{"meta":{"query_hash":"164eed1457d5","filters":{"topic":"Remote-Sensing Image Classification"},"cohort_total":769,"direct_labels_cover":0,"predictions_cover":769,"exported":769,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/164eed1457d5","api":"https://metacan.xera.ac/api/v1/cohort?topic=Remote-Sensing+Image+Classification"},"results":[{"id":"W116475707","doi":"10.1007/3-540-27468-5_74","title":"High-Resolution Satellite Image Sources for Disaster Management in Urban Areas","year":2005,"lang":"en","type":"book-chapter","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Geospatial analysis; Focus (optics); Computer science; Emergency management; Remote sensing; Earth observation; Satellite; Geography; Data science; Urban management; Urban planning; Engineering; Civil engineering","score_opus":0.014632525651267417,"score_gpt":0.2106971669802768,"score_spread":0.1960646413290094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W116475707","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0066581923,0.022551468,0.81621355,0.0014378664,0.0012167362,0.00020566916,0.0033070769,0.004363146,0.1440463],"genre_scores_gemma":[0.052435722,0.03266806,0.6200652,0.0007238394,0.0006955903,0.00017955391,0.009845877,0.0017259622,0.28166017],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9998889,0.000009332311,0.0000042173992,0.000015373558,0.00007713363,0.000005062265],"domain_scores_gemma":[0.9998338,0.00006691709,0.0000077608565,0.00002364481,0.00006322238,0.0000047239264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002493592,0.0007340907,0.00036779672,0.0011362999,0.00023520757,0.0009238916,0.00083203625,0.0005996816,0.014010529],"category_scores_gemma":[0.0004085495,0.00034586317,0.00038615137,0.0019670592,0.00018737066,0.0012192961,0.00039881084,0.0006401922,0.007175955],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014922745,0.000031539857,0.00037354536,0.00040835328,0.000025037223,0.00009277544,0.00008809262,0.0068796813,0.010363167,0.012090078,0.09221857,0.8774142],"study_design_scores_gemma":[0.000014938528,0.00004492134,0.006360422,0.00045164835,0.00007777583,0.00096225296,0.0002060034,0.07983896,0.029933045,0.04961116,0.8324387,0.00006013553],"about_ca_topic_score_codex":0.0020994693,"about_ca_topic_score_gemma":0.0060685533,"teacher_disagreement_score":0.014010529,"about_ca_system_score_codex":0.00025755566,"about_ca_system_score_gemma":0.00032157998,"threshold_uncertainty_score":0.046869874},"labels":[],"label_agreement":null},{"id":"W1235516772","doi":"10.17265/2159-581x/2015.01.004","title":"A Review on Back-Propagation Neural Networks in the Application of Remote Sensing Image Classification","year":2015,"lang":"en","type":"review","venue":"Journal of Earth Science and Engineering","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Artificial neural network; Computer science; Implementation; Backpropagation; Process (computing); Artificial intelligence; Machine learning; Contextual image classification; Image (mathematics); Software engineering","score_opus":0.050026898561512254,"score_gpt":0.2988450550158843,"score_spread":0.24881815645437205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1235516772","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00032488347,0.9933328,0.0030263257,0.00048317673,0.00038982186,0.000019398112,0.000055921177,0.000025925508,0.0023417321],"genre_scores_gemma":[0.0022611513,0.9933704,0.0028585554,0.00018470298,0.0002683443,0.000018796327,0.000075637014,0.0000057772354,0.0009564689],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99950874,0.00008501759,0.00010962817,0.000088572066,0.00018304576,0.00002505921],"domain_scores_gemma":[0.9988524,0.0006394861,0.00011981563,0.000028102993,0.0003316375,0.000028652328],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011567693,0.0011525473,0.0010980305,0.0036505545,0.0003385036,0.0011505646,0.0010539145,0.0011403745,0.0036353804],"category_scores_gemma":[0.0022069456,0.0004248664,0.0008990801,0.005173026,0.00040073236,0.0017846769,0.00053211645,0.0010569607,0.0018241353],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038394868,0.00006623292,0.00040635857,0.029311307,0.00013850385,0.00018642636,0.00008089729,0.0015876569,0.0013168685,0.004300563,0.015712963,0.9468538],"study_design_scores_gemma":[0.000012449974,0.00020037095,0.002842568,0.017050335,0.00048869685,0.0014372246,0.00013448126,0.002289788,0.0026260465,0.0057954052,0.96703655,0.00008599162],"about_ca_topic_score_codex":0.002174337,"about_ca_topic_score_gemma":0.0029549147,"teacher_disagreement_score":0.0036505545,"about_ca_system_score_codex":0.00067424256,"about_ca_system_score_gemma":0.0014049286,"threshold_uncertainty_score":0.012161553},"labels":[],"label_agreement":null},{"id":"W12623448","doi":"10.1007/978-3-642-32316-4_8","title":"Integrating Change Vector Analysis, Post-Classification Comparison, and Object-Oriented Image Analysis for Land Use and Land Cover Change Detection Using RADARSAT-2 Polarimetric SAR Images","year":2012,"lang":"en","type":"book-chapter","venue":"Advances in geographic information science","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Space Agency","keywords":"Wishart distribution; Change detection; Support vector machine; Land cover; Artificial intelligence; Pattern recognition (psychology); Polarimetry; Computer science; Remote sensing; Computer vision; Geography; Land use; Machine learning; Multivariate statistics; Engineering","score_opus":0.03507620862023723,"score_gpt":0.2792796213562032,"score_spread":0.244203412735966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W12623448","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012885612,0.005039011,0.95600396,0.0002408889,0.00044330762,0.00014692853,0.00036919108,0.002822419,0.022048594],"genre_scores_gemma":[0.07072485,0.004375863,0.8958751,0.00022466967,0.00024588502,0.00010879463,0.0012024295,0.0006572191,0.026585167],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999602,0.000040575498,0.00002385356,0.00008416897,0.00022488939,0.000024614672],"domain_scores_gemma":[0.99975556,0.00006717701,0.000017602826,0.000024191864,0.0001275535,0.000007916952],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007175044,0.0007880286,0.0006560536,0.0021905734,0.00021483857,0.0012788171,0.00073276274,0.0005086501,0.0040793894],"category_scores_gemma":[0.000577188,0.00035328936,0.00071823027,0.003312481,0.00024890507,0.0017955389,0.0004474515,0.0005066823,0.0026530721],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025185045,0.00005590883,0.0009026981,0.0002074442,0.00005040928,0.000035128407,0.000041358788,0.0027350574,0.021371765,0.004176656,0.005092893,0.9653054],"study_design_scores_gemma":[0.000047683418,0.0004756708,0.04637009,0.00028559944,0.00055416615,0.0017384088,0.00035150713,0.4762698,0.1638518,0.059270952,0.25054488,0.00023945911],"about_ca_topic_score_codex":0.0014848115,"about_ca_topic_score_gemma":0.003928501,"teacher_disagreement_score":0.0040793894,"about_ca_system_score_codex":0.00028588783,"about_ca_system_score_gemma":0.00040846792,"threshold_uncertainty_score":0.01364696},"labels":[],"label_agreement":null},{"id":"W1490069855","doi":"10.1007/978-3-642-13772-3_9","title":"Segmentation of Very High Resolution Remote Sensing Imagery of Urban Areas Using Particle Swarm Optimization Algorithm","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Particle swarm optimization; Computer science; Segmentation; Remote sensing; Resolution (logic); Swarm behaviour; High resolution; Computer vision; Image segmentation; Artificial intelligence; Algorithm; Geography","score_opus":0.016127664362913276,"score_gpt":0.22939516611351354,"score_spread":0.21326750175060027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1490069855","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032619134,0.00034490824,0.96452945,0.00007393751,0.000039765135,0.00007491794,0.0001310513,0.00071260467,0.0014741797],"genre_scores_gemma":[0.21938758,0.00045944742,0.77573335,0.000074372794,0.000054814172,0.0001468107,0.0008383357,0.00027271948,0.003032573],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99981374,0.000024440527,0.00001328408,0.000057543166,0.0000608654,0.000030114932],"domain_scores_gemma":[0.99980134,0.00009253944,0.000021976923,0.000026983085,0.00004630855,0.000010916791],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032473973,0.00079142937,0.000935413,0.0014249581,0.0003460533,0.0010104731,0.00071219617,0.0008615846,0.0010406872],"category_scores_gemma":[0.0005672316,0.0006113849,0.0010802868,0.0014068681,0.0003523227,0.00063897274,0.0004538041,0.00048068698,0.00048548845],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002773703,0.00016579826,0.0012833792,0.00029215703,0.00011420595,0.00031036048,0.0002688719,0.55170757,0.0776285,0.0035707306,0.004114346,0.36026663],"study_design_scores_gemma":[0.000008950184,0.000022932012,0.0013285277,0.0000096000485,0.000022865908,0.00006259845,0.000028859824,0.9890192,0.0064921295,0.0018190272,0.0011730222,0.000012258724],"about_ca_topic_score_codex":0.004554401,"about_ca_topic_score_gemma":0.0041076858,"teacher_disagreement_score":0.004554401,"about_ca_system_score_codex":0.0003617804,"about_ca_system_score_gemma":0.0006437092,"threshold_uncertainty_score":0.009055734},"labels":[],"label_agreement":null},{"id":"W1492179299","doi":"10.1007/978-3-642-10331-5_42","title":"Maximum Likelihood Estimation Sample Consensus with Validation of Individual Correspondences","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Communications Research Centre Canada","funders":"","keywords":"RANSAC; Estimator; Computer science; Sample (material); Statistics; Estimation; Sequence (biology); Algorithm; Maximum likelihood; Artificial intelligence; Mathematics; Pattern recognition (psychology); Image (mathematics)","score_opus":0.018317673876315492,"score_gpt":0.23498420242081386,"score_spread":0.21666652854449836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1492179299","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009860599,0.00006367908,0.98892957,0.000045991943,0.000019523604,0.000033975066,0.000031299118,0.0005496672,0.00046576685],"genre_scores_gemma":[0.40169662,0.00007488765,0.5926775,0.00010472861,0.00005251892,0.00024105883,0.00077425386,0.00046798534,0.003910483],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99387133,0.0026585541,0.00031865443,0.0015220882,0.001283318,0.00034596605],"domain_scores_gemma":[0.97640353,0.012875479,0.0011906582,0.005408079,0.0038288904,0.00029338888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0088118585,0.0017166801,0.0031331554,0.0014348597,0.0013745774,0.0019412764,0.004467994,0.004399102,0.0031348865],"category_scores_gemma":[0.032581087,0.0016550354,0.0018892266,0.0017411785,0.002367537,0.0034462465,0.004749284,0.00286716,0.0025508457],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006807541,0.000192625,0.002141229,0.00026934748,0.0002974847,0.00015876103,0.00029874346,0.6191665,0.012700538,0.012167502,0.0025330645,0.34939343],"study_design_scores_gemma":[0.000022307127,0.000052387746,0.0003253293,0.000008737671,0.00001665261,0.00003987518,0.000022178898,0.987407,0.004139977,0.007674335,0.0002771457,0.000014121192],"about_ca_topic_score_codex":0.0028173365,"about_ca_topic_score_gemma":0.003307466,"teacher_disagreement_score":0.0088118585,"about_ca_system_score_codex":0.0009367137,"about_ca_system_score_gemma":0.0020436826,"threshold_uncertainty_score":0.04660213},"labels":[],"label_agreement":null},{"id":"W1509362770","doi":"10.1007/978-3-642-15470-6_35","title":"Robust and Efficient Change Detection Algorithm","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Change detection; Computer science; Pixel; Fault detection and isolation; Artificial intelligence; Image (mathematics); Algorithm; Noise (video); Vulnerability (computing); Range (aeronautics); Ranging; Pattern recognition (psychology); Data mining; Engineering; Computer security; Telecommunications","score_opus":0.025052075932205223,"score_gpt":0.21195256873821108,"score_spread":0.18690049280600585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1509362770","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005674442,0.00046196635,0.99020445,0.000084446474,0.000115216775,0.000055339373,0.00011176004,0.0017206285,0.0015717539],"genre_scores_gemma":[0.06463055,0.00040157625,0.9247334,0.00012225026,0.00010904648,0.00009932299,0.00069381786,0.00026009363,0.008949942],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992077,0.00006460209,0.000041700303,0.00022491992,0.00039501488,0.0000661013],"domain_scores_gemma":[0.9993783,0.00012792229,0.00005011874,0.00016481768,0.0002567978,0.00002193095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005989972,0.00091515115,0.0015045116,0.0017458999,0.00051381125,0.0010476605,0.0016503172,0.0012095154,0.004531651],"category_scores_gemma":[0.001255375,0.0005759488,0.0010355045,0.0016095572,0.0004093163,0.0012351573,0.001070463,0.0009763672,0.0034603588],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014699253,0.000088516186,0.00047592397,0.00009863766,0.00007130221,0.00007874655,0.00002811645,0.01923499,0.059073713,0.0044298847,0.007963073,0.90831],"study_design_scores_gemma":[0.000038126873,0.00013765295,0.0026747908,0.00001800797,0.0001126368,0.0006782401,0.0000259158,0.89051324,0.07543327,0.0050763893,0.02523008,0.0000616196],"about_ca_topic_score_codex":0.0016748363,"about_ca_topic_score_gemma":0.0026086743,"teacher_disagreement_score":0.004531651,"about_ca_system_score_codex":0.00039901107,"about_ca_system_score_gemma":0.0007975002,"threshold_uncertainty_score":0.015159905},"labels":[],"label_agreement":null},{"id":"W1510047790","doi":"10.1109/tip.2015.2456505","title":"Incorporating Adaptive Local Information Into Fuzzy Clustering for Image Segmentation","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":107,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"China Scholarship Council; National Natural Science Foundation of China","keywords":"Artificial intelligence; Image segmentation; Pattern recognition (psychology); Pixel; Cluster analysis; Range segmentation; Computer science; Fuzzy clustering; Smoothing; Scale-space segmentation; Segmentation-based object categorization; Computer vision; Fuzzy logic; Region growing; Segmentation; Mathematics","score_opus":0.024490925494218007,"score_gpt":0.26077186565465554,"score_spread":0.23628094016043755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1510047790","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0061768135,0.00014813822,0.9930254,0.000024209574,0.0000075301496,0.000018015033,0.000009091067,0.00022410482,0.00036668443],"genre_scores_gemma":[0.22308661,0.00030109793,0.7752935,0.00006716442,0.000042821768,0.00009099018,0.00009119068,0.00012523793,0.00090134726],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99930024,0.0001090864,0.000041452495,0.00017398293,0.0003247656,0.000050470226],"domain_scores_gemma":[0.99936825,0.0002516274,0.00008513277,0.00007341605,0.00019772435,0.000023734492],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008809239,0.00065700524,0.00077886047,0.0018132274,0.00057602895,0.0005872645,0.0011760836,0.00096467766,0.00068435294],"category_scores_gemma":[0.0021804143,0.0004248522,0.00083733845,0.0013583254,0.000659088,0.001040364,0.0007691251,0.000596567,0.00028237846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012362185,0.00008336696,0.0010903749,0.00022094733,0.000112646485,0.00012039465,0.00026809232,0.49123558,0.067905314,0.0093153,0.0011822507,0.42834213],"study_design_scores_gemma":[0.0000041729145,0.000023497876,0.0004152417,0.0000078218945,0.000018089326,0.000038836,0.000014820307,0.98783743,0.008384434,0.0024658479,0.00077225995,0.000017487937],"about_ca_topic_score_codex":0.006496937,"about_ca_topic_score_gemma":0.008679034,"teacher_disagreement_score":0.006496937,"about_ca_system_score_codex":0.0010201202,"about_ca_system_score_gemma":0.0009569114,"threshold_uncertainty_score":0.012918234},"labels":[],"label_agreement":null},{"id":"W1511081204","doi":"10.1109/igarss.2005.1526435","title":"Linear features for semi-automatic registration and change detection of multi-source imagery","year":2005,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Change detection; Image registration; Computer vision; Artificial intelligence; Image (mathematics)","score_opus":0.031174245464149566,"score_gpt":0.25598805796400576,"score_spread":0.22481381249985619,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1511081204","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04713693,0.00041435027,0.94723123,0.00013923355,0.00005334566,0.00008005796,0.0004759056,0.0033621576,0.0011068177],"genre_scores_gemma":[0.48881203,0.00028959467,0.5060556,0.00006320881,0.000074701544,0.000235235,0.0013754591,0.0003516886,0.0027425424],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995559,0.00013526542,0.000028097882,0.000091546455,0.000138545,0.00005056886],"domain_scores_gemma":[0.99922395,0.00032828967,0.00009905509,0.00015616773,0.00016599683,0.00002647793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005915175,0.00042230473,0.00047178063,0.0015924347,0.0004013186,0.0007431216,0.0008793934,0.00053330406,0.0025429563],"category_scores_gemma":[0.0022050259,0.0003782937,0.0004787794,0.0016610925,0.0003328977,0.0009892366,0.0007195834,0.00056636694,0.0014650953],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003941876,0.00014227394,0.001164426,0.00018493163,0.00006314175,0.00006084299,0.00008812659,0.029848402,0.084817275,0.0027762547,0.004639216,0.875821],"study_design_scores_gemma":[0.00004879465,0.00013182362,0.00628829,0.000019081383,0.00006930622,0.00016060114,0.000057630616,0.9042669,0.08012336,0.0037783515,0.005015896,0.00003998754],"about_ca_topic_score_codex":0.0025600404,"about_ca_topic_score_gemma":0.0032361092,"teacher_disagreement_score":0.0025600404,"about_ca_system_score_codex":0.00036073843,"about_ca_system_score_gemma":0.0004985323,"threshold_uncertainty_score":0.008507013},"labels":[],"label_agreement":null},{"id":"W1516724916","doi":"10.1109/lgrs.2015.2438227","title":"Semisupervised Hyperspectral Image Classification via Neighborhood Graph Learning","year":2015,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Hyperspectral imaging; Artificial intelligence; Computer science; Pattern recognition (psychology); Exploit; Pixel; Graph; Labeled data; Binary classification; Contextual image classification; Image (mathematics); Machine learning; Support vector machine; Theoretical computer science","score_opus":0.02144790727728335,"score_gpt":0.2257903075405959,"score_spread":0.20434240026331255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1516724916","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028785812,0.00020463586,0.96839386,0.00023446137,0.000019526033,0.00006790628,0.00011405526,0.00082932395,0.0013504311],"genre_scores_gemma":[0.54775345,0.00031257272,0.446785,0.0003187088,0.000116994874,0.00025586487,0.0013162415,0.00022874524,0.0029124592],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988801,0.00048405904,0.000038563096,0.00029689237,0.00024712307,0.00005324855],"domain_scores_gemma":[0.9973437,0.0011952404,0.00046634767,0.0005246439,0.00038387868,0.00008623793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001093695,0.0007408836,0.0010700944,0.001337087,0.0005160307,0.00073495274,0.0015442182,0.0011046329,0.0009763053],"category_scores_gemma":[0.0041113836,0.00034515894,0.00070999475,0.001150145,0.0010805355,0.0020055005,0.0012798609,0.0009928098,0.00044622045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025417577,0.0003198292,0.0041082143,0.00024072145,0.00017805703,0.0002159493,0.0002741628,0.5303573,0.013859576,0.042757533,0.010638896,0.39679557],"study_design_scores_gemma":[0.0000043181017,0.000012964137,0.00018843767,0.0000036837166,0.000004015436,0.000024712856,0.000012673222,0.9862564,0.0009197159,0.012118741,0.0004496185,0.0000047352305],"about_ca_topic_score_codex":0.0022941781,"about_ca_topic_score_gemma":0.0046200706,"teacher_disagreement_score":0.0022941781,"about_ca_system_score_codex":0.0006845676,"about_ca_system_score_gemma":0.00065135414,"threshold_uncertainty_score":0.0057840943},"labels":[],"label_agreement":null},{"id":"W1554757576","doi":"10.1109/dfua.2003.1219978","title":"A neural network based approach to detecting urban land cover changes using Landsat TM and IKONOS imagery","year":2003,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of New Brunswick; Communications Security Establishment","funders":"","keywords":"Change detection; Remote sensing; Computer science; Satellite; Satellite imagery; Land cover; Benchmark (surveying); Change analysis; High resolution; Image resolution; Environmental science; Artificial intelligence; Geography; Cartography; Land use; Physical geography","score_opus":0.02863358001509029,"score_gpt":0.21445967989766823,"score_spread":0.18582609988257795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1554757576","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19179162,0.0010312217,0.7949969,0.0004847953,0.00015260378,0.00024092142,0.00041422588,0.0015304358,0.009357133],"genre_scores_gemma":[0.7421663,0.0005059504,0.24799682,0.00011715686,0.000102732934,0.0002479738,0.0005249207,0.000036882524,0.008301244],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99982774,0.000032243184,0.000012459054,0.000049737224,0.00005117228,0.000026570877],"domain_scores_gemma":[0.9998374,0.000051944826,0.00001866002,0.000010906498,0.00007163582,0.000009416409],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041501425,0.0005363745,0.0003360898,0.0012804862,0.0003345955,0.0006695074,0.00052790495,0.0006283823,0.0014748772],"category_scores_gemma":[0.00086213526,0.00024226864,0.00029384674,0.0008973082,0.00021958082,0.00063032395,0.0002857121,0.00044815216,0.00037243633],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003002861,0.0004242409,0.009255096,0.000151932,0.00016494359,0.00017967986,0.0000899112,0.24092497,0.020607477,0.0028659005,0.0021774787,0.7228581],"study_design_scores_gemma":[0.0000091225365,0.000067791094,0.0034961207,0.000009463122,0.000026613587,0.00003867847,0.000029202225,0.99136996,0.003036024,0.0011659877,0.0007381423,0.000012865072],"about_ca_topic_score_codex":0.009315102,"about_ca_topic_score_gemma":0.013771104,"teacher_disagreement_score":0.009315102,"about_ca_system_score_codex":0.00053442357,"about_ca_system_score_gemma":0.00037456417,"threshold_uncertainty_score":0.018521786},"labels":[],"label_agreement":null},{"id":"W1595472190","doi":"10.1109/icip.2002.1039085","title":"Adaptive color image segmentation using Markov random fields","year":2003,"lang":"en","type":"article","venue":"Proceedings - International Conference on Image Processing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Image segmentation; Random field; Gibbs sampling; Markov random field; Markov chain; Computer science; Artificial intelligence; Markov process; Variable-order Markov model; Segmentation; Markov model; Hidden Markov model; Algorithm; Pattern recognition (psychology); Computer vision; Mathematics; Machine learning; Bayesian probability; Statistics","score_opus":0.042120776502551124,"score_gpt":0.2917701363816775,"score_spread":0.24964935987912634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1595472190","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013928574,0.000100961115,0.99783,0.000043385084,0.0000163443,0.000011921901,0.000015382835,0.00025584205,0.0003333495],"genre_scores_gemma":[0.13697937,0.00040629372,0.8596455,0.00013223615,0.000097983386,0.000115992414,0.00015427452,0.00025673202,0.0022117728],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993812,0.00016193022,0.000023562807,0.00016560152,0.00020023268,0.0000674087],"domain_scores_gemma":[0.9994748,0.0002680307,0.00006732841,0.00006527529,0.00009225698,0.000032383767],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010264345,0.000541295,0.0009480317,0.0012875746,0.00048355837,0.0011102706,0.001384976,0.0010830985,0.001717181],"category_scores_gemma":[0.0018471103,0.00050381914,0.0011256358,0.0010122962,0.0011320199,0.0013883037,0.0011443419,0.0010066791,0.00049770187],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011128089,0.000051360235,0.0005587577,0.00009027732,0.000064954154,0.00012492998,0.00011464242,0.6536118,0.029979024,0.105767876,0.0025669504,0.20695822],"study_design_scores_gemma":[0.000007819528,0.00001569635,0.00014154508,0.0000063821735,0.000006918725,0.00003708807,0.000004551956,0.9777876,0.0023502836,0.017971624,0.0016547865,0.000015597538],"about_ca_topic_score_codex":0.005736031,"about_ca_topic_score_gemma":0.0052755177,"teacher_disagreement_score":0.005736031,"about_ca_system_score_codex":0.0012570034,"about_ca_system_score_gemma":0.0011127208,"threshold_uncertainty_score":0.011405289},"labels":[],"label_agreement":null},{"id":"W1600782882","doi":"10.1109/multi-temp.2015.7245765","title":"Change detection using multiscale segmentation and Kullback-Leibler divergence: Application on road damage extraction","year":2015,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Divergence (linguistics); Computer science; Change detection; Kullback–Leibler divergence; Artificial intelligence; Segmentation; Pattern recognition (psychology); Extraction (chemistry); Image segmentation; Dempster–Shafer theory; Similarity (geometry); Feature extraction; Wavelet; Computer vision; Data mining; Image (mathematics)","score_opus":0.08008840819505132,"score_gpt":0.3008679326651675,"score_spread":0.22077952447011617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1600782882","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18468988,0.00074221153,0.8125317,0.00014571451,0.000031184176,0.00006041608,0.000079041434,0.00058593845,0.0011338961],"genre_scores_gemma":[0.7312649,0.00043056638,0.26747987,0.000036248282,0.00003592242,0.000030472165,0.00010863233,0.000050247632,0.00056316634],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99947196,0.00010114548,0.000041278727,0.00011871896,0.00022467665,0.00004227004],"domain_scores_gemma":[0.99929464,0.00031243693,0.0001311785,0.000067683126,0.00015312571,0.000040980387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008936185,0.0003975836,0.00087498565,0.0026804272,0.00027437723,0.00070545933,0.00037605668,0.0008113852,0.00045139648],"category_scores_gemma":[0.0021054437,0.00019673542,0.00055446563,0.0018167822,0.00063055585,0.00084490323,0.0005948378,0.00036594307,0.00015676636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025751197,0.0002007185,0.0076311044,0.0003180003,0.00017197337,0.00069423014,0.00033279648,0.16800487,0.13592827,0.004064752,0.0008463566,0.6815494],"study_design_scores_gemma":[0.000009200643,0.00010377292,0.010211595,0.000010009383,0.000029547735,0.00044246583,0.000074807016,0.9667759,0.019096758,0.0023460647,0.0008580581,0.00004190974],"about_ca_topic_score_codex":0.0017198119,"about_ca_topic_score_gemma":0.0015562329,"teacher_disagreement_score":0.0026804272,"about_ca_system_score_codex":0.00035789493,"about_ca_system_score_gemma":0.00033591216,"threshold_uncertainty_score":0.0047259927},"labels":[],"label_agreement":null},{"id":"W1696305814","doi":"10.1155/2015/538063","title":"Urban Land Use and Land Cover Classification Using Remotely Sensed SAR Data through Deep Belief Networks","year":2015,"lang":"en","type":"article","venue":"Journal of Sensors","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":128,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Deep belief network; Artificial intelligence; Computer science; Deep learning; Land cover; Support vector machine; Artificial neural network; Synthetic aperture radar; Field (mathematics); Pattern recognition (psychology); Machine learning; Remote sensing; Land use; Geography; Engineering","score_opus":0.1331286178345331,"score_gpt":0.2854826539302463,"score_spread":0.1523540360957132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1696305814","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65500146,0.00035975565,0.34109312,0.0003248718,0.000031359465,0.0000620451,0.00032073603,0.00071436027,0.0020923414],"genre_scores_gemma":[0.9686801,0.000106893414,0.030021288,0.00003360296,0.000010385398,0.00002532209,0.00031937595,0.000010258787,0.0007927234],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99986315,0.00003110592,0.000008044623,0.000036186055,0.00003568101,0.000025955365],"domain_scores_gemma":[0.99970067,0.00012856869,0.00005243101,0.000023412644,0.00007382134,0.000021154892],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045448483,0.0005204156,0.00032965673,0.00087053084,0.00019344967,0.0005959518,0.0004637597,0.0004587965,0.00044596044],"category_scores_gemma":[0.0009677094,0.00030240865,0.00042212926,0.000552367,0.0002505226,0.00079961144,0.00043363954,0.0005010613,0.00014946226],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016467806,0.00021783554,0.007404417,0.00003689296,0.000069090966,0.0000741334,0.00005512001,0.85191417,0.0041607027,0.00092217576,0.0006556981,0.13432512],"study_design_scores_gemma":[0.0000015035386,0.000006638993,0.00053167867,0.0000012189224,0.0000031474985,0.0000022342253,0.000006152186,0.9987943,0.0003869271,0.0002363317,0.000028126966,0.000001706692],"about_ca_topic_score_codex":0.012717648,"about_ca_topic_score_gemma":0.015429028,"teacher_disagreement_score":0.012717648,"about_ca_system_score_codex":0.0006738719,"about_ca_system_score_gemma":0.00041125625,"threshold_uncertainty_score":0.025287211},"labels":[],"label_agreement":null},{"id":"W1741870144","doi":"","title":"ONP-MF: An Orthogonal Nonnegative Matrix Factorization Algorithm with Application to Clustering","year":2013,"lang":"en","type":"article","venue":"ORBi UMONS","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Non-negative matrix factorization; Cluster analysis; Nonnegative matrix; Matrix (chemical analysis); Orthogonal matrix; Algorithm; Matrix decomposition; Mathematics; Product (mathematics); Matrix algebra; Computer science; Biclustering; Pattern recognition (psychology); Combinatorics; Symmetric matrix; Artificial intelligence; Correlation clustering; Canopy clustering algorithm; Eigenvalues and eigenvectors; Orthogonal basis; Physics","score_opus":0.009131639003803458,"score_gpt":0.2344866193498282,"score_spread":0.22535498034602475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1741870144","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029843033,0.00038703694,0.99239725,0.00020036154,0.00021315746,0.00015622308,0.0004041455,0.002065474,0.001192003],"genre_scores_gemma":[0.049727652,0.00036300684,0.9424051,0.00012348755,0.00021879058,0.0003201354,0.0017024145,0.00038790307,0.0047514844],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99748623,0.0007835023,0.00014991286,0.00044141116,0.0009817161,0.0001571244],"domain_scores_gemma":[0.9963929,0.0009584884,0.00022124013,0.0006711219,0.001624545,0.00013162271],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002587247,0.0013387417,0.0015303872,0.002652203,0.0015483106,0.0015081061,0.0021562818,0.0016916115,0.00517008],"category_scores_gemma":[0.010614505,0.0005252162,0.0010291531,0.003026573,0.0006628402,0.0023115627,0.0021733078,0.0013029049,0.0031765548],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002257756,0.00015419614,0.0007121306,0.00024644562,0.00010671844,0.000094591494,0.00013946065,0.061922226,0.006521039,0.010325106,0.032122724,0.88742954],"study_design_scores_gemma":[0.000027931537,0.000054588345,0.0005006445,0.00002818577,0.000021296686,0.0001224772,0.000045688066,0.9610534,0.0046675396,0.017019592,0.016421828,0.000036846362],"about_ca_topic_score_codex":0.0069135316,"about_ca_topic_score_gemma":0.0105926385,"teacher_disagreement_score":0.0069135316,"about_ca_system_score_codex":0.0007011631,"about_ca_system_score_gemma":0.0023600624,"threshold_uncertainty_score":0.017295659},"labels":[],"label_agreement":null},{"id":"W1760980278","doi":"10.5829/idosi.jaidm.2015.03.01.02","title":"Impact