{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:G7MHQXAT2RJTXENUF2SKG33H5M","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":"d4a4c976027b6256f83ea2a3bbca05297854c01e479ca637878575c22adb1a1b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T18:43:24Z","title_canon_sha256":"640253596b0cfba6a4bc5ee00bea62fcb8542ddd0178c7f762ceb13a88f2123d"},"schema_version":"1.0","source":{"id":"2502.12118","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.12118","created_at":"2026-07-05T10:16:22Z"},{"alias_kind":"arxiv_version","alias_value":"2502.12118v2","created_at":"2026-07-05T10:16:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12118","created_at":"2026-07-05T10:16:22Z"},{"alias_kind":"pith_short_12","alias_value":"G7MHQXAT2RJT","created_at":"2026-07-05T10:16:22Z"},{"alias_kind":"pith_short_16","alias_value":"G7MHQXAT2RJTXENU","created_at":"2026-07-05T10:16:22Z"},{"alias_kind":"pith_short_8","alias_value":"G7MHQXAT","created_at":"2026-07-05T10:16:22Z"}],"graph_snapshots":[{"event_id":"sha256:6c28b4e2f306b01dda74bb8d880fa23a6a24f521a6b60132866dcd50bd6debc8","target":"graph","created_at":"2026-07-05T10:16:22Z","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/2502.12118/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite substantial advances in scaling test-time compute, an ongoing debate in the community is how it should be scaled up to enable continued and efficient improvements with scaling. There are largely two approaches: first, distilling successful search or thinking traces; and second, using verification (e.g., 0/1 outcome rewards, reward models, or verifiers) to guide reinforcement learning (RL) and search algorithms. In this paper, we prove that finetuning LLMs with verifier-based (VB) methods based on RL or search is far superior to verifier-free (VF) approaches based on distilling or cloni","authors_text":"Amrith Setlur, Aviral Kumar, Nived Rajaraman, Sergey Levine","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T18:43:24Z","title":"Scaling Test-Time Compute Without Verification or RL is Suboptimal"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12118","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:d4f8687cfd463434d1db704a7d9588f05db7c51c995292f88e18cdd8e7f83cc0","target":"record","created_at":"2026-07-05T10:16:22Z","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":"d4a4c976027b6256f83ea2a3bbca05297854c01e479ca637878575c22adb1a1b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T18:43:24Z","title_canon_sha256":"640253596b0cfba6a4bc5ee00bea62fcb8542ddd0178c7f762ceb13a88f2123d"},"schema_version":"1.0","source":{"id":"2502.12118","kind":"arxiv","version":2}},"canonical_sha256":"37d8785c13d4533b91b42ea4a36f67eb0305ed4b31d8e8a5fa36f6b6f84d0743","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"37d8785c13d4533b91b42ea4a36f67eb0305ed4b31d8e8a5fa36f6b6f84d0743","first_computed_at":"2026-07-05T10:16:22.239164Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:16:22.239164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AsTiGUyBU7fWQ1H5l/sOvbfr0svhvfhMZlJq2vGqzNU6un8IQUKPUbT8CGZ9PXIlfESK+qLzL5UlZSdiN6j4Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:16:22.239676Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.12118","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4f8687cfd463434d1db704a7d9588f05db7c51c995292f88e18cdd8e7f83cc0","sha256:6c28b4e2f306b01dda74bb8d880fa23a6a24f521a6b60132866dcd50bd6debc8"],"state_sha256":"392e7561ffc0837722f1d03c1d2cdd7d06073e21bb01dbf7c30c55351212a4ce"}