{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RRBTEL5UPJHM7VJIPWBSJWU4FF","short_pith_number":"pith:RRBTEL5U","schema_version":"1.0","canonical_sha256":"8c43322fb47a4ecfd5287d8324da9c296524658084b42dae213e110b4ae42753","source":{"kind":"arxiv","id":"2306.15006","version":2},"attestation_state":"computed","paper":{"title":"DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species Genome","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CE","cs.CL"],"primary_cat":"q-bio.GN","authors_text":"Han Liu, Pratik Dutta, Ramana Davuluri, Weijian Li, Yanrong Ji, Zhihan Zhou","submitted_at":"2023-06-26T18:43:46Z","abstract_excerpt":"Decoding the linguistic intricacies of the genome is a crucial problem in biology, and pre-trained foundational models such as DNABERT and Nucleotide Transformer have made significant strides in this area. Existing works have largely hinged on k-mer, fixed-length permutations of A, T, C, and G, as the token of the genome language due to its simplicity. However, we argue that the computation and sample inefficiencies introduced by k-mer tokenization are primary obstacles in developing large genome foundational models. We provide conceptual and empirical insights into genome tokenization, buildi"},"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":"2306.15006","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2023-06-26T18:43:46Z","cross_cats_sorted":["cs.AI","cs.CE","cs.CL"],"title_canon_sha256":"ccc526cd6f38783172ac22776afa9e84c78a721f57ea0aefb643017f0dcb0283","abstract_canon_sha256":"029df7d02de00b4102279d9820396e7bd693e8aa7af132ea291018b72e84bc00"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:41.362993Z","signature_b64":"t9letc6GX0mfhVyTsx+tyfBnsX7MLmeEA6+EqjKcQoWv4xETjiQ4/5Q2HZ6HdlS/wtX6KPRANnnVFYdwqTwOCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c43322fb47a4ecfd5287d8324da9c296524658084b42dae213e110b4ae42753","last_reissued_at":"2026-07-05T07:57:41.362489Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:41.362489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species Genome","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CE","cs.CL"],"primary_cat":"q-bio.GN","authors_text":"Han Liu, Pratik Dutta, Ramana Davuluri, Weijian Li, Yanrong Ji, Zhihan Zhou","submitted_at":"2023-06-26T18:43:46Z","abstract_excerpt":"Decoding the linguistic intricacies of the genome is a crucial problem in biology, and pre-trained foundational models such as DNABERT and Nucleotide Transformer have made significant strides in this area. Existing works have largely hinged on k-mer, fixed-length permutations of A, T, C, and G, as the token of the genome language due to its simplicity. However, we argue that the computation and sample inefficiencies introduced by k-mer tokenization are primary obstacles in developing large genome foundational models. We provide conceptual and empirical insights into genome tokenization, buildi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.15006","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/2306.15006/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":"2306.15006","created_at":"2026-07-05T07:57:41.362547+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.15006v2","created_at":"2026-07-05T07:57:41.362547+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.15006","created_at":"2026-07-05T07:57:41.362547+00:00"},{"alias_kind":"pith_short_12","alias_value":"RRBTEL5UPJHM","created_at":"2026-07-05T07:57:41.362547+00:00"},{"alias_kind":"pith_short_16","alias_value":"RRBTEL5UPJHM7VJI","created_at":"2026-07-05T07:57:41.362547+00:00"},{"alias_kind":"pith_short_8","alias_value":"RRBTEL5U","created_at":"2026-07-05T07:57:41.362547+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10543","citing_title":"Flexible Flows for Biological Sequence Design","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08147","citing_title":"Biological Reasoning-Informed Regression for Interpretable Regulatory DNA Activity Prediction","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2606.16517","citing_title":"How Post-Training Shapes Biological Reasoning Models","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30140","citing_title":"DNA Language Models: An Assessment of Pre-Training for Fine-Tuning Tasks","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02624","citing_title":"TadA-Bench: A Million-Variant Benchmark for Future-Round Discovery Toward Agentic Protein Engineering","ref_index":99,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14442","citing_title":"GGBound: A Genome-Grounded Agent for Microbial Life-Boundary Prediction","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12286","citing_title":"Set-Aggregated Genome Embeddings for Microbiome Abundance Prediction","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16570","citing_title":"In Search of Lost DNA Sequence Pretraining","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21690","citing_title":"Evaluating Post-hoc Explanations of the Transformer-based Genome Language Model DNABERT-2","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RRBTEL5UPJHM7VJIPWBSJWU4FF","json":"https://pith.science/pith/RRBTEL5UPJHM7VJIPWBSJWU4FF.json","graph_json":"https://pith.science/api/pith-number/RRBTEL5UPJHM7VJIPWBSJWU4FF/graph.json","events_json":"https://pith.science/api/pith-number/RRBTEL5UPJHM7VJIPWBSJWU4FF/events.json","paper":"https://pith.science/paper/RRBTEL5U"},"agent_actions":{"view_html":"https://pith.science/pith/RRBTEL5UPJHM7VJIPWBSJWU4FF","download_json":"https://pith.science/pith/RRBTEL5UPJHM7VJIPWBSJWU4FF.json","view_paper":"https://pith.science/paper/RRBTEL5U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.15006&json=true","fetch_graph":"https://pith.science/api/pith-number/RRBTEL5UPJHM7VJIPWBSJWU4FF/graph.json","fetch_events":"https://pith.science/api/pith-number/RRBTEL5UPJHM7VJIPWBSJWU4FF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RRBTEL5UPJHM7VJIPWBSJWU4FF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RRBTEL5UPJHM7VJIPWBSJWU4FF/action/storage_attestation","attest_author":"https://pith.science/pith/RRBTEL5UPJHM7VJIPWBSJWU4FF/action/author_attestation","sign_citation":"https://pith.science/pith/RRBTEL5UPJHM7VJIPWBSJWU4FF/action/citation_signature","submit_replication":"https://pith.science/pith/RRBTEL5UPJHM7VJIPWBSJWU4FF/action/replication_record"}},"created_at":"2026-07-05T07:57:41.362547+00:00","updated_at":"2026-07-05T07:57:41.362547+00:00"}