{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:L4JFOJRUVYBD2MWM2CB43VKT44","short_pith_number":"pith:L4JFOJRU","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"},"canonical_sha256":"5f12572634ae023d32ccd083cdd553e704ec28c470019039f6df1765a04fb8ca","source":{"kind":"arxiv","id":"2408.14594","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.14594","created_at":"2026-07-05T08:59:36Z"},{"alias_kind":"arxiv_version","alias_value":"2408.14594v1","created_at":"2026-07-05T08:59:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14594","created_at":"2026-07-05T08:59:36Z"},{"alias_kind":"pith_short_12","alias_value":"L4JFOJRUVYBD","created_at":"2026-07-05T08:59:36Z"},{"alias_kind":"pith_short_16","alias_value":"L4JFOJRUVYBD2MWM","created_at":"2026-07-05T08:59:36Z"},{"alias_kind":"pith_short_8","alias_value":"L4JFOJRU","created_at":"2026-07-05T08:59:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:L4JFOJRUVYBD2MWM2CB43VKT44","target":"record","payload":{"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"},"canonical_sha256":"5f12572634ae023d32ccd083cdd553e704ec28c470019039f6df1765a04fb8ca","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"},"source_kind":"arxiv","source_id":"2408.14594","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:59:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EYOaSkrL2pTC9twBEqxJ9R2nKVuCU4U4L53hD02h0AFryVGbPi6Z0EZzsHdqlOuNpVbZCmTmBr28irKVVJ6TCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:02:52.716079Z"},"content_sha256":"1128ad435e6816dccade73ce045b3982bfb4b57f3d96f1bf663123722b52a513","schema_version":"1.0","event_id":"sha256:1128ad435e6816dccade73ce045b3982bfb4b57f3d96f1bf663123722b52a513"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:L4JFOJRUVYBD2MWM2CB43VKT44","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:59:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F4+XIV/QgUJzGBTorQz3H3fCPgjhJbuHpfrRU4pW+nbFKBAFxxKkXH1DG6cc73iuEr1WkkoMVPaOzfvU2v3RBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:02:52.716738Z"},"content_sha256":"4bb9f921dc4cae764399460eb0ee0cd48e0bb38b37e067b3810538b67048b302","schema_version":"1.0","event_id":"sha256:4bb9f921dc4cae764399460eb0ee0cd48e0bb38b37e067b3810538b67048b302"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L4JFOJRUVYBD2MWM2CB43VKT44/bundle.json","state_url":"https://pith.science/pith/L4JFOJRUVYBD2MWM2CB43VKT44/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L4JFOJRUVYBD2MWM2CB43VKT44/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T16:02:52Z","links":{"resolver":"https://pith.science/pith/L4JFOJRUVYBD2MWM2CB43VKT44","bundle":"https://pith.science/pith/L4JFOJRUVYBD2MWM2CB43VKT44/bundle.json","state":"https://pith.science/pith/L4JFOJRUVYBD2MWM2CB43VKT44/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L4JFOJRUVYBD2MWM2CB43VKT44/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:L4JFOJRUVYBD2MWM2CB43VKT44","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":"11f05f2e2254ffb7b13b8b77c8f8ed241a8446cc48ed3ab04b8c859d01ca8aa4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-26T19:26:50Z","title_canon_sha256":"bae1f701f0000dd598afa01f642250214ca9160a58ed2342dd283249e6db1297"},"schema_version":"1.0","source":{"id":"2408.14594","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.14594","created_at":"2026-07-05T08:59:36Z"},{"alias_kind":"arxiv_version","alias_value":"2408.14594v1","created_at":"2026-07-05T08:59:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14594","created_at":"2026-07-05T08:59:36Z"},{"alias_kind":"pith_short_12","alias_value":"L4JFOJRUVYBD","created_at":"2026-07-05T08:59:36Z"},{"alias_kind":"pith_short_16","alias_value":"L4JFOJRUVYBD2MWM","created_at":"2026-07-05T08:59:36Z"},{"alias_kind":"pith_short_8","alias_value":"L4JFOJRU","created_at":"2026-07-05T08:59:36Z"}],"graph_snapshots":[{"event_id":"sha256:4bb9f921dc4cae764399460eb0ee0cd48e0bb38b37e067b3810538b67048b302","target":"graph","created_at":"2026-07-05T08:59:36Z","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/2408.14594/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Changyou Chen, Jian Chen, Jiuxiang Gu, Ruiyi Zhang, Ryan Rossi, Yufan Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-26T19:26:50Z","title":"MMR: Evaluating Reading Ability of Large Multimodal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.14594","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":"sha256:1128ad435e6816dccade73ce045b3982bfb4b57f3d96f1bf663123722b52a513","target":"record","created_at":"2026-07-05T08:59:36Z","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":"11f05f2e2254ffb7b13b8b77c8f8ed241a8446cc48ed3ab04b8c859d01ca8aa4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-26T19:26:50Z","title_canon_sha256":"bae1f701f0000dd598afa01f642250214ca9160a58ed2342dd283249e6db1297"},"schema_version":"1.0","source":{"id":"2408.14594","kind":"arxiv","version":1}},"canonical_sha256":"5f12572634ae023d32ccd083cdd553e704ec28c470019039f6df1765a04fb8ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f12572634ae023d32ccd083cdd553e704ec28c470019039f6df1765a04fb8ca","first_computed_at":"2026-07-05T08:59:36.069309Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:59:36.069309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wwBiwk0BYwcQj4205/1OF2qgAbGAoBa9WAWPPcb8fp7cTJ6VDQfisUf8OtcZZWZXTBjbpPu2AQSzaQs5oXYUAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:59:36.069820Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.14594","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1128ad435e6816dccade73ce045b3982bfb4b57f3d96f1bf663123722b52a513","sha256:4bb9f921dc4cae764399460eb0ee0cd48e0bb38b37e067b3810538b67048b302"],"state_sha256":"65d403db7de68ecefb411a05662607eb5844aea18398f15b19b4ca52892e326f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P1w6Zg9OO+Oa/7NnFRdL23W0y4IL2k4/ZVJ2w2p3FhhZqA7d3Ei2C0/ik8/CU4eRMYRIIDycqGnGJ+emePmVCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T16:02:52.721697Z","bundle_sha256":"581e0cb9f2589b1647f070315091e6b4043a86cb56dd01fcf8da2453df9c5fe7"}}