{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XUTUUO4UI5BIE3OYIJ2LWMZPYM","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"492f3fb6a495cadcac7f9ead1a6584b141393dbcfdecc9581ef7c53eb1cceb8c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"q-bio.GN","submitted_at":"2025-06-26T13:56:32Z","title_canon_sha256":"cb39b2e9e9162aecc247097d74f29a0035afeda5c89ce0a3b8fcec6e97697183"},"schema_version":"1.0","source":{"id":"2507.05265","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.05265","created_at":"2026-07-05T11:33:27Z"},{"alias_kind":"arxiv_version","alias_value":"2507.05265v1","created_at":"2026-07-05T11:33:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05265","created_at":"2026-07-05T11:33:27Z"},{"alias_kind":"pith_short_12","alias_value":"XUTUUO4UI5BI","created_at":"2026-07-05T11:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"XUTUUO4UI5BIE3OY","created_at":"2026-07-05T11:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"XUTUUO4U","created_at":"2026-07-05T11:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:a107d091ed3422a30a7fdbba3f9df9e53701e725772de86cb881ccfdfeeac4db","target":"graph","created_at":"2026-07-05T11:33:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.05265/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) trained on text demonstrated remarkable results on natural language processing (NLP) tasks. These models have been adapted to decipher the language of DNA, where sequences of nucleotides act as \"words\" that encode genomic functions. However, the genome differs fundamentally from natural language, as it lacks clearly defined words or a consistent grammar. Although DNA language models (DNALMs) such as DNABERT, GENA-LM have achieved high level of performance on genome-related biological tasks, these models do not encode biological functions in the presence of sequence","authors_text":"Bharath Dandala, Bum Chul Kwon, Ching-Huei Tsou, Hongyang Li, James Kozloski, Jianying Hu, Michael Danziger, Michal Rosen-Tzvi, Pablo Meyer, Sanjoy Dey","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"q-bio.GN","submitted_at":"2025-06-26T13:56:32Z","title":"BMFM-DNA: A SNP-aware DNA foundation model to capture variant effects"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05265","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cd0d975adb0346766dc3bf4d378536155ce3551119dbb2a2457789fada054d2a","target":"record","created_at":"2026-07-05T11:33:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"492f3fb6a495cadcac7f9ead1a6584b141393dbcfdecc9581ef7c53eb1cceb8c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"q-bio.GN","submitted_at":"2025-06-26T13:56:32Z","title_canon_sha256":"cb39b2e9e9162aecc247097d74f29a0035afeda5c89ce0a3b8fcec6e97697183"},"schema_version":"1.0","source":{"id":"2507.05265","kind":"arxiv","version":1}},"canonical_sha256":"bd274a3b944742826dd84274bb332fc328c5d44154424e4e42c494149f9b9398","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd274a3b944742826dd84274bb332fc328c5d44154424e4e42c494149f9b9398","first_computed_at":"2026-07-05T11:33:27.283647Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:27.283647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g+wjnjcgVM+CS1ubXeRlnmPxk+7cTUj/NwgMMTvDzxd+qGEx8L3Q7VKj0sfEO+BGdfyJsIfw51uLmBDmgPLkBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:27.284120Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.05265","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd0d975adb0346766dc3bf4d378536155ce3551119dbb2a2457789fada054d2a","sha256:a107d091ed3422a30a7fdbba3f9df9e53701e725772de86cb881ccfdfeeac4db"],"state_sha256":"d15677b8591f078486f4c187c3bc39d7efa4f390666617f3508809911aceccd3"}