{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EGO2DI5W6N63OAVOZBFO4F2MUU","short_pith_number":"pith:EGO2DI5W","canonical_record":{"source":{"id":"2404.06512","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-09T17:59:32Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"07f648b459094d68b3d00e94cbe3e26dcfb4798b1ebcc89dfd2bb160e9412330","abstract_canon_sha256":"8e7348888d8e03fe2d813a2ab3518c3c670ffb3c533514f10e25275f03510af5"},"schema_version":"1.0"},"canonical_sha256":"219da1a3b6f37db702aec84aee174ca50cc73fde560ddca53bfec0efd38d3ae9","source":{"kind":"arxiv","id":"2404.06512","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.06512","created_at":"2026-07-05T08:06:09Z"},{"alias_kind":"arxiv_version","alias_value":"2404.06512v1","created_at":"2026-07-05T08:06:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.06512","created_at":"2026-07-05T08:06:09Z"},{"alias_kind":"pith_short_12","alias_value":"EGO2DI5W6N63","created_at":"2026-07-05T08:06:09Z"},{"alias_kind":"pith_short_16","alias_value":"EGO2DI5W6N63OAVO","created_at":"2026-07-05T08:06:09Z"},{"alias_kind":"pith_short_8","alias_value":"EGO2DI5W","created_at":"2026-07-05T08:06:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EGO2DI5W6N63OAVOZBFO4F2MUU","target":"record","payload":{"canonical_record":{"source":{"id":"2404.06512","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-09T17:59:32Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"07f648b459094d68b3d00e94cbe3e26dcfb4798b1ebcc89dfd2bb160e9412330","abstract_canon_sha256":"8e7348888d8e03fe2d813a2ab3518c3c670ffb3c533514f10e25275f03510af5"},"schema_version":"1.0"},"canonical_sha256":"219da1a3b6f37db702aec84aee174ca50cc73fde560ddca53bfec0efd38d3ae9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:09.844994Z","signature_b64":"JdKZM8hL2/1gITHk0sxNefjF8ibP7Uv1/qzh8Df2c7iK8jMlOfXE4M+dvRAjFeABTW2CnkzdGH0KMhD+ukDQBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"219da1a3b6f37db702aec84aee174ca50cc73fde560ddca53bfec0efd38d3ae9","last_reissued_at":"2026-07-05T08:06:09.844584Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:09.844584Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.06512","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":"2026-07-05T08:06:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dO0k9Rz6TJoZZgcKxvbmHGJ0jdoqdTEbwcIMi1an11PeudW/iIhDW3YQ7GmNQzTRnc41LM9VDx1NEoW5I0XEDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T04:43:04.197030Z"},"content_sha256":"beaf9af439429ac20411ef4cded71deee4903199c92c165f4579b6889e3c199d","schema_version":"1.0","event_id":"sha256:beaf9af439429ac20411ef4cded71deee4903199c92c165f4579b6889e3c199d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EGO2DI5W6N63OAVOZBFO4F2MUU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Bin Wang, Conghui He, Dahua Lin, Hang Yan, Haodong Duan, Jiaqi Wang, Jifeng Dai, Jingwen Li, Kai Chen, Linke Ouyang, Pan Zhang, Songyang Zhang, Wei Li, Wenhai Wang, Wenwei Zhang, Xiaoyi Dong, Xingcheng Zhang, Xinyue Zhang, Yang Gao, Yining Li, Yuhang Cao, Yuhang Zang, Yu Qiao, Zhe Chen","submitted_at":"2024-04-09T17:59:32Z","abstract_excerpt":"The Large Vision-Language Model (LVLM) field has seen significant advancements, yet its progression has been hindered by challenges in comprehending fine-grained visual content due to limited resolution. Recent efforts have aimed to enhance the high-resolution understanding capabilities of LVLMs, yet they remain capped at approximately 1500 x 1500 pixels and constrained to a relatively narrow resolution range. This paper represents InternLM-XComposer2-4KHD, a groundbreaking exploration into elevating LVLM resolution capabilities up to 4K HD (3840 x 1600) and beyond. Concurrently, considering t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.06512","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/2404.06512/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":"2026-07-05T08:06:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P0qAcw48lGUlh4/rRqtkGKrtsjMm+QAerNPHFSfy23cB4/yPHXm8AOxQtQQlUhpnL6Ly/v5E4jLC8DQkdzh5BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T04:43:04.197422Z"},"content_sha256":"4dcfa2985482ed737dac7ab683f97247cef7d93da6ee92c5f095f138901f8d30","schema_version":"1.0","event_id":"sha256:4dcfa2985482ed737dac7ab683f97247cef7d93da6ee92c5f095f138901f8d30"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EGO2DI5W6N63OAVOZBFO4F2MUU/bundle.json","state_url":"https://pith.science/pith/EGO2DI5W6N