{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5WQDIGR43CGMERYL6XJH4PWRDY","short_pith_number":"pith:5WQDIGR4","schema_version":"1.0","canonical_sha256":"eda0341a3cd88cc2470bf5d27e3ed11e18ae2ae521f7ebf003457b2e2686634d","source":{"kind":"arxiv","id":"2404.10242","version":1},"attestation_state":"computed","paper":{"title":"Masked Autoencoders for Microscopy are Scalable Learners of Cellular Biology","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ayla Khan, Ben Mabey, Berton Earnshaw, Chi Vicky Cheng, Dominique Beaini, Jess Leung, Jia Balakrishnan, Kian Kenyon-Dean, Kristen Morse, Maciej Sypetkowski, Maryam Fallah, Maureen Makes, Oren Kraus, Peter McLean, Saber Saberian, Safiye Celik, Vasudev Sharma","submitted_at":"2024-04-16T02:42:06Z","abstract_excerpt":"Featurizing microscopy images for use in biological research remains a significant challenge, especially for large-scale experiments spanning millions of images. This work explores the scaling properties of weakly supervised classifiers and self-supervised masked autoencoders (MAEs) when training with increasingly larger model backbones and microscopy datasets. Our results show that ViT-based MAEs outperform weakly supervised classifiers on a variety of tasks, achieving as much as a 11.5% relative improvement when recalling known biological relationships curated from public databases. Addition"},"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":"2404.10242","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-16T02:42:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9c0bc0571483576491c29d116e9077a2c4b9d69b6f2e91807b8fa6e9e1372b40","abstract_canon_sha256":"0b13323781900edf31c709bcd6802210b94ecba77e1aa5f5487c01df63777fc9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:08.830701Z","signature_b64":"nTJrgGGpGd+fFpHybfRiYSSPpgD5dc+Sdf8KieKHVwpmuLb57geiPVeTInN0gJ5sbKswrZzEu43Kk1cm69uWAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eda0341a3cd88cc2470bf5d27e3ed11e18ae2ae521f7ebf003457b2e2686634d","last_reissued_at":"2026-07-05T11:13:08.830140Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:08.830140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Masked Autoencoders for Microscopy are Scalable Learners of Cellular Biology","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ayla Khan, Ben Mabey, Berton Earnshaw, Chi Vicky Cheng, Dominique Beaini, Jess Leung, Jia Balakrishnan, Kian Kenyon-Dean, Kristen Morse, Maciej Sypetkowski, Maryam Fallah, Maureen Makes, Oren Kraus, Peter McLean, Saber Saberian, Safiye Celik, Vasudev Sharma","submitted_at":"2024-04-16T02:42:06Z","abstract_excerpt":"Featurizing microscopy images for use in biological research remains a significant challenge, especially for large-scale experiments spanning millions of images. This work explores the scaling properties of weakly supervised classifiers and self-supervised masked autoencoders (MAEs) when training with increasingly larger model backbones and microscopy datasets. Our results show that ViT-based MAEs outperform weakly supervised classifiers on a variety of tasks, achieving as much as a 11.5% relative improvement when recalling known biological relationships curated from public databases. Addition"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10242","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/2404.10242/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":"2404.10242","created_at":"2026-07-05T11:13:08.830205+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.10242v1","created_at":"2026-07-05T11:13:08.830205+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10242","created_at":"2026-07-05T11:13:08.830205+00:00"},{"alias_kind":"pith_short_12","alias_value":"5WQDIGR43CGM","created_at":"2026-07-05T11:13:08.830205+00:00"},{"alias_kind":"pith_short_16","alias_value":"5WQDIGR43CGMERYL","created_at":"2026-07-05T11:13:08.830205+00:00"},{"alias_kind":"pith_short_8","alias_value":"5WQDIGR4","created_at":"2026-07-05T11:13:08.830205+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/5WQDIGR43CGMERYL6XJH4PWRDY","json":"https://pith.science/pith/5WQDIGR43CGMERYL6XJH4PWRDY.json","graph_json":"https://pith.science/api/pith-number/5WQDIGR43CGMERYL6XJH4PWRDY/graph.json","events_json":"https://pith.science/api/pith-number/5WQDIGR43CGMERYL6XJH4PWRDY/events.json","paper":"https://pith.science/paper/5WQDIGR4"},"agent_actions":{"view_html":"https://pith.science/pith/5WQDIGR43CGMERYL6XJH4PWRDY","download_json":"https://pith.science/pith/5WQDIGR43CGMERYL6XJH4PWRDY.json","view_paper":"https://pith.science/paper/5WQDIGR4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.10242&json=true","fetch_graph":"https://pith.science/api/pith-number/5WQDIGR43CGMERYL6XJH4PWRDY/graph.json","fetch_events":"https://pith.science/api/pith-number/5WQDIGR43CGMERYL6XJH4PWRDY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5WQDIGR43CGMERYL6XJH4PWRDY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5WQDIGR43CGMERYL6XJH4PWRDY/action/storage_attestation","attest_author":"https://pith.science/pith/5WQDIGR43CGMERYL6XJH4PWRDY/action/author_attestation","sign_citation":"https://pith.science/pith/5WQDIGR43CGMERYL6XJH4PWRDY/action/citation_signature","submit_replication":"https://pith.science/pith/5WQDIGR43CGMERYL6XJH4PWRDY/action/replication_record"}},"created_at":"2026-07-05T11:13:08.830205+00:00","updated_at":"2026-07-05T11:13:08.830205+00:00"}