{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PNVWP2QJTWMX23D3D7O42NTO4I","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ecc9aa401dd9878c1e1f5c34485c7725816187d5a701ab95eaab5012e7c6d68b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-24T08:28:17Z","title_canon_sha256":"bf993db41ac404c7b016d805b709d4c8d394edfce25366933a819099fd8693f6"},"schema_version":"1.0","source":{"id":"2507.18182","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.18182","created_at":"2026-07-05T11:48:06Z"},{"alias_kind":"arxiv_version","alias_value":"2507.18182v2","created_at":"2026-07-05T11:48:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18182","created_at":"2026-07-05T11:48:06Z"},{"alias_kind":"pith_short_12","alias_value":"PNVWP2QJTWMX","created_at":"2026-07-05T11:48:06Z"},{"alias_kind":"pith_short_16","alias_value":"PNVWP2QJTWMX23D3","created_at":"2026-07-05T11:48:06Z"},{"alias_kind":"pith_short_8","alias_value":"PNVWP2QJ","created_at":"2026-07-05T11:48:06Z"}],"graph_snapshots":[{"event_id":"sha256:7a4e3fc42c81a317e1d0904ac195ff1c80dbf6392216d03d2ee81642a09c58d9","target":"graph","created_at":"2026-07-05T11:48:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.18182/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) can achieve inflated scores on multiple-choice tasks by exploiting inherent biases in option positions or labels, rather than demonstrating genuine understanding. This study introduces SCOPE, an evaluation framework designed to measure and mitigate such selection bias in a dataset-independent manner. By repeatedly invoking a null prompt that lacks semantic content, SCOPE estimates each model's unique position-bias distribution. It then redistributes the answer slot according to the inverse-bias distribution, thereby equalizing the lucky-rate, the probability of sel","authors_text":"Dongseok Kim, Taegkeun Whangbo, Wonjun Jeong","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-24T08:28:17Z","title":"SCOPE: Stochastic and Counterbiased Option Placement for Evaluating Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18182","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1235be17c7ab791be4bc1e93d8430c8dc25cb573f07f3b0b797e3d5f84eb00be","target":"record","created_at":"2026-07-05T11:48:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ecc9aa401dd9878c1e1f5c34485c7725816187d5a701ab95eaab5012e7c6d68b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-24T08:28:17Z","title_canon_sha256":"bf993db41ac404c7b016d805b709d4c8d394edfce25366933a819099fd8693f6"},"schema_version":"1.0","source":{"id":"2507.18182","kind":"arxiv","version":2}},"canonical_sha256":"7b6b67ea099d997d6c7b1fddcd366ee236852c7312da7983b0629a857740c514","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b6b67ea099d997d6c7b1fddcd366ee236852c7312da7983b0629a857740c514","first_computed_at":"2026-07-05T11:48:06.006762Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:48:06.006762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sWZksdZoKoveZFyvLGg/upI4xH54RJarzoreJ/vZ3xoMo1MuA4TDOeCpKhCqvZFANQeBsOcMZCBr7o7xTZVJCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:48:06.007274Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.18182","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1235be17c7ab791be4bc1e93d8430c8dc25cb573f07f3b0b797e3d5f84eb00be","sha256:7a4e3fc42c81a317e1d0904ac195ff1c80dbf6392216d03d2ee81642a09c58d9"],"state_sha256":"709b926fd350799781845a593d5106feb1410eff159d859c9a902f2d0ea0eb01"}