{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4WSTEKI73P7YDWIHTXGG577WET","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":"d2daa484a456520262bb492b503c25acd8cdd6c09056106298e1943901ab4228","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-27T04:45:53Z","title_canon_sha256":"eae4bd0e43e4dff9a8232c6ff4daf1062b2305e4e84691ce86962704be7c4643"},"schema_version":"1.0","source":{"id":"2408.14776","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.14776","created_at":"2026-07-05T09:41:01Z"},{"alias_kind":"arxiv_version","alias_value":"2408.14776v2","created_at":"2026-07-05T09:41:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14776","created_at":"2026-07-05T09:41:01Z"},{"alias_kind":"pith_short_12","alias_value":"4WSTEKI73P7Y","created_at":"2026-07-05T09:41:01Z"},{"alias_kind":"pith_short_16","alias_value":"4WSTEKI73P7YDWIH","created_at":"2026-07-05T09:41:01Z"},{"alias_kind":"pith_short_8","alias_value":"4WSTEKI7","created_at":"2026-07-05T09:41:01Z"}],"graph_snapshots":[{"event_id":"sha256:d88afc0e158eea1086cfb14d050a44901f6e599257bb1dbf2cecb16e3e0e2974","target":"graph","created_at":"2026-07-05T09:41:01Z","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/2408.14776/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretrained vision-language models (VLMs), \\eg CLIP, are increasingly used to bridge the gap between open- and close-vocabulary recognition in open-vocabulary image segmentation. As VLMs are generally pretrained with low-resolution images (e.g. $224\\times224$), most previous methods operate only on downscaled images. We question this design as low resolution features often fail to preserve fine details. A typical solution is to employ additional image backbones for high-resolution inputs, but it also introduce significant computation overhead. Therefore, we propose MROVSeg, a multi-resolution t","authors_text":"Bingke Zhu, Jinqiao Wang, Ming Tang, Yingying Chen, Yuanbing Zhu, Yunfang Niu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-27T04:45:53Z","title":"MROVSeg: Breaking the Resolution Curse of Vision-Language Models in Open-Vocabulary Image Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.14776","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:ea78ab3ba02dae54fb12686899020981bfdc8bf0bafe5dcc4d0f3dbda25bc0f1","target":"record","created_at":"2026-07-05T09:41:01Z","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":"d2daa484a456520262bb492b503c25acd8cdd6c09056106298e1943901ab4228","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-27T04:45:53Z","title_canon_sha256":"eae4bd0e43e4dff9a8232c6ff4daf1062b2305e4e84691ce86962704be7c4643"},"schema_version":"1.0","source":{"id":"2408.14776","kind":"arxiv","version":2}},"canonical_sha256":"e5a532291fdbff81d9079dcc6efff624e4d257d9ed51733a613424176c62d817","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e5a532291fdbff81d9079dcc6efff624e4d257d9ed51733a613424176c62d817","first_computed_at":"2026-07-05T09:41:01.029926Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:41:01.029926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m7YxBetjR//HTZQTfoG+VYB8N+FIdKRtKqPTLWmuKXSDQzcjRSbK4M32scQXoEBI9rd3DtqfL2lVwKawaQvaDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:41:01.030395Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.14776","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea78ab3ba02dae54fb12686899020981bfdc8bf0bafe5dcc4d0f3dbda25bc0f1","sha256:d88afc0e158eea1086cfb14d050a44901f6e599257bb1dbf2cecb16e3e0e2974"],"state_sha256":"bbf17471a4f13338f97135a0a2f626c94fae9b5f7112029f1b98d8f4bb798dd9"}