{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:L4JFOJRUVYBD2MWM2CB43VKT44","short_pith_number":"pith:L4JFOJRU","schema_version":"1.0","canonical_sha256":"5f12572634ae023d32ccd083cdd553e704ec28c470019039f6df1765a04fb8ca","source":{"kind":"arxiv","id":"2408.14594","version":1},"attestation_state":"computed","paper":{"title":"MMR: Evaluating Reading Ability of Large Multimodal Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changyou Chen, Jian Chen, Jiuxiang Gu, Ruiyi Zhang, Ryan Rossi, Yufan Zhou","submitted_at":"2024-08-26T19:26:50Z","abstract_excerpt":"Large multimodal models (LMMs) have demonstrated impressive capabilities in understanding various types of image, including text-rich images. Most existing text-rich image benchmarks are simple extraction-based question answering, and many LMMs now easily achieve high scores. This means that current benchmarks fail to accurately reflect performance of different models, and a natural idea is to build a new benchmark to evaluate their complex reasoning and spatial understanding abilities. In this work, we propose the Multi-Modal Reading (MMR) benchmark in 11 diverse tasks to evaluate LMMs for te"},"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":"2408.14594","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-26T19:26:50Z","cross_cats_sorted":[],"title_canon_sha256":"bae1f701f0000dd598afa01f642250214ca9160a58ed2342dd283249e6db1297","abstract_canon_sha256":"11f05f2e2254ffb7b13b8b77c8f8ed241a8446cc48ed3ab04b8c859d01ca8aa4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:59:36.069820Z","signature_b64":"wwBiwk0BYwcQj4205/1OF2qgAbGAoBa9WAWPPcb8fp7cTJ6VDQfisUf8OtcZZWZXTBjbpPu2AQSzaQs5oXYUAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f12572634ae023d32ccd083cdd553e704ec28c470019039f6df1765a04fb8ca","last_reissued_at":"2026-07-05T08:59:36.069309Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:59:36.069309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMR: Evaluating Reading Ability of Large Multimodal Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changyou Chen, Jian Chen, Jiuxiang Gu, Ruiyi Zhang, Ryan Rossi, Yufan Zhou","submitted_at":"2024-08-26T19:26:50Z","abstract_excerpt":"Large multimodal models (LMMs) have demonstrated impressive capabilities in understanding various types of image, including text-rich images. Most existing text-rich image benchmarks are simple extraction-based question answering, and many LMMs now easily achieve high scores. This means that current benchmarks fail to accurately reflect performance of different models, and a natural idea is to build a new benchmark to evaluate their complex reasoning and spatial understanding abilities. In this work, we propose the Multi-Modal Reading (MMR) benchmark in 11 diverse tasks to evaluate LMMs for te"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.14594","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/2408.14594/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":"2408.14594","created_at":"2026-07-05T08:59:36.069377+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.14594v1","created_at":"2026-07-05T08:59:36.069377+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14594","created_at":"2026-07-05T08:59:36.069377+00:00"},{"alias_kind":"pith_short_12","alias_value":"L4JFOJRUVYBD","created_at":"2026-07-05T08:59:36.069377+00:00"},{"alias_kind":"pith_short_16","alias_value":"L4JFOJRUVYBD2MWM","created_at":"2026-07-05T08:59:36.069377+00:00"},{"alias_kind":"pith_short_8","alias_value":"L4JFOJRU","created_at":"2026-07-05T08:59:36.069377+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.07493","citing_title":"VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L4JFOJRUVYBD2MWM2CB43VKT44","json":"https://pith.science/pith/L4JFOJRUVYBD2MWM2CB43VKT44.json","graph_json":"https://pith.science/api/pith-number/L4JFOJRUVYBD2MWM2CB43VKT44/graph.json","events_json":"https://pith.science/api/pith-number/L4JFOJRUVYBD2MWM2CB43VKT44/events.json","paper":"https://pith.science/paper/L4JFOJRU"},"agent_actions":{"view_html":"https://pith.science/pith/L4JFOJRUVYBD2MWM2CB43VKT44","download_json":"https://pith.science/pith/L4JFOJRUVYBD2MWM2CB43VKT44.json","view_paper":"https://pith.science/paper/L4JFOJRU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.14594&json=true","fetch_graph":"https://pith.science/api/pith-number/L4JFOJRUVYBD2MWM2CB43VKT44/graph.json","fetch_events":"https://pith.science/api/pith-number/L4JFOJRUVYBD2MWM2CB43VKT44/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L4JFOJRUVYBD2MWM2CB43VKT44/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L4JFOJRUVYBD2MWM2CB43VKT44/action/storage_attestation","attest_author":"https://pith.science/pith/L4JFOJRUVYBD2MWM2CB43VKT44/action/author_attestation","sign_citation":"https://pith.science/pith/L4JFOJRUVYBD2MWM2CB43VKT44/action/citation_signature","submit_replication":"https://pith.science/pith/L4JFOJRUVYBD2MWM2CB43VKT44/action/replication_record"}},"created_at":"2026-07-05T08:59:36.069377+00:00","updated_at":"2026-07-05T08:59:36.069377+00:00"}