{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GMMOVXDBT547OM4YZBEQIMSJQD","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":"fa0d16a4d425ca7f9bf7912ae21f373b9313e76ee2752bc2450a4320e98e7f95","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-25T17:59:58Z","title_canon_sha256":"e69acd156954ca445929de5946ec77a60f115da0a9d121280b9fcf6f7b732d37"},"schema_version":"1.0","source":{"id":"2208.12262","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.12262","created_at":"2026-07-05T05:59:03Z"},{"alias_kind":"arxiv_version","alias_value":"2208.12262v2","created_at":"2026-07-05T05:59:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.12262","created_at":"2026-07-05T05:59:03Z"},{"alias_kind":"pith_short_12","alias_value":"GMMOVXDBT547","created_at":"2026-07-05T05:59:03Z"},{"alias_kind":"pith_short_16","alias_value":"GMMOVXDBT547OM4Y","created_at":"2026-07-05T05:59:03Z"},{"alias_kind":"pith_short_8","alias_value":"GMMOVXDB","created_at":"2026-07-05T05:59:03Z"}],"graph_snapshots":[{"event_id":"sha256:1e37d11bc7dda863a2e5a3cfbef0d975d35cefcc43791e14d894307c25427d35","target":"graph","created_at":"2026-07-05T05:59:03Z","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/2208.12262/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-25T17:59:58Z","title":"MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.12262","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":"sha256:9dd7601e6b0326c3749d2d1459501e976a0c13dae9f9cb046505f553e17021f6","target":"record","created_at":"2026-07-05T05:59:03Z","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":"fa0d16a4d425ca7f9bf7912ae21f373b9313e76ee2752bc2450a4320e98e7f95","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-25T17:59:58Z","title_canon_sha256":"e69acd156954ca445929de5946ec77a60f115da0a9d121280b9fcf6f7b732d37"},"schema_version":"1.0","source":{"id":"2208.12262","kind":"arxiv","version":2}},"canonical_sha256":"3318eadc619f79f73398c84904324980fd9b15195c653c872d6d91a6ee1e092a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3318eadc619f79f73398c84904324980fd9b15195c653c872d6d91a6ee1e092a","first_computed_at":"2026-07-05T05:59:03.985366Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:59:03.985366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pfQulgwx0f+0SmopsFCCfKDbjSdGSQLlitXG8CZoS/wEu7MfgNBnGbTixGJ9C7MKJc5P9kisqDVjAPQ/vb6JBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:59:03.985790Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.12262","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9dd7601e6b0326c3749d2d1459501e976a0c13dae9f9cb046505f553e17021f6","sha256:1e37d11bc7dda863a2e5a3cfbef0d975d35cefcc43791e14d894307c25427d35"],"state_sha256":"15425ed7fde6a29fab2e34b02bfef5202df34dd68f6e9fae9c900e946d43b0e7"}