{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4WSTEKI73P7YDWIHTXGG577WET","short_pith_number":"pith:4WSTEKI7","canonical_record":{"source":{"id":"2408.14776","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-27T04:45:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eae4bd0e43e4dff9a8232c6ff4daf1062b2305e4e84691ce86962704be7c4643","abstract_canon_sha256":"d2daa484a456520262bb492b503c25acd8cdd6c09056106298e1943901ab4228"},"schema_version":"1.0"},"canonical_sha256":"e5a532291fdbff81d9079dcc6efff624e4d257d9ed51733a613424176c62d817","source":{"kind":"arxiv","id":"2408.14776","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4WSTEKI73P7YDWIHTXGG577WET","target":"record","payload":{"canonical_record":{"source":{"id":"2408.14776","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-27T04:45:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eae4bd0e43e4dff9a8232c6ff4daf1062b2305e4e84691ce86962704be7c4643","abstract_canon_sha256":"d2daa484a456520262bb492b503c25acd8cdd6c09056106298e1943901ab4228"},"schema_version":"1.0"},"canonical_sha256":"e5a532291fdbff81d9079dcc6efff624e4d257d9ed51733a613424176c62d817","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:01.030395Z","signature_b64":"m7YxBetjR//HTZQTfoG+VYB8N+FIdKRtKqPTLWmuKXSDQzcjRSbK4M32scQXoEBI9rd3DtqfL2lVwKawaQvaDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5a532291fdbff81d9079dcc6efff624e4d257d9ed51733a613424176c62d817","last_reissued_at":"2026-07-05T09:41:01.029926Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:01.029926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.14776","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:41:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4E/R8UIRWoJKXaJrlZDJa5ECnIKcSclkZJq0/8Q9jZEbOiaAkKAwS99iREn1Pa7n3C/Y+pRK4EEoKiKv0mTJDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:41:16.609078Z"},"content_sha256":"ea78ab3ba02dae54fb12686899020981bfdc8bf0bafe5dcc4d0f3dbda25bc0f1","schema_version":"1.0","event_id":"sha256:ea78ab3ba02dae54fb12686899020981bfdc8bf0bafe5dcc4d0f3dbda25bc0f1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4WSTEKI73P7YDWIHTXGG577WET","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MROVSeg: Breaking the Resolution Curse of Vision-Language Models in Open-Vocabulary Image Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bingke Zhu, Jinqiao Wang, Ming Tang, Yingying Chen, Yuanbing Zhu, Yunfang Niu","submitted_at":"2024-08-27T04:45:53Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.14776","kind":"arxiv","version":2},"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/2408.14776/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:41:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bkwBemHW0A6tJlNx9I4uKkTvfvQO9uksiohuM+4p2sc7jM9PeK+0OSTAWtXKX0DpOrXSUitQ9DZ8vVDXiufEBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:41:16.609500Z"},"content_sha256":"d88afc0e158eea1086cfb14d050a44901f6e599257bb1dbf2cecb16e3e0e2974","schema_version":"1.0","event_id":"sha256:d88afc0e158eea1086cfb14d050a44901f6e599257bb1dbf2cecb16e3e0e2974"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4WSTEKI73P7YDWIHTXGG577WET/bundle.json","state_url":"https://pith.science/pith/4WSTEKI73P7YDWIHTXGG577WET/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4WSTEKI73P7YDWIHTXGG577WET/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T04:41:16Z","links":{"resolver":"https://pith.science/pith/4WSTEKI73P7YDWIHTXGG577WET","bundle":"https://pith.science/pith/4WSTEKI73P7YDWIHTXGG577WET/bundle.json","state":"https://pith.science/pith/4WSTEKI73P7YDWIHTXGG577WET/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4WSTEKI73P7YDWIHTXGG577WET/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4jbfObuEbVIll3q3Hpu2actjvCTxfre0oUAV1IQAvto2cdRIc/Nr7GZLTvNFcYzNpEg81MYr8m/sd/benAzODA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T04:41:16.612611Z","bundle_sha256":"3bd8dd2cab190c48c446b1b605f116f6c16145d8d0b0fb10e804f1293ac484bc"}}