{"id":"W6921126819","doi":"10.6084/m9.figshare.26596085.v1","title":"Additional file 1 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":"Focus (optics); Representation (politics); Window (computing); Simple (philosophy)","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":[0.00001537587,0.00006684692,0.00009559723,0.00007221004,0.00002917479,0.00004664996,0.000352208,0.00004399916,0.9734361],"category_scores_gemma":[0.0004564339,0.00005859364,0.00005803931,0.0002874415,0.000007108284,0.0004242741,0.0002595477,0.00006430643,0.00160499],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008763513,"about_ca_system_score_gemma":0.00008165016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000429754,"about_ca_topic_score_gemma":8.610153e-7,"domain_scores_codex":[0.9992436,0.00002187697,0.000171767,0.0002217175,0.0002502292,0.0000908748],"domain_scores_gemma":[0.9985039,0.001000476,0.00007808721,0.0003012529,0.00008169739,0.0000346165],"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":[0.000001036944,0.00001394234,1.277056e-7,0.00008453523,0.000006770702,0.000008684927,0.00007390619,0.000009735979,0.00003121354,0.0000523593,0.9827095,0.01700817],"study_design_scores_gemma":[0.00004512858,0.00002691182,0.000498345,0.003178209,0.000001430576,0.000009453811,0.00001816852,0.07458249,0.00086477,0.0003899415,0.9203042,0.0000809226],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.000003718448,0.00008117357,0.000268818,0.00004630769,0.0000480154,0.00006413029,0.9967127,0.00005562535,0.002719542],"genre_scores_gemma":[0.0007200051,7.021085e-7,0.01365711,0.000033076,0.0000600276,0.0001522579,0.984609,0.000006431493,0.000761394],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.9718311,"threshold_uncertainty_score":0.9991724,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03103496098622592,"score_gpt":0.275710049284035,"score_spread":0.244675088297809,"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."}}