{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GAMKVTX6ARKPF4ZBCWB7NQCTLT","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":"b1a9341107f383fb15057a7c00d7ff841b9dd6d483275304df9b41fc1c5a8f5d","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-01T09:01:55Z","title_canon_sha256":"4d7d7fbd9f89909d05de743fec973e63c8518103270140dba671b61ebdc22feb"},"schema_version":"1.0","source":{"id":"2606.01934","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01934","created_at":"2026-06-02T02:05:00Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01934v1","created_at":"2026-06-02T02:05:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01934","created_at":"2026-06-02T02:05:00Z"},{"alias_kind":"pith_short_12","alias_value":"GAMKVTX6ARKP","created_at":"2026-06-02T02:05:00Z"},{"alias_kind":"pith_short_16","alias_value":"GAMKVTX6ARKPF4ZB","created_at":"2026-06-02T02:05:00Z"},{"alias_kind":"pith_short_8","alias_value":"GAMKVTX6","created_at":"2026-06-02T02:05:00Z"}],"graph_snapshots":[{"event_id":"sha256:e782c06aa88e376994c49cab0aab3f6bf6dc07681087b629cfdd6106d4a69a3c","target":"graph","created_at":"2026-06-02T02:05:00Z","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/2606.01934/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models achieve remarkable performance via extended chain-of-thought (CoT) reasoning, yet this lengthy process incurs substantial inference overhead. Existing CoT compression methods struggle with inflexible manual length budgets, computationally expensive multi-stage training pipelines, and fragile scalability restricted to small models. We propose HMPO (Hybrid Median-length Policy Optimization), a cost-effective, single-stage reinforcement learning framework. HMPO efficiently compresses CoT via three synergistic components: an adaptive median-based budget derived from successfu","authors_text":"Hongsheng Xin, Hongxu Chen, Huimin Ren, Kaike Zhang, Kun Zhan, Minghui Zheng, Pan Zhou, Shuling Yang, Xiaoyang Qu, Ze Wang, Ziyu Peng","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-01T09:01:55Z","title":"HMPO: Hybrid Median-length Policy Optimization for Chain-of-Thought Compression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01934","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":"sha256:02d6bd0f457a1b5d175636f31f7ea428bd3d3458bd972ea2c4344053099012e5","target":"record","created_at":"2026-06-02T02:05:00Z","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":"b1a9341107f383fb15057a7c00d7ff841b9dd6d483275304df9b41fc1c5a8f5d","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-01T09:01:55Z","title_canon_sha256":"4d7d7fbd9f89909d05de743fec973e63c8518103270140dba671b61ebdc22feb"},"schema_version":"1.0","source":{"id":"2606.01934","kind":"arxiv","version":1}},"canonical_sha256":"3018aacefe0454f2f3211583f6c0535cfea515ad1cf950c90e197d023cda9b5c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3018aacefe0454f2f3211583f6c0535cfea515ad1cf950c90e197d023cda9b5c","first_computed_at":"2026-06-02T02:05:00.944552Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:05:00.944552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9im4fVkKpkKRNl1JoscYMn/7B7evurUgX5Doz/SCTUhBw4D62MrlsLJYiGhwCNSoWMPWknw0r63Rnz5c0GxjAg==","signature_status":"signed_v1","signed_at":"2026-06-02T02:05:00.944944Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.01934","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02d6bd0f457a1b5d175636f31f7ea428bd3d3458bd972ea2c4344053099012e5","sha256:e782c06aa88e376994c49cab0aab3f6bf6dc07681087b629cfdd6106d4a69a3c"],"state_sha256":"74368dce3fddf3f4139dcd3af4c2ff99c2902f3bfac5a1e79607b613b3ff4698"}