{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:V3OHOFGP4QOW5PRR54DM4Y74WR","short_pith_number":"pith:V3OHOFGP","canonical_record":{"source":{"id":"2402.06782","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-09T21:05:01Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"11448bd75042b782594be7292b98ec2d1225554db9c6b3df1f1459c6fe3b2cc3","abstract_canon_sha256":"4b83a323fb110cc01394c9c18fe949ab731413a54801a10cba5cf91c85b9aa85"},"schema_version":"1.0"},"canonical_sha256":"aedc7714cfe41d6ebe31ef06ce63fcb474c7d116d6e571c6308445a0f73d24bd","source":{"kind":"arxiv","id":"2402.06782","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.06782","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"arxiv_version","alias_value":"2402.06782v4","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.06782","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"pith_short_12","alias_value":"V3OHOFGP4QOW","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"pith_short_16","alias_value":"V3OHOFGP4QOW5PRR","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"pith_short_8","alias_value":"V3OHOFGP","created_at":"2026-07-05T08:48:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:V3OHOFGP4QOW5PRR54DM4Y74WR","target":"record","payload":{"canonical_record":{"source":{"id":"2402.06782","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-09T21:05:01Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"11448bd75042b782594be7292b98ec2d1225554db9c6b3df1f1459c6fe3b2cc3","abstract_canon_sha256":"4b83a323fb110cc01394c9c18fe949ab731413a54801a10cba5cf91c85b9aa85"},"schema_version":"1.0"},"canonical_sha256":"aedc7714cfe41d6ebe31ef06ce63fcb474c7d116d6e571c6308445a0f73d24bd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:41.149468Z","signature_b64":"FBdmzaWqwegbOOvGpbpWsHS+zV3BeP+R6f3zi0T+LRhGyVXkw3Z4x2VVhs+ElPrLhfMG7PFt+rXmvBd9PZNTBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aedc7714cfe41d6ebe31ef06ce63fcb474c7d116d6e571c6308445a0f73d24bd","last_reissued_at":"2026-07-05T08:48:41.149047Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:41.149047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.06782","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:48:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ByU+YqDBPl485CImuG8Frt8mUWWZV8jMP+LMQ0rUujcB2hGCfMwXZOcdPq8rRkSR+IcOw87Xw7ISwtMMFqE0Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T03:08:40.975002Z"},"content_sha256":"de34a3596bda3786d8e4bd9bf574211e5b60e3cb2bd2e11d75a293b4ff96806c","schema_version":"1.0","event_id":"sha256:de34a3596bda3786d8e4bd9bf574211e5b60e3cb2bd2e11d75a293b4ff96806c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:V3OHOFGP4QOW5PRR54DM4Y74WR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Debating with More Persuasive LLMs Leads to More Truthful Answers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Akbir Khan, Ansh Radhakrishnan, Dan Valentine, Edward Grefenstette, Ethan Perez, John Hughes, Kshitij Sachan, Laura Ruis, Samuel R. Bowman, Tim Rockt\\\"aschel","submitted_at":"2024-02-09T21:05:01Z","abstract_excerpt":"Common methods for aligning large language models (LLMs) with desired behaviour heavily rely on human-labelled data. However, as models grow increasingly sophisticated, they will surpass human expertise, and the role of human evaluation will evolve into non-experts overseeing experts. In anticipation of this, we ask: can weaker models assess the correctness of stronger models? We investigate this question in an analogous setting, where stronger models (experts) possess the necessary information to answer questions and weaker models (non-experts) lack this information. The method we evaluate is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.06782","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.06782/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:48:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ESbrRJAFvIbz60aJINj3yfD6R5ymLvMQSvANp8nqW9OJfkSXgt12nJjBEQ6S4Wmu8J+IYG4qyqIQiIY5dl1/AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T03:08:40.975412Z"},"content_sha256":"fcda3e67dea99e247d6a1614c65f23f0653f87f05866c54aece702350c0ef423","schema_version":"1.0","event_id":"sha256:fcda3e67dea99e247d6a1614c65f23f0653f87f05866c54aece702350c0ef423"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V3OHOFGP4QOW5PRR54DM4Y74WR/bundle.json","state_url":"https://pith.science/pith/V3OHOFGP4