{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KIDQJHHECD3OXBRRZWSJ5NZJAU","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":"8385aae6c152aa4dd031ca8ed93e1cee9be56758f7c80f6628b04996f3148ca0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-24T12:31:14Z","title_canon_sha256":"319c297a5f9b707d72107d68f5dec870ad9024c9422e65367a202667f83682df"},"schema_version":"1.0","source":{"id":"2606.25757","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.25757","created_at":"2026-06-25T01:18:14Z"},{"alias_kind":"arxiv_version","alias_value":"2606.25757v1","created_at":"2026-06-25T01:18:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25757","created_at":"2026-06-25T01:18:14Z"},{"alias_kind":"pith_short_12","alias_value":"KIDQJHHECD3O","created_at":"2026-06-25T01:18:14Z"},{"alias_kind":"pith_short_16","alias_value":"KIDQJHHECD3OXBRR","created_at":"2026-06-25T01:18:14Z"},{"alias_kind":"pith_short_8","alias_value":"KIDQJHHE","created_at":"2026-06-25T01:18:14Z"}],"graph_snapshots":[{"event_id":"sha256:8354a03be0c7913665a7d7ed9f0fd3e8b46a375aed4407bd78fb1438c78c3f94","target":"graph","created_at":"2026-06-25T01:18:14Z","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/2606.25757/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) has enabled LLMs to excel in objective reasoning tasks such as mathematics and code generation. However, applying RL to open-ended tasks, such as creative writing, remains challenging because LLM-as-a-judge reward models often exhibit stylistic biases and positional inconsistencies, leading to unstable supervision. To address this, we propose OPERA (Objective Perplexity-based Reflective Alignment), which replaces unreliable external judges with intrinsic rewards derived from perplexity dynamics. Specifically, we derive an intrinsic reward signal from perplexity dyna","authors_text":"Haoyang Dai, Hongming Tan, Ninghao Liu, Wenxuan Jiang, Xiaoyu Li, Xuecheng Wu, Xuezhi Cao, Zijian Zhang, Zining Fan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-24T12:31:14Z","title":"OPERA: Aligning Open-Ended Reasoning via Objective Perplexity-based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25757","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":"sha256:8648f9361a213d6533e0325205b8b87d6ad1ff7bd11c1a3776e80e7f25df3e7e","target":"record","created_at":"2026-06-25T01:18:14Z","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":"8385aae6c152aa4dd031ca8ed93e1cee9be56758f7c80f6628b04996f3148ca0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-24T12:31:14Z","title_canon_sha256":"319c297a5f9b707d72107d68f5dec870ad9024c9422e65367a202667f83682df"},"schema_version":"1.0","source":{"id":"2606.25757","kind":"arxiv","version":1}},"canonical_sha256":"5207049ce410f6eb8631cda49eb729050489ccbe2e73b5786089cfefd7e6c764","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5207049ce410f6eb8631cda49eb729050489ccbe2e73b5786089cfefd7e6c764","first_computed_at":"2026-06-25T01:18:14.439878Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-25T01:18:14.439878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S0magTbRKnIyILF9JebZIA8tKHRSFo0wvDETD/XCP54tlysM57rPecq4bYsQSgWcQu+z51ByFtuhHUKTrRkbBw==","signature_status":"signed_v1","signed_at":"2026-06-25T01:18:14.440220Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.25757","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8648f9361a213d6533e0325205b8b87d6ad1ff7bd11c1a3776e80e7f25df3e7e","sha256:8354a03be0c7913665a7d7ed9f0fd3e8b46a375aed4407bd78fb1438c78c3f94"],"state_sha256":"e981fda707d0197bab08ef9dc3c942b25f21c50cadd6c258e10ff5c0a21fe7b6"}