{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CEYM26CGOJFCQ3BQIUM7ZDWKYN","short_pith_number":"pith:CEYM26CG","canonical_record":{"source":{"id":"2403.01487","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-03T11:39:41Z","cross_cats_sorted":[],"title_canon_sha256":"46102e1d542c8e0ec52ee1ecd12c9395c9b3b190d5fa0e17a5c2d9c8727b9e88","abstract_canon_sha256":"a64408316e5170e5bf34d71fa449f23d9c32fe5517634ec4b77b27a26e67716e"},"schema_version":"1.0"},"canonical_sha256":"1130cd7846724a286c304519fc8ecac37e15c90e950809862f25b3d0a2009da0","source":{"kind":"arxiv","id":"2403.01487","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.01487","created_at":"2026-07-05T07:51:47Z"},{"alias_kind":"arxiv_version","alias_value":"2403.01487v1","created_at":"2026-07-05T07:51:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01487","created_at":"2026-07-05T07:51:47Z"},{"alias_kind":"pith_short_12","alias_value":"CEYM26CGOJFC","created_at":"2026-07-05T07:51:47Z"},{"alias_kind":"pith_short_16","alias_value":"CEYM26CGOJFCQ3BQ","created_at":"2026-07-05T07:51:47Z"},{"alias_kind":"pith_short_8","alias_value":"CEYM26CG","created_at":"2026-07-05T07:51:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CEYM26CGOJFCQ3BQIUM7ZDWKYN","target":"record","payload":{"canonical_record":{"source":{"id":"2403.01487","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-03T11:39:41Z","cross_cats_sorted":[],"title_canon_sha256":"46102e1d542c8e0ec52ee1ecd12c9395c9b3b190d5fa0e17a5c2d9c8727b9e88","abstract_canon_sha256":"a64408316e5170e5bf34d71fa449f23d9c32fe5517634ec4b77b27a26e67716e"},"schema_version":"1.0"},"canonical_sha256":"1130cd7846724a286c304519fc8ecac37e15c90e950809862f25b3d0a2009da0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:47.957367Z","signature_b64":"4Jb5ADLkXWae7seCfwJXua072V4PqSUqYUhAGJqVR2FwY0VOKMbogPWVweTmG9UjcAXQB2s2OOkoE4MHye5fBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1130cd7846724a286c304519fc8ecac37e15c90e950809862f25b3d0a2009da0","last_reissued_at":"2026-07-05T07:51:47.956931Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:47.956931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.01487","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":"2026-07-05T07:51:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4plLHCX83lFnWDYG2/iAggmWI2fpU44jY3LWVsMl/zAYQmMFM1VTv6vNjt8hNTE02fAthCPFiS1xM8Vr6hfJBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:05:57.235063Z"},"content_sha256":"622f5076442c7f92f85209c400edc57150b7e707e75fe8b992ab502061e19ead","schema_version":"1.0","event_id":"sha256:622f5076442c7f92f85209c400edc57150b7e707e75fe8b992ab502061e19ead"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CEYM26CGOJFCQ3BQIUM7ZDWKYN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"InfiMM-HD: A Leap Forward in High-Resolution Multimodal Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohan Zhai, Haogeng Liu, Hongxia Yang, Huaibo Huang, Quanzeng You, Ran He, Xiaotian Han, Yiqi Wang, Yongfei Liu, Yunzhe Tao","submitted_at":"2024-03-03T11:39:41Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have experienced significant advancements recently. Nevertheless, challenges persist in the accurate recognition and comprehension of intricate details within high-resolution images. Despite being indispensable for the development of robust MLLMs, this area remains underinvestigated. To tackle this challenge, our work introduces InfiMM-HD, a novel architecture specifically designed for processing images of different resolutions with low computational overhead. This innovation facilitates the enlargement of MLLMs to higher-resolution capabilities. InfiMM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01487","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/2403.01487/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":"2026-07-05T07:51:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZlpEjDSyZrojYqT8LYrKKF4o726V+YZsCvWoNY8HKAMcKB6yJlyVsIWKfVddMfYN1KIsq6eajlzzUBVCM48lCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:05:57.235446Z"},"content_sha256":"55cbee6960a3141d2bf7c1e124ccc7ca4a7b3ce062499cdb30670578a79d095e","schema_version":"1.0","event_id":"sha256:55cbee6960a3141d2bf7c1e124ccc7ca4a7b3ce062499cdb30670578a79d095e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CEYM26CGOJFCQ3BQIUM7ZDWKYN/bundle.json","state_url":"https