{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NTW5TVHGLCCEIZNFZ2C4IGFAMK","short_pith_number":"pith:NTW5TVHG","schema_version":"1.0","canonical_sha256":"6cedd9d4e658844465a5ce85c418a06296d0b40ffeb377741cc1abd65979e6e2","source":{"kind":"arxiv","id":"2412.05506","version":2},"attestation_state":"computed","paper":{"title":"Confidence Diagram of Nonparametric Ranking for Uncertainty Assessment in Large Language Models Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Ethan X. Fang, Junwei Lu, Lan Wang, Yi Han, Zebin Wang","submitted_at":"2024-12-07T02:34:30Z","abstract_excerpt":"We consider the inference for the ranking of large language models (LLMs). Alignment arises as a significant challenge to mitigate hallucinations in the use of LLMs. Ranking LLMs has proven to be an effective tool to improve alignment based on the best-of-$N$ policy. In this paper, we propose a new inferential framework for hypothesis testing among the ranking for language models. Our framework is based on a nonparametric contextual ranking framework designed to assess large language models' domain-specific expertise, leveraging nonparametric scoring methods to account for their sensitivity to"},"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":"2412.05506","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-12-07T02:34:30Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"18a34f7716637971d28f10d8acd5ff4c058614bed8631360ff62bdb8f3d384dc","abstract_canon_sha256":"96f3c3937b4bdd31b64abb5f3f30b39998a88bb11ce83339940ad5e89b28c1e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:02.479949Z","signature_b64":"FlIQoemjFPGEA2+oNyjiB3FGrgwRcpfIluUn5OQ/u7OW/WrmEWRDzx0vf+mEOt8b66rwpeQ1XNTg5KG6FYlUBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6cedd9d4e658844465a5ce85c418a06296d0b40ffeb377741cc1abd65979e6e2","last_reissued_at":"2026-07-05T10:12:02.479414Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:02.479414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Confidence Diagram of Nonparametric Ranking for Uncertainty Assessment in Large Language Models Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Ethan X. Fang, Junwei Lu, Lan Wang, Yi Han, Zebin Wang","submitted_at":"2024-12-07T02:34:30Z","abstract_excerpt":"We consider the inference for the ranking of large language models (LLMs). Alignment arises as a significant challenge to mitigate hallucinations in the use of LLMs. Ranking LLMs has proven to be an effective tool to improve alignment based on the best-of-$N$ policy. In this paper, we propose a new inferential framework for hypothesis testing among the ranking for language models. Our framework is based on a nonparametric contextual ranking framework designed to assess large language models' domain-specific expertise, leveraging nonparametric scoring methods to account for their sensitivity to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05506","kind":"arxiv","version":2},"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/2412.05506/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":"2412.05506","created_at":"2026-07-05T10:12:02.479473+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.05506v2","created_at":"2026-07-05T10:12:02.479473+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05506","created_at":"2026-07-05T10:12:02.479473+00:00"},{"alias_kind":"pith_short_12","alias_value":"NTW5TVHGLCCE","created_at":"2026-07-05T10:12:02.479473+00:00"},{"alias_kind":"pith_short_16","alias_value":"NTW5TVHGLCCEIZNF","created_at":"2026-07-05T10:12:02.479473+00:00"},{"alias_kind":"pith_short_8","alias_value":"NTW5TVHG","created_at":"2026-07-05T10:12:02.479473+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08679","citing_title":"Rank Intervals for Leaderboards: A Hierarchical Framework for Model Evaluation","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15761","citing_title":"A Unified Perturbation Framework for Analyzing Leaderboard Stability and Manipulation","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02507","citing_title":"Reinforcement Learning from Human Feedback: A Statistical Perspective","ref_index":80,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NTW5TVHGLCCEIZNFZ2C4IGFAMK","json":"https://pith.science/pith/NTW5TVHGLCCEIZNFZ2C4IGFAMK.json","graph_json":"https://pith.science/api/pith-number/NTW5TVHGLCCEIZNFZ2C4IGFAMK/graph.json","events_json":"https://pith.science/api/pith-number/NTW5TVHGLCCEIZNFZ2C4IGFAMK/events.json","paper":"https://pith.science/paper/NTW5TVHG"},"agent_actions":{"view_html":"https://pith.science/pith/NTW5TVHGLCCEIZNFZ2C4IGFAMK","download_json":"https://pith.science/pith/NTW5TVHGLCCEIZNFZ2C4IGFAMK.json","view_paper":"https://pith.science/paper/NTW5TVHG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.05506&json=true","fetch_graph":"https://pith.science/api/pith-number/NTW5TVHGLCCEIZNFZ2C4IGFAMK/graph.json","fetch_events":"https://pith.science/api/pith-number/NTW5TVHGLCCEIZNFZ2C4IGFAMK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NTW5TVHGLCCEIZNFZ2C4IGFAMK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NTW5TVHGLCCEIZNFZ2C4IGFAMK/action/storage_attestation","attest_author":"https://pith.science/pith/NTW5TVHGLCCEIZNFZ2C4IGFAMK/action/author_attestation","sign_citation":"https://pith.science/pith/NTW5TVHGLCCEIZNFZ2C4IGFAMK/action/citation_signature","submit_replication":"https://pith.science/pith/NTW5TVHGLCCEIZNFZ2C4IGFAMK/action/replication_record"}},"created_at":"2026-07-05T10:12:02.479473+00:00","updated_at":"2026-07-05T10:12:02.479473+00:00"}