of linear dimensionality reduction methods on the performance of anomaly detection algorithms in hyperspectral images","year":2015,"lang":"en","type":"article","venue":"Journal of artificial intelligence and data mining","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Hyperspectral imaging; Anomaly detection; Computer science; Dimensionality reduction; Kernel (algebra); Algorithm; Principal component analysis; Artificial intelligence; Benchmark (surveying); Pattern recognition (psychology); Imaging spectrometer; Fast Fourier transform; Mathematics; Spectrometer","score_opus":0.1944009534162595,"score_gpt":0.4051895053149928,"score_spread":0.21078855189873333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1760980278","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80317193,0.00807765,0.17987427,0.00063603686,0.00032040844,0.00013828602,0.0003036798,0.0037732972,0.0037045164],"genre_scores_gemma":[0.8696883,0.0015817322,0.12638944,0.00011753286,0.000071259004,0.000092683644,0.00077467784,0.00019032054,0.0010941271],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960303,0.001382444,0.00036631644,0.0005644983,0.0014271357,0.00022935786],"domain_scores_gemma":[0.988588,0.0073584565,0.00090111187,0.0010034641,0.0019910245,0.00015799607],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004098802,0.0013681217,0.0009250512,0.001116321,0.00054688705,0.0013359663,0.0006376669,0.0007799043,0.00059156003],"category_scores_gemma":[0.014515662,0.00023149344,0.0006737708,0.0010914323,0.0006221851,0.0014297604,0.00071894214,0.00085755374,0.0003457336],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018854525,0.0010099263,0.0179267,0.00076172745,0.00072155945,0.00023032294,0.00030642626,0.22618102,0.056194685,0.0018405645,0.003589235,0.6893524],"study_design_scores_gemma":[0.000060886014,0.00097489834,0.016330088,0.000043269123,0.00014444458,0.0003196262,0.00017499762,0.9094253,0.06973781,0.00095120695,0.0017594545,0.000078071294],"about_ca_topic_score_codex":0.0025929813,"about_ca_topic_score_gemma":0.0020105182,"teacher_disagreement_score":0.004098802,"about_ca_system_score_codex":0.00057936955,"about_ca_system_score_gemma":0.00068235165,"threshold_uncertainty_score":0.021676779},"labels":[],"label_agreement":null},{"id":"W1790272602","doi":"10.1117/1.oe.54.7.070502","title":"Multispectral index for the remote detection of human skin signatures","year":2015,"lang":"en","type":"article","venue":"Optical Engineering","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Multispectral image; Remote sensing; Computer science; Snow; Spectral signature; Environmental science; Multispectral pattern recognition; Reflectivity; Vegetation Index; Photochemical Reflectance Index; Vegetation (pathology); Geology; Normalized Difference Vegetation Index; Optics; Oceanography","score_opus":0.02152263924811798,"score_gpt":0.247613561445801,"score_spread":0.226090922197683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1790272602","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06526235,0.0012352993,0.9254662,0.00011221145,0.00013625842,0.00009036397,0.00028986685,0.0009648696,0.006442561],"genre_scores_gemma":[0.37739143,0.00075901934,0.6183164,0.0001286447,0.00011542418,0.00011930697,0.00046461148,0.000110706555,0.0025944922],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996705,0.000056160556,0.0000158279,0.000056606583,0.0001761971,0.000024682626],"domain_scores_gemma":[0.99970394,0.00004917686,0.000041855317,0.000050662424,0.0001284103,0.00002583727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032729618,0.00044963037,0.00030663284,0.0018109496,0.00018717317,0.0005386198,0.00045547434,0.0004592593,0.0013755967],"category_scores_gemma":[0.0006091882,0.00011302833,0.00027668366,0.00082581845,0.00025283676,0.00090924045,0.0004161984,0.0004320193,0.0012033588],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021637016,0.00020747956,0.0067175506,0.00034703233,0.00006239958,0.00012925203,0.00008110098,0.010788611,0.48874652,0.006257449,0.0030155983,0.48343056],"study_design_scores_gemma":[0.000024331195,0.0004984875,0.039002117,0.000080590566,0.00017591521,0.001914811,0.00013984209,0.55940604,0.3672797,0.0053378535,0.025990812,0.00014947311],"about_ca_topic_score_codex":0.00033844408,"about_ca_topic_score_gemma":0.0006635825,"teacher_disagreement_score":0.0018109496,"about_ca_system_score_codex":0.0001575555,"about_ca_system_score_gemma":0.00021397402,"threshold_uncertainty_score":0.0046017766},"labels":[],"label_agreement":null},{"id":"W1844741564","doi":"10.1109/igarss.1995.521715","title":"Combined analysis of SAR C and TM/Landsat data in the assessment of aquatic vegetation changes in the Tucurui reservoir, Para State, Brazilian Amazon","year":2002,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Vegetation (pathology); Amazon rainforest; Remote sensing; Environmental science; Mosaic; Stage (stratigraphy); Aquatic plant; Aquatic ecosystem; Hydrology (agriculture); Geography; Geology; Ecology; Oceanography","score_opus":0.06451611387013048,"score_gpt":0.3058019987464012,"score_spread":0.2412858848762707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1844741564","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99935323,0.000045401724,0.00014232578,0.000014585171,7.074447e-7,0.0000040984646,0.000041637904,0.0000040717077,0.00039392812],"genre_scores_gemma":[0.99945563,0.000036363122,0.00031844457,0.0000035368848,0.0000013734834,0.000002829972,0.000075099575,0.0000014345388,0.00010521026],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99984276,0.000051056053,0.000010242264,0.000021604272,0.000043985376,0.000030285099],"domain_scores_gemma":[0.999747,0.00007134082,0.00004484006,0.000015173761,0.00008872923,0.000032914584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033770292,0.00017379188,0.00018032436,0.00078353914,0.00016700084,0.00035410014,0.00013849145,0.0001426088,0.0003091216],"category_scores_gemma":[0.0009174432,0.00014392735,0.0001136967,0.0007171213,0.00015249429,0.00020309363,0.0001906733,0.000105838335,0.00006807688],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003755826,0.00015755642,0.9058023,0.00007241083,0.000082003644,0.0004989577,0.00058789673,0.002484356,0.045182817,0.00008638741,0.00017119902,0.04449869],"study_design_scores_gemma":[0.00001100157,0.00009796415,0.98913646,0.000008932042,0.00004037608,0.00013457192,0.00069975574,0.007723682,0.0018040786,0.000029592104,0.00030668575,0.0000068863606],"about_ca_topic_score_codex":0.05296551,"about_ca_topic_score_gemma":0.13486783,"teacher_disagreement_score":0.05296551,"about_ca_system_score_codex":0.00040465387,"about_ca_system_score_gemma":0.00032859054,"threshold_uncertainty_score":0.10531443},"labels":[],"label_agreement":null},{"id":"W1942068614","doi":"10.1155/2015/240354","title":"A Color Texture Image Segmentation Method Based on Fuzzy c-Means Clustering and Region-Level Markov Random Field Model","year":2015,"lang":"en","type":"article","venue":"Mathematical Problems in Engineering","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"Southwest Forestry University; China Scholarship Council; National Natural Science Foundation of China; Canada Research Chairs","keywords":"Artificial intelligence; Markov random field; Pattern recognition (psychology); Cluster analysis; Fuzzy clustering; Image segmentation; Fuzzy logic; Image texture; Computer vision; Computer science; Pixel; Mathematics; Segmentation","score_opus":0.03767410724835893,"score_gpt":0.263141590138535,"score_spread":0.22546748289017607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1942068614","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029907234,0.0001357679,0.9957131,0.000041908825,0.000034902445,0.000036869922,0.00002634384,0.00042486808,0.0005955508],"genre_scores_gemma":[0.07690175,0.00022622469,0.9205355,0.00008615361,0.000057725898,0.00008700057,0.00015728398,0.00016893253,0.0017794544],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99945277,0.00006429779,0.000022179609,0.00016214488,0.00025375496,0.000044885768],"domain_scores_gemma":[0.9995467,0.00010872472,0.00005187236,0.0000582183,0.0002034023,0.000031041523],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065096596,0.0006767291,0.001055471,0.0024186117,0.0006759965,0.00084729004,0.0014018895,0.0010453869,0.0014706986],"category_scores_gemma":[0.0013386351,0.00049973174,0.0011792576,0.0016724197,0.00064635085,0.001065833,0.000534434,0.00087684643,0.0006483266],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016982773,0.00011424193,0.0015287192,0.00030782138,0.00016096549,0.00012706852,0.00018092971,0.18354687,0.06288734,0.01734507,0.004985171,0.728646],"study_design_scores_gemma":[0.00001260064,0.000038957365,0.0007565725,0.000012039829,0.000027161066,0.00016794815,0.00002239691,0.98286533,0.009604873,0.003341198,0.003103335,0.000047544934],"about_ca_topic_score_codex":0.010129303,"about_ca_topic_score_gemma":0.008954811,"teacher_disagreement_score":0.010129303,"about_ca_system_score_codex":0.0012289099,"about_ca_system_score_gemma":0.0012459649,"threshold_uncertainty_score":0.020140707},"labels":[],"label_agreement":null},{"id":"W1963512686","doi":"10.3138/carto.46.3.200","title":"Damage Assessment of the 2011 Japanese Tsunami Using High-Resolution Satellite Data","year":2011,"lang":"en","type":"article","venue":"Cartographica The International Journal for Geographic Information and Geovisualization","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"U.S. Geological Survey; National Oceanic and Atmospheric Administration","keywords":"Geological survey; Geology; Seismology; Satellite; Indian ocean; Geography; Oceanography; Geophysics; Engineering","score_opus":0.04461132913132682,"score_gpt":0.2956028860797211,"score_spread":0.2509915569483943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1963512686","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9942053,0.00015649217,0.0016525212,0.00007463962,0.000010547564,0.000049302595,0.0023804521,0.00006780142,0.0014030183],"genre_scores_gemma":[0.99444616,0.000091133385,0.0020994288,0.000007993649,0.000007190941,0.000020493624,0.0028680235,0.0000051000115,0.00045434432],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.999665,0.000056071458,0.000040238403,0.000059066515,0.00011273575,0.00006687836],"domain_scores_gemma":[0.9991691,0.000083514904,0.00016381174,0.000078275625,0.00039344202,0.000111912916],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069283973,0.0006016143,0.00033265818,0.0033901506,0.0003232876,0.000751058,0.00031624842,0.0003942626,0.0009149527],"category_scores_gemma":[0.0014870677,0.00021042168,0.00039058208,0.0018746539,0.00016296483,0.00062751124,0.0005881708,0.00018776233,0.0002689468],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049156946,0.00047537955,0.7554566,0.00018034909,0.00031548098,0.0006386318,0.00034161535,0.105888486,0.0065241978,0.00043806256,0.004993489,0.124256164],"study_design_scores_gemma":[0.000024928157,0.00022917212,0.7825857,0.000025634026,0.00010493085,0.00007943676,0.00042646666,0.213577,0.0015885725,0.00013151577,0.0011923357,0.00003430127],"about_ca_topic_score_codex":0.033897344,"about_ca_topic_score_gemma":0.0722064,"teacher_disagreement_score":0.033897344,"about_ca_system_score_codex":0.00087841396,"about_ca_system_score_gemma":0.0005142895,"threshold_uncertainty_score":0.0674001},"labels":[],"label_agreement":null},{"id":"W1964175518","doi":"10.1080/01431160110076153","title":"S-Space: A new concept for information extraction from imaging spectrometer data","year":2002,"lang":"en","type":"article","venue":"International Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; North Dakota State University","keywords":"Full spectral imaging; Spectral space; Hyperspectral imaging; Remote sensing; Imaging spectrometer; Land cover; Pixel; Curse of dimensionality; Computer science; Imaging spectroscopy; Variogram; Spectral imaging; Image resolution; Principal component analysis; Spectral resolution; Spatial analysis; Spatial dependence; Basis (linear algebra); Pattern recognition (psychology); Artificial intelligence; Spectrometer; Mathematics; Spectral line; Geology; Kriging; Physics; Optics; Land use; Statistics; Geometry","score_opus":0.03491766156629219,"score_gpt":0.2802327638009182,"score_spread":0.24531510223462602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964175518","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00158233,0.0004577039,0.9959025,0.00012607117,0.000052765965,0.0000614987,0.00046870662,0.00087910326,0.00046930084],"genre_scores_gemma":[0.021417338,0.0009886195,0.9748147,0.00013290756,0.00015074872,0.00027513914,0.0013811063,0.00016855111,0.00067085325],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99790907,0.00047674082,0.00030455884,0.00043083233,0.0008031518,0.000075694385],"domain_scores_gemma":[0.99666756,0.0017832236,0.0003513469,0.00058537745,0.0005026327,0.00010993431],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002695629,0.0015524656,0.0015600258,0.0075014452,0.00068206986,0.0035599642,0.0015093969,0.0010421993,0.0023254391],"category_scores_gemma":[0.006547572,0.00067311036,0.002290576,0.007881701,0.0018981256,0.0046205837,0.0023858664,0.0018625293,0.0018155755],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019287689,0.00011213818,0.0022700536,0.0009885177,0.0002932313,0.0005350076,0.0008410203,0.022730824,0.02363122,0.1297751,0.0092045395,0.8094254],"study_design_scores_gemma":[0.00008343918,0.0004897487,0.0051535964,0.00049040915,0.0002321642,0.0027100986,0.0005622488,0.4232592,0.033831764,0.38449842,0.14827645,0.00041249787],"about_ca_topic_score_codex":0.0011112748,"about_ca_topic_score_gemma":0.0008207416,"teacher_disagreement_score":0.0075014452,"about_ca_system_score_codex":0.0005570159,"about_ca_system_score_gemma":0.0010726843,"threshold_uncertainty_score":0.01425606},"labels":[],"label_agreement":null},{"id":"W1965696863","doi":"10.1117/12.2016291","title":"Scale profile as feature for quick satellite image object-based classification","year":2013,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Scale (ratio); Pixel; Artificial intelligence; Feature (linguistics); Contextual image classification; Remote sensing; Set (abstract data type); Computer vision; Data set; Satellite; Representation (politics); Transformation (genetics); Feature extraction; Pattern recognition (psychology); Object detection; Image (mathematics); Geology; Cartography; Geography","score_opus":0.010879262735199744,"score_gpt":0.22672978983039066,"score_spread":0.21585052709519092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1965696863","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45023292,0.0006098848,0.53687614,0.00019166863,0.00007946053,0.00030426166,0.002228389,0.0021571298,0.007320088],"genre_scores_gemma":[0.8597013,0.00030365,0.13568723,0.00003124801,0.000034300545,0.000119309196,0.0023705629,0.00012244468,0.0016298974],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9998313,0.000016982536,0.000010250218,0.000022823686,0.00008375464,0.000034763518],"domain_scores_gemma":[0.9998221,0.000039412756,0.000027217337,0.000029733688,0.000060432634,0.00002116085],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002367508,0.00028392344,0.00025952718,0.0016994794,0.00021545724,0.00060242444,0.00021814033,0.00021145004,0.0015800474],"category_scores_gemma":[0.0006326139,0.00010598346,0.00034871278,0.0013190773,0.00020215122,0.0006619513,0.00033831678,0.0003106271,0.0009437348],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035441553,0.00019797414,0.031469386,0.00020300923,0.00005435423,0.00032242123,0.0001894157,0.015791442,0.21399534,0.003676464,0.0042792303,0.7294665],"study_design_scores_gemma":[0.000045495322,0.0005156483,0.23888153,0.0000635647,0.0001268917,0.0011329283,0.0006244565,0.60269165,0.1329109,0.006246242,0.016641486,0.00011921485],"about_ca_topic_score_codex":0.001652901,"about_ca_topic_score_gemma":0.0017191563,"teacher_disagreement_score":0.0016994794,"about_ca_system_score_codex":0.00020160033,"about_ca_system_score_gemma":0.00026376892,"threshold_uncertainty_score":0.0052857995},"labels":[],"label_agreement":null},{"id":"W1965991201","doi":"10.1080/07038992.2000.10874784","title":"A Framework for the Development and Assessment of Object Recognition Modules from High-Resolution Satellite Images","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Cartography; Geography; Art","score_opus":0.029084314686472164,"score_gpt":0.24925607475149947,"score_spread":0.2201717600650273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1965991201","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017039567,0.00012017307,0.9931329,0.000095543626,0.000017871113,0.00026484547,0.00012948,0.0030041665,0.0015310278],"genre_scores_gemma":[0.031796247,0.00022902247,0.9640539,0.000047087484,0.000016901227,0.0005503891,0.0007255021,0.00023074675,0.0023501145],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880266,0.0002639849,0.00009681408,0.0002048577,0.0005166021,0.000115049974],"domain_scores_gemma":[0.99860126,0.00027259014,0.000120773475,0.00025044687,0.0006480251,0.00010685701],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003308988,0.0013465482,0.00069538783,0.0018174043,0.00082773756,0.0028038372,0.003115528,0.0018454609,0.0057857707],"category_scores_gemma":[0.0041303537,0.00074174436,0.0020959927,0.00085108494,0.000979395,0.0024520631,0.0021529573,0.0013731832,0.0028304793],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020321982,0.00045446705,0.00450646,0.0010533392,0.00031947007,0.0007424527,0.0005598667,0.2847295,0.062914476,0.13043232,0.013845996,0.5002384],"study_design_scores_gemma":[0.000047049925,0.00017485552,0.0016187843,0.00017432091,0.00007794894,0.00033705187,0.00015628409,0.9049587,0.02139301,0.02986449,0.041137602,0.000059833557],"about_ca_topic_score_codex":0.013568869,"about_ca_topic_score_gemma":0.01284724,"teacher_disagreement_score":0.013568869,"about_ca_system_score_codex":0.0017574881,"about_ca_system_score_gemma":0.003876678,"threshold_uncertainty_score":0.026979804},"labels":[],"label_agreement":null},{"id":"W1966818575","doi":"10.1109/isspa.2012.6310665","title":"Hyperspectral band selection based on graph clustering","year":2012,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hyperspectral imaging; Cluster analysis; Adjacency matrix; Adjacency list; Computer science; Pattern recognition (psychology); Graph; Spectral clustering; Artificial intelligence; Selection (genetic algorithm); Data mining; Algorithm; Theoretical computer science","score_opus":0.015869457846515098,"score_gpt":0.21822851969573742,"score_spread":0.2023590618492223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1966818575","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010686875,0.00015942662,0.987665,0.00011695971,0.000016856424,0.00005285157,0.000048867685,0.0004439529,0.00080929906],"genre_scores_gemma":[0.20608057,0.00040860928,0.78928864,0.00019656382,0.00010546276,0.00020852534,0.00066766806,0.00023516186,0.0028087902],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906546,0.0002234421,0.000027858849,0.00023440237,0.00037653014,0.000072207105],"domain_scores_gemma":[0.9994004,0.00027323893,0.000077581106,0.00007114532,0.00014610704,0.000031625084],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006219308,0.00090745196,0.0010978156,0.0028589896,0.0008202329,0.00086147554,0.0012507597,0.00094101735,0.0015385185],"category_scores_gemma":[0.0013925689,0.00035877866,0.0008704504,0.0021534048,0.00065764895,0.0013986683,0.00088124,0.0006994205,0.00071691285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002266841,0.00022326567,0.0018788856,0.00020975008,0.00015888765,0.0001690202,0.0002056005,0.3344413,0.02731462,0.018050358,0.006613154,0.61050844],"study_design_scores_gemma":[0.00001405923,0.000029377023,0.00047053065,0.0000078010435,0.000019581994,0.000081623155,0.000040019786,0.98075587,0.005292824,0.011476129,0.0017952182,0.000016970576],"about_ca_topic_score_codex":0.003312314,"about_ca_topic_score_gemma":0.003637248,"teacher_disagreement_score":0.003312314,"about_ca_system_score_codex":0.0006402075,"about_ca_system_score_gemma":0.00067631126,"threshold_uncertainty_score":0.006586075},"labels":[],"label_agreement":null},{"id":"W1968264145","doi":"10.1016/s0380-1330(03)70539-5","title":"Remote Sensing of the Coastal Zone of Tropical Lakes Using Synthetic Aperture Radar and Optical Data","year":2003,"lang":"en","type":"article","venue":"Journal of Great Lakes Research","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Canadian Space Agency; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; United States Agency for International Development","keywords":"Remote sensing; Synthetic aperture radar; Geology; Radar; Oceanography; Environmental science; Computer science; Telecommunications","score_opus":0.0868005210510355,"score_gpt":0.3279802892554196,"score_spread":0.2411797682043841,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968264145","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9964994,0.00013170848,0.001370642,0.00006353337,0.0000067591936,0.000009943949,0.00048038227,0.000054087086,0.0013834006],"genre_scores_gemma":[0.9955556,0.00011609799,0.003117116,0.000020184427,0.000013897781,0.000007054507,0.0005733447,0.0000059823738,0.00059077964],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99993384,0.000008996202,0.000004566534,0.000012946465,0.000024649158,0.000014974943],"domain_scores_gemma":[0.9998381,0.00002990026,0.000036252884,0.00001229896,0.000056746132,0.000026726024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016900095,0.00023054189,0.00017888822,0.0007442307,0.00021425945,0.00037119468,0.00017700368,0.0001942841,0.0005320563],"category_scores_gemma":[0.00031565773,0.00016102323,0.00016614616,0.0007248168,0.00016945567,0.00037359112,0.0002686329,0.000117809504,0.00012984473],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011887775,0.00031631786,0.34588212,0.00039665084,0.00023922921,0.00068822625,0.0008857985,0.04365622,0.43878153,0.0011357125,0.0035985822,0.16323085],"study_design_scores_gemma":[0.00012662789,0.00011214287,0.87605256,0.000026377162,0.00012702242,0.00019243172,0.00063824066,0.09851721,0.021024996,0.00031225398,0.0028341645,0.00003604674],"about_ca_topic_score_codex":0.01826981,"about_ca_topic_score_gemma":0.028224055,"teacher_disagreement_score":0.01826981,"about_ca_system_score_codex":0.000260378,"about_ca_system_score_gemma":0.0004762645,"threshold_uncertainty_score":0.036326945},"labels":[],"label_agreement":null},{"id":"W1969184429","doi":"10.1109/tgrs.2011.2160646","title":"A Bicriteria-Optimization-Approach-Based Dimensionality-Reduction Model for the Color Display of Hyperspectral Images","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Hyperspectral imaging; Computer science; Dimensionality reduction; Artificial intelligence; Visualization; Curse of dimensionality; Pattern recognition (psychology); Mathematical optimization; Mathematics","score_opus":0.03629205643565588,"score_gpt":0.2370224482504469,"score_spread":0.20073039181479102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969184429","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025922358,0.000059720638,0.9966564,0.00007068523,0.000007075237,0.0000127147605,0.000021082285,0.00005076663,0.0005293226],"genre_scores_gemma":[0.32122722,0.0004178078,0.6697331,0.00020008648,0.00005886713,0.0003783414,0.00029962795,0.0002095295,0.007475367],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992716,0.0002971688,0.000028292712,0.0001437697,0.0002134006,0.000045842393],"domain_scores_gemma":[0.9995109,0.00021299014,0.000071600196,0.000059078702,0.00012517808,0.000020238855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010758148,0.0007486823,0.0009797086,0.0005324779,0.0003525984,0.000872183,0.001499308,0.00083411887,0.001469965],"category_scores_gemma":[0.0017519122,0.00050670886,0.0010264331,0.00068277965,0.0010087558,0.0010299481,0.00096275855,0.0012345539,0.00053967506],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039794715,0.000035016776,0.00039067116,0.000071406306,0.00005361362,0.00004542221,0.00007912939,0.923337,0.003937525,0.04392564,0.0010124536,0.027072307],"study_design_scores_gemma":[0.0000021709382,0.000008710734,0.00005749578,0.000002167661,0.0000031766285,0.000011579137,0.000002422575,0.9954146,0.0003166768,0.0038413373,0.00033319273,0.0000063877437],"about_ca_topic_score_codex":0.0033209915,"about_ca_topic_score_gemma":0.004350886,"teacher_disagreement_score":0.0033209915,"about_ca_system_score_codex":0.0009098033,"about_ca_system_score_gemma":0.00079538574,"threshold_uncertainty_score":0.0066033006},"labels":[],"label_agreement":null},{"id":"W1969903290","doi":"10.1016/j.ijleo.2011.06.018","title":"Image difference detection under varying illumination based on vector space and correlations","year":2011,"lang":"en","type":"article","venue":"Optik","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"European Regional Development Fund; Natural Sciences and Engineering Research Council of Canada; Ministerio de Ciencia e Innovación","keywords":"Robustness (evolution); Computer science; Invariant (physics); Artificial intelligence; Image (mathematics); Computer vision; Algorithm; Physics","score_opus":0.02330660881830407,"score_gpt":0.20949647279676412,"score_spread":0.18618986397846005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969903290","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36894843,0.0004229678,0.6281649,0.00016755804,0.00005643218,0.000050205035,0.00015548828,0.00039376202,0.0016403309],"genre_scores_gemma":[0.8979419,0.000331322,0.10075137,0.000039551225,0.000047875976,0.00003457317,0.00020578725,0.000043466287,0.0006041318],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995777,0.00010590941,0.000019725318,0.00008531334,0.00015697692,0.00005433738],"domain_scores_gemma":[0.99888974,0.00055478094,0.00016460175,0.00009176751,0.00024409243,0.000055004013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006497604,0.00034610857,0.0005254376,0.0009607006,0.00024341333,0.0007683127,0.0003526186,0.0003737021,0.0005998236],"category_scores_gemma":[0.0022472441,0.00020736028,0.00038661808,0.0011092399,0.00049011095,0.0009140858,0.00042814927,0.0004820741,0.00021332035],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016935883,0.00031496113,0.019026868,0.00031883735,0.00020050815,0.00034926916,0.00034313125,0.06800705,0.33683562,0.014081175,0.0024900977,0.5563389],"study_design_scores_gemma":[0.000036840218,0.00018867599,0.024185311,0.000020566025,0.00007973007,0.00047650357,0.000076708566,0.91114026,0.05953397,0.003332893,0.0008765478,0.00005202463],"about_ca_topic_score_codex":0.0009473852,"about_ca_topic_score_gemma":0.0013730008,"teacher_disagreement_score":0.0009607006,"about_ca_system_score_codex":0.00028513873,"about_ca_system_score_gemma":0.00055622513,"threshold_uncertainty_score":0.003436327},"labels":[],"label_agreement":null},{"id":"W1970212900","doi":"10.1109/igarss.2014.6946801","title":"Z-Score distance: A spectral matching technique for automatic class labelling in unsupervised classification","year":2014,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"Natural Sciences and Engineering Research Council of Canada; University of Lethbridge","keywords":"Hyperspectral imaging; Pattern recognition (psychology); Artificial intelligence; Computer science; Classifier (UML); Pixel; Contextual image classification; Matching (statistics); Mathematics; Image (mathematics); Statistics","score_opus":0.022131127508909606,"score_gpt":0.24358365579572577,"score_spread":0.22145252828681616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970212900","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011756608,0.0000702583,0.98444253,0.00003652044,0.000028104967,0.00007405803,0.00013894211,0.002483616,0.0009693358],"genre_scores_gemma":[0.0833883,0.00007597736,0.9136626,0.000044771703,0.000035554425,0.0001703172,0.0006206354,0.00048433375,0.0015175147],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99727255,0.0005221204,0.00017101904,0.00052801456,0.0013353031,0.00017097846],"domain_scores_gemma":[0.99795616,0.0005935283,0.00029873865,0.00038135867,0.0006910566,0.00007911439],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023555558,0.0009579495,0.0010032979,0.0046552513,0.00092878734,0.0011410916,0.0017332623,0.00091384543,0.003354566],"category_scores_gemma":[0.003943953,0.00035763503,0.0009843502,0.0037243457,0.00085455854,0.0018105712,0.0014616644,0.0011035411,0.002491104],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018624616,0.00021421678,0.0038217327,0.0001676667,0.00013847888,0.00007751843,0.00027164066,0.011837516,0.043480355,0.0066324635,0.0054924,0.92767966],"study_design_scores_gemma":[0.00009463683,0.00038244177,0.016727274,0.00007607082,0.00010917103,0.00077829364,0.00044388842,0.7761938,0.14068854,0.025908407,0.03840841,0.0001891413],"about_ca_topic_score_codex":0.0022845143,"about_ca_topic_score_gemma":0.003911543,"teacher_disagreement_score":0.0046552513,"about_ca_system_score_codex":0.0005142439,"about_ca_system_score_gemma":0.0011177049,"threshold_uncertainty_score":0.01245755},"labels":[],"label_agreement":null},{"id":"W1973989678","doi":"10.1016/s1002-0705(08)60076-x","title":"Solution of Multiple-Point Statistics to Extracting Information from Remotely Sensed Imagery","year":2008,"lang":"en","type":"article","venue":"Journal of China University of Geosciences","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Classifier (UML); Pattern recognition (psychology); Point (geometry); Artificial intelligence; Remote sensing; Identification (biology); Basis (linear algebra); Spatial analysis; Contextual image classification; Image (mathematics); Data mining; Mathematics; Geography","score_opus":0.014483757743966414,"score_gpt":0.19285393596038572,"score_spread":0.17837017821641932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973989678","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0116069,0.00010704934,0.9876956,0.00007486352,0.000027835114,0.000026809083,0.000038322258,0.00019855228,0.0002242228],"genre_scores_gemma":[0.21411583,0.0003501835,0.78305924,0.00004077058,0.0001049461,0.0002337943,0.00041588352,0.00011449319,0.0015649409],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995522,0.0001289971,0.000032929493,0.000091977374,0.00015809879,0.000035747762],"domain_scores_gemma":[0.99852705,0.0009217816,0.00012826499,0.00010193383,0.0002818496,0.000039072453],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011419681,0.0009608984,0.0011799308,0.0010784011,0.000544468,0.0009558872,0.00098848,0.0011034091,0.00094298023],"category_scores_gemma":[0.004369693,0.0007995082,0.0013463694,0.0014509984,0.000646784,0.0010151771,0.0007785084,0.001145468,0.000370719],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012568246,0.00012225985,0.0013747454,0.00026946477,0.00015283779,0.00015046625,0.0001568981,0.72766846,0.011089672,0.014337244,0.0023620643,0.24219021],"study_design_scores_gemma":[0.000004864375,0.000010289323,0.0001500619,0.0000023952646,0.0000062967047,0.0000100441575,0.0000096457015,0.99681014,0.0007559412,0.0020369925,0.00019884485,0.000004497876],"about_ca_topic_score_codex":0.005772956,"about_ca_topic_score_gemma":0.0049486104,"teacher_disagreement_score":0.005772956,"about_ca_system_score_codex":0.0005611687,"about_ca_system_score_gemma":0.002545645,"threshold_uncertainty_score":0.0114786625},"labels":[],"label_agreement":null},{"id":"W1974154854","doi":"10.1109/lgrs.2012.2193552","title":"Building Detection in Very High Spatial Resolution Multispectral Images Using the Hit-or-Miss Transform","year":2012,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Multispectral image; Dilation (metric