{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:E2W7POCQKPQ5ULBRSOVT5WEML5","short_pith_number":"pith:E2W7POCQ","schema_version":"1.0","canonical_sha256":"26adf7b85053e1da2c3193ab3ed88c5f6bddcf2cdc33700af71f79d3e3c6b0ed","source":{"kind":"arxiv","id":"2504.21303","version":1},"attestation_state":"computed","paper":{"title":"Confidence in Large Language Model Evaluation: A Bayesian Approach to Limited-Sample Challenges","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Sijing Zhang, Tian Liu, Xiao Xiao, Yadong Chen, Yu Su, Zhang Chen","submitted_at":"2025-04-30T04:24:50Z","abstract_excerpt":"Large language models (LLMs) exhibit probabilistic output characteristics, yet conventional evaluation frameworks rely on deterministic scalar metrics. This study introduces a Bayesian approach for LLM capability assessment that integrates prior knowledge through probabilistic inference, addressing limitations under limited-sample regimes. By treating model capabilities as latent variables and leveraging a curated query set to induce discriminative responses, we formalize model ranking as a Bayesian hypothesis testing problem over mutually exclusive capability intervals. Experimental evaluatio"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2504.21303","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-30T04:24:50Z","cross_cats_sorted":[],"title_canon_sha256":"59dae40383b06985d541f80723587efc631e9779def794799992afea14ce8837","abstract_canon_sha256":"c7beb0a9fd9a8690b4bbeb989275c6c451092d0f209429c935435bf4bf8150b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:56:21.800176Z","signature_b64":"SXIRlPOwFbjdYJnSCXaO8kiM2qPAPzp6emT/FiH5OvnXzx+pUinmepSHIfZOBEUMn5bDXSSbm9HKLTbkwmB+Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26adf7b85053e1da2c3193ab3ed88c5f6bddcf2cdc33700af71f79d3e3c6b0ed","last_reissued_at":"2026-07-05T10:56:21.799704Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:56:21.799704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Confidence in Large Language Model Evaluation: A Bayesian Approach to Limited-Sample Challenges","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Sijing Zhang, Tian Liu, Xiao Xiao, Yadong Chen, Yu Su, Zhang Chen","submitted_at":"2025-04-30T04:24:50Z","abstract_excerpt":"Large language models (LLMs) exhibit probabilistic output characteristics, yet conventional evaluation frameworks rely on deterministic scalar metrics. This study introduces a Bayesian approach for LLM capability assessment that integrates prior knowledge through probabilistic inference, addressing limitations under limited-sample regimes. By treating model capabilities as latent variables and leveraging a curated query set to induce discriminative responses, we formalize model ranking as a Bayesian hypothesis testing problem over mutually exclusive capability intervals. Experimental evaluatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.21303","kind":"arxiv","version":1},"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/2504.21303/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2504.21303","created_at":"2026-07-05T10:56:21.799760+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.21303v1","created_at":"2026-07-05T10:56:21.799760+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21303","created_at":"2026-07-05T10:56:21.799760+00:00"},{"alias_kind":"pith_short_12","alias_value":"E2W7POCQKPQ5","created_at":"2026-07-05T10:56:21.799760+00:00"},{"alias_kind":"pith_short_16","alias_value":"E2W7POCQKPQ5ULBR","created_at":"2026-07-05T10:56:21.799760+00:00"},{"alias_kind":"pith_short_8","alias_value":"E2W7POCQ","created_at":"2026-07-05T10:56:21.799760+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.04265","citing_title":"Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E2W7POCQKPQ5ULBRSOVT5WEML5","json":"https://pith.science/pith/E2W7POCQKPQ5ULBRSOVT5WEML5.json","graph_json":"https://pith.science/api/pith-number/E2W7POCQKPQ5ULBRSOVT5WEML5/graph.json","events_json":"https://pith.science/api/pith-number/E2W7POCQKPQ5ULBRSOVT5WEML5/events.json","paper":"https://pith.science/paper/E2W7POCQ"},"agent_actions":{"view_html":"https://pith.science/pith/E2W7POCQKPQ5ULBRSOVT5WEML5","download_json":"https://pith.science/pith/E2W7POCQKPQ5ULBRSOVT5WEML5.json","view_paper":"https://pith.science/paper/E2W7POCQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.21303&json=true","fetch_graph":"https://pith.science/api/pith-number/E2W7POCQKPQ5ULBRSOVT5WEML5/graph.json","fetch_events":"https://pith.science/api/pith-number/E2W7POCQKPQ5ULBRSOVT5WEML5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E2W7POCQKPQ5ULBRSOVT5WEML5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E2W7POCQKPQ5ULBRSOVT5WEML5/action/storage_attestation","attest_author":"https://pith.science/pith/E2W7POCQKPQ5ULBRSOVT5WEML5/action/author_attestation","sign_citation":"https://pith.science/pith/E2W7POCQKPQ5ULBRSOVT5WEML5/action/citation_signature","submit_replication":"https://pith.science/pith/E2W7POCQKPQ5ULBRSOVT5WEML5/action/replication_record"}},"created_at":"2026-07-05T10:56:21.799760+00:00","updated_at":"2026-07-05T10:56:21.799760+00:00"}