{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4DXPKZQRLL2NOVFAG7YBYFMVFW","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":"0ab10eff8bea0ca955d02d0f666c0ffcb10d316b78ebd9b5efc69a99db205903","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-07T23:48:52Z","title_canon_sha256":"e765a444a5ad80d86de12c7296adb7d5921f67e0a25bba6258eade92c94d761f"},"schema_version":"1.0","source":{"id":"2410.05563","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.05563","created_at":"2026-07-05T11:26:01Z"},{"alias_kind":"arxiv_version","alias_value":"2410.05563v3","created_at":"2026-07-05T11:26:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.05563","created_at":"2026-07-05T11:26:01Z"},{"alias_kind":"pith_short_12","alias_value":"4DXPKZQRLL2N","created_at":"2026-07-05T11:26:01Z"},{"alias_kind":"pith_short_16","alias_value":"4DXPKZQRLL2NOVFA","created_at":"2026-07-05T11:26:01Z"},{"alias_kind":"pith_short_8","alias_value":"4DXPKZQR","created_at":"2026-07-05T11:26:01Z"}],"graph_snapshots":[{"event_id":"sha256:3c7616445e6b827ddab755e6847728196fe3820f125d7031bf66cc5d600b4dd5","target":"graph","created_at":"2026-07-05T11:26:01Z","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/2410.05563/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Being prompted to engage in reasoning has emerged as a core technique for using large language models (LLMs), deploying additional inference-time compute to improve task performance. However, as LLMs increase in both size and adoption, inference costs are correspondingly becoming increasingly burdensome. How, then, might we optimize reasoning's cost-performance tradeoff? This work introduces a novel approach based on computational models of metareasoning used in cognitive science, training LLMs to selectively use intermediate reasoning steps only when necessary. We first develop a reward funct","authors_text":"Antoine Bosselut, Badr AlKhamissi, C. Nicol\\`o De Sabbata, Theodore R. Sumers, Thomas L. Griffiths","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-07T23:48:52Z","title":"Rational Metareasoning for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.05563","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":"sha256:028fd1a3b629fbbd77c180594e2c5e6b9287b8ca72f8005249f40559f877be63","target":"record","created_at":"2026-07-05T11:26:01Z","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":"0ab10eff8bea0ca955d02d0f666c0ffcb10d316b78ebd9b5efc69a99db205903","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-07T23:48:52Z","title_canon_sha256":"e765a444a5ad80d86de12c7296adb7d5921f67e0a25bba6258eade92c94d761f"},"schema_version":"1.0","source":{"id":"2410.05563","kind":"arxiv","version":3}},"canonical_sha256":"e0eef566115af4d754a037f01c15952d9ce18eb627d785fbdb2beeb798f21290","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e0eef566115af4d754a037f01c15952d9ce18eb627d785fbdb2beeb798f21290","first_computed_at":"2026-07-05T11:26:01.099723Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:26:01.099723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sULJsfs0N2TynZedIIqlIu6GmZERASNJjdRDhpn4aDQiljtEWMHDFo8Yz4Qm0DCh3Src0Bl+IqAFIXLxDgv1CA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:26:01.100223Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.05563","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:028fd1a3b629fbbd77c180594e2c5e6b9287b8ca72f8005249f40559f877be63","sha256:3c7616445e6b827ddab755e6847728196fe3820f125d7031bf66cc5d600b4dd5"],"state_sha256":"487d46a8e82c71cc32cd6161ada4c58de8b64e37bd9e0b54ebecbeba29192109"}