{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WDES6ZZL22SIBXQ6S2XHDHYWVK","short_pith_number":"pith:WDES6ZZL","canonical_record":{"source":{"id":"2403.11703","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T12:04:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"26e12074e6e35d6c3a619c4e9ddbfe529adfcf49849b3360c8a937104a0287e0","abstract_canon_sha256":"10d2331a102a3a12685e889dda5b94f87f48fe779db77a9b89c497c846871e4c"},"schema_version":"1.0"},"canonical_sha256":"b0c92f672bd6a480de1e96ae719f16aaa5a8e37aa8c85bd4fbf959ec79575e75","source":{"kind":"arxiv","id":"2403.11703","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.11703","created_at":"2026-07-05T07:57:20Z"},{"alias_kind":"arxiv_version","alias_value":"2403.11703v1","created_at":"2026-07-05T07:57:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11703","created_at":"2026-07-05T07:57:20Z"},{"alias_kind":"pith_short_12","alias_value":"WDES6ZZL22SI","created_at":"2026-07-05T07:57:20Z"},{"alias_kind":"pith_short_16","alias_value":"WDES6ZZL22SIBXQ6","created_at":"2026-07-05T07:57:20Z"},{"alias_kind":"pith_short_8","alias_value":"WDES6ZZL","created_at":"2026-07-05T07:57:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WDES6ZZL22SIBXQ6S2XHDHYWVK","target":"record","payload":{"canonical_record":{"source":{"id":"2403.11703","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T12:04:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"26e12074e6e35d6c3a619c4e9ddbfe529adfcf49849b3360c8a937104a0287e0","abstract_canon_sha256":"10d2331a102a3a12685e889dda5b94f87f48fe779db77a9b89c497c846871e4c"},"schema_version":"1.0"},"canonical_sha256":"b0c92f672bd6a480de1e96ae719f16aaa5a8e37aa8c85bd4fbf959ec79575e75","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:20.286734Z","signature_b64":"pKOl3xzUzwuMvBJ23mzkOGLL3p4YoWSBudHCEQptWr5Grbms4QezJ2abHCKtVim9/+ePWH1Ww4J3B4otZ3ZFCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0c92f672bd6a480de1e96ae719f16aaa5a8e37aa8c85bd4fbf959ec79575e75","last_reissued_at":"2026-07-05T07:57:20.286207Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:20.286207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.11703","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":"2026-07-05T07:57:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JF6klkPg0fQhYzMvvWrsJFv5meg1oCpZz4fduILv0doFx3RHTWJf02/LahPORLrn57Yb7FQ4XyWyjPBP43k/AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T15:16:57.538713Z"},"content_sha256":"4019454b221bbb0836c14743cc1b50a004fc3d4d1b5d0d96474ff5448f872e2a","schema_version":"1.0","event_id":"sha256:4019454b221bbb0836c14743cc1b50a004fc3d4d1b5d0d96474ff5448f872e2a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WDES6ZZL22SIBXQ6S2XHDHYWVK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLaVA-UHD: an LMM Perceiving Any Aspect Ratio and High-Resolution Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chunjiang Ge, Gao Huang, Junbo Cui, Maosong Sun, Ruyi Xu, Tat-Seng Chua, Yuan Yao, Zanlin Ni, Zhiyuan Liu, Zonghao Guo","submitted_at":"2024-03-18T12:04:11Z","abstract_excerpt":"Visual encoding constitutes the basis of large multimodal models (LMMs) in understanding the visual world. Conventional LMMs process images in fixed sizes and limited resolutions, while recent explorations in this direction are limited in adaptivity, efficiency, and even correctness. In this work, we first take GPT-4V and LLaVA-1.5 as representative examples and expose systematic flaws rooted in their visual encoding strategy. To address the challenges, we present LLaVA-UHD, a large multimodal model that can efficiently perceive images in any aspect ratio and high resolution. LLaVA-UHD include"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11703","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/2403.11703/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":"2026-07-05T07:57:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qlC3tdVWaEHRebkC7bBVQEpOWXeYwcD8nadfO4LarSOOcX74N/V76KFQJVOl+opf0d0xrcFZKjbZ8D9qSM1SAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T15:16:57.539086Z"},"content_sha256":"613c6b9adbd3172c168dad8940ec03e674c523d6e63a56182e3ecb4f70e1d430","schema_version":"1.0","event_id":"sha256:613c6b9adbd3172c168dad8940ec03e674c523d6e63a56182e3ecb4f70e1d430"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WDES6ZZL22SIBXQ6S2XHDHYWVK/bundle.json","state_url":"https://pith.