{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ST5A73XEB3JY6I4T5MT6PSPS72","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":"f6c2eb87587f95a66a2ab7994d8002c2919f63f3e3e07ef672532c9ecacad7cd","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-02T16:55:01Z","title_canon_sha256":"dbab08b21e31e34700dfa29924b0bdb3ef95f4a87d53aababf4fce036adedabf"},"schema_version":"1.0","source":{"id":"2410.01744","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01744","created_at":"2026-07-05T11:17:22Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01744v3","created_at":"2026-07-05T11:17:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01744","created_at":"2026-07-05T11:17:22Z"},{"alias_kind":"pith_short_12","alias_value":"ST5A73XEB3JY","created_at":"2026-07-05T11:17:22Z"},{"alias_kind":"pith_short_16","alias_value":"ST5A73XEB3JY6I4T","created_at":"2026-07-05T11:17:22Z"},{"alias_kind":"pith_short_8","alias_value":"ST5A73XE","created_at":"2026-07-05T11:17:22Z"}],"graph_snapshots":[{"event_id":"sha256:11325d50c5e0ea1f3a52ed4f6d3439caf86d3de396a77820f015b6f8bfa8d2ef","target":"graph","created_at":"2026-07-05T11:17:22Z","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/2410.01744/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dong Yu, Hongming Zhang, Kaixin Ma, Meng Jiang, Mengzhao Jia, Siru Ouyang, Tianqing Fang, Wenhao Yu, Zhihan Zhang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-02T16:55:01Z","title":"Leopard: A Vision Language Model For Text-Rich Multi-Image Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01744","kind":"arxiv","version":3},"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":"sha256:43e2a96059726462a76b338804b16f9bd91bab3ea3af16054e6325ab4f1233f9","target":"record","created_at":"2026-07-05T11:17:22Z","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":"f6c2eb87587f95a66a2ab7994d8002c2919f63f3e3e07ef672532c9ecacad7cd","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-02T16:55:01Z","title_canon_sha256":"dbab08b21e31e34700dfa29924b0bdb3ef95f4a87d53aababf4fce036adedabf"},"schema_version":"1.0","source":{"id":"2410.01744","kind":"arxiv","version":3}},"canonical_sha256":"94fa0feee40ed38f2393eb27e7c9f2fea5932f60408ff724a9e804709c03579c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"94fa0feee40ed38f2393eb27e7c9f2fea5932f60408ff724a9e804709c03579c","first_computed_at":"2026-07-05T11:17:22.464635Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:22.464635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dVCvC0dFMPtk0jKpwI8gXWjXvqXq8oABWfWIvnws/DeCp1CsE04RQMS/eqoGwpSbDu9C4ShXTDGuSVXdTvkCBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:22.465183Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.01744","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43e2a96059726462a76b338804b16f9bd91bab3ea3af16054e6325ab4f1233f9","sha256:11325d50c5e0ea1f3a52ed4f6d3439caf86d3de396a77820f015b6f8bfa8d2ef"],"state_sha256":"d6c3daae6814b7590c6253cee5bd6df6033f881292bc078ca2ffb46ce9ad91ad"}