{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:3HKWMK26YKDT4FMRD4XOUJZCXM","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":"f749b03cbe15f96b7a18b83faa1857749fcbc7b6c3d11a96144738452b3f80b6","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-04T18:34:24Z","title_canon_sha256":"02bacf07a5869f71181df563ce1af7430f4387bcb8e3295d4df938e1d53d7ed4"},"schema_version":"1.0","source":{"id":"2112.02399","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.02399","created_at":"2026-07-05T06:39:48Z"},{"alias_kind":"arxiv_version","alias_value":"2112.02399v3","created_at":"2026-07-05T06:39:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.02399","created_at":"2026-07-05T06:39:48Z"},{"alias_kind":"pith_short_12","alias_value":"3HKWMK26YKDT","created_at":"2026-07-05T06:39:48Z"},{"alias_kind":"pith_short_16","alias_value":"3HKWMK26YKDT4FMR","created_at":"2026-07-05T06:39:48Z"},{"alias_kind":"pith_short_8","alias_value":"3HKWMK26","created_at":"2026-07-05T06:39:48Z"}],"graph_snapshots":[{"event_id":"sha256:29a99ac986c6d2093d834bbb3f51c4839404fa1fbcbe4cd334d7232fb158fa5e","target":"graph","created_at":"2026-07-05T06:39:48Z","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/2112.02399/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 drawn increasing attention recently for its transferable visual representation learning. However, due to the semantic gap within datasets, CLIP's pre-trained image-text alignment becomes sub-optimal on downstream tasks, which severely harms its transferring performance. To better adapt the cross-modality embedding space, we propose to enhance CLIP via Visual-guided Texts, named VT-CLIP. Specifically, we guide textual features of different categories to adaptively explore informative regions on the image and aggregate visual features by attenti","authors_text":"Guangnan Zhang, Longtian Qiu, Renrui Zhang, Yafeng Li, Zilu Guo, Ziyao Zeng, Ziyu Guo","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-04T18:34:24Z","title":"VT-CLIP: Enhancing Vision-Language Models with Visual-guided Texts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.02399","kind":"arxiv","version":3},"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":"sha256:38ea5ae4d7bbadcbff07da86c2e7d054dcab993ed6fb9b879838963bd8915ee6","target":"record","created_at":"2026-07-05T06:39:48Z","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":"f749b03cbe15f96b7a18b83faa1857749fcbc7b6c3d11a96144738452b3f80b6","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-04T18:34:24Z","title_canon_sha256":"02bacf07a5869f71181df563ce1af7430f4387bcb8e3295d4df938e1d53d7ed4"},"schema_version":"1.0","source":{"id":"2112.02399","kind":"arxiv","version":3}},"canonical_sha256":"d9d5662b5ec2873e15911f2eea2722bb393670722e8320c8a06915680e9846ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d9d5662b5ec2873e15911f2eea2722bb393670722e8320c8a06915680e9846ff","first_computed_at":"2026-07-05T06:39:48.210576Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:39:48.210576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e7X3GBMA+rWPQEesffBARsQ+PKYSmoUTxXSKURzJleEMSaNSduvtvbFoO46Kouv8u4CgJ08Gf00RqIynzp0LDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:39:48.211007Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.02399","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:38ea5ae4d7bbadcbff07da86c2e7d054dcab993ed6fb9b879838963bd8915ee6","sha256:29a99ac986c6d2093d834bbb3f51c4839404fa1fbcbe4cd334d7232fb158fa5e"],"state_sha256":"af083e29105f22e91ecbec2d89776b39f6d8162c386505387808de7cc22e0eb9"}