space); Image resolution; Computer science; Pixel; Mathematical morphology; Remote sensing; Artificial intelligence; Multispectral pattern recognition; Computer vision; Similarity (geometry); Hyperspectral imaging; Pattern recognition (psychology); Image processing; Geography; Image (mathematics); Mathematics","score_opus":0.01776498053635428,"score_gpt":0.24044533247161146,"score_spread":0.22268035193525718,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1974154854","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0977218,0.00035462843,0.8996683,0.00010171249,0.000025308102,0.00004178167,0.00007763186,0.00061362656,0.0013952317],"genre_scores_gemma":[0.35669014,0.00040547916,0.6410834,0.000038761933,0.000042219537,0.000043095497,0.00018550006,0.000054124637,0.001457275],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99968934,0.00006229508,0.000014435067,0.00005213415,0.00015229388,0.000029487019],"domain_scores_gemma":[0.9997019,0.000091640555,0.000060927116,0.000045834764,0.0000790064,0.000020727035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038496256,0.00036524233,0.00039007768,0.0011444036,0.00021541124,0.000572576,0.0003489559,0.00042355052,0.00085513724],"category_scores_gemma":[0.00075969443,0.00024988566,0.0004538002,0.0007644268,0.00042001507,0.0007029511,0.00045351588,0.0003486478,0.0005104289],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030815054,0.0001134241,0.004235315,0.0002849674,0.00010684759,0.00052312406,0.00016461864,0.024573313,0.40976134,0.0045717526,0.0013011178,0.554056],"study_design_scores_gemma":[0.000040990133,0.00054340146,0.032055862,0.000044218606,0.00014007834,0.0044588693,0.00024435943,0.70545805,0.2441728,0.0053399205,0.007371708,0.00012980332],"about_ca_topic_score_codex":0.0003746597,"about_ca_topic_score_gemma":0.00068642845,"teacher_disagreement_score":0.0011444036,"about_ca_system_score_codex":0.00013612847,"about_ca_system_score_gemma":0.00019358123,"threshold_uncertainty_score":0.002860725},"labels":[],"label_agreement":null},{"id":"W1975219361","doi":"10.1117/12.760747","title":"Fusion of RADARSAT fine-beam SAR and QuickBird data for land-cover mapping and change detection","year":2007,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Space Agency","keywords":"Change detection; Land cover; Cohen's kappa; Remote sensing; Synthetic aperture radar; Computer science; Contextual image classification; Artificial intelligence; Pattern recognition (psychology); Land use; Geography; Image (mathematics); Machine learning","score_opus":0.027990396082177852,"score_gpt":0.23987557811933982,"score_spread":0.21188518203716197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975219361","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9515523,0.0008416548,0.04283113,0.00012920942,0.00006879534,0.00012949959,0.0007710035,0.00071052794,0.0029659832],"genre_scores_gemma":[0.9445455,0.000314081,0.05344966,0.000052119387,0.000024237903,0.000032545286,0.0010749178,0.00003186857,0.00047502396],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989562,0.0002496089,0.00006740709,0.00014077277,0.0005093954,0.00007654055],"domain_scores_gemma":[0.9990528,0.00024756967,0.00012265469,0.00014043492,0.00038634177,0.000050135204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024398386,0.00061705156,0.00065070175,0.0014949136,0.00019836512,0.0006962257,0.00031673754,0.00029605842,0.0006813561],"category_scores_gemma":[0.0020476037,0.00024131815,0.0005947684,0.0009867722,0.00019860301,0.0013362317,0.0005364962,0.00021821169,0.00048049024],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024872909,0.00070739817,0.11106985,0.0006247008,0.0006264022,0.00024724356,0.00028813744,0.096264265,0.2939917,0.0005302839,0.0016324923,0.49153027],"study_design_scores_gemma":[0.00020406207,0.0028976144,0.38123187,0.00007728677,0.00080025574,0.00068470364,0.00041334573,0.4115681,0.19491036,0.0012173252,0.00580714,0.00018796069],"about_ca_topic_score_codex":0.0020125436,"about_ca_topic_score_gemma":0.0036769067,"teacher_disagreement_score":0.0024398386,"about_ca_system_score_codex":0.00046534414,"about_ca_system_score_gemma":0.0002975749,"threshold_uncertainty_score":0.012903273},"labels":[],"label_agreement":null},{"id":"W1975415806","doi":"10.1109/igarss.2014.6947221","title":"Comparative study of feature space projection methods for hyperspectral image classification","year":2014,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Projection (relational algebra); Hyperspectral imaging; Pattern recognition (psychology); Artificial intelligence; Dimensionality reduction; Feature (linguistics); Feature vector; Computer science; Dimension (graph theory); Feature extraction; Mathematics; Algorithm","score_opus":0.05561923082773211,"score_gpt":0.36944800540090533,"score_spread":0.3138287745731732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975415806","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1523705,0.01768737,0.81925744,0.00063700095,0.00028417964,0.0002299527,0.00033756116,0.0015240734,0.0076720016],"genre_scores_gemma":[0.5899542,0.008709919,0.3966832,0.000121879886,0.00020443006,0.0002618024,0.0011663843,0.00022597314,0.002672244],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99768364,0.0006769421,0.00016008159,0.00028711738,0.0010909889,0.000101224905],"domain_scores_gemma":[0.99538285,0.0023925812,0.00021495612,0.0003052859,0.0016152996,0.00008895593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033402261,0.0010026027,0.0010573495,0.0027282864,0.0004598187,0.0012170352,0.00063844805,0.0006710498,0.001477981],"category_scores_gemma":[0.006924616,0.0002322194,0.0010535491,0.0027085713,0.00048180582,0.001916003,0.000736908,0.00095873786,0.00047659967],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038785097,0.00018739747,0.0040993737,0.0005360358,0.00034901613,0.000088363166,0.0002083363,0.043263163,0.009702264,0.0029882113,0.0027288035,0.9354612],"study_design_scores_gemma":[0.00003506153,0.00041498363,0.012487108,0.00011682172,0.00018520787,0.00037389976,0.00030119513,0.95556325,0.020209199,0.003938566,0.0062818592,0.000092759365],"about_ca_topic_score_codex":0.0021243647,"about_ca_topic_score_gemma":0.0016500603,"teacher_disagreement_score":0.0033402261,"about_ca_system_score_codex":0.00044781182,"about_ca_system_score_gemma":0.0006947245,"threshold_uncertainty_score":0.017665029},"labels":[],"label_agreement":null},{"id":"W1976152398","doi":"10.1109/igarss.2014.6947074","title":"Semi-supervised classification of hyperspectral image using random forest algorithm","year":2014,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Hyperspectral imaging; Random forest; Pattern recognition (psychology); Computer science; Artificial intelligence; Contextual image classification; Classifier (UML); Statistical classification; Cohen's kappa; Image (mathematics); Algorithm; Mathematics; Machine learning","score_opus":0.019371358439767238,"score_gpt":0.23478478660954916,"score_spread":0.21541342816978193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976152398","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02188775,0.00016651246,0.9760659,0.000039281298,0.000019920293,0.00006519086,0.00007364921,0.0010193901,0.000662434],"genre_scores_gemma":[0.3492199,0.00021318505,0.6477295,0.000069122536,0.00007462852,0.0002750622,0.0008173435,0.00012229655,0.0014789088],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985806,0.000426761,0.000081620914,0.00033112543,0.00045885393,0.000121030396],"domain_scores_gemma":[0.9988368,0.00044636647,0.00015633099,0.00011671437,0.00041353906,0.000030236513],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014620627,0.000751821,0.0011956248,0.0015536989,0.00048357493,0.00053786155,0.0009251398,0.00069493864,0.00085344363],"category_scores_gemma":[0.001927717,0.00031065612,0.0011451076,0.00095466705,0.0004421354,0.0009207973,0.00041166143,0.0006520545,0.00054137706],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036011575,0.0003315973,0.0042599486,0.000257276,0.000219209,0.00013550138,0.00015381916,0.29488716,0.044433434,0.003941005,0.0034657703,0.6475551],"study_design_scores_gemma":[0.000013880958,0.000045722823,0.0011399805,0.00001045133,0.000017379982,0.0000749377,0.00001475591,0.99058634,0.0058287284,0.0015301898,0.00071839854,0.000019136842],"about_ca_topic_score_codex":0.0025943285,"about_ca_topic_score_gemma":0.0032996563,"teacher_disagreement_score":0.0025943285,"about_ca_system_score_codex":0.00034548566,"about_ca_system_score_gemma":0.00065054646,"threshold_uncertainty_score":0.0077322125},"labels":[],"label_agreement":null},{"id":"W1977076643","doi":"10.1117/12.853919","title":"Local vector space operators for detection of differences in images under varying illumination","year":2010,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"European Regional Development Fund","keywords":"Artificial intelligence; Computer vision; Image (mathematics); Computer science; Representation (politics); Image processing; Space (punctuation); Pattern recognition (psychology); Mathematics","score_opus":0.011237086830851936,"score_gpt":0.2205428373079488,"score_spread":0.20930575047709687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977076643","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02028349,0.00016123384,0.97863823,0.000044912267,0.000021047867,0.00005573586,0.00004217733,0.00026714127,0.00048592265],"genre_scores_gemma":[0.2870555,0.00032955254,0.7107934,0.00008368963,0.00007926795,0.00023010447,0.00022971639,0.00020540885,0.0009933212],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998389,0.00044357686,0.000087368506,0.00022168101,0.00077175815,0.000086742184],"domain_scores_gemma":[0.995237,0.002463371,0.0007866385,0.00058257324,0.0007662069,0.0001641992],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032422985,0.00064582675,0.0006696482,0.0013834098,0.0003269288,0.0011292401,0.0010038624,0.0006554261,0.0015204259],"category_scores_gemma":[0.0074636596,0.00015969813,0.000642281,0.0012250807,0.0013381756,0.002584143,0.0009944788,0.0010086688,0.00041567345],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007767202,0.00037980048,0.005273704,0.00058887264,0.00014468461,0.00025129857,0.0005644555,0.14108738,0.14259224,0.15274514,0.0033160846,0.55227965],"study_design_scores_gemma":[0.000046435234,0.00048270344,0.0036590926,0.000037236045,0.000050372008,0.00044534635,0.00018112067,0.90226525,0.043245867,0.045639835,0.003818413,0.00012841787],"about_ca_topic_score_codex":0.0006904921,"about_ca_topic_score_gemma":0.0005839123,"teacher_disagreement_score":0.0032422985,"about_ca_system_score_codex":0.0005183655,"about_ca_system_score_gemma":0.00075234706,"threshold_uncertainty_score":0.017147124},"labels":[],"label_agreement":null},{"id":"W1979393858","doi":"10.1109/icif.2007.4407991","title":"Comparing several AFE tools in the context of ships and vehicles detection based on RGB and EO data","year":2007,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Defence Research and Development Canada","funders":"","keywords":"Context (archaeology); Computer science; Feature (linguistics); RGB color model; False alarm; National laboratory; Machine learning; Artificial intelligence; Engineering","score_opus":0.09850031136562903,"score_gpt":0.2702102723753235,"score_spread":0.1717099610096945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979393858","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43268502,0.0049823183,0.54271716,0.00054086576,0.00032613633,0.0005504937,0.0015209342,0.006211302,0.01046571],"genre_scores_gemma":[0.67559874,0.0012282217,0.3187419,0.00018801291,0.00008296583,0.00023295962,0.0015973303,0.00045161977,0.0018783084],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99528694,0.0016444855,0.00043357155,0.00066198764,0.0016479614,0.00032495186],"domain_scores_gemma":[0.97683513,0.015477324,0.0006773485,0.001681689,0.0049653943,0.00036299357],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008035057,0.0012299464,0.0012828099,0.008971614,0.00069913594,0.001871083,0.0011652545,0.0015249018,0.0015288397],"category_scores_gemma":[0.026414078,0.0003329577,0.0009536985,0.0031713303,0.00057044317,0.0027033288,0.0013562377,0.0006954843,0.0008085253],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002998899,0.0005993721,0.04623592,0.0011672041,0.0013297751,0.000366562,0.0005839313,0.022953525,0.023817457,0.0021520634,0.002305684,0.8954896],"study_design_scores_gemma":[0.0006706026,0.0040221885,0.17103276,0.00056199357,0.0020031813,0.0034983126,0.0030857073,0.5415018,0.22957978,0.006074719,0.03733006,0.0006388959],"about_ca_topic_score_codex":0.0020876217,"about_ca_topic_score_gemma":0.0028386454,"teacher_disagreement_score":0.008971614,"about_ca_system_score_codex":0.00037297636,"about_ca_system_score_gemma":0.00032142826,"threshold_uncertainty_score":0.042494},"labels":[],"label_agreement":null},{"id":"W1979713463","doi":"10.5589/m08-007","title":"Evaluation and comparison of dimensionality reduction methods and band selection","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Endmember; Hyperspectral imaging; Dimensionality reduction; Principal component analysis; Selection (genetic algorithm); Pattern recognition (psychology); Artificial intelligence; Wavelet; Computer science; Noise reduction; Remote sensing; Mathematics; Geography","score_opus":0.06356255588470132,"score_gpt":0.33550071435141715,"score_spread":0.2719381584667158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979713463","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5176944,0.00951791,0.458709,0.0006776495,0.0004951455,0.00083002757,0.0013949935,0.004416093,0.006264813],"genre_scores_gemma":[0.5457916,0.0019997752,0.44615573,0.00014134913,0.000114519775,0.0006810306,0.002312581,0.00032205004,0.0024813854],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9957111,0.0016458894,0.00033826946,0.00045478146,0.0016877364,0.00016219747],"domain_scores_gemma":[0.9926238,0.003571074,0.0004325871,0.0006437537,0.0026275886,0.00010113155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0051054657,0.0014455849,0.0008278784,0.003056173,0.0004703935,0.0011211509,0.00063087593,0.0006999096,0.0013812839],"category_scores_gemma":[0.009621654,0.00025179342,0.001228703,0.0019492983,0.00038763203,0.0010717814,0.0008680381,0.0005556706,0.0005585896],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013469361,0.00067115953,0.009966725,0.0010328717,0.0007120024,0.00008971617,0.00026543796,0.08432594,0.03473003,0.0019640203,0.0046548313,0.8602403],"study_design_scores_gemma":[0.00017154116,0.0015838185,0.029901579,0.00017421329,0.0003321748,0.0003135917,0.00040433998,0.88834816,0.06909105,0.0016518339,0.007902503,0.00012516585],"about_ca_topic_score_codex":0.0023633882,"about_ca_topic_score_gemma":0.0016772848,"teacher_disagreement_score":0.0051054657,"about_ca_system_score_codex":0.0005874895,"about_ca_system_score_gemma":0.0006083127,"threshold_uncertainty_score":0.027000606},"labels":[],"label_agreement":null},{"id":"W1980641044","doi":"10.1016/j.isprsjprs.2015.04.003","title":"Multiband compact texture unit descriptor for intra-band and inter-band texture analysis","year":2015,"lang":"en","type":"article","venue":"ISPRS Journal of Photogrammetry and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Multispectral image; Panchromatic film; Artificial intelligence; Principal component analysis; Texture (cosmology); Pattern recognition (psychology); Computer science; Spectral bands; Multispectral pattern recognition; Mathematics; Computer vision; Remote sensing; Geography; Image (mathematics)","score_opus":0.03425808024276311,"score_gpt":0.2708681096196606,"score_spread":0.2366100293768975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980641044","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09444133,0.0010959393,0.89780724,0.00016157738,0.00027142907,0.00013761604,0.0015131853,0.0014548331,0.0031169087],"genre_scores_gemma":[0.5728188,0.0011666783,0.41051096,0.00019167516,0.00021261272,0.00033575363,0.0045788274,0.00041042097,0.009774199],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99970657,0.000038404265,0.000018847377,0.00004754371,0.00014070584,0.000047826023],"domain_scores_gemma":[0.99951565,0.0000748344,0.00004889858,0.000105195904,0.00021707875,0.000038356233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000327318,0.0004635206,0.0007168657,0.0017610798,0.00023526925,0.0007404555,0.00052901084,0.00035988618,0.0041006985],"category_scores_gemma":[0.0008026249,0.0001429647,0.0005601181,0.0020647105,0.00024161514,0.00066555577,0.00062144554,0.00056469004,0.0013167107],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00077705906,0.00025708362,0.0013226599,0.00018143204,0.00006216264,0.00007017934,0.000042956268,0.009609574,0.17153516,0.004123186,0.008723938,0.8032946],"study_design_scores_gemma":[0.0000807194,0.00039687322,0.014764654,0.000045041226,0.00016084153,0.00045279568,0.00016721414,0.8619654,0.099416204,0.0031703822,0.019293334,0.00008649659],"about_ca_topic_score_codex":0.002189542,"about_ca_topic_score_gemma":0.0033819394,"teacher_disagreement_score":0.0041006985,"about_ca_system_score_codex":0.00030006716,"about_ca_system_score_gemma":0.00049418974,"threshold_uncertainty_score":0.013718247},"labels":[],"label_agreement":null},{"id":"W1982738077","doi":"10.1109/icspt.2011.6064666","title":"Lower bounds in classification for feature and algorithm selection","year":2011,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"AUG Signals (Canada)","funders":"","keywords":"Computer science; Classifier (UML); Clutter; Algorithm; Artificial intelligence; Feature selection; Machine learning; Statistical classification; Confusion; Upper and lower bounds; Bayesian probability; Data mining; Pattern recognition (psychology); Set (abstract data type); Radar; Mathematics","score_opus":0.028368494279106742,"score_gpt":0.23054358772861738,"score_spread":0.20217509344951065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982738077","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003621799,0.010795945,0.97686243,0.0010113383,0.00026623803,0.000061543215,0.00013875274,0.00030366622,0.0069382107],"genre_scores_gemma":[0.259364,0.018516172,0.6992421,0.0019035967,0.0030951938,0.0011724487,0.0019462365,0.0015252007,0.013235022],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97122914,0.010966685,0.0014966697,0.0033646019,0.011209351,0.0017335607],"domain_scores_gemma":[0.86299336,0.116476625,0.003990547,0.0070268656,0.0088888,0.00062373525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023300419,0.0031867658,0.0032097707,0.0055677835,0.0019463411,0.010228017,0.003861613,0.0034404509,0.0068728235],"category_scores_gemma":[0.12561294,0.0012054094,0.0022366715,0.0056506493,0.004278924,0.010406782,0.004543767,0.008355324,0.00365491],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004744036,0.00020870175,0.0030318617,0.0011637291,0.00026097498,0.00018289888,0.0003813231,0.32897463,0.0028450212,0.34806114,0.0137217315,0.30069363],"study_design_scores_gemma":[0.000021487931,0.000114684895,0.00074977643,0.00032003628,0.00006673771,0.0001636855,0.00008042002,0.75126827,0.0030030054,0.23307964,0.011069498,0.000062768406],"about_ca_topic_score_codex":0.003337897,"about_ca_topic_score_gemma":0.0026748206,"teacher_disagreement_score":0.023300419,"about_ca_system_score_codex":0.005353994,"about_ca_system_score_gemma":0.0023320364,"threshold_uncertainty_score":0.12322587},"labels":[],"label_agreement":null},{"id":"W1985275146","doi":"10.1109/igarss.2014.6946788","title":"A pixel- and object-based image analysis framework for automatic well site extraction at regional scales using Landsat data","year":2014,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Correctness; Pixel; Computer science; Extraction (chemistry); Artificial intelligence; Computer vision; Image segmentation; Remote sensing; Object (grammar); Object based; Segmentation; Completeness (order theory); Image (mathematics); Geography; Mathematics","score_opus":0.04049152612329718,"score_gpt":0.2987524516094814,"score_spread":0.2582609254861842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985275146","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0082637,0.000066585315,0.9887738,0.00002811251,0.000008477864,0.00007654347,0.00027329882,0.0019837676,0.0005255784],"genre_scores_gemma":[0.067186914,0.00008512877,0.9302288,0.000032392687,0.000018526174,0.00012159538,0.0009627371,0.00013734194,0.001226539],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997718,0.000018783145,0.000013858781,0.000058523972,0.00010810644,0.000028961078],"domain_scores_gemma":[0.9997918,0.000023445235,0.000035350608,0.000027692975,0.00010711038,0.000014487716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004583127,0.0007432916,0.0005462252,0.0019659204,0.00046265763,0.00085990044,0.00069980917,0.00047589786,0.0012522151],"category_scores_gemma":[0.00043580338,0.00033494565,0.000758137,0.0010687012,0.00039332223,0.0006441287,0.00042199666,0.00047622027,0.00081709767],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000094959105,0.00032195498,0.0062875394,0.00018167382,0.00022366046,0.00022854818,0.00019621529,0.049865365,0.19954309,0.0067553846,0.006399125,0.7299025],"study_design_scores_gemma":[0.000022593813,0.00014501311,0.022188835,0.00003395688,0.00013552979,0.00039651582,0.0001823591,0.8928651,0.061422694,0.0053733457,0.017146919,0.000087221],"about_ca_topic_score_codex":0.01842234,"about_ca_topic_score_gemma":0.03767447,"teacher_disagreement_score":0.01842234,"about_ca_system_score_codex":0.0006224716,"about_ca_system_score_gemma":0.0011318263,"threshold_uncertainty_score":0.036630213},"labels":[],"label_agreement":null},{"id":"W1985703929","doi":"10.1109/igarss.2014.6947532","title":"Combining rotation forests and adaboost for hyperspectral imagery classification using few labeled samples","year":2014,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Hyperspectral imaging; AdaBoost; Boosting (machine learning); Artificial intelligence; Pattern recognition (psychology); Computer science; Classifier (UML); Curse of dimensionality; Mathematics","score_opus":0.04781157696588741,"score_gpt":0.2651586465620374,"score_spread":0.21734706959615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985703929","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021915734,0.0005181001,0.9751922,0.00007762328,0.00010084708,0.0000691958,0.00003933749,0.00132435,0.00076259207],"genre_scores_gemma":[0.3792832,0.00044325122,0.61741483,0.00016694028,0.00021006598,0.00014879588,0.0003624186,0.00014960578,0.0018208603],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987413,0.00037317938,0.00006686814,0.00025720356,0.0004062023,0.00015514132],"domain_scores_gemma":[0.9986375,0.00050913164,0.00013870577,0.00016604755,0.0004948261,0.0000537582],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029797729,0.0014271201,0.0015288019,0.002010898,0.0006165472,0.00077486836,0.0012495434,0.0010123637,0.00082934264],"category_scores_gemma":[0.0024720917,0.00053806277,0.0009951347,0.001662689,0.00050971686,0.001547494,0.0006938184,0.0010940457,0.00077089533],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034152053,0.00031686798,0.0030488635,0.0001446324,0.0003036592,0.000074062016,0.00006213868,0.19954966,0.024375,0.0015964638,0.0030522633,0.76713485],"study_design_scores_gemma":[0.000010568468,0.00006267958,0.000753193,0.000008118588,0.00003770566,0.000046548645,0.000014986452,0.9905806,0.0061977655,0.0011822365,0.001088593,0.000016970605],"about_ca_topic_score_codex":0.0037538102,"about_ca_topic_score_gemma":0.0049977084,"teacher_disagreement_score":0.0037538102,"about_ca_system_score_codex":0.00041983358,"about_ca_system_score_gemma":0.00073660613,"threshold_uncertainty_score":0.015758693},"labels":[],"label_agreement":null},{"id":"W1986043678","doi":"10.1109/tgrs.2012.2205579","title":"A Multiscale Latent Dirichlet Allocation Model for Object-Oriented Clustering of VHR Panchromatic Satellite Images","year":2012,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":53,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Cluster analysis; Probabilistic logic; Latent Dirichlet allocation; Artificial intelligence; Topic model; Statistical model; Pattern recognition (psychology); Data mining","score_opus":0.02241149015345338,"score_gpt":0.24624201388245737,"score_spread":0.22383052372900397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986043678","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005076194,0.00028774375,0.9936784,0.00012472755,0.00004112231,0.000039956023,0.00010142638,0.0002444433,0.00040607172],"genre_scores_gemma":[0.36873373,0.001161585,0.62100446,0.00032125314,0.0003494314,0.0007060533,0.0014451451,0.0002834488,0.0059949034],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988335,0.0003991886,0.00005946132,0.00035453343,0.00023649543,0.00011689923],"domain_scores_gemma":[0.9990771,0.00048209127,0.00010975183,0.00011621558,0.00016535848,0.000049438553],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019102714,0.0008351154,0.0013685739,0.0013502886,0.0005345076,0.0013762972,0.0029000095,0.0012556829,0.0013508622],"category_scores_gemma":[0.0034687747,0.0005988717,0.0016495938,0.0017069506,0.00080133724,0.0015924604,0.0012032675,0.0017752285,0.00079952873],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023277255,0.0001570277,0.002232334,0.0002562319,0.00020621579,0.00018774658,0.000368097,0.7302412,0.00786828,0.066640414,0.005966986,0.18564275],"study_design_scores_gemma":[0.0000065202285,0.000009509576,0.00018780083,0.000005162073,0.000012532856,0.000023350725,0.000013912619,0.98993087,0.0004486733,0.008427344,0.0009233277,0.000010966675],"about_ca_topic_score_codex":0.007144845,"about_ca_topic_score_gemma":0.00820844,"teacher_disagreement_score":0.007144845,"about_ca_system_score_codex":0.0012276851,"about_ca_system_score_gemma":0.0010295018,"threshold_uncertainty_score":0.014206529},"labels":[],"label_agreement":null},{"id":"W1986930867","doi":"10.3166/ts.27.79-108","title":"SAlgorithmes bayésiens pour le démélange supervisé, semi-supervisé et non-supervisé d’images hyperspectrales","year":2010,"lang":"fr","type":"article","venue":"Traitement du signal","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Physics; Philosophy","score_opus":0.015143267129762463,"score_gpt":0.23178036924435144,"score_spread":0.21663710211458898,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986930867","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008696161,0.0002697889,0.9894427,0.0001381107,0.000026842446,0.000038313494,0.000067190034,0.0004383368,0.00088253757],"genre_scores_gemma":[0.101998635,0.00035993397,0.88826466,0.00015282269,0.00008290075,0.00016585473,0.00047689938,0.00027403922,0.00822422],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99881977,0.0002856048,0.00006175966,0.0003027638,0.00042090993,0.00010914205],"domain_scores_gemma":[0.99827147,0.00092731975,0.00010975666,0.00014576243,0.00048702062,0.000058746766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018913669,0.0011165518,0.0010460329,0.0009752965,0.00071485905,0.0014659419,0.0016225885,0.0013501246,0.0042131464],"category_scores_gemma":[0.0052304342,0.00087712554,0.0011386821,0.0005403148,0.0010843797,0.0012392494,0.0013645627,0.0026263052,0.001433651],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003830139,0.00009028423,0.0015072692,0.00022667299,0.00014769204,0.00013931331,0.00036490307,0.41198823,0.02171222,0.043227855,0.002856655,0.5173559],"study_design_scores_gemma":[0.0000154682,0.00003997758,0.00039398362,0.000024406943,0.000015529538,0.00004466001,0.000035732064,0.98085356,0.00551089,0.010613629,0.0024351517,0.000017014921],"about_ca_topic_score_codex":0.015423755,"about_ca_topic_score_gemma":0.021646349,"teacher_disagreement_score":0.015423755,"about_ca_system_score_codex":0.0014162604,"about_ca_system_score_gemma":0.0019327768,"threshold_uncertainty_score":0.03066796},"labels":[],"label_agreement":null},{"id":"W1987785235","doi":"10.1109/lgrs.2015.2487226","title":"Feature Extraction for Hyperspectral Imagery via Ensemble Localized Manifold Learning","year":2015,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Canadian Space Agency; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Hyperspectral imaging; Feature extraction; Pattern recognition (psychology); Nonlinear dimensionality reduction; Artificial intelligence; Manifold (fluid mechanics); Computer science; Manifold alignment; Classifier (UML); Feature vector; Feature (linguistics); Dimensionality reduction","score_opus":0.020309313794779908,"score_gpt":0.24384963397887383,"score_spread":0.22354032018409392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987785235","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014580341,0.00018865113,0.984046,0.00006768738,0.000017609449,0.000022151326,0.000053375254,0.0007288943,0.00029529637],"genre_scores_gemma":[0.31324387,0.00034834188,0.68377453,0.000079897574,0.00006473488,0.00015816749,0.00081388577,0.00016232573,0.001354206],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995715,0.00009444618,0.000023226978,0.000112121896,0.00015646852,0.00004224491],"domain_scores_gemma":[0.9994305,0.00014705306,0.00008194139,0.00013794386,0.00017931114,0.000023238923],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006455102,0.0008747877,0.0011129137,0.0013367751,0.00046579633,0.0005324675,0.0008285042,0.00066107785,0.0008996088],"category_scores_gemma":[0.0015188472,0.00034793772,0.0011206745,0.0015874238,0.0004661639,0.0019108097,0.0011627615,0.0012996199,0.00062644307],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011610447,0.00018159309,0.0026698567,0.00012199317,0.00015548353,0.00014758049,0.00022094788,0.19025755,0.071154825,0.009505275,0.0053827837,0.72008604],"study_design_scores_gemma":[0.0000032773262,0.00003084657,0.00067008234,0.0000038859243,0.000008933888,0.0000429581,0.000015891028,0.985986,0.007949604,0.004187923,0.0010865256,0.000014148257],"about_ca_topic_score_codex":0.001339965,"about_ca_topic_score_gemma":0.0018236925,"teacher_disagreement_score":0.001339965,"about_ca_system_score_codex":0.0004186516,"about_ca_system_score_gemma":0.0003799619,"threshold_uncertainty_score":0.0034137964},"labels":[],"label_agreement":null},{"id":"W1988532740","doi":"10.1109/igarss.2015.7326973","title":"Detection of unexploded ordnance using airborne LWIR emissivity signatures","year":2015,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Defence Research and Development Canada","funders":"","keywords":"Unexploded ordnance; Emissivity; Remote sensing; Projectile; False alarm; Environmental science; Vegetation (pathology); Computer science; Optics; Materials science; Artificial intelligence; Geology; Physics","score_opus":0.04410414806026977,"score_gpt":0.24721049618966448,"score_spread":0.2031063481293947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988532740","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99374217,0.00018524159,0.004066169,0.00002077927,0.0000043073615,0.000015809454,0.0000856405,0.00010028731,0.0017796817],"genre_scores_gemma":[0.9920964,0.0001585025,0.006905911,0.00002014839,0.0000034148366,0.0000044055064,0.00014924892,0.000011304941,0.0006506556],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99976057,0.000014469051,0.0000038255967,0.00004004699,0.00010147327,0.0000797042],"domain_scores_gemma":[0.99975175,0.000056322817,0.000038094768,0.0000130294175,0.00011566493,0.00002509039],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003583743,0.00045961468,0.0002813149,0.00082428777,0.0003333166,0.0006841772,0.00035288592,0.00026464832,0.0004118106],"category_scores_gemma":[0.00050961436,0.0001554382,0.00016110984,0.00051043817,0.0002888509,0.0003373549,0.00026391205,0.00022179185,0.00013793923],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00079232274,0.00018959773,0.40489686,0.00022037962,0.00011767149,0.00054609583,0.00062698155,0.0150105,0.38458502,0.00025297122,0.00044921009,0.19231232],"study_design_scores_gemma":[0.000019439933,0.0003623546,0.8112219,0.000035153465,0.000118631295,0.00042694135,0.0011353864,0.06818996,0.11550526,0.00014406283,0.0027782319,0.00006258672],"about_ca_topic_score_codex":0.07228292,"about_ca_topic_score_gemma":0.23715661,"teacher_disagreement_score":0.07228292,"about_ca_system_score_codex":0.0005844226,"about_ca_system_score_gemma":0.00068103516,"threshold_uncertainty_score":0.14372438},"labels":[],"label_agreement":null},{"id":"W1988627994","doi":"10.1117/12.799232","title":"Improved