{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LDE6LJ2DTDSSAHTWDW6PHQUMDH","short_pith_number":"pith:LDE6LJ2D","schema_version":"1.0","canonical_sha256":"58c9e5a74398e5201e761dbcf3c28c19f6f03a00b8b36094620e44944f6c6e18","source":{"kind":"arxiv","id":"2411.16044","version":4},"attestation_state":"computed","paper":{"title":"ZoomEye: Enhancing Multimodal LLMs with Human-Like Zooming Capabilities through Tree-Based Image Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haozhan Shen, Jianwei Yin, Kangjia Zhao, Mingwei Zhu, Ruochen Xu, Tiancheng Zhao, Zilun Zhang","submitted_at":"2024-11-25T02:15:30Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in vision-language understanding. Recently, with the integration of test-time scaling techniques, these models have also shown strong potential in visual reasoning. However, most existing reasoning approaches remain text-level in nature: MLLMs are prompted to explore various combinations of textual tokens via their underlying language model, while the visual input remains fixed throughout the reasoning process. This paradigm limits the model's ability to fully exploit rich visual information, particularly when d"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2411.16044","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T02:15:30Z","cross_cats_sorted":[],"title_canon_sha256":"f8acd0863499cc809c9ec05cd788109495162b03793847346e8500e68ba30ae4","abstract_canon_sha256":"040948a3fce5e3d2bea76f3f724562e97322bb254f90786919a32f8ab720434e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:37.983291Z","signature_b64":"fjW9SkpYrql7LfRogbS+N8T8so3ecAR9Kb6WGjm/y3ckaD2nsADPlu4gr0KHSBYmQGqgqfkPMqdaQRxrnHalBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58c9e5a74398e5201e761dbcf3c28c19f6f03a00b8b36094620e44944f6c6e18","last_reissued_at":"2026-07-05T12:02:37.982813Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:37.982813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ZoomEye: Enhancing Multimodal LLMs with Human-Like Zooming Capabilities through Tree-Based Image Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haozhan Shen, Jianwei Yin, Kangjia Zhao, Mingwei Zhu, Ruochen Xu, Tiancheng Zhao, Zilun Zhang","submitted_at":"2024-11-25T02:15:30Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in vision-language understanding. Recently, with the integration of test-time scaling techniques, these models have also shown strong potential in visual reasoning. However, most existing reasoning approaches remain text-level in nature: MLLMs are prompted to explore various combinations of textual tokens via their underlying language model, while the visual input remains fixed throughout the reasoning process. This paradigm limits the model's ability to fully exploit rich visual information, particularly when d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16044","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.16044/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2411.16044","created_at":"2026-07-05T12:02:37.982865+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.16044v4","created_at":"2026-07-05T12:02:37.982865+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16044","created_at":"2026-07-05T12:02:37.982865+00:00"},{"alias_kind":"pith_short_12","alias_value":"LDE6LJ2DTDSS","created_at":"2026-07-05T12:02:37.982865+00:00"},{"alias_kind":"pith_short_16","alias_value":"LDE6LJ2DTDSSAHTW","created_at":"2026-07-05T12:02:37.982865+00:00"},{"alias_kind":"pith_short_8","alias_value":"LDE6LJ2D","created_at":"2026-07-05T12:02:37.982865+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26196","citing_title":"From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models","ref_index":136,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21968","citing_title":"Look Before You Zoom: Adaptive Routing for the Resolution-Context Trade-off in Visual RAG","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2510.00054","citing_title":"HiDe: Rethinking The Zoom-IN method in High Resolution MLLMs via Hierarchical Decoupling","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19852","citing_title":"Are Tools Always Beneficial? Learning to Invoke Tools Adaptively for Dual-Mode Multimodal LLM Reasoning","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2509.22746","citing_title":"Mixture-of-Visual-Thoughts: Exploring Context-Adaptive Reasoning Mode Selection for General Visual Reasoning","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09146","citing_title":"Beyond Thinking: Imagining in 360$^\\circ$ for Humanoid Visual Search","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LDE6LJ2DTDSSAHTWDW6PHQUMDH","json":"https://pith.science/pith/LDE6LJ2DTDSSAHTWDW6PHQUMDH.json","graph_json":"https://pith.science/api/pith-number/LDE6LJ2DTDSSAHTWDW6PHQUMDH/graph.json","events_json":"https://pith.science/api/pith-number/LDE6LJ2DTDSSAHTWDW6PHQUMDH/events.json","paper":"https://pith.science/paper/LDE6LJ2D"},"agent_actions":{"view_html":"https://pith.science/pith/LDE6LJ2DTDSSAHTWDW6PHQUMDH","download_json":"https://pith.science/pith/LDE6LJ2DTDSSAHTWDW6PHQUMDH.json","view_paper":"https://pith.science/paper/LDE6LJ2D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.16044&json=true","fetch_graph":"https://pith.science/api/pith-number/LDE6LJ2DTDSSAHTWDW6PHQUMDH/graph.json","fetch_events":"https://pith.science/api/pith-number/LDE6LJ2DTDSSAHTWDW6PHQUMDH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LDE6LJ2DTDSSAHTWDW6PHQUMDH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LDE6LJ2DTDSSAHTWDW6PHQUMDH/action/storage_attestation","attest_author":"https://pith.science/pith/LDE6LJ2DTDSSAHTWDW6PHQUMDH/action/author_attestation","sign_citation":"https://pith.science/pith/LDE6LJ2DTDSSAHTWDW6PHQUMDH/action/citation_signature","submit_replication":"https://pith.science/pith/LDE6LJ2DTDSSAHTWDW6PHQUMDH/action/replication_record"}},"created_at":"2026-07-05T12:02:37.982865+00:00","updated_at":"2026-07-05T12:02:37.982865+00:00"}