{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5NLKD4F44VGBCYOKX26VZZMP6D","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":"84005b2a8897484143eb660fee06ed4906d90b517de3512092be99d41c46c842","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2024-05-10T14:50:40Z","title_canon_sha256":"30602ae9707f0beaccd80ce24873981dc5b495730f84d71df215b9adbb9571e7"},"schema_version":"1.0","source":{"id":"2405.06729","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.06729","created_at":"2026-07-05T08:18:11Z"},{"alias_kind":"arxiv_version","alias_value":"2405.06729v1","created_at":"2026-07-05T08:18:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.06729","created_at":"2026-07-05T08:18:11Z"},{"alias_kind":"pith_short_12","alias_value":"5NLKD4F44VGB","created_at":"2026-07-05T08:18:11Z"},{"alias_kind":"pith_short_16","alias_value":"5NLKD4F44VGBCYOK","created_at":"2026-07-05T08:18:11Z"},{"alias_kind":"pith_short_8","alias_value":"5NLKD4F4","created_at":"2026-07-05T08:18:11Z"}],"graph_snapshots":[{"event_id":"sha256:7212c896c701c60cf6dc2de3911eeb5fd3c490c588ee797b28a204dd574e43a1","target":"graph","created_at":"2026-07-05T08:18:11Z","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/2405.06729/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Protein Language Models (PLMs) have emerged as performant and scalable tools for predicting the functional impact and clinical significance of protein-coding variants, but they still lag experimental accuracy. Here, we present a novel fine-tuning approach to improve the performance of PLMs with experimental maps of variant effects from Deep Mutational Scanning (DMS) assays using a Normalised Log-odds Ratio (NLR) head. We find consistent improvements in a held-out protein test set, and on independent DMS and clinical variant annotation benchmarks from ProteinGym and ClinVar. These findings demo","authors_text":"Aleix Lafita, Ari Allyn-Feuer, Daniel Seaton, Ferran Gonzalez, Jacob Deasy, Mahmoud Hossam, Paul Smyth, Stephen Young","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2024-05-10T14:50:40Z","title":"Fine-tuning Protein Language Models with Deep Mutational Scanning improves Variant Effect Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.06729","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:d758470125bf3849457a8d43f8516237a6f3b75b303be438144a9778c02b621d","target":"record","created_at":"2026-07-05T08:18:11Z","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":"84005b2a8897484143eb660fee06ed4906d90b517de3512092be99d41c46c842","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2024-05-10T14:50:40Z","title_canon_sha256":"30602ae9707f0beaccd80ce24873981dc5b495730f84d71df215b9adbb9571e7"},"schema_version":"1.0","source":{"id":"2405.06729","kind":"arxiv","version":1}},"canonical_sha256":"eb56a1f0bce54c1161cabebd5ce58ff0fc489ceb473529756d1cbf90569eac7b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eb56a1f0bce54c1161cabebd5ce58ff0fc489ceb473529756d1cbf90569eac7b","first_computed_at":"2026-07-05T08:18:11.010780Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:18:11.010780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DeTjYnRWNHnGaEWp6aPjmdr0XIenLFxYA+a0G31NG+TdckYrXnGjdT0p+tBIwuwoDAvLM6mQ5IDe2TkMBZkxAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:18:11.011255Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.06729","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d758470125bf3849457a8d43f8516237a6f3b75b303be438144a9778c02b621d","sha256:7212c896c701c60cf6dc2de3911eeb5fd3c490c588ee797b28a204dd574e43a1"],"state_sha256":"454775a26fe799d3b4114807c4c1ef166a219ca119473a0d4f3b0f9a393ae8be"}