iterative error analysis for endmember extraction from hyperspectral imagery","year":2008,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Resources Canada","funders":"","keywords":"Endmember; Hyperspectral imaging; Pixel; Pattern recognition (psychology); Computer science; Abundance estimation; Artificial intelligence; Constraint (computer-aided design); Image (mathematics); Feature extraction; Set (abstract data type); Algorithm; Mathematics; Abundance (ecology)","score_opus":0.018553961766707962,"score_gpt":0.2434374902112321,"score_spread":0.22488352844452414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988627994","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003220578,0.000082476545,0.9961171,0.000025301479,0.000011934852,0.000011355542,0.000016718952,0.00020620307,0.0003082313],"genre_scores_gemma":[0.061138608,0.00021275989,0.9355961,0.00004889703,0.000038844126,0.000108462424,0.00025724265,0.00024195966,0.0023571427],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986492,0.0002668876,0.00008795564,0.00023057316,0.00069936656,0.00006604854],"domain_scores_gemma":[0.9984131,0.00065762695,0.00013649289,0.00018673204,0.00057131884,0.000034690318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017535791,0.0010517756,0.00088570826,0.0011148257,0.00041763496,0.000846959,0.0015496492,0.00093226694,0.0013965878],"category_scores_gemma":[0.0040220427,0.0005196334,0.0016272871,0.00084694446,0.0006111297,0.0013028714,0.0015213571,0.0013448879,0.0006960811],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019996247,0.000087607,0.0013535694,0.00027823215,0.0001818758,0.0001464393,0.00030753054,0.59354246,0.061754208,0.022842603,0.002138426,0.31716704],"study_design_scores_gemma":[0.0000034654677,0.000010983634,0.00015649834,0.0000052269643,0.0000075594953,0.000018127597,0.000004545781,0.9923613,0.0049694325,0.0015403058,0.0009114759,0.000010984953],"about_ca_topic_score_codex":0.0036313822,"about_ca_topic_score_gemma":0.0036036337,"teacher_disagreement_score":0.0036313822,"about_ca_system_score_codex":0.00049754797,"about_ca_system_score_gemma":0.0011884583,"threshold_uncertainty_score":0.009273946},"labels":[],"label_agreement":null},{"id":"W1989203653","doi":"10.1080/01431160050121348","title":"Adaptive thresholding of texture towards white region normalization","year":2000,"lang":"en","type":"article","venue":"International Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Thresholding; Artificial intelligence; Color constancy; Preprocessor; Computer vision; Computer science; Normalization (sociology); Pixel; Remote sensing; Image processing; Pattern recognition (psychology); Image (mathematics); Geography","score_opus":0.01770776087125281,"score_gpt":0.24224732785105094,"score_spread":0.22453956697979813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989203653","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048093524,0.00031810714,0.94542325,0.00008473279,0.00007287265,0.00006152648,0.000050075803,0.0007367012,0.0051592267],"genre_scores_gemma":[0.32982412,0.0005169353,0.6616987,0.00007839841,0.00006109559,0.00008753292,0.00016455882,0.0004959889,0.0070726555],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995542,0.000059154216,0.000015760932,0.00010554947,0.00021326076,0.00005199265],"domain_scores_gemma":[0.9995018,0.000118798846,0.000050671893,0.00010084,0.00020745814,0.000020453857],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069241266,0.00042126217,0.00042998084,0.0007987474,0.0002720882,0.00090694113,0.0007586559,0.00039814113,0.0023097675],"category_scores_gemma":[0.001954555,0.00020517976,0.00044874015,0.0009009908,0.0008761324,0.0006995631,0.00074912055,0.00045930434,0.0010109287],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031001354,0.00006360801,0.0008488496,0.0001775624,0.0000391501,0.00010668054,0.00017014003,0.047657322,0.4709084,0.017316213,0.0017612693,0.46064085],"study_design_scores_gemma":[0.000033722754,0.0001714346,0.004529475,0.000035684014,0.00007293374,0.00054772897,0.0000779227,0.6160868,0.35010394,0.011721509,0.016577993,0.00004087655],"about_ca_topic_score_codex":0.0013983047,"about_ca_topic_score_gemma":0.0014283498,"teacher_disagreement_score":0.0023097675,"about_ca_system_score_codex":0.00039322797,"about_ca_system_score_gemma":0.00042833274,"threshold_uncertainty_score":0.0077269673},"labels":[],"label_agreement":null},{"id":"W1990829950","doi":"10.1109/igarss.2014.6947537","title":"Classification of land cover based on deep belief networks using polarimetric RADARSAT-2 data","year":2014,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"National Natural Science Foundation of China","keywords":"Deep belief network; Computer science; Land cover; Artificial intelligence; Support vector machine; Remote sensing; Deep learning; Pattern recognition (psychology); Geography; Land use; Engineering","score_opus":0.04207195488702933,"score_gpt":0.2535840156259814,"score_spread":0.21151206073895204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1990829950","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6480049,0.00045030063,0.34679592,0.00037947512,0.000064941094,0.00007187474,0.0009929925,0.0009709293,0.002268597],"genre_scores_gemma":[0.97089964,0.00010335013,0.027031882,0.00004411805,0.000017059807,0.000025926664,0.0009044101,0.000014349749,0.00095921126],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99982446,0.00003290643,0.000010160211,0.000051292987,0.000038427337,0.00004284406],"domain_scores_gemma":[0.9996234,0.00015394497,0.000057935966,0.000034638226,0.00010083842,0.000029224584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042739775,0.0007179162,0.00039067294,0.0011646565,0.00020461768,0.0006607736,0.00052611914,0.0004840608,0.00064953166],"category_scores_gemma":[0.0009247027,0.00023022141,0.00043772647,0.0007012309,0.0002487134,0.00086934585,0.0005129862,0.00059849623,0.00022418199],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003466732,0.0003263194,0.021763405,0.000069534144,0.00014342635,0.00014206598,0.000097694276,0.6615548,0.007848825,0.0013951358,0.0021012588,0.30421078],"study_design_scores_gemma":[0.0000025306242,0.000011668047,0.0013134751,0.000002709325,0.0000057480715,0.000005258805,0.000012329004,0.9974498,0.00074992405,0.00036828552,0.00007525907,0.0000029364603],"about_ca_topic_score_codex":0.009760003,"about_ca_topic_score_gemma":0.012815391,"teacher_disagreement_score":0.009760003,"about_ca_system_score_codex":0.0006361724,"about_ca_system_score_gemma":0.00032200702,"threshold_uncertainty_score":0.019406378},"labels":[],"label_agreement":null},{"id":"W1991780252","doi":"10.5623/cig2014-302","title":"Classification Of Submerged Aquatic Vegetation In Black River Using Hyperspectral Image Analysis","year":2014,"lang":"en","type":"article","venue":"GEOMATICA","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Hyperspectral imaging; Support vector machine; Environmental science; Remote sensing; Water quality; Vegetation (pathology); Aquatic plant; Surface water; Artificial neural network; Artificial intelligence; Macrophyte; Computer science; Geography; Ecology; Environmental engineering","score_opus":0.01742746959839895,"score_gpt":0.23903660931418844,"score_spread":0.2216091397157895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991780252","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98864996,0.000086452485,0.009862856,0.000031482883,0.000008037117,0.000010205237,0.00018440277,0.00009555848,0.0010710695],"genre_scores_gemma":[0.9904208,0.00009655253,0.007919134,0.000012882353,0.000008651624,0.000009023357,0.0003458698,0.000011198638,0.0011759938],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99994946,0.0000034930124,0.000002040147,0.000014425019,0.00001557567,0.0000149454],"domain_scores_gemma":[0.99994934,0.000008737158,0.000007906247,0.0000035200794,0.000019667006,0.000010823681],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008294292,0.0003023752,0.00019019848,0.0007640801,0.00026181713,0.00037027593,0.0001663792,0.00025006584,0.0004902691],"category_scores_gemma":[0.00007754424,0.00010328989,0.00022215885,0.00039191454,0.00015537151,0.00030698645,0.00014898459,0.00015639116,0.00014809624],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005487707,0.0003506143,0.15629329,0.00017607346,0.00009942375,0.00062801497,0.00047855297,0.01806098,0.5434388,0.0005781287,0.0017780552,0.27756923],"study_design_scores_gemma":[0.00002459372,0.000120423545,0.62722796,0.00002345047,0.00012080982,0.0002936024,0.0009973656,0.32277513,0.046203457,0.00048327865,0.001681706,0.0000481835],"about_ca_topic_score_codex":0.006456188,"about_ca_topic_score_gemma":0.011041236,"teacher_disagreement_score":0.006456188,"about_ca_system_score_codex":0.0001303924,"about_ca_system_score_gemma":0.0002156922,"threshold_uncertainty_score":0.012837231},"labels":[],"label_agreement":null},{"id":"W1992024126","doi":"10.1007/s10661-015-4489-3","title":"Land cover mapping based on random forest classification of multitemporal spectral and thermal images","year":2015,"lang":"en","type":"article","venue":"Environmental Monitoring and Assessment","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":120,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"U.S. Geological Survey","keywords":"Random forest; Land cover; Remote sensing; Thematic map; Environmental science; Change detection; Thematic Mapper; Contextual image classification; Land use; Spectral bands; Satellite imagery; Computer science; Geography; Cartography; Artificial intelligence; Image (mathematics)","score_opus":0.024336794575897627,"score_gpt":0.24695736959107223,"score_spread":0.2226205750151746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992024126","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61250514,0.00047021703,0.37697685,0.00012061589,0.00006382823,0.00021686587,0.0016402635,0.002228652,0.005777497],"genre_scores_gemma":[0.877038,0.00019442872,0.11915228,0.000024712426,0.000028195895,0.00006207853,0.0015579693,0.000073397314,0.0018688563],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99983776,0.000023652163,0.000008016864,0.00004306461,0.000051129373,0.00003633064],"domain_scores_gemma":[0.9998634,0.000024136421,0.000021159849,0.000017984918,0.000059803715,0.000013443078],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000273089,0.00043340586,0.00036452716,0.0022542472,0.00027275126,0.00044540392,0.0002979028,0.00023894667,0.0012198398],"category_scores_gemma":[0.0003398959,0.00016546018,0.00046248143,0.0009027605,0.00017318477,0.0005225447,0.00016511724,0.00016545845,0.0005110136],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006248527,0.00046252337,0.03337193,0.00020741059,0.00014403266,0.00025964802,0.00012502086,0.061547864,0.11918859,0.0015593865,0.0036396119,0.77886915],"study_design_scores_gemma":[0.0000420421,0.00011694331,0.0940975,0.000029043273,0.00015258031,0.00033381852,0.00012537789,0.8756981,0.02611683,0.0011700875,0.0020678823,0.0000497994],"about_ca_topic_score_codex":0.0071278843,"about_ca_topic_score_gemma":0.0099568395,"teacher_disagreement_score":0.0071278843,"about_ca_system_score_codex":0.00021520205,"about_ca_system_score_gemma":0.00038449198,"threshold_uncertainty_score":0.014172792},"labels":[],"label_agreement":null},{"id":"W1993770861","doi":"10.1117/12.849910","title":"Hybrid algorithm for hyperspectral target detection","year":2010,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Defence Research and Development Canada","funders":"","keywords":"Hyperspectral imaging; Computer science; Algorithm; Artificial intelligence","score_opus":0.008742852541246801,"score_gpt":0.21522903997161089,"score_spread":0.2064861874303641,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993770861","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011173346,0.00018402918,0.9870084,0.000036632424,0.000018992892,0.000025486026,0.0000166393,0.0005521131,0.0009844202],"genre_scores_gemma":[0.23051944,0.00021117463,0.76393396,0.000110834044,0.000029317898,0.00011966751,0.000113100075,0.000108634056,0.0048539145],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99935395,0.00012486907,0.000035596913,0.00013738325,0.00029961678,0.00004857672],"domain_scores_gemma":[0.99959725,0.00013104241,0.00005549807,0.00007048238,0.00013273348,0.000012972456],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067412143,0.00051251554,0.00045759283,0.0008682557,0.00025974377,0.0007870995,0.0011903545,0.0006048388,0.001597262],"category_scores_gemma":[0.0016002938,0.00026947862,0.00036328778,0.0006805855,0.00035038064,0.0010638833,0.00085724576,0.00049928296,0.0008552806],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034981457,0.000113306574,0.0015234705,0.000114580005,0.00014237304,0.000085035186,0.00010918379,0.1087424,0.0714661,0.024313053,0.0021802124,0.7908605],"study_design_scores_gemma":[0.000019177442,0.00007072316,0.0008381624,0.000008815504,0.000021619884,0.00022149064,0.000020802587,0.97085637,0.02048907,0.0035963706,0.003828267,0.00002919947],"about_ca_topic_score_codex":0.0014895996,"about_ca_topic_score_gemma":0.0025634384,"teacher_disagreement_score":0.001597262,"about_ca_system_score_codex":0.00045530917,"about_ca_system_score_gemma":0.0003788993,"threshold_uncertainty_score":0.0053433776},"labels":[],"label_agreement":null},{"id":"W1994033675","doi":"10.1117/1.3134137","title":"Segmentation of non-natural objects in landscape images using ridgelet transform","year":2009,"lang":"en","type":"article","venue":"Journal of Electronic Imaging","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Université de Montréal","keywords":"Artificial intelligence; Pattern recognition (psychology); Computer science; Linear discriminant analysis; Principal component analysis; Image segmentation; Segmentation; Computer vision; Classifier (UML); Kernel (algebra); Gabor transform; Feature extraction; Contextual image classification; Feature vector; Mathematics; Image (mathematics); Time–frequency analysis","score_opus":0.004385675403479626,"score_gpt":0.2377478117758263,"score_spread":0.23336213637234668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1994033675","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1895637,0.00031072495,0.8072428,0.000094479794,0.000034098364,0.00004429154,0.00014997975,0.0012094617,0.0013504243],"genre_scores_gemma":[0.47176355,0.00043475823,0.5253201,0.00004733228,0.00003577957,0.00003250771,0.00062593987,0.00015059407,0.0015894267],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99979585,0.00003699283,0.00001352297,0.000048608817,0.000072742165,0.000032394444],"domain_scores_gemma":[0.9996245,0.00016467868,0.00004841664,0.000057783345,0.00008424241,0.000020451413],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004404939,0.0003643887,0.00059138105,0.0014076025,0.00014103766,0.0006464216,0.00032675464,0.00051879406,0.00081908796],"category_scores_gemma":[0.0007253388,0.00025253586,0.0007041989,0.0008550489,0.0003339763,0.0008230528,0.0002372882,0.0003717152,0.0008156947],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038614776,0.00019200172,0.003957682,0.00018123917,0.00009575303,0.00031195793,0.0001697939,0.038932923,0.48299885,0.0018596648,0.0011210347,0.46979284],"study_design_scores_gemma":[0.000019374838,0.00016113187,0.018071277,0.000015064725,0.000056498673,0.0006361522,0.000089505505,0.82453525,0.15183459,0.002095857,0.0024523002,0.00003303528],"about_ca_topic_score_codex":0.000582267,"about_ca_topic_score_gemma":0.0009804836,"teacher_disagreement_score":0.0014076025,"about_ca_system_score_codex":0.00021057764,"about_ca_system_score_gemma":0.0002443474,"threshold_uncertainty_score":0.0027401447},"labels":[],"label_agreement":null},{"id":"W1994983012","doi":"10.1109/igarss.2014.6947603","title":"URC: Unsupervised regional clustering of remote sensing imagery","year":2014,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Conditional random field; CRFS; Cluster analysis; Computer science; Artificial intelligence; Pixel; Pattern recognition (psychology); Segmentation; Satellite imagery; Image segmentation; Inference; Satellite; Synthetic aperture radar; Remote sensing; Geography","score_opus":0.021742430490081583,"score_gpt":0.22092538664275288,"score_spread":0.1991829561526713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1994983012","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047412375,0.00017688533,0.98687196,0.0000815959,0.000035127843,0.00017002072,0.00096019765,0.005718015,0.0012448588],"genre_scores_gemma":[0.097839564,0.00017425272,0.8904426,0.00016590912,0.00007814826,0.00039118537,0.005651585,0.0017296306,0.0035270907],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99851936,0.0003427982,0.00006695052,0.0005545374,0.00037205996,0.00014437581],"domain_scores_gemma":[0.9980895,0.0005469561,0.00020984281,0.0005878523,0.00050341844,0.00006240418],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017480563,0.001040267,0.0014177064,0.0032249663,0.0009718497,0.001105513,0.0027743632,0.0012485356,0.0042912997],"category_scores_gemma":[0.0043322793,0.0007844196,0.0018720609,0.0029747172,0.0009171054,0.0012925694,0.001390546,0.0013520721,0.003441314],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027036743,0.00014984171,0.0020790878,0.00035167782,0.00023033273,0.0002240576,0.00030439257,0.51135635,0.012542468,0.021092704,0.035434987,0.41596365],"study_design_scores_gemma":[0.000013659056,0.000022082211,0.0010368613,0.000019066634,0.000017647651,0.000077057804,0.000033066033,0.9797677,0.0038181432,0.0090184575,0.0061467024,0.000029647523],"about_ca_topic_score_codex":0.021194523,"about_ca_topic_score_gemma":0.029471558,"teacher_disagreement_score":0.021194523,"about_ca_system_score_codex":0.0015210783,"about_ca_system_score_gemma":0.0020736607,"threshold_uncertainty_score":0.04214233},"labels":[],"label_agreement":null},{"id":"W1996828724","doi":"10.1016/j.rse.2012.09.022","title":"Landcover classification of the Lower Nhecolândia subregion of the Brazilian Pantanal Wetlands using ALOS/PALSAR, RADARSAT-2 and ENVISAT/ASAR imagery","year":2012,"lang":"en","type":"article","venue":"Remote Sensing of Environment","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":106,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Wetland; Habitat; Vegetation (pathology); Environmental science; Geography; Grassland; Biodiversity; Physical geography; Remote sensing; Ecology; Hydrology (agriculture); Geology","score_opus":0.018722230997571213,"score_gpt":0.2107248522293865,"score_spread":0.19200262123181527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996828724","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9961511,0.0001103879,0.00020202273,0.00005031386,0.000001941944,0.000011946032,0.00078306685,0.00002158671,0.002667692],"genre_scores_gemma":[0.99855155,0.00005747973,0.00032317045,0.000005867776,9.123842e-7,0.000005668303,0.00059308263,0.000003178108,0.00045916674],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9998996,0.000013636871,0.000009860591,0.000022300006,0.00002235017,0.00003212708],"domain_scores_gemma":[0.99982613,0.000026108944,0.000049794664,0.000018761035,0.00005868286,0.000020507632],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011762082,0.00014027933,0.00013074037,0.0016225892,0.00022716874,0.00042964707,0.00013257653,0.00011339764,0.0011783049],"category_scores_gemma":[0.00047523621,0.00008392302,0.00014585632,0.0014668215,0.00020711664,0.00017812314,0.00027993566,0.00006994683,0.0001895187],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013150054,0.00004459818,0.9265403,0.00009626264,0.000043486776,0.00023450489,0.0014582056,0.0008940228,0.012872045,0.00052494626,0.00074049976,0.05641966],"study_design_scores_gemma":[0.0000021124085,0.000007206302,0.9970553,0.000009361068,0.0000124328035,0.000053339,0.00046597302,0.0008431761,0.00021630581,0.000028330858,0.0013040351,0.000002530767],"about_ca_topic_score_codex":0.18457456,"about_ca_topic_score_gemma":0.37902573,"teacher_disagreement_score":0.18457456,"about_ca_system_score_codex":0.0006193007,"about_ca_system_score_gemma":0.0004429492,"threshold_uncertainty_score":0.3670004},"labels":[],"label_agreement":null},{"id":"W1997830184","doi":"10.1016/j.patrec.2009.07.005","title":"Color image segmentation using an enhanced Gradient Network Method","year":2009,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Segmentation; Artificial intelligence; Image segmentation; Scale-space segmentation; Computer science; Computer vision; Segmentation-based object categorization; Ground truth; Region growing; Pattern recognition (psychology); Bipartite graph; Cut; Matching (statistics); Graph; Mathematics","score_opus":0.03577567186239731,"score_gpt":0.28344382990786,"score_spread":0.2476681580454627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997830184","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01577973,0.00012063075,0.9821223,0.00006447151,0.000033198645,0.00004768029,0.000037140177,0.00056161056,0.0012332589],"genre_scores_gemma":[0.16841677,0.00025345833,0.8263474,0.000068495225,0.00005861943,0.00009375321,0.00017025835,0.00019244543,0.004398815],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99973387,0.00004665841,0.000013235146,0.00007573292,0.00010169114,0.0000288314],"domain_scores_gemma":[0.9997625,0.000060080973,0.00002206549,0.000031923435,0.00010728277,0.000016175401],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004700119,0.00068085926,0.0007543169,0.001469811,0.00036886963,0.0008520948,0.0007731981,0.00075262156,0.0022743237],"category_scores_gemma":[0.00053926214,0.00044786284,0.0005853187,0.0008817154,0.00040497363,0.0011579472,0.00053592224,0.00054007646,0.0006917366],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004837632,0.00022128341,0.0012302906,0.0001842991,0.00012794316,0.00013445166,0.00010489287,0.10527784,0.18153632,0.007933001,0.002605945,0.7001601],"study_design_scores_gemma":[0.00001613703,0.000046348516,0.0010841434,0.0000070781475,0.000039862585,0.00010548024,0.000009915053,0.9690053,0.026642097,0.0012592798,0.001763817,0.000020570718],"about_ca_topic_score_codex":0.0035234303,"about_ca_topic_score_gemma":0.004822414,"teacher_disagreement_score":0.0035234303,"about_ca_system_score_codex":0.00045062945,"about_ca_system_score_gemma":0.0005570074,"threshold_uncertainty_score":0.0076084137},"labels":[],"label_agreement":null},{"id":"W1999583826","doi":"10.1109/isspa.2012.6310623","title":"Object- versus pixel-based building detection for disaster response","year":2012,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Pixel; Computer science; Object (grammar); Disaster response; Object detection; Field (mathematics); Artificial intelligence; Computer vision; Emergency management; Data mining; Pattern recognition (psychology); Mathematics","score_opus":0.03111455700406378,"score_gpt":0.27000780767595217,"score_spread":0.23889325067188838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999583826","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26896125,0.0023166947,0.7163627,0.00046988472,0.00032805523,0.00013205549,0.0001771848,0.0024323019,0.00881994],"genre_scores_gemma":[0.6502489,0.00058105466,0.3465234,0.00012910643,0.00011311138,0.00004646006,0.00019616907,0.00011769847,0.00204411],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99945396,0.00016871824,0.000017736127,0.00008086108,0.0002235241,0.00005523373],"domain_scores_gemma":[0.99958175,0.0001589904,0.000031691245,0.000061023642,0.00013548529,0.00003109266],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009131234,0.00039908467,0.0005602762,0.0016501734,0.00025810607,0.00077351613,0.0004947343,0.0009136217,0.0018578051],"category_scores_gemma":[0.0013077516,0.00019585295,0.00033992037,0.00082641,0.00038521382,0.00086703495,0.00044026706,0.0002748891,0.0007162265],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009800062,0.0003574406,0.01236761,0.00026155327,0.00018162954,0.0001411565,0.00012638666,0.037460756,0.12757051,0.005363376,0.002850836,0.81233877],"study_design_scores_gemma":[0.00007175412,0.00059722696,0.030318229,0.000043270444,0.00019683733,0.0005796034,0.00020208793,0.88293946,0.06953294,0.005461963,0.009979998,0.00007657791],"about_ca_topic_score_codex":0.0009169827,"about_ca_topic_score_gemma":0.0015537603,"teacher_disagreement_score":0.0018578051,"about_ca_system_score_codex":0.00025815333,"about_ca_system_score_gemma":0.0002247491,"threshold_uncertainty_score":0.006215036},"labels":[],"label_agreement":null},{"id":"W2001004170","doi":"10.1179/136821909x12581187860130","title":"Texture analysis of IKONOS satellite imagery for urban land use and land cover classification","year":2010,"lang":"en","type":"article","venue":"The Imaging Science Journal","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Land cover; Remote sensing; Pattern recognition (psychology); Artificial intelligence; Satellite imagery; Computer science; Texture (cosmology); Satellite; Image resolution; Homogeneity (statistics); Land use; Computer vision; Geography; Image (mathematics)","score_opus":0.018058364000386753,"score_gpt":0.25622022152624024,"score_spread":0.2381618575258535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001004170","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78779596,0.00073461566,0.19774485,0.00035945213,0.0000860785,0.00021178955,0.0043942365,0.0012100174,0.007462906],"genre_scores_gemma":[0.9079266,0.0002897335,0.087335214,0.000034895755,0.000029300496,0.00008235838,0.0029100801,0.00005169973,0.0013401926],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996704,0.00006640644,0.000017450502,0.000039188737,0.0001741975,0.00003243795],"domain_scores_gemma":[0.99954045,0.00012873823,0.00006138083,0.000056107532,0.00017877677,0.00003465693],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043390915,0.00037562026,0.00035279142,0.00219957,0.00021893546,0.0005352989,0.00021486808,0.0001980378,0.0013520605],"category_scores_gemma":[0.001482371,0.000100734454,0.00045708974,0.001588672,0.00018014734,0.0003888862,0.0002242658,0.00023288147,0.00059941877],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009576444,0.0004264112,0.06968663,0.0004737816,0.00022498894,0.00023579157,0.00019497723,0.031933144,0.16373897,0.0013574302,0.0059551564,0.7248151],"study_design_scores_gemma":[0.0000878864,0.00044598273,0.302859,0.00005577584,0.00021740956,0.0005772177,0.000648971,0.626645,0.058345538,0.0020544447,0.007982526,0.00008028336],"about_ca_topic_score_codex":0.004932431,"about_ca_topic_score_gemma":0.009112965,"teacher_disagreement_score":0.004932431,"about_ca_system_score_codex":0.00033809562,"about_ca_system_score_gemma":0.00031923677,"threshold_uncertainty_score":0.009807467},"labels":[],"label_agreement":null},{"id":"W2001096515","doi":"10.1137/130940670","title":"Semidefinite Programming Based Preconditioning for More Robust Near-Separable Nonnegative Matrix Factorization","year":2015,"lang":"en","type":"article","venue":"SIAM Journal on Optimization","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Non-negative matrix factorization; Separable space; Hyperspectral imaging; Mathematics; Semidefinite programming; Matrix (chemical analysis); Matrix decomposition; Algorithm; Factorization; Mathematical optimization; Artificial intelligence; Computer science; Eigenvalues and eigenvectors","score_opus":0.04063804245902447,"score_gpt":0.27524008602790423,"score_spread":0.23460204356887976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001096515","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043023992,0.000042664225,0.99445575,0.00008841312,0.00002402157,0.000016440981,0.000025739795,0.00013610626,0.00090859423],"genre_scores_gemma":[0.16633847,0.00022232455,0.83026105,0.0002305205,0.00010606911,0.00018556914,0.00029504314,0.00023516711,0.0021258176],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992792,0.0003090034,0.000035621317,0.00012576103,0.00020024643,0.00005022793],"domain_scores_gemma":[0.9985246,0.00083236047,0.00014225254,0.00021836645,0.00021239578,0.0000700465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013797166,0.0012579178,0.0010027441,0.0003828021,0.00034987577,0.00072925375,0.0006092521,0.00082411536,0.0037254551],"category_scores_gemma":[0.00415092,0.00036317523,0.00067645084,0.00062623597,0.0011393158,0.0013025965,0.0012453538,0.0022195862,0.0008454907],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015922562,0.00016057151,0.0003373144,0.00031569065,0.000058056616,0.0002244572,0.00017420731,0.76109475,0.037167888,0.091987,0.0066154944,0.10170532],"study_design_scores_gemma":[0.0000109895545,0.000029091927,0.000036343696,0.0000058305163,0.0000023039731,0.000023508974,0.000009116893,0.98503506,0.0021378717,0.011781142,0.0009232325,0.0000054620846],"about_ca_topic_score_codex":0.0010419461,"about_ca_topic_score_gemma":0.0017784084,"teacher_disagreement_score":0.0037254551,"about_ca_system_score_codex":0.0003421127,"about_ca_system_score_gemma":0.0009869062,"threshold_uncertainty_score":0.012462914},"labels":[],"label_agreement":null},{"id":"W2003131921","doi":"10.1007/s12517-013-1141-9","title":"SVM-based hyperspectral image classification using intrinsic dimension","year":2013,"lang":"en","type":"article","venue":"Arabian Journal of Geosciences","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Hyperspectral imaging; Support vector machine; Pattern recognition (psychology); Dimensionality reduction; Computer science; Artificial intelligence; Curse of dimensionality; Classifier (UML); Dimension (graph theory); Feature extraction; Feature vector; Margin (machine learning); Intrinsic dimension; Data mining; Machine learning; Mathematics","score_opus":0.02550684330267868,"score_gpt":0.24261530136471932,"score_spread":0.21710845806204063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2003131921","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14275086,0.0007657465,0.8507246,0.00024188725,0.00017447775,0.00005854392,0.00032035733,0.0016673374,0.0032961953],"genre_scores_gemma":[0.8285532,0.00033775362,0.16605237,0.00008840423,0.00011400788,0.00008185456,0.0011421863,0.00006600316,0.0035643068],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996049,0.000093028495,0.000034435092,0.00007952674,0.00014585443,0.000042278643],"domain_scores_gemma":[0.99941564,0.00018569943,0.00004792253,0.00006669146,0.0002588267,0.000025301613],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006006414,0.00044324808,0.0006722058,0.00058297056,0.0002820701,0.0007185343,0.00051380636,0.0004210385,0.0015135255],"category_scores_gemma":[0.0012424896,0.00014844163,0.0005882117,0.00059277745,0.00020585916,0.00079403317,0.0005590794,0.0006879882,0.00073451444],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045941846,0.0002856566,0.0037097186,0.00017326196,0.00013959521,0.000046696015,0.00007661831,0.06832584,0.043515846,0.0034124574,0.0058719395,0.87398297],"study_design_scores_gemma":[0.0000076311,0.000037405127,0.0014679525,0.0000074134414,0.000019539435,0.000032617583,0.000015745993,0.99192566,0.0049973247,0.0008046402,0.00067648053,0.0000075848548],"about_ca_topic_score_codex":0.0012434609,"about_ca_topic_score_gemma":0.0011168997,"teacher_disagreement_score":0.0015135255,"about_ca_system_score_codex":0.00024198585,"about_ca_system_score_gemma":0.000433195,"threshold_uncertainty_score":0.005063176},"labels":[],"label_agreement":null},{"id":"W2003335539","doi":"10.1016/j.patrec.2008.05.003","title":"A