://pith.science/pith/CEYM26CGOJFCQ3BQIUM7ZDWKYN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CEYM26CGOJFCQ3BQIUM7ZDWKYN/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":"2026-07-07T10:05:57Z","links":{"resolver":"https://pith.science/pith/CEYM26CGOJFCQ3BQIUM7ZDWKYN","bundle":"https://pith.science/pith/CEYM26CGOJFCQ3BQIUM7ZDWKYN/bundle.json","state":"https://pith.science/pith/CEYM26CGOJFCQ3BQIUM7ZDWKYN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CEYM26CGOJFCQ3BQIUM7ZDWKYN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CEYM26CGOJFCQ3BQIUM7ZDWKYN","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":"a64408316e5170e5bf34d71fa449f23d9c32fe5517634ec4b77b27a26e67716e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-03T11:39:41Z","title_canon_sha256":"46102e1d542c8e0ec52ee1ecd12c9395c9b3b190d5fa0e17a5c2d9c8727b9e88"},"schema_version":"1.0","source":{"id":"2403.01487","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.01487","created_at":"2026-07-05T07:51:47Z"},{"alias_kind":"arxiv_version","alias_value":"2403.01487v1","created_at":"2026-07-05T07:51:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01487","created_at":"2026-07-05T07:51:47Z"},{"alias_kind":"pith_short_12","alias_value":"CEYM26CGOJFC","created_at":"2026-07-05T07:51:47Z"},{"alias_kind":"pith_short_16","alias_value":"CEYM26CGOJFCQ3BQ","created_at":"2026-07-05T07:51:47Z"},{"alias_kind":"pith_short_8","alias_value":"CEYM26CG","created_at":"2026-07-05T07:51:47Z"}],"graph_snapshots":[{"event_id":"sha256:55cbee6960a3141d2bf7c1e124ccc7ca4a7b3ce062499cdb30670578a79d095e","target":"graph","created_at":"2026-07-05T07:51:47Z","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/2403.01487/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) have experienced significant advancements recently. Nevertheless, challenges persist in the accurate recognition and comprehension of intricate details within high-resolution images. Despite being indispensable for the development of robust MLLMs, this area remains underinvestigated. To tackle this challenge, our work introduces InfiMM-HD, a novel architecture specifically designed for processing images of different resolutions with low computational overhead. This innovation facilitates the enlargement of MLLMs to higher-resolution capabilities. InfiMM","authors_text":"Bohan Zhai, Haogeng Liu, Hongxia Yang, Huaibo Huang, Quanzeng You, Ran He, Xiaotian Han, Yiqi Wang, Yongfei Liu, Yunzhe Tao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-03T11:39:41Z","title":"InfiMM-HD: A Leap Forward in High-Resolution Multimodal Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01487","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":"sha256:622f5076442c7f92f85209c400edc57150b7e707e75fe8b992ab502061e19ead","target":"record","created_at":"2026-07-05T07:51:47Z","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":"a64408316e5170e5bf34d71fa449f23d9c32fe5517634ec4b77b27a26e67716e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-03T11:39:41Z","title_canon_sha256":"46102e1d542c8e0ec52ee1ecd12c9395c9b3b190d5fa0e17a5c2d9c8727b9e88"},"schema_version":"1.0","source":{"id":"2403.01487","kind":"arxiv","version":1}},"canonical_sha256":"1130cd7846724a286c304519fc8ecac37e15c90e950809862f25b3d0a2009da0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1130cd7846724a286c304519fc8ecac37e15c90e950809862f25b3d0a2009da0","first_computed_at":"2026-07-05T07:51:47.956931Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:51:47.956931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4Jb5ADLkXWae7seCfwJXua072V4PqSUqYUhAGJqVR2FwY0VOKMbogPWVweTmG9UjcAXQB2s2OOkoE4MHye5fBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:51:47.957367Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.01487","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:622f5076442c7f92f85209c400edc57150b7e707e75fe8b992ab502061e19ead","sha256:55cbee6960a3141d2bf7c1e124ccc7ca4a7b3ce062499cdb30670578a79d095e"],"state_sha256":"29e2ae7dec3e2bb9bd3da2cdd42ce33d95264693e355f3fa0a953afceaaef972"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OqNSzQZbLE/fbHY01Gm+Fgwh5IAe5SNj4x81afffv48B+VbSkRPSYzprZz3pXk1M6SM2KuaoJoP6hQCsJmBvDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T10:05:57.237422Z","bundle_sha256":"6341661b0787b1dfba3c4e77e78a2cbdd5166889cdb24413c7055342b63e8884"}}