{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:O6GUERMUX5XG5PKRD6JAHWWU5W","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":"440affbc27309f38ef9711e24eec8c2c9db9149378f4eb36027bea9f44f699ec","cross_cats_sorted":["stat.AP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2022-09-23T17:23:59Z","title_canon_sha256":"80e3313ecb2126cbdbae65e44c5f000e22b5084902695bc328480abe47b15250"},"schema_version":"1.0","source":{"id":"2209.11730","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.11730","created_at":"2026-07-05T09:48:58Z"},{"alias_kind":"arxiv_version","alias_value":"2209.11730v3","created_at":"2026-07-05T09:48:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.11730","created_at":"2026-07-05T09:48:58Z"},{"alias_kind":"pith_short_12","alias_value":"O6GUERMUX5XG","created_at":"2026-07-05T09:48:58Z"},{"alias_kind":"pith_short_16","alias_value":"O6GUERMUX5XG5PKR","created_at":"2026-07-05T09:48:58Z"},{"alias_kind":"pith_short_8","alias_value":"O6GUERMU","created_at":"2026-07-05T09:48:58Z"}],"graph_snapshots":[{"event_id":"sha256:25b3e1606de85a509dfae4f7886f6721cb4f205ae36bf19e6df3a6dbcd223e0b","target":"graph","created_at":"2026-07-05T09:48:58Z","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/2209.11730/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Summary: Accurate phenotype prediction from genomic sequences is a highly coveted task in biological and medical research. While machine-learning holds the key to accurate prediction in a variety of fields, the complexity of biological data can render many methodologies inapplicable. We introduce BioKlustering, a user-friendly open-source and publicly available web app for unsupervised and semi-supervised learning specialized for cases when sequence alignment and/or experimental phenotyping of all classes are not possible. Among its main advantages, BioKlustering 1) allows for maximally imbala","authors_text":"Chunrong Huang, Claudia Solis-Lemus, Hailey Bruzzone, Helena Jaramillo-Mesa, Liule Yang, Luke Selberg, Samuel Ozminkowski, Yuke Wu, Zhiwen Xu","cross_cats":["stat.AP"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2022-09-23T17:23:59Z","title":"BioKlustering: a web app for semi-supervised learning of maximally imbalanced genomic data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.11730","kind":"arxiv","version":3},"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":"sha256:0be11dd8c93fbadae322cf697587163ef0d3c4997118f640a8cc567413a0cfc4","target":"record","created_at":"2026-07-05T09:48:58Z","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":"440affbc27309f38ef9711e24eec8c2c9db9149378f4eb36027bea9f44f699ec","cross_cats_sorted":["stat.AP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2022-09-23T17:23:59Z","title_canon_sha256":"80e3313ecb2126cbdbae65e44c5f000e22b5084902695bc328480abe47b15250"},"schema_version":"1.0","source":{"id":"2209.11730","kind":"arxiv","version":3}},"canonical_sha256":"778d424594bf6e6ebd511f9203dad4eda7a4a0a481bd0f4b794ec50f2d2265c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"778d424594bf6e6ebd511f9203dad4eda7a4a0a481bd0f4b794ec50f2d2265c7","first_computed_at":"2026-07-05T09:48:58.672286Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:48:58.672286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0KmeywavtdMpk+0wr3E4KZKT1SHcIZH04sfduqyEUEKoXlLUOTSa7liRQ4y0nTIDZz3C2zQDrWNxidJ0KmFFCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:48:58.673065Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.11730","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0be11dd8c93fbadae322cf697587163ef0d3c4997118f640a8cc567413a0cfc4","sha256:25b3e1606de85a509dfae4f7886f6721cb4f205ae36bf19e6df3a6dbcd223e0b"],"state_sha256":"ec07242106eee19f50a2b9056f77c6d72626ba747fe6bcd74c532ddc6dd6792c"}