{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JGBGL2UZSDW44HLJKLDOWC2SHD","short_pith_number":"pith:JGBGL2UZ","schema_version":"1.0","canonical_sha256":"498265ea9990edce1d6952c6eb0b5238daca1908daa72e00a7f1b57c0acf1c72","source":{"kind":"arxiv","id":"2310.01403","version":2},"attestation_state":"computed","paper":{"title":"CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Change Loy, Lumin Xu, Sheng Jin, Size Wu, Wentao Liu, Wenwei Zhang, Xiangtai Li","submitted_at":"2023-10-02T17:58:52Z","abstract_excerpt":"Open-vocabulary dense prediction tasks including object detection and image segmentation have been advanced by the success of Contrastive Language-Image Pre-training (CLIP). CLIP models, particularly those incorporating vision transformers (ViTs), have exhibited remarkable generalization ability in zero-shot image classification. However, when transferring the vision-language alignment of CLIP from global image representation to local region representation for the open-vocabulary dense prediction tasks, CLIP ViTs suffer from the domain shift from full images to local image regions. In this pap"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2310.01403","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-02T17:58:52Z","cross_cats_sorted":[],"title_canon_sha256":"679dd212ae79b63e54c0e3bb7e9584572bbb421887b2f5bc62d4ba14635fd20a","abstract_canon_sha256":"c4b47745fd31c9eecb97fc4de67f08e7d69e5ae8186108e6b2c02ecbe3a08620"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:54.871586Z","signature_b64":"+yn1Mteuz5FGCaBRp4tsbB++Za4Xa/mrxEw6eq2IsbrHP1r5vHfgsWbcx3pgXnaOJ8NjHYSwySRcLRsBFSOgAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"498265ea9990edce1d6952c6eb0b5238daca1908daa72e00a7f1b57c0acf1c72","last_reissued_at":"2026-07-05T07:36:54.871161Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:54.871161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Change Loy, Lumin Xu, Sheng Jin, Size Wu, Wentao Liu, Wenwei Zhang, Xiangtai Li","submitted_at":"2023-10-02T17:58:52Z","abstract_excerpt":"Open-vocabulary dense prediction tasks including object detection and image segmentation have been advanced by the success of Contrastive Language-Image Pre-training (CLIP). CLIP models, particularly those incorporating vision transformers (ViTs), have exhibited remarkable generalization ability in zero-shot image classification. However, when transferring the vision-language alignment of CLIP from global image representation to local region representation for the open-vocabulary dense prediction tasks, CLIP ViTs suffer from the domain shift from full images to local image regions. In this pap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01403","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/2310.01403/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2310.01403","created_at":"2026-07-05T07:36:54.871219+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.01403v2","created_at":"2026-07-05T07:36:54.871219+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01403","created_at":"2026-07-05T07:36:54.871219+00:00"},{"alias_kind":"pith_short_12","alias_value":"JGBGL2UZSDW4","created_at":"2026-07-05T07:36:54.871219+00:00"},{"alias_kind":"pith_short_16","alias_value":"JGBGL2UZSDW44HLJ","created_at":"2026-07-05T07:36:54.871219+00:00"},{"alias_kind":"pith_short_8","alias_value":"JGBGL2UZ","created_at":"2026-07-05T07:36:54.871219+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07135","citing_title":"Sparse Attention for Dense Open-Vocabulary Prediction in CLIP","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2606.09360","citing_title":"ExDet: Open-Domain Open-Vocabulary Detection with Cross-modal Extrapolation and Rectification","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30342","citing_title":"A Classifier-Agnostic Zero-Shot Adversarial Attack Detection via CLIP","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30342","citing_title":"A Classifier-Agnostic Zero-Shot Adversarial Attack Detection via CLIP","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27116","citing_title":"COVD: Continual Open-Vocabulary Object Detection with Novel Concept Injection","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28271","citing_title":"LV-OSD: Language-Vision-Complementary Open-Set Object Detection","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2502.18816","citing_title":"Grad-ECLIP: Gradient-based Visual and Textual Explanations for CLIP","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16903","citing_title":"WOW-Seg: A Word-free Open World Segmentation Model","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16973","citing_title":"SHED: Style-Homogenized Embedding Alignment for Domain Generalization","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2602.22394","citing_title":"Vision Transformers Need More Than Registers","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12923","citing_title":"Pi-HOC: Pairwise 3D Human-Object Contact Estimation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12923","citing_title":"Pi-HOC: Pairwise 3D Human-Object Contact Estimation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07723","citing_title":"Direct Segmentation without Logits Optimization for Training-Free Open-Vocabulary Semantic Segmentation","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08461","citing_title":"OVS-DINO: Open-Vocabulary Segmentation via Structure-Aligned SAM-DINO with Language Guidance","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08230","citing_title":"Generalization Under Scrutiny: Cross-Domain Detection Progresses, Pitfalls, and Persistent Challenges","ref_index":109,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07415","citing_title":"SubSearch: Intermediate Rewards for Unsupervised Guided Reasoning in Complex Retrieval","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JGBGL2UZSDW44HLJKLDOWC2SHD","json":"https://pith.science/pith/JGBGL2UZSDW44HLJKLDOWC2SHD.json","graph_json":"https://pith.science/api/pith-number/JGBGL2UZSDW44HLJKLDOWC2SHD/graph.json","events_json":"https://pith.science/api/pith-number/JGBGL2UZSDW44HLJKLDOWC2SHD/events.json","paper":"https://pith.science/paper/JGBGL2UZ"},"agent_actions":{"view_html":"https://pith.science/pith/JGBGL2UZSDW44HLJKLDOWC2SHD","download_json":"https://pith.science/pith/JGBGL2UZSDW44HLJKLDOWC2SHD.json","view_paper":"https://pith.science/paper/JGBGL2UZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.01403&json=true","fetch_graph":"https://pith.science/api/pith-number/JGBGL2UZSDW44HLJKLDOWC2SHD/graph.json","fetch_events":"https://pith.science/api/pith-number/JGBGL2UZSDW44HLJKLDOWC2SHD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JGBGL2UZSDW44HLJKLDOWC2SHD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JGBGL2UZSDW44HLJKLDOWC2SHD/action/storage_attestation","attest_author":"https://pith.science/pith/JGBGL2UZSDW44HLJKLDOWC2SHD/action/author_attestation","sign_citation":"https://pith.science/pith/JGBGL2UZSDW44HLJKLDOWC2SHD/action/citation_signature","submit_replication":"https://pith.science/pith/JGBGL2UZSDW44HLJKLDOWC2SHD/action/replication_record"}},"created_at":"2026-07-05T07:36:54.871219+00:00","updated_at":"2026-07-05T07:36:54.871219+00:00"}