{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6RLVP255NRNIYKXWU4MDEVRQVC","short_pith_number":"pith:6RLVP255","schema_version":"1.0","canonical_sha256":"f45757ebbd6c5a8c2af6a718325630a8a561cf618ddcfc6f4a92af1fc845bb6d","source":{"kind":"arxiv","id":"2502.10807","version":2},"attestation_state":"computed","paper":{"title":"HybriDNA: A Hybrid Transformer-Mamba2 Long-Range DNA Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","q-bio.GN"],"primary_cat":"cs.LG","authors_text":"Albert Gu, Chuan Cao, Guoqing Liu, Haiguang Liu, Mingqian Ma, Pan Deng, Peiran Jin, Pipi Hu, Renqian Luo, Tao Qin, Tri Dao, Yingce Xia, Yuan-Jyue Chen, Zhao Yang, Zun Wang","submitted_at":"2025-02-15T14:23:43Z","abstract_excerpt":"Advances in natural language processing and large language models have sparked growing interest in modeling DNA, often referred to as the \"language of life\". However, DNA modeling poses unique challenges. First, it requires the ability to process ultra-long DNA sequences while preserving single-nucleotide resolution, as individual nucleotides play a critical role in DNA function. Second, success in this domain requires excelling at both generative and understanding tasks: generative tasks hold potential for therapeutic and industrial applications, while understanding tasks provide crucial insi"},"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":"2502.10807","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-15T14:23:43Z","cross_cats_sorted":["cs.AI","q-bio.GN"],"title_canon_sha256":"0088b97ac3d23080f70a73c3d2ada7c024916ddcc0740f49a44560373319d681","abstract_canon_sha256":"67c67865f64e209358873499f6657f91795370711b57f2214f710279098c0551"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:49.546721Z","signature_b64":"n94us0kI+5b7y6xRakkEWo3F+Xk3Wvny+I8hSmAMMf83uAC7h2rJaa+XMlJFVpA86pkfV952r5hugddclfjDBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f45757ebbd6c5a8c2af6a718325630a8a561cf618ddcfc6f4a92af1fc845bb6d","last_reissued_at":"2026-07-05T10:15:49.546132Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:49.546132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HybriDNA: A Hybrid Transformer-Mamba2 Long-Range DNA Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","q-bio.GN"],"primary_cat":"cs.LG","authors_text":"Albert Gu, Chuan Cao, Guoqing Liu, Haiguang Liu, Mingqian Ma, Pan Deng, Peiran Jin, Pipi Hu, Renqian Luo, Tao Qin, Tri Dao, Yingce Xia, Yuan-Jyue Chen, Zhao Yang, Zun Wang","submitted_at":"2025-02-15T14:23:43Z","abstract_excerpt":"Advances in natural language processing and large language models have sparked growing interest in modeling DNA, often referred to as the \"language of life\". However, DNA modeling poses unique challenges. First, it requires the ability to process ultra-long DNA sequences while preserving single-nucleotide resolution, as individual nucleotides play a critical role in DNA function. Second, success in this domain requires excelling at both generative and understanding tasks: generative tasks hold potential for therapeutic and industrial applications, while understanding tasks provide crucial insi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10807","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/2502.10807/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":"2502.10807","created_at":"2026-07-05T10:15:49.546209+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.10807v2","created_at":"2026-07-05T10:15:49.546209+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10807","created_at":"2026-07-05T10:15:49.546209+00:00"},{"alias_kind":"pith_short_12","alias_value":"6RLVP255NRNI","created_at":"2026-07-05T10:15:49.546209+00:00"},{"alias_kind":"pith_short_16","alias_value":"6RLVP255NRNIYKXW","created_at":"2026-07-05T10:15:49.546209+00:00"},{"alias_kind":"pith_short_8","alias_value":"6RLVP255","created_at":"2026-07-05T10:15:49.546209+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17765","citing_title":"AURORA: Contextual Orthogonalization for Geometric Representation Learning in Healthcare Foundation Models","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08685","citing_title":"Event Fields: Learning Latent Event Structure for Waveform Foundation Models","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09765","citing_title":"WISTERIA: Learning Clinical Representations from Noisy Supervision via Multi-View Consistency in Electronic Health Records","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6RLVP255NRNIYKXWU4MDEVRQVC","json":"https://pith.science/pith/6RLVP255NRNIYKXWU4MDEVRQVC.json","graph_json":"https://pith.science/api/pith-number/6RLVP255NRNIYKXWU4MDEVRQVC/graph.json","events_json":"https://pith.science/api/pith-number/6RLVP255NRNIYKXWU4MDEVRQVC/events.json","paper":"https://pith.science/paper/6RLVP255"},"agent_actions":{"view_html":"https://pith.science/pith/6RLVP255NRNIYKXWU4MDEVRQVC","download_json":"https://pith.science/pith/6RLVP255NRNIYKXWU4MDEVRQVC.json","view_paper":"https://pith.science/paper/6RLVP255","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.10807&json=true","fetch_graph":"https://pith.science/api/pith-number/6RLVP255NRNIYKXWU4MDEVRQVC/graph.json","fetch_events":"https://pith.science/api/pith-number/6RLVP255NRNIYKXWU4MDEVRQVC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6RLVP255NRNIYKXWU4MDEVRQVC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6RLVP255NRNIYKXWU4MDEVRQVC/action/storage_attestation","attest_author":"https://pith.science/pith/6RLVP255NRNIYKXWU4MDEVRQVC/action/author_attestation","sign_citation":"https://pith.science/pith/6RLVP255NRNIYKXWU4MDEVRQVC/action/citation_signature","submit_replication":"https://pith.science/pith/6RLVP255NRNIYKXWU4MDEVRQVC/action/replication_record"}},"created_at":"2026-07-05T10:15:49.546209+00:00","updated_at":"2026-07-05T10:15:49.546209+00:00"}