{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HPS7QFEY2CUXWUP2IQ2QXBPUP3","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":"c814a075428bd1e658d13bf3ddac661a1b54c08bc256338c8112efcf3ab40b30","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T13:32:35Z","title_canon_sha256":"51a31485d90e2297ae94720bb2ca66ac000dab6ea70234814981af721f8198bf"},"schema_version":"1.0","source":{"id":"2506.01663","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01663","created_at":"2026-07-05T11:51:27Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01663v2","created_at":"2026-07-05T11:51:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01663","created_at":"2026-07-05T11:51:27Z"},{"alias_kind":"pith_short_12","alias_value":"HPS7QFEY2CUX","created_at":"2026-07-05T11:51:27Z"},{"alias_kind":"pith_short_16","alias_value":"HPS7QFEY2CUXWUP2","created_at":"2026-07-05T11:51:27Z"},{"alias_kind":"pith_short_8","alias_value":"HPS7QFEY","created_at":"2026-07-05T11:51:27Z"}],"graph_snapshots":[{"event_id":"sha256:d3fd0039f871807a185d16258633a3cc319cb0d77cac959cf93fb561ea86ed4e","target":"graph","created_at":"2026-07-05T11:51:27Z","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/2506.01663/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLM) often struggle to interpret high-resolution images accurately, where fine-grained details are crucial for complex visual understanding. We introduce Zoom-Refine, a novel training-free method that enhances MLLM capabilities to address this issue. Zoom-Refine operates through a synergistic process of \\textit{Localized Zoom} and \\textit{Self-Refinement}. In the \\textit{Localized Zoom} step, Zoom-Refine leverages the MLLM to provide a preliminary response to an input query and identifies the most task-relevant image region by predicting its bounding box coor","authors_text":"Dayan Guan, Xuan Yu, Yanfeng Gu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T13:32:35Z","title":"Zoom-Refine: Boosting High-Resolution Multimodal Understanding via Localized Zoom and Self-Refinement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01663","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:b26bb6bad9e3a0c110403a62bea37e310ef9560452a8e4dc47fcaa852ac53db2","target":"record","created_at":"2026-07-05T11:51:27Z","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":"c814a075428bd1e658d13bf3ddac661a1b54c08bc256338c8112efcf3ab40b30","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T13:32:35Z","title_canon_sha256":"51a31485d90e2297ae94720bb2ca66ac000dab6ea70234814981af721f8198bf"},"schema_version":"1.0","source":{"id":"2506.01663","kind":"arxiv","version":2}},"canonical_sha256":"3be5f81498d0a97b51fa44350b85f47ef3c3971be372ec0ac7cc2f290bd33a83","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3be5f81498d0a97b51fa44350b85f47ef3c3971be372ec0ac7cc2f290bd33a83","first_computed_at":"2026-07-05T11:51:27.975645Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:51:27.975645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JE3Biks67cKCiZ7Hpr46zYa3SXEjQJxCrkL8MQBWQZf99GU/Z2pd+7DPbFJiGbb98PU2gSxlikZB7LxY5Cd0Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:51:27.976131Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.01663","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b26bb6bad9e3a0c110403a62bea37e310ef9560452a8e4dc47fcaa852ac53db2","sha256:d3fd0039f871807a185d16258633a3cc319cb0d77cac959cf93fb561ea86ed4e"],"state_sha256":"d478ffa74e6145e957451a9a3719ca0e7eb24f6d523057724dad03ee7e462eac"}