{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HN6FYJQVGPI3F42MXFDNZOBFJW","short_pith_number":"pith:HN6FYJQV","schema_version":"1.0","canonical_sha256":"3b7c5c261533d1b2f34cb946dcb8254db2dafe164971ef74d4ea4d9e47cfccc4","source":{"kind":"arxiv","id":"2602.01705","version":3},"attestation_state":"computed","paper":{"title":"LaDi-RL: Latent Diffusion Reasoning Prevents Entropy Collapse in Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haoqiang Kang, Lianhui Qin, Nikki Lijing Kuang, Yi-An Ma, Yizhe Zhang","submitted_at":"2026-02-02T06:26:31Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2602.01705","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-02T06:26:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ae6b906766f30e52a18874f4ccf910de7ae5864e22ad1cafa9ad6d2e02e5f21a","abstract_canon_sha256":"41f38bc72bc00571e34d5aa00e168aaae22e6ce9bd34c5c0657f3cda742b4321"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:04.045919Z","signature_b64":"HyNOQtc0dxq71Jx2KcaxCGiaW0KsSJkonDhJE9HevX8YGKqYVJ6c6xm0lrzWRpa1RzcEec/MQMFPtLoUQipKCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b7c5c261533d1b2f34cb946dcb8254db2dafe164971ef74d4ea4d9e47cfccc4","last_reissued_at":"2026-05-20T00:03:04.044972Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:04.044972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LaDi-RL: Latent Diffusion Reasoning Prevents Entropy Collapse in Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haoqiang Kang, Lianhui Qin, Nikki Lijing Kuang, Yi-An Ma, Yizhe Zhang","submitted_at":"2026-02-02T06:26:31Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.01705","kind":"arxiv","version":3},"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/2602.01705/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2602.01705","created_at":"2026-05-20T00:03:04.045121+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.01705v3","created_at":"2026-05-20T00:03:04.045121+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.01705","created_at":"2026-05-20T00:03:04.045121+00:00"},{"alias_kind":"pith_short_12","alias_value":"HN6FYJQVGPI3","created_at":"2026-05-20T00:03:04.045121+00:00"},{"alias_kind":"pith_short_16","alias_value":"HN6FYJQVGPI3F42M","created_at":"2026-05-20T00:03:04.045121+00:00"},{"alias_kind":"pith_short_8","alias_value":"HN6FYJQV","created_at":"2026-05-20T00:03:04.045121+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HN6FYJQVGPI3F42MXFDNZOBFJW","json":"https://pith.science/pith/HN6FYJQVGPI3F42MXFDNZOBFJW.json","graph_json":"https://pith.science/api/pith-number/HN6FYJQVGPI3F42MXFDNZOBFJW/graph.json","events_json":"https://pith.science/api/pith-number/HN6FYJQVGPI3F42MXFDNZOBFJW/events.json","paper":"https://pith.science/paper/HN6FYJQV"},"agent_actions":{"view_html":"https://pith.science/pith/HN6FYJQVGPI3F42MXFDNZOBFJW","download_json":"https://pith.science/pith/HN6FYJQVGPI3F42MXFDNZOBFJW.json","view_paper":"https://pith.science/paper/HN6FYJQV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.01705&json=true","fetch_graph":"https://pith.science/api/pith-number/HN6FYJQVGPI3F42MXFDNZOBFJW/graph.json","fetch_events":"https://pith.science/api/pith-number/HN6FYJQVGPI3F42MXFDNZOBFJW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HN6FYJQVGPI3F42MXFDNZOBFJW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HN6FYJQVGPI3F42MXFDNZOBFJW/action/storage_attestation","attest_author":"https://pith.science/pith/HN6FYJQVGPI3F42MXFDNZOBFJW/action/author_attestation","sign_citation":"https://pith.science/pith/HN6FYJQVGPI3F42MXFDNZOBFJW/action/citation_signature","submit_replication":"https://pith.science/pith/HN6FYJQVGPI3F42MXFDNZOBFJW/action/replication_record"}},"created_at":"2026-05-20T00:03:04.045121+00:00","updated_at":"2026-05-20T00:03:04.045121+00:00"}