{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AXMK6UAAELJC3FEUBBRCF3JODZ","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":"12fcfa6b283d531d3f29ac2b467309f278edfb66782fd1d71ae1faf5a4087ae9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-25T15:01:41Z","title_canon_sha256":"8a6a46f97bafdf31678ea9ced97c14d6b2224cdad46a6799d60e7ce75f6ab5a6"},"schema_version":"1.0","source":{"id":"2504.18406","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.18406","created_at":"2026-07-05T10:55:35Z"},{"alias_kind":"arxiv_version","alias_value":"2504.18406v2","created_at":"2026-07-05T10:55:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.18406","created_at":"2026-07-05T10:55:35Z"},{"alias_kind":"pith_short_12","alias_value":"AXMK6UAAELJC","created_at":"2026-07-05T10:55:35Z"},{"alias_kind":"pith_short_16","alias_value":"AXMK6UAAELJC3FEU","created_at":"2026-07-05T10:55:35Z"},{"alias_kind":"pith_short_8","alias_value":"AXMK6UAA","created_at":"2026-07-05T10:55:35Z"}],"graph_snapshots":[{"event_id":"sha256:4332eeff919b2356f37f13a2a195754f4775878ebd1c61ab3782432d0a812dd8","target":"graph","created_at":"2026-07-05T10:55:35Z","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/2504.18406/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"High-resolution image (HRI) understanding aims to process images with a large number of pixels, such as pathological images and agricultural aerial images, both of which can exceed 1 million pixels. Vision Large Language Models (VLMs) can allegedly handle HRIs, however, there is a lack of a comprehensive benchmark for VLMs to evaluate HRI understanding. To address this gap, we introduce HRScene, a novel unified benchmark for HRI understanding with rich scenes. HRScene incorporates 25 real-world datasets and 2 synthetic diagnostic datasets with resolutions ranging from 1,024 $\\times$ 1,024 to 3","authors_text":"Aashrith Madasu, Avitej Iyer, Hao Zhou, Nan Zhang, Peng Shi, Ranran Haoran Zhang, Renze Lou, Rui Zhang, Ryo Kamoi, Sarkar Snigdha Sarathi Das, Shu Zhao, Vipul Gupta, Wenliang Zheng, Wenpeng Yin, Xiaoxin Lu, Yusen Zhang, Zhuoyang Zou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-25T15:01:41Z","title":"HRScene: How Far Are VLMs from Effective High-Resolution Image Understanding?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.18406","kind":"arxiv","version":2},"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:c83feb52d35c55e0915eae8c0b88f3bf81dce7b5290d142b697ec96de021f7fd","target":"record","created_at":"2026-07-05T10:55:35Z","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":"12fcfa6b283d531d3f29ac2b467309f278edfb66782fd1d71ae1faf5a4087ae9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-25T15:01:41Z","title_canon_sha256":"8a6a46f97bafdf31678ea9ced97c14d6b2224cdad46a6799d60e7ce75f6ab5a6"},"schema_version":"1.0","source":{"id":"2504.18406","kind":"arxiv","version":2}},"canonical_sha256":"05d8af500022d22d9494086222ed2e1e5e1857ef22619836b2186ddcd51e2769","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"05d8af500022d22d9494086222ed2e1e5e1857ef22619836b2186ddcd51e2769","first_computed_at":"2026-07-05T10:55:35.201433Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:55:35.201433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"npTThvhunVaE4MGWNLWez2KiCXU6h5qnP4rEi1lcZiO5SSGlwhTaOQ1pUU/WH2ZeOb2QxArjDRzY2dxT5DD/Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:55:35.202585Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.18406","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c83feb52d35c55e0915eae8c0b88f3bf81dce7b5290d142b697ec96de021f7fd","sha256:4332eeff919b2356f37f13a2a195754f4775878ebd1c61ab3782432d0a812dd8"],"state_sha256":"38e5d5eeecc8d5fa6654054b6b61ad0508a3a17f225b549e284d656c50339b6b"}