{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BV2ATAP7DQFSVKRRM3M5LCGNDF","short_pith_number":"pith:BV2ATAP7","schema_version":"1.0","canonical_sha256":"0d740981ff1c0b2aaa3166d9d588cd196756e5dd28cabab4dce3ece9088a25d3","source":{"kind":"arxiv","id":"2602.13110","version":3},"attestation_state":"computed","paper":{"title":"SCOPE: Selective Conformal Optimized Pairwise LLM Judging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ali Emami, Hassan Sajjad, Sher Badshah","submitted_at":"2026-02-13T17:10:43Z","abstract_excerpt":"Large language models (LLMs) are increasingly used as scalable judges in pairwise evaluation, but they remain prone to miscalibration and biases. We propose SCOPE (Selective Conformal Optimized Pairwise Evaluation), a framework that calibrates an acceptance threshold so that, under exchangeability, the error rate among non-abstained judgments is at most a user-specified level $\\alpha$. To supply SCOPE with a bias-neutral uncertainty signal, we introduce Bidirectional Preference Entropy (BPE), which queries the judge under both response positions and converts the order-averaged preference proba"},"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":"2602.13110","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-13T17:10:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8f96e6f1b5dae498d9a13b51e992758b81d66e586924ed4b4aeeb16a6d52ddbc","abstract_canon_sha256":"1ce0ffdc270c7ac27af98f820888925d76add7fef4926e08653f7fdd8234cb40"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T02:03:35.165379Z","signature_b64":"yglX1+m6y0goucHC7aFnWVCjztvTNeVKxRbpcO2OcaSOMiM1xKDyfYom5UhdCGJchXlykwb7fX4GALcJz6UNBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d740981ff1c0b2aaa3166d9d588cd196756e5dd28cabab4dce3ece9088a25d3","last_reissued_at":"2026-06-01T02:03:35.164233Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T02:03:35.164233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SCOPE: Selective Conformal Optimized Pairwise LLM Judging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ali Emami, Hassan Sajjad, Sher Badshah","submitted_at":"2026-02-13T17:10:43Z","abstract_excerpt":"Large language models (LLMs) are increasingly used as scalable judges in pairwise evaluation, but they remain prone to miscalibration and biases. We propose SCOPE (Selective Conformal Optimized Pairwise Evaluation), a framework that calibrates an acceptance threshold so that, under exchangeability, the error rate among non-abstained judgments is at most a user-specified level $\\alpha$. To supply SCOPE with a bias-neutral uncertainty signal, we introduce Bidirectional Preference Entropy (BPE), which queries the judge under both response positions and converts the order-averaged preference proba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.13110","kind":"arxiv","version":3},"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/2602.13110/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":"2602.13110","created_at":"2026-06-01T02:03:35.164407+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.13110v3","created_at":"2026-06-01T02:03:35.164407+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.13110","created_at":"2026-06-01T02:03:35.164407+00:00"},{"alias_kind":"pith_short_12","alias_value":"BV2ATAP7DQFS","created_at":"2026-06-01T02:03:35.164407+00:00"},{"alias_kind":"pith_short_16","alias_value":"BV2ATAP7DQFSVKRR","created_at":"2026-06-01T02:03:35.164407+00:00"},{"alias_kind":"pith_short_8","alias_value":"BV2ATAP7","created_at":"2026-06-01T02:03:35.164407+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/BV2ATAP7DQFSVKRRM3M5LCGNDF","json":"https://pith.science/pith/BV2ATAP7DQFSVKRRM3M5LCGNDF.json","graph_json":"https://pith.science/api/pith-number/BV2ATAP7DQFSVKRRM3M5LCGNDF/graph.json","events_json":"https://pith.science/api/pith-number/BV2ATAP7DQFSVKRRM3M5LCGNDF/events.json","paper":"https://pith.science/paper/BV2ATAP7"},"agent_actions":{"view_html":"https://pith.science/pith/BV2ATAP7DQFSVKRRM3M5LCGNDF","download_json":"https://pith.science/pith/BV2ATAP7DQFSVKRRM3M5LCGNDF.json","view_paper":"https://pith.science/paper/BV2ATAP7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.13110&json=true","fetch_graph":"https://pith.science/api/pith-number/BV2ATAP7DQFSVKRRM3M5LCGNDF/graph.json","fetch_events":"https://pith.science/api/pith-number/BV2ATAP7DQFSVKRRM3M5LCGNDF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BV2ATAP7DQFSVKRRM3M5LCGNDF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BV2ATAP7DQFSVKRRM3M5LCGNDF/action/storage_attestation","attest_author":"https://pith.science/pith/BV2ATAP7DQFSVKRRM3M5LCGNDF/action/author_attestation","sign_citation":"https://pith.science/pith/BV2ATAP7DQFSVKRRM3M5LCGNDF/action/citation_signature","submit_replication":"https://pith.science/pith/BV2ATAP7DQFSVKRRM3M5LCGNDF/action/replication_record"}},"created_at":"2026-06-01T02:03:35.164407+00:00","updated_at":"2026-06-01T02:03:35.164407+00:00"}