{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XBGMKSBZJI373HQ53WEOEO3CZT","short_pith_number":"pith:XBGMKSBZ","canonical_record":{"source":{"id":"2505.24517","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T12:29:38Z","cross_cats_sorted":[],"title_canon_sha256":"b43c392b6cef70357f767f3067999610a4a5465f249479ee78bafadc4d204267","abstract_canon_sha256":"d8a22fc66c86978c52e76148fc14c56428f212838fe3bd503f248e34ae74b31c"},"schema_version":"1.0"},"canonical_sha256":"b84cc548394a37fd9e1ddd88e23b62ccc6eafde45dccee6a4c2fe47fc0b464b3","source":{"kind":"arxiv","id":"2505.24517","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24517","created_at":"2026-07-05T11:12:51Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24517v1","created_at":"2026-07-05T11:12:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24517","created_at":"2026-07-05T11:12:51Z"},{"alias_kind":"pith_short_12","alias_value":"XBGMKSBZJI37","created_at":"2026-07-05T11:12:51Z"},{"alias_kind":"pith_short_16","alias_value":"XBGMKSBZJI373HQ5","created_at":"2026-07-05T11:12:51Z"},{"alias_kind":"pith_short_8","alias_value":"XBGMKSBZ","created_at":"2026-07-05T11:12:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XBGMKSBZJI373HQ53WEOEO3CZT","target":"record","payload":{"canonical_record":{"source":{"id":"2505.24517","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T12:29:38Z","cross_cats_sorted":[],"title_canon_sha256":"b43c392b6cef70357f767f3067999610a4a5465f249479ee78bafadc4d204267","abstract_canon_sha256":"d8a22fc66c86978c52e76148fc14c56428f212838fe3bd503f248e34ae74b31c"},"schema_version":"1.0"},"canonical_sha256":"b84cc548394a37fd9e1ddd88e23b62ccc6eafde45dccee6a4c2fe47fc0b464b3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:51.593145Z","signature_b64":"xpPygi43nEsyetgGGvF/XhW6z+Hcj5vpxkAMseHQ8KKcCO/fMAF2FS6sqjyyzjMxbt/q17oBInYAFafbZlHfCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b84cc548394a37fd9e1ddd88e23b62ccc6eafde45dccee6a4c2fe47fc0b464b3","last_reissued_at":"2026-07-05T11:12:51.592567Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:51.592567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.24517","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:12:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UKtkSfQGFQrYWsepAw+Kb7W12HpYtT7AbkNgPZnpF+rQJ4f1lRi9+hqREWRqSnM0m7elB8IOIuxt2bIOq1XbDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T23:34:39.807995Z"},"content_sha256":"5fbbd7a2ae0336cd6016b300c07ec313b67525c37d93643e98b90cae447b4d28","schema_version":"1.0","event_id":"sha256:5fbbd7a2ae0336cd6016b300c07ec313b67525c37d93643e98b90cae447b4d28"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XBGMKSBZJI373HQ53WEOEO3CZT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"un$^2$CLIP: Improving CLIP's Visual Detail Capturing Ability via Inverting unCLIP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hong Chang, Jiahe Zhao, Ruibing Hou, Shiguang Shan, Xilin Chen, Yinqi Li","submitted_at":"2025-05-30T12:29:38Z","abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) has become a foundation model and has been applied to various vision and multimodal tasks. However, recent works indicate that CLIP falls short in distinguishing detailed differences in images and shows suboptimal performance on dense-prediction and vision-centric multimodal tasks. Therefore, this work focuses on improving existing CLIP models, aiming to capture as many visual details in images as possible. We find that a specific type of generative models, unCLIP, provides a suitable framework for achieving our goal. Specifically, unCLIP trains a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24517","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/2505.24517/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":"2026-07-05T11:12:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zJMgP+kkn6x695CG7YFobH9qQBStK6r5+mmNXpoQ67Rkvppa3MaagK/XvtJsoBwQ8LTbE8ToXUZW3UylCy7lAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T23:34:39.808912Z"},"content_sha256":"701552b548f989c8485c89e9ae041a28ad20afaa013b8515662d53554efbdeba","schema_version":"1.0","event_id":"sha256:701552b548f989c8485c89e9ae041a28ad20afaa013b8515662d53554efbdeba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XBGMKSBZJI373HQ53WEOEO3CZT/bundle.json","state_url":