{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VPU7FUVDX3LYDD33GZVJ5ZNVQN","short_pith_number":"pith:VPU7FUVD","canonical_record":{"source":{"id":"2405.06706","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-09T07:47:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"27b05056c53fc91b4abc40bdc6fcc92e86b43a2d124b3bb653997f47f07aa42a","abstract_canon_sha256":"1cdbe134e11c514409830694f84e367c42c2f23195e5ced3eef390fdeaa14193"},"schema_version":"1.0"},"canonical_sha256":"abe9f2d2a3bed7818f7b366a9ee5b583420beb0e0fa55dcec4d99e20a050346f","source":{"kind":"arxiv","id":"2405.06706","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.06706","created_at":"2026-07-05T08:18:10Z"},{"alias_kind":"arxiv_version","alias_value":"2405.06706v1","created_at":"2026-07-05T08:18:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.06706","created_at":"2026-07-05T08:18:10Z"},{"alias_kind":"pith_short_12","alias_value":"VPU7FUVDX3LY","created_at":"2026-07-05T08:18:10Z"},{"alias_kind":"pith_short_16","alias_value":"VPU7FUVDX3LYDD33","created_at":"2026-07-05T08:18:10Z"},{"alias_kind":"pith_short_8","alias_value":"VPU7FUVD","created_at":"2026-07-05T08:18:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VPU7FUVDX3LYDD33GZVJ5ZNVQN","target":"record","payload":{"canonical_record":{"source":{"id":"2405.06706","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-09T07:47:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"27b05056c53fc91b4abc40bdc6fcc92e86b43a2d124b3bb653997f47f07aa42a","abstract_canon_sha256":"1cdbe134e11c514409830694f84e367c42c2f23195e5ced3eef390fdeaa14193"},"schema_version":"1.0"},"canonical_sha256":"abe9f2d2a3bed7818f7b366a9ee5b583420beb0e0fa55dcec4d99e20a050346f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:18:10.707916Z","signature_b64":"OPRaf1GdfB0x2+bh00/LBb57fA1TaxyeKZgLRFC1uuoAD6V9UH13y2QPptFpuQoMqO8uPEWUrUFpNc9FtgoECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abe9f2d2a3bed7818f7b366a9ee5b583420beb0e0fa55dcec4d99e20a050346f","last_reissued_at":"2026-07-05T08:18:10.707367Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:18:10.707367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.06706","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":"2026-07-05T08:18:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"opKUM0Y1sa+GXycPVqSSpDYSRE52j1qcDKiHmkTfkheNI05sZqOhJ77uVsC8ajqZ9L3wr7gSr10JTA7WoPo8Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T08:00:11.858293Z"},"content_sha256":"7cbf7dcbf349cf618c2a8bdf4330ebdf7d18dcfcfdd43197dcd145b932f697aa","schema_version":"1.0","event_id":"sha256:7cbf7dcbf349cf618c2a8bdf4330ebdf7d18dcfcfdd43197dcd145b932f697aa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VPU7FUVDX3LYDD33GZVJ5ZNVQN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploring the Capabilities of Large Multimodal Models on Dense Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Biao Yang, Shuo Zhang, Xiang Bai, Yuliang Liu, Zhang Li, Zhiyin Ma","submitted_at":"2024-05-09T07:47:25Z","abstract_excerpt":"While large multi-modal models (LMM) have shown notable progress in multi-modal tasks, their capabilities in tasks involving dense textual content remains to be fully explored. Dense text, which carries important information, is often found in documents, tables, and product descriptions. Understanding dense text enables us to obtain more accurate information, assisting in making better decisions. To further explore the capabilities of LMM in complex text tasks, we propose the DT-VQA dataset, with 170k question-answer pairs. In this paper, we conduct a comprehensive evaluation of GPT4V, Gemini,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.06706","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/2405.06706/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":"2026-07-05T08:18:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JeVXD/JLovaoGokjegH+Vs5LohaYjrQWgd4y7jBwrSHLbKytls1EHvhGDdZxZZ1n3ND97aBZNvvunYtuYCj9Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T08:00:11.858620Z"},"content_sha256":"cff88a5608a603e42386bb17d8b2b0f975e5fa1c1f183fcbcc69cbc996531d2f","schema_version":"1.0","event_id":"sha256:cff88a5608a603e42386bb17d8b2b0f975e5fa1c1f183fcbcc69cbc996531d2f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VPU7FUVDX3LYDD33GZVJ5ZNVQN/bundle.json","state_url":"https://pith.science