{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VF3W63QC6OGCOXHS6KEZSEBRVE","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":"e1a0b0d64abe0ccfd17fd31b8ee8925f2993ff731859ab64db6e86d526ef0d8d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-10T00:45:24Z","title_canon_sha256":"262c8108b0b86a824b6357dbd167037be45f834d28f6c14d933d14549640b451"},"schema_version":"1.0","source":{"id":"2602.09305","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.09305","created_at":"2026-06-30T01:17:33Z"},{"alias_kind":"arxiv_version","alias_value":"2602.09305v2","created_at":"2026-06-30T01:17:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.09305","created_at":"2026-06-30T01:17:33Z"},{"alias_kind":"pith_short_12","alias_value":"VF3W63QC6OGC","created_at":"2026-06-30T01:17:33Z"},{"alias_kind":"pith_short_16","alias_value":"VF3W63QC6OGCOXHS","created_at":"2026-06-30T01:17:33Z"},{"alias_kind":"pith_short_8","alias_value":"VF3W63QC","created_at":"2026-06-30T01:17:33Z"}],"graph_snapshots":[{"event_id":"sha256:73696f0a223fd43e92ffc9d0941f5be1c74d9b87d7492938f503a68167e56367","target":"graph","created_at":"2026-06-30T01:17:33Z","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/2602.09305/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) demonstrate transformative potential, yet their reasoning remains inconsistent and unreliable. Reinforcement learning (RL)-based fine-tuning is a key mechanism for improvement, but its effectiveness is fundamentally governed by reward design. Despite its importance, the relationship between reward modeling and core LLM challenges--such as evaluation bias, hallucination, distribution shift, and efficient learning--remains poorly understood. This work argues that reward modeling is not merely an implementation detail but a central architect of reasoning alignment, sh","authors_text":"Pei-Chi Pan, Sen Lin, Yingbin Liang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-10T00:45:24Z","title":"Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.09305","kind":"arxiv","version":2},"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":"sha256:923af637240e759f58c849789da2b370a801a5186b7c11f3d6a65b046841e637","target":"record","created_at":"2026-06-30T01:17:33Z","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":"e1a0b0d64abe0ccfd17fd31b8ee8925f2993ff731859ab64db6e86d526ef0d8d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-10T00:45:24Z","title_canon_sha256":"262c8108b0b86a824b6357dbd167037be45f834d28f6c14d933d14549640b451"},"schema_version":"1.0","source":{"id":"2602.09305","kind":"arxiv","version":2}},"canonical_sha256":"a9776f6e02f38c275cf2f289991031a922d9375c6248aa1269e58fedb2e2710a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9776f6e02f38c275cf2f289991031a922d9375c6248aa1269e58fedb2e2710a","first_computed_at":"2026-06-30T01:17:33.809625Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:17:33.809625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aY5SKyy/lJ9++Dtu0kyGspYxE2+r3WvC8RoyJV2HH8AzhBYNKO2cTByRueZ6kEdjo825WDp2bovElwvp/gCJCg==","signature_status":"signed_v1","signed_at":"2026-06-30T01:17:33.810304Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.09305","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:923af637240e759f58c849789da2b370a801a5186b7c11f3d6a65b046841e637","sha256:73696f0a223fd43e92ffc9d0941f5be1c74d9b87d7492938f503a68167e56367"],"state_sha256":"ec3d8ee6453c5f110fc966266ae284b1fc7bcca78ff8ba4444089af73fa4073a"}