{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VWH64TAKBKYBFU55DWD6YRNLQQ","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":"178df820896ce72111bc10ff854a69d760dec85459c610e9cf8af7e8dc4cdd2c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T16:58:18Z","title_canon_sha256":"0e621d2ade5b1a3e6cc1cdb381ecf1f0139de3ff1297e6f4af0f0eafacd66e8d"},"schema_version":"1.0","source":{"id":"2407.13692","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.13692","created_at":"2026-07-05T08:50:57Z"},{"alias_kind":"arxiv_version","alias_value":"2407.13692v2","created_at":"2026-07-05T08:50:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13692","created_at":"2026-07-05T08:50:57Z"},{"alias_kind":"pith_short_12","alias_value":"VWH64TAKBKYB","created_at":"2026-07-05T08:50:57Z"},{"alias_kind":"pith_short_16","alias_value":"VWH64TAKBKYBFU55","created_at":"2026-07-05T08:50:57Z"},{"alias_kind":"pith_short_8","alias_value":"VWH64TAK","created_at":"2026-07-05T08:50:57Z"}],"graph_snapshots":[{"event_id":"sha256:a845660b8f02cfcb79aad51f43a44e0a7d37aa2fb53174e23e0e0c696a51252e","target":"graph","created_at":"2026-07-05T08:50:57Z","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/2407.13692/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One way to increase confidence in the outputs of Large Language Models (LLMs) is to support them with reasoning that is clear and easy to check -- a property we call legibility. We study legibility in the context of solving grade-school math problems and show that optimizing chain-of-thought solutions only for answer correctness can make them less legible. To mitigate the loss in legibility, we propose a training algorithm inspired by Prover-Verifier Game from Anil et al. (2021). Our algorithm iteratively trains small verifiers to predict solution correctness, \"helpful\" provers to produce corr","authors_text":"Harri Edwards, Jan Hendrik Kirchner, Jan Leike, Nat McAleese, Yining Chen, Yuri Burda","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T16:58:18Z","title":"Prover-Verifier Games improve legibility of LLM outputs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13692","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:b59cf4807fc68798b84b0a86c55284659bfd25bb9e07f1add7d773a8a5829017","target":"record","created_at":"2026-07-05T08:50:57Z","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":"178df820896ce72111bc10ff854a69d760dec85459c610e9cf8af7e8dc4cdd2c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T16:58:18Z","title_canon_sha256":"0e621d2ade5b1a3e6cc1cdb381ecf1f0139de3ff1297e6f4af0f0eafacd66e8d"},"schema_version":"1.0","source":{"id":"2407.13692","kind":"arxiv","version":2}},"canonical_sha256":"ad8fee4c0a0ab012d3bd1d87ec45ab84379df1cc40a699d2cab11b32c2efc424","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad8fee4c0a0ab012d3bd1d87ec45ab84379df1cc40a699d2cab11b32c2efc424","first_computed_at":"2026-07-05T08:50:57.742519Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:50:57.742519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YEgC1UEy0kjuzo6DvYROjPEpICFKxvLjNCDJlue/RphByWBbGgDs/SI5r1VWMVDL2Xt0CoJL4zXR+EIO7p+3Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:50:57.742954Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.13692","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b59cf4807fc68798b84b0a86c55284659bfd25bb9e07f1add7d773a8a5829017","sha256:a845660b8f02cfcb79aad51f43a44e0a7d37aa2fb53174e23e0e0c696a51252e"],"state_sha256":"82ae927e34971843b3334618c029a24dd905ea34fc071e8fdbc27d807ecd7646"}