science/pith/WDES6ZZL22SIBXQ6S2XHDHYWVK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WDES6ZZL22SIBXQ6S2XHDHYWVK/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":"2026-08-18T15:16:57Z","links":{"resolver":"https://pith.science/pith/WDES6ZZL22SIBXQ6S2XHDHYWVK","bundle":"https://pith.science/pith/WDES6ZZL22SIBXQ6S2XHDHYWVK/bundle.json","state":"https://pith.science/pith/WDES6ZZL22SIBXQ6S2XHDHYWVK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WDES6ZZL22SIBXQ6S2XHDHYWVK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WDES6ZZL22SIBXQ6S2XHDHYWVK","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":"10d2331a102a3a12685e889dda5b94f87f48fe779db77a9b89c497c846871e4c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T12:04:11Z","title_canon_sha256":"26e12074e6e35d6c3a619c4e9ddbfe529adfcf49849b3360c8a937104a0287e0"},"schema_version":"1.0","source":{"id":"2403.11703","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.11703","created_at":"2026-07-05T07:57:20Z"},{"alias_kind":"arxiv_version","alias_value":"2403.11703v1","created_at":"2026-07-05T07:57:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11703","created_at":"2026-07-05T07:57:20Z"},{"alias_kind":"pith_short_12","alias_value":"WDES6ZZL22SI","created_at":"2026-07-05T07:57:20Z"},{"alias_kind":"pith_short_16","alias_value":"WDES6ZZL22SIBXQ6","created_at":"2026-07-05T07:57:20Z"},{"alias_kind":"pith_short_8","alias_value":"WDES6ZZL","created_at":"2026-07-05T07:57:20Z"}],"graph_snapshots":[{"event_id":"sha256:613c6b9adbd3172c168dad8940ec03e674c523d6e63a56182e3ecb4f70e1d430","target":"graph","created_at":"2026-07-05T07:57:20Z","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/2403.11703/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual encoding constitutes the basis of large multimodal models (LMMs) in understanding the visual world. Conventional LMMs process images in fixed sizes and limited resolutions, while recent explorations in this direction are limited in adaptivity, efficiency, and even correctness. In this work, we first take GPT-4V and LLaVA-1.5 as representative examples and expose systematic flaws rooted in their visual encoding strategy. To address the challenges, we present LLaVA-UHD, a large multimodal model that can efficiently perceive images in any aspect ratio and high resolution. LLaVA-UHD include","authors_text":"Chunjiang Ge, Gao Huang, Junbo Cui, Maosong Sun, Ruyi Xu, Tat-Seng Chua, Yuan Yao, Zanlin Ni, Zhiyuan Liu, Zonghao Guo","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T12:04:11Z","title":"LLaVA-UHD: an LMM Perceiving Any Aspect Ratio and High-Resolution Images"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11703","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":"sha256:4019454b221bbb0836c14743cc1b50a004fc3d4d1b5d0d96474ff5448f872e2a","target":"record","created_at":"2026-07-05T07:57:20Z","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":"10d2331a102a3a12685e889dda5b94f87f48fe779db77a9b89c497c846871e4c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T12:04:11Z","title_canon_sha256":"26e12074e6e35d6c3a619c4e9ddbfe529adfcf49849b3360c8a937104a0287e0"},"schema_version":"1.0","source":{"id":"2403.11703","kind":"arxiv","version":1}},"canonical_sha256":"b0c92f672bd6a480de1e96ae719f16aaa5a8e37aa8c85bd4fbf959ec79575e75","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0c92f672bd6a480de1e96ae719f16aaa5a8e37aa8c85bd4fbf959ec79575e75","first_computed_at":"2026-07-05T07:57:20.286207Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:57:20.286207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pKOl3xzUzwuMvBJ23mzkOGLL3p4YoWSBudHCEQptWr5Grbms4QezJ2abHCKtVim9/+ePWH1Ww4J3B4otZ3ZFCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:57:20.286734Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.11703","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4019454b221bbb0836c14743cc1b50a004fc3d4d1b5d0d96474ff5448f872e2a","sha256:613c6b9adbd3172c168dad8940ec03e674c523d6e63a56182e3ecb4f70e1d430"],"state_sha256":"7299bb0b6e73be6acbe3f952d884ae2b3e7b707bc603ff55b558530e1503c2c0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WDlQzZldnQmx0j58MJ7Tg4b01teaxK46HoJWZdgsSI/d734jFg78YzOoQzW/gwACMWLbpFMuA1OMJPR7MhmRDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T15:16:57.542519Z","bundle_sha256":"84d2445b112ddb7990eb283babc15e62e4aa849ceeb951504a84298c44d8ab72"}}