{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:55M5ZALI7JNFOTTOHGRCX3EBP5","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":"a84783693a2713aef0485e2efa205e080f195b1d54e8c71818062156a2119b9d","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-11T16:37:41Z","title_canon_sha256":"ce407ffad4c80ac37ce4f08bb4b34c0da30b6f273dffccdf1c301b6b14583845"},"schema_version":"1.0","source":{"id":"2311.06607","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.06607","created_at":"2026-07-05T08:59:04Z"},{"alias_kind":"arxiv_version","alias_value":"2311.06607v4","created_at":"2026-07-05T08:59:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.06607","created_at":"2026-07-05T08:59:04Z"},{"alias_kind":"pith_short_12","alias_value":"55M5ZALI7JNF","created_at":"2026-07-05T08:59:04Z"},{"alias_kind":"pith_short_16","alias_value":"55M5ZALI7JNFOTTO","created_at":"2026-07-05T08:59:04Z"},{"alias_kind":"pith_short_8","alias_value":"55M5ZALI","created_at":"2026-07-05T08:59:04Z"}],"graph_snapshots":[{"event_id":"sha256:4740647eb0a9dc30534b724e5b6d63d2fa7067f4743dbd4b49c7838e365e6171","target":"graph","created_at":"2026-07-05T08:59:04Z","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/2311.06607/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Multimodal Models (LMMs) have shown promise in vision-language tasks but struggle with high-resolution input and detailed scene understanding. Addressing these challenges, we introduce Monkey to enhance LMM capabilities. Firstly, Monkey processes input images by dividing them into uniform patches, each matching the size (e.g., 448x448) used in the original training of the well-trained vision encoder. Equipped with individual adapter for each patch, Monkey can handle higher resolutions up to 1344x896 pixels, enabling the detailed capture of complex visual information. Secondly, it employs","authors_text":"Biao Yang, Jingxu Yang, Qiang Liu, Shuo Zhang, Xiang Bai, Yabo Sun, Yuliang Liu, Zhang Li, Zhiyin Ma","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-11T16:37:41Z","title":"Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.06607","kind":"arxiv","version":4},"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":"sha256:6fc608e47d0a6f6570bed432d6d347547301c15104b2052b089f9034b0f755ca","target":"record","created_at":"2026-07-05T08:59:04Z","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":"a84783693a2713aef0485e2efa205e080f195b1d54e8c71818062156a2119b9d","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-11T16:37:41Z","title_canon_sha256":"ce407ffad4c80ac37ce4f08bb4b34c0da30b6f273dffccdf1c301b6b14583845"},"schema_version":"1.0","source":{"id":"2311.06607","kind":"arxiv","version":4}},"canonical_sha256":"ef59dc8168fa5a574e6e39a22bec817f42c7e01a0f1f1b3fcf3c26c14e9ccc17","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef59dc8168fa5a574e6e39a22bec817f42c7e01a0f1f1b3fcf3c26c14e9ccc17","first_computed_at":"2026-07-05T08:59:04.206801Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:59:04.206801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wMyPNyN+qInemHFJmQyukIxRknkjXNK+YsvBgeyBHB6cjnfN0jqqnMp8A4bx28STCgQKnv0gG0EaeDS8vlwTCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:59:04.207225Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.06607","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6fc608e47d0a6f6570bed432d6d347547301c15104b2052b089f9034b0f755ca","sha256:4740647eb0a9dc30534b724e5b6d63d2fa7067f4743dbd4b49c7838e365e6171"],"state_sha256":"f3a5beec158936c1517245b8038ad1610de3b3b4d70e5ad8ed0d41e332951d0c"}