{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DEZQOJD4K27AFR7SXDYRKTZ3IG","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":"8148bd0e312c51040f1dcbb2c9879695f663eb2b46a24b32b94b153fb6b0a7c3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-19T18:56:08Z","title_canon_sha256":"93d4c79516c60d4ada2da6971f4850fe826cef3c604419e22bc899d573144b77"},"schema_version":"1.0","source":{"id":"2601.13300","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.13300","created_at":"2026-06-26T01:15:48Z"},{"alias_kind":"arxiv_version","alias_value":"2601.13300v2","created_at":"2026-06-26T01:15:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.13300","created_at":"2026-06-26T01:15:48Z"},{"alias_kind":"pith_short_12","alias_value":"DEZQOJD4K27A","created_at":"2026-06-26T01:15:48Z"},{"alias_kind":"pith_short_16","alias_value":"DEZQOJD4K27AFR7S","created_at":"2026-06-26T01:15:48Z"},{"alias_kind":"pith_short_8","alias_value":"DEZQOJD4","created_at":"2026-06-26T01:15:48Z"}],"graph_snapshots":[{"event_id":"sha256:5a0dcfce039be15afec89502181f27fc81ee2a40639308bca32b2cf587a71b7c","target":"graph","created_at":"2026-06-26T01:15:48Z","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/2601.13300/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Benchmarking large language models (LLMs) is critical for understanding their capabilities, limitations, and robustness. In addition to interface artifacts, prior studies have shown that LLM decisions can be influenced by directive signals such as social cues, framing, and instructions. In this work, we introduce option injection, a benchmarking approach that augments the multiple-choice question answering (MCQA) interface with an additional option containing a misleading directive, leveraging standardized choice structure and scalable evaluation. We construct OI-Bench, a benchmark of 3,000 qu","authors_text":"An-Zi Yen, Yow-Fu Liou, Yu-Chien Tang, Yu-Hsiang Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-19T18:56:08Z","title":"OI-Bench: An Option Injection Benchmark for Evaluating LLM Susceptibility to Directive Interference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.13300","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":"sha256:225a598b95461e7bc9fa1442276669145f158044612c51bb613ae9bdfd637096","target":"record","created_at":"2026-06-26T01:15:48Z","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":"8148bd0e312c51040f1dcbb2c9879695f663eb2b46a24b32b94b153fb6b0a7c3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-19T18:56:08Z","title_canon_sha256":"93d4c79516c60d4ada2da6971f4850fe826cef3c604419e22bc899d573144b77"},"schema_version":"1.0","source":{"id":"2601.13300","kind":"arxiv","version":2}},"canonical_sha256":"193307247c56be02c7f2b8f1154f3b41ad3ddd0bf3fdafa7028d2135e15963aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"193307247c56be02c7f2b8f1154f3b41ad3ddd0bf3fdafa7028d2135e15963aa","first_computed_at":"2026-06-26T01:15:48.533171Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-26T01:15:48.533171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zcZGfFSR459Iwus30lkhdCubQwOrNrXF3G7NaSVX+oQvCTMvDDpgDP+x7Q05Dr37Efo6KvF0g0rSX5lPvBvXBA==","signature_status":"signed_v1","signed_at":"2026-06-26T01:15:48.533676Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.13300","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:225a598b95461e7bc9fa1442276669145f158044612c51bb613ae9bdfd637096","sha256:5a0dcfce039be15afec89502181f27fc81ee2a40639308bca32b2cf587a71b7c"],"state_sha256":"b9e16f68d97d16edbe39432e6202866f4d502e8b8e912b6f5b57004a88214190"}