combined Markovian and Dirichlet sub-mixture modeling for evidence assignment: Application to image fusion","year":2008,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bishop's University","funders":"","keywords":"Hierarchical Dirichlet process; Context (archaeology); Computer science; Mixture model; Artificial intelligence; Pattern recognition (psychology); Noise (video); Latent Dirichlet allocation; Algorithm; Dirichlet distribution; Mathematics; Image (mathematics); Topic model","score_opus":0.031499239321772364,"score_gpt":0.2322209857675299,"score_spread":0.20072174644575752,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2003335539","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020088246,0.00017933894,0.9973239,0.000102068145,0.000024404273,0.000025569605,0.00003527273,0.00015765533,0.00014294942],"genre_scores_gemma":[0.15740465,0.0007327452,0.8374055,0.00031918325,0.00028273885,0.00040411524,0.0005355664,0.00024100684,0.002674564],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995423,0.002118153,0.00038807484,0.0007773775,0.0010346905,0.00025869388],"domain_scores_gemma":[0.98657817,0.010091513,0.00044644153,0.0009548891,0.0015777766,0.0003512886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011210212,0.0013822379,0.0038024257,0.003104358,0.0017548633,0.0031904243,0.0051395916,0.0036065695,0.0029079474],"category_scores_gemma":[0.026209308,0.0020256457,0.0040504024,0.0033675425,0.0020457134,0.005316165,0.0051954743,0.0041426206,0.0014034222],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009279122,0.00031264828,0.00149827,0.00037200737,0.00064263074,0.00015819453,0.0004500504,0.49951798,0.0054773455,0.06217707,0.0033139554,0.4251519],"study_design_scores_gemma":[0.00001853474,0.000022079274,0.00011108283,0.00001284006,0.000045138557,0.000032079475,0.000009885448,0.9804842,0.00076331774,0.018107727,0.00036711022,0.000026035748],"about_ca_topic_score_codex":0.00822187,"about_ca_topic_score_gemma":0.010607908,"teacher_disagreement_score":0.011210212,"about_ca_system_score_codex":0.0016021789,"about_ca_system_score_gemma":0.002856981,"threshold_uncertainty_score":0.059286},"labels":[],"label_agreement":null},{"id":"W2005119484","doi":"10.3390/rs6076500","title":"Moving Vehicle Information Extraction from Single-Pass WorldView-2 Imagery Based on ERGAS-SNS Analysis","year":2014,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"National Science Fund for Distinguished Young Scholars; National Natural Science Foundation of China","keywords":"Computer science; Multispectral image; Panchromatic film; Computer vision; Artificial intelligence; Displacement (psychology); Correctness; Focus (optics); Remote sensing; Process (computing); Geography; Optics","score_opus":0.01110141182137648,"score_gpt":0.21357888061631777,"score_spread":0.2024774687949413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005119484","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3114588,0.00044131902,0.68069375,0.000095480806,0.000066887944,0.0001283458,0.00073410873,0.0017254706,0.004655853],"genre_scores_gemma":[0.62021446,0.00053195475,0.3730022,0.000039801063,0.000035062534,0.00008229703,0.00193118,0.00011638849,0.0040466106],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9998356,0.000012800919,0.000010531336,0.000043900953,0.00007133552,0.000025794232],"domain_scores_gemma":[0.9998696,0.000012519847,0.000017873732,0.000014932838,0.0000777876,0.000007226291],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022577385,0.00065170566,0.00039580662,0.0025626668,0.00019072494,0.00044822053,0.0003959702,0.00032131246,0.0009148281],"category_scores_gemma":[0.0003117025,0.00019890851,0.00060611265,0.0010652631,0.00019454249,0.0007356346,0.00032027994,0.00022576457,0.0007263429],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025988906,0.00013644101,0.012228604,0.0003189701,0.00013007838,0.00030000982,0.00017796077,0.028711902,0.28083813,0.0018663625,0.0019850489,0.6730466],"study_design_scores_gemma":[0.00002547636,0.00014207825,0.06991286,0.000041241314,0.00018452428,0.00062004995,0.0003850712,0.68466026,0.23393904,0.0019827061,0.008012428,0.000094353876],"about_ca_topic_score_codex":0.002287638,"about_ca_topic_score_gemma":0.004359111,"teacher_disagreement_score":0.0025626668,"about_ca_system_score_codex":0.00020212193,"about_ca_system_score_gemma":0.0003250526,"threshold_uncertainty_score":0.0045486093},"labels":[],"label_agreement":null},{"id":"W2005916864","doi":"10.1109/igarss.2013.6723487","title":"Transformation-invariant image descriptors for change monitoring based on multi-modality imagery","year":2013,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec en Outaouais","funders":"","keywords":"Artificial intelligence; Pattern recognition (psychology); Computer vision; Feature extraction; Salient; Computer science; Robustness (evolution); Pixel; Image segmentation; Invariant (physics); Mathematics; Segmentation","score_opus":0.06501317476525674,"score_gpt":0.2675924869789163,"score_spread":0.20257931221365955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005916864","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024809487,0.000273174,0.97346467,0.00006235879,0.000032149426,0.00007001365,0.00010737008,0.0004860379,0.00069479167],"genre_scores_gemma":[0.35979098,0.00042813364,0.63796574,0.000060786693,0.00007413274,0.00010992886,0.00045208153,0.00012267778,0.0009955895],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996469,0.000042918397,0.00002065037,0.00008554052,0.00016768975,0.000036352365],"domain_scores_gemma":[0.9996081,0.000089590096,0.00007244378,0.000087401306,0.00011666311,0.000025786496],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042070274,0.00037441085,0.00067852344,0.0023882815,0.00021194133,0.0006168481,0.00072461856,0.0004240927,0.0013380444],"category_scores_gemma":[0.0013337701,0.0001841568,0.00068941346,0.002066526,0.00039988843,0.0013187458,0.0005487352,0.00046945977,0.00051359605],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020896294,0.00012334235,0.0017782416,0.00026370387,0.00008075948,0.00018462454,0.00013326292,0.015935991,0.19191688,0.005288361,0.0019275903,0.7821583],"study_design_scores_gemma":[0.000040201034,0.000330243,0.017066825,0.00002780722,0.0001375941,0.0011062975,0.00021704512,0.8366592,0.12561472,0.009451188,0.009257307,0.00009147615],"about_ca_topic_score_codex":0.0008986305,"about_ca_topic_score_gemma":0.0011861416,"teacher_disagreement_score":0.0023882815,"about_ca_system_score_codex":0.0003309377,"about_ca_system_score_gemma":0.00035232573,"threshold_uncertainty_score":0.0044761896},"labels":[],"label_agreement":null},{"id":"W2009963903","doi":"10.1109/igarss.2008.4778987","title":"Vegetation Species Identification Using Hyperspectral Imagery","year":2008,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Defence Research and Development Canada; York University","funders":"Natural Sciences and Engineering Research Council of Canada; University of Alberta","keywords":"Hyperspectral imaging; Remote sensing; Euclidean distance; Entropy (arrow of time); Vegetation (pathology); Similarity measure; Computer science; Metric (unit); Artificial intelligence; Full spectral imaging; Vegetation classification; Pattern recognition (psychology); Geography; Engineering; Physics","score_opus":0.043795590505419785,"score_gpt":0.23317524973401543,"score_spread":0.18937965922859565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009963903","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7403227,0.0003796049,0.2561092,0.000065003595,0.00003373339,0.000050160423,0.00014519383,0.0003953087,0.0024991857],"genre_scores_gemma":[0.8924464,0.00013597698,0.10663112,0.000022117965,0.0000132965915,0.000018014252,0.00024485314,0.00001497056,0.00047317453],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995894,0.00010822927,0.000028700448,0.00006539905,0.00018561202,0.000022681805],"domain_scores_gemma":[0.9992618,0.0003530787,0.00011553109,0.000056283403,0.00017450115,0.00003881631],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095965323,0.00033260076,0.00036077193,0.00218944,0.00025022993,0.00045965367,0.00025087732,0.00036991356,0.0004984171],"category_scores_gemma":[0.0022959711,0.000108653774,0.00022086775,0.0007422086,0.00028682538,0.0013407883,0.0004175631,0.00018715639,0.000229702],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041982534,0.00029916418,0.051377032,0.0002719436,0.00013094467,0.00024241894,0.0002851513,0.035076894,0.37329063,0.003235446,0.0008236064,0.5345469],"study_design_scores_gemma":[0.000017700424,0.00051401637,0.09793432,0.00003125021,0.0000641157,0.0010739362,0.0004884387,0.67806226,0.21479304,0.005040694,0.0018855106,0.00009469697],"about_ca_topic_score_codex":0.00042053653,"about_ca_topic_score_gemma":0.00074922154,"teacher_disagreement_score":0.00218944,"about_ca_system_score_codex":0.00015853778,"about_ca_system_score_gemma":0.00012710216,"threshold_uncertainty_score":0.0050751567},"labels":[],"label_agreement":null},{"id":"W2010841346","doi":"10.1007/s00267-007-9031-0","title":"Object-Based Classification as an Alternative Approach to the Traditional Pixel-Based Classification to Identify Potential Habitat of the Grasshopper Sparrow","year":2007,"lang":"en","type":"article","venue":"Environmental Management","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":49,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada","funders":"","keywords":"Habitat; Segmentation; Pixel; Sparrow; Computer science; Artificial intelligence; Land cover; Object (grammar); Remote sensing; Ecology; Cartography; Pattern recognition (psychology); Geography; Land use; Biology","score_opus":0.02815977623308425,"score_gpt":0.24294249755158812,"score_spread":0.21478272131850387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2010841346","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20132928,0.00046877807,0.78791976,0.00023804164,0.0001845032,0.00017558418,0.0005275137,0.0015290711,0.0076274993],"genre_scores_gemma":[0.505296,0.00023071129,0.489775,0.00012750668,0.00008526515,0.00012040654,0.0005909488,0.00008953087,0.0036846066],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998041,0.000043685195,0.000013303527,0.00003890388,0.00007547254,0.000024554345],"domain_scores_gemma":[0.9996371,0.00010745813,0.000033513643,0.000048779642,0.00015284754,0.00002019583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061455806,0.00036344296,0.00045185993,0.0019452336,0.00030590108,0.0007680075,0.00045511738,0.00043028488,0.0018735327],"category_scores_gemma":[0.00061881926,0.00013545774,0.00043503984,0.0014992229,0.00023865522,0.00063621457,0.00030499892,0.00028062778,0.00057712663],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029217612,0.00036290183,0.021210331,0.0001332156,0.00021028849,0.00013199108,0.00018477983,0.021212116,0.074721836,0.004656786,0.0025665178,0.87431705],"study_design_scores_gemma":[0.000060178772,0.00029222685,0.05185606,0.00004096958,0.00026836147,0.00049838907,0.00025521367,0.9075606,0.02552923,0.005479654,0.008087517,0.000071631985],"about_ca_topic_score_codex":0.004748027,"about_ca_topic_score_gemma":0.006896856,"teacher_disagreement_score":0.004748027,"about_ca_system_score_codex":0.00022881124,"about_ca_system_score_gemma":0.0003507707,"threshold_uncertainty_score":0.00944078},"labels":[],"label_agreement":null},{"id":"W2011661018","doi":"10.1590/1809-4392201401439","title":"Land cover classification of Lago Grande de Curuai floodplain (Amazon, Brazil) using multi-sensor and image fusion techniques","year":2015,"lang":"en","type":"article","venue":"Acta Amazonica","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Space Agency; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Land cover; Remote sensing; Amazon rainforest; Cohen's kappa; Contextual image classification; Computer science; Sensor fusion; Image fusion; Artificial intelligence; Land use; Pattern recognition (psychology); Image (mathematics); Geography; Machine learning","score_opus":0.038371822456754606,"score_gpt":0.2905017488343343,"score_spread":0.2521299263775797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011661018","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9931009,0.00029657446,0.004195984,0.00008207122,0.0000055152823,0.000032019867,0.0003445745,0.000072875184,0.0018694215],"genre_scores_gemma":[0.9950481,0.00008948298,0.0043297564,0.00000817608,0.0000020444509,0.000011737702,0.0002492589,0.000005791299,0.0002555732],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9998388,0.000029790555,0.000011866625,0.000042427582,0.00005204834,0.000024945932],"domain_scores_gemma":[0.9997888,0.000056032804,0.000051590214,0.000018997085,0.00007121589,0.0000132261575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030794766,0.000277658,0.00019546249,0.0011474064,0.00021300612,0.00042042913,0.00019361095,0.00018829443,0.00029305305],"category_scores_gemma":[0.00064692734,0.00012358958,0.0002336675,0.00092254364,0.00021470814,0.00031487385,0.0002456876,0.00012132246,0.0001043631],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025461704,0.00015357677,0.6101114,0.00032201956,0.00013116752,0.00082950405,0.001696619,0.01110965,0.13367721,0.0011013715,0.00088300835,0.23972987],"study_design_scores_gemma":[0.000015471735,0.00007351393,0.93349063,0.00003534733,0.0000693522,0.00029068175,0.0012775442,0.05413861,0.007942231,0.00030107013,0.0023393168,0.00002628239],"about_ca_topic_score_codex":0.088166215,"about_ca_topic_score_gemma":0.17437391,"teacher_disagreement_score":0.088166215,"about_ca_system_score_codex":0.00057787774,"about_ca_system_score_gemma":0.00045486473,"threshold_uncertainty_score":0.17530602},"labels":[],"label_agreement":null},{"id":"W2015582040","doi":"10.1007/s12145-014-0200-4","title":"Developing an algorithm for local anomaly detection based on spectral space window in hyperspectral image","year":2015,"lang":"en","type":"article","venue":"Earth Science Informatics","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Hyperspectral imaging; Anomaly detection; Anomaly (physics); Spectral space; Computer science; Algorithm; Sliding window protocol; Manifold (fluid mechanics); Pattern recognition (psychology); Nonlinear system; Nonlinear dimensionality reduction; Artificial intelligence; Mathematics; Window (computing); Dimensionality reduction","score_opus":0.025806205436570744,"score_gpt":0.2559727172730781,"score_spread":0.23016651183650733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015582040","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007657404,0.00007434419,0.99119896,0.000029005138,0.000029349027,0.00003598498,0.000025360641,0.00071334536,0.00023622594],"genre_scores_gemma":[0.060878925,0.00014203328,0.9368912,0.000035305955,0.0000379237,0.000093393646,0.00026114428,0.000089235735,0.0015708695],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99960965,0.000030798932,0.00003080516,0.00013870065,0.00015374755,0.00003631792],"domain_scores_gemma":[0.9995784,0.00007932277,0.00004124613,0.000050479557,0.00022704032,0.00002350896],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047466147,0.00063752016,0.00073259685,0.0011388492,0.0005180543,0.0009276921,0.0011990932,0.00066737965,0.0015792729],"category_scores_gemma":[0.0010409193,0.00033986507,0.0006804305,0.0011935096,0.0003147286,0.001258423,0.00076318503,0.0008735733,0.0009682937],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011141344,0.00012060482,0.0022314352,0.00010950156,0.0000723884,0.00008916297,0.00008698669,0.029444505,0.100851886,0.0058236015,0.0030366755,0.8580218],"study_design_scores_gemma":[0.000016547383,0.000056368535,0.0016472077,0.000008432174,0.000032796957,0.0001975103,0.000040094634,0.9474806,0.04415595,0.0030027835,0.0033390997,0.000022657789],"about_ca_topic_score_codex":0.0034582352,"about_ca_topic_score_gemma":0.0033398166,"teacher_disagreement_score":0.0034582352,"about_ca_system_score_codex":0.000328977,"about_ca_system_score_gemma":0.0010577147,"threshold_uncertainty_score":0.0068762302},"labels":[],"label_agreement":null},{"id":"W2015830159","doi":"10.1111/1467-9671.00080","title":"Integration of Remote Sensing and GIS to Detect Pockets of Urban Poverty: The Case of Rosario, Argentina","year":2001,"lang":"en","type":"article","venue":"Transactions in GIS","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Waterloo","funders":"Universidad Nacional de Rosario","keywords":"Remote sensing; Geography; Land cover; Multispectral image; Satellite imagery; Urban planning; Poverty; Cartography; Computer science; Land use; Engineering; Civil engineering","score_opus":0.020026215528847334,"score_gpt":0.24631245472035512,"score_spread":0.22628623919150778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015830159","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9807704,0.0007180982,0.0014954569,0.0007636371,0.000009579258,0.00009084371,0.0002974929,0.000030569026,0.0158239],"genre_scores_gemma":[0.9946396,0.0005088754,0.0023523138,0.000030715117,0.0000069502835,0.000029312789,0.00024887704,0.0000102639415,0.0021730557],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99939966,0.0002754708,0.000024560897,0.000057875623,0.00012267726,0.00011977854],"domain_scores_gemma":[0.9994874,0.00017208529,0.000089542795,0.00005103664,0.00014727983,0.000052555526],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006509446,0.00034178412,0.00024814444,0.00087998394,0.0006349894,0.0008891039,0.0004451662,0.0003293671,0.0013278319],"category_scores_gemma":[0.002339194,0.00022944128,0.00026751394,0.0013929867,0.00042144975,0.0005639064,0.00052172755,0.00037118865,0.00013984634],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008034227,0.00080634456,0.794049,0.00037133382,0.00022461185,0.012945888,0.0051642726,0.029574534,0.0048579457,0.013522293,0.0057734414,0.13190684],"study_design_scores_gemma":[0.00010701044,0.00020784636,0.87560064,0.0001305537,0.00014159069,0.0019595115,0.010035224,0.09185857,0.001660621,0.002011735,0.0162354,0.000051172585],"about_ca_topic_score_codex":0.31628272,"about_ca_topic_score_gemma":0.3864496,"teacher_disagreement_score":0.31628272,"about_ca_system_score_codex":0.00232525,"about_ca_system_score_gemma":0.000772663,"threshold_uncertainty_score":0.6288835},"labels":[],"label_agreement":null},{"id":"W2016115888","doi":"10.1117/12.974605","title":"LWIR hyperspectral imaging application and detection of chemical precursors","year":2012,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Defence Research and Development Canada","funders":"Defence Research and Development Canada","keywords":"Hyperspectral imaging; Context (archaeology); Remote sensing; Identification (biology); Interferometry; Computer science; Environmental science; Geology; Optics; Physics","score_opus":0.007992037499613443,"score_gpt":0.21192756409873334,"score_spread":0.2039355265991199,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016115888","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7708196,0.0024626465,0.19469772,0.00052842364,0.0001223113,0.000246468,0.00064408896,0.0014025621,0.029076096],"genre_scores_gemma":[0.8131669,0.001967283,0.1738081,0.0002934762,0.00005365219,0.00012591126,0.00051465625,0.00009418265,0.009975896],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996495,0.000039726157,0.000008682821,0.00007461317,0.00019876078,0.000028629509],"domain_scores_gemma":[0.99979645,0.000043937092,0.000037973976,0.000024741548,0.00008066331,0.000016165035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039833706,0.00049505534,0.00025937552,0.00060382276,0.00024287737,0.00046062085,0.0004270878,0.0006347601,0.0015300697],"category_scores_gemma":[0.00037486083,0.00017893223,0.00026498185,0.00048883306,0.00034282543,0.00058958516,0.00047522876,0.00053071993,0.00050685863],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005947964,0.000049347516,0.00092787854,0.000082751794,0.000005266873,0.00006651526,0.000045921293,0.00096766633,0.973347,0.00039731205,0.0002942425,0.023756675],"study_design_scores_gemma":[0.0000060156804,0.00025650655,0.0049543544,0.000011400013,0.000011322425,0.0003305567,0.00006371608,0.01451029,0.9750481,0.0002126506,0.004577609,0.00001748068],"about_ca_topic_score_codex":0.0009786111,"about_ca_topic_score_gemma":0.0019462327,"teacher_disagreement_score":0.0015300697,"about_ca_system_score_codex":0.00034421435,"about_ca_system_score_gemma":0.0002738783,"threshold_uncertainty_score":0.0051186085},"labels":[],"label_agreement":null},{"id":"W2016747440","doi":"10.1117/12.766621","title":"Image analysis of hyperspectral and multispectral data using projection pursuit","year":2007,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Hyperspectral imaging; Multispectral image; Computer science; Anomaly detection; Artificial intelligence; Projection (relational algebra); Pattern recognition (psychology); Projection pursuit; Data set; Dimensionality reduction; Detector; Feature extraction; Computer vision; Outlier; Algorithm","score_opus":0.025174250575443105,"score_gpt":0.2661026257735788,"score_spread":0.2409283751981357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016747440","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020495431,0.00014054835,0.9778668,0.000090408816,0.000016657494,0.000037662743,0.00006298835,0.00039686455,0.00089261454],"genre_scores_gemma":[0.16610652,0.00044764526,0.8310519,0.00005800105,0.00003655653,0.0001284224,0.00038665134,0.00007816596,0.0017061273],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995546,0.0000797384,0.000024019844,0.00009741284,0.00021027033,0.000033840988],"domain_scores_gemma":[0.9996412,0.00013566596,0.000068143265,0.000046808014,0.000086707216,0.00002141981],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060730794,0.00071773864,0.0006475701,0.0010225533,0.00028862982,0.00076540204,0.00050384103,0.00048005622,0.0009253532],"category_scores_gemma":[0.0010843704,0.0002694224,0.00094245165,0.0012872864,0.0004679916,0.000878203,0.0010928619,0.0010400831,0.00045720348],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019061957,0.00019130977,0.0027672537,0.00033635934,0.00020469945,0.00026179163,0.00027769204,0.1923551,0.14195591,0.013350746,0.0019700322,0.6461385],"study_design_scores_gemma":[0.0000071332033,0.00007797161,0.0016368914,0.000010669765,0.000012780063,0.00013648563,0.00005654499,0.9777445,0.014197669,0.0043488513,0.0017504906,0.000019976125],"about_ca_topic_score_codex":0.001296334,"about_ca_topic_score_gemma":0.0011926424,"teacher_disagreement_score":0.001296334,"about_ca_system_score_codex":0.00023366282,"about_ca_system_score_gemma":0.0007199631,"threshold_uncertainty_score":0.0032117963},"labels":[],"label_agreement":null},{"id":"W2017497730","doi":"10.1007/bf02912690","title":"Multi-sensor data fusion for supervised land-cover classification using Bayesian and geostatistical techniques","year":2002,"lang":"en","type":"article","venue":"Geosciences Journal","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"National Aeronautics and Space Administration","keywords":"Kriging; Sensor fusion; Spatial analysis; Bayesian probability; Computer science; Land cover; Data mining; Pattern recognition (psychology); Artificial intelligence; Basis (linear algebra); Machine learning; Remote sensing; Mathematics; Land use; Geography","score_opus":0.13040946339073362,"score_gpt":0.3136105061249536,"score_spread":0.18320104273422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017497730","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023821535,0.00033887415,0.97424656,0.00016959378,0.00005842811,0.000028160428,0.00011823126,0.0005676741,0.00065101194],"genre_scores_gemma":[0.41659808,0.0004928688,0.58019155,0.00011263276,0.0001362681,0.00015972827,0.0006633537,0.00009975123,0.0015457163],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990478,0.0002581242,0.00008296372,0.00013401847,0.00041193663,0.000065087996],"domain_scores_gemma":[0.998428,0.0006310023,0.00018825901,0.00017551084,0.00053952105,0.000037718146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018627535,0.0007002091,0.0012436754,0.0016314152,0.0005860765,0.0008749174,0.0007965435,0.001000768,0.0010568565],"category_scores_gemma":[0.0050378004,0.0006347909,0.00096884085,0.0017602057,0.000510979,0.0021712314,0.001040368,0.0009000024,0.00057476916],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044543258,0.00040417825,0.0031105017,0.0002624801,0.00025564275,0.00007129497,0.00018808711,0.20013714,0.0502245,0.0066955313,0.0035465227,0.7346587],"study_design_scores_gemma":[0.000025295141,0.000050899984,0.003116771,0.000013103113,0.0000747739,0.00004440376,0.00003258497,0.97740334,0.011364143,0.006563245,0.0012754137,0.000036058158],"about_ca_topic_score_codex":0.0035673112,"about_ca_topic_score_gemma":0.0070189936,"teacher_disagreement_score":0.0035673112,"about_ca_system_score_codex":0.000523158,"about_ca_system_score_gemma":0.0011017097,"threshold_uncertainty_score":0.009851277},"labels":[],"label_agreement":null},{"id":"W2018738856","doi":"10.1109/tip.2012.2192130","title":"Object Detection With DoG Scale-Space: A Multiple Kernel Learning Approach","year":2012,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Artificial intelligence; Multiple kernel learning; Scale space; Weighting; Pattern recognition (psychology); Kernel (algebra); Support vector machine; Computer science; Kernel method; Radial basis function kernel; Scale (ratio); Object detection; Computer vision; Mathematics; Machine learning; Image processing; Image (mathematics)","score_opus":0.012542724179788765,"score_gpt":0.22325323565896585,"score_spread":0.21071051147917708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2018738856","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006176544,0.00013792377,0.992906,0.00008497586,0.000014795868,0.000017204691,0.000016566208,0.00040053352,0.00024548115],"genre_scores_gemma":[0.31813934,0.00035333386,0.6786758,0.00013074407,0.00007345108,0.00008954726,0.00018506641,0.00017333333,0.0021794243],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894863,0.00027191135,0.000050204322,0.00024654984,0.00038737443,0.00009527542],"domain_scores_gemma":[0.99892706,0.00030415136,0.00014270277,0.00025435447,0.00031313565,0.000058630987],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013647174,0.0006851005,0.0011730526,0.0015330717,0.00034280453,0.0011358563,0.0014521112,0.0010879387,0.001089512],"category_scores_gemma":[0.003404495,0.00042319135,0.0009329119,0.0014304549,0.00080415374,0.0020358087,0.0014550178,0.0011990132,0.00065722445],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021889355,0.00019388305,0.0019918086,0.00018667917,0.0001762205,0.00012759086,0.00017101751,0.122479364,0.040739592,0.01888288,0.0043934146,0.81043863],"study_design_scores_gemma":[0.000010577405,0.0000570903,0.00062035536,0.0000053925064,0.000014427628,0.000102857746,0.00002349974,0.9839639,0.007778804,0.005601406,0.0018006248,0.000021161035],"about_ca_topic_score_codex":0.0014832104,"about_ca_topic_score_gemma":0.0011916397,"teacher_disagreement_score":0.0015330717,"about_ca_system_score_codex":0.0006649126,"about_ca_system_score_gemma":0.00055475504,"threshold_uncertainty_score":0.007217407},"labels":[],"label_agreement":null},{"id":"W2018951830","doi":"10.1109/igarss.2015.7326811","title":"Sub-pixel target detection in LWIR hyperspectral imagery using ground leaving radiance","year":2015,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Defence Research and Development Canada","funders":"","keywords":"Radiance; Emissivity; Hyperspectral imaging; Remote sensing; Pixel; Noise (video); Environmental science; Irradiance; Materials science; Optics; Computer science; Physics; Geology; Artificial intelligence; Image (mathematics)","score_opus":0.036211301265379525,"score_gpt":0.2379883408178051,"score_spread":0.20177703955242557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2018951830","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7014071,0.00012486437,0.2957292,0.000043902048,0.000015639404,0.000041919684,0.000055981967,0.0012747783,0.0013065299],"genre_scores_gemma":[0.8307116,0.00008683857,0.16810113,0.00002835054,0.0000069935536,0.000023031753,0.00013741045,0.00006691193,0.00083774753],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998437,0.000021319265,0.0000045055453,0.000041847357,0.00006167698,0.000026913118],"domain_scores_gemma":[0.99985456,0.0000509581,0.00002957797,0.000019949657,0.000034877696,0.000010025637],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036690178,0.0003844002,0.00032895725,0.00048929104,0.00016198124,0.0004258986,0.00037015043,0.00037532282,0.00046694576],"category_scores_gemma":[0.0005792003,0.00020801356,0.00032529625,0.00029434584,0.00025721823,0.0005781515,0.00030058253,0.00021193204,0.00034308978],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006308064,0.00030463145,0.010872997,0.00012660239,0.00007778264,0.00026360285,0.00023292906,0.11662251,0.5928006,0.00092275813,0.00048133504,0.27666348],"study_design_scores_gemma":[0.00001328106,0.00020113264,0.0133270295,0.0000053868457,0.000029380526,0.00021228389,0.00007424491,0.76637375,0.21862602,0.00039641137,0.00072047784,0.000020635716],"about_ca_topic_score_codex":0.0012997834,"about_ca_topic_score_gemma":0.0018026334,"teacher_disagreement_score":0.0012997834,"about_ca_system_score_codex":0.00020975826,"about_ca_system_score_gemma":0.00020726678,"threshold_uncertainty_score":0.0025844574},"labels":[],"label_agreement":null},{"id":"W2019087970","doi":"10.1016/j.forsciint.2014.08.020","title":"Detection of single graves by airborne hyperspectral imaging","year":2014,"lang":"en","type":"article","venue":"Forensic Science International","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":38,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; National Research Council Canada","funders":"","keywords":"Hyperspectral imaging; Remote sensing; Range (aeronautics); Pixel; Spectral signature; Global Positioning System; Computer science; Geology; Environmental science; Artificial intelligence; Telecommunications; Engineering","score_opus":0.009079958388462787,"score_gpt":0.221160331973484,"score_spread":0.21208037358502121,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019087970","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9423864,0.00036167237,0.051460568,0.00008893296,0.000038028815,0.000026247526,0.00023027518,0.00024377964,0.005164011],"genre_scores_gemma":[0.94194806,0.00024142167,0.053967547,0.00004369641,0.000030078107,0.000009335552,0.00024791755,0.000029812065,0.0034821278],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9998933,0.000007969573,0.0000032460462,0.00003067399,0.000048950093,0.000015820893],"domain_scores_gemma":[0.99987733,0.00003233048,0.00002227341,0.00001896148,0.000036116235,0.000013004448],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010444772,0.0003280043,0.00022252562,0.0008201833,0.00021646023,0.00041287288,0.00030531923,0.0005120861,0.001124285],"category_scores_gemma":[0.00025698097,0.0002624099,0.00017728627,0.0003449655,0.00026837253,0.0005280111,0.00045506944,0.00025625504,0.0006217056],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028170427,0.00006250416,0.019597081,0.00012317598,0.000047062334,0.00028236487,0.0002047108,0.0039866376,0.83462614,0.0006672721,0.0006932942,0.13942806],"study_design_scores_gemma":[0.000046688634,0.00044036048,0.2210437,0.000071766524,0.00022661514,0.0031460102,0.0010405425,0.2911918,0.4718006,0.0030469229,0.007852847,0.00009215478],"about_ca_topic_score_codex":0.001119937,"about_ca_topic_score_gemma":0.0028343066,"teacher_disagreement_score":0.001124285,"about_ca_system_score_codex":0.000091872826,"about_ca_system_score_gemma":0.00012095294,"threshold_uncertainty_score":0.0037611127},"labels":[],"label_agreement":null},{"id":"W2020756293","doi":"10.1117/12.800298","title":"Urban