{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CDYOOFFC5VSLLZG7NI2KRWDXXM","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":"8cd0c57758bbb44884d893e3a6f15f5ad552e9be1e7b4cb905d6fff9034a3cf8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-21T07:39:29Z","title_canon_sha256":"420c47eb50775fa9505e9b721caaaf7999aed8e4172e2467c19a7f6af1d99402"},"schema_version":"1.0","source":{"id":"2504.14920","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.14920","created_at":"2026-07-05T10:51:53Z"},{"alias_kind":"arxiv_version","alias_value":"2504.14920v1","created_at":"2026-07-05T10:51:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14920","created_at":"2026-07-05T10:51:53Z"},{"alias_kind":"pith_short_12","alias_value":"CDYOOFFC5VSL","created_at":"2026-07-05T10:51:53Z"},{"alias_kind":"pith_short_16","alias_value":"CDYOOFFC5VSLLZG7","created_at":"2026-07-05T10:51:53Z"},{"alias_kind":"pith_short_8","alias_value":"CDYOOFFC","created_at":"2026-07-05T10:51:53Z"}],"graph_snapshots":[{"event_id":"sha256:97dad2d87e01441aec5d472bf1213b6b632b8b61f52bf75d613d8be347ea7249","target":"graph","created_at":"2026-07-05T10:51:53Z","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/2504.14920/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans can effortlessly locate desired objects in cluttered environments, relying on a cognitive mechanism known as visual search to efficiently filter out irrelevant information and focus on task-related regions. Inspired by this process, we propose Dyfo (Dynamic Focus), a training-free dynamic focusing visual search method that enhances fine-grained visual understanding in large multimodal models (LMMs). Unlike existing approaches which require additional modules or data collection, Dyfo leverages a bidirectional interaction between LMMs and visual experts, using a Monte Carlo Tree Search (M","authors_text":"Geng Li, Jinglin Xu, Yunzhen Zhao, Yuxin Peng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-21T07:39:29Z","title":"DyFo: A Training-Free Dynamic Focus Visual Search for Enhancing LMMs in Fine-Grained Visual Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14920","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":"sha256:129abd803b1cf55332c54384318abfde0126eab66fd8b38cb81cd322a34ee85b","target":"record","created_at":"2026-07-05T10:51:53Z","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":"8cd0c57758bbb44884d893e3a6f15f5ad552e9be1e7b4cb905d6fff9034a3cf8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-21T07:39:29Z","title_canon_sha256":"420c47eb50775fa9505e9b721caaaf7999aed8e4172e2467c19a7f6af1d99402"},"schema_version":"1.0","source":{"id":"2504.14920","kind":"arxiv","version":1}},"canonical_sha256":"10f0e714a2ed64b5e4df6a34a8d877bb0f385c916b830a232cf9589847f7cfda","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"10f0e714a2ed64b5e4df6a34a8d877bb0f385c916b830a232cf9589847f7cfda","first_computed_at":"2026-07-05T10:51:53.345632Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:51:53.345632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gxYuwz5OEB0bKunHSwgOpZKFRmov1M8Y8Do+cNhhWFSt+LfL/RX+oRzphhOTRfkJxC+4laV2qO60edU61HOiBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:51:53.346123Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.14920","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:129abd803b1cf55332c54384318abfde0126eab66fd8b38cb81cd322a34ee85b","sha256:97dad2d87e01441aec5d472bf1213b6b632b8b61f52bf75d613d8be347ea7249"],"state_sha256":"b70e8edc9faf805996e96feb7a1d479f31ba18a6c2e18d407e2c4f4c2b39d38b"}