{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XYYEOBJLJUVNNQ2LKMNEGY5HBO","short_pith_number":"pith:XYYEOBJL","schema_version":"1.0","canonical_sha256":"be3047052b4d2ad6c34b531a4363a70bb0abdee0015a6062dd6aff2f936a94c9","source":{"kind":"arxiv","id":"2605.29395","version":1},"attestation_state":"computed","paper":{"title":"Low Rank for Rank: Uncertainty-Aware Task-Specific LLM Ranking under Sparse Pairwise Comparisons","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"stat.ME","authors_text":"David Simchi-Levi, Jiachun Li, Will Wei Sun","submitted_at":"2026-05-28T05:44:43Z","abstract_excerpt":"Pairwise human-preference platforms such as Chatbot Arena have become central to large language model (LLM) evaluation, yet reliable task-specific ranking remains challenging. Global leaderboards mask task heterogeneity, while ranking each fine-grained task independently is unstable under sparse, imbalanced comparisons. We propose a low-rank framework for task-specific LLM ranking from sparse pairwise comparisons, modeling the task-by-model ability matrix $\\Theta^\\star \\in \\mathbb{R}^{d_t \\times d_m}$ as low rank so that information is shared across related tasks while task-specific difference"},"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":"2605.29395","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2026-05-28T05:44:43Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"50f0a515284e7aadb81ffca265c4807648ec0cd65b99dcec5087ac3e41ba2705","abstract_canon_sha256":"1ac437431f22e93a477288c30498adb43f39ae0ca79fd66792599a22e5067f67"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:36.840428Z","signature_b64":"C6kpRWDUCvs18j+nsqRiEtzwvsaKqZAYFoZ5Mr8pfIM6L4KwIIcxSusbwjLP1FGzdxaiZsRghDFHY/GrTas7AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be3047052b4d2ad6c34b531a4363a70bb0abdee0015a6062dd6aff2f936a94c9","last_reissued_at":"2026-05-29T01:05:36.839620Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:36.839620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Low Rank for Rank: Uncertainty-Aware Task-Specific LLM Ranking under Sparse Pairwise Comparisons","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"stat.ME","authors_text":"David Simchi-Levi, Jiachun Li, Will Wei Sun","submitted_at":"2026-05-28T05:44:43Z","abstract_excerpt":"Pairwise human-preference platforms such as Chatbot Arena have become central to large language model (LLM) evaluation, yet reliable task-specific ranking remains challenging. Global leaderboards mask task heterogeneity, while ranking each fine-grained task independently is unstable under sparse, imbalanced comparisons. We propose a low-rank framework for task-specific LLM ranking from sparse pairwise comparisons, modeling the task-by-model ability matrix $\\Theta^\\star \\in \\mathbb{R}^{d_t \\times d_m}$ as low rank so that information is shared across related tasks while task-specific difference"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29395","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/2605.29395/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":"2605.29395","created_at":"2026-05-29T01:05:36.839761+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29395v1","created_at":"2026-05-29T01:05:36.839761+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29395","created_at":"2026-05-29T01:05:36.839761+00:00"},{"alias_kind":"pith_short_12","alias_value":"XYYEOBJLJUVN","created_at":"2026-05-29T01:05:36.839761+00:00"},{"alias_kind":"pith_short_16","alias_value":"XYYEOBJLJUVNNQ2L","created_at":"2026-05-29T01:05:36.839761+00:00"},{"alias_kind":"pith_short_8","alias_value":"XYYEOBJL","created_at":"2026-05-29T01:05:36.839761+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XYYEOBJLJUVNNQ2LKMNEGY5HBO","json":"https://pith.science/pith/XYYEOBJLJUVNNQ2LKMNEGY5HBO.json","graph_json":"https://pith.science/api/pith-number/XYYEOBJLJUVNNQ2LKMNEGY5HBO/graph.json","events_json":"https://pith.science/api/pith-number/XYYEOBJLJUVNNQ2LKMNEGY5HBO/events.json","paper":"https://pith.science/paper/XYYEOBJL"},"agent_actions":{"view_html":"https://pith.science/pith/XYYEOBJLJUVNNQ2LKMNEGY5HBO","download_json":"https://pith.science/pith/XYYEOBJLJUVNNQ2LKMNEGY5HBO.json","view_paper":"https://pith.science/paper/XYYEOBJL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29395&json=true","fetch_graph":"https://pith.science/api/pith-number/XYYEOBJLJUVNNQ2LKMNEGY5HBO/graph.json","fetch_events":"https://pith.science/api/pith-number/XYYEOBJLJUVNNQ2LKMNEGY5HBO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XYYEOBJLJUVNNQ2LKMNEGY5HBO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XYYEOBJLJUVNNQ2LKMNEGY5HBO/action/storage_attestation","attest_author":"https://pith.science/pith/XYYEOBJLJUVNNQ2LKMNEGY5HBO/action/author_attestation","sign_citation":"https://pith.science/pith/XYYEOBJLJUVNNQ2LKMNEGY5HBO/action/citation_signature","submit_replication":"https://pith.science/pith/XYYEOBJLJUVNNQ2LKMNEGY5HBO/action/replication_record"}},"created_at":"2026-05-29T01:05:36.839761+00:00","updated_at":"2026-05-29T01:05:36.839761+00:00"}