{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SGPMRMN6PMS4EOMBN3KD7B65AX","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":"b2f857e41fccc27e06222e99f7e9fdf1fb868520ca3d9c210e736b763fb8ee15","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-06T01:09:17Z","title_canon_sha256":"43ca99f03fe488ab26d651ae0e54170b32e65af2d25f1297ab8d513d1a828e00"},"schema_version":"1.0","source":{"id":"2411.03590","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.03590","created_at":"2026-07-05T09:31:34Z"},{"alias_kind":"arxiv_version","alias_value":"2411.03590v1","created_at":"2026-07-05T09:31:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.03590","created_at":"2026-07-05T09:31:34Z"},{"alias_kind":"pith_short_12","alias_value":"SGPMRMN6PMS4","created_at":"2026-07-05T09:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"SGPMRMN6PMS4EOMB","created_at":"2026-07-05T09:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"SGPMRMN6","created_at":"2026-07-05T09:31:34Z"}],"graph_snapshots":[{"event_id":"sha256:b730bf6d0479d57bcdbf10606cb3547925004d15fc64f9ae7abfae209911a0ad","target":"graph","created_at":"2026-07-05T09:31:34Z","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/2411.03590/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Run-time steering strategies like Medprompt are valuable for guiding large language models (LLMs) to top performance on challenging tasks. Medprompt demonstrates that a general LLM can be focused to deliver state-of-the-art performance on specialized domains like medicine by using a prompt to elicit a run-time strategy involving chain of thought reasoning and ensembling. OpenAI's o1-preview model represents a new paradigm, where a model is designed to do run-time reasoning before generating final responses. We seek to understand the behavior of o1-preview on a diverse set of medical challenge ","authors_text":"Eric Horvitz, Harsha Nori, Naoto Usuyama, Nicholas King, Scott Mayer McKinney, Sheng Zhang, Xavier Fernandes","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-06T01:09:17Z","title":"From Medprompt to o1: Exploration of Run-Time Strategies for Medical Challenge Problems and Beyond"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.03590","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":"sha256:0a5648447b7de6662b7d634520ae7ebd342b361c47cc178ed55203e11eb5f1a3","target":"record","created_at":"2026-07-05T09:31:34Z","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":"b2f857e41fccc27e06222e99f7e9fdf1fb868520ca3d9c210e736b763fb8ee15","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-06T01:09:17Z","title_canon_sha256":"43ca99f03fe488ab26d651ae0e54170b32e65af2d25f1297ab8d513d1a828e00"},"schema_version":"1.0","source":{"id":"2411.03590","kind":"arxiv","version":1}},"canonical_sha256":"919ec8b1be7b25c239816ed43f87dd05f5db4c0cc1e937f6173881b0a8483955","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"919ec8b1be7b25c239816ed43f87dd05f5db4c0cc1e937f6173881b0a8483955","first_computed_at":"2026-07-05T09:31:34.882718Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:31:34.882718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6UR99/2dRKgD+21r/OA6XuPMYwjXZiPvZ//74KivOp/7FZyg7zVgt6dVYVlEUJ/d2L8knPlcYrdqQ5i/Pnc0CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:31:34.883176Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.03590","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a5648447b7de6662b7d634520ae7ebd342b361c47cc178ed55203e11eb5f1a3","sha256:b730bf6d0479d57bcdbf10606cb3547925004d15fc64f9ae7abfae209911a0ad"],"state_sha256":"c5c667fc1b10ad047ba752dba223e6045d5742678abfe356c066ea4278da30f3"}