/pith/VPU7FUVDX3LYDD33GZVJ5ZNVQN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VPU7FUVDX3LYDD33GZVJ5ZNVQN/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":"2026-08-22T08:00:11Z","links":{"resolver":"https://pith.science/pith/VPU7FUVDX3LYDD33GZVJ5ZNVQN","bundle":"https://pith.science/pith/VPU7FUVDX3LYDD33GZVJ5ZNVQN/bundle.json","state":"https://pith.science/pith/VPU7FUVDX3LYDD33GZVJ5ZNVQN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VPU7FUVDX3LYDD33GZVJ5ZNVQN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VPU7FUVDX3LYDD33GZVJ5ZNVQN","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":"1cdbe134e11c514409830694f84e367c42c2f23195e5ced3eef390fdeaa14193","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-09T07:47:25Z","title_canon_sha256":"27b05056c53fc91b4abc40bdc6fcc92e86b43a2d124b3bb653997f47f07aa42a"},"schema_version":"1.0","source":{"id":"2405.06706","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.06706","created_at":"2026-07-05T08:18:10Z"},{"alias_kind":"arxiv_version","alias_value":"2405.06706v1","created_at":"2026-07-05T08:18:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.06706","created_at":"2026-07-05T08:18:10Z"},{"alias_kind":"pith_short_12","alias_value":"VPU7FUVDX3LY","created_at":"2026-07-05T08:18:10Z"},{"alias_kind":"pith_short_16","alias_value":"VPU7FUVDX3LYDD33","created_at":"2026-07-05T08:18:10Z"},{"alias_kind":"pith_short_8","alias_value":"VPU7FUVD","created_at":"2026-07-05T08:18:10Z"}],"graph_snapshots":[{"event_id":"sha256:cff88a5608a603e42386bb17d8b2b0f975e5fa1c1f183fcbcc69cbc996531d2f","target":"graph","created_at":"2026-07-05T08:18:10Z","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/2405.06706/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While large multi-modal models (LMM) have shown notable progress in multi-modal tasks, their capabilities in tasks involving dense textual content remains to be fully explored. Dense text, which carries important information, is often found in documents, tables, and product descriptions. Understanding dense text enables us to obtain more accurate information, assisting in making better decisions. To further explore the capabilities of LMM in complex text tasks, we propose the DT-VQA dataset, with 170k question-answer pairs. In this paper, we conduct a comprehensive evaluation of GPT4V, Gemini,","authors_text":"Biao Yang, Shuo Zhang, Xiang Bai, Yuliang Liu, Zhang Li, Zhiyin Ma","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-09T07:47:25Z","title":"Exploring the Capabilities of Large Multimodal Models on Dense Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.06706","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":"sha256:7cbf7dcbf349cf618c2a8bdf4330ebdf7d18dcfcfdd43197dcd145b932f697aa","target":"record","created_at":"2026-07-05T08:18:10Z","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":"1cdbe134e11c514409830694f84e367c42c2f23195e5ced3eef390fdeaa14193","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-09T07:47:25Z","title_canon_sha256":"27b05056c53fc91b4abc40bdc6fcc92e86b43a2d124b3bb653997f47f07aa42a"},"schema_version":"1.0","source":{"id":"2405.06706","kind":"arxiv","version":1}},"canonical_sha256":"abe9f2d2a3bed7818f7b366a9ee5b583420beb0e0fa55dcec4d99e20a050346f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"abe9f2d2a3bed7818f7b366a9ee5b583420beb0e0fa55dcec4d99e20a050346f","first_computed_at":"2026-07-05T08:18:10.707367Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:18:10.707367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OPRaf1GdfB0x2+bh00/LBb57fA1TaxyeKZgLRFC1uuoAD6V9UH13y2QPptFpuQoMqO8uPEWUrUFpNc9FtgoECg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:18:10.707916Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.06706","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7cbf7dcbf349cf618c2a8bdf4330ebdf7d18dcfcfdd43197dcd145b932f697aa","sha256:cff88a5608a603e42386bb17d8b2b0f975e5fa1c1f183fcbcc69cbc996531d2f"],"state_sha256":"db02d61e26c3d702df7a28642b1b3f011ec681862a2fc9d2e474412e00e2a4a4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4C0PAjvibrnbTHloN09HQP5Z+sjuQOJHv/BRUAjrTFSpBjRh9dNyC3Lae0X5cwk2NI1OuFR2O8OYd0E5iknQCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T08:00:11.862080Z","bundle_sha256":"d61ace3515d60f6d6f39891910bd5d9acc6afbc34bc34f9951ed38f29dba33ed"}}