{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3PZX3FDIGWZUBEP764V7LAZOCI","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":"3ccd4d04f11785c23d19ce065c1ddbbcab3fa7e7575bd401e95df46f6143ecdf","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-07-21T17:52:34Z","title_canon_sha256":"b818768177e489d901938a2367c256d9d97aeab78a4720f917e8b0c7a9647f67"},"schema_version":"1.0","source":{"id":"2507.15844","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.15844","created_at":"2026-07-05T11:49:57Z"},{"alias_kind":"arxiv_version","alias_value":"2507.15844v3","created_at":"2026-07-05T11:49:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15844","created_at":"2026-07-05T11:49:57Z"},{"alias_kind":"pith_short_12","alias_value":"3PZX3FDIGWZU","created_at":"2026-07-05T11:49:57Z"},{"alias_kind":"pith_short_16","alias_value":"3PZX3FDIGWZUBEP7","created_at":"2026-07-05T11:49:57Z"},{"alias_kind":"pith_short_8","alias_value":"3PZX3FDI","created_at":"2026-07-05T11:49:57Z"}],"graph_snapshots":[{"event_id":"sha256:9eb5e56122fe4bec014e3a41b1d121f502f28248efa422cc48996800d914671a","target":"graph","created_at":"2026-07-05T11:49:57Z","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/2507.15844/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large reasoning models achieve remarkable performance through extensive chain-of-thought generation, yet they suffer from a critical inefficiency: applying uniformly extensive reasoning regardless of problem complexity. We present Hierarchical Budget Policy Optimization (HBPO), a reinforcement learning framework that enables models to learn problem-specific reasoning depths without sacrificing capability. Unlike existing approaches that impose rigid constraints or rely on discrete mode selection, HBPO partitions the exploration space into budget-constrained hierarchies (512-2560 tokens), each ","authors_text":"Hao Li, Jun Xiao, Linjuan Wu, Peisheng Jiang, Shangke Lyu, Weiming Lu, Xingyu Wu, Yongliang Shen, Yuchen Yan, Yueting Zhuang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-07-21T17:52:34Z","title":"Hierarchical Budget Policy Optimization for Adaptive Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15844","kind":"arxiv","version":3},"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":"sha256:14dad6d475bcbfd02be890beadf78934bf94bbff85ffda51d32f8c8e59cfbc4f","target":"record","created_at":"2026-07-05T11:49:57Z","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":"3ccd4d04f11785c23d19ce065c1ddbbcab3fa7e7575bd401e95df46f6143ecdf","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-07-21T17:52:34Z","title_canon_sha256":"b818768177e489d901938a2367c256d9d97aeab78a4720f917e8b0c7a9647f67"},"schema_version":"1.0","source":{"id":"2507.15844","kind":"arxiv","version":3}},"canonical_sha256":"dbf37d946835b34091fff72bf5832e122b2c718e9d14161637aabb1982806372","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dbf37d946835b34091fff72bf5832e122b2c718e9d14161637aabb1982806372","first_computed_at":"2026-07-05T11:49:57.453621Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:57.453621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G7obdUpvYd3a7lknJuopJXOty7ndbQ2y2jPzMwB0LcFx1wKh/qGtbntKICD5mAD8On6eDVkKPOvvnv/qr6++Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:49:57.454079Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.15844","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14dad6d475bcbfd02be890beadf78934bf94bbff85ffda51d32f8c8e59cfbc4f","sha256:9eb5e56122fe4bec014e3a41b1d121f502f28248efa422cc48996800d914671a"],"state_sha256":"7a05911ecaa8016c11e48cd19fd357bdaef4a842bfb1680eaaf374788295784c"}