land use/land cover mapping with high-resolution SAR imagery by integrating support vector machines into object-based analysis","year":2008,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Canadian Space Agency","keywords":"Support vector machine; Land cover; Computer science; Artificial intelligence; Segmentation; Pattern recognition (psychology); Remote sensing; Image resolution; Computer vision; Pixel; Synthetic aperture radar; Image segmentation; Contextual image classification; Object (grammar); Geography; Image (mathematics); Land use; Engineering","score_opus":0.00976091495121549,"score_gpt":0.20392977400298626,"score_spread":0.19416885905177078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020756293","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26844263,0.0006734309,0.7279238,0.00014804704,0.00003345989,0.000052111136,0.00010265055,0.0011418074,0.0014820694],"genre_scores_gemma":[0.76199394,0.00024457183,0.23666222,0.00003323892,0.000041367373,0.000030820058,0.00020311697,0.000042915734,0.00074772816],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99955934,0.000136732,0.00002619994,0.00007010237,0.00017257118,0.00003503266],"domain_scores_gemma":[0.9993864,0.0003018665,0.00009260113,0.00008048526,0.00011528069,0.000023281043],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010351056,0.0005016245,0.00044184853,0.0013650898,0.00016161961,0.0007516806,0.00034908782,0.00041919507,0.0006675155],"category_scores_gemma":[0.0016331075,0.00022681465,0.000496505,0.00091050065,0.00029209015,0.00129302,0.00037153435,0.00034453295,0.00043410488],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023901048,0.00027822988,0.020070877,0.00015437212,0.00019614545,0.00017485513,0.00018085283,0.15359521,0.037658338,0.0015542915,0.0008895701,0.7850082],"study_design_scores_gemma":[0.000010010802,0.00010919172,0.014107502,0.000012634339,0.000044623484,0.00011001707,0.0000692173,0.9719906,0.010797078,0.0016529487,0.0010763315,0.000019877669],"about_ca_topic_score_codex":0.0012834717,"about_ca_topic_score_gemma":0.0014363882,"teacher_disagreement_score":0.0013650898,"about_ca_system_score_codex":0.00020773667,"about_ca_system_score_gemma":0.00015743461,"threshold_uncertainty_score":0.0054742694},"labels":[],"label_agreement":null},{"id":"W2021266528","doi":"10.1117/12.864142","title":"Analysing multitemporal SAR images for forest mapping","year":2010,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Preprocessor; Artificial intelligence; Pattern recognition (psychology); Feature selection; Synthetic aperture radar; Classifier (UML); Contextual image classification; Feature extraction; Data mining; Image (mathematics)","score_opus":0.014296010117344198,"score_gpt":0.2325119237287529,"score_spread":0.2182159136114087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021266528","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24771291,0.003919013,0.7341097,0.00062835414,0.00017033695,0.00021220499,0.0014332855,0.001395295,0.010418891],"genre_scores_gemma":[0.5455045,0.0024359361,0.44752124,0.00016573956,0.00011780367,0.00008537564,0.0018832246,0.000075419804,0.002210784],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99971527,0.00008406138,0.0000150901005,0.00005000747,0.00011042223,0.000025032117],"domain_scores_gemma":[0.9997836,0.000058702193,0.000044485863,0.000047738427,0.000054369877,0.00001116657],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048735767,0.0005170728,0.0003849939,0.0022958575,0.00020229717,0.00063176075,0.00029630636,0.00049473194,0.0014929425],"category_scores_gemma":[0.00069121073,0.0001582668,0.0004538651,0.0019595807,0.00020767488,0.00064258656,0.00026865696,0.00031063214,0.0005442804],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019938307,0.00016969239,0.016630856,0.0005271019,0.00018034468,0.000499662,0.0002324438,0.028768111,0.21875979,0.0040102843,0.0035576534,0.72646457],"study_design_scores_gemma":[0.00004638553,0.00046304692,0.20117305,0.00022535888,0.00041706488,0.0025476557,0.001668351,0.5532231,0.1702356,0.017985564,0.051874302,0.00014053889],"about_ca_topic_score_codex":0.0008068198,"about_ca_topic_score_gemma":0.0020794363,"teacher_disagreement_score":0.0022958575,"about_ca_system_score_codex":0.00021249594,"about_ca_system_score_gemma":0.00028162618,"threshold_uncertainty_score":0.0049943924},"labels":[],"label_agreement":null},{"id":"W2021450183","doi":"10.5539/esr.v1n2p200","title":"Unmixing and Target Recognition in Airborne Hyper-Spectral Images","year":2012,"lang":"en","type":"article","venue":"Earth Science Research","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Robustness (evolution); Pixel; Artificial intelligence; Computer science; Extension (predicate logic); Spectral signature; Pattern recognition (psychology); Spectral shape analysis; Algorithm; Mathematics; Computer vision; Spectral line; Remote sensing; Geography; Physics","score_opus":0.08245912863312659,"score_gpt":0.33933250861324743,"score_spread":0.25687337998012083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021450183","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034792718,0.00019853076,0.9635039,0.00008958772,0.000027713731,0.000020991465,0.000036457513,0.00044355972,0.0008866369],"genre_scores_gemma":[0.29003817,0.0003176627,0.7064961,0.00010641647,0.00006755088,0.00006498771,0.00020648798,0.00008055659,0.0026220048],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999479,0.00009997705,0.000026306892,0.00016637238,0.00017815715,0.000050172475],"domain_scores_gemma":[0.9994295,0.00024984125,0.000084135514,0.0001131459,0.00009760988,0.00002576031],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000627854,0.0004963713,0.0004097504,0.0011095279,0.00029946328,0.0010244908,0.00068794814,0.00075436005,0.0015131559],"category_scores_gemma":[0.0017995206,0.00031711248,0.0005824102,0.0010280655,0.0008107546,0.002098744,0.0007798014,0.00075419503,0.00081712066],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027790345,0.0001987481,0.002146546,0.00016108931,0.00008897673,0.000118782875,0.00020127237,0.10722149,0.11645095,0.016515182,0.0009961867,0.75562286],"study_design_scores_gemma":[0.000013251337,0.000059512484,0.0015778715,0.0000070943165,0.000022130249,0.00018745865,0.00006681272,0.9131138,0.07040017,0.012543926,0.0019844628,0.000023515418],"about_ca_topic_score_codex":0.00093757536,"about_ca_topic_score_gemma":0.0012878316,"teacher_disagreement_score":0.0015131559,"about_ca_system_score_codex":0.0002626998,"about_ca_system_score_gemma":0.00035301346,"threshold_uncertainty_score":0.005061984},"labels":[],"label_agreement":null},{"id":"W2022876194","doi":"10.14358/pers.79.11.999","title":"A Combined Object- and Pixel-Based Image Analysis Framework for Urban Land Cover Classification of VHR Imagery","year":2013,"lang":"en","type":"article","venue":"Photogrammetric Engineering & Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Land cover; Artificial intelligence; Pixel; Pattern recognition (psychology); Wavelet; Computer science; Curse of dimensionality; Image resolution; Object (grammar); Computer vision; Feature (linguistics); Geography; Remote sensing; Feature extraction; Image (mathematics); Land use; Engineering","score_opus":0.011861054778616436,"score_gpt":0.22414238531649552,"score_spread":0.2122813305378791,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022876194","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008714921,0.0001820306,0.98970234,0.000031949818,0.000014551849,0.000044850043,0.00008871548,0.0005825504,0.0006381383],"genre_scores_gemma":[0.12734802,0.000267533,0.87013865,0.000053140197,0.000057958467,0.00011395379,0.00050402054,0.00008123727,0.0014355546],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996358,0.000060129245,0.000016715818,0.000076932374,0.00017444234,0.000035918034],"domain_scores_gemma":[0.9998129,0.000030441686,0.000025902727,0.000026856422,0.00009118977,0.000012774166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061663997,0.00057370384,0.000642402,0.0020782938,0.0003113924,0.0009430858,0.0006495991,0.00042249923,0.0009878399],"category_scores_gemma":[0.0005367126,0.0002359767,0.0008053699,0.0009171588,0.00035741893,0.0008459005,0.0004917179,0.0004377361,0.000604616],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008207464,0.00020931006,0.004572182,0.00024529052,0.0002464893,0.00012979154,0.00014111369,0.05559595,0.08910145,0.007662326,0.0021053038,0.8399088],"study_design_scores_gemma":[0.000017461087,0.00025343554,0.013535285,0.000043090466,0.00017670747,0.00041937514,0.00015179739,0.93757224,0.030052263,0.006819642,0.0108808195,0.00007781556],"about_ca_topic_score_codex":0.0033827752,"about_ca_topic_score_gemma":0.004382064,"teacher_disagreement_score":0.0033827752,"about_ca_system_score_codex":0.00032059677,"about_ca_system_score_gemma":0.00052827667,"threshold_uncertainty_score":0.0067261457},"labels":[],"label_agreement":null},{"id":"W2023008685","doi":"10.1109/icip.2012.6466850","title":"Bilateral filter based mixture model for image segmentation","year":2012,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Mixture model; Artificial intelligence; Markov random field; Image segmentation; Expectation–maximization algorithm; Computer science; Pattern recognition (psychology); Pixel; Segmentation; Noise (video); Bilateral filter; Filter (signal processing); Computer vision; Image (mathematics); Mathematics; Maximum likelihood; Statistics","score_opus":0.025991579959165116,"score_gpt":0.25199021574762975,"score_spread":0.22599863578846463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2023008685","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00060468516,0.00016380096,0.9984509,0.00003755537,0.000017625785,0.000013250976,0.0000317089,0.00029062186,0.00038989133],"genre_scores_gemma":[0.11671527,0.001416163,0.8725473,0.00019707157,0.0001377337,0.00029287787,0.0006598384,0.00047665022,0.0075570196],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99900216,0.00021470325,0.000050726514,0.00023083226,0.00042455376,0.00007707919],"domain_scores_gemma":[0.9994517,0.00027555242,0.000055086628,0.00006538274,0.00012896383,0.00002337877],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014043541,0.0009711481,0.0015507953,0.0016001887,0.000554472,0.0012502933,0.0018616166,0.0020164722,0.0041130926],"category_scores_gemma":[0.0026059675,0.0007901423,0.002148387,0.0019119504,0.0006872008,0.0025309934,0.0009951338,0.0015353478,0.0018542822],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017694407,0.000071373186,0.0007370539,0.0002495968,0.00018477837,0.00015573675,0.00017422224,0.6115013,0.026303373,0.05534501,0.0042025014,0.30089822],"study_design_scores_gemma":[0.000005070763,0.000013167657,0.00017123712,0.0000080777945,0.000018431034,0.000065279346,0.0000057198913,0.9850574,0.0019933041,0.00932344,0.0033206062,0.000018237562],"about_ca_topic_score_codex":0.0071829427,"about_ca_topic_score_gemma":0.006792154,"teacher_disagreement_score":0.0071829427,"about_ca_system_score_codex":0.0012958741,"about_ca_system_score_gemma":0.0009328497,"threshold_uncertainty_score":0.014282286},"labels":[],"label_agreement":null},{"id":"W2023501853","doi":"10.1108/dpm-12-2012-0148","title":"Towards a rapid automatic detection of building damage using remote sensing for disaster management","year":2014,"lang":"en","type":"article","venue":"Disaster Prevention and Management An International Journal","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Computer science; Damages; Emergency management; Remote sensing; Image resolution; Computer vision; Data mining; Geography","score_opus":0.022051855471841932,"score_gpt":0.2905902920509053,"score_spread":0.2685384365790634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2023501853","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42040712,0.00236038,0.5623251,0.0009010664,0.00021988258,0.0009101998,0.0011146133,0.0045001856,0.007261477],"genre_scores_gemma":[0.4911739,0.0006179067,0.50453633,0.00018470662,0.00006838788,0.00023066936,0.0012539214,0.00007678233,0.0018573902],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99959284,0.000113619215,0.00001793224,0.0000821291,0.00015161622,0.000041933363],"domain_scores_gemma":[0.9995245,0.00009323967,0.00007924085,0.00006501077,0.00019873175,0.000039293216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075411634,0.00064189435,0.00036152714,0.0020358302,0.00022149282,0.0006929137,0.0005570953,0.0007669722,0.00086399924],"category_scores_gemma":[0.0008080663,0.00026593753,0.0004848828,0.0009498354,0.0002780262,0.0007664834,0.00058146205,0.00047925496,0.0009816829],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035477174,0.00059350336,0.02980801,0.00067412696,0.00009455279,0.00033595774,0.00048479522,0.017312052,0.27526367,0.0011009213,0.0054025054,0.66857517],"study_design_scores_gemma":[0.00015088695,0.0012838044,0.17521708,0.00033318996,0.00020295249,0.0008570894,0.0011654254,0.66150457,0.13285737,0.0034208999,0.02283689,0.00016985428],"about_ca_topic_score_codex":0.0012648465,"about_ca_topic_score_gemma":0.0015330461,"teacher_disagreement_score":0.0020358302,"about_ca_system_score_codex":0.00017361596,"about_ca_system_score_gemma":0.00039665043,"threshold_uncertainty_score":0.0039882064},"labels":[],"label_agreement":null},{"id":"W2023827825","doi":"10.1080/01431160500180699","title":"Deriving terrain and textural information from stereo RADARSAT data for mountainous land cover mapping","year":2005,"lang":"en","type":"article","venue":"International Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Universidad de Buenos Aires","keywords":"Terrain; Remote sensing; Land cover; Digital elevation model; Elevation (ballistics); Classifier (UML); Computer science; Artificial intelligence; Cartography; Geology; Land use; Geography; Mathematics","score_opus":0.02301866619277868,"score_gpt":0.2570222357940321,"score_spread":0.23400356960125343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2023827825","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1927604,0.0003792922,0.8007407,0.000108654116,0.00004525172,0.00014306199,0.0012232435,0.0014418341,0.0031575614],"genre_scores_gemma":[0.41018352,0.00035722755,0.58547175,0.00003278415,0.00004928614,0.00010070177,0.0023274445,0.000059898084,0.0014173726],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99987996,0.00001974894,0.000009262517,0.000023921617,0.00005382996,0.000013160662],"domain_scores_gemma":[0.999821,0.000030554464,0.000039833663,0.000029181423,0.00006872632,0.000010700371],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020342795,0.00030936155,0.00024965825,0.0019329342,0.00018463169,0.00030782816,0.00027933528,0.00020812485,0.0007884398],"category_scores_gemma":[0.00053955085,0.00015637625,0.00032123097,0.0012997882,0.000120828096,0.00040874642,0.00024623377,0.00019041896,0.00039393854],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001259128,0.00013062602,0.019156616,0.0001319215,0.00008340714,0.00022518102,0.00010758642,0.028796962,0.08835006,0.0013633922,0.0018795747,0.8596488],"study_design_scores_gemma":[0.000044190903,0.0001546668,0.109621845,0.00004021702,0.00011046699,0.0005820627,0.00020359091,0.83314055,0.04272751,0.0038120965,0.009485272,0.00007743875],"about_ca_topic_score_codex":0.002524496,"about_ca_topic_score_gemma":0.0055156653,"teacher_disagreement_score":0.002524496,"about_ca_system_score_codex":0.00017275529,"about_ca_system_score_gemma":0.0002943773,"threshold_uncertainty_score":0.005019605},"labels":[],"label_agreement":null},{"id":"W2024448972","doi":"10.3390/rs6087339","title":"Urban Built-Up Area Extraction from Landsat TM/ETM+ Images Using Spectral Information and Multivariate Texture","year":2014,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":96,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"National Science Foundation","keywords":"Remote sensing; Multispectral image; Multivariate statistics; Computer science; Mahalanobis distance; Hyperspectral imaging; Variogram; Pattern recognition (psychology); Artificial intelligence; Confusion matrix; Geography; Kriging","score_opus":0.015847882457083344,"score_gpt":0.2357304390796938,"score_spread":0.21988255662261044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024448972","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47978598,0.0006944589,0.5116995,0.0001162366,0.000058346242,0.00011651773,0.001329485,0.001909031,0.0042904457],"genre_scores_gemma":[0.8296324,0.0005252143,0.16629498,0.000032407574,0.000036996247,0.000055867724,0.0017181636,0.00011149898,0.0015925035],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99988294,0.000011264977,0.000008831827,0.000026576954,0.00004826281,0.00002216069],"domain_scores_gemma":[0.99984765,0.000027787806,0.000032495667,0.000017407849,0.0000628217,0.000011767803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017596105,0.0006999689,0.00035809868,0.003622312,0.00017112322,0.00056579936,0.00019713765,0.00025104266,0.0005684567],"category_scores_gemma":[0.00031697043,0.00019795871,0.0006342222,0.0019802416,0.00019550574,0.0006204548,0.00035710444,0.00022965511,0.0002603497],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025489926,0.00015240806,0.036905307,0.0005039717,0.0001623677,0.0004170009,0.00016465463,0.03705957,0.17793822,0.0016437027,0.0026843522,0.74211353],"study_design_scores_gemma":[0.000033528784,0.000118187345,0.2045458,0.000066331115,0.0003343789,0.00090900203,0.00057731,0.6892349,0.09328082,0.0027740994,0.008007281,0.00011840892],"about_ca_topic_score_codex":0.0027477082,"about_ca_topic_score_gemma":0.004984388,"teacher_disagreement_score":0.003622312,"about_ca_system_score_codex":0.0001596406,"about_ca_system_score_gemma":0.00022477571,"threshold_uncertainty_score":0.0054634213},"labels":[],"label_agreement":null},{"id":"W2026829374","doi":"10.1007/s11760-012-0404-3","title":"SN-SVM: a sparse nonparametric support vector machine classifier","year":2012,"lang":"en","type":"article","venue":"Signal Image and Video Processing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor; Toronto Metropolitan University","funders":"","keywords":"Support vector machine; Artificial intelligence; Pattern recognition (psychology); Computer science; Nonparametric statistics; Relevance vector machine; Classifier (UML); Kernel (algebra); Machine learning; Kernel method; Structured support vector machine; Quadratic classifier; Mathematics","score_opus":0.022735923478807544,"score_gpt":0.25463939849288003,"score_spread":0.2319034750140725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026829374","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010181591,0.00053271477,0.98366207,0.00017826617,0.00019892358,0.000088640445,0.00042933252,0.0034010725,0.0013274517],"genre_scores_gemma":[0.21219648,0.00064934226,0.7714177,0.00040417074,0.0003729924,0.00031421753,0.0037558207,0.00041747838,0.010471816],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989213,0.0002963886,0.000085155574,0.00017232703,0.00045391862,0.00007091081],"domain_scores_gemma":[0.99843794,0.00044656222,0.000089470625,0.00024163013,0.00071720156,0.000067141336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014207764,0.0007290853,0.001394083,0.0012080076,0.00043681194,0.00094773096,0.0014265473,0.0011880809,0.003923981],"category_scores_gemma":[0.0034400749,0.00034837952,0.0008615296,0.0012519247,0.00028690603,0.0014322365,0.0011564972,0.0013560052,0.0034461073],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002935564,0.00026955365,0.0014595193,0.00014900567,0.00015864627,0.00006149686,0.000022898228,0.042454958,0.0077889296,0.0038290767,0.018905839,0.9246065],"study_design_scores_gemma":[0.000018926266,0.00009663794,0.00040051283,0.000010284441,0.000024769255,0.000099767385,0.0000093263725,0.9872307,0.0035428728,0.0025159235,0.0060389875,0.000011282824],"about_ca_topic_score_codex":0.0015665367,"about_ca_topic_score_gemma":0.0029100785,"teacher_disagreement_score":0.003923981,"about_ca_system_score_codex":0.00029201442,"about_ca_system_score_gemma":0.0008906327,"threshold_uncertainty_score":0.013127029},"labels":[],"label_agreement":null},{"id":"W2028151808","doi":"10.1016/j.isprsjprs.2014.04.010","title":"SAR change detection based on intensity and texture changes","year":2014,"lang":"en","type":"article","venue":"ISPRS Journal of Photogrammetry and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":91,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China; Defence Research and Development Canada","keywords":"Synthetic aperture radar; Artificial intelligence; Pattern recognition (psychology); Change detection; Computer science; Principal component analysis; Interferometric synthetic aperture radar; Texture (cosmology); Computer vision; Gaussian; Image (mathematics)","score_opus":0.0165192862651067,"score_gpt":0.22166852541513563,"score_spread":0.20514923915002892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2028151808","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7305433,0.0005386398,0.24946848,0.00021743822,0.00023797617,0.0002772775,0.0011096898,0.001394786,0.016212385],"genre_scores_gemma":[0.93767536,0.0005065056,0.056022886,0.00009060894,0.0001275889,0.000067142224,0.0011122989,0.000115767994,0.0042819316],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997588,0.00001785705,0.000011684366,0.00005190821,0.00010744517,0.000052241892],"domain_scores_gemma":[0.9996778,0.000043167416,0.0000437206,0.000028339948,0.00016586961,0.00004105463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002749224,0.0005420832,0.0005069219,0.0027781124,0.00017775498,0.0006958791,0.00022643653,0.00033332294,0.0019286696],"category_scores_gemma":[0.00055673136,0.00019299664,0.00041008764,0.0014708044,0.0003139383,0.0005855255,0.00030355252,0.00037937734,0.0008602951],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012214805,0.00032888888,0.029528514,0.00025308132,0.00010651843,0.00028506736,0.00013306705,0.007011828,0.45339558,0.00094104675,0.0022524744,0.5045424],"study_design_scores_gemma":[0.00008931247,0.00073524576,0.3389374,0.00005624439,0.00044489434,0.0015164807,0.00038840473,0.42060483,0.22549817,0.001467653,0.010161626,0.00009981292],"about_ca_topic_score_codex":0.0010837668,"about_ca_topic_score_gemma":0.0017700469,"teacher_disagreement_score":0.0027781124,"about_ca_system_score_codex":0.00014937377,"about_ca_system_score_gemma":0.00022370285,"threshold_uncertainty_score":0.006452024},"labels":[],"label_agreement":null},{"id":"W2028469338","doi":"10.1109/jstars.2015.2414816","title":"Hyperspectral Image Classification With Limited Labeled Training Samples Using Enhanced Ensemble Learning and Conditional Random Fields","year":2015,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Canadian Space Agency; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Hyperspectral imaging; Artificial intelligence; Pattern recognition (psychology); Overfitting; AdaBoost; Computer science; Random forest; Contextual image classification; Ensemble learning; Conditional random field; Context (archaeology); Curse of dimensionality; Support vector machine; Machine learning; Image (mathematics); Artificial neural network","score_opus":0.06267270060563282,"score_gpt":0.2538046624579312,"score_spread":0.1911319618522984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2028469338","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055126794,0.00040023244,0.94209594,0.00010737873,0.000044007957,0.0000377075,0.00009501377,0.001294345,0.00079856784],"genre_scores_gemma":[0.6263388,0.0002922066,0.37076303,0.00014364434,0.000102031074,0.000088052046,0.0008011311,0.0001090443,0.0013620111],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99912435,0.0002975129,0.00003927981,0.000242923,0.00020721828,0.000088714405],"domain_scores_gemma":[0.99803275,0.0009020563,0.00015970843,0.00035956712,0.00048620443,0.00005971745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023500691,0.0007688401,0.0010982555,0.0010360774,0.0003904877,0.0005452283,0.0010746917,0.0007420446,0.0007462757],"category_scores_gemma":[0.0033031506,0.00033031643,0.0010104072,0.0010083128,0.00037743655,0.0015734304,0.0007544322,0.0011168108,0.000346296],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002196602,0.0002554565,0.0041506924,0.000077665034,0.00017842816,0.000070665476,0.000098248434,0.51702243,0.012949347,0.002761263,0.0024808422,0.45973536],"study_design_scores_gemma":[0.0000028704567,0.000015756408,0.00037966607,0.0000028806035,0.000009880808,0.000011320939,0.0000041366125,0.99733377,0.0013468562,0.0007188188,0.00016876076,0.0000053408953],"about_ca_topic_score_codex":0.0052907257,"about_ca_topic_score_gemma":0.006645953,"teacher_disagreement_score":0.0052907257,"about_ca_system_score_codex":0.00039977103,"about_ca_system_score_gemma":0.0006737942,"threshold_uncertainty_score":0.0124284625},"labels":[],"label_agreement":null},{"id":"W2029483220","doi":"10.1117/12.2017942","title":"Fusion of active and passive infrared images for face recognition","year":2013,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Facial recognition system; Computer science; Artificial intelligence; Multispectral image; Fusion; Computer vision; Image fusion; Face (sociological concept); Infrared; Pattern recognition (psychology); Optics; Image (mathematics); Physics","score_opus":0.01269697570065748,"score_gpt":0.21893068929795909,"score_spread":0.2062337135973016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029483220","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03717418,0.00079812383,0.95782506,0.00009301751,0.000121395366,0.00006901993,0.00013767762,0.000886828,0.0028946188],"genre_scores_gemma":[0.5231942,0.0009942133,0.47052526,0.00015873277,0.00017298757,0.00012663828,0.000605938,0.00010688896,0.004115073],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99949276,0.00006873704,0.000018680379,0.00009617766,0.00027106857,0.000052565683],"domain_scores_gemma":[0.99978834,0.00004950646,0.000025499567,0.000044602813,0.00008154439,0.000010587805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006578963,0.00062537385,0.00063344016,0.00095324294,0.00024381565,0.00048099522,0.0007301432,0.00057707465,0.0017049846],"category_scores_gemma":[0.0008325042,0.00023157909,0.0007710864,0.00059806654,0.0002556742,0.0010373435,0.0006768571,0.00056295964,0.0010238278],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044540403,0.00023619669,0.0013721281,0.00025757108,0.000097751166,0.00010775993,0.000080060905,0.017795445,0.3492892,0.0035141706,0.0018586718,0.62494564],"study_design_scores_gemma":[0.000034844325,0.0006690081,0.010032985,0.00005190418,0.0002314007,0.0008461323,0.00012667703,0.6032751,0.36538962,0.007150158,0.012094579,0.00009763864],"about_ca_topic_score_codex":0.0005028004,"about_ca_topic_score_gemma":0.0006600004,"teacher_disagreement_score":0.0017049846,"about_ca_system_score_codex":0.00020813399,"about_ca_system_score_gemma":0.00020503563,"threshold_uncertainty_score":0.0057037473},"labels":[],"label_agreement":null},{"id":"W2030180421","doi":"10.1080/2150704x.2014.912765","title":"PolSAR image classification using a semi-supervised classifier based on hypergraph learning","year":2014,"lang":"en","type":"article","venue":"Remote Sensing Letters","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Pattern recognition (psychology); Computer science; Classifier (UML); Hyperspectral imaging; Support vector machine; Hypergraph; Contextual image classification; Synthetic aperture radar; Polarimetry; Image (mathematics); Mathematics; Scattering; Physics","score_opus":0.01990635304895458,"score_gpt":0.22621729155909354,"score_spread":0.20631093851013896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030180421","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020084932,0.00012859504,0.9774194,0.000101503,0.000027949633,0.00006863211,0.00009720601,0.0011257286,0.0009461449],"genre_scores_gemma":[0.4232872,0.00029868048,0.57119954,0.0002519786,0.00016317693,0.0002515492,0.0009228178,0.00015538173,0.0034697307],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99920183,0.00020574522,0.000044159788,0.00023161786,0.00026175752,0.00005487133],"domain_scores_gemma":[0.99884367,0.00038581723,0.00014745389,0.0002133729,0.00035718043,0.000052511463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000646385,0.00064972515,0.0009894355,0.0019760826,0.0004714507,0.00078698253,0.0012076625,0.00094419747,0.00090343395],"category_scores_gemma":[0.0014372378,0.00029525874,0.000883963,0.0012847211,0.00068692456,0.0012871865,0.0006747925,0.0008651336,0.00079334615],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018352525,0.00039507434,0.0037828535,0.0001664789,0.00021668799,0.00013083637,0.00013060264,0.1630802,0.04062961,0.007344833,0.0056659044,0.7782734],"study_design_scores_gemma":[0.0000048752095,0.000025185398,0.0006838652,0.00000552303,0.000014012025,0.000049660124,0.000011908374,0.9918572,0.0045041777,0.0021530404,0.0006777136,0.000012958608],"about_ca_topic_score_codex":0.0022861408,"about_ca_topic_score_gemma":0.0033692103,"teacher_disagreement_score":0.0022861408,"about_ca_system_score_codex":0.0005240224,"about_ca_system_score_gemma":0.00069448317,"threshold_uncertainty_score":0.004545629},"labels":[],"label_agreement":null},{"id":"W2030428246","doi":"10.3390/a6040762","title":"Very High Resolution Satellite Image Classification Using Fuzzy Rule-Based Systems","year":2013,"lang":"en","type":"article","venue":"Algorithms","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":68,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Fuzzy logic; Artificial intelligence; Image (mathematics); Pattern recognition (psychology); Fuzzy classification; Contextual image classification; Fuzzy rule; Classification rule; Data mining; Computer science; Satellite; Object (grammar); Rule-based system; Mathematics; Fuzzy set; Computer vision","score_opus":0.026471729881210364,"score_gpt":0.23228585718033554,"score_spread":0.20581412729912518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030428246","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028592587,0.00040506604,0.967775,0.00007019585,0.000051769246,0.0001499671,0.00005708853,0.00086447515,0.0020337498],"genre_scores_gemma":[0.340749,0.000390393,0.65691996,0.00006247711,0.00004763563,0.00018399785,0.0001877017,0.000036589743,0.0014222512],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99857557,0.00038113273,0.00016695487,0.0002201355,0.0005939958,0.000062128325],"domain_scores_gemma":[0.99861836,0.00063551473,0.00013894288,0.00015124974,0.0004286531,0.000027268226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017504352,0.00057918014,0.00083047745,0.0017477643,0.00057633757,0.0018888633,0.0011104272,0.0009579923,0.0012500576],"category_scores_gemma":[0.0042944164,0.0003010282,0.00078659336,0.0011536832,0.0005424274,0.00092689204,0.0003900736,0.0006165507,0.0007520904],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026051266,0.00026400603,0.0037217187,0.00042260764,0.0002571359,0.00028948404,0.0003871084,0.22079152,0.040184606,0.0064986586,0.0013499851,0.7255727],"study_design_scores_gemma":[0.000027084256,0.00010926746,0.0021627715,0.00007434946,0.00008724489,0.00017272182,0.00006713897,0.97902465,0.011874072,0.0042551085,0.0020989338,0.000046634694],"about_ca_topic_score_codex":0.0037719733,"about_ca_topic_score_gemma":0.0033036578,"teacher_disagreement_score":0.0037719733,"about_ca_system_score_codex":0.00051354175,"about_ca_system_score_gemma":0.0005202871,"threshold_uncertainty_score":0.009257317},"labels":[],"label_agreement":null},{"id":"W2034264117","doi":"10.1109/igarss.2014.6947152","title":"Object based building extraction by QuickBird image for population estimation: A case study of the City of