{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XSPRTKSIRXEWQ7TCQYHVWLZC4O","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":"89d60ff9b4d7fa3b6240eb08a92b846ecbf3bcc383c71b0287c01803599a5480","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T19:38:58Z","title_canon_sha256":"a94957d4f3559c4986bfd8121d4c50b1de9ce3c2856934c5059ebf827e683d46"},"schema_version":"1.0","source":{"id":"2402.12483","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.12483","created_at":"2026-07-05T08:28:59Z"},{"alias_kind":"arxiv_version","alias_value":"2402.12483v2","created_at":"2026-07-05T08:28:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12483","created_at":"2026-07-05T08:28:59Z"},{"alias_kind":"pith_short_12","alias_value":"XSPRTKSIRXEW","created_at":"2026-07-05T08:28:59Z"},{"alias_kind":"pith_short_16","alias_value":"XSPRTKSIRXEWQ7TC","created_at":"2026-07-05T08:28:59Z"},{"alias_kind":"pith_short_8","alias_value":"XSPRTKSI","created_at":"2026-07-05T08:28:59Z"}],"graph_snapshots":[{"event_id":"sha256:14882b7d30a3c8011a1848acb0b3c8701b014b4b3dda4822bd3a819173b00ed1","target":"graph","created_at":"2026-07-05T08:28:59Z","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/2402.12483/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multiple-choice question answering (MCQA) is often used to evaluate large language models (LLMs). To see if MCQA assesses LLMs as intended, we probe if LLMs can perform MCQA with choices-only prompts, where models must select the correct answer only from the choices. In three MCQA datasets and four LLMs, this prompt bests a majority baseline in 11/12 cases, with up to 0.33 accuracy gain. To help explain this behavior, we conduct an in-depth, black-box analysis on memorization, choice dynamics, and question inference. Our key findings are threefold. First, we find no evidence that the choices-o","authors_text":"Abhilasha Ravichander, Nishant Balepur, Rachel Rudinger","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T19:38:58Z","title":"Artifacts or Abduction: How Do LLMs Answer Multiple-Choice Questions Without the Question?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12483","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":"sha256:84e00fb665b47fd288202a62d857fcbe12b034fd36a896c39b5f85fe08d33046","target":"record","created_at":"2026-07-05T08:28:59Z","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":"89d60ff9b4d7fa3b6240eb08a92b846ecbf3bcc383c71b0287c01803599a5480","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T19:38:58Z","title_canon_sha256":"a94957d4f3559c4986bfd8121d4c50b1de9ce3c2856934c5059ebf827e683d46"},"schema_version":"1.0","source":{"id":"2402.12483","kind":"arxiv","version":2}},"canonical_sha256":"bc9f19aa488dc9687e62860f5b2f22e380fd78fe815e3774e48fa8e09dbc04d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc9f19aa488dc9687e62860f5b2f22e380fd78fe815e3774e48fa8e09dbc04d8","first_computed_at":"2026-07-05T08:28:59.760025Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:59.760025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"txNI/f20AyVpi+nVpc3iA5zK0p5EoVgs68B+Y0yJWqIw/N2WJ5PPbKxAIF4V7P01Wkq1qvvXYxlRx8+PRGtPAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:59.760514Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.12483","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84e00fb665b47fd288202a62d857fcbe12b034fd36a896c39b5f85fe08d33046","sha256:14882b7d30a3c8011a1848acb0b3c8701b014b4b3dda4822bd3a819173b00ed1"],"state_sha256":"260d8d12a6814c0ce057855ffb6a6cafedf3fec459c6d406b5f7ddfd8d6dd9d3"}