QOW5PRR54DM4Y74WR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V3OHOFGP4QOW5PRR54DM4Y74WR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-11T03:08:40Z","links":{"resolver":"https://pith.science/pith/V3OHOFGP4QOW5PRR54DM4Y74WR","bundle":"https://pith.science/pith/V3OHOFGP4QOW5PRR54DM4Y74WR/bundle.json","state":"https://pith.science/pith/V3OHOFGP4QOW5PRR54DM4Y74WR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V3OHOFGP4QOW5PRR54DM4Y74WR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:V3OHOFGP4QOW5PRR54DM4Y74WR","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":"4b83a323fb110cc01394c9c18fe949ab731413a54801a10cba5cf91c85b9aa85","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-09T21:05:01Z","title_canon_sha256":"11448bd75042b782594be7292b98ec2d1225554db9c6b3df1f1459c6fe3b2cc3"},"schema_version":"1.0","source":{"id":"2402.06782","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.06782","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"arxiv_version","alias_value":"2402.06782v4","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.06782","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"pith_short_12","alias_value":"V3OHOFGP4QOW","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"pith_short_16","alias_value":"V3OHOFGP4QOW5PRR","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"pith_short_8","alias_value":"V3OHOFGP","created_at":"2026-07-05T08:48:41Z"}],"graph_snapshots":[{"event_id":"sha256:fcda3e67dea99e247d6a1614c65f23f0653f87f05866c54aece702350c0ef423","target":"graph","created_at":"2026-07-05T08:48:41Z","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/2402.06782/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Common methods for aligning large language models (LLMs) with desired behaviour heavily rely on human-labelled data. However, as models grow increasingly sophisticated, they will surpass human expertise, and the role of human evaluation will evolve into non-experts overseeing experts. In anticipation of this, we ask: can weaker models assess the correctness of stronger models? We investigate this question in an analogous setting, where stronger models (experts) possess the necessary information to answer questions and weaker models (non-experts) lack this information. The method we evaluate is","authors_text":"Akbir Khan, Ansh Radhakrishnan, Dan Valentine, Edward Grefenstette, Ethan Perez, John Hughes, Kshitij Sachan, Laura Ruis, Samuel R. Bowman, Tim Rockt\\\"aschel","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-09T21:05:01Z","title":"Debating with More Persuasive LLMs Leads to More Truthful Answers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.06782","kind":"arxiv","version":4},"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:de34a3596bda3786d8e4bd9bf574211e5b60e3cb2bd2e11d75a293b4ff96806c","target":"record","created_at":"2026-07-05T08:48:41Z","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":"4b83a323fb110cc01394c9c18fe949ab731413a54801a10cba5cf91c85b9aa85","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-09T21:05:01Z","title_canon_sha256":"11448bd75042b782594be7292b98ec2d1225554db9c6b3df1f1459c6fe3b2cc3"},"schema_version":"1.0","source":{"id":"2402.06782","kind":"arxiv","version":4}},"canonical_sha256":"aedc7714cfe41d6ebe31ef06ce63fcb474c7d116d6e571c6308445a0f73d24bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aedc7714cfe41d6ebe31ef06ce63fcb474c7d116d6e571c6308445a0f73d24bd","first_computed_at":"2026-07-05T08:48:41.149047Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:48:41.149047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FBdmzaWqwegbOOvGpbpWsHS+zV3BeP+R6f3zi0T+LRhGyVXkw3Z4x2VVhs+ElPrLhfMG7PFt+rXmvBd9PZNTBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:48:41.149468Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.06782","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de34a3596bda3786d8e4bd9bf574211e5b60e3cb2bd2e11d75a293b4ff96806c","sha256:fcda3e67dea99e247d6a1614c65f23f0653f87f05866c54aece702350c0ef423"],"state_sha256":"89007d35b7318e91cb83b838dc29e5534486a645acc1fcb34d4edca0b9400795"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5vaNSYeQhhqhb/0AVPOHT1BnXZ/1kBqQrAXS0AJyJ3fmbMRLNvkQqClt9IFu65FDV90KmSb1GQ5uKCWLwaf5AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T03:08:40.977962Z","bundle_sha256":"d007f215c26125e3a00e1e970b602cd2eb8a6b24da5b2589340ae9fd06c15a79"}}