{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AQPPTHZNGGXSLLCA743YFUHNIR","short_pith_number":"pith:AQPPTHZN","schema_version":"1.0","canonical_sha256":"041ef99f2d31af25ac40ff3782d0ed4475806a5f7e07cb9d2e8169fb764c8cd8","source":{"kind":"arxiv","id":"2606.26348","version":1},"attestation_state":"computed","paper":{"title":"What We are Missing in Multimodal LLM Evaluation?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Po-han Li, Sandeep Chinchali, Shenghui Chen, Ufuk Topcu","submitted_at":"2026-06-24T19:40:53Z","abstract_excerpt":"Multimodal large language models (MLLMs) can process diverse inputs, e.g., text, images, audio, and video, and generate textual responses. While their capabilities have advanced rapidly, evaluation of such models has not kept pace. Most existing evaluation benchmarks are limited to isolated tasks and reveal little about whether a model integrates information across modalities. We examine current means for evaluating MLLMs and review the existing benchmark taxonomy to identify gaps, including temporal-spatial coherence, physical world understanding, multimodal consistency, and selective attenti"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.26348","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-24T19:40:53Z","cross_cats_sorted":[],"title_canon_sha256":"86b30553bfb4482b8f7b48f430cc0c8c462835aca627429dafb3812fea9632a3","abstract_canon_sha256":"817ffc30a5381db52fae2fdedbd62ff5abd1a5ec3f3a2ff1d11ef723946bfc9c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T00:15:37.485542Z","signature_b64":"WfzBinEB3zrhmGelyiIcB/VCsIivjrYuykO4fS86AsUfZQFsM/+nu2qnwd/F9fPU5mdoC+ErjLf2VGf0OQNHCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"041ef99f2d31af25ac40ff3782d0ed4475806a5f7e07cb9d2e8169fb764c8cd8","last_reissued_at":"2026-06-26T00:15:37.484986Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T00:15:37.484986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What We are Missing in Multimodal LLM Evaluation?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Po-han Li, Sandeep Chinchali, Shenghui Chen, Ufuk Topcu","submitted_at":"2026-06-24T19:40:53Z","abstract_excerpt":"Multimodal large language models (MLLMs) can process diverse inputs, e.g., text, images, audio, and video, and generate textual responses. While their capabilities have advanced rapidly, evaluation of such models has not kept pace. Most existing evaluation benchmarks are limited to isolated tasks and reveal little about whether a model integrates information across modalities. We examine current means for evaluating MLLMs and review the existing benchmark taxonomy to identify gaps, including temporal-spatial coherence, physical world understanding, multimodal consistency, and selective attenti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26348","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.26348/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.26348","created_at":"2026-06-26T00:15:37.485059+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.26348v1","created_at":"2026-06-26T00:15:37.485059+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26348","created_at":"2026-06-26T00:15:37.485059+00:00"},{"alias_kind":"pith_short_12","alias_value":"AQPPTHZNGGXS","created_at":"2026-06-26T00:15:37.485059+00:00"},{"alias_kind":"pith_short_16","alias_value":"AQPPTHZNGGXSLLCA","created_at":"2026-06-26T00:15:37.485059+00:00"},{"alias_kind":"pith_short_8","alias_value":"AQPPTHZN","created_at":"2026-06-26T00:15:37.485059+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AQPPTHZNGGXSLLCA743YFUHNIR","json":"https://pith.science/pith/AQPPTHZNGGXSLLCA743YFUHNIR.json","graph_json":"https://pith.science/api/pith-number/AQPPTHZNGGXSLLCA743YFUHNIR/graph.json","events_json":"https://pith.science/api/pith-number/AQPPTHZNGGXSLLCA743YFUHNIR/events.json","paper":"https://pith.science/paper/AQPPTHZN"},"agent_actions":{"view_html":"https://pith.science/pith/AQPPTHZNGGXSLLCA743YFUHNIR","download_json":"https://pith.science/pith/AQPPTHZNGGXSLLCA743YFUHNIR.json","view_paper":"https://pith.science/paper/AQPPTHZN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.26348&json=true","fetch_graph":"https://pith.science/api/pith-number/AQPPTHZNGGXSLLCA743YFUHNIR/graph.json","fetch_events":"https://pith.science/api/pith-number/AQPPTHZNGGXSLLCA743YFUHNIR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AQPPTHZNGGXSLLCA743YFUHNIR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AQPPTHZNGGXSLLCA743YFUHNIR/action/storage_attestation","attest_author":"https://pith.science/pith/AQPPTHZNGGXSLLCA743YFUHNIR/action/author_attestation","sign_citation":"https://pith.science/pith/AQPPTHZNGGXSLLCA743YFUHNIR/action/citation_signature","submit_replication":"https://pith.science/pith/AQPPTHZNGGXSLLCA743YFUHNIR/action/replication_record"}},"created_at":"2026-06-26T00:15:37.485059+00:00","updated_at":"2026-06-26T00:15:37.485059+00:00"}