63OAVOZBFO4F2MUU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EGO2DI5W6N63OAVOZBFO4F2MUU/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":"2026-07-25T04:43:04Z","links":{"resolver":"https://pith.science/pith/EGO2DI5W6N63OAVOZBFO4F2MUU","bundle":"https://pith.science/pith/EGO2DI5W6N63OAVOZBFO4F2MUU/bundle.json","state":"https://pith.science/pith/EGO2DI5W6N63OAVOZBFO4F2MUU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EGO2DI5W6N63OAVOZBFO4F2MUU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EGO2DI5W6N63OAVOZBFO4F2MUU","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":"8e7348888d8e03fe2d813a2ab3518c3c670ffb3c533514f10e25275f03510af5","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-09T17:59:32Z","title_canon_sha256":"07f648b459094d68b3d00e94cbe3e26dcfb4798b1ebcc89dfd2bb160e9412330"},"schema_version":"1.0","source":{"id":"2404.06512","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.06512","created_at":"2026-07-05T08:06:09Z"},{"alias_kind":"arxiv_version","alias_value":"2404.06512v1","created_at":"2026-07-05T08:06:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.06512","created_at":"2026-07-05T08:06:09Z"},{"alias_kind":"pith_short_12","alias_value":"EGO2DI5W6N63","created_at":"2026-07-05T08:06:09Z"},{"alias_kind":"pith_short_16","alias_value":"EGO2DI5W6N63OAVO","created_at":"2026-07-05T08:06:09Z"},{"alias_kind":"pith_short_8","alias_value":"EGO2DI5W","created_at":"2026-07-05T08:06:09Z"}],"graph_snapshots":[{"event_id":"sha256:4dcfa2985482ed737dac7ab683f97247cef7d93da6ee92c5f095f138901f8d30","target":"graph","created_at":"2026-07-05T08:06:09Z","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/2404.06512/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Large Vision-Language Model (LVLM) field has seen significant advancements, yet its progression has been hindered by challenges in comprehending fine-grained visual content due to limited resolution. Recent efforts have aimed to enhance the high-resolution understanding capabilities of LVLMs, yet they remain capped at approximately 1500 x 1500 pixels and constrained to a relatively narrow resolution range. This paper represents InternLM-XComposer2-4KHD, a groundbreaking exploration into elevating LVLM resolution capabilities up to 4K HD (3840 x 1600) and beyond. Concurrently, considering t","authors_text":"Bin Wang, Conghui He, Dahua Lin, Hang Yan, Haodong Duan, Jiaqi Wang, Jifeng Dai, Jingwen Li, Kai Chen, Linke Ouyang, Pan Zhang, Songyang Zhang, Wei Li, Wenhai Wang, Wenwei Zhang, Xiaoyi Dong, Xingcheng Zhang, Xinyue Zhang, Yang Gao, Yining Li, Yuhang Cao, Yuhang Zang, Yu Qiao, Zhe Chen","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-09T17:59:32Z","title":"InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.06512","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:beaf9af439429ac20411ef4cded71deee4903199c92c165f4579b6889e3c199d","target":"record","created_at":"2026-07-05T08:06:09Z","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":"8e7348888d8e03fe2d813a2ab3518c3c670ffb3c533514f10e25275f03510af5","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-09T17:59:32Z","title_canon_sha256":"07f648b459094d68b3d00e94cbe3e26dcfb4798b1ebcc89dfd2bb160e9412330"},"schema_version":"1.0","source":{"id":"2404.06512","kind":"arxiv","version":1}},"canonical_sha256":"219da1a3b6f37db702aec84aee174ca50cc73fde560ddca53bfec0efd38d3ae9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"219da1a3b6f37db702aec84aee174ca50cc73fde560ddca53bfec0efd38d3ae9","first_computed_at":"2026-07-05T08:06:09.844584Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:06:09.844584Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JdKZM8hL2/1gITHk0sxNefjF8ibP7Uv1/qzh8Df2c7iK8jMlOfXE4M+dvRAjFeABTW2CnkzdGH0KMhD+ukDQBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:06:09.844994Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.06512","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:beaf9af439429ac20411ef4cded71deee4903199c92c165f4579b6889e3c199d","sha256:4dcfa2985482ed737dac7ab683f97247cef7d93da6ee92c5f095f138901f8d30"],"state_sha256":"d399c15b77151dcd566eaff80c7432e76f9a3f383e385d8cf4260dec3e4b0fc6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WAX7DGeO3z/PtR0RD+CuSEpExAHzMHv1YLn+Ie15iZT03G2Mg9buMeB2zlgGE69QVDWcztXY2NRcjfDNBLE7Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-25T04:43:04.199470Z","bundle_sha256":"cf15098a1ff28f15d06e04221d6ff4f2df350acb29018ed838c9cfde472655a7"}}