{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HN6FYJQVGPI3F42MXFDNZOBFJW","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":"41f38bc72bc00571e34d5aa00e168aaae22e6ce9bd34c5c0657f3cda742b4321","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-02T06:26:31Z","title_canon_sha256":"ae6b906766f30e52a18874f4ccf910de7ae5864e22ad1cafa9ad6d2e02e5f21a"},"schema_version":"1.0","source":{"id":"2602.01705","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.01705","created_at":"2026-05-20T00:03:04Z"},{"alias_kind":"arxiv_version","alias_value":"2602.01705v3","created_at":"2026-05-20T00:03:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.01705","created_at":"2026-05-20T00:03:04Z"},{"alias_kind":"pith_short_12","alias_value":"HN6FYJQVGPI3","created_at":"2026-05-20T00:03:04Z"},{"alias_kind":"pith_short_16","alias_value":"HN6FYJQVGPI3F42M","created_at":"2026-05-20T00:03:04Z"},{"alias_kind":"pith_short_8","alias_value":"HN6FYJQV","created_at":"2026-05-20T00:03:04Z"}],"graph_snapshots":[{"event_id":"sha256:b34cf578684daacf106cf87a99a709d41b5120845335df17f2a71d732a2c87d3","target":"graph","created_at":"2026-05-20T00:03:04Z","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/2602.01705/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning has become a central paradigm for improving LLM reasoning, but most existing methods optimize policies over discrete token sequences. This creates a mismatch between the optimization space and the structure of reasoning: many important decisions are semantic, global, and trajectory-level rather than local token choices. Continuous latent-space RL offers a promising alternative by allowing policies to explore higher-level reasoning representations. However, simply moving to latent space is not sufficient. The resulting policy must model a complex, multi-modal distribution","authors_text":"Haoqiang Kang, Lianhui Qin, Nikki Lijing Kuang, Yi-An Ma, Yizhe Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-02T06:26:31Z","title":"LaDi-RL: Latent Diffusion Reasoning Prevents Entropy Collapse in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.01705","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":"sha256:78d70db0801839e4627577a48cfaf1e1c59335f3bf971c0d2df2e6d45f8d5dd1","target":"record","created_at":"2026-05-20T00:03:04Z","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":"41f38bc72bc00571e34d5aa00e168aaae22e6ce9bd34c5c0657f3cda742b4321","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-02T06:26:31Z","title_canon_sha256":"ae6b906766f30e52a18874f4ccf910de7ae5864e22ad1cafa9ad6d2e02e5f21a"},"schema_version":"1.0","source":{"id":"2602.01705","kind":"arxiv","version":3}},"canonical_sha256":"3b7c5c261533d1b2f34cb946dcb8254db2dafe164971ef74d4ea4d9e47cfccc4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3b7c5c261533d1b2f34cb946dcb8254db2dafe164971ef74d4ea4d9e47cfccc4","first_computed_at":"2026-05-20T00:03:04.044972Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:04.044972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HyNOQtc0dxq71Jx2KcaxCGiaW0KsSJkonDhJE9HevX8YGKqYVJ6c6xm0lrzWRpa1RzcEec/MQMFPtLoUQipKCQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:04.045919Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.01705","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:78d70db0801839e4627577a48cfaf1e1c59335f3bf971c0d2df2e6d45f8d5dd1","sha256:b34cf578684daacf106cf87a99a709d41b5120845335df17f2a71d732a2c87d3"],"state_sha256":"558070d7799e83c6b5a898f9cad8adf9ce3d45616b9474abf0df532ad9e3efd3"}