{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":4,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":4,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"2a2bee68baa3","filters":{"venue":"2022 IEEE Biomedical Circuits and Systems Conference (BioCAS)"}},"results":[{"id":"W4309270060","doi":"10.1109/biocas54905.2022.9948614","title":"Classify Respiratory Abnormality in Lung Sounds Using STFT and a Fine-Tuned ResNet18 Network","year":2022,"lang":"en","type":"article","venue":"2022 IEEE Biomedical Circuits and Systems Conference (BioCAS)","topic":"Phonocardiography and Auscultation Techniques","field":"Medicine","cited_by":38,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Spectrogram; Short-time Fourier transform; Speech recognition; Computer science; Crackles; Feature extraction; Respiratory sounds; Pattern recognition (psychology); Artificial intelligence; Bioacoustics; Abnormality; Fourier transform; Lung; Fourier analysis; Medicine; Mathematics; Telecommunications","retraction":null,"screen_n_in":null,"score":{"opus":0.06807724960689192,"gpt":0.3053152979358064,"spread":0.2372380483289144,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002496456,0.0002644272,0.0006863307,0.0004048065,0.0004153817,0.00009220681,0.0001962133,0.000215742,0.0001100994],"category_scores_gemma":[0.0001185,0.0002428643,0.0001078095,0.0009822528,0.0003653298,0.0001253167,0.000176868,0.0006572849,9.06096e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000133524,"about_ca_system_score_gemma":0.0002982062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000292789,"about_ca_topic_score_gemma":0.00002589723,"domain_scores_codex":[0.9967864,0.0006747283,0.0007291812,0.0006016913,0.0007124268,0.0004955739],"domain_scores_gemma":[0.9987457,0.0001703787,0.0002174207,0.0004065974,0.00009743716,0.0003624928],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001609274,0.001699315,0.6354108,0.007556531,0.001771702,0.004154238,0.01037009,0.0001605331,0.1504881,0.03297089,0.07262754,0.08118097],"study_design_scores_gemma":[0.02706686,0.007496634,0.5837206,0.005613707,0.001468693,0.00467993,0.02010486,0.08309112,0.001509425,0.008697149,0.2512541,0.005296847],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9836501,0.008030287,0.004567938,0.0002699675,0.0009217976,0.001094716,0.0001588342,0.0001727773,0.001133543],"genre_scores_gemma":[0.9986407,0.0001545868,0.00004919153,0.000391038,0.000338002,0.0001718806,0.00005341234,0.00002270651,0.0001784728],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1786266,"threshold_uncertainty_score":0.9903717,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4309242540","doi":"10.1109/biocas54905.2022.9948611","title":"Prediction of Protein-Protein Interactions through Deep Learning Based on Sequence Feature Extraction and Interaction Network","year":2022,"lang":"en","type":"article","venue":"2022 IEEE Biomedical Circuits and Systems Conference (BioCAS)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Ministry of Education; Ministry of Science and Technology","keywords":"Computer science; Artificial intelligence; Artificial neural network; Machine learning; Deep learning; Process (computing); Feature extraction; Cross-validation; Field (mathematics); Protein function prediction; Set (abstract data type); Sequence (biology); Test set; Pattern recognition (psychology); Data mining; Protein function; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.03705778356705998,"gpt":0.2796034131993648,"spread":0.2425456296323049,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005890418,0.0002128834,0.0002495931,0.0001000476,0.0004302746,0.00007226263,0.0001420468,0.0001716862,0.00008699388],"category_scores_gemma":[0.0001690708,0.0002024257,0.00005835309,0.0002168003,0.0001484385,0.00003083154,0.00009022788,0.0007510924,0.000002031452],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006154527,"about_ca_system_score_gemma":0.00008612303,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009411873,"about_ca_topic_score_gemma":0.00001031562,"domain_scores_codex":[0.9980872,0.0004078329,0.0004183815,0.0004009456,0.0004336101,0.0002520343],"domain_scores_gemma":[0.9990821,0.00005197565,0.0004078532,0.0002443806,0.0001015699,0.000112076],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003435455,0.0002821433,0.003003024,0.0008125025,0.0001524254,0.00001800267,0.0009026518,0.01341571,0.938752,0.001351002,0.001601489,0.03936549],"study_design_scores_gemma":[0.002116048,0.005428127,0.002868797,0.0008513054,0.0001011318,0.0005520198,0.0038405,0.7334126,0.008495771,0.0001398532,0.2413823,0.0008116019],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8980055,0.0006134456,0.09531568,0.0005002244,0.001959287,0.001364151,0.0001813664,0.00008559854,0.001974753],"genre_scores_gemma":[0.9981004,0.00004780453,0.0001734953,0.00007666092,0.0003130168,0.0001982759,0.000399089,0.00002048636,0.0006707874],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9302562,"threshold_uncertainty_score":0.8254682,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4309263363","doi":"10.1109/biocas54905.2022.9948580","title":"Spike