{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FY32WNTCRTU4236QG4XFOVUZBM","short_pith_number":"pith:FY32WNTC","schema_version":"1.0","canonical_sha256":"2e37ab36628ce9cd6fd0372e5756990b19af86a94dfcf1c246a8239fdb13e010","source":{"kind":"arxiv","id":"2608.05329","version":1},"attestation_state":"computed","paper":{"title":"Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.GN","authors_text":"M. Sohel Rahman, Nirjhor Datta, Swakkhar Shatabda","submitted_at":"2026-08-05T18:37:06Z","abstract_excerpt":"Genomic foundation models are increasingly reused as frozen feature extractors for downstream sequence prediction, offering a compute-efficient alternative to full fine-tuning. However, it remains unclear when biological information encoded by these models is accessible without task-specific adaptation. We present a representation-accessibility analysis of frozen genomic language models across regulatory, epigenetic, promoter, splice-site, and variant-effect prediction tasks. We evaluate DNABERT-2, Nucleotide Transformer, HyenaDNA, GENERATOR-v2, and Omni-DNA under unified frozen-probing protoc"},"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":"2608.05329","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2026-08-05T18:37:06Z","cross_cats_sorted":[],"title_canon_sha256":"c912cb92c70ec46508b56b96e17c55a774abe165f3327a0e3228d0bde88bfe0d","abstract_canon_sha256":"a43b6267c471d52e8a7485bc1a195d89d3d17ea9fe9c34f0c908607472e07a44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T00:47:01.378267Z","signature_b64":"OeJT6nLKUDpO6hg+OyHITNPgmatxmZKsM80upcMTD5ENdEkAMFldHXmiD4ANaRleM0owYqXdcIQTL3fhmjasDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e37ab36628ce9cd6fd0372e5756990b19af86a94dfcf1c246a8239fdb13e010","last_reissued_at":"2026-08-07T00:47:01.376715Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T00:47:01.376715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.GN","authors_text":"M. Sohel Rahman, Nirjhor Datta, Swakkhar Shatabda","submitted_at":"2026-08-05T18:37:06Z","abstract_excerpt":"Genomic foundation models are increasingly reused as frozen feature extractors for downstream sequence prediction, offering a compute-efficient alternative to full fine-tuning. However, it remains unclear when biological information encoded by these models is accessible without task-specific adaptation. We present a representation-accessibility analysis of frozen genomic language models across regulatory, epigenetic, promoter, splice-site, and variant-effect prediction tasks. We evaluate DNABERT-2, Nucleotide Transformer, HyenaDNA, GENERATOR-v2, and Omni-DNA under unified frozen-probing protoc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05329","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/2608.05329/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":"2608.05329","created_at":"2026-08-07T00:47:01.378140+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.05329v1","created_at":"2026-08-07T00:47:01.378140+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05329","created_at":"2026-08-07T00:47:01.378140+00:00"},{"alias_kind":"pith_short_12","alias_value":"FY32WNTCRTU4","created_at":"2026-08-07T00:47:01.378140+00:00"},{"alias_kind":"pith_short_16","alias_value":"FY32WNTCRTU4236Q","created_at":"2026-08-07T00:47:01.378140+00:00"},{"alias_kind":"pith_short_8","alias_value":"FY32WNTC","created_at":"2026-08-07T00:47:01.378140+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FY32WNTCRTU4236QG4XFOVUZBM","json":"https://pith.science/pith/FY32WNTCRTU4236QG4XFOVUZBM.json","graph_json":"https://pith.science/api/pith-number/FY32WNTCRTU4236QG4XFOVUZBM/graph.json","events_json":"https://pith.science/api/pith-number/FY32WNTCRTU4236QG4XFOVUZBM/events.json","paper":"https://pith.science/paper/FY32WNTC"},"agent_actions":{"view_html":"https://pith.science/pith/FY32WNTCRTU4236QG4XFOVUZBM","download_json":"https://pith.science/pith/FY32WNTCRTU4236QG4XFOVUZBM.json","view_paper":"https://pith.science/paper/FY32WNTC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.05329&json=true","fetch_graph":"https://pith.science/api/pith-number/FY32WNTCRTU4236QG4XFOVUZBM/graph.json","fetch_events":"https://pith.science/api/pith-number/FY32WNTCRTU4236QG4XFOVUZBM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FY32WNTCRTU4236QG4XFOVUZBM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FY32WNTCRTU4236QG4XFOVUZBM/action/storage_attestation","attest_author":"https://pith.science/pith/FY32WNTCRTU4236QG4XFOVUZBM/action/author_attestation","sign_citation":"https://pith.science/pith/FY32WNTCRTU4236QG4XFOVUZBM/action/citation_signature","submit_replication":"https://pith.science/pith/FY32WNTCRTU4236QG4XFOVUZBM/action/replication_record"}},"created_at":"2026-08-07T00:47:01.378140+00:00","updated_at":"2026-08-07T00:47:01.378140+00:00"}