{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CRG5ANIUBFVKC3W7C7M3HYAUIK","short_pith_number":"pith:CRG5ANIU","schema_version":"1.0","canonical_sha256":"144dd03514096aa16edf17d9b3e01442964c49db8ae2b1614dbf665665639464","source":{"kind":"arxiv","id":"2606.23964","version":1},"attestation_state":"computed","paper":{"title":"3D Masked Autoencoders are Robust Learners of Volumetric and Multimodal Cellular Representations for Microscopy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Amirhossein Kardoost, Carsten Marr, Lion Gleiter, Tingying Peng","submitted_at":"2026-06-22T21:45:15Z","abstract_excerpt":"Self-supervised learning in fluorescence microscopy often relies on 2D projections, despite the inherently three-dimensional nature of cells. We present a systematic comparison of 2D and 3D masked autoencoders (MAE-2D vs. MAE-3D) on volumetric microscopy data. Under matched architectures and training protocols, MAE-3D consistently outperforms 2D max-projection and slice-based variants on downstream single-cell tasks. We further align visual representations with a pretrained protein language model (ESM2) and show that cross-modal supervision yields larger gains for volumetric models. Channel cr"},"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":"2606.23964","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T21:45:15Z","cross_cats_sorted":["cs.CV","q-bio.QM"],"title_canon_sha256":"356036791d9884644b48200779b30fb44616da37b96e919df9d35b59cdc167f0","abstract_canon_sha256":"dd2995a90ee8b468d9d36a2c65e77290348cd227c6853b381ad41ac32975f9e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T00:14:31.505545Z","signature_b64":"e8snky+ds3SQ+j6GsbasDOtoSMntVO4ofqDEiQZL0g3OkxIOU+YayWMouaVuhw3+PgY+imHkauYzdeP9Fr5YAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"144dd03514096aa16edf17d9b3e01442964c49db8ae2b1614dbf665665639464","last_reissued_at":"2026-06-24T00:14:31.505159Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T00:14:31.505159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3D Masked Autoencoders are Robust Learners of Volumetric and Multimodal Cellular Representations for Microscopy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Amirhossein Kardoost, Carsten Marr, Lion Gleiter, Tingying Peng","submitted_at":"2026-06-22T21:45:15Z","abstract_excerpt":"Self-supervised learning in fluorescence microscopy often relies on 2D projections, despite the inherently three-dimensional nature of cells. We present a systematic comparison of 2D and 3D masked autoencoders (MAE-2D vs. MAE-3D) on volumetric microscopy data. Under matched architectures and training protocols, MAE-3D consistently outperforms 2D max-projection and slice-based variants on downstream single-cell tasks. We further align visual representations with a pretrained protein language model (ESM2) and show that cross-modal supervision yields larger gains for volumetric models. Channel cr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23964","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/2606.23964/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":"2606.23964","created_at":"2026-06-24T00:14:31.505220+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.23964v1","created_at":"2026-06-24T00:14:31.505220+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23964","created_at":"2026-06-24T00:14:31.505220+00:00"},{"alias_kind":"pith_short_12","alias_value":"CRG5ANIUBFVK","created_at":"2026-06-24T00:14:31.505220+00:00"},{"alias_kind":"pith_short_16","alias_value":"CRG5ANIUBFVKC3W7","created_at":"2026-06-24T00:14:31.505220+00:00"},{"alias_kind":"pith_short_8","alias_value":"CRG5ANIU","created_at":"2026-06-24T00:14:31.505220+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/CRG5ANIUBFVKC3W7C7M3HYAUIK","json":"https://pith.science/pith/CRG5ANIUBFVKC3W7C7M3HYAUIK.json","graph_json":"https://pith.science/api/pith-number/CRG5ANIUBFVKC3W7C7M3HYAUIK/graph.json","events_json":"https://pith.science/api/pith-number/CRG5ANIUBFVKC3W7C7M3HYAUIK/events.json","paper":"https://pith.science/paper/CRG5ANIU"},"agent_actions":{"view_html":"https://pith.science/pith/CRG5ANIUBFVKC3W7C7M3HYAUIK","download_json":"https://pith.science/pith/CRG5ANIUBFVKC3W7C7M3HYAUIK.json","view_paper":"https://pith.science/paper/CRG5ANIU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.23964&json=true","fetch_graph":"https://pith.science/api/pith-number/CRG5ANIUBFVKC3W7C7M3HYAUIK/graph.json","fetch_events":"https://pith.science/api/pith-number/CRG5ANIUBFVKC3W7C7M3HYAUIK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CRG5ANIUBFVKC3W7C7M3HYAUIK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CRG5ANIUBFVKC3W7C7M3HYAUIK/action/storage_attestation","attest_author":"https://pith.science/pith/CRG5ANIUBFVKC3W7C7M3HYAUIK/action/author_attestation","sign_citation":"https://pith.science/pith/CRG5ANIUBFVKC3W7C7M3HYAUIK/action/citation_signature","submit_replication":"https://pith.science/pith/CRG5ANIUBFVKC3W7C7M3HYAUIK/action/replication_record"}},"created_at":"2026-06-24T00:14:31.505220+00:00","updated_at":"2026-06-24T00:14:31.505220+00:00"}