{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2KN573JIBWH6RRBMCS7FRKKUFN","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":"65aa91f856ea55cc12b4ae910c1c68eb5908604e679ab3fe04fe84945d55cd5c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-22T06:57:55Z","title_canon_sha256":"88499cbefc69f569a05c1eaada82436b7c0b5bf13a3d4b65a5bd5982beb92bec"},"schema_version":"1.0","source":{"id":"2607.19824","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.19824","created_at":"2026-07-23T01:24:01Z"},{"alias_kind":"arxiv_version","alias_value":"2607.19824v1","created_at":"2026-07-23T01:24:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19824","created_at":"2026-07-23T01:24:01Z"},{"alias_kind":"pith_short_12","alias_value":"2KN573JIBWH6","created_at":"2026-07-23T01:24:01Z"},{"alias_kind":"pith_short_16","alias_value":"2KN573JIBWH6RRBM","created_at":"2026-07-23T01:24:01Z"},{"alias_kind":"pith_short_8","alias_value":"2KN573JI","created_at":"2026-07-23T01:24:01Z"}],"graph_snapshots":[{"event_id":"sha256:2c8f507cf15f33f7c56a6131ec18c5d28d154afd6e5f8cd870ba97ff29feb51b","target":"graph","created_at":"2026-07-23T01:24:01Z","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/2607.19824/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM preference alignment aims to optimize models toward human preferences across diverse user instructions. Reinforcement learning has become a major post-training approach for this goal, but existing proxy rewards are often outcome-level, mainly evaluating the final response while providing limited guidance for the reasoning trajectory. This can make credit assignment coarse when multiple responses receive similar final scores, leaving trajectory-level preferences under-specified. To address this limitation, we propose Thinking Checklist Reward (TCR), a process-oriented reward for RL-based pr","authors_text":"Ruxue Yan, Wenya Guo, Xinying Qian, Xubo Liu, Ying Zhang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-22T06:57:55Z","title":"Rewarding Better Thinking for LLM Preference Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19824","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":"sha256:0755cadd7b3589d9767f1e4028f19fe1157731a96b72ed5a8f8df0873f81f045","target":"record","created_at":"2026-07-23T01:24:01Z","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":"65aa91f856ea55cc12b4ae910c1c68eb5908604e679ab3fe04fe84945d55cd5c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-22T06:57:55Z","title_canon_sha256":"88499cbefc69f569a05c1eaada82436b7c0b5bf13a3d4b65a5bd5982beb92bec"},"schema_version":"1.0","source":{"id":"2607.19824","kind":"arxiv","version":1}},"canonical_sha256":"d29bdfed280d8fe8c42c14be58a9542b5d0e2142d39adf3ed0c6399503c88586","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d29bdfed280d8fe8c42c14be58a9542b5d0e2142d39adf3ed0c6399503c88586","first_computed_at":"2026-07-23T01:24:01.636618Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-23T01:24:01.636618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CupHAuPDvS2G3SncrONqUZaG4Myrvv5zqIDulkv/WYtni2P0+zvfqdFIMaJAOakfAqb1Rv2ngNZvIEHQeikJAQ==","signature_status":"signed_v1","signed_at":"2026-07-23T01:24:01.637837Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.19824","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0755cadd7b3589d9767f1e4028f19fe1157731a96b72ed5a8f8df0873f81f045","sha256:2c8f507cf15f33f7c56a6131ec18c5d28d154afd6e5f8cd870ba97ff29feb51b"],"state_sha256":"63eb8ff8a09b8c93bfe2dcc1fe53a4e82c0024e6c9048b0672c6f1c259b8fd36"}