{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MPW2WC7J3STYDB3XTT3MGKSZCE","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":"9a169005ab4cc98a77bd1cc160f2609cf698cccbfb5fa0547ce86ba7f0a9cebf","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-03T04:17:12Z","title_canon_sha256":"8cdb2a573f3c14003610cd67828f052e00ec263624971f4c0291a31e2accd1fc"},"schema_version":"1.0","source":{"id":"2406.00977","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.00977","created_at":"2026-07-05T09:20:23Z"},{"alias_kind":"arxiv_version","alias_value":"2406.00977v2","created_at":"2026-07-05T09:20:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00977","created_at":"2026-07-05T09:20:23Z"},{"alias_kind":"pith_short_12","alias_value":"MPW2WC7J3STY","created_at":"2026-07-05T09:20:23Z"},{"alias_kind":"pith_short_16","alias_value":"MPW2WC7J3STYDB3X","created_at":"2026-07-05T09:20:23Z"},{"alias_kind":"pith_short_8","alias_value":"MPW2WC7J","created_at":"2026-07-05T09:20:23Z"}],"graph_snapshots":[{"event_id":"sha256:6fa45e8c52f6b03cfeff1fdd0f0fa455627c46a7f2310fcc33191b9d5de34359","target":"graph","created_at":"2026-07-05T09:20:23Z","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/2406.00977/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in vision-language models (VLMs) have demonstrated the advantages of processing images at higher resolutions and utilizing multi-crop features to preserve native resolution details. However, despite these improvements, existing vision transformers (ViTs) still struggle to capture fine-grained details from less prominent objects, charts, and embedded text, limiting their effectiveness in certain tasks. In this paper, we extend recent high-resolution and multi-crop techniques by not only preserving the native resolution, but zooming in beyond it and extracting features from a lar","authors_text":"Ben Athiwaratkun, Ian Covert, James Zou, Kezhen Chen, Rahul Chalamala, Rahul Thapa, Shuaiwen Leon Song","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-03T04:17:12Z","title":"Dragonfly: Multi-Resolution Zoom-In Encoding Enhances Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00977","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":"sha256:54e67f9041bb052ed3056a4bef0c3ce2735f369e13d5a01c230a26fa5764ad21","target":"record","created_at":"2026-07-05T09:20:23Z","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":"9a169005ab4cc98a77bd1cc160f2609cf698cccbfb5fa0547ce86ba7f0a9cebf","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-03T04:17:12Z","title_canon_sha256":"8cdb2a573f3c14003610cd67828f052e00ec263624971f4c0291a31e2accd1fc"},"schema_version":"1.0","source":{"id":"2406.00977","kind":"arxiv","version":2}},"canonical_sha256":"63edab0be9dca78187779cf6c32a5911263d83e2a74b87b252ed6630569cb16c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63edab0be9dca78187779cf6c32a5911263d83e2a74b87b252ed6630569cb16c","first_computed_at":"2026-07-05T09:20:23.590468Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:20:23.590468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q05Pq5EDXLSw7gDlXjtM8UWUJn1VpybiHvaouHoroNOGS7P5dHrmzLp0oBqkGUKQBIaz3HDT//Nuk9JzP+LSAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:20:23.591007Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.00977","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:54e67f9041bb052ed3056a4bef0c3ce2735f369e13d5a01c230a26fa5764ad21","sha256:6fa45e8c52f6b03cfeff1fdd0f0fa455627c46a7f2310fcc33191b9d5de34359"],"state_sha256":"6bdd2f2500756ef8902a26060321d3b21b1d5883d82d4ccf91e2a63f8b572097"}