{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SDT6RVDXUNVLK7LVGN2HWPIPX7","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":"6a176e33a0ee753d947d701f5d15dca482036f1a9cce07618fcbf9d6ee581739","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T08:01:42Z","title_canon_sha256":"1e8f40ece78900b71e7dba7d7a65a99033b24a251acc2b031195ecd3a4bb9146"},"schema_version":"1.0","source":{"id":"2605.28109","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28109","created_at":"2026-05-28T01:04:59Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28109v1","created_at":"2026-05-28T01:04:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28109","created_at":"2026-05-28T01:04:59Z"},{"alias_kind":"pith_short_12","alias_value":"SDT6RVDXUNVL","created_at":"2026-05-28T01:04:59Z"},{"alias_kind":"pith_short_16","alias_value":"SDT6RVDXUNVLK7LV","created_at":"2026-05-28T01:04:59Z"},{"alias_kind":"pith_short_8","alias_value":"SDT6RVDX","created_at":"2026-05-28T01:04:59Z"}],"graph_snapshots":[{"event_id":"sha256:95d27bc57dfe33319ba92948a3dbe16fc888e30a5b4ec10886712348848fb08b","target":"graph","created_at":"2026-05-28T01:04:59Z","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/2605.28109/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in online reinforcement learning (RL) for large language models (LLMs) have demonstrated promising performance in complex reasoning tasks. However, they often exhibit an imbalanced exploration-exploitation trade-off, resulting in unstable optimization and sub-optimal performance. We introduce IB-Score, a novel metric grounded in Information Bottleneck theory that evaluates policy's exploration-exploitation balance by quantifying the trade-off between step-level reasoning diversity and mutual information shared with the correct answer. Analysis based on IB-Score shows that popul","authors_text":"Bin Yang, Bowen Xu, Hao Jiang, Hongtao Duan, Lulu Hu, Minying Zhang, Qihua Chen, Shurui Li, Tianpeng Bu, Xin Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T08:01:42Z","title":"Long Live The Balance: Information Bottleneck Driven Tree-based Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28109","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":"sha256:0b6a31644d07e3cc39b21f5fa9a1c1c1ad40478349b1c5a7c34f8efaed4a620c","target":"record","created_at":"2026-05-28T01:04:59Z","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":"6a176e33a0ee753d947d701f5d15dca482036f1a9cce07618fcbf9d6ee581739","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T08:01:42Z","title_canon_sha256":"1e8f40ece78900b71e7dba7d7a65a99033b24a251acc2b031195ecd3a4bb9146"},"schema_version":"1.0","source":{"id":"2605.28109","kind":"arxiv","version":1}},"canonical_sha256":"90e7e8d477a36ab57d7533747b3d0fbfc3e357ea03f7820040b221a0a819d421","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"90e7e8d477a36ab57d7533747b3d0fbfc3e357ea03f7820040b221a0a819d421","first_computed_at":"2026-05-28T01:04:59.121748Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:59.121748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ff4VcVSlfRnkfo5MsB7q0aobyRu+MkYEk9wOXI/MJ+zj5yJc8U+akc7kEEjMgitQGzMwIjEWUuWj54ido4p5AQ==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:59.122210Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28109","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b6a31644d07e3cc39b21f5fa9a1c1c1ad40478349b1c5a7c34f8efaed4a620c","sha256:95d27bc57dfe33319ba92948a3dbe16fc888e30a5b4ec10886712348848fb08b"],"state_sha256":"f90ca98828b142d2bd6c44e51071e142c67d7aa5f8b9296cad2e200d4127c12c"}