{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:E5S7KXFASLDB2MHBIZPNXD6BR7","short_pith_number":"pith:E5S7KXFA","schema_version":"1.0","canonical_sha256":"2765f55ca092c61d30e1465edb8fc18fc4309b22a7eea002c65086a0ca20c17a","source":{"kind":"arxiv","id":"2602.15253","version":2},"attestation_state":"computed","paper":{"title":"Scaling Laws for Masked-Reconstruction Transformers on Single-Cell Transcriptomics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.GN"],"primary_cat":"cs.LG","authors_text":"Ihor Kendiukhov","submitted_at":"2026-02-16T23:20:58Z","abstract_excerpt":"Neural scaling laws -- power-law relationships between loss, model size, and data -- have been extensively documented for language and vision transformers, yet their existence in single-cell genomics remains largely unexplored. We present the first systematic study of scaling behaviour for masked-reconstruction transformers trained on single-cell RNA sequencing (scRNA-seq) data. Using expression profiles from the CELLxGENE Census, we construct two experimental regimes: a data-rich regime (512 highly variable genes, 200,000 cells) and a data-limited regime (1,024 genes, 10,000 cells). Across se"},"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":"2602.15253","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-16T23:20:58Z","cross_cats_sorted":["q-bio.GN"],"title_canon_sha256":"797f92432d2183d803434b4ddcf5f88ba76902c7693645883ae92eaf56633322","abstract_canon_sha256":"261e889099b1a547d81ee3da013f236db1d3bff57eb70184094b8c6c326c0e9a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:04:41.431112Z","signature_b64":"5FOQiC7mg8DRagoHIQ4Sgyh1bi3LJkWtTWEiWDdcLyTcgd4QlKlEkB2TmaXz41Wmpc/nNWQPTORLJavTciUsAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2765f55ca092c61d30e1465edb8fc18fc4309b22a7eea002c65086a0ca20c17a","last_reissued_at":"2026-06-09T01:04:41.430562Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:04:41.430562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Laws for Masked-Reconstruction Transformers on Single-Cell Transcriptomics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.GN"],"primary_cat":"cs.LG","authors_text":"Ihor Kendiukhov","submitted_at":"2026-02-16T23:20:58Z","abstract_excerpt":"Neural scaling laws -- power-law relationships between loss, model size, and data -- have been extensively documented for language and vision transformers, yet their existence in single-cell genomics remains largely unexplored. We present the first systematic study of scaling behaviour for masked-reconstruction transformers trained on single-cell RNA sequencing (scRNA-seq) data. Using expression profiles from the CELLxGENE Census, we construct two experimental regimes: a data-rich regime (512 highly variable genes, 200,000 cells) and a data-limited regime (1,024 genes, 10,000 cells). Across se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.15253","kind":"arxiv","version":2},"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/2602.15253/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":"2602.15253","created_at":"2026-06-09T01:04:41.430634+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.15253v2","created_at":"2026-06-09T01:04:41.430634+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.15253","created_at":"2026-06-09T01:04:41.430634+00:00"},{"alias_kind":"pith_short_12","alias_value":"E5S7KXFASLDB","created_at":"2026-06-09T01:04:41.430634+00:00"},{"alias_kind":"pith_short_16","alias_value":"E5S7KXFASLDB2MHB","created_at":"2026-06-09T01:04:41.430634+00:00"},{"alias_kind":"pith_short_8","alias_value":"E5S7KXFA","created_at":"2026-06-09T01:04:41.430634+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/E5S7KXFASLDB2MHBIZPNXD6BR7","json":"https://pith.science/pith/E5S7KXFASLDB2MHBIZPNXD6BR7.json","graph_json":"https://pith.science/api/pith-number/E5S7KXFASLDB2MHBIZPNXD6BR7/graph.json","events_json":"https://pith.science/api/pith-number/E5S7KXFASLDB2MHBIZPNXD6BR7/events.json","paper":"https://pith.science/paper/E5S7KXFA"},"agent_actions":{"view_html":"https://pith.science/pith/E5S7KXFASLDB2MHBIZPNXD6BR7","download_json":"https://pith.science/pith/E5S7KXFASLDB2MHBIZPNXD6BR7.json","view_paper":"https://pith.science/paper/E5S7KXFA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.15253&json=true","fetch_graph":"https://pith.science/api/pith-number/E5S7KXFASLDB2MHBIZPNXD6BR7/graph.json","fetch_events":"https://pith.science/api/pith-number/E5S7KXFASLDB2MHBIZPNXD6BR7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E5S7KXFASLDB2MHBIZPNXD6BR7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E5S7KXFASLDB2MHBIZPNXD6BR7/action/storage_attestation","attest_author":"https://pith.science/pith/E5S7KXFASLDB2MHBIZPNXD6BR7/action/author_attestation","sign_citation":"https://pith.science/pith/E5S7KXFASLDB2MHBIZPNXD6BR7/action/citation_signature","submit_replication":"https://pith.science/pith/E5S7KXFASLDB2MHBIZPNXD6BR7/action/replication_record"}},"created_at":"2026-06-09T01:04:41.430634+00:00","updated_at":"2026-06-09T01:04:41.430634+00:00"}