{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TEMDNXY57VF3LNA6NMTYGKCHDJ","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":"ae0efe4d59daca0b34fd7e6555a5ec89086026d47232667eca66d882de5df5ff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-25T06:29:18Z","title_canon_sha256":"f5d3b50f4a4c19615367623f79b1f33bca57e98b99c53d7579dd35f5adae46a2"},"schema_version":"1.0","source":{"id":"2506.20160","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.20160","created_at":"2026-07-05T11:50:37Z"},{"alias_kind":"arxiv_version","alias_value":"2506.20160v2","created_at":"2026-07-05T11:50:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20160","created_at":"2026-07-05T11:50:37Z"},{"alias_kind":"pith_short_12","alias_value":"TEMDNXY57VF3","created_at":"2026-07-05T11:50:37Z"},{"alias_kind":"pith_short_16","alias_value":"TEMDNXY57VF3LNA6","created_at":"2026-07-05T11:50:37Z"},{"alias_kind":"pith_short_8","alias_value":"TEMDNXY5","created_at":"2026-07-05T11:50:37Z"}],"graph_snapshots":[{"event_id":"sha256:4984c718861a28bb4bade0004313eff7aa2b578b3c44039470ed36e7ad267b4b","target":"graph","created_at":"2026-07-05T11:50:37Z","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/2506.20160/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large reasoning models (LRMs) achieve impressive reasoning capabilities by generating lengthy chain-of-thoughts, but this \"overthinking\" incurs high latency and cost without commensurate accuracy gains. In this work, we introduce AALC, a lightweight, accuracy-aware length reward integrated into reinforcement learning that dynamically balances correctness and brevity during training. By incorporating validation accuracy into the reward and employing a smooth, dynamically scheduled length penalty, AALC delays length penalty until target performance is met. Through extensive experiments across st","authors_text":"Ali Payani, Ben Zhou, Quan Zhang, Ruochen Li, Ruosen Li, Xinya Du, Ziming Luo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-25T06:29:18Z","title":"AALC: Large Language Model Efficient Reasoning via Adaptive Accuracy-Length Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20160","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":"sha256:1093bd03511489d8d94f7c1802b2678e6b8265d83ff3052511a547100e6e13d2","target":"record","created_at":"2026-07-05T11:50:37Z","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":"ae0efe4d59daca0b34fd7e6555a5ec89086026d47232667eca66d882de5df5ff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-25T06:29:18Z","title_canon_sha256":"f5d3b50f4a4c19615367623f79b1f33bca57e98b99c53d7579dd35f5adae46a2"},"schema_version":"1.0","source":{"id":"2506.20160","kind":"arxiv","version":2}},"canonical_sha256":"991836df1dfd4bb5b41e6b278328471a6595d4cf7d261b2f261837a7f31312e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"991836df1dfd4bb5b41e6b278328471a6595d4cf7d261b2f261837a7f31312e7","first_computed_at":"2026-07-05T11:50:37.880986Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:50:37.880986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9Cw2ufrdEE3JJmuHJ1736JqhS9lDwd7qIX8Dj3T7mIlWDyxp3VMgcEfFuzaVbZaIvIBprFrT8KvB1lm3pvXwCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:50:37.881490Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.20160","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1093bd03511489d8d94f7c1802b2678e6b8265d83ff3052511a547100e6e13d2","sha256:4984c718861a28bb4bade0004313eff7aa2b578b3c44039470ed36e7ad267b4b"],"state_sha256":"e16b0bd5ece3a23e69369383cd22ccbdfcbb36acd06db2a4dbc8ea581cd2ac9e"}