{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PJLR7YHMCEGYLTOBTPWLZXJPIX","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":"fddd75dbb09313db81bd9bba2a6f2ecf1c48b80a939c48c8962114d256f7ce06","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-04T08:13:06Z","title_canon_sha256":"eadac637eb68da13373ae92e4ef824fb8244c10123b8b52d21ad086c275dbe75"},"schema_version":"1.0","source":{"id":"2509.03986","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.03986","created_at":"2026-07-05T12:04:51Z"},{"alias_kind":"arxiv_version","alias_value":"2509.03986v1","created_at":"2026-07-05T12:04:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.03986","created_at":"2026-07-05T12:04:51Z"},{"alias_kind":"pith_short_12","alias_value":"PJLR7YHMCEGY","created_at":"2026-07-05T12:04:51Z"},{"alias_kind":"pith_short_16","alias_value":"PJLR7YHMCEGYLTOB","created_at":"2026-07-05T12:04:51Z"},{"alias_kind":"pith_short_8","alias_value":"PJLR7YHM","created_at":"2026-07-05T12:04:51Z"}],"graph_snapshots":[{"event_id":"sha256:8e5c0a7c582e57323b9149e94f7bcc7e7bb34228e5a980e237bd09163567d30e","target":"graph","created_at":"2026-07-05T12:04:51Z","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/2509.03986/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the success of Large Multimodal Models (LMMs) in recent years, prompt design for LMMs in Multiple-Choice Question Answering (MCQA) remains poorly understood. We show that even minor variations in prompt phrasing and structure can lead to accuracy deviations of up to 15% for certain prompts and models. This variability poses a challenge for transparent and fair LMM evaluation, as models often report their best-case performance using carefully selected prompts. To address this, we introduce Promptception, a systematic framework for evaluating prompt sensitivity in LMMs. It consists of 61","authors_text":"Mohamed Insaf Ismithdeen, Muhammad Uzair Khattak, Salman Khan","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-04T08:13:06Z","title":"Promptception: How Sensitive Are Large Multimodal Models to Prompts?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.03986","kind":"arxiv","version":1},"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":"sha256:748238c608b42772af39efb98f351989f3550a9abc476d4b6af6ef2229353c1f","target":"record","created_at":"2026-07-05T12:04:51Z","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":"fddd75dbb09313db81bd9bba2a6f2ecf1c48b80a939c48c8962114d256f7ce06","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-04T08:13:06Z","title_canon_sha256":"eadac637eb68da13373ae92e4ef824fb8244c10123b8b52d21ad086c275dbe75"},"schema_version":"1.0","source":{"id":"2509.03986","kind":"arxiv","version":1}},"canonical_sha256":"7a571fe0ec110d85cdc19becbcdd2f45d2b883abc82ebbbaecbc6fa9f617ac21","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7a571fe0ec110d85cdc19becbcdd2f45d2b883abc82ebbbaecbc6fa9f617ac21","first_computed_at":"2026-07-05T12:04:51.199610Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:04:51.199610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+8dlO0M7B7J2m4HMCWC1UvvdtroqOXHQNfAPlbWHWbMj2q4IKoNfW66i+YS3Ni3h+6gD3DH0p4CDpLYohylHDw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:04:51.200121Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.03986","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:748238c608b42772af39efb98f351989f3550a9abc476d4b6af6ef2229353c1f","sha256:8e5c0a7c582e57323b9149e94f7bcc7e7bb34228e5a980e237bd09163567d30e"],"state_sha256":"5977ce56a367c2f305bdfe6e811f5aa2157a123926b16337f75a79798dc209b4"}