{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:AT4LCNZW35FS6NCOEIGWMPMUYT","short_pith_number":"pith:AT4LCNZW","schema_version":"1.0","canonical_sha256":"04f8b13736df4b2f344e220d663d94c4d4f9e34b3e3290fcd7fc6e24b823169b","source":{"kind":"arxiv","id":"2112.07571","version":1},"attestation_state":"computed","paper":{"title":"Epigenomic language models powered by Cerebras","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["q-bio.GN"],"primary_cat":"cs.LG","authors_text":"Cuong Q. Nguyen, Kim M. Branson, Meredith V. Trotter, Rob T. Woodruff, Stephen Young","submitted_at":"2021-12-14T17:23:42Z","abstract_excerpt":"Large scale self-supervised pre-training of Transformer language models has advanced the field of Natural Language Processing and shown promise in cross-application to the biological `languages' of proteins and DNA. Learning effective representations of DNA sequences using large genomic sequence corpuses may accelerate the development of models of gene regulation and function through transfer learning. However, to accurately model cell type-specific gene regulation and function, it is necessary to consider not only the information contained in DNA nucleotide sequences, which is mostly invarian"},"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":"2112.07571","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-14T17:23:42Z","cross_cats_sorted":["q-bio.GN"],"title_canon_sha256":"8e794bb34d717208ee2bf8f607482487f3fcc48a1f5d0463cdeb46504dc49c09","abstract_canon_sha256":"6de44e8e4c6cf5bc9bf535561f60a00cabb32dc05c76d7feb78b3e3934bbcab8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:40:59.672609Z","signature_b64":"FyUJrC8wKyCnHuulXF2u2HaLI/ZE3NY/m5XmdJycWSOtXU1mrK2K1TekA2kupb4Ecj9D9uPM2Oxf/hIuH9xZBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04f8b13736df4b2f344e220d663d94c4d4f9e34b3e3290fcd7fc6e24b823169b","last_reissued_at":"2026-07-05T03:40:59.672161Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:40:59.672161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Epigenomic language models powered by Cerebras","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["q-bio.GN"],"primary_cat":"cs.LG","authors_text":"Cuong Q. Nguyen, Kim M. Branson, Meredith V. Trotter, Rob T. Woodruff, Stephen Young","submitted_at":"2021-12-14T17:23:42Z","abstract_excerpt":"Large scale self-supervised pre-training of Transformer language models has advanced the field of Natural Language Processing and shown promise in cross-application to the biological `languages' of proteins and DNA. Learning effective representations of DNA sequences using large genomic sequence corpuses may accelerate the development of models of gene regulation and function through transfer learning. However, to accurately model cell type-specific gene regulation and function, it is necessary to consider not only the information contained in DNA nucleotide sequences, which is mostly invarian"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.07571","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/2112.07571/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":"2112.07571","created_at":"2026-07-05T03:40:59.672217+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.07571v1","created_at":"2026-07-05T03:40:59.672217+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.07571","created_at":"2026-07-05T03:40:59.672217+00:00"},{"alias_kind":"pith_short_12","alias_value":"AT4LCNZW35FS","created_at":"2026-07-05T03:40:59.672217+00:00"},{"alias_kind":"pith_short_16","alias_value":"AT4LCNZW35FS6NCO","created_at":"2026-07-05T03:40:59.672217+00:00"},{"alias_kind":"pith_short_8","alias_value":"AT4LCNZW","created_at":"2026-07-05T03:40:59.672217+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.09447","citing_title":"SpaDA: A Spatial Dataflow Architecture Programming Language","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AT4LCNZW35FS6NCOEIGWMPMUYT","json":"https://pith.science/pith/AT4LCNZW35FS6NCOEIGWMPMUYT.json","graph_json":"https://pith.science/api/pith-number/AT4LCNZW35FS6NCOEIGWMPMUYT/graph.json","events_json":"https://pith.science/api/pith-number/AT4LCNZW35FS6NCOEIGWMPMUYT/events.json","paper":"https://pith.science/paper/AT4LCNZW"},"agent_actions":{"view_html":"https://pith.science/pith/AT4LCNZW35FS6NCOEIGWMPMUYT","download_json":"https://pith.science/pith/AT4LCNZW35FS6NCOEIGWMPMUYT.json","view_paper":"https://pith.science/paper/AT4LCNZW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.07571&json=true","fetch_graph":"https://pith.science/api/pith-number/AT4LCNZW35FS6NCOEIGWMPMUYT/graph.json","fetch_events":"https://pith.science/api/pith-number/AT4LCNZW35FS6NCOEIGWMPMUYT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AT4LCNZW35FS6NCOEIGWMPMUYT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AT4LCNZW35FS6NCOEIGWMPMUYT/action/storage_attestation","attest_author":"https://pith.science/pith/AT4LCNZW35FS6NCOEIGWMPMUYT/action/author_attestation","sign_citation":"https://pith.science/pith/AT4LCNZW35FS6NCOEIGWMPMUYT/action/citation_signature","submit_replication":"https://pith.science/pith/AT4LCNZW35FS6NCOEIGWMPMUYT/action/replication_record"}},"created_at":"2026-07-05T03:40:59.672217+00:00","updated_at":"2026-07-05T03:40:59.672217+00:00"}