{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FMUJI42Z3TC7CI5WDPTYXJWBOJ","short_pith_number":"pith:FMUJI42Z","schema_version":"1.0","canonical_sha256":"2b28947359dcc5f123b61be78ba6c1724abdd7c15b55bec3d9496727520b2af3","source":{"kind":"arxiv","id":"2506.10031","version":1},"attestation_state":"computed","paper":{"title":"scSSL-Bench: Benchmarking Self-Supervised Learning for Single-Cell Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.QM","authors_text":"Florian Barkmann, Imant Daunhawer, Julia Vogt, Olga Ovcharenko, Philip Toma, Sebastian Schelter, Valentina Boeva","submitted_at":"2025-06-10T12:31:42Z","abstract_excerpt":"Self-supervised learning (SSL) has proven to be a powerful approach for extracting biologically meaningful representations from single-cell data. To advance our understanding of SSL methods applied to single-cell data, we present scSSL-Bench, a comprehensive benchmark that evaluates nineteen SSL methods. Our evaluation spans nine datasets and focuses on three common downstream tasks: batch correction, cell type annotation, and missing modality prediction. Furthermore, we systematically assess various data augmentation strategies. Our analysis reveals task-specific trade-offs: the specialized s"},"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":"2506.10031","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2025-06-10T12:31:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d3215345cc7f92612fa003372e72814d3623e20bb00a784dc393bf16f942a224","abstract_canon_sha256":"d2d6ce5ae27ff7250550946ec16a8dfd17135aab385fb71b29de3b5d810c9f27"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:15.519738Z","signature_b64":"2VWrafmba4SDhs4HzASp04qTyE6QGHMyIFI63ALEOLGPFi8+HJkJAufhoFCUW6Y02hhKvknnu9VCP27jdV1EDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b28947359dcc5f123b61be78ba6c1724abdd7c15b55bec3d9496727520b2af3","last_reissued_at":"2026-07-05T11:20:15.519263Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:15.519263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"scSSL-Bench: Benchmarking Self-Supervised Learning for Single-Cell Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.QM","authors_text":"Florian Barkmann, Imant Daunhawer, Julia Vogt, Olga Ovcharenko, Philip Toma, Sebastian Schelter, Valentina Boeva","submitted_at":"2025-06-10T12:31:42Z","abstract_excerpt":"Self-supervised learning (SSL) has proven to be a powerful approach for extracting biologically meaningful representations from single-cell data. To advance our understanding of SSL methods applied to single-cell data, we present scSSL-Bench, a comprehensive benchmark that evaluates nineteen SSL methods. Our evaluation spans nine datasets and focuses on three common downstream tasks: batch correction, cell type annotation, and missing modality prediction. Furthermore, we systematically assess various data augmentation strategies. Our analysis reveals task-specific trade-offs: the specialized s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10031","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/2506.10031/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":"2506.10031","created_at":"2026-07-05T11:20:15.519323+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.10031v1","created_at":"2026-07-05T11:20:15.519323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10031","created_at":"2026-07-05T11:20:15.519323+00:00"},{"alias_kind":"pith_short_12","alias_value":"FMUJI42Z3TC7","created_at":"2026-07-05T11:20:15.519323+00:00"},{"alias_kind":"pith_short_16","alias_value":"FMUJI42Z3TC7CI5W","created_at":"2026-07-05T11:20:15.519323+00:00"},{"alias_kind":"pith_short_8","alias_value":"FMUJI42Z","created_at":"2026-07-05T11:20:15.519323+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05139","citing_title":"BBOmix: A Tabular Benchmark for Hyperparameter Optimization of Unsupervised Biological Representation Learning","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FMUJI42Z3TC7CI5WDPTYXJWBOJ","json":"https://pith.science/pith/FMUJI42Z3TC7CI5WDPTYXJWBOJ.json","graph_json":"https://pith.science/api/pith-number/FMUJI42Z3TC7CI5WDPTYXJWBOJ/graph.json","events_json":"https://pith.science/api/pith-number/FMUJI42Z3TC7CI5WDPTYXJWBOJ/events.json","paper":"https://pith.science/paper/FMUJI42Z"},"agent_actions":{"view_html":"https://pith.science/pith/FMUJI42Z3TC7CI5WDPTYXJWBOJ","download_json":"https://pith.science/pith/FMUJI42Z3TC7CI5WDPTYXJWBOJ.json","view_paper":"https://pith.science/paper/FMUJI42Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.10031&json=true","fetch_graph":"https://pith.science/api/pith-number/FMUJI42Z3TC7CI5WDPTYXJWBOJ/graph.json","fetch_events":"https://pith.science/api/pith-number/FMUJI42Z3TC7CI5WDPTYXJWBOJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FMUJI42Z3TC7CI5WDPTYXJWBOJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FMUJI42Z3TC7CI5WDPTYXJWBOJ/action/storage_attestation","attest_author":"https://pith.science/pith/FMUJI42Z3TC7CI5WDPTYXJWBOJ/action/author_attestation","sign_citation":"https://pith.science/pith/FMUJI42Z3TC7CI5WDPTYXJWBOJ/action/citation_signature","submit_replication":"https://pith.science/pith/FMUJI42Z3TC7CI5WDPTYXJWBOJ/action/replication_record"}},"created_at":"2026-07-05T11:20:15.519323+00:00","updated_at":"2026-07-05T11:20:15.519323+00:00"}