{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:E7GRV62IZUZNMHGSZRPCS7B23F","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":"c2ab0b706e2245ba3cf7460c78b1e835589ed3038c758bb4a3184ce580e28423","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-29T09:17:16Z","title_canon_sha256":"af0da1c70890ec61a046cd9236206ee5d1990128bc709b54d0fa72d986691797"},"schema_version":"1.0","source":{"id":"2307.15933","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.15933","created_at":"2026-07-05T07:00:25Z"},{"alias_kind":"arxiv_version","alias_value":"2307.15933v1","created_at":"2026-07-05T07:00:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.15933","created_at":"2026-07-05T07:00:25Z"},{"alias_kind":"pith_short_12","alias_value":"E7GRV62IZUZN","created_at":"2026-07-05T07:00:25Z"},{"alias_kind":"pith_short_16","alias_value":"E7GRV62IZUZNMHGS","created_at":"2026-07-05T07:00:25Z"},{"alias_kind":"pith_short_8","alias_value":"E7GRV62I","created_at":"2026-07-05T07:00:25Z"}],"graph_snapshots":[{"event_id":"sha256:0e48910c35729991e9393cce920ff054f9ce806510258639c03e94eecaff9be5","target":"graph","created_at":"2026-07-05T07:00:25Z","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/2307.15933/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale language models such as DNABert and LOGO aim to learn optimal gene representations and are trained on the entire Human Reference Genome. However, standard tokenization schemes involve a simple sliding window of tokens like k-mers that do not leverage any gene-based semantics and thus may lead to (trivial) masking of easily predictable sequences and subsequently inefficient Masked Language Modeling (MLM) training. Therefore, we propose a novel masking algorithm, GeneMask, for MLM training of gene sequences, where we randomly identify positions in a gene sequence as mask centers and ","authors_text":"Jonas Wallat, Niloy Ganguly, Soumyadeep Roy, Sowmya S Sundaram, Wolfgang Nejdl","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-29T09:17:16Z","title":"GeneMask: Fast Pretraining of Gene Sequences to Enable Few-Shot Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.15933","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:b1202ae1ccccf96c05b919288687f3946521802d6c2a2595053129d16ec79969","target":"record","created_at":"2026-07-05T07:00:25Z","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":"c2ab0b706e2245ba3cf7460c78b1e835589ed3038c758bb4a3184ce580e28423","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-29T09:17:16Z","title_canon_sha256":"af0da1c70890ec61a046cd9236206ee5d1990128bc709b54d0fa72d986691797"},"schema_version":"1.0","source":{"id":"2307.15933","kind":"arxiv","version":1}},"canonical_sha256":"27cd1afb48cd32d61cd2cc5e297c3ad96837e1cbf648039fdfa9a36efa241eaa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27cd1afb48cd32d61cd2cc5e297c3ad96837e1cbf648039fdfa9a36efa241eaa","first_computed_at":"2026-07-05T07:00:25.965631Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:00:25.965631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GlcDrzRdVGyUgeEjlYuf/7JDBsloS0qOUaRB4C7xeOQb300ez7YDwE5zv+nrzKHyU6s65jcohcY3Jqy4d1iuCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:00:25.966187Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.15933","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b1202ae1ccccf96c05b919288687f3946521802d6c2a2595053129d16ec79969","sha256:0e48910c35729991e9393cce920ff054f9ce806510258639c03e94eecaff9be5"],"state_sha256":"8a550a14622e3f5c16d449dabb2237a1fe1a6e0539ebfb1d212a0d0260a4f722"}