{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Y6C2V5CYAVWDDJNFS7DHQZLSMN","short_pith_number":"pith:Y6C2V5CY","schema_version":"1.0","canonical_sha256":"c785aaf458056c31a5a597c6786572636398b664b0be27ddace31cb301feb61a","source":{"kind":"arxiv","id":"2603.20562","version":3},"attestation_state":"computed","paper":{"title":"Permutation-Consensus Listwise Judging for Robust Factuality Evaluation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"Rerunning listwise factuality prompts over multiple candidate orderings and aggregating the results produces up to 7-point gains over direct judging.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Elsa Fan, Justin Tang, Nathan Huang, Tianyi Huang, Wenqian Chen","submitted_at":"2026-03-20T23:35:14Z","abstract_excerpt":"Large language models (LLMs) are now widely used as judges, yet their decisions can change under presentation choices that should be irrelevant. We study one such source of instability: candidate-order sensitivity in listwise factuality evaluation, where several answers can look similarly polished while differing substantially in hallucination risk. We introduce PCFJudge, an inference-time method that reruns the same factuality-first listwise prompt over multiple orderings of the same candidate set and aggregates the resulting scores, ranks, and uncertainty signals into a single consensus deci"},"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":true},"canonical_record":{"source":{"id":"2603.20562","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-20T23:35:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8d8d32cb18b503d168f265f111f7598b03d48c127137e03d8956c95ae4504a5f","abstract_canon_sha256":"6c6d8cdc9a91a96e54dd7e7019e29a6d11d9294c1c8bc21410f8d5a52ad293fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:10.924658Z","signature_b64":"gKDtxzdDF3C5WkYd68scuw/ZUZrC+6wouQ0yk2BA5diiDqpSjCfy75TnWyolhFANdBSwB2IMv8UzK7x/LG/rCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c785aaf458056c31a5a597c6786572636398b664b0be27ddace31cb301feb61a","last_reissued_at":"2026-05-20T00:02:10.923891Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:10.923891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Permutation-Consensus Listwise Judging for Robust Factuality Evaluation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"Rerunning listwise factuality prompts over multiple candidate orderings and aggregating the results produces up to 7-point gains over direct judging.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Elsa Fan, Justin Tang, Nathan Huang, Tianyi Huang, Wenqian Chen","submitted_at":"2026-03-20T23:35:14Z","abstract_excerpt":"Large language models (LLMs) are now widely used as judges, yet their decisions can change under presentation choices that should be irrelevant. We study one such source of instability: candidate-order sensitivity in listwise factuality evaluation, where several answers can look similarly polished while differing substantially in hallucination risk. We introduce PCFJudge, an inference-time method that reruns the same factuality-first listwise prompt over multiple orderings of the same candidate set and aggregates the resulting scores, ranks, and uncertainty signals into a single consensus deci"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"On RewardBench 2 Factuality, PCFJudge improves over direct judging by up to 7 absolute points.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That order sensitivity is a dominant, fixable source of error in listwise factuality judging and that simple aggregation over permutations does not introduce compensating biases or reduce discriminative power.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"PCFJudge improves direct LLM factuality judging by up to 7 points on RewardBench 2 Factuality by aggregating results over multiple candidate permutations.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Rerunning listwise factuality prompts over multiple candidate orderings and aggregating the results produces up to 7-point gains over direct judging.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c68f66b662db5835cf046036d05e1ddccf3636dfabb6850a40a5f541e1652e11"},"source":{"id":"2603.20562","kind":"arxiv","version":3},"verdict":{"id":"798d4e1b-8339-4951-a6f9-5627e1118dd8","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T07:40:00.308621Z","strongest_claim":"On RewardBench 2 Factuality, PCFJudge improves over direct judging by up to 7 absolute points.","one_line_summary":"PCFJudge improves direct LLM factuality judging by up to 7 points on RewardBench 2 Factuality by aggregating results over multiple candidate permutations.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That order sensitivity is a dominant, fixable source of error in listwise factuality judging and that simple aggregation over permutations does not introduce compensating biases or reduce discriminative power.","pith_extraction_headline":"Rerunning listwise factuality prompts over multiple candidate orderings and aggregating the results produces up to 7-point gains over direct judging."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.20562/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":2,"snapshot_sha256":"18923d2f25a092660d10d8c7010dd1c664130752d6fe7974b1e19df3d06303ab"},"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":"2603.20562","created_at":"2026-05-20T00:02:10.924009+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.20562v3","created_at":"2026-05-20T00:02:10.924009+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.20562","created_at":"2026-05-20T00:02:10.924009+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y6C2V5CYAVWD","created_at":"2026-05-20T00:02:10.924009+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y6C2V5CYAVWDDJNF","created_at":"2026-05-20T00:02:10.924009+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y6C2V5CY","created_at":"2026-05-20T00:02:10.924009+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y6C2V5CYAVWDDJNFS7DHQZLSMN","json":"https://pith.science/pith/Y6C2V5CYAVWDDJNFS7DHQZLSMN.json","graph_json":"https://pith.science/api/pith-number/Y6C2V5CYAVWDDJNFS7DHQZLSMN/graph.json","events_json":"https://pith.science/api/pith-number/Y6C2V5CYAVWDDJNFS7DHQZLSMN/events.json","paper":"https://pith.science/paper/Y6C2V5CY"},"agent_actions":{"view_html":"https://pith.science/pith/Y6C2V5CYAVWDDJNFS7DHQZLSMN","download_json":"https://pith.science/pith/Y6C2V5CYAVWDDJNFS7DHQZLSMN.json","view_paper":"https://pith.science/paper/Y6C2V5CY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.20562&json=true","fetch_graph":"https://pith.science/api/pith-number/Y6C2V5CYAVWDDJNFS7DHQZLSMN/graph.json","fetch_events":"https://pith.science/api/pith-number/Y6C2V5CYAVWDDJNFS7DHQZLSMN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y6C2V5CYAVWDDJNFS7DHQZLSMN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y6C2V5CYAVWDDJNFS7DHQZLSMN/action/storage_attestation","attest_author":"https://pith.science/pith/Y6C2V5CYAVWDDJNFS7DHQZLSMN/action/author_attestation","sign_citation":"https://pith.science/pith/Y6C2V5CYAVWDDJNFS7DHQZLSMN/action/citation_signature","submit_replication":"https://pith.science/pith/Y6C2V5CYAVWDDJNFS7DHQZLSMN/action/replication_record"}},"created_at":"2026-05-20T00:02:10.924009+00:00","updated_at":"2026-05-20T00:02:10.924009+00:00"}