{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NOZBYL5T2Q5DLVWOHTMHC46ZNA","short_pith_number":"pith:NOZBYL5T","schema_version":"1.0","canonical_sha256":"6bb21c2fb3d43a35d6ce3cd87173d9682a4f0841ad084fc226b7b0ed08a69d60","source":{"kind":"arxiv","id":"2311.15156","version":2},"attestation_state":"computed","paper":{"title":"xTrimoGene: An Efficient and Scalable Representation Learner for Single-Cell RNA-Seq Data","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","q-bio.GN"],"primary_cat":"cs.LG","authors_text":"Chiming Liu, Jianzhu Ma, Jing Gong, Le Song, Minsheng Hao, Taifeng Wang, Xingyi Cheng, Xin Zeng, Xuegong Zhang","submitted_at":"2023-11-26T01:23:01Z","abstract_excerpt":"Advances in high-throughput sequencing technology have led to significant progress in measuring gene expressions at the single-cell level. The amount of publicly available single-cell RNA-seq (scRNA-seq) data is already surpassing 50M records for humans with each record measuring 20,000 genes. This highlights the need for unsupervised representation learning to fully ingest these data, yet classical transformer architectures are prohibitive to train on such data in terms of both computation and memory. To address this challenge, we propose a novel asymmetric encoder-decoder transformer for scR"},"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":"2311.15156","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-26T01:23:01Z","cross_cats_sorted":["cs.AI","q-bio.GN"],"title_canon_sha256":"f80c4769056beb21e815f1ab7fd4353a31577ab3362db3f952f235bfcd9e9091","abstract_canon_sha256":"e9ea4c1954190bab6623d976e6ffa20ada647938996e6b00fba13423374adad3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:50.598388Z","signature_b64":"aJnSNj+ELob+EsJjEKoeH6S2OBu8O2dpLPBw3qEBkuhztH31jpN35oHNW8tUNpnf+v4EfulghiBTOPuz5j+oDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6bb21c2fb3d43a35d6ce3cd87173d9682a4f0841ad084fc226b7b0ed08a69d60","last_reissued_at":"2026-07-05T07:48:50.597932Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:50.597932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"xTrimoGene: An Efficient and Scalable Representation Learner for Single-Cell RNA-Seq Data","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","q-bio.GN"],"primary_cat":"cs.LG","authors_text":"Chiming Liu, Jianzhu Ma, Jing Gong, Le Song, Minsheng Hao, Taifeng Wang, Xingyi Cheng, Xin Zeng, Xuegong Zhang","submitted_at":"2023-11-26T01:23:01Z","abstract_excerpt":"Advances in high-throughput sequencing technology have led to significant progress in measuring gene expressions at the single-cell level. The amount of publicly available single-cell RNA-seq (scRNA-seq) data is already surpassing 50M records for humans with each record measuring 20,000 genes. This highlights the need for unsupervised representation learning to fully ingest these data, yet classical transformer architectures are prohibitive to train on such data in terms of both computation and memory. To address this challenge, we propose a novel asymmetric encoder-decoder transformer for scR"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.15156","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/2311.15156/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":"2311.15156","created_at":"2026-07-05T07:48:50.597991+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.15156v2","created_at":"2026-07-05T07:48:50.597991+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.15156","created_at":"2026-07-05T07:48:50.597991+00:00"},{"alias_kind":"pith_short_12","alias_value":"NOZBYL5T2Q5D","created_at":"2026-07-05T07:48:50.597991+00:00"},{"alias_kind":"pith_short_16","alias_value":"NOZBYL5T2Q5DLVWO","created_at":"2026-07-05T07:48:50.597991+00:00"},{"alias_kind":"pith_short_8","alias_value":"NOZBYL5T","created_at":"2026-07-05T07:48:50.597991+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.11588","citing_title":"SToFM: a Multi-scale Foundation Model for Spatial Transcriptomics","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NOZBYL5T2Q5DLVWOHTMHC46ZNA","json":"https://pith.science/pith/NOZBYL5T2Q5DLVWOHTMHC46ZNA.json","graph_json":"https://pith.science/api/pith-number/NOZBYL5T2Q5DLVWOHTMHC46ZNA/graph.json","events_json":"https://pith.science/api/pith-number/NOZBYL5T2Q5DLVWOHTMHC46ZNA/events.json","paper":"https://pith.science/paper/NOZBYL5T"},"agent_actions":{"view_html":"https://pith.science/pith/NOZBYL5T2Q5DLVWOHTMHC46ZNA","download_json":"https://pith.science/pith/NOZBYL5T2Q5DLVWOHTMHC46ZNA.json","view_paper":"https://pith.science/paper/NOZBYL5T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.15156&json=true","fetch_graph":"https://pith.science/api/pith-number/NOZBYL5T2Q5DLVWOHTMHC46ZNA/graph.json","fetch_events":"https://pith.science/api/pith-number/NOZBYL5T2Q5DLVWOHTMHC46ZNA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NOZBYL5T2Q5DLVWOHTMHC46ZNA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NOZBYL5T2Q5DLVWOHTMHC46ZNA/action/storage_attestation","attest_author":"https://pith.science/pith/NOZBYL5T2Q5DLVWOHTMHC46ZNA/action/author_attestation","sign_citation":"https://pith.science/pith/NOZBYL5T2Q5DLVWOHTMHC46ZNA/action/citation_signature","submit_replication":"https://pith.science/pith/NOZBYL5T2Q5DLVWOHTMHC46ZNA/action/replication_record"}},"created_at":"2026-07-05T07:48:50.597991+00:00","updated_at":"2026-07-05T07:48:50.597991+00:00"}