"https://pith.science/pith/XBGMKSBZJI373HQ53WEOEO3CZT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XBGMKSBZJI373HQ53WEOEO3CZT/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":"2026-08-18T23:34:39Z","links":{"resolver":"https://pith.science/pith/XBGMKSBZJI373HQ53WEOEO3CZT","bundle":"https://pith.science/pith/XBGMKSBZJI373HQ53WEOEO3CZT/bundle.json","state":"https://pith.science/pith/XBGMKSBZJI373HQ53WEOEO3CZT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XBGMKSBZJI373HQ53WEOEO3CZT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XBGMKSBZJI373HQ53WEOEO3CZT","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":"d8a22fc66c86978c52e76148fc14c56428f212838fe3bd503f248e34ae74b31c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T12:29:38Z","title_canon_sha256":"b43c392b6cef70357f767f3067999610a4a5465f249479ee78bafadc4d204267"},"schema_version":"1.0","source":{"id":"2505.24517","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24517","created_at":"2026-07-05T11:12:51Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24517v1","created_at":"2026-07-05T11:12:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24517","created_at":"2026-07-05T11:12:51Z"},{"alias_kind":"pith_short_12","alias_value":"XBGMKSBZJI37","created_at":"2026-07-05T11:12:51Z"},{"alias_kind":"pith_short_16","alias_value":"XBGMKSBZJI373HQ5","created_at":"2026-07-05T11:12:51Z"},{"alias_kind":"pith_short_8","alias_value":"XBGMKSBZ","created_at":"2026-07-05T11:12:51Z"}],"graph_snapshots":[{"event_id":"sha256:701552b548f989c8485c89e9ae041a28ad20afaa013b8515662d53554efbdeba","target":"graph","created_at":"2026-07-05T11:12:51Z","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/2505.24517/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) has become a foundation model and has been applied to various vision and multimodal tasks. However, recent works indicate that CLIP falls short in distinguishing detailed differences in images and shows suboptimal performance on dense-prediction and vision-centric multimodal tasks. Therefore, this work focuses on improving existing CLIP models, aiming to capture as many visual details in images as possible. We find that a specific type of generative models, unCLIP, provides a suitable framework for achieving our goal. Specifically, unCLIP trains a","authors_text":"Hong Chang, Jiahe Zhao, Ruibing Hou, Shiguang Shan, Xilin Chen, Yinqi Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T12:29:38Z","title":"un$^2$CLIP: Improving CLIP's Visual Detail Capturing Ability via Inverting unCLIP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24517","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":"sha256:5fbbd7a2ae0336cd6016b300c07ec313b67525c37d93643e98b90cae447b4d28","target":"record","created_at":"2026-07-05T11:12:51Z","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":"d8a22fc66c86978c52e76148fc14c56428f212838fe3bd503f248e34ae74b31c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T12:29:38Z","title_canon_sha256":"b43c392b6cef70357f767f3067999610a4a5465f249479ee78bafadc4d204267"},"schema_version":"1.0","source":{"id":"2505.24517","kind":"arxiv","version":1}},"canonical_sha256":"b84cc548394a37fd9e1ddd88e23b62ccc6eafde45dccee6a4c2fe47fc0b464b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b84cc548394a37fd9e1ddd88e23b62ccc6eafde45dccee6a4c2fe47fc0b464b3","first_computed_at":"2026-07-05T11:12:51.592567Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:51.592567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xpPygi43nEsyetgGGvF/XhW6z+Hcj5vpxkAMseHQ8KKcCO/fMAF2FS6sqjyyzjMxbt/q17oBInYAFafbZlHfCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:51.593145Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.24517","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5fbbd7a2ae0336cd6016b300c07ec313b67525c37d93643e98b90cae447b4d28","sha256:701552b548f989c8485c89e9ae041a28ad20afaa013b8515662d53554efbdeba"],"state_sha256":"ef0659a0cf469d558ff0be0e3232cfcabe520061a8075fc8d9f2fea38ae94eda"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q5v/6VYU7GI+6a2hScGsvzLrxbWBmQz43lTTfC/piliAs+1q/9YQRgOLOoh97AG1lMrB5qumYa7U5f2jDempCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T23:34:39.814297Z","bundle_sha256":"c3a56fbc00ba657e52dad4d609f1bc87cf81e2e64ad2fe3d8161d27ba51cce01"}}