{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VA7QBRQLFGL66TAXWY7FHO7CMX","short_pith_number":"pith:VA7QBRQL","schema_version":"1.0","canonical_sha256":"a83f00c60b2997ef4c17b63e53bbe265d54f67bc46f4da50c7a00ff1c7d08e06","source":{"kind":"arxiv","id":"2412.16262","version":1},"attestation_state":"computed","paper":{"title":"VirusT5: Harnessing Large Language Models to Predicting SARS-CoV-2 Evolution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"q-bio.QM","authors_text":"Changhui Yan, Deewan Bajracharya, Vishwajeet Marathe","submitted_at":"2024-12-20T08:46:42Z","abstract_excerpt":"During a virus's evolution,various regions of the genome are subjected to distinct levels of functional constraints.Combined with factors like codon bias and DNA repair efficiency,these constraints contribute to unique mutation patterns within the genome or a specific gene. In this project, we harnessed the power of Large Language Models(LLMs) to predict the evolution of SARS-CoV-2. By treating the mutation process from one generation to the next as a translation task, we trained a transformer model, called VirusT5, to capture the mutation patterns underlying SARS-CoV-2 evolution. We evaluated"},"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":"2412.16262","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2024-12-20T08:46:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0302b4d2f3086c3bbcd4b2f8704f909f44df295cbbbbb456db7d6f9ac9d93fbd","abstract_canon_sha256":"64c530be70047ce293168f74a253a42ac655a4c97c0f9b8b5650d0e5ed586d3c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:47.445460Z","signature_b64":"I7PoHtVutbia0nC6VoUEwWnQ9MpA6DzwcQxTeozOt7PwFFN/q7aZ5zUmBJuwEA39msqoN6y9OCA5qgrFn6sKBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a83f00c60b2997ef4c17b63e53bbe265d54f67bc46f4da50c7a00ff1c7d08e06","last_reissued_at":"2026-07-05T09:53:47.444972Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:47.444972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VirusT5: Harnessing Large Language Models to Predicting SARS-CoV-2 Evolution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"q-bio.QM","authors_text":"Changhui Yan, Deewan Bajracharya, Vishwajeet Marathe","submitted_at":"2024-12-20T08:46:42Z","abstract_excerpt":"During a virus's evolution,various regions of the genome are subjected to distinct levels of functional constraints.Combined with factors like codon bias and DNA repair efficiency,these constraints contribute to unique mutation patterns within the genome or a specific gene. In this project, we harnessed the power of Large Language Models(LLMs) to predict the evolution of SARS-CoV-2. By treating the mutation process from one generation to the next as a translation task, we trained a transformer model, called VirusT5, to capture the mutation patterns underlying SARS-CoV-2 evolution. We evaluated"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16262","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/2412.16262/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":"2412.16262","created_at":"2026-07-05T09:53:47.445033+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.16262v1","created_at":"2026-07-05T09:53:47.445033+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16262","created_at":"2026-07-05T09:53:47.445033+00:00"},{"alias_kind":"pith_short_12","alias_value":"VA7QBRQLFGL6","created_at":"2026-07-05T09:53:47.445033+00:00"},{"alias_kind":"pith_short_16","alias_value":"VA7QBRQLFGL66TAX","created_at":"2026-07-05T09:53:47.445033+00:00"},{"alias_kind":"pith_short_8","alias_value":"VA7QBRQL","created_at":"2026-07-05T09:53:47.445033+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/VA7QBRQLFGL66TAXWY7FHO7CMX","json":"https://pith.science/pith/VA7QBRQLFGL66TAXWY7FHO7CMX.json","graph_json":"https://pith.science/api/pith-number/VA7QBRQLFGL66TAXWY7FHO7CMX/graph.json","events_json":"https://pith.science/api/pith-number/VA7QBRQLFGL66TAXWY7FHO7CMX/events.json","paper":"https://pith.science/paper/VA7QBRQL"},"agent_actions":{"view_html":"https://pith.science/pith/VA7QBRQLFGL66TAXWY7FHO7CMX","download_json":"https://pith.science/pith/VA7QBRQLFGL66TAXWY7FHO7CMX.json","view_paper":"https://pith.science/paper/VA7QBRQL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.16262&json=true","fetch_graph":"https://pith.science/api/pith-number/VA7QBRQLFGL66TAXWY7FHO7CMX/graph.json","fetch_events":"https://pith.science/api/pith-number/VA7QBRQLFGL66TAXWY7FHO7CMX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VA7QBRQLFGL66TAXWY7FHO7CMX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VA7QBRQLFGL66TAXWY7FHO7CMX/action/storage_attestation","attest_author":"https://pith.science/pith/VA7QBRQLFGL66TAXWY7FHO7CMX/action/author_attestation","sign_citation":"https://pith.science/pith/VA7QBRQLFGL66TAXWY7FHO7CMX/action/citation_signature","submit_replication":"https://pith.science/pith/VA7QBRQLFGL66TAXWY7FHO7CMX/action/replication_record"}},"created_at":"2026-07-05T09:53:47.445033+00:00","updated_at":"2026-07-05T09:53:47.445033+00:00"}