{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NXFTGE4WO3V5LIH22UZXNEY5BX","short_pith_number":"pith:NXFTGE4W","schema_version":"1.0","canonical_sha256":"6dcb33139676ebd5a0fad53376931d0dcee50fb52905ac2ed9b6043bf2b48ccb","source":{"kind":"arxiv","id":"2602.17162","version":2},"attestation_state":"computed","paper":{"title":"JEPA-DNA: Grounding Genomic Foundation Models through Joint-Embedding Predictive Architectures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.GN"],"primary_cat":"cs.AI","authors_text":"Alexander W. Charney, Amit Bleiweiss, Ariel Larey, Dan Dominissini, Dan Ofer, Dung Hoang, Elay Dahan, Gideon Rechavi, Guy Leib, Marissa Wirth, Nati Daniel, Nicole Bussola, Omri Nayshool, Raizy Kellerman, Shane O'Connell, Simon Lee, Tal Zinger, Yoli Shavit","submitted_at":"2026-02-19T08:20:51Z","abstract_excerpt":"Genomic Foundation Models (GFMs) typically rely on Masked Language Modeling (MLM) or Next-Token Prediction (NTP) to learn the \"Laws of Nature\". While effective at capturing local syntax, these generative paradigms prioritize token-level reconstruction over high-level functional context. We introduce JEPA-DNA, a model-agnostic continual training framework that integrates a Joint-Embedding Predictive Architecture (JEPA) with traditional generative objectives. By supervising global sequence embeddings in a latent space, JEPA-DNA forces models to predict the functional representations of masked ge"},"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":"2602.17162","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-02-19T08:20:51Z","cross_cats_sorted":["q-bio.GN"],"title_canon_sha256":"5665bc2222c8252a75317adbc46c4773a1dac8d980b51bad90d0b89fc9933de0","abstract_canon_sha256":"aa5207d221c189c2de3849ad4b81d1ec887ab5a7dd7310fd90bc1e2c6fe64683"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:05:07.225076Z","signature_b64":"55yiG3/a/ysma2MK4IOtCOlVYu2MO2nX4fD9ReAzFFDqE6Db9fuuEOUMCCQKb2lrNIgm0XsfOgZICIcFsUa0BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6dcb33139676ebd5a0fad53376931d0dcee50fb52905ac2ed9b6043bf2b48ccb","last_reissued_at":"2026-05-26T02:05:07.224292Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:05:07.224292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"JEPA-DNA: Grounding Genomic Foundation Models through Joint-Embedding Predictive Architectures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.GN"],"primary_cat":"cs.AI","authors_text":"Alexander W. Charney, Amit Bleiweiss, Ariel Larey, Dan Dominissini, Dan Ofer, Dung Hoang, Elay Dahan, Gideon Rechavi, Guy Leib, Marissa Wirth, Nati Daniel, Nicole Bussola, Omri Nayshool, Raizy Kellerman, Shane O'Connell, Simon Lee, Tal Zinger, Yoli Shavit","submitted_at":"2026-02-19T08:20:51Z","abstract_excerpt":"Genomic Foundation Models (GFMs) typically rely on Masked Language Modeling (MLM) or Next-Token Prediction (NTP) to learn the \"Laws of Nature\". While effective at capturing local syntax, these generative paradigms prioritize token-level reconstruction over high-level functional context. We introduce JEPA-DNA, a model-agnostic continual training framework that integrates a Joint-Embedding Predictive Architecture (JEPA) with traditional generative objectives. By supervising global sequence embeddings in a latent space, JEPA-DNA forces models to predict the functional representations of masked ge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.17162","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/2602.17162/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":"2602.17162","created_at":"2026-05-26T02:05:07.224402+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.17162v2","created_at":"2026-05-26T02:05:07.224402+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.17162","created_at":"2026-05-26T02:05:07.224402+00:00"},{"alias_kind":"pith_short_12","alias_value":"NXFTGE4WO3V5","created_at":"2026-05-26T02:05:07.224402+00:00"},{"alias_kind":"pith_short_16","alias_value":"NXFTGE4WO3V5LIH2","created_at":"2026-05-26T02:05:07.224402+00:00"},{"alias_kind":"pith_short_8","alias_value":"NXFTGE4W","created_at":"2026-05-26T02:05:07.224402+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"2605.17765","citing_title":"AURORA: Contextual Orthogonalization for Geometric Representation Learning in Healthcare Foundation Models","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04175","citing_title":"Uncertainty-Aware Foundation Models for Clinical Data","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08685","citing_title":"Event Fields: Learning Latent Event Structure for Waveform Foundation Models","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09765","citing_title":"WISTERIA: Learning Clinical Representations from Noisy Supervision via Multi-View Consistency in Electronic Health Records","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07554","citing_title":"ProteinJEPA: Latent prediction complements protein language models","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NXFTGE4WO3V5LIH22UZXNEY5BX","json":"https://pith.science/pith/NXFTGE4WO3V5LIH22UZXNEY5BX.json","graph_json":"https://pith.science/api/pith-number/NXFTGE4WO3V5LIH22UZXNEY5BX/graph.json","events_json":"https://pith.science/api/pith-number/NXFTGE4WO3V5LIH22UZXNEY5BX/events.json","paper":"https://pith.science/paper/NXFTGE4W"},"agent_actions":{"view_html":"https://pith.science/pith/NXFTGE4WO3V5LIH22UZXNEY5BX","download_json":"https://pith.science/pith/NXFTGE4WO3V5LIH22UZXNEY5BX.json","view_paper":"https://pith.science/paper/NXFTGE4W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.17162&json=true","fetch_graph":"https://pith.science/api/pith-number/NXFTGE4WO3V5LIH22UZXNEY5BX/graph.json","fetch_events":"https://pith.science/api/pith-number/NXFTGE4WO3V5LIH22UZXNEY5BX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NXFTGE4WO3V5LIH22UZXNEY5BX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NXFTGE4WO3V5LIH22UZXNEY5BX/action/storage_attestation","attest_author":"https://pith.science/pith/NXFTGE4WO3V5LIH22UZXNEY5BX/action/author_attestation","sign_citation":"https://pith.science/pith/NXFTGE4WO3V5LIH22UZXNEY5BX/action/citation_signature","submit_replication":"https://pith.science/pith/NXFTGE4WO3V5LIH22UZXNEY5BX/action/replication_record"}},"created_at":"2026-05-26T02:05:07.224402+00:00","updated_at":"2026-05-26T02:05:07.224402+00:00"}