{"id":"W7101397496","doi":"10.5281/zenodo.17458967","title":"Zero-Shot Protein Segmentation (ZPS) Data and Embeddings","year":2025,"lang":"","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"","keywords":"UniProt; Parsing; Segmentation; Human proteome project; Search engine indexing; Proteome; Human proteins; File format","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":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001533702,0.0005353715,0.0003946066,0.0003541103,0.002817345,0.001855531,0.003573873,0.000494314,0.00395026],"category_scores_gemma":[0.002676459,0.0006093638,0.00007236968,0.0004915894,0.0004240676,0.00007359149,0.01270021,0.0009127002,0.0009318951],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001151626,"about_ca_system_score_gemma":0.00003177299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003220313,"about_ca_topic_score_gemma":8.326954e-7,"domain_scores_codex":[0.9959932,0.0007027767,0.0007891845,0.001293257,0.0005815755,0.0006399886],"domain_scores_gemma":[0.9959266,0.00002479365,0.0005668394,0.002542665,0.0006499153,0.0002892564],"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":[0.0001616365,0.0001496248,0.000001312411,0.001101494,0.0002147429,0.000007103828,0.0002126471,0.00003325791,0.01076725,0.0001116912,0.9357111,0.05152813],"study_design_scores_gemma":[0.0009050401,0.0006389419,0.00001314504,0.0002521445,0.0001209131,0.0001274637,0.0002433026,0.0021775,0.001435215,0.00002372641,0.9935067,0.0005559465],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.003224957,0.0008424246,0.01562719,0.0009601373,0.0003666216,0.003212304,0.9487823,0.0003168369,0.02666722],"genre_scores_gemma":[0.005042505,0.001410256,0.002156419,0.0003346166,0.0002597727,1.980819e-7,0.9875871,0.0008178251,0.002391302],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.05779556,"threshold_uncertainty_score":0.999846,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02744503348056311,"score_gpt":0.2919406257354329,"score_spread":0.2644955922548698,"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."}}