{"id":"W7108644313","doi":"10.5281/zenodo.17811473","title":"Simple and Effective Semantic Song Segmentation","year":2025,"lang":"","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Music and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Spectrogram; Convolutional neural network; Set (abstract data type); Segmentation; Training set; Deep learning; Semantics (computer science); Pattern recognition (psychology)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0009589379,0.0002246368,0.0002263383,0.0003618455,0.004656768,0.003503829,0.001051375,0.00008966911,0.001903741],"category_scores_gemma":[0.0004562922,0.000249606,0.00005132348,0.001254558,0.0002757696,0.0008275213,0.002709053,0.00032837,0.001301263],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001812105,"about_ca_system_score_gemma":0.00001218902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001920415,"about_ca_topic_score_gemma":2.999317e-7,"domain_scores_codex":[0.9974739,0.0005555671,0.0003378781,0.0007877058,0.0003607975,0.0004841648],"domain_scores_gemma":[0.9985754,0.00006734773,0.0001687642,0.0004694093,0.0005511049,0.0001679483],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004169136,0.0001033262,0.000023152,0.0004260865,0.00007341457,0.00001259617,0.002931278,0.00006362058,0.005106239,0.008119787,0.0463942,0.9367046],"study_design_scores_gemma":[0.001946915,0.0006383351,0.00666351,0.0005475243,0.0001050506,0.0001154355,0.0008887587,0.06277017,0.006769957,0.004283113,0.9146522,0.0006190887],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04182648,0.0008880186,0.876418,0.003117003,0.0004183571,0.00132142,0.00005224774,0.0008225502,0.07513593],"genre_scores_gemma":[0.9965161,0.0001497474,0.0008454004,0.0007628778,0.0001111605,6.946521e-8,0.0001655464,0.0004738332,0.0009752715],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9546896,"threshold_uncertainty_score":0.9999956,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01879698264052648,"score_gpt":0.2606456550458555,"score_spread":0.241848672405329,"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."}}