{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JLW4JM6BCJEHV36LCVWAXJUVCC","short_pith_number":"pith:JLW4JM6B","canonical_record":{"source":{"id":"2410.11538","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-15T12:13:42Z","cross_cats_sorted":[],"title_canon_sha256":"acdca62b29054998c2f0e5ead94fba658cbedd4791e812ab95649b956951ea17","abstract_canon_sha256":"eb90b16a732fc051d2172acf2aa8b3ad68aac0fff1eef4ccf053e8d4e8b2e335"},"schema_version":"1.0"},"canonical_sha256":"4aedc4b3c112487aefcb156c0ba69510b0c164ab428d41c50519e3d357b02a5a","source":{"kind":"arxiv","id":"2410.11538","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.11538","created_at":"2026-07-05T09:20:55Z"},{"alias_kind":"arxiv_version","alias_value":"2410.11538v1","created_at":"2026-07-05T09:20:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11538","created_at":"2026-07-05T09:20:55Z"},{"alias_kind":"pith_short_12","alias_value":"JLW4JM6BCJEH","created_at":"2026-07-05T09:20:55Z"},{"alias_kind":"pith_short_16","alias_value":"JLW4JM6BCJEHV36L","created_at":"2026-07-05T09:20:55Z"},{"alias_kind":"pith_short_8","alias_value":"JLW4JM6B","created_at":"2026-07-05T09:20:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JLW4JM6BCJEHV36LCVWAXJUVCC","target":"record","payload":{"canonical_record":{"source":{"id":"2410.11538","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-15T12:13:42Z","cross_cats_sorted":[],"title_canon_sha256":"acdca62b29054998c2f0e5ead94fba658cbedd4791e812ab95649b956951ea17","abstract_canon_sha256":"eb90b16a732fc051d2172acf2aa8b3ad68aac0fff1eef4ccf053e8d4e8b2e335"},"schema_version":"1.0"},"canonical_sha256":"4aedc4b3c112487aefcb156c0ba69510b0c164ab428d41c50519e3d357b02a5a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:55.357442Z","signature_b64":"uye1ZVNqSRO2rflrcWzRdG8UsOKJ9KH9KnWZnyquIYUIQKE3RdF24TpEihN/twSHC75S1ILSKe90PuAl6ntOBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4aedc4b3c112487aefcb156c0ba69510b0c164ab428d41c50519e3d357b02a5a","last_reissued_at":"2026-07-05T09:20:55.356917Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:55.356917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.11538","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":"2026-07-05T09:20:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+Xg5NJWC6VL8KnZt/BQ0Tm52ajTuLVZv63wc2oUMcsOc4shK+tb7ijC2JNnWcDxr/eLWbyt2BiTDlLXYgx4DAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:16:18.813501Z"},"content_sha256":"847f95c0c0ea6a58945c76e6102af6a8d847114b74ccd53ae5f04d7e67cb8c11","schema_version":"1.0","event_id":"sha256:847f95c0c0ea6a58945c76e6102af6a8d847114b74ccd53ae5f04d7e67cb8c11"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JLW4JM6BCJEHV36LCVWAXJUVCC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MCTBench: Multimodal Cognition towards Text-Rich Visual Scenes Benchmark","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"An-Lan Wang, Bin Shan, Can Huang, Guozhi Tang, Jingqun Tang, Lei Liao, Wei Shi, Xiang Bai, Xiang Fei","submitted_at":"2024-10-15T12:13:42Z","abstract_excerpt":"The comprehension of text-rich visual scenes has become a focal point for evaluating Multi-modal Large Language Models (MLLMs) due to their widespread applications. Current benchmarks tailored to the scenario emphasize perceptual capabilities, while overlooking the assessment of cognitive abilities. To address this limitation, we introduce a Multimodal benchmark towards Text-rich visual scenes, to evaluate the Cognitive capabilities of MLLMs through visual reasoning and content-creation tasks (MCTBench). To mitigate potential evaluation bias from the varying distributions of datasets, MCTBench"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11538","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/2410.11538/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":"2026-07-05T09:20:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R6s1D6Sf2oDc9b2vlcRPElD7dyvo8cTHlTEKWyhAZZnCkJ2KPlQTuzzt2UThCi1TeRpesWVP3HuB15UVxzBxDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:16:18.814407Z"},"content_sha256":"1ffc10d8ee10e715f024be9311141304bb618dceeaa823dfd5befb88b8432de0","schema_version":"1.0","event_id":"sha256:1ffc10d8ee10e715f024be9311141304bb618dceeaa823dfd5befb88b8432de0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JLW4JM6BCJEHV36LCVWAXJUVCC/bundle.json","state_url":"https://pith.science