{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OVVJNLFFWX6MU5B3QWJQMUUOD7","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":"8e60131523b87061752ebc334e0007629675188daec45cb5cbfa686c8d7e6451","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-01T17:53:35Z","title_canon_sha256":"784146118c756944401f72de017854405ed04d189f927931d84d9b2f22d4bd40"},"schema_version":"1.0","source":{"id":"2407.01509","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.01509","created_at":"2026-07-05T10:35:34Z"},{"alias_kind":"arxiv_version","alias_value":"2407.01509v5","created_at":"2026-07-05T10:35:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01509","created_at":"2026-07-05T10:35:34Z"},{"alias_kind":"pith_short_12","alias_value":"OVVJNLFFWX6M","created_at":"2026-07-05T10:35:34Z"},{"alias_kind":"pith_short_16","alias_value":"OVVJNLFFWX6MU5B3","created_at":"2026-07-05T10:35:34Z"},{"alias_kind":"pith_short_8","alias_value":"OVVJNLFF","created_at":"2026-07-05T10:35:34Z"}],"graph_snapshots":[{"event_id":"sha256:0a268da916f3380686a0ec82b6311d0088b25954528f8d58772f04c3744e0ec3","target":"graph","created_at":"2026-07-05T10:35:34Z","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/2407.01509/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce MIA-Bench, a new benchmark designed to evaluate multimodal large language models (MLLMs) on their ability to strictly adhere to complex instructions. Our benchmark comprises a diverse set of 400 image-prompt pairs, each crafted to challenge the models' compliance with layered instructions in generating accurate responses that satisfy specific requested patterns. Evaluation results from a wide array of state-of-the-art MLLMs reveal significant variations in performance, highlighting areas for improvement in instruction fidelity. Additionally, we create extra training data and explo","authors_text":"Hanrong Ye, Jean-Philippe Fauconnier, Peter Grasch, Yinfei Yang, Yusu Qian, Zhe Gan","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-01T17:53:35Z","title":"MIA-Bench: Towards Better Instruction Following Evaluation of Multimodal LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01509","kind":"arxiv","version":5},"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":"sha256:023e52459066fa391b7479dadbf1181dc3b0b5e95ecdc3332e508827b5cb3dba","target":"record","created_at":"2026-07-05T10:35:34Z","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":"8e60131523b87061752ebc334e0007629675188daec45cb5cbfa686c8d7e6451","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-01T17:53:35Z","title_canon_sha256":"784146118c756944401f72de017854405ed04d189f927931d84d9b2f22d4bd40"},"schema_version":"1.0","source":{"id":"2407.01509","kind":"arxiv","version":5}},"canonical_sha256":"756a96aca5b5fcca743b859306528e1fce9b6a51ab334ce045b3b37d48f6008b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"756a96aca5b5fcca743b859306528e1fce9b6a51ab334ce045b3b37d48f6008b","first_computed_at":"2026-07-05T10:35:34.149659Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:35:34.149659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iO0GxhVr9S5ARINhZh2fG48+PrdU4fDtkrlbnRgRFBMxXUh3rlY0YHfcPAMT0GBGW4OTuviLFT84Bc79hqa3Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:35:34.150628Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.01509","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:023e52459066fa391b7479dadbf1181dc3b0b5e95ecdc3332e508827b5cb3dba","sha256:0a268da916f3380686a0ec82b6311d0088b25954528f8d58772f04c3744e0ec3"],"state_sha256":"0c737652fbe4dc8fae96812375a0d30a58b7d734efa68a69dabab83b1c30f573"}