","title_canon_sha256":"07ce4d66058e11c17bf9b3155070d12c9ffffe1a3c6ded0bb0fbb825414f172a"},"schema_version":"1.0","source":{"id":"2607.15200","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.15200","created_at":"2026-07-17T01:22:14Z"},{"alias_kind":"arxiv_version","alias_value":"2607.15200v1","created_at":"2026-07-17T01:22:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.15200","created_at":"2026-07-17T01:22:14Z"},{"alias_kind":"pith_short_12","alias_value":"PNEOTERX6UN5","created_at":"2026-07-17T01:22:14Z"},{"alias_kind":"pith_short_16","alias_value":"PNEOTERX6UN55LNL","created_at":"2026-07-17T01:22:14Z"},{"alias_kind":"pith_short_8","alias_value":"PNEOTERX","created_at":"2026-07-17T01:22:14Z"}],"graph_snapshots":[{"event_id":"sha256:65967b345db69e516f02947122fcc7d4bb5bb2842626b5ca8a116ec0b2656ea1","target":"graph","created_at":"2026-07-17T01:22:14Z","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/2607.15200/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning has proven effective for improving reasoning in large language models, but extending it to Masked Diffusion Language Models (MDLMs) remains challenging due to the intractability of the log-likelihood estimation. Existing approaches approximate this log-likelihood by modeling only the token predictions, ignoring the order in which positions are unmasked during generation. We observe that MDLM generation involves two decisions at each step: what tokens to place at each masked position and which positions to remask. We formalize this as a two-stage action MDP, showing that ","authors_text":"Adam Klivans, Haran Raajesh, Kulin Shah, Philipp Kr\\\"ahenb\\\"uhl","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T16:57:34Z","title":"Mask-Aware Policy Gradients for Diffusion Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15200","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":"sha256:24324fc581e25c918d5adb15626ab47216ef44256f2809236536591cf1a00dd1","target":"record","created_at":"2026-07-17T01:22:14Z","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":"cf35a7296f385eca049c5623057a2e5e0b125c92f332d0db480939aa4b6be7d9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T16:57:34Z","title_canon_sha256":"07ce4d66058e11c17bf9b3155070d12c9ffffe1a3c6ded0bb0fbb825414f172a"},"schema_version":"1.0","source":{"id":"2607.15200","kind":"arxiv","version":1}},"canonical_sha256":"7b48e99237f51bdeadabdb985fc430c12eed3fbee36cd6c2ac5bca275fff65aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b48e99237f51bdeadabdb985fc430c12eed3fbee36cd6c2ac5bca275fff65aa","first_computed_at":"2026-07-17T01:22:14.172288Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-17T01:22:14.172288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ty1uJJpifdW94A47qpLmoUZleZbzvtuK8UTXq44GMASk8ZVS0mOTjY5vENN2L3lmQhKn5bl8RDd2tv6XRPnUAw==","signature_status":"signed_v1","signed_at":"2026-07-17T01:22:14.173112Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.15200","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:24324fc581e25c918d5adb15626ab47216ef44256f2809236536591cf1a00dd1","sha256:65967b345db69e516f02947122fcc7d4bb5bb2842626b5ca8a116ec0b2656ea1"],"state_sha256":"7c8a76450f168c45abd6323332db0b77b9e42afb006430d3884d78cef82f0b0a"}