{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:66CTJRRUGLIROJATESDHLERWY7","short_pith_number":"pith:66CTJRRU","schema_version":"1.0","canonical_sha256":"f78534c63432d11724132486759236c7e33ee311201ee6ba4f0f710bf66fa133","source":{"kind":"arxiv","id":"2211.09799","version":1},"attestation_state":"computed","paper":{"title":"CAE v2: Context Autoencoder with CLIP Target","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Errui Ding, Jiahui Chen, Jian Wang, Jimin Pi, Jingdong Wang, Junkun Yuan, Junyu Han, Kun Yao, Qiang Chen, Shumin Han, Xiaodi Wang, Xiaokang Chen, Xinyu Zhang","submitted_at":"2022-11-17T18:58:33Z","abstract_excerpt":"Masked image modeling (MIM) learns visual representation by masking and reconstructing image patches. Applying the reconstruction supervision on the CLIP representation has been proven effective for MIM. However, it is still under-explored how CLIP supervision in MIM influences performance. To investigate strategies for refining the CLIP-targeted MIM, we study two critical elements in MIM, i.e., the supervision position and the mask ratio, and reveal two interesting perspectives, relying on our developed simple pipeline, context autodecoder with CLIP target (CAE v2). Firstly, we observe that t"},"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":"2211.09799","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-17T18:58:33Z","cross_cats_sorted":[],"title_canon_sha256":"0ed04184101696baa02b93b33e3145f3f407ef7796d74fd2e9ad92b82fa74d1e","abstract_canon_sha256":"967e58dc2678f2598935ca62a7029e42a61e512c19eda970c66c66cc81c34931"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:17:06.695077Z","signature_b64":"nT5chpChjltMtCRtki9cB32K+eA/5fYOYDbAMXGQJ9au5ab/GIbtIehdv3jMsjxtZ9SukG73sVBpQr0WyaqWAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f78534c63432d11724132486759236c7e33ee311201ee6ba4f0f710bf66fa133","last_reissued_at":"2026-07-05T05:17:06.694592Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:17:06.694592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CAE v2: Context Autoencoder with CLIP Target","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Errui Ding, Jiahui Chen, Jian Wang, Jimin Pi, Jingdong Wang, Junkun Yuan, Junyu Han, Kun Yao, Qiang Chen, Shumin Han, Xiaodi Wang, Xiaokang Chen, Xinyu Zhang","submitted_at":"2022-11-17T18:58:33Z","abstract_excerpt":"Masked image modeling (MIM) learns visual representation by masking and reconstructing image patches. Applying the reconstruction supervision on the CLIP representation has been proven effective for MIM. However, it is still under-explored how CLIP supervision in MIM influences performance. To investigate strategies for refining the CLIP-targeted MIM, we study two critical elements in MIM, i.e., the supervision position and the mask ratio, and reveal two interesting perspectives, relying on our developed simple pipeline, context autodecoder with CLIP target (CAE v2). Firstly, we observe that t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.09799","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/2211.09799/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":"2211.09799","created_at":"2026-07-05T05:17:06.694653+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.09799v1","created_at":"2026-07-05T05:17:06.694653+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.09799","created_at":"2026-07-05T05:17:06.694653+00:00"},{"alias_kind":"pith_short_12","alias_value":"66CTJRRUGLIR","created_at":"2026-07-05T05:17:06.694653+00:00"},{"alias_kind":"pith_short_16","alias_value":"66CTJRRUGLIROJAT","created_at":"2026-07-05T05:17:06.694653+00:00"},{"alias_kind":"pith_short_8","alias_value":"66CTJRRU","created_at":"2026-07-05T05:17:06.694653+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13288","citing_title":"Cross-Modal Masked Compositional Concept Modeling for Enhancing Visio-Linguistic Compositionality","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31201","citing_title":"ExPLoRe: Expert Patch-Level Loss Routing for Multi-Objective Masked Image Modeling","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/66CTJRRUGLIROJATESDHLERWY7","json":"https://pith.science/pith/66CTJRRUGLIROJATESDHLERWY7.json","graph_json":"https://pith.science/api/pith-number/66CTJRRUGLIROJATESDHLERWY7/graph.json","events_json":"https://pith.science/api/pith-number/66CTJRRUGLIROJATESDHLERWY7/events.json","paper":"https://pith.science/paper/66CTJRRU"},"agent_actions":{"view_html":"https://pith.science/pith/66CTJRRUGLIROJATESDHLERWY7","download_json":"https://pith.science/pith/66CTJRRUGLIROJATESDHLERWY7.json","view_paper":"https://pith.science/paper/66CTJRRU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.09799&json=true","fetch_graph":"https://pith.science/api/pith-number/66CTJRRUGLIROJATESDHLERWY7/graph.json","fetch_events":"https://pith.science/api/pith-number/66CTJRRUGLIROJATESDHLERWY7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/66CTJRRUGLIROJATESDHLERWY7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/66CTJRRUGLIROJATESDHLERWY7/action/storage_attestation","attest_author":"https://pith.science/pith/66CTJRRUGLIROJATESDHLERWY7/action/author_attestation","sign_citation":"https://pith.science/pith/66CTJRRUGLIROJATESDHLERWY7/action/citation_signature","submit_replication":"https://pith.science/pith/66CTJRRUGLIROJATESDHLERWY7/action/replication_record"}},"created_at":"2026-07-05T05:17:06.694653+00:00","updated_at":"2026-07-05T05:17:06.694653+00:00"}