{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GMMOVXDBT547OM4YZBEQIMSJQD","short_pith_number":"pith:GMMOVXDB","schema_version":"1.0","canonical_sha256":"3318eadc619f79f73398c84904324980fd9b15195c653c872d6d91a6ee1e092a","source":{"kind":"arxiv","id":"2208.12262","version":2},"attestation_state":"computed","paper":{"title":"MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong Chen, Dongdong Chen, Fang Wen, Hao Yang, Jianmin Bao, Lu Yuan, Ming Zeng, Nenghai Yu, Ting Zhang, Weiming Zhang, Xiaoyi Dong, Yinglin Zheng","submitted_at":"2022-08-25T17:59:58Z","abstract_excerpt":"This paper presents a simple yet effective framework MaskCLIP, which incorporates a newly proposed masked self-distillation into contrastive language-image pretraining. The core idea of masked self-distillation is to distill representation from a full image to the representation predicted from a masked image. Such incorporation enjoys two vital benefits. First, masked self-distillation targets local patch representation learning, which is complementary to vision-language contrastive focusing on text-related representation. Second, masked self-distillation is also consistent with vision-languag"},"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":"2208.12262","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-25T17:59:58Z","cross_cats_sorted":[],"title_canon_sha256":"e69acd156954ca445929de5946ec77a60f115da0a9d121280b9fcf6f7b732d37","abstract_canon_sha256":"fa0d16a4d425ca7f9bf7912ae21f373b9313e76ee2752bc2450a4320e98e7f95"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:59:03.985790Z","signature_b64":"pfQulgwx0f+0SmopsFCCfKDbjSdGSQLlitXG8CZoS/wEu7MfgNBnGbTixGJ9C7MKJc5P9kisqDVjAPQ/vb6JBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3318eadc619f79f73398c84904324980fd9b15195c653c872d6d91a6ee1e092a","last_reissued_at":"2026-07-05T05:59:03.985366Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:59:03.985366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong Chen, Dongdong Chen, Fang Wen, Hao Yang, Jianmin Bao, Lu Yuan, Ming Zeng, Nenghai Yu, Ting Zhang, Weiming Zhang, Xiaoyi Dong, Yinglin Zheng","submitted_at":"2022-08-25T17:59:58Z","abstract_excerpt":"This paper presents a simple yet effective framework MaskCLIP, which incorporates a newly proposed masked self-distillation into contrastive language-image pretraining. The core idea of masked self-distillation is to distill representation from a full image to the representation predicted from a masked image. Such incorporation enjoys two vital benefits. First, masked self-distillation targets local patch representation learning, which is complementary to vision-language contrastive focusing on text-related representation. Second, masked self-distillation is also consistent with vision-languag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.12262","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/2208.12262/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":"2208.12262","created_at":"2026-07-05T05:59:03.985425+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.12262v2","created_at":"2026-07-05T05:59:03.985425+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.12262","created_at":"2026-07-05T05:59:03.985425+00:00"},{"alias_kind":"pith_short_12","alias_value":"GMMOVXDBT547","created_at":"2026-07-05T05:59:03.985425+00:00"},{"alias_kind":"pith_short_16","alias_value":"GMMOVXDBT547OM4Y","created_at":"2026-07-05T05:59:03.985425+00:00"},{"alias_kind":"pith_short_8","alias_value":"GMMOVXDB","created_at":"2026-07-05T05:59:03.985425+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.16329","citing_title":"sDREAMER: Self-distilled Mixture-of-Modality-Experts Transformer for Automatic Sleep Staging","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GMMOVXDBT547OM4YZBEQIMSJQD","json":"https://pith.science/pith/GMMOVXDBT547OM4YZBEQIMSJQD.json","graph_json":"https://pith.science/api/pith-number/GMMOVXDBT547OM4YZBEQIMSJQD/graph.json","events_json":"https://pith.science/api/pith-number/GMMOVXDBT547OM4YZBEQIMSJQD/events.json","paper":"https://pith.science/paper/GMMOVXDB"},"agent_actions":{"view_html":"https://pith.science/pith/GMMOVXDBT547OM4YZBEQIMSJQD","download_json":"https://pith.science/pith/GMMOVXDBT547OM4YZBEQIMSJQD.json","view_paper":"https://pith.science/paper/GMMOVXDB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.12262&json=true","fetch_graph":"https://pith.science/api/pith-number/GMMOVXDBT547OM4YZBEQIMSJQD/graph.json","fetch_events":"https://pith.science/api/pith-number/GMMOVXDBT547OM4YZBEQIMSJQD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GMMOVXDBT547OM4YZBEQIMSJQD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GMMOVXDBT547OM4YZBEQIMSJQD/action/storage_attestation","attest_author":"https://pith.science/pith/GMMOVXDBT547OM4YZBEQIMSJQD/action/author_attestation","sign_citation":"https://pith.science/pith/GMMOVXDBT547OM4YZBEQIMSJQD/action/citation_signature","submit_replication":"https://pith.science/pith/GMMOVXDBT547OM4YZBEQIMSJQD/action/replication_record"}},"created_at":"2026-07-05T05:59:03.985425+00:00","updated_at":"2026-07-05T05:59:03.985425+00:00"}