{"id":"W3216336514","doi":"10.1016/j.simpa.2021.100185","title":"vid-SAMGRAH: A PyTorch framework for multi-latent space reinforcement learning driven video summarization in ultrasound imaging","year":2021,"lang":"en","type":"article","venue":"Software Impacts","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Science and Engineering Research Board; Compute Canada; Nvidia; Yale University","keywords":"Automatic summarization; Computer science; Artificial intelligence; Reinforcement learning; Unsupervised learning; Deep learning; Scalability; Machine learning; Feature (linguistics); Feature learning","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004438654,0.0003125414,0.0004656041,0.0002950168,0.0001821533,0.0001473502,0.000115502,0.0001908711,0.00009899976],"category_scores_gemma":[0.02267282,0.0003286784,0.0001862012,0.0007188822,0.00005871265,0.0002470991,0.0000934534,0.0005635769,0.00002915712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009716984,"about_ca_system_score_gemma":0.0007242165,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003710159,"about_ca_topic_score_gemma":0.0001507485,"domain_scores_codex":[0.9976433,0.0001023988,0.0004874002,0.000589792,0.0004491458,0.0007279891],"domain_scores_gemma":[0.996567,0.002029997,0.0002093991,0.0004733135,0.0003887466,0.000331528],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003159623,0.0005083312,0.9084153,0.0007169766,0.0001614055,0.0003185061,0.005346753,0.05726269,0.01415149,0.0003451941,0.007126434,0.005330968],"study_design_scores_gemma":[0.01933017,0.001115237,0.7679325,0.01215907,0.0008355709,0.0002784278,0.0016602,0.07720412,0.04837061,0.002004344,0.06683854,0.002271234],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1761592,0.001226569,0.7993672,0.02043166,0.0005919613,0.001630965,0.00001666619,0.0005599398,0.00001576939],"genre_scores_gemma":[0.887653,0.0002857479,0.100444,0.01033698,0.0002462856,0.0001042418,0.0004054098,0.000116903,0.0004074047],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7114937,"threshold_uncertainty_score":0.9999166,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04108269217835239,"score_gpt":0.3526894819637394,"score_spread":0.311606789785387,"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."}}