{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:O4NFWJLN6SFRYPFXQ3FDACS7RH","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":"12d920a953d233c8bc2e365b99537f94ef995ab9710f725fcba13c599177531b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-28T17:09:16Z","title_canon_sha256":"e8af1cecfe38519295c10018dc7088b8bab608da9972ae405463c023c230bcdd"},"schema_version":"1.0","source":{"id":"2607.25993","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.25993","created_at":"2026-07-29T01:26:18Z"},{"alias_kind":"arxiv_version","alias_value":"2607.25993v1","created_at":"2026-07-29T01:26:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.25993","created_at":"2026-07-29T01:26:18Z"},{"alias_kind":"pith_short_12","alias_value":"O4NFWJLN6SFR","created_at":"2026-07-29T01:26:18Z"},{"alias_kind":"pith_short_16","alias_value":"O4NFWJLN6SFRYPFX","created_at":"2026-07-29T01:26:18Z"},{"alias_kind":"pith_short_8","alias_value":"O4NFWJLN","created_at":"2026-07-29T01:26:18Z"}],"graph_snapshots":[{"event_id":"sha256:eae9d2ada03e08aae65f2658ec7737a4ded13e5efa1206804644e7296135f901","target":"graph","created_at":"2026-07-29T01:26:18Z","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/2607.25993/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Ultra-high-resolution (UHR) remote-sensing (RS) imagery provides fine-grained Earth-observation evidence over city-scale scenes, but poses a fundamental challenge for multimodal large language models (MLLMs): task-relevant evidence is often sparse, local, and spatially dispersed across extremely large visual contexts. A natural solution is to equip MLLMs with zoom-in tools for active local inspection. However, through a pilot study on XLRS-Bench, we find that zoom-in is only partially effective: it resolves easy and medium-level tasks with locally recoverable evidence, but saturates on hard ca","authors_text":"Fengxiang Wang, Haiyan Zhao, Haoyu Wang, Jiangnan Huang, Jing Zhang, Junwei Luo, Mingshuo Chen, Wenjing Yang, Yang Shi, Yansheng Li, Yueying Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-28T17:09:16Z","title":"Beyond Zooming: Learning Multi-Tool Visual Reasoning for Ultra-High-Resolution Remote Sensing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.25993","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":"sha256:11bb09af0c78cf377f78476b94d4cdb38434415c70bf2131a1a3e03f578cab21","target":"record","created_at":"2026-07-29T01:26:18Z","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":"12d920a953d233c8bc2e365b99537f94ef995ab9710f725fcba13c599177531b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-28T17:09:16Z","title_canon_sha256":"e8af1cecfe38519295c10018dc7088b8bab608da9972ae405463c023c230bcdd"},"schema_version":"1.0","source":{"id":"2607.25993","kind":"arxiv","version":1}},"canonical_sha256":"771a5b256df48b1c3cb786ca300a5f89da3bcd0a41f0720daa1c8e5668cd3258","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"771a5b256df48b1c3cb786ca300a5f89da3bcd0a41f0720daa1c8e5668cd3258","first_computed_at":"2026-07-29T01:26:18.019779Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-29T01:26:18.019779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BFexLZoXjOK1OH5wjuFKd4FtdI3S0Yk/BTenmJYpFIB2UUAxfvGWft3DgNTxaJfU7tx3aR/K+bPfr/inqUlkDw==","signature_status":"signed_v1","signed_at":"2026-07-29T01:26:18.020642Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.25993","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:11bb09af0c78cf377f78476b94d4cdb38434415c70bf2131a1a3e03f578cab21","sha256:eae9d2ada03e08aae65f2658ec7737a4ded13e5efa1206804644e7296135f901"],"state_sha256":"e5303058ef8789dcc558162493b16497156578fc23ecdb274d6d14988b1baf34"}