{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4ZAEECH554PDSRL4USYWOEF6Q6","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":"4943b40556c0f6cbac4c52e66aa34a93b9b6e4f551a790e2e02d1d2d68f253c9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-17T03:50:28Z","title_canon_sha256":"a013c8469ffb92c38a4633361b1d5d461e63e4c80437e76ae29c70298e1155dc"},"schema_version":"1.0","source":{"id":"2405.10516","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.10516","created_at":"2026-07-05T08:41:45Z"},{"alias_kind":"arxiv_version","alias_value":"2405.10516v2","created_at":"2026-07-05T08:41:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.10516","created_at":"2026-07-05T08:41:45Z"},{"alias_kind":"pith_short_12","alias_value":"4ZAEECH554PD","created_at":"2026-07-05T08:41:45Z"},{"alias_kind":"pith_short_16","alias_value":"4ZAEECH554PDSRL4","created_at":"2026-07-05T08:41:45Z"},{"alias_kind":"pith_short_8","alias_value":"4ZAEECH5","created_at":"2026-07-05T08:41:45Z"}],"graph_snapshots":[{"event_id":"sha256:9f10f3d5aaae1f9c4d89d652c56e56fb88cd4b7eb894b1e28dfcc19187316951","target":"graph","created_at":"2026-07-05T08:41:45Z","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/2405.10516/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we initiate our discussion by demonstrating how Large Language Models (LLMs), when tasked with responding to queries, display a more even probability distribution in their answers if they are more adept, as opposed to their less skilled counterparts. Expanding on this foundational insight, we propose a new self-evaluation method ProbDiff for assessing the efficacy of various LLMs. This approach obviates the necessity for an additional evaluation model or the dependence on external, proprietary models like GPT-4 for judgment. It uniquely utilizes the LLMs being tested to compute ","authors_text":"Bowen Yu, Chang Zhou, Tingyu Xia, Yi Chang, Yuan Wu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-17T03:50:28Z","title":"Language Models can Evaluate Themselves via Probability Discrepancy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.10516","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:b333236eea6e250a237afc0459662b80a9a4b98b7a8c4b91e26beb2a6cca2348","target":"record","created_at":"2026-07-05T08:41:45Z","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":"4943b40556c0f6cbac4c52e66aa34a93b9b6e4f551a790e2e02d1d2d68f253c9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-17T03:50:28Z","title_canon_sha256":"a013c8469ffb92c38a4633361b1d5d461e63e4c80437e76ae29c70298e1155dc"},"schema_version":"1.0","source":{"id":"2405.10516","kind":"arxiv","version":2}},"canonical_sha256":"e6404208fdef1e39457ca4b16710be87b34de6e30eab785103570d225f96d5b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e6404208fdef1e39457ca4b16710be87b34de6e30eab785103570d225f96d5b6","first_computed_at":"2026-07-05T08:41:45.195803Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:41:45.195803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LyyPXLZ+Fd5DN1jucgOjiW3w6uoJOqfj5mDXZFXb+Ppen+fP695JlcDRslWU3liU3u8kAuS/Yr31qKlJ2ZlDCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:41:45.196263Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.10516","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b333236eea6e250a237afc0459662b80a9a4b98b7a8c4b91e26beb2a6cca2348","sha256:9f10f3d5aaae1f9c4d89d652c56e56fb88cd4b7eb894b1e28dfcc19187316951"],"state_sha256":"a43689fa57e3c43a90de3952e1e4a510c1272fdaeca5896683bef364b24ce0ca"}