{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HLJ66AEPRSWHDQPNCYOLVAFXA3","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":"1101fe7620a5a170ae019106d4ea63b3229fa982abd9f3482e3c7b62ee3c3482","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-22T05:30:14Z","title_canon_sha256":"14d1161a84a31e11fc4717168c8706b45dc2ed983f33bce314ed9462580c9300"},"schema_version":"1.0","source":{"id":"2602.19049","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.19049","created_at":"2026-06-01T01:02:35Z"},{"alias_kind":"arxiv_version","alias_value":"2602.19049v2","created_at":"2026-06-01T01:02:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.19049","created_at":"2026-06-01T01:02:35Z"},{"alias_kind":"pith_short_12","alias_value":"HLJ66AEPRSWH","created_at":"2026-06-01T01:02:35Z"},{"alias_kind":"pith_short_16","alias_value":"HLJ66AEPRSWHDQPN","created_at":"2026-06-01T01:02:35Z"},{"alias_kind":"pith_short_8","alias_value":"HLJ66AEP","created_at":"2026-06-01T01:02:35Z"}],"graph_snapshots":[{"event_id":"sha256:82f9e3a287ceb63b920ad2beeec64b98a2e52538e7531559ab8f6bb0f05e1a8b","target":"graph","created_at":"2026-06-01T01:02:35Z","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/2602.19049/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models increasingly rely on long chains of thought to improve accuracy, yet such gains come with substantial inference-time costs. We revisit token-efficient post-training and argue that existing sequence-level reward-shaping methods offer limited control over how reasoning effort is allocated across tokens. To bridge the gap, we propose IAPO, an information-theoretic post-training framework that assigns token-wise advantages based on each token's conditional mutual information (MI) with the final answer. This yields an explicit, principled mechanism for identifying informative ","authors_text":"Jundong Li, Lin Su, Mingjia Shi, Qi Guo, Wendy Zheng, Xiaoqing Wang, Yaochen Zhu, Yinhan He","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-22T05:30:14Z","title":"IAPO: Information-Aware Policy Optimization for Token-Efficient Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.19049","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":"sha256:28e0b3c4b64befa92af82b3f37f715549e7fa21dca9dc20cbb57fcd80b74b7d9","target":"record","created_at":"2026-06-01T01:02:35Z","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":"1101fe7620a5a170ae019106d4ea63b3229fa982abd9f3482e3c7b62ee3c3482","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-22T05:30:14Z","title_canon_sha256":"14d1161a84a31e11fc4717168c8706b45dc2ed983f33bce314ed9462580c9300"},"schema_version":"1.0","source":{"id":"2602.19049","kind":"arxiv","version":2}},"canonical_sha256":"3ad3ef008f8cac71c1ed161cba80b706ca5afea0399c8163a820ef63656dadbf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ad3ef008f8cac71c1ed161cba80b706ca5afea0399c8163a820ef63656dadbf","first_computed_at":"2026-06-01T01:02:35.084547Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:02:35.084547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I6MbZRWcHf/B8pfplWIXZREv7sZbuO/FLP63/9iEuYlT7dUCrRvH7M7ep8zBk8uDnWew3ql9twfjRVGnN3kWDw==","signature_status":"signed_v1","signed_at":"2026-06-01T01:02:35.085863Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.19049","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28e0b3c4b64befa92af82b3f37f715549e7fa21dca9dc20cbb57fcd80b74b7d9","sha256:82f9e3a287ceb63b920ad2beeec64b98a2e52538e7531559ab8f6bb0f05e1a8b"],"state_sha256":"5a7854c40827156b6411b69c1ccf31a2a81791f864d43bd50b4a0bf57f12188a"}