{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HBXNF2BCVHTOBOL5O3TPHGZ6MI","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":"ecaf81b9e69c6132129489c1e73f90b9accc40974758b64121749ee1458625f6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-03T07:23:22Z","title_canon_sha256":"de3c63672c9e0e842998e7add9e8dcf37427718d68bef7fc3c6ec8a314cd02be"},"schema_version":"1.0","source":{"id":"2310.01846","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.01846","created_at":"2026-07-05T06:56:46Z"},{"alias_kind":"arxiv_version","alias_value":"2310.01846v1","created_at":"2026-07-05T06:56:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01846","created_at":"2026-07-05T06:56:46Z"},{"alias_kind":"pith_short_12","alias_value":"HBXNF2BCVHTO","created_at":"2026-07-05T06:56:46Z"},{"alias_kind":"pith_short_16","alias_value":"HBXNF2BCVHTOBOL5","created_at":"2026-07-05T06:56:46Z"},{"alias_kind":"pith_short_8","alias_value":"HBXNF2BC","created_at":"2026-07-05T06:56:46Z"}],"graph_snapshots":[{"event_id":"sha256:290506df101567c4a5873b1583d5fbda7ecf1421fd2f602bbe7505c10763f414","target":"graph","created_at":"2026-07-05T06:56:46Z","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/2310.01846/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As of September 2023, ChatGPT correctly answers \"what is 7+8\" with 15, but when asked \"7+8=15, True or False\" it responds with \"False\". This inconsistency between generating and validating an answer is prevalent in language models (LMs) and erodes trust. In this paper, we propose a framework for measuring the consistency between generation and validation (which we call generator-validator consistency, or GV-consistency), finding that even GPT-4, a state-of-the-art LM, is GV-consistent only 76% of the time. To improve the consistency of LMs, we propose to finetune on the filtered generator and ","authors_text":"Percy Liang, Siyan Li, Tatsunori Hashimoto, Vaishnavi Shrivastava, Xiang Lisa Li","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-03T07:23:22Z","title":"Benchmarking and Improving Generator-Validator Consistency of Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01846","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":"sha256:8066b267de67ed2c38e431dc31c2f16355c7916b493fa9f0bee33c63d3f926b4","target":"record","created_at":"2026-07-05T06:56:46Z","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":"ecaf81b9e69c6132129489c1e73f90b9accc40974758b64121749ee1458625f6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-03T07:23:22Z","title_canon_sha256":"de3c63672c9e0e842998e7add9e8dcf37427718d68bef7fc3c6ec8a314cd02be"},"schema_version":"1.0","source":{"id":"2310.01846","kind":"arxiv","version":1}},"canonical_sha256":"386ed2e822a9e6e0b97d76e6f39b3e6210f91bc1019ac843c526de836583896d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"386ed2e822a9e6e0b97d76e6f39b3e6210f91bc1019ac843c526de836583896d","first_computed_at":"2026-07-05T06:56:46.673118Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:56:46.673118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bB6eALY38Pjq3e0enI1Ty6UDunfPLsadZm0MpqbE8Oh127rmIudmQ7IxQkipDHCn7XDR2cqwg4XjALr3Ko2KDw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:56:46.673613Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.01846","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8066b267de67ed2c38e431dc31c2f16355c7916b493fa9f0bee33c63d3f926b4","sha256:290506df101567c4a5873b1583d5fbda7ecf1421fd2f602bbe7505c10763f414"],"state_sha256":"2ad55af52a85e9537a14a6b2f19eddd8b91ff2dd17b8ecdad27109322e8754ab"}