{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OYB3TXHMS3OATEW5BBJ3V263D3","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":"b790e72b3cbbfe0da01caec05d6bc2872d10c4aca2f69104cf9506182f5a6518","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-12T17:59:49Z","title_canon_sha256":"50c184a2fa163689e562941c757d5658e6b07e9b62b574564091b078726b6350"},"schema_version":"1.0","source":{"id":"2406.08487","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.08487","created_at":"2026-07-05T08:31:53Z"},{"alias_kind":"arxiv_version","alias_value":"2406.08487v3","created_at":"2026-07-05T08:31:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08487","created_at":"2026-07-05T08:31:53Z"},{"alias_kind":"pith_short_12","alias_value":"OYB3TXHMS3OA","created_at":"2026-07-05T08:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"OYB3TXHMS3OATEW5","created_at":"2026-07-05T08:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"OYB3TXHM","created_at":"2026-07-05T08:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:69cfacebe47cb6c30e6ea7c9dac8b8e471374e171278c9f398dc6464d7896037","target":"graph","created_at":"2026-07-05T08:31:53Z","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/2406.08487/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Seeing clearly with high resolution is a foundation of Large Multimodal Models (LMMs), which has been proven to be vital for visual perception and reasoning. Existing works usually employ a straightforward resolution upscaling method, where the image consists of global and local branches, with the latter being the sliced image patches but resized to the same resolution as the former. This means that higher resolution requires more local patches, resulting in exorbitant computational expenses, and meanwhile, the dominance of local image tokens may diminish the global context. In this paper, we ","authors_text":"Chaoyou Fu, Liang Wang, Qingsong Wen, Rong Jin, Xue Wang, Yi-Fan Zhang, Zhang Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-12T17:59:49Z","title":"Beyond LLaVA-HD: Diving into High-Resolution Large Multimodal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08487","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":"sha256:77591697a9c2b34100a7366ee06fd4991fd4d9ea4e7234fff66b3f4e541ed677","target":"record","created_at":"2026-07-05T08:31:53Z","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":"b790e72b3cbbfe0da01caec05d6bc2872d10c4aca2f69104cf9506182f5a6518","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-12T17:59:49Z","title_canon_sha256":"50c184a2fa163689e562941c757d5658e6b07e9b62b574564091b078726b6350"},"schema_version":"1.0","source":{"id":"2406.08487","kind":"arxiv","version":3}},"canonical_sha256":"7603b9dcec96dc0992dd0853baebdb1eeb536d55fba66e30e8237529ac7b73d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7603b9dcec96dc0992dd0853baebdb1eeb536d55fba66e30e8237529ac7b73d1","first_computed_at":"2026-07-05T08:31:53.260836Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:31:53.260836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4jZ4bZXTIKflC45BM75oqzfXgDWvQznX2057yMMqXiGv2AtIAmj04OHfhyL7X7BkRfSP9LcaRV3vYBw9qnflBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:31:53.261347Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.08487","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77591697a9c2b34100a7366ee06fd4991fd4d9ea4e7234fff66b3f4e541ed677","sha256:69cfacebe47cb6c30e6ea7c9dac8b8e471374e171278c9f398dc6464d7896037"],"state_sha256":"b11025cfaf79da09f9ba3d3948b854a7766f8d6e993d455c6e460a243b5c8bf8"}