{"id":"W6921022441","doi":"10.6084/m9.figshare.26596100","title":"Additional file 6 of Matchtigs: minimum plain text representation of k-mer sets","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Representation (politics); Set (abstract data type); Plain text; Window (computing)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00001539182,0.00006685001,0.00009565279,0.00007221609,0.0000291845,0.00004679278,0.0003521335,0.00004399906,0.9718763],"category_scores_gemma":[0.0004509984,0.00005859358,0.00005804435,0.0002874014,0.0000071109,0.0004247683,0.0002594738,0.00006430333,0.001578458],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008753635,"about_ca_system_score_gemma":0.00008146845,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004407384,"about_ca_topic_score_gemma":8.933894e-7,"domain_scores_codex":[0.9992434,0.00002187172,0.0001719256,0.0002216687,0.0002502887,0.0000908869],"domain_scores_gemma":[0.9985138,0.0009911328,0.0000781145,0.0003008535,0.00008153739,0.00003462127],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001043609,0.00001401957,1.27344e-7,0.00008545444,0.000006764417,0.000008837125,0.00007420282,0.000009560737,0.00003095794,0.00005477026,0.9824201,0.01729417],"study_design_scores_gemma":[0.00004588709,0.00002712251,0.0005058226,0.003197005,0.000001436353,0.000009507872,0.00001827382,0.07432179,0.0008707021,0.0003979892,0.920523,0.00008141283],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.000003722833,0.00008221761,0.0002724385,0.00004630477,0.00004806816,0.00006430117,0.9966615,0.00005564568,0.002765793],"genre_scores_gemma":[0.0007462706,7.157423e-7,0.01354464,0.00003326018,0.00006040414,0.0001498387,0.9846954,0.000006459207,0.0007629729],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.9702979,"threshold_uncertainty_score":0.9991989,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03038355100818139,"score_gpt":0.2753442938230059,"score_spread":0.2449607428148245,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}