{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:N6PCWXV7OGXO4EIGFTKTZJUEW7","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":"a11110ddd7815b5c9948ada730657a53b58f2d058f89c24f56e1941938edf5f5","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-12T13:48:03Z","title_canon_sha256":"7bb3ef54eba45e2c9056885940e4459d38de2e8a3b8f92e6e709ca1a2b7d97af"},"schema_version":"1.0","source":{"id":"2508.08940","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.08940","created_at":"2026-07-05T11:52:37Z"},{"alias_kind":"arxiv_version","alias_value":"2508.08940v1","created_at":"2026-07-05T11:52:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.08940","created_at":"2026-07-05T11:52:37Z"},{"alias_kind":"pith_short_12","alias_value":"N6PCWXV7OGXO","created_at":"2026-07-05T11:52:37Z"},{"alias_kind":"pith_short_16","alias_value":"N6PCWXV7OGXO4EIG","created_at":"2026-07-05T11:52:37Z"},{"alias_kind":"pith_short_8","alias_value":"N6PCWXV7","created_at":"2026-07-05T11:52:37Z"}],"graph_snapshots":[{"event_id":"sha256:d41538812edfeb6df4945ddd12e2cd534f2ec676466a8483161c013ab47af115","target":"graph","created_at":"2026-07-05T11:52:37Z","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/2508.08940/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work on enhancing the reasoning abilities of large language models (LLMs) has introduced explicit length control as a means of constraining computational cost while preserving accuracy. However, existing approaches rely on fixed-length training budgets, which do not take advantage of the natural progression from exploration to compression during learning. In this work, we propose a curriculum learning strategy for length-controlled reasoning using Group Relative Policy Optimization (GRPO). Our method starts with generous token budgets and gradually tightens them over training, encouragi","authors_text":"Abed Hammoud, Bernard Ghanem, Elie Bou-Zeid, Hasan Abed Al Kader Hammoud, Kumail Alhamoud, Marzyeh Ghassemi","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-12T13:48:03Z","title":"Train Long, Think Short: Curriculum Learning for Efficient Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.08940","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":"sha256:298931011c65624108badb3e8935a2237d8eb3de232fcd6ff3412d94e2e329e0","target":"record","created_at":"2026-07-05T11:52:37Z","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":"a11110ddd7815b5c9948ada730657a53b58f2d058f89c24f56e1941938edf5f5","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-12T13:48:03Z","title_canon_sha256":"7bb3ef54eba45e2c9056885940e4459d38de2e8a3b8f92e6e709ca1a2b7d97af"},"schema_version":"1.0","source":{"id":"2508.08940","kind":"arxiv","version":1}},"canonical_sha256":"6f9e2b5ebf71aeee11062cd53ca684b7d2d491151074742f2732adfe93bafc1b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f9e2b5ebf71aeee11062cd53ca684b7d2d491151074742f2732adfe93bafc1b","first_computed_at":"2026-07-05T11:52:37.067783Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:52:37.067783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VtxYuaLWPzMiBaOkFWuZmjCK08FdKrXA9XIXrKc1DhMZ/FyFueIznp1CG3vRT39pj7tzWjdovr8Q1Zg8U02wAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:52:37.068478Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.08940","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:298931011c65624108badb3e8935a2237d8eb3de232fcd6ff3412d94e2e329e0","sha256:d41538812edfeb6df4945ddd12e2cd534f2ec676466a8483161c013ab47af115"],"state_sha256":"d8dfdfa888cf15b8657e5dec48262150ad5d0a84d9aee104c3f3e187d6fe391f"}