Compression through Selective Downsampling and Piecewise Curve Fitting Dedicated to Neural Recording Brain Implants","year":2022,"lang":"en","type":"article","venue":"2022 IEEE Biomedical Circuits and Systems Conference (BioCAS)","topic":"Neuroscience and Neural Engineering","field":"Neuroscience","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Upsampling; Spike (software development); Brain implant; Computer science; CMOS; Piecewise; Artificial neural network; Data compression; Companding; Neuromorphic engineering; Application-specific integrated circuit; Artificial intelligence; Algorithm; Electronic engineering; Channel (broadcasting); Computer hardware; Mathematics; Engineering; Telecommunications","retraction":null,"screen_n_in":null,"score":{"opus":0.0861887668677823,"gpt":0.2963537313995677,"spread":0.2101649645317854,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007313824,0.0003556479,0.0005114021,0.0002778905,0.001194096,0.0002777897,0.0004965952,0.0001036804,0.00005111587],"category_scores_gemma":[0.0006712059,0.0003185832,0.00005659705,0.001106886,0.000223408,0.0003684395,0.000443042,0.0007168042,0.00000739391],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008429749,"about_ca_system_score_gemma":0.00008709471,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002458014,"about_ca_topic_score_gemma":0.000004372249,"domain_scores_codex":[0.9961024,0.0004009592,0.0005853865,0.001202338,0.0009024568,0.0008064493],"domain_scores_gemma":[0.998293,0.0006621734,0.0002092892,0.0002714983,0.00004503796,0.0005190449],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002602313,0.00005202945,0.000391769,0.0000901766,0.000005732198,0.0001660973,0.0010889,0.0001157266,0.9843544,0.0005581462,0.0009500536,0.01220099],"study_design_scores_gemma":[0.006224285,0.005176931,0.005731174,0.001466721,0.0001262948,0.009016983,0.006218389,0.6356196,0.2512377,0.000700007,0.07393391,0.004548028],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9919495,0.0001728172,0.00309642,0.0008681482,0.002623464,0.0007171084,0.0001852989,0.0001973671,0.0001898765],"genre_scores_gemma":[0.9981646,0.00006726885,0.00001512848,0.001232243,0.0001936609,0.0001247025,0.00001110615,0.0000338057,0.000157506],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7331166,"threshold_uncertainty_score":0.9999266,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4309263403","doi":"10.1109/biocas54905.2022.9948548","title":"Efficient Ultrasound Image Enhancement Using Lightweight CNNs","year":2022,"lang":"en","type":"article","venue":"2022 IEEE Biomedical Circuits and Systems Conference (BioCAS)","topic":"Ultrasound Imaging and Elastography","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Beamforming; Convolutional neural network; Computer science; Artificial intelligence; Image quality; Image (mathematics); Frequency domain; Fourier transform; Envelope (radar); Computer vision; Pattern recognition (psychology); Telecommunications; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.02969359492168597,"gpt":0.2651719536404734,"spread":0.2354783587187874,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000923603,0.0003702701,0.000674826,0.000428575,0.0007684897,0.0001722767,0.0002445023,0.0001200689,0.001184337],"category_scores_gemma":[0.00008655271,0.0003158276,0.0001766046,0.0007739711,0.000485121,0.00005527299,0.0001037628,0.0006109643,0.0000364947],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002129692,"about_ca_system_score_gemma":0.0003261831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002837563,"about_ca_topic_score_gemma":0.000002044995,"domain_scores_codex":[0.9962366,0.000243714,0.0006870227,0.0007945803,0.001313149,0.0007249036],"domain_scores_gemma":[0.99835,0.0001763482,0.0002174598,0.0004790253,0.0001566549,0.0006205472],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000671844,0.0009794595,0.002645895,0.0004918758,0.0003049855,0.0001499397,0.002020463,0.00002676483,0.9850736,0.000925191,0.004224612,0.003089996],"study_design_scores_gemma":[0.01614476,0.007513983,0.009331444,0.002215645,0.002134601,0.01723425,0.03023593,0.09854151,0.01161019,0.0002927559,0.8000032,0.00474174],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9701604,0.002110407,0.02043155,0.0004327507,0.003047717,0.0008140877,0.0002057394,0.0001390161,0.002658283],"genre_scores_gemma":[0.9977002,0.000098072,0.000169976,0.0003063006,0.0004216896,0.0001197342,0.000115302,0.00004041431,0.001028282],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9734634,"threshold_uncertainty_score":0.9999294,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}