{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SZJ3S63RHN4NHTCV226Q3FDFFO","short_pith_number":"pith:SZJ3S63R","schema_version":"1.0","canonical_sha256":"9653b97b713b78d3cc55d6bd0d94652b96d0396e699f17c2c8c9752acb7bd3a5","source":{"kind":"arxiv","id":"2310.07644","version":3},"attestation_state":"computed","paper":{"title":"Toward Understanding BERT-Like Pre-Training for DNA Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Chaoqi Liang, Chunfeng Song, Hongliang Yan, Jianle Sun, Lifeng Qiao, Nanqing Dong, Peng Ye, Wangmeng Zuo, Wanli Ouyang, Weiqiang Bai, Xinzhu Ma, Yuchen Ren","submitted_at":"2023-10-11T16:40:57Z","abstract_excerpt":"With the success of large-scale pre-training in language tasks, there is an increasing trend of applying it to the domain of life sciences. In particular, pre-training methods based on DNA sequences have received increasing attention because of their potential to capture general information about genes. However, existing pre-training methods for DNA sequences largely rely on direct adoptions of BERT pre-training from NLP, lacking a comprehensive understanding and a specifically tailored approach. To address this research gap, we provide the first empirical study with three insightful observati"},"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":"2310.07644","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-11T16:40:57Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"cf8d7471ad1fa4b775022de9b1dfc9167bbf9eb746e79e60451beef4a28fada1","abstract_canon_sha256":"d3bf3b013bd2396a8f310af5c5d43d2c97bc251cf460cf202951515e5cb306cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:04:29.813501Z","signature_b64":"kFM6Mn+Pq7CtRBsZhaM+9BkP+eu8/+xndxJc0sA9+KpbHioD2v7opR7DzxxnSvfvls9HWhZr1rztq3lS1iCiAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9653b97b713b78d3cc55d6bd0d94652b96d0396e699f17c2c8c9752acb7bd3a5","last_reissued_at":"2026-07-05T09:04:29.813014Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:04:29.813014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Toward Understanding BERT-Like Pre-Training for DNA Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Chaoqi Liang, Chunfeng Song, Hongliang Yan, Jianle Sun, Lifeng Qiao, Nanqing Dong, Peng Ye, Wangmeng Zuo, Wanli Ouyang, Weiqiang Bai, Xinzhu Ma, Yuchen Ren","submitted_at":"2023-10-11T16:40:57Z","abstract_excerpt":"With the success of large-scale pre-training in language tasks, there is an increasing trend of applying it to the domain of life sciences. In particular, pre-training methods based on DNA sequences have received increasing attention because of their potential to capture general information about genes. However, existing pre-training methods for DNA sequences largely rely on direct adoptions of BERT pre-training from NLP, lacking a comprehensive understanding and a specifically tailored approach. To address this research gap, we provide the first empirical study with three insightful observati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07644","kind":"arxiv","version":3},"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/2310.07644/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":"2310.07644","created_at":"2026-07-05T09:04:29.813070+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.07644v3","created_at":"2026-07-05T09:04:29.813070+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07644","created_at":"2026-07-05T09:04:29.813070+00:00"},{"alias_kind":"pith_short_12","alias_value":"SZJ3S63RHN4N","created_at":"2026-07-05T09:04:29.813070+00:00"},{"alias_kind":"pith_short_16","alias_value":"SZJ3S63RHN4NHTCV","created_at":"2026-07-05T09:04:29.813070+00:00"},{"alias_kind":"pith_short_8","alias_value":"SZJ3S63R","created_at":"2026-07-05T09:04:29.813070+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.13716","citing_title":"Model Decides How to Tokenize: Adaptive DNA Sequence Tokenization with MxDNA","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SZJ3S63RHN4NHTCV226Q3FDFFO","json":"https://pith.science/pith/SZJ3S63RHN4NHTCV226Q3FDFFO.json","graph_json":"https://pith.science/api/pith-number/SZJ3S63RHN4NHTCV226Q3FDFFO/graph.json","events_json":"https://pith.science/api/pith-number/SZJ3S63RHN4NHTCV226Q3FDFFO/events.json","paper":"https://pith.science/paper/SZJ3S63R"},"agent_actions":{"view_html":"https://pith.science/pith/SZJ3S63RHN4NHTCV226Q3FDFFO","download_json":"https://pith.science/pith/SZJ3S63RHN4NHTCV226Q3FDFFO.json","view_paper":"https://pith.science/paper/SZJ3S63R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.07644&json=true","fetch_graph":"https://pith.science/api/pith-number/SZJ3S63RHN4NHTCV226Q3FDFFO/graph.json","fetch_events":"https://pith.science/api/pith-number/SZJ3S63RHN4NHTCV226Q3FDFFO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SZJ3S63RHN4NHTCV226Q3FDFFO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SZJ3S63RHN4NHTCV226Q3FDFFO/action/storage_attestation","attest_author":"https://pith.science/pith/SZJ3S63RHN4NHTCV226Q3FDFFO/action/author_attestation","sign_citation":"https://pith.science/pith/SZJ3S63RHN4NHTCV226Q3FDFFO/action/citation_signature","submit_replication":"https://pith.science/pith/SZJ3S63RHN4NHTCV226Q3FDFFO/action/replication_record"}},"created_at":"2026-07-05T09:04:29.813070+00:00","updated_at":"2026-07-05T09:04:29.813070+00:00"}