{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ST5A73XEB3JY6I4T5MT6PSPS72","short_pith_number":"pith:ST5A73XE","schema_version":"1.0","canonical_sha256":"94fa0feee40ed38f2393eb27e7c9f2fea5932f60408ff724a9e804709c03579c","source":{"kind":"arxiv","id":"2410.01744","version":3},"attestation_state":"computed","paper":{"title":"Leopard: A Vision Language Model For Text-Rich Multi-Image Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Dong Yu, Hongming Zhang, Kaixin Ma, Meng Jiang, Mengzhao Jia, Siru Ouyang, Tianqing Fang, Wenhao Yu, Zhihan Zhang","submitted_at":"2024-10-02T16:55:01Z","abstract_excerpt":"Text-rich images, where text serves as the central visual element guiding the overall understanding, are prevalent in real-world applications, such as presentation slides, scanned documents, and webpage snapshots. Tasks involving multiple text-rich images are especially challenging, as they require not only understanding the content of individual images but reasoning about inter-relationships and logical flows across multiple visual inputs. Despite the importance of these scenarios, current multimodal large language models (MLLMs) struggle to handle such tasks due to two key challenges: (1) th"},"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":"2410.01744","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-02T16:55:01Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"dbab08b21e31e34700dfa29924b0bdb3ef95f4a87d53aababf4fce036adedabf","abstract_canon_sha256":"f6c2eb87587f95a66a2ab7994d8002c2919f63f3e3e07ef672532c9ecacad7cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:22.465183Z","signature_b64":"dVCvC0dFMPtk0jKpwI8gXWjXvqXq8oABWfWIvnws/DeCp1CsE04RQMS/eqoGwpSbDu9C4ShXTDGuSVXdTvkCBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94fa0feee40ed38f2393eb27e7c9f2fea5932f60408ff724a9e804709c03579c","last_reissued_at":"2026-07-05T11:17:22.464635Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:22.464635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leopard: A Vision Language Model For Text-Rich Multi-Image Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Dong Yu, Hongming Zhang, Kaixin Ma, Meng Jiang, Mengzhao Jia, Siru Ouyang, Tianqing Fang, Wenhao Yu, Zhihan Zhang","submitted_at":"2024-10-02T16:55:01Z","abstract_excerpt":"Text-rich images, where text serves as the central visual element guiding the overall understanding, are prevalent in real-world applications, such as presentation slides, scanned documents, and webpage snapshots. Tasks involving multiple text-rich images are especially challenging, as they require not only understanding the content of individual images but reasoning about inter-relationships and logical flows across multiple visual inputs. Despite the importance of these scenarios, current multimodal large language models (MLLMs) struggle to handle such tasks due to two key challenges: (1) th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01744","kind":"arxiv","version":3},"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/2410.01744/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":"2410.01744","created_at":"2026-07-05T11:17:22.464709+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.01744v3","created_at":"2026-07-05T11:17:22.464709+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01744","created_at":"2026-07-05T11:17:22.464709+00:00"},{"alias_kind":"pith_short_12","alias_value":"ST5A73XEB3JY","created_at":"2026-07-05T11:17:22.464709+00:00"},{"alias_kind":"pith_short_16","alias_value":"ST5A73XEB3JY6I4T","created_at":"2026-07-05T11:17:22.464709+00:00"},{"alias_kind":"pith_short_8","alias_value":"ST5A73XE","created_at":"2026-07-05T11:17:22.464709+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.09861","citing_title":"A Survey on MLLM-based Visually Rich Document Understanding: Methods, Challenges, and Emerging Trends","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2601.22149","citing_title":"DynaWeb: Model-Based Reinforcement Learning of Web Agents","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ST5A73XEB3JY6I4T5MT6PSPS72","json":"https://pith.science/pith/ST5A73XEB3JY6I4T5MT6PSPS72.json","graph_json":"https://pith.science/api/pith-number/ST5A73XEB3JY6I4T5MT6PSPS72/graph.json","events_json":"https://pith.science/api/pith-number/ST5A73XEB3JY6I4T5MT6PSPS72/events.json","paper":"https://pith.science/paper/ST5A73XE"},"agent_actions":{"view_html":"https://pith.science/pith/ST5A73XEB3JY6I4T5MT6PSPS72","download_json":"https://pith.science/pith/ST5A73XEB3JY6I4T5MT6PSPS72.json","view_paper":"https://pith.science/paper/ST5A73XE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.01744&json=true","fetch_graph":"https://pith.science/api/pith-number/ST5A73XEB3JY6I4T5MT6PSPS72/graph.json","fetch_events":"https://pith.science/api/pith-number/ST5A73XEB3JY6I4T5MT6PSPS72/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ST5A73XEB3JY6I4T5MT6PSPS72/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ST5A73XEB3JY6I4T5MT6PSPS72/action/storage_attestation","attest_author":"https://pith.science/pith/ST5A73XEB3JY6I4T5MT6PSPS72/action/author_attestation","sign_citation":"https://pith.science/pith/ST5A73XEB3JY6I4T5MT6PSPS72/action/citation_signature","submit_replication":"https://pith.science/pith/ST5A73XEB3JY6I4T5MT6PSPS72/action/replication_record"}},"created_at":"2026-07-05T11:17:22.464709+00:00","updated_at":"2026-07-05T11:17:22.464709+00:00"}