{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DBL3B7VQNN65QMV727TK6DJFSK","short_pith_number":"pith:DBL3B7VQ","schema_version":"1.0","canonical_sha256":"1857b0feb06b7dd832bfd7e6af0d259294bffed1b3ff69009fa5123fda6a28fb","source":{"kind":"arxiv","id":"2605.23655","version":1},"attestation_state":"computed","paper":{"title":"CVSearch: Empowering Multimodal LLMs with Cognitive Visual Search for High-Resolution Image Perception","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Bin Chen, Haoqian Kang, Jinpeng Wang, Ke Chen, Liupeng Li, Yaowei Wang, Zhenyu Lu","submitted_at":"2026-05-22T14:07:44Z","abstract_excerpt":"High-resolution (HR) image perception presents a key bottleneck for multimodal large language models (MLLMs). While visual search offers a promising solution, existing methods struggle with the trade-off between coverage and efficiency. Visual expert-assisted search is efficient but prone to blind spots when proposals fail, whereas scan-based search guarantees coverage at the cost of computational redundancy and semantic fragmentation. To address this dilemma, we introduce CVSearch, a training-free adaptive framework that dynamically schedules search strategies via an Assess-then-Search workfl"},"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":"2605.23655","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-22T14:07:44Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"title_canon_sha256":"4f2554845a2fca685900adfa24d043cd5b801f4856301fa079c46a6a60e095ca","abstract_canon_sha256":"fa405f299920e54662aa2128fc9cd73f84f7ac276db0ce987beb40b525890b64"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:02:24.438751Z","signature_b64":"lkhmeHP8QGl2zfo1vsbrgeCCyfOVFEQhXxCxNRPEJuPR+D/aSnMUdK2KLzDFDiCuoYWGhi0egtLNzTtrkW1kAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1857b0feb06b7dd832bfd7e6af0d259294bffed1b3ff69009fa5123fda6a28fb","last_reissued_at":"2026-05-25T02:02:24.438001Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:02:24.438001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CVSearch: Empowering Multimodal LLMs with Cognitive Visual Search for High-Resolution Image Perception","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Bin Chen, Haoqian Kang, Jinpeng Wang, Ke Chen, Liupeng Li, Yaowei Wang, Zhenyu Lu","submitted_at":"2026-05-22T14:07:44Z","abstract_excerpt":"High-resolution (HR) image perception presents a key bottleneck for multimodal large language models (MLLMs). While visual search offers a promising solution, existing methods struggle with the trade-off between coverage and efficiency. Visual expert-assisted search is efficient but prone to blind spots when proposals fail, whereas scan-based search guarantees coverage at the cost of computational redundancy and semantic fragmentation. To address this dilemma, we introduce CVSearch, a training-free adaptive framework that dynamically schedules search strategies via an Assess-then-Search workfl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23655","kind":"arxiv","version":1},"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/2605.23655/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":"2605.23655","created_at":"2026-05-25T02:02:24.438110+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.23655v1","created_at":"2026-05-25T02:02:24.438110+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23655","created_at":"2026-05-25T02:02:24.438110+00:00"},{"alias_kind":"pith_short_12","alias_value":"DBL3B7VQNN65","created_at":"2026-05-25T02:02:24.438110+00:00"},{"alias_kind":"pith_short_16","alias_value":"DBL3B7VQNN65QMV7","created_at":"2026-05-25T02:02:24.438110+00:00"},{"alias_kind":"pith_short_8","alias_value":"DBL3B7VQ","created_at":"2026-05-25T02:02:24.438110+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DBL3B7VQNN65QMV727TK6DJFSK","json":"https://pith.science/pith/DBL3B7VQNN65QMV727TK6DJFSK.json","graph_json":"https://pith.science/api/pith-number/DBL3B7VQNN65QMV727TK6DJFSK/graph.json","events_json":"https://pith.science/api/pith-number/DBL3B7VQNN65QMV727TK6DJFSK/events.json","paper":"https://pith.science/paper/DBL3B7VQ"},"agent_actions":{"view_html":"https://pith.science/pith/DBL3B7VQNN65QMV727TK6DJFSK","download_json":"https://pith.science/pith/DBL3B7VQNN65QMV727TK6DJFSK.json","view_paper":"https://pith.science/paper/DBL3B7VQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.23655&json=true","fetch_graph":"https://pith.science/api/pith-number/DBL3B7VQNN65QMV727TK6DJFSK/graph.json","fetch_events":"https://pith.science/api/pith-number/DBL3B7VQNN65QMV727TK6DJFSK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DBL3B7VQNN65QMV727TK6DJFSK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DBL3B7VQNN65QMV727TK6DJFSK/action/storage_attestation","attest_author":"https://pith.science/pith/DBL3B7VQNN65QMV727TK6DJFSK/action/author_attestation","sign_citation":"https://pith.science/pith/DBL3B7VQNN65QMV727TK6DJFSK/action/citation_signature","submit_replication":"https://pith.science/pith/DBL3B7VQNN65QMV727TK6DJFSK/action/replication_record"}},"created_at":"2026-05-25T02:02:24.438110+00:00","updated_at":"2026-05-25T02:02:24.438110+00:00"}