{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:D7YQCPCHYYKWIV7BJEURZPN6VH","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":"08e1903f20e847ecb264d3e6ee352009a3a464e345bfa72199b20ee65966e805","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-11T04:39:42Z","title_canon_sha256":"931a8c64075c56d2b425397d3b2b0516de4464167550275060031f42db9dd5cf"},"schema_version":"1.0","source":{"id":"2602.10520","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.10520","created_at":"2026-05-29T02:05:02Z"},{"alias_kind":"arxiv_version","alias_value":"2602.10520v3","created_at":"2026-05-29T02:05:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.10520","created_at":"2026-05-29T02:05:02Z"},{"alias_kind":"pith_short_12","alias_value":"D7YQCPCHYYKW","created_at":"2026-05-29T02:05:02Z"},{"alias_kind":"pith_short_16","alias_value":"D7YQCPCHYYKWIV7B","created_at":"2026-05-29T02:05:02Z"},{"alias_kind":"pith_short_8","alias_value":"D7YQCPCH","created_at":"2026-05-29T02:05:02Z"}],"graph_snapshots":[{"event_id":"sha256:0ed565c200e6eba3902a398e9af52f97af5e3f2f17e286bb6bd4a8417a532b4f","target":"graph","created_at":"2026-05-29T02:05:02Z","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/2602.10520/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Looped Language Models (LoopLMs) perform multi-step latent reasoning prior to token generation and outperform conventional LLMs on reasoning benchmarks at smaller parameter budgets. However, attempts to further improve LoopLM reasoning with reinforcement learning have failed - standard objectives such as Group Relative Policy Optimization (GRPO) only assign credit to the final latent state, creating a fundamental mismatch with the model's internal computation. To resolve this, we introduce RLTT (Reward Latent Thought Trajectories), a reinforcement learning framework which distributes reward ac","authors_text":"Esin Tureci, Jonathan Williams","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-11T04:39:42Z","title":"Prioritize the Process, Not Just the Outcome: Rewarding Latent Thought Trajectories Improves Reasoning in Looped Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.10520","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":"sha256:4a4842b844e907a5a612918b55390023ec6e93071bc1b21335cd152ba8cbcfac","target":"record","created_at":"2026-05-29T02:05:02Z","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":"08e1903f20e847ecb264d3e6ee352009a3a464e345bfa72199b20ee65966e805","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-11T04:39:42Z","title_canon_sha256":"931a8c64075c56d2b425397d3b2b0516de4464167550275060031f42db9dd5cf"},"schema_version":"1.0","source":{"id":"2602.10520","kind":"arxiv","version":3}},"canonical_sha256":"1ff1013c47c6156457e149291cbdbea9e98558b800fb1ad00c698db0df2b4a57","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ff1013c47c6156457e149291cbdbea9e98558b800fb1ad00c698db0df2b4a57","first_computed_at":"2026-05-29T02:05:02.114788Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:05:02.114788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gll3cT3ng+yLEcxzhiDK2sNKiZ8UyXeQQcmoentKEDqVKQxag5zZWdXj+xuxB6tbzd3BBXxBvJki2457BZwiBA==","signature_status":"signed_v1","signed_at":"2026-05-29T02:05:02.115621Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.10520","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a4842b844e907a5a612918b55390023ec6e93071bc1b21335cd152ba8cbcfac","sha256:0ed565c200e6eba3902a398e9af52f97af5e3f2f17e286bb6bd4a8417a532b4f"],"state_sha256":"853f14b99e756f407b643153da02bccd29aa160adcd675a42c96b4613da13a32"}