Waterloo","year":2014,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Census; Population; Computer science; Extraction (chemistry); Geography; Object (grammar); Artificial intelligence; Cartography; Remote sensing","score_opus":0.017060869314906527,"score_gpt":0.2750881257952993,"score_spread":0.25802725648039276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034264117","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9800888,0.00023878433,0.012355045,0.00018748904,0.000007913768,0.00013737033,0.0018031187,0.00034310258,0.004838411],"genre_scores_gemma":[0.9737412,0.0002896847,0.02187678,0.000029348776,0.000005315723,0.000029259541,0.0015658519,0.00004070934,0.002421913],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997898,0.000025720345,0.000008355829,0.000038278748,0.00009147518,0.000046423953],"domain_scores_gemma":[0.9997987,0.00006362807,0.000018026683,0.00002096795,0.000083944455,0.000014834652],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021066259,0.00039504326,0.00025510055,0.0019799345,0.00054756907,0.00055700605,0.00045042805,0.00030848183,0.0011732829],"category_scores_gemma":[0.0005079376,0.00015585806,0.00035611104,0.0021215696,0.00025375374,0.00032229238,0.00022796221,0.00015837295,0.00024618075],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002450605,0.000392458,0.4061693,0.00066409033,0.00019716214,0.008101359,0.004120575,0.061340112,0.042386215,0.001419254,0.0069525912,0.46801192],"study_design_scores_gemma":[0.000055416043,0.000117353804,0.68260616,0.00006927131,0.0002095902,0.0016319001,0.0063205017,0.24936105,0.0439014,0.00050746254,0.015109979,0.000109887646],"about_ca_topic_score_codex":0.6136665,"about_ca_topic_score_gemma":0.80709225,"teacher_disagreement_score":0.38633353,"about_ca_system_score_codex":0.0018975431,"about_ca_system_score_gemma":0.0011792441,"threshold_uncertainty_score":0.77721745},"labels":[],"label_agreement":null},{"id":"W2035790115","doi":"10.1109/wacvw.2015.9","title":"Evolutionary Computational Methods for Optimizing the Classification of Sea Stars in Underwater Images","year":2015,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Mitacs","keywords":"Computer science; Underwater; Artificial intelligence; Process (computing); Sampling (signal processing); Stars; Contextual image classification; Pattern recognition (psychology); Machine learning; Computer vision; Data mining; Image (mathematics); Geology","score_opus":0.0762737477214243,"score_gpt":0.3395422993648277,"score_spread":0.2632685516434034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2035790115","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044985466,0.0002300934,0.95180494,0.00022271596,0.000036416233,0.00007792281,0.00003465899,0.00024518743,0.0023627526],"genre_scores_gemma":[0.45465732,0.0002172284,0.541437,0.0002138567,0.00007551509,0.00047096895,0.00018458981,0.00015897363,0.0025845957],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996087,0.00014037469,0.00002573406,0.00007004689,0.00011153991,0.000043606404],"domain_scores_gemma":[0.9984358,0.0011289087,0.00011665349,0.00006617861,0.00021078122,0.000041648862],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013986169,0.0010128007,0.0009551261,0.0009943164,0.00049783115,0.0008365896,0.0011582673,0.0012381414,0.0011694233],"category_scores_gemma":[0.00449911,0.00054812175,0.0006285746,0.0008682379,0.0008134267,0.0006984763,0.0007149408,0.0008908037,0.00021009053],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022193048,0.000035584053,0.000397677,0.000024602461,0.000021679236,0.000021160162,0.00002352294,0.96345985,0.0007296706,0.0021626726,0.0003520346,0.03274939],"study_design_scores_gemma":[0.000003069978,0.0000049925707,0.000042299827,0.0000014351709,0.0000016458679,0.000002377484,0.0000025071108,0.99919826,0.00010364502,0.00057895004,0.00005967611,0.0000012137049],"about_ca_topic_score_codex":0.0058877408,"about_ca_topic_score_gemma":0.0061387494,"teacher_disagreement_score":0.0058877408,"about_ca_system_score_codex":0.0009250931,"about_ca_system_score_gemma":0.0010515682,"threshold_uncertainty_score":0.011706948},"labels":[],"label_agreement":null},{"id":"W2036842392","doi":"10.1109/lgrs.2012.2236818","title":"Learn Multiple-Kernel SVMs for Domain Adaptation in Hyperspectral Data","year":2013,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":89,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Hyperspectral imaging; Support vector machine; Pattern recognition (psychology); Artificial intelligence; Computer science; Domain adaptation; Pairwise comparison; Robustness (evolution); Kernel (algebra); Boosting (machine learning); Classifier (UML); Binary classification; Machine learning; Data mining; Mathematics","score_opus":0.036166280117890824,"score_gpt":0.23944160212607288,"score_spread":0.20327532200818205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036842392","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022525473,0.00015077215,0.9765929,0.00006203701,0.000017667246,0.000020364918,0.000025329715,0.00032711023,0.0002782314],"genre_scores_gemma":[0.5168106,0.00020932301,0.4804689,0.000119505035,0.00006545725,0.00013808266,0.0003557657,0.00015317409,0.0016791803],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993024,0.000276298,0.000040399802,0.00017710649,0.00015727528,0.000046602967],"domain_scores_gemma":[0.99858654,0.00053537916,0.0001916813,0.0002909353,0.00034570388,0.000049803886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013992818,0.0006101572,0.0007746823,0.00052484946,0.00029490847,0.00055291224,0.0010665212,0.00076146045,0.00074592984],"category_scores_gemma":[0.004066768,0.00029819773,0.0006238031,0.0006396674,0.000510105,0.0014899835,0.0012146797,0.0013957756,0.00055640197],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020513064,0.00021974421,0.0026654617,0.00013745557,0.00011936176,0.00008256042,0.00017861373,0.4063278,0.02398162,0.012937687,0.0028245167,0.55031997],"study_design_scores_gemma":[0.0000026990638,0.0000092501805,0.00013587986,0.0000016548415,0.0000022695795,0.000010410806,0.0000070321075,0.9962748,0.0013413099,0.0019458741,0.00026564611,0.000003068136],"about_ca_topic_score_codex":0.0006396765,"about_ca_topic_score_gemma":0.0008033985,"teacher_disagreement_score":0.0013992818,"about_ca_system_score_codex":0.000366382,"about_ca_system_score_gemma":0.00047685375,"threshold_uncertainty_score":0.007400155},"labels":[],"label_agreement":null},{"id":"W2038304857","doi":"10.1016/j.laa.2012.04.033","title":"Sparse nonnegative matrix underapproximation and its application to hyperspectral image analysis","year":2012,"lang":"en","type":"article","venue":"Linear Algebra and its Applications","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":51,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Hyperspectral imaging; Non-negative matrix factorization; Interpretability; Principal component analysis; Dimensionality reduction; Pattern recognition (psychology); Matrix decomposition; Constraint (computer-aided design); Artificial intelligence; Matrix (chemical analysis); Mathematics; Sparse matrix; Image (mathematics); Curse of dimensionality; Sparse PCA; Computer science; Feature extraction; Nonnegative matrix; Symmetric matrix; Eigenvalues and eigenvectors","score_opus":0.01359840595848155,"score_gpt":0.2617552126817133,"score_spread":0.24815680672323176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2038304857","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005344073,0.00020622028,0.99337405,0.00021752599,0.000040612565,0.000009829067,0.00003798642,0.000114838986,0.000654792],"genre_scores_gemma":[0.36693746,0.0016936306,0.623145,0.0003925621,0.00050883257,0.0001508358,0.00057266676,0.00026420198,0.006334834],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99818367,0.0009042979,0.00007424976,0.00020175363,0.00054569414,0.000090317706],"domain_scores_gemma":[0.99279237,0.0046746642,0.00056951394,0.0007905946,0.0009864119,0.00018643119],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002400697,0.0009536162,0.0012093115,0.00087980484,0.00044230657,0.0014004903,0.0012935324,0.0011580929,0.0021513114],"category_scores_gemma":[0.01583369,0.0004372346,0.00089968985,0.0014167615,0.0015624409,0.0021319573,0.002486674,0.0021783735,0.0006086119],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038481047,0.00016969447,0.001314035,0.0003210409,0.00012030444,0.00023090256,0.0002672426,0.56539243,0.013441959,0.21315639,0.006962919,0.1982382],"study_design_scores_gemma":[0.0000034733787,0.000018206667,0.00006654459,0.0000064711235,0.000005290374,0.00004094598,0.000009843637,0.9682026,0.00085885415,0.030053657,0.0007248407,0.0000092212185],"about_ca_topic_score_codex":0.002343518,"about_ca_topic_score_gemma":0.0018110581,"teacher_disagreement_score":0.002400697,"about_ca_system_score_codex":0.00054462685,"about_ca_system_score_gemma":0.0007946342,"threshold_uncertainty_score":0.012696266},"labels":[],"label_agreement":null},{"id":"W2038552727","doi":"10.1109/igarss.2007.4423372","title":"Change detection of buildings in urban environment from high spatial resolution satellite images using existing cartographic data and prior knowledge","year":2007,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Change detection; Computer science; Process (computing); Remote sensing; Image resolution; Object detection; Spatial analysis; Computer vision; Geography; Artificial intelligence","score_opus":0.05827173070775962,"score_gpt":0.2619838098343505,"score_spread":0.20371207912659087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2038552727","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36325818,0.0007321859,0.6310755,0.00016823172,0.00003965015,0.00013515181,0.00029542134,0.0009644566,0.003331268],"genre_scores_gemma":[0.6956223,0.00077441876,0.3019371,0.00003428957,0.00003943015,0.0000401295,0.0005616479,0.000041162162,0.0009494468],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99974877,0.000032290212,0.00001332111,0.000066232715,0.000109886176,0.00002946207],"domain_scores_gemma":[0.9996593,0.000117091426,0.00006380969,0.000049034355,0.00008617468,0.000024667077],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040743055,0.00031658867,0.00040724903,0.0035819255,0.00023951894,0.00079482276,0.0003643604,0.00044039148,0.0005737331],"category_scores_gemma":[0.0009168997,0.00026679743,0.00046295824,0.001478756,0.00048018666,0.00093069236,0.0003985562,0.00029835443,0.0003173027],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023459038,0.00029960822,0.029716207,0.00041638393,0.00014456072,0.0003889636,0.00046663568,0.040740136,0.09326658,0.0025230155,0.0009597918,0.8308435],"study_design_scores_gemma":[0.0000350913,0.00026703527,0.2031722,0.000092938135,0.00028361042,0.0011111476,0.0008636099,0.70061606,0.081091985,0.0046588215,0.007717021,0.000090477355],"about_ca_topic_score_codex":0.002651004,"about_ca_topic_score_gemma":0.005391554,"teacher_disagreement_score":0.0035819255,"about_ca_system_score_codex":0.0002955505,"about_ca_system_score_gemma":0.00027187608,"threshold_uncertainty_score":0.005271077},"labels":[],"label_agreement":null},{"id":"W2038806915","doi":"10.1117/12.421120","title":"&lt;title&gt;Combination of fuzzy sets and Dempster-Shafer theories in forest map updating using multispectral data&lt;/title&gt;","year":2001,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Dempster–Shafer theory; Computer science; Multispectral image; Fuzzy set; Context (archaeology); Class (philosophy); Confusion; Fuzzy logic; Object (grammar); Artificial intelligence; Sensor fusion; Set (abstract data type); Data mining; Data set; Geography","score_opus":0.01833625143347684,"score_gpt":0.24677937899960656,"score_spread":0.22844312756612972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2038806915","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020683592,0.009391627,0.94965184,0.0022457768,0.0022700822,0.00012946967,0.00018890455,0.0007093727,0.014729261],"genre_scores_gemma":[0.30732724,0.011630049,0.6407723,0.000701259,0.002596298,0.00015648387,0.00050588755,0.00028503162,0.03602545],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99959093,0.000094737596,0.00002460377,0.00006897035,0.0002025808,0.000018249404],"domain_scores_gemma":[0.9994006,0.0002773921,0.000036432175,0.000051579133,0.00021610962,0.000017895294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011729068,0.0003195763,0.0004892824,0.0013221703,0.00029108766,0.001136156,0.000493469,0.0006629015,0.00372725],"category_scores_gemma":[0.001855663,0.00014836408,0.0004320271,0.0014571728,0.000635946,0.0018353532,0.00035161607,0.0006545603,0.0014598867],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023868348,0.00007326969,0.0019475409,0.00041896862,0.0000785962,0.00048626552,0.00020264668,0.046065796,0.011765112,0.064310946,0.027506933,0.8469053],"study_design_scores_gemma":[0.000034593104,0.00014603155,0.004756922,0.00020388367,0.00010136788,0.0005229746,0.00018208793,0.7948479,0.027911374,0.08481668,0.086334154,0.00014199845],"about_ca_topic_score_codex":0.0020778943,"about_ca_topic_score_gemma":0.002445895,"teacher_disagreement_score":0.00372725,"about_ca_system_score_codex":0.00062177045,"about_ca_system_score_gemma":0.00023447539,"threshold_uncertainty_score":0.012468934},"labels":[],"label_agreement":null},{"id":"W2040310366","doi":"10.1117/12.453858","title":"Using Kernel Principal Components for Color Image Segmentation","year":2002,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Kernel principal component analysis; Pattern recognition (psychology); Artificial intelligence; Principal component analysis; Feature vector; Kernel (algebra); Cluster analysis; Computer science; Mathematics; Computer vision; RGB color model; Kernel method; Support vector machine","score_opus":0.03329727602575075,"score_gpt":0.2535673530734288,"score_spread":0.22027007704767806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040310366","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009734249,0.00035449918,0.986642,0.000096418895,0.00003495903,0.000039340404,0.000054792476,0.0020746721,0.0009689236],"genre_scores_gemma":[0.19620436,0.0006177509,0.8002137,0.000055090735,0.000048400987,0.000098720026,0.00033057795,0.0004136209,0.00201792],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992118,0.00022762075,0.00004058171,0.00016271448,0.00027000436,0.00008720184],"domain_scores_gemma":[0.9989938,0.00037625618,0.00008584493,0.00016580499,0.00034789482,0.000030363508],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008968385,0.0010508157,0.0010927025,0.0022062548,0.00052835495,0.0016080636,0.00067910535,0.0010555736,0.0020739508],"category_scores_gemma":[0.0032231612,0.00045020122,0.00085440505,0.0025177174,0.00070449966,0.0014899068,0.00066897774,0.00085566746,0.001496322],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045977163,0.000086111424,0.0009452724,0.0001913401,0.00012573438,0.000107232525,0.00016233002,0.16778633,0.045283087,0.012046132,0.0039187614,0.7688879],"study_design_scores_gemma":[0.000013142946,0.000029669822,0.00084863475,0.000010054853,0.00002578211,0.00008340954,0.00003122517,0.97283065,0.015535219,0.0070923977,0.0034653614,0.000034462788],"about_ca_topic_score_codex":0.0057891514,"about_ca_topic_score_gemma":0.004347283,"teacher_disagreement_score":0.0057891514,"about_ca_system_score_codex":0.0008815704,"about_ca_system_score_gemma":0.0008561131,"threshold_uncertainty_score":0.011510909},"labels":[],"label_agreement":null},{"id":"W2040401776","doi":"10.1371/journal.pone.0082722","title":"Robust Spectral Clustering Using Statistical Sub-Graph Affinity Model","year":2013,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Ontario Ministry of Research and Innovation; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Cluster analysis; Spectral clustering; Pattern recognition (psychology); Computer science; Segmentation; Graph; Artificial intelligence; Image segmentation; Clustering coefficient; Noise (video); Affinity propagation; Correlation clustering; Image (mathematics); CURE data clustering algorithm; Theoretical computer science","score_opus":0.11037120908323364,"score_gpt":0.22092618478567824,"score_spread":0.1105549757024446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040401776","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013100818,0.00008525039,0.9856464,0.00005288529,0.00001087437,0.000023528724,0.000024678055,0.0002618038,0.0007937436],"genre_scores_gemma":[0.6977821,0.0003874011,0.2973148,0.00013403247,0.00006987735,0.00018889803,0.00035130055,0.00018889985,0.0035827754],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991066,0.00024595775,0.000036202906,0.00022868332,0.00030662498,0.00007596206],"domain_scores_gemma":[0.9986792,0.000526761,0.00020179931,0.00021868601,0.00031546727,0.000058035064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008381559,0.00073872594,0.0008960454,0.0014704284,0.00058449304,0.0009878502,0.0016876905,0.0011229599,0.0012079731],"category_scores_gemma":[0.0030259702,0.00043686337,0.0009246609,0.0014546196,0.0008091184,0.0017318611,0.0010210688,0.0008196009,0.00076344435],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010383805,0.000081448954,0.0011384775,0.000098770965,0.00009896746,0.00010326686,0.00017016102,0.86144656,0.013645064,0.029197033,0.0013995137,0.092516944],"study_design_scores_gemma":[0.0000015276979,0.0000076213605,0.00013579763,0.0000014674223,0.0000040736513,0.000017327759,0.000008497054,0.994518,0.00061570335,0.0044408715,0.0002438097,0.000005338015],"about_ca_topic_score_codex":0.0046309177,"about_ca_topic_score_gemma":0.004530818,"teacher_disagreement_score":0.0046309177,"about_ca_system_score_codex":0.0009365219,"about_ca_system_score_gemma":0.0008734322,"threshold_uncertainty_score":0.009207964},"labels":[],"label_agreement":null},{"id":"W2040895580","doi":"10.1109/icif.2007.4408010","title":"Change detection methodology based on region classification fusion","year":2007,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"AUG Signals (Canada)","funders":"","keywords":"Computer science; Change detection; Fusion; Data mining; Sensor fusion; Artificial intelligence; Layer (electronics); Statistical classification; Pattern recognition (psychology)","score_opus":0.20127940688722382,"score_gpt":0.3148974236725987,"score_spread":0.11361801678537489,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040895580","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009549021,0.00025102354,0.98758274,0.00004697528,0.00006681725,0.00009008513,0.000045383735,0.0011225387,0.0012455262],"genre_scores_gemma":[0.22237007,0.0003178712,0.77453685,0.000083841995,0.00011340533,0.00016421886,0.00027019708,0.00018608276,0.0019574345],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99860245,0.00016744858,0.000082856546,0.00042518516,0.00059730775,0.00012474819],"domain_scores_gemma":[0.9988619,0.00024578336,0.00015519897,0.00015661487,0.00053150347,0.000049007347],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014804214,0.00070135517,0.0011289552,0.0035794468,0.00054370466,0.0013689799,0.0013604823,0.00091822114,0.0018325505],"category_scores_gemma":[0.0024000418,0.00041317253,0.0008923579,0.0020444558,0.0006588685,0.0020618415,0.00082561385,0.00083134917,0.0012676012],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002175122,0.00012231947,0.002898548,0.00024496124,0.00012995458,0.00010838041,0.00023640064,0.02650144,0.08662745,0.007574786,0.0020935957,0.8732448],"study_design_scores_gemma":[0.000046701738,0.00035169665,0.009572756,0.00006400915,0.00022580073,0.00073249184,0.00016606749,0.818141,0.13945433,0.010436613,0.02064153,0.0001669988],"about_ca_topic_score_codex":0.001467231,"about_ca_topic_score_gemma":0.0009625839,"teacher_disagreement_score":0.0035794468,"about_ca_system_score_codex":0.0006174701,"about_ca_system_score_gemma":0.00053595623,"threshold_uncertainty_score":0.0078293085},"labels":[],"label_agreement":null},{"id":"W2041334995","doi":"10.1364/ao.45.003022","title":"Application of integrated sensing and processing decision trees for target detection and localization on digital mirror array imagery","year":2006,"lang":"en","type":"article","venue":"Applied Optics","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lockheed Martin (Canada)","funders":"","keywords":"Hyperspectral imaging; Computer science; Hadamard transform; Computer vision; Data cube; Artificial intelligence; Image processing; Remote sensing; Digital image processing; Set (abstract data type); Suite; Data set; Data processing; Pattern recognition (psychology); Optics; Data mining; Geology; Image (mathematics); Physics","score_opus":0.00651941891569049,"score_gpt":0.206025895745138,"score_spread":0.1995064768294475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041334995","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.117790185,0.000116012015,0.88007516,0.00011049755,0.000021765525,0.000050954994,0.00010282684,0.0004684228,0.0012641296],"genre_scores_gemma":[0.63147914,0.00007430267,0.3673193,0.000041491836,0.000023461516,0.00009232427,0.00020858741,0.000032803688,0.00072858157],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995425,0.000152559,0.000026519254,0.0000703188,0.0001581431,0.000050001832],"domain_scores_gemma":[0.9991266,0.00048199104,0.00007900922,0.000068532085,0.00019588885,0.000047924892],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085509894,0.0004900115,0.00043647416,0.00049005676,0.0002569197,0.00041915613,0.00044401942,0.00030395304,0.0007639115],"category_scores_gemma":[0.0022720117,0.00013292045,0.0003692202,0.0005994839,0.0002592136,0.00045555402,0.00041068273,0.00047584908,0.00015089194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040393954,0.00019352631,0.003471998,0.00011037781,0.00009362963,0.00017336605,0.00014461494,0.51829493,0.0375945,0.011341757,0.0015402174,0.42663708],"study_design_scores_gemma":[0.000008523321,0.000054192282,0.00039967897,0.000002534614,0.000010423749,0.000027093209,0.000010445024,0.988235,0.0072695664,0.0035844047,0.00039235517,0.0000058603455],"about_ca_topic_score_codex":0.0016365756,"about_ca_topic_score_gemma":0.0016543911,"teacher_disagreement_score":0.0016365756,"about_ca_system_score_codex":0.0003711704,"about_ca_system_score_gemma":0.00046757868,"threshold_uncertainty_score":0.004522264},"labels":[],"label_agreement":null},{"id":"W2041524230","doi":"10.1016/j.isprsjprs.2014.12.015","title":"A discrepancy measure for segmentation evaluation from the perspective of object recognition","year":2015,"lang":"en","type":"article","venue":"ISPRS Journal of Photogrammetry and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":58,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ministry of Natural Resources and Forestry; Ontario Forest Research Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Segmentation; Artificial intelligence; Computer science; Pattern recognition (psychology); Euclidean distance; Object (grammar); Scale-space segmentation; Measure (data warehouse); Segmentation-based object categorization; Image segmentation; Identification (biology); Workflow; Perspective (graphical); Metric (unit); Computer vision; Data mining; Engineering","score_opus":0.06243988039587603,"score_gpt":0.30076019289901595,"score_spread":0.23832031250313992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041524230","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055168927,0.0007990323,0.941181,0.000120568424,0.00008595462,0.00010254451,0.00034763617,0.0007202014,0.001474201],"genre_scores_gemma":[0.560267,0.00030415328,0.43523684,0.000082545834,0.000115127375,0.00026270666,0.0021232776,0.00035046178,0.0012578282],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9934408,0.0020265714,0.0007305244,0.00087601255,0.0026128497,0.00031318137],"domain_scores_gemma":[0.9818122,0.010508242,0.0010801483,0.0016107175,0.0043817884,0.0006069533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008367478,0.0010647684,0.0018783709,0.0056428877,0.0008581868,0.0028722112,0.0020315864,0.002392225,0.0020174312],"category_scores_gemma":[0.024252139,0.0004232841,0.0012536084,0.003334529,0.0014851466,0.002980109,0.0020802727,0.0015234164,0.0006760713],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00223618,0.00060461764,0.019539371,0.00071618694,0.00055764406,0.0003475852,0.00047386976,0.28135428,0.0547845,0.04998818,0.0066731684,0.5827245],"study_design_scores_gemma":[0.000030440338,0.00042530024,0.0039529274,0.000040835188,0.000056089677,0.00024777517,0.00008928792,0.9733017,0.009404503,0.010890859,0.0015154472,0.000044947163],"about_ca_topic_score_codex":0.0016561222,"about_ca_topic_score_gemma":0.0010553206,"teacher_disagreement_score":0.008367478,"about_ca_system_score_codex":0.0016329663,"about_ca_system_score_gemma":0.0011764286,"threshold_uncertainty_score":0.04425198},"labels":[],"label_agreement":null},{"id":"W2041553308","doi":"10.1117/12.485913","title":"Texture-based segmentation of temperate-zone woodland in panchromatic IKONOS imagery","year":2003,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Computer Research Institute of Montréal","funders":"Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Panchromatic film; Texture (cosmology); Artificial intelligence; Segmentation; Image texture; Histogram; Woodland; Standard deviation; Temperate climate; Pattern recognition (psychology); Image segmentation; Computer science; Computer vision; Mathematics; Geology; Multispectral image; Statistics; Image (mathematics); Ecology; Biology","score_opus":0.0106953993286301,"score_gpt":0.22013175220539047,"score_spread":0.20943635287676038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041553308","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9912004,0.00005822094,0.008248587,0.000010369215,0.0000019184665,0.000011207154,0.0000996316,0.000046906476,0.0003227925],"genre_scores_gemma":[0.98467386,0.000050918727,0.014683794,0.0000063609605,0.0000038068392,0.000006676536,0.00031885935,0.00002318255,0.00023268236],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99989164,0.000022084254,0.0000055981814,0.000028052586,0.000024772591,0.000027792077],"domain_scores_gemma":[0.99981827,0.000068346446,0.000027612825,0.000021073587,0.00004377874,0.000020947095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036674636,0.0002948441,0.0003055825,0.00072078896,0.00014728171,0.0003959217,0.0001950847,0.00020799789,0.00031762142],"category_scores_gemma":[0.0006661885,0.00018477716,0.00021886887,0.00043781765,0.00020809688,0.00032089767,0.00010048846,0.00011100847,0.00018457837],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017964568,0.00022525534,0.07721284,0.00021749786,0.000066773326,0.0003353292,0.00046360088,0.063798584,0.7567334,0.00028500386,0.00043434385,0.09843099],"study_design_scores_gemma":[0.000057849888,0.00037455087,0.48237088,0.00001533991,0.000113702685,0.00033786017,0.00042069217,0.35719752,0.15795115,0.000249122,0.00087270717,0.000038659244],"about_ca_topic_score_codex":0.0047162315,"about_ca_topic_score_gemma":0.0101249665,"teacher_disagreement_score":0.0047162315,"about_ca_system_score_codex":0.00016419172,"about_ca_system_score_gemma":0.00016693413,"threshold_uncertainty_score":0.009377539},"labels":[],"label_agreement":null},{"id":"W2042806874","doi":"10.1016/j.isprsjprs.2009.10.002","title":"Automatic change detection of buildings in urban environment from very high spatial resolution images using existing geodatabase and prior knowledge","year":2009,"lang":"en","type":"article","venue":"ISPRS Journal of Photogrammetry and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":223,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Change detection; Spatial database; Computer science; Segmentation; Scale (ratio); Image resolution; Knowledge base; Spatial analysis; Artificial intelligence; Remote sensing; Data mining; Computer vision; Database; Geography; Cartography","score_opus":0.025090578687344725,"score_gpt":0.24739217704084873,"score_spread":0.222301598353504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042806874","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6786375,0.00092424196,0.30704257,0.00018843074,0.0000888976,0.00024670438,0.00395353,0.004097474,0.004820691],"genre_scores_gemma":[0.8756261,0.0004251449,0.11433409,0.000044268425,0.00003721307,0.000070475704,0.007689817,0.000075280004,0.001697662],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996867,0.000023453526,0.000023002109,0.00009912128,0.00011401349,0.000053629316],"domain_scores_gemma":[0.99961793,0.00007507496,0.0000473328,0.00008394825,0.00014485106,0.000030756335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036179778,0.00038853846,0.0006099985,0.0038057086,0.00035259555,0.0008645028,0.0007501796,0.00051898597,0.00120056],"category_scores_gemma":[0.00080200454,0.0004140486,0.00050425495,0.0019833643,0.0002800638,0.0011313063,0.0006369639,0.00038530288,0.00096097065],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00053491624,0.00047355465,0.03938035,0.00029516013,0.00016764842,0.0004119575,0.00025980562,0.02563525,0.11871927,0.00077953236,0.0049420903,0.80840045],"study_design_scores_gemma":[0.00006472069,0.0001808664,0.23876444,0.00006680286,0.0003119401,0.0006646882,0.0005184583,0.68377733,0.06604161,0.0015601304,0.007981828,0.00006716781],"about_ca_topic_score_codex":0.010766183,"about_ca_topic_score_gemma":0.020942891,"teacher_disagreement_score":0.010766183,"about_ca_system_score_codex":0.00033341005,"about_ca_system_score_gemma":0.0005999311,"threshold_uncertainty_score":0.021407008},"labels":[],"label_agreement":null},{"id":"W2043755928","doi":"10.1117/12.2016135","title":"Undercomplete learned dictionaries for land cover classification in multispectral imagery of Arctic landscapes using CoSA: clustering of sparse approximations","year":2013,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"U.S. Department of Energy","keywords":"Computer science; Multispectral image; Land cover; Cluster analysis; Artificial intelligence; Field (mathematics); Remote sensing; Feature (linguistics); Feature extraction; Pattern recognition (psychology); Machine learning; Land use; Geography","score_opus":0.031042565623115078,"score_gpt":0.24452924094338185,"score_spread":0.21348667532026677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043755928","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0638592,0.00017693477,0.9341949,0.0002741256,0.00003195372,0.000041829087,0.00014610247,0.00045499523,0.00081988773],"genre_scores_gemma":[0.48554835,0.00024941677,0.5109325,0.00014561038,0.000072147974,0.00012830504,0.0009773017,0.00013864126,0.0018077627],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997212,0.000085428095,0.000018328445,0.000062243096,0.000081931,0.00003080525],"domain_scores_gemma":[0.9990741,0.0004010024,0.00013297725,0.0001734567,0.00017187098,0.000046491656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064677134,0.00042962725,0.00048831844,0.0008083682,0.00037583878,0.00071614946,0.0006961182,0.0005666993,0.00093307905],"category_scores_gemma":[0.002737278,0.0002446747,0.0005617113,0.0009155497,0.0005456972,0.00085121556,0.00062413147,0.00090511405,0.0005136085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014855745,0.0001538528,0.0029136264,0.000080917314,0.00006549941,0.000077396144,0.00021253679,0.62216496,0.0152637595,0.012465592,0.0034727242,0.34298047],"study_design_scores_gemma":[0.000002063068,0.00000679496,0.00023651478,0.000001899107,0.000001764974,0.00000690832,0.000010814116,0.99722004,0.0007790164,0.0015185477,0.00021322811,0.0000024545939],"about_ca_topic_score_codex":0.006737308,"about_ca_topic_score_gemma":0.009246868,"teacher_disagreement_score":0.006737308,"about_ca_system_score_codex":0.0006600255,"about_ca_system_score_gemma":0.0007613915,"threshold_uncertainty_score":0.0133962035},"labels":[],"label_agreement":null},{"id":"W2044238265","doi":"10.1016/j.inffus.2003.10.005","title":"Land