{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TTWJ3XTA4UJANH7CXAHT5FNIYO","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":"c596a5a41de87c46792daa7150fb271a5dba4714fdf8c016fd0eaecc7e53a997","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-10T17:40:43Z","title_canon_sha256":"ba21c14a13242817fd97b1d13d9e755bb0bb5cbe71627ec5b825eb564d60b7a0"},"schema_version":"1.0","source":{"id":"2503.07572","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.07572","created_at":"2026-07-05T10:28:07Z"},{"alias_kind":"arxiv_version","alias_value":"2503.07572v1","created_at":"2026-07-05T10:28:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07572","created_at":"2026-07-05T10:28:07Z"},{"alias_kind":"pith_short_12","alias_value":"TTWJ3XTA4UJA","created_at":"2026-07-05T10:28:07Z"},{"alias_kind":"pith_short_16","alias_value":"TTWJ3XTA4UJANH7C","created_at":"2026-07-05T10:28:07Z"},{"alias_kind":"pith_short_8","alias_value":"TTWJ3XTA","created_at":"2026-07-05T10:28:07Z"}],"graph_snapshots":[{"event_id":"sha256:ae93ec574dae310c0198c88911fec2ac127889fe36062297177ee969132576de","target":"graph","created_at":"2026-07-05T10:28:07Z","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/2503.07572/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training models to effectively use test-time compute is crucial for improving the reasoning performance of LLMs. Current methods mostly do so via fine-tuning on search traces or running RL with 0/1 outcome reward, but do these approaches efficiently utilize test-time compute? Would these approaches continue to scale as the budget improves? In this paper, we try to answer these questions. We formalize the problem of optimizing test-time compute as a meta-reinforcement learning (RL) problem, which provides a principled perspective on spending test-time compute. This perspective enables us to vie","authors_text":"Amrith Setlur, Aviral Kumar, Edward Emanuel Beeching, Lewis Tunstall, Matthew Y. R. Yang, Ruslan Salakhutdinov, Yuxiao Qu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-10T17:40:43Z","title":"Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.07572","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":"sha256:67840f808f661d768d9fdc3b24bd7e8642fc00cca0cc53365c3338c540f01962","target":"record","created_at":"2026-07-05T10:28:07Z","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":"c596a5a41de87c46792daa7150fb271a5dba4714fdf8c016fd0eaecc7e53a997","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-10T17:40:43Z","title_canon_sha256":"ba21c14a13242817fd97b1d13d9e755bb0bb5cbe71627ec5b825eb564d60b7a0"},"schema_version":"1.0","source":{"id":"2503.07572","kind":"arxiv","version":1}},"canonical_sha256":"9cec9dde60e512069fe2b80f3e95a8c3a82dc7784ec333f3533c5f14ed1b2957","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9cec9dde60e512069fe2b80f3e95a8c3a82dc7784ec333f3533c5f14ed1b2957","first_computed_at":"2026-07-05T10:28:07.323637Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:28:07.323637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C6a6BbB8aK7IgHUTBN2SGfSbuqYwo2H/O2WKpw+9Udr0ZdYIB+8ToKOGOLBTIq0MK6L0nCjOPq3v0ymP+LULDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:28:07.324493Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.07572","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:67840f808f661d768d9fdc3b24bd7e8642fc00cca0cc53365c3338c540f01962","sha256:ae93ec574dae310c0198c88911fec2ac127889fe36062297177ee969132576de"],"state_sha256":"d54c33e8581b2af26902cb0a17fd1a59684ffbe30a2f002ac0ce89a9a551c009"}