{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:B7CRNILAFRK2NV564PJ2SA6DXS","short_pith_number":"pith:B7CRNILA","schema_version":"1.0","canonical_sha256":"0fc516a1602c55a6d7bee3d3a903c3bc84773a5fe95e1ba38966d46651c89579","source":{"kind":"arxiv","id":"2607.02104","version":1},"attestation_state":"computed","paper":{"title":"Ask the Right Comparison:Bias-Aware Bayesian Active Top-$k$ Ranking with LLM Judges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Delu Zeng, Jian Xu, John Paisley, Qibin Zhao","submitted_at":"2026-07-02T12:39:30Z","abstract_excerpt":"Large language models (LLMs) are increasingly used as cheap, scalable judges that compare candidate outputs pairwise -- to rank responses, select models, or triage papers. Yet LLM judges are both noisy and systematically biased: they favor verbose or well-formatted answers and exhibit position effects, so simply aggregating their votes recovers a ranking of presentation, not of true quality. We study the practical goal of identifying the \\topk{} items under a fixed comparison budget, and make two contributions. First, we cast judging as Bayesian inference over latent quality with explicit, jud"},"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":"2607.02104","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-02T12:39:30Z","cross_cats_sorted":[],"title_canon_sha256":"e38e40a853229a0dc57ac347e1408b102ce84ba5510487d710d4c984d9e2ea33","abstract_canon_sha256":"5b971a5be58b9d7feb2223a63091f9bc3c4e26e2f6e1c5277cbb24e68cfa6c54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:42.360040Z","signature_b64":"MvHB+ZxMfSvN36UK7jWGGHi3l/8RnLBH/PnyfePAAOCvIXTFSDQGJ5CLjJPNp0p6AflNF3z3hwzAiw/R14bzCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fc516a1602c55a6d7bee3d3a903c3bc84773a5fe95e1ba38966d46651c89579","last_reissued_at":"2026-07-03T01:17:42.359640Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:42.359640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ask the Right Comparison:Bias-Aware Bayesian Active Top-$k$ Ranking with LLM Judges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Delu Zeng, Jian Xu, John Paisley, Qibin Zhao","submitted_at":"2026-07-02T12:39:30Z","abstract_excerpt":"Large language models (LLMs) are increasingly used as cheap, scalable judges that compare candidate outputs pairwise -- to rank responses, select models, or triage papers. Yet LLM judges are both noisy and systematically biased: they favor verbose or well-formatted answers and exhibit position effects, so simply aggregating their votes recovers a ranking of presentation, not of true quality. We study the practical goal of identifying the \\topk{} items under a fixed comparison budget, and make two contributions. First, we cast judging as Bayesian inference over latent quality with explicit, jud"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02104","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/2607.02104/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":"2607.02104","created_at":"2026-07-03T01:17:42.359702+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.02104v1","created_at":"2026-07-03T01:17:42.359702+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02104","created_at":"2026-07-03T01:17:42.359702+00:00"},{"alias_kind":"pith_short_12","alias_value":"B7CRNILAFRK2","created_at":"2026-07-03T01:17:42.359702+00:00"},{"alias_kind":"pith_short_16","alias_value":"B7CRNILAFRK2NV56","created_at":"2026-07-03T01:17:42.359702+00:00"},{"alias_kind":"pith_short_8","alias_value":"B7CRNILA","created_at":"2026-07-03T01:17:42.359702+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/B7CRNILAFRK2NV564PJ2SA6DXS","json":"https://pith.science/pith/B7CRNILAFRK2NV564PJ2SA6DXS.json","graph_json":"https://pith.science/api/pith-number/B7CRNILAFRK2NV564PJ2SA6DXS/graph.json","events_json":"https://pith.science/api/pith-number/B7CRNILAFRK2NV564PJ2SA6DXS/events.json","paper":"https://pith.science/paper/B7CRNILA"},"agent_actions":{"view_html":"https://pith.science/pith/B7CRNILAFRK2NV564PJ2SA6DXS","download_json":"https://pith.science/pith/B7CRNILAFRK2NV564PJ2SA6DXS.json","view_paper":"https://pith.science/paper/B7CRNILA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.02104&json=true","fetch_graph":"https://pith.science/api/pith-number/B7CRNILAFRK2NV564PJ2SA6DXS/graph.json","fetch_events":"https://pith.science/api/pith-number/B7CRNILAFRK2NV564PJ2SA6DXS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B7CRNILAFRK2NV564PJ2SA6DXS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B7CRNILAFRK2NV564PJ2SA6DXS/action/storage_attestation","attest_author":"https://pith.science/pith/B7CRNILAFRK2NV564PJ2SA6DXS/action/author_attestation","sign_citation":"https://pith.science/pith/B7CRNILAFRK2NV564PJ2SA6DXS/action/citation_signature","submit_replication":"https://pith.science/pith/B7CRNILAFRK2NV564PJ2SA6DXS/action/replication_record"}},"created_at":"2026-07-03T01:17:42.359702+00:00","updated_at":"2026-07-03T01:17:42.359702+00:00"}