{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NA4RM74XC5JUK3AG4FLZ3CT4JS","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":"ebe2cebabb20c563b84cc7b90218548b93a5a8b24402fe67063ba4896ef51e4a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-05T03:53:16Z","title_canon_sha256":"aeeb7f8b7c0d2631b188b181ef5445955c437edaf3939ecd740affd80d79364c"},"schema_version":"1.0","source":{"id":"2510.04019","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.04019","created_at":"2026-07-24T01:23:00Z"},{"alias_kind":"arxiv_version","alias_value":"2510.04019v3","created_at":"2026-07-24T01:23:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.04019","created_at":"2026-07-24T01:23:00Z"},{"alias_kind":"pith_short_12","alias_value":"NA4RM74XC5JU","created_at":"2026-07-24T01:23:00Z"},{"alias_kind":"pith_short_16","alias_value":"NA4RM74XC5JUK3AG","created_at":"2026-07-24T01:23:00Z"},{"alias_kind":"pith_short_8","alias_value":"NA4RM74X","created_at":"2026-07-24T01:23:00Z"}],"graph_snapshots":[{"event_id":"sha256:e48a798476d05ecc4ef1759584abf176a9981e0fbc40a636fa86241775f2d6b0","target":"graph","created_at":"2026-07-24T01:23:00Z","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/2510.04019/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion large language models (dLLMs) represent a promising alternative to autoregressive LLMs; however, the lack of effective post-training techniques, including reinforcement learning (RL), remains a key challenge for dLLMs, especially for downstream applications. Existing approaches often rely on a sequence-level view that requires biased likelihood approximations. In this work, we propose Amortized Group Relative Policy Optimization (AGRPO), a policy gradient algorithm that leverages the Markovian nature of dLLMs, optimizing individual denoising steps rather than full sequences. Our appr","authors_text":"Anthony Zhan","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-05T03:53:16Z","title":"Simple Policy Gradients for Reasoning with Diffusion Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.04019","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":"sha256:14cb1e71f54cdef99c47c76507735dc2d2259e9720cd453e060f53d2c22b696d","target":"record","created_at":"2026-07-24T01:23:00Z","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":"ebe2cebabb20c563b84cc7b90218548b93a5a8b24402fe67063ba4896ef51e4a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-05T03:53:16Z","title_canon_sha256":"aeeb7f8b7c0d2631b188b181ef5445955c437edaf3939ecd740affd80d79364c"},"schema_version":"1.0","source":{"id":"2510.04019","kind":"arxiv","version":3}},"canonical_sha256":"6839167f971753456c06e1579d8a7c4c84b4f5a8b4ad63bc3d1bddafd06800f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6839167f971753456c06e1579d8a7c4c84b4f5a8b4ad63bc3d1bddafd06800f0","first_computed_at":"2026-07-24T01:23:00.223943Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-24T01:23:00.223943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2ia5Wetmk/Ld59gAD37IpMl9L6i5FN7Z8rdg+PvyHnUx6REGojgJL4qoiH9NzfgvNvCqkKzqz3CyFMNsbkxbDA==","signature_status":"signed_v1","signed_at":"2026-07-24T01:23:00.224956Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.04019","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14cb1e71f54cdef99c47c76507735dc2d2259e9720cd453e060f53d2c22b696d","sha256:e48a798476d05ecc4ef1759584abf176a9981e0fbc40a636fa86241775f2d6b0"],"state_sha256":"b7d48a96096f408cb5845b4c86d7b7bb4b336f41c33b15a585c3c0562a339b1a"}