{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OKRCLUZXSMJELEWTVHUHU4YATX","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":"b7cdec21f49c50990ead54439fbc7d49edccafc82376dc44e45fd5429247d0e8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-16T03:19:53Z","title_canon_sha256":"efdb1c45811bafcdfa4312523a2574cebb316dec7159b1b2681a2c5ecd20084a"},"schema_version":"1.0","source":{"id":"2607.14522","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.14522","created_at":"2026-07-17T01:21:16Z"},{"alias_kind":"arxiv_version","alias_value":"2607.14522v1","created_at":"2026-07-17T01:21:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14522","created_at":"2026-07-17T01:21:16Z"},{"alias_kind":"pith_short_12","alias_value":"OKRCLUZXSMJE","created_at":"2026-07-17T01:21:16Z"},{"alias_kind":"pith_short_16","alias_value":"OKRCLUZXSMJELEWT","created_at":"2026-07-17T01:21:16Z"},{"alias_kind":"pith_short_8","alias_value":"OKRCLUZX","created_at":"2026-07-17T01:21:16Z"}],"graph_snapshots":[{"event_id":"sha256:9c65e7e370a2a4d23330c8685a60d911c75fb0bb8fd18ed7f437b84e961f6b24","target":"graph","created_at":"2026-07-17T01:21:16Z","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/2607.14522/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We formulate reinforcement learning (RL) in continuous time with discrete state spaces and possibly arbitrary action spaces via a stochastic control approach, where the state dynamics are modeled as a controlled continuous-time Markov chain (CTMC). We consider policy optimization problems and derive the corresponding policy gradient methods, leading to continuous-time variants of proximal policy optimization (PPO) and group relative policy optimization (GRPO). As a primary application, we develop a complete continuous-time RL framework for fine-tuning score-based discrete diffusion models. The","authors_text":"David D. Yao, Jiayuan Sheng, Wenpin Tang, Zikun Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-16T03:19:53Z","title":"A Continuous-Time Reinforcement Learning Framework for Fine-Tuning Discrete Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14522","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:a088a4b184334eace5649eb2094dcad00af387babb75ff8763b224015a76c2ca","target":"record","created_at":"2026-07-17T01:21:16Z","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":"b7cdec21f49c50990ead54439fbc7d49edccafc82376dc44e45fd5429247d0e8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-16T03:19:53Z","title_canon_sha256":"efdb1c45811bafcdfa4312523a2574cebb316dec7159b1b2681a2c5ecd20084a"},"schema_version":"1.0","source":{"id":"2607.14522","kind":"arxiv","version":1}},"canonical_sha256":"72a225d33793124592d3a9e87a73009dd97653fa77463f770e4690a3cadb00d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"72a225d33793124592d3a9e87a73009dd97653fa77463f770e4690a3cadb00d2","first_computed_at":"2026-07-17T01:21:16.023152Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-17T01:21:16.023152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pi9nPJ+xDHBerrZe20RR7TWfiHOMOYQCrz1NN094AGB9oN5PyrwC/09o9prq4pVyZAXNovdHNKhRbrnMwopJAA==","signature_status":"signed_v1","signed_at":"2026-07-17T01:21:16.024041Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.14522","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a088a4b184334eace5649eb2094dcad00af387babb75ff8763b224015a76c2ca","sha256:9c65e7e370a2a4d23330c8685a60d911c75fb0bb8fd18ed7f437b84e961f6b24"],"state_sha256":"ce7d0a0952c0f2d0ef3314d52f7f2a5d4d61a41445847e7fdf75d1a7cf957cc8"}