{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CB7SBAW3XEJBYWYLIOOWXYN7K7","short_pith_number":"pith:CB7SBAW3","schema_version":"1.0","canonical_sha256":"107f2082dbb9121c5b0b439d6be1bf57ffb98c0dc3c7abd0009ae6514dac2527","source":{"kind":"arxiv","id":"2210.16870","version":1},"attestation_state":"computed","paper":{"title":"A simple, efficient and scalable contrastive masked autoencoder for learning visual representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aaron Maschinot, Aaron Sarna, David Jacobs, Dilip Krishnan, Huiwen Chang, Joshua Robinson, Shlok Mishra","submitted_at":"2022-10-30T16:21:22Z","abstract_excerpt":"We introduce CAN, a simple, efficient and scalable method for self-supervised learning of visual representations. Our framework is a minimal and conceptually clean synthesis of (C) contrastive learning, (A) masked autoencoders, and (N) the noise prediction approach used in diffusion models. The learning mechanisms are complementary to one another: contrastive learning shapes the embedding space across a batch of image samples; masked autoencoders focus on reconstruction of the low-frequency spatial correlations in a single image sample; and noise prediction encourages the reconstruction of the"},"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":"2210.16870","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-30T16:21:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d7749f35cd3e216d27905b81f31b10e8d547c46b513c36d40e6e925ae39c1340","abstract_canon_sha256":"3f3c2c142426d655547c4ab524487890ffe90e670906cdabe89aebcd2dc0c518"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:11:51.736979Z","signature_b64":"q1Z6PqwJCcLvYk+mTFGsCHMznsXEqtSPKACxnRRzJyCAh9liiVv/tHplh/0qpr2yb+0iuEuK3fPw3y9a9B9kCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"107f2082dbb9121c5b0b439d6be1bf57ffb98c0dc3c7abd0009ae6514dac2527","last_reissued_at":"2026-07-05T05:11:51.736552Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:11:51.736552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A simple, efficient and scalable contrastive masked autoencoder for learning visual representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aaron Maschinot, Aaron Sarna, David Jacobs, Dilip Krishnan, Huiwen Chang, Joshua Robinson, Shlok Mishra","submitted_at":"2022-10-30T16:21:22Z","abstract_excerpt":"We introduce CAN, a simple, efficient and scalable method for self-supervised learning of visual representations. Our framework is a minimal and conceptually clean synthesis of (C) contrastive learning, (A) masked autoencoders, and (N) the noise prediction approach used in diffusion models. The learning mechanisms are complementary to one another: contrastive learning shapes the embedding space across a batch of image samples; masked autoencoders focus on reconstruction of the low-frequency spatial correlations in a single image sample; and noise prediction encourages the reconstruction of the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.16870","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/2210.16870/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":"2210.16870","created_at":"2026-07-05T05:11:51.736614+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.16870v1","created_at":"2026-07-05T05:11:51.736614+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.16870","created_at":"2026-07-05T05:11:51.736614+00:00"},{"alias_kind":"pith_short_12","alias_value":"CB7SBAW3XEJB","created_at":"2026-07-05T05:11:51.736614+00:00"},{"alias_kind":"pith_short_16","alias_value":"CB7SBAW3XEJBYWYL","created_at":"2026-07-05T05:11:51.736614+00:00"},{"alias_kind":"pith_short_8","alias_value":"CB7SBAW3","created_at":"2026-07-05T05:11:51.736614+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CB7SBAW3XEJBYWYLIOOWXYN7K7","json":"https://pith.science/pith/CB7SBAW3XEJBYWYLIOOWXYN7K7.json","graph_json":"https://pith.science/api/pith-number/CB7SBAW3XEJBYWYLIOOWXYN7K7/graph.json","events_json":"https://pith.science/api/pith-number/CB7SBAW3XEJBYWYLIOOWXYN7K7/events.json","paper":"https://pith.science/paper/CB7SBAW3"},"agent_actions":{"view_html":"https://pith.science/pith/CB7SBAW3XEJBYWYLIOOWXYN7K7","download_json":"https://pith.science/pith/CB7SBAW3XEJBYWYLIOOWXYN7K7.json","view_paper":"https://pith.science/paper/CB7SBAW3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.16870&json=true","fetch_graph":"https://pith.science/api/pith-number/CB7SBAW3XEJBYWYLIOOWXYN7K7/graph.json","fetch_events":"https://pith.science/api/pith-number/CB7SBAW3XEJBYWYLIOOWXYN7K7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CB7SBAW3XEJBYWYLIOOWXYN7K7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CB7SBAW3XEJBYWYLIOOWXYN7K7/action/storage_attestation","attest_author":"https://pith.science/pith/CB7SBAW3XEJBYWYLIOOWXYN7K7/action/author_attestation","sign_citation":"https://pith.science/pith/CB7SBAW3XEJBYWYLIOOWXYN7K7/action/citation_signature","submit_replication":"https://pith.science/pith/CB7SBAW3XEJBYWYLIOOWXYN7K7/action/replication_record"}},"created_at":"2026-07-05T05:11:51.736614+00:00","updated_at":"2026-07-05T05:11:51.736614+00:00"}