/pith/JLW4JM6BCJEHV36LCVWAXJUVCC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JLW4JM6BCJEHV36LCVWAXJUVCC/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":"2026-08-08T13:16:18Z","links":{"resolver":"https://pith.science/pith/JLW4JM6BCJEHV36LCVWAXJUVCC","bundle":"https://pith.science/pith/JLW4JM6BCJEHV36LCVWAXJUVCC/bundle.json","state":"https://pith.science/pith/JLW4JM6BCJEHV36LCVWAXJUVCC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JLW4JM6BCJEHV36LCVWAXJUVCC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JLW4JM6BCJEHV36LCVWAXJUVCC","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":"eb90b16a732fc051d2172acf2aa8b3ad68aac0fff1eef4ccf053e8d4e8b2e335","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-15T12:13:42Z","title_canon_sha256":"acdca62b29054998c2f0e5ead94fba658cbedd4791e812ab95649b956951ea17"},"schema_version":"1.0","source":{"id":"2410.11538","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.11538","created_at":"2026-07-05T09:20:55Z"},{"alias_kind":"arxiv_version","alias_value":"2410.11538v1","created_at":"2026-07-05T09:20:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11538","created_at":"2026-07-05T09:20:55Z"},{"alias_kind":"pith_short_12","alias_value":"JLW4JM6BCJEH","created_at":"2026-07-05T09:20:55Z"},{"alias_kind":"pith_short_16","alias_value":"JLW4JM6BCJEHV36L","created_at":"2026-07-05T09:20:55Z"},{"alias_kind":"pith_short_8","alias_value":"JLW4JM6B","created_at":"2026-07-05T09:20:55Z"}],"graph_snapshots":[{"event_id":"sha256:1ffc10d8ee10e715f024be9311141304bb618dceeaa823dfd5befb88b8432de0","target":"graph","created_at":"2026-07-05T09:20:55Z","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/2410.11538/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The comprehension of text-rich visual scenes has become a focal point for evaluating Multi-modal Large Language Models (MLLMs) due to their widespread applications. Current benchmarks tailored to the scenario emphasize perceptual capabilities, while overlooking the assessment of cognitive abilities. To address this limitation, we introduce a Multimodal benchmark towards Text-rich visual scenes, to evaluate the Cognitive capabilities of MLLMs through visual reasoning and content-creation tasks (MCTBench). To mitigate potential evaluation bias from the varying distributions of datasets, MCTBench","authors_text":"An-Lan Wang, Bin Shan, Can Huang, Guozhi Tang, Jingqun Tang, Lei Liao, Wei Shi, Xiang Bai, Xiang Fei","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-15T12:13:42Z","title":"MCTBench: Multimodal Cognition towards Text-Rich Visual Scenes Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11538","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":"sha256:847f95c0c0ea6a58945c76e6102af6a8d847114b74ccd53ae5f04d7e67cb8c11","target":"record","created_at":"2026-07-05T09:20:55Z","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":"eb90b16a732fc051d2172acf2aa8b3ad68aac0fff1eef4ccf053e8d4e8b2e335","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-15T12:13:42Z","title_canon_sha256":"acdca62b29054998c2f0e5ead94fba658cbedd4791e812ab95649b956951ea17"},"schema_version":"1.0","source":{"id":"2410.11538","kind":"arxiv","version":1}},"canonical_sha256":"4aedc4b3c112487aefcb156c0ba69510b0c164ab428d41c50519e3d357b02a5a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4aedc4b3c112487aefcb156c0ba69510b0c164ab428d41c50519e3d357b02a5a","first_computed_at":"2026-07-05T09:20:55.356917Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:20:55.356917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uye1ZVNqSRO2rflrcWzRdG8UsOKJ9KH9KnWZnyquIYUIQKE3RdF24TpEihN/twSHC75S1ILSKe90PuAl6ntOBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:20:55.357442Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.11538","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:847f95c0c0ea6a58945c76e6102af6a8d847114b74ccd53ae5f04d7e67cb8c11","sha256:1ffc10d8ee10e715f024be9311141304bb618dceeaa823dfd5befb88b8432de0"],"state_sha256":"735af9afcb18e2f193d0256d54727b51569fc12b524bd7ffe62580f6283bf448"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EP+FNeVsS9LnnxqxiB2BhCXvTsrIwfCFHY1KyfhHXjTl+A+UNHhAKZ7aW1bQIfXGTwqyhqc5JXFX6n9KSFuGBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:16:18.819730Z","bundle_sha256":"777ad1697f2b761bb2f28cde13b4aa8d6ef503dab03dc04f2de52dd54384e7cb"}}