{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:D6K6JLEXCVDYQVMJWPU4PQY36I","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":"fa664d2533daa95a6b0c9ffbd358854a5fce21a59d4cb7f2d583faaf630657be","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T15:09:29Z","title_canon_sha256":"fa15fd6c5b7d27804fc610d6796a9567a5784303d44eb47189cc0893b7b6006d"},"schema_version":"1.0","source":{"id":"2606.10968","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10968","created_at":"2026-06-10T01:10:50Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10968v1","created_at":"2026-06-10T01:10:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10968","created_at":"2026-06-10T01:10:50Z"},{"alias_kind":"pith_short_12","alias_value":"D6K6JLEXCVDY","created_at":"2026-06-10T01:10:50Z"},{"alias_kind":"pith_short_16","alias_value":"D6K6JLEXCVDYQVMJ","created_at":"2026-06-10T01:10:50Z"},{"alias_kind":"pith_short_8","alias_value":"D6K6JLEX","created_at":"2026-06-10T01:10:50Z"}],"graph_snapshots":[{"event_id":"sha256:37bd2bbae0cbd9b9ee35091fad7e63dbe510ea5b75a0ecb801e374f03f2bd46e","target":"graph","created_at":"2026-06-10T01:10:50Z","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/2606.10968/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) has become standard for improving LLM reasoning. However, existing PPO-style trust-region mechanisms remain position-agnostic by enforcing uniform thresholds across all tokens independently. This pointwise treatment conflicts with autoregressive generation in two critical ways. First, uniform thresholds ignore autoregressive asymmetry. Early-stage deviations produce compounding sequence-level drift, causing static thresholds to under-regulate early divergence and excessively constrain late-stage exploration. Second, evaluating token-level d","authors_text":"Honglin Zhu, Lvfang Tao, Qian Qiu, Renjie Mao, Wenxi Zhu, Xiangxin Zhou, Yixin Ding, Yongguang Lin, Yuheng Wu, Yu Shi","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T15:09:29Z","title":"Beyond Uniform Token-Level Trust Region in LLM Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10968","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":"sha256:9a9ac62f465b49344824ebbb1f1b2bf6ce8e213c213c5a3baec3a49a93c93ff3","target":"record","created_at":"2026-06-10T01:10:50Z","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":"fa664d2533daa95a6b0c9ffbd358854a5fce21a59d4cb7f2d583faaf630657be","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T15:09:29Z","title_canon_sha256":"fa15fd6c5b7d27804fc610d6796a9567a5784303d44eb47189cc0893b7b6006d"},"schema_version":"1.0","source":{"id":"2606.10968","kind":"arxiv","version":1}},"canonical_sha256":"1f95e4ac971547885589b3e9c7c31bf2063a915af4a490b7147dad0e77b6565c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f95e4ac971547885589b3e9c7c31bf2063a915af4a490b7147dad0e77b6565c","first_computed_at":"2026-06-10T01:10:50.538050Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:10:50.538050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H+cML8R3XyquMEXSkYltTV4mOcrwP5ZE7BnR0OkumA60Qi1PMBDKnohHpSEHjQS8QoHzWvwqYPBRaqrtODBrAA==","signature_status":"signed_v1","signed_at":"2026-06-10T01:10:50.538909Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.10968","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a9ac62f465b49344824ebbb1f1b2bf6ce8e213c213c5a3baec3a49a93c93ff3","sha256:37bd2bbae0cbd9b9ee35091fad7e63dbe510ea5b75a0ecb801e374f03f2bd46e"],"state_sha256":"af80ca980b3e3fdb5136cde21ab005c571d6d583d095b0d0e45b87a60d377711"}