{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2KTVXSW4IQD565WRAL3E7ATSSA","short_pith_number":"pith:2KTVXSW4","schema_version":"1.0","canonical_sha256":"d2a75bcadc4407df76d102f64f8272903798b7561cc592dea5756de5cef072e2","source":{"kind":"arxiv","id":"2503.09427","version":4},"attestation_state":"computed","paper":{"title":"Language-Enhanced Representation Learning for Single-Cell Transcriptomics","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Changhao Nai, Jiaqi Yang, Junfeng Fang, Sihang Li, Xiang Wang, Yang Zhang, Yaorui Shi, Zhiyuan Liu","submitted_at":"2025-03-12T14:26:16Z","abstract_excerpt":"Single-cell RNA sequencing (scRNA-seq) offers detailed insights into cellular heterogeneity. Recent advancements leverage single-cell large language models (scLLMs) for effective representation learning. These models focus exclusively on transcriptomic data, neglecting complementary biological knowledge from textual descriptions. To overcome this limitation, we propose scMMGPT, a novel multimodal framework designed for language-enhanced representation learning in single-cell transcriptomics. Unlike existing methods, scMMGPT employs robust cell representation extraction, preserving quantitative"},"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":"2503.09427","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-12T14:26:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9e648d6a348ed0f2151b49633cf7ee460790c574dc2413b9d9c67fee65682704","abstract_canon_sha256":"f1209053dc82e623a9fe2a3ed6242260501097ddd480994e812aadc370812fc0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:20.003926Z","signature_b64":"KniOljk+pgTKgDlqnWKFe1+tYJLRQsWW13f6WMwAZLreZ34sPFvTdqFeq8l6uSfA14j7EV0k9cFxBf2hPRLfAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2a75bcadc4407df76d102f64f8272903798b7561cc592dea5756de5cef072e2","last_reissued_at":"2026-07-05T11:15:20.003438Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:20.003438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language-Enhanced Representation Learning for Single-Cell Transcriptomics","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Changhao Nai, Jiaqi Yang, Junfeng Fang, Sihang Li, Xiang Wang, Yang Zhang, Yaorui Shi, Zhiyuan Liu","submitted_at":"2025-03-12T14:26:16Z","abstract_excerpt":"Single-cell RNA sequencing (scRNA-seq) offers detailed insights into cellular heterogeneity. Recent advancements leverage single-cell large language models (scLLMs) for effective representation learning. These models focus exclusively on transcriptomic data, neglecting complementary biological knowledge from textual descriptions. To overcome this limitation, we propose scMMGPT, a novel multimodal framework designed for language-enhanced representation learning in single-cell transcriptomics. Unlike existing methods, scMMGPT employs robust cell representation extraction, preserving quantitative"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.09427","kind":"arxiv","version":4},"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/2503.09427/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":"2503.09427","created_at":"2026-07-05T11:15:20.003500+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.09427v4","created_at":"2026-07-05T11:15:20.003500+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.09427","created_at":"2026-07-05T11:15:20.003500+00:00"},{"alias_kind":"pith_short_12","alias_value":"2KTVXSW4IQD5","created_at":"2026-07-05T11:15:20.003500+00:00"},{"alias_kind":"pith_short_16","alias_value":"2KTVXSW4IQD565WR","created_at":"2026-07-05T11:15:20.003500+00:00"},{"alias_kind":"pith_short_8","alias_value":"2KTVXSW4","created_at":"2026-07-05T11:15:20.003500+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02911","citing_title":"Cell-o1: Training LLMs to Solve Single-Cell Reasoning Puzzles with Reinforcement Learning","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2KTVXSW4IQD565WRAL3E7ATSSA","json":"https://pith.science/pith/2KTVXSW4IQD565WRAL3E7ATSSA.json","graph_json":"https://pith.science/api/pith-number/2KTVXSW4IQD565WRAL3E7ATSSA/graph.json","events_json":"https://pith.science/api/pith-number/2KTVXSW4IQD565WRAL3E7ATSSA/events.json","paper":"https://pith.science/paper/2KTVXSW4"},"agent_actions":{"view_html":"https://pith.science/pith/2KTVXSW4IQD565WRAL3E7ATSSA","download_json":"https://pith.science/pith/2KTVXSW4IQD565WRAL3E7ATSSA.json","view_paper":"https://pith.science/paper/2KTVXSW4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.09427&json=true","fetch_graph":"https://pith.science/api/pith-number/2KTVXSW4IQD565WRAL3E7ATSSA/graph.json","fetch_events":"https://pith.science/api/pith-number/2KTVXSW4IQD565WRAL3E7ATSSA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2KTVXSW4IQD565WRAL3E7ATSSA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2KTVXSW4IQD565WRAL3E7ATSSA/action/storage_attestation","attest_author":"https://pith.science/pith/2KTVXSW4IQD565WRAL3E7ATSSA/action/author_attestation","sign_citation":"https://pith.science/pith/2KTVXSW4IQD565WRAL3E7ATSSA/action/citation_signature","submit_replication":"https://pith.science/pith/2KTVXSW4IQD565WRAL3E7ATSSA/action/replication_record"}},"created_at":"2026-07-05T11:15:20.003500+00:00","updated_at":"2026-07-05T11:15:20.003500+00:00"}