use mapping with evidential fusion of features extracted from polarimetric synthetic aperture radar and hyperspectral imagery","year":2003,"lang":"en","type":"article","venue":"Information Fusion","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lockheed Martin (Canada); Defence Research and Development Canada","funders":"","keywords":"Hyperspectral imaging; Remote sensing; Synthetic aperture radar; Computer science; Artificial intelligence; Inverse synthetic aperture radar; Geology; Polarimetry; Radar; Pattern recognition (psychology); Radar imaging; Computer vision","score_opus":0.0095088097954964,"score_gpt":0.18736686430539956,"score_spread":0.17785805450990316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044238265","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.310309,0.0004428065,0.6836906,0.00035073556,0.00007003844,0.00006220088,0.0005848899,0.001088795,0.0034010229],"genre_scores_gemma":[0.7782329,0.00021094263,0.21924101,0.00005554326,0.000036049536,0.000033119046,0.0008466505,0.000049852515,0.0012939252],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997844,0.00004101369,0.000011930451,0.00004640011,0.00008990805,0.000026454758],"domain_scores_gemma":[0.9997354,0.000045937955,0.00005520209,0.00006539002,0.00008669489,0.000011425323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004985166,0.00040840486,0.0003738523,0.0010898017,0.0002492943,0.0007011263,0.00042164966,0.00036949644,0.0007600681],"category_scores_gemma":[0.0011667196,0.0002526635,0.00047100644,0.00093378697,0.0002707808,0.0014404936,0.0007039302,0.0004324049,0.00040125375],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055997533,0.00033942057,0.011647289,0.00017686746,0.000230647,0.00020794955,0.00032791396,0.06509902,0.20919316,0.0048670946,0.0025833738,0.7047673],"study_design_scores_gemma":[0.00007517322,0.00020654341,0.062365863,0.000030510831,0.00026013,0.00043526408,0.0001554057,0.8227931,0.09914275,0.008806226,0.0056496477,0.000079353704],"about_ca_topic_score_codex":0.0012184463,"about_ca_topic_score_gemma":0.0028978705,"teacher_disagreement_score":0.0012184463,"about_ca_system_score_codex":0.00021079321,"about_ca_system_score_gemma":0.00035904898,"threshold_uncertainty_score":0.0026364326},"labels":[],"label_agreement":null},{"id":"W2044578128","doi":"10.1117/12.892424","title":"Fast endmember extraction method using the geometry of the hyperspectral datacube","year":2011,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Space Agency","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Endmember; Hyperspectral imaging; Simplex; Data cube; Pixel; Vertex (graph theory); Computer science; Artificial intelligence; Mathematics; Combinatorics; Data mining; Theoretical computer science","score_opus":0.030330612125398816,"score_gpt":0.26251739617526537,"score_spread":0.23218678404986656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044578128","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00990532,0.0002046533,0.9875167,0.000071893526,0.000046823698,0.00006141163,0.00013766161,0.00082755095,0.0012279145],"genre_scores_gemma":[0.05598314,0.00037882695,0.9401573,0.000069700836,0.000054703905,0.00013816396,0.000818587,0.00024584652,0.0021537584],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994111,0.00006681338,0.000025619307,0.00012428455,0.00032870928,0.000043527118],"domain_scores_gemma":[0.9995327,0.00009891999,0.000057274527,0.000093458024,0.00019665141,0.000021031336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047997982,0.0012340735,0.0010203142,0.0014090448,0.0005452668,0.0009667543,0.0011194748,0.00054903707,0.0019205841],"category_scores_gemma":[0.0010721612,0.00057243067,0.0012796395,0.0009061637,0.0005167801,0.002282677,0.0017042625,0.0009557355,0.0014717921],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022486798,0.00012154573,0.0018028691,0.00038020805,0.00012702339,0.00030012566,0.0003756945,0.10593753,0.1712958,0.011906572,0.0053457636,0.70218205],"study_design_scores_gemma":[0.000028576213,0.00011778436,0.002628964,0.000036067402,0.00003598601,0.000835246,0.00019397441,0.8592703,0.10660354,0.009350044,0.020796902,0.00010259881],"about_ca_topic_score_codex":0.0015921316,"about_ca_topic_score_gemma":0.002197159,"teacher_disagreement_score":0.0019205841,"about_ca_system_score_codex":0.0004929472,"about_ca_system_score_gemma":0.0011214804,"threshold_uncertainty_score":0.0064249635},"labels":[],"label_agreement":null},{"id":"W2046357986","doi":"10.1117/12.826412","title":"&lt;title&gt;An ad-hoc approach for quality assessment of hyperspectral datacubes in target detection&lt;/title&gt;","year":2009,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Space Agency","funders":"","keywords":"Hyperspectral imaging; Computer science; Data cube; Artificial intelligence; Noise (video); Computer vision; Pattern recognition (psychology); Noise reduction; Data mining; Image (mathematics)","score_opus":0.022834529780412414,"score_gpt":0.2697846637658247,"score_spread":0.2469501339854123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046357986","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038124464,0.00019703808,0.9580095,0.000102863625,0.00009505141,0.00028988507,0.00018318354,0.0008313064,0.0021666926],"genre_scores_gemma":[0.215035,0.00020601098,0.78003186,0.00007875296,0.00006619121,0.00035617998,0.0005657789,0.00020453607,0.0034557495],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974316,0.0009531804,0.00016520661,0.00033520302,0.0010448302,0.0000700287],"domain_scores_gemma":[0.9936386,0.0018475311,0.00059178163,0.0012920221,0.0025036985,0.00012638413],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003769324,0.00061583595,0.000601737,0.0015702948,0.00047065972,0.0014889976,0.0008389042,0.00045883327,0.002305802],"category_scores_gemma":[0.006802082,0.00021851191,0.0006540402,0.00130631,0.0009764411,0.00094918004,0.0008513413,0.00059988,0.0007671147],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008880662,0.00048007534,0.008473915,0.00040120748,0.00027450916,0.00022296749,0.00024719207,0.07148412,0.16512404,0.0071740584,0.0050616176,0.7401683],"study_design_scores_gemma":[0.000076198296,0.001513861,0.017091252,0.000063409134,0.00012457366,0.00097345596,0.0003208778,0.66147274,0.29590392,0.007484963,0.014832499,0.00014215407],"about_ca_topic_score_codex":0.00074548426,"about_ca_topic_score_gemma":0.0013713764,"teacher_disagreement_score":0.003769324,"about_ca_system_score_codex":0.00093801593,"about_ca_system_score_gemma":0.00042204236,"threshold_uncertainty_score":0.019934297},"labels":[],"label_agreement":null},{"id":"W2047152380","doi":"10.1080/01431160500406888","title":"Assessment of land‐cover changes related to shrimp aquaculture using remote sensing data: a case study in the Giao Thuy District, Vietnam","year":2006,"lang":"en","type":"article","venue":"International Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":91,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Mangrove; Deforestation (computer science); Reforestation; Aquaculture; Shrimp; Land cover; Feature (linguistics); Shrimp farming; Wetland; Environmental science; Remote sensing; Land use; Geography; Environmental resource management; Ecology; Agroforestry; Computer science; Fishery; Biology","score_opus":0.03734489949515291,"score_gpt":0.3302010912201152,"score_spread":0.2928561917249623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047152380","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99963784,0.000010925056,0.000107963075,0.000014364015,6.461764e-7,0.000012913167,0.000073960735,0.0000026822065,0.00013876145],"genre_scores_gemma":[0.9991837,0.000028003438,0.00042051234,0.0000058556716,0.0000014844023,0.00000943267,0.00017601544,0.0000014058303,0.00017370486],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9997578,0.00007245194,0.000018467854,0.000041538486,0.00006161243,0.00004808844],"domain_scores_gemma":[0.9989033,0.00041672317,0.00026467853,0.000062004736,0.00024059552,0.0001127641],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005054146,0.0002529554,0.00019872386,0.000684443,0.00032278313,0.00040478085,0.0003987966,0.00028824428,0.00030854595],"category_scores_gemma":[0.0011606126,0.00018834148,0.00021383473,0.0008444231,0.00037189366,0.00025369035,0.00021074558,0.00018954727,0.00005210707],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000397136,0.0006262687,0.9147524,0.00019711896,0.00014503059,0.010670927,0.0034354038,0.02344194,0.011578245,0.00028497452,0.0005340671,0.0339364],"study_design_scores_gemma":[0.00004146643,0.00032620007,0.9479712,0.000018674526,0.000052887874,0.0013393865,0.0048737605,0.03994564,0.004490246,0.00009050366,0.0008239811,0.000026066296],"about_ca_topic_score_codex":0.13392344,"about_ca_topic_score_gemma":0.1761377,"teacher_disagreement_score":0.13392344,"about_ca_system_score_codex":0.0014842884,"about_ca_system_score_gemma":0.00059153436,"threshold_uncertainty_score":0.26628786},"labels":[],"label_agreement":null},{"id":"W2047570085","doi":"10.1364/ao.48.003967","title":"Approach to nonparametric cooperative multiband segmentation with adaptive threshold","year":2009,"lang":"en","type":"article","venue":"Applied Optics","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Segmentation; Nonparametric statistics; Computer science; Artificial intelligence; Homogeneity (statistics); Image segmentation; Scale-space segmentation; Computer vision; Pattern recognition (psychology); Segmentation-based object categorization; Image resolution; Mathematics; Statistics; Machine learning","score_opus":0.01856026190975653,"score_gpt":0.22204670565249762,"score_spread":0.2034864437427411,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047570085","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026172241,0.000058180416,0.9966288,0.000030696814,0.0000071041686,0.000009401895,0.000006262535,0.00007565656,0.0005666587],"genre_scores_gemma":[0.20942023,0.00016402455,0.78721094,0.00008739294,0.00006601171,0.00014099752,0.000071779235,0.000110020934,0.002728636],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904794,0.0002131753,0.000034979053,0.00022129042,0.00041017163,0.0000723978],"domain_scores_gemma":[0.9991078,0.0003013222,0.00008986263,0.00021109535,0.00024966386,0.00004028568],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012471878,0.0005645969,0.00066866825,0.001076374,0.0004933383,0.00082691456,0.001930281,0.0011352774,0.0012014088],"category_scores_gemma":[0.0017428858,0.0004196983,0.0007946187,0.000863275,0.0009769906,0.0012810109,0.0015179355,0.0009972611,0.0005423095],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020911572,0.00016639501,0.0013831055,0.00022220908,0.00016722128,0.0003571019,0.00064863253,0.42728078,0.12933439,0.09403292,0.0021273918,0.34407067],"study_design_scores_gemma":[0.0000063652815,0.000036049154,0.00026512457,0.0000052084465,0.000015781077,0.00011170399,0.000017495671,0.97663474,0.008468381,0.011536516,0.0028843232,0.000018346098],"about_ca_topic_score_codex":0.0011621641,"about_ca_topic_score_gemma":0.0014202393,"teacher_disagreement_score":0.001930281,"about_ca_system_score_codex":0.00069721305,"about_ca_system_score_gemma":0.0006199104,"threshold_uncertainty_score":0.0065957904},"labels":[],"label_agreement":null},{"id":"W2047698599","doi":"10.1109/igarss.2014.6947464","title":"Mathematical morphological analysis of typical cyclone eyes on ocean SAR","year":2014,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Space Agency; National Aeronautics and Space Administration","keywords":"Synthetic aperture radar; Tropical cyclone; Pruning; Remote sensing; Geology; Mathematical morphology; Backscatter (email); Computer science; Meteorology; Geography; Artificial intelligence; Climatology; Image processing; Image (mathematics)","score_opus":0.015416322568908816,"score_gpt":0.233267933554692,"score_spread":0.21785161098578318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047698599","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70204824,0.0002633352,0.2928192,0.000075483,0.000020427335,0.000057689784,0.00027470491,0.00024073634,0.004200146],"genre_scores_gemma":[0.8834923,0.0006240976,0.11344927,0.000016381191,0.000027308612,0.000032147993,0.0006313928,0.00007702693,0.0016501555],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9998977,0.0000151354625,0.000008932214,0.000021721607,0.00004080029,0.00001573671],"domain_scores_gemma":[0.999602,0.00013073484,0.00009024718,0.000058022586,0.00010371064,0.000015314383],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003036909,0.00029830835,0.00018477117,0.0012892847,0.00014582057,0.0008112627,0.00021169696,0.00019316215,0.0008058824],"category_scores_gemma":[0.000841002,0.00013561825,0.00039851668,0.0007879265,0.0003443023,0.00037175862,0.00031920665,0.00019090471,0.00024047842],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033776282,0.00007257278,0.018404027,0.0004264782,0.000085955515,0.0012692563,0.00065305975,0.12457068,0.35625774,0.013768329,0.0014162556,0.48273784],"study_design_scores_gemma":[0.000012708325,0.00013330491,0.08879187,0.00006401666,0.000053270454,0.0013546791,0.00031877143,0.83727115,0.06291281,0.00397035,0.0050663743,0.00005066357],"about_ca_topic_score_codex":0.00062622287,"about_ca_topic_score_gemma":0.0008684778,"teacher_disagreement_score":0.0012892847,"about_ca_system_score_codex":0.00014210383,"about_ca_system_score_gemma":0.00021548211,"threshold_uncertainty_score":0.0026959777},"labels":[],"label_agreement":null},{"id":"W2050635843","doi":"10.1117/12.689113","title":"Spectral angle mapper based assessment of detectability of man-made targets from hyperspectral imagery after SNR enhancement","year":2006,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Defence Research and Development Canada; Canadian Space Agency","funders":"","keywords":"Hyperspectral imaging; Remote sensing; Data set; Computer science; Set (abstract data type); Image resolution; Artificial intelligence; Full spectral imaging; Signal-to-noise ratio (imaging); Computer vision; Noise (video); Near-infrared spectroscopy; Pattern recognition (psychology); Image (mathematics); Geology; Optics; Physics; Telecommunications","score_opus":0.007979203837288206,"score_gpt":0.22095282371331426,"score_spread":0.21297361987602606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050635843","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9464231,0.00015080457,0.051656865,0.000025398012,0.00001102328,0.000020284931,0.00010966486,0.00020877905,0.0013940647],"genre_scores_gemma":[0.9613374,0.00016413644,0.03706655,0.000030511324,0.0000127793555,0.000020709202,0.00039490635,0.000043472333,0.00092940504],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997329,0.000047023233,0.000015361635,0.000055647855,0.00012390768,0.000025141271],"domain_scores_gemma":[0.99908686,0.00043420077,0.00013360716,0.000069384325,0.00023183803,0.000044042165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005948702,0.0003843749,0.0002359749,0.00055874645,0.00010547784,0.00030415508,0.00016666105,0.00028223553,0.0010734152],"category_scores_gemma":[0.0019247092,0.00013023942,0.00020341185,0.00021884176,0.00027306977,0.0006596533,0.00028201338,0.00022574478,0.00045387074],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007692819,0.000062351144,0.0135231335,0.0000903948,0.000052052485,0.0001226036,0.000105342115,0.004461251,0.93963474,0.00010267171,0.00007315181,0.041002907],"study_design_scores_gemma":[0.0000151311415,0.00049954344,0.10104559,0.0000084410785,0.00011364852,0.0006196423,0.00012160097,0.039904676,0.8564614,0.000175832,0.0010055472,0.00002887032],"about_ca_topic_score_codex":0.0002639941,"about_ca_topic_score_gemma":0.00046992698,"teacher_disagreement_score":0.0010734152,"about_ca_system_score_codex":0.00009416987,"about_ca_system_score_gemma":0.0000654368,"threshold_uncertainty_score":0.0035909414},"labels":[],"label_agreement":null},{"id":"W2051197289","doi":"10.1109/cvrs.2012.6421273","title":"Hyperspectral image classification with SVM-based domain adaption classifiers","year":2012,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Università degli Studi di Pavia; University of Chinese Academy of Sciences; Purdue University","keywords":"Hyperspectral imaging; Support vector machine; Pattern recognition (psychology); Artificial intelligence; Computer science; Kernel (algebra); Classifier (UML); Contextual image classification; Image (mathematics); Domain (mathematical analysis); Mathematics","score_opus":0.02033984252764886,"score_gpt":0.2208007194987851,"score_spread":0.20046087697113624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051197289","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022458035,0.00015852769,0.97605294,0.00007628522,0.000026315589,0.000027227272,0.00003109971,0.00063444645,0.0005351391],"genre_scores_gemma":[0.5737361,0.00021932574,0.42288142,0.00012811949,0.00008629207,0.00013766282,0.00034351516,0.000098819495,0.002368638],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993486,0.00021008149,0.00004919469,0.00014046778,0.00020573149,0.000045901397],"domain_scores_gemma":[0.9990951,0.0002584904,0.00013169978,0.0001516775,0.00033739556,0.000025573961],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012066247,0.000546006,0.0008188487,0.00065576355,0.00022362053,0.0007043462,0.0009006011,0.0008602902,0.0007232802],"category_scores_gemma":[0.002268588,0.00029450192,0.0007629072,0.0007251598,0.00039753583,0.0013067693,0.0008817968,0.0012812988,0.000652908],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026340786,0.00026513185,0.0019803843,0.00010741598,0.00014026985,0.0000844878,0.00009053212,0.429015,0.036263593,0.006053457,0.0031119708,0.5226244],"study_design_scores_gemma":[0.0000025489358,0.000014553118,0.00018015961,0.0000021133212,0.0000036653637,0.000016429025,0.0000036688436,0.9966654,0.0020656702,0.00080882275,0.0002326581,0.000004299752],"about_ca_topic_score_codex":0.00063366,"about_ca_topic_score_gemma":0.0005700858,"teacher_disagreement_score":0.0012066247,"about_ca_system_score_codex":0.00028833057,"about_ca_system_score_gemma":0.0003395356,"threshold_uncertainty_score":0.0063812733},"labels":[],"label_agreement":null},{"id":"W2051440202","doi":"10.1080/01431161.2014.978035","title":"Land-use and land-cover classification in semi-arid regions using independent component analysis (ICA) and expert classification","year":2014,"lang":"en","type":"article","venue":"International Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Land cover; Thematic Mapper; Thematic map; Watershed; Remote sensing; Cohen's kappa; Vegetation (pathology); Land use; Arid; Arable land; Preprocessor; Environmental science; Cartography; Geography; Computer science; Satellite imagery; Artificial intelligence; Statistics; Mathematics; Geology; Agriculture","score_opus":0.04407450553201075,"score_gpt":0.27924470252677597,"score_spread":0.2351701969947652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051440202","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47979784,0.00029047194,0.513435,0.00014201344,0.00005252619,0.00023768446,0.0003368513,0.00091323064,0.0047944146],"genre_scores_gemma":[0.7798248,0.00014683645,0.21814823,0.00003197099,0.000023877688,0.00010836069,0.00051943184,0.000036941776,0.0011596057],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9994808,0.0001876861,0.0000363335,0.00011361558,0.00013319196,0.000048418777],"domain_scores_gemma":[0.9995584,0.00016561983,0.00004036847,0.00004130919,0.00017329438,0.00002098351],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009790605,0.00040597742,0.00028966554,0.0018864351,0.00029807893,0.00066584983,0.00030848655,0.00028121486,0.00068104523],"category_scores_gemma":[0.001706053,0.00012103162,0.00035891347,0.001071766,0.00027790747,0.0005546504,0.0003430129,0.00026050987,0.0002447853],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018742858,0.00032532375,0.0634846,0.0001621643,0.00016470169,0.00017301526,0.0004635636,0.05403109,0.01814172,0.0032146622,0.0025772303,0.8570745],"study_design_scores_gemma":[0.000019559347,0.00008533401,0.12564516,0.000028558055,0.000067270375,0.000114908544,0.00047149445,0.8585383,0.0090996465,0.0032363185,0.0026385346,0.000054831697],"about_ca_topic_score_codex":0.009520696,"about_ca_topic_score_gemma":0.015497486,"teacher_disagreement_score":0.009520696,"about_ca_system_score_codex":0.00040166956,"about_ca_system_score_gemma":0.0005828414,"threshold_uncertainty_score":0.018930614},"labels":[],"label_agreement":null},{"id":"W2051878103","doi":"10.1080/01431161.2011.572093","title":"A change detection measure based on a likelihood ratio and statistical properties of SAR intensity images","year":2011,"lang":"en","type":"article","venue":"Remote Sensing Letters","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"China Scholarship Council","keywords":"Change detection; Measure (data warehouse); Histogram; Synthetic aperture radar; Computer science; Likelihood-ratio test; Detector; Artificial intelligence; Intensity (physics); Pattern recognition (psychology); Statistics; Image (mathematics); Data mining; Mathematics; Optics; Physics; Telecommunications","score_opus":0.04266488147491038,"score_gpt":0.20192387894872982,"score_spread":0.15925899747381944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051878103","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08813685,0.00070465467,0.90703183,0.00045157716,0.00010757142,0.00007873021,0.00012364096,0.0006440973,0.0027211262],"genre_scores_gemma":[0.7859527,0.00035686465,0.21182375,0.00017674018,0.0003022574,0.00011236733,0.00028738257,0.00013452508,0.0008534725],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99762315,0.00065519905,0.00017552964,0.00049180177,0.00095555536,0.00009879374],"domain_scores_gemma":[0.98984855,0.0060910457,0.0015086327,0.0005803653,0.0016989551,0.00027253755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030780036,0.0005418037,0.00069983624,0.0039507793,0.00037069127,0.001858946,0.0007936387,0.0010604423,0.0013436703],"category_scores_gemma":[0.018978965,0.00030912572,0.00076457247,0.0017356557,0.001827815,0.0038366967,0.00072728755,0.00089980086,0.00061111484],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010795628,0.00037379086,0.048168246,0.00070756016,0.00051447266,0.001253212,0.0007374469,0.13579594,0.15404318,0.07021062,0.00505888,0.5820571],"study_design_scores_gemma":[0.00007541387,0.0006061209,0.05313046,0.0000738963,0.00016893863,0.0030599646,0.00023545956,0.8452715,0.06182796,0.029268371,0.0060227476,0.00025913547],"about_ca_topic_score_codex":0.0004587863,"about_ca_topic_score_gemma":0.00035927942,"teacher_disagreement_score":0.0039507793,"about_ca_system_score_codex":0.00081360765,"about_ca_system_score_gemma":0.00033464815,"threshold_uncertainty_score":0.016278207},"labels":[],"label_agreement":null},{"id":"W2054260492","doi":"10.1109/icif.2007.4408172","title":"Automated learning multi-criteria classifiers for FLIR ship imagery classification","year":2007,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Defence Research and Development Canada","funders":"","keywords":"Artificial intelligence; Computer science; Random subspace method; Naive Bayes classifier; Machine learning; Statistical classification; Pattern recognition (psychology); Data mining; Support vector machine","score_opus":0.05527929841485289,"score_gpt":0.3142312569847577,"score_spread":0.25895195856990477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054260492","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023778727,0.00019243266,0.9747338,0.00008205098,0.000016467497,0.00007243826,0.0000312161,0.00035583452,0.0007369916],"genre_scores_gemma":[0.45345452,0.000098253346,0.5450468,0.00008541358,0.000052433625,0.00020900789,0.00015814071,0.00007399299,0.00082145556],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969214,0.0014446854,0.00016946513,0.00039496704,0.0009347777,0.00013464926],"domain_scores_gemma":[0.9918956,0.0053650723,0.0007085658,0.00043552928,0.001481604,0.000113625974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046637636,0.0008737343,0.0011210932,0.0029303674,0.0006496784,0.0010947806,0.0014573226,0.001176399,0.0009683214],"category_scores_gemma":[0.013071253,0.00037751466,0.0007602615,0.0013322606,0.0007490673,0.0011737869,0.0006895376,0.0010657716,0.00038900838],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009881648,0.0001795823,0.0041189073,0.00012505341,0.000115479925,0.000082065235,0.00018110959,0.56535745,0.0057075717,0.005311249,0.0010186743,0.41770405],"study_design_scores_gemma":[0.000007641344,0.000029056831,0.0005308841,0.000008148207,0.000007459423,0.00001949002,0.00001330995,0.9953035,0.0015667236,0.0022501675,0.0002537198,0.000009885674],"about_ca_topic_score_codex":0.003730492,"about_ca_topic_score_gemma":0.0028435627,"teacher_disagreement_score":0.0046637636,"about_ca_system_score_codex":0.001009321,"about_ca_system_score_gemma":0.0009255829,"threshold_uncertainty_score":0.02466464},"labels":[],"label_agreement":null},{"id":"W2055149942","doi":"10.1109/jstars.2014.2344017","title":"Unsupervised Change Detection in Multitemporal SAR Images Over Large Urban Areas","year":2014,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":94,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Swedish National Space Agency","keywords":"Thresholding; Histogram; Artificial intelligence; Synthetic aperture radar; Balanced histogram thresholding; Change detection; Pixel; Pattern recognition (psychology); Image histogram; Computer science; Histogram matching; Computer vision; Mathematics; Image segmentation; Image (mathematics); Image texture","score_opus":0.024555120849533704,"score_gpt":0.22406208482265486,"score_spread":0.19950696397312115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055149942","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79999006,0.00022414628,0.19720516,0.000088626424,0.0000163014,0.00006919778,0.00014216725,0.0010519546,0.0012123933],"genre_scores_gemma":[0.9242594,0.00012696609,0.074533954,0.00003502583,0.000022523183,0.000027655233,0.00035559092,0.00006246376,0.00057650823],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999711,0.00005359442,0.0000135988985,0.0000836463,0.00009371328,0.000044451674],"domain_scores_gemma":[0.9995627,0.00014441699,0.00010525294,0.000054655513,0.00009877805,0.000034279412],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004195733,0.0004229679,0.0004569856,0.0022606796,0.0002498099,0.0004868335,0.00040336847,0.00035598627,0.0003063009],"category_scores_gemma":[0.0007834951,0.00025146498,0.00035280705,0.0011207728,0.0003809059,0.0005217338,0.00036150683,0.00027052892,0.0001542142],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007232267,0.00046505642,0.03845142,0.0002073196,0.00019787291,0.0007851921,0.0005024137,0.098238826,0.30711204,0.0011313994,0.0015330932,0.5506521],"study_design_scores_gemma":[0.00002243794,0.0001478216,0.12358071,0.000010869615,0.00007690571,0.0004956402,0.00034324205,0.8094591,0.0635375,0.0011176761,0.0011757598,0.000032335105],"about_ca_topic_score_codex":0.0021978144,"about_ca_topic_score_gemma":0.0059911874,"teacher_disagreement_score":0.0022606796,"about_ca_system_score_codex":0.00027292792,"about_ca_system_score_gemma":0.00022972608,"threshold_uncertainty_score":0.0043700337},"labels":[],"label_agreement":null},{"id":"W2056289506","doi":"10.1080/0143116042000298220","title":"Comparison of function‐ and structure‐based schemes for classification of remotely sensed data","year":2005,"lang":"en","type":"article","venue":"International Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; York University","funders":"Universitas Sam Ratulangi","keywords":"Thematic map; Multispectral image; Computer science; Class (philosophy); Remote sensing; Land cover; Classification scheme; Watershed; Function (biology); Data mining; Pattern recognition (psychology); Geography; Artificial intelligence; Land use; Cartography; Machine learning; Ecology","score_opus":0.07598598703332751,"score_gpt":0.3455163693930938,"score_spread":0.26953038235976634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056289506","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8133022,0.0005758665,0.17905185,0.00035727714,0.0000542297,0.00052599417,0.0007455042,0.00051973277,0.0048673498],"genre_scores_gemma":[0.9112559,0.00014782819,0.087198876,0.00003739479,0.000015986212,0.00013543504,0.00071789714,0.000045269455,0.0004453849],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99467826,0.0025792276,0.00039913485,0.0003628177,0.0017549086,0.00022573218],"domain_scores_gemma":[0.97511363,0.017157292,0.0012922226,0.0024460566,0.0037007637,0.00029000116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013745934,0.00044064302,0.00041156044,0.0041112974,0.00043259579,0.0017557917,0.0006240639,0.0006031426,0.0008788866],"category_scores_gemma":[0.031182658,0.00019131141,0.000627621,0.0019464382,0.0006940736,0.0021532478,0.00074935256,0.00056001294,0.00036260302],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018245451,0.0004030482,0.1778554,0.000526285,0.0006213631,0.00008069964,0.0018017379,0.0680932,0.01644465,0.01221579,0.0020126943,0.71812046],"study_design_scores_gemma":[0.00017771818,0.0010495173,0.25962028,0.00019612604,0.000329467,0.000226181,0.0013238243,0.7026771,0.018980399,0.010380525,0.0048817727,0.00015715076],"about_ca_topic_score_codex":0.0026160008,"about_ca_topic_score_gemma":0.003472964,"teacher_disagreement_score":0.013745934,"about_ca_system_score_codex":0.0013421375,"about_ca_system_score_gemma":0.00069209107,"threshold_uncertainty_score":0.07269633},"labels":[],"label_agreement":null},{"id":"W2057768602","doi":"10.1117/12.865035","title":"Correction of cardinal effects in high resolution SAR imagery","year":2010,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Effigis (Canada); École de Technologie Supérieure","funders":"Canadian Space Agency; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Computer science; Obstacle; Remote sensing; Azimuth; Position (finance); Artificial intelligence; Pixel; Computer vision; Orientation (vector space); Aerial imagery; Synthetic aperture radar; Radar imaging; Geology; Radar; Geography; Telecommunications; Mathematics; Geometry","score_opus":0.007228767468959866,"score_gpt":0.21232018279879583,"score_spread":0.20509141532983596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2057768602","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44335124,0.0017071366,0.5464745,0.0002671858,0.00023370124,0.00012832471,0.00052804645,0.0029638398,0.0043459786],"genre_scores_gemma":[0.76764274,0.0008526507,0.2276149,0.00007953785,0.000064992535,0.000040888295,0.00096767745,0.00024970583,0.002486957],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998806,0.00027044016,0.0000767377,0.00023037462,0.000479121,0.00013733697],"domain_scores_gemma":[0.99712163,0.00056726916,0.00049167173,0.0010245667,0.0006490024,0.00014582256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017778254,0.00087695214,0.0005766818,0.0013342693,0.00049481425,0.0011470508,0.0008423654,0.0005365829,0.0013631397],"category_scores_gemma":[0.0043803523,0.000647955,0.00045167303,0.0017104921,0.0006465412,0.0012199768,0.0012431879,0.0014112425,0.00075978966],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011891297,0.0003840458,0.07315851,0.0007827368,0.0002968781,0.000790768,0.00073992915,0.079795696,0.3907424,0.006494391,0.005528849,0.44009665],"study_design_scores_gemma":[0.00012020305,0.00046396643,0.18416636,0.00013803736,0.0003133623,0.002672713,0.000589258,0.52338845,0.27087173,0.0051864516,0.011882536,0.00020695652],"about_ca_topic_score_codex":0.0021084675,"about_ca_topic_score_gemma":0.0055362307,"teacher_disagreement_score":0.0021084675,"about_ca_system_score_codex":0.0002866966,"about_ca_system_score_gemma":0.0008480327,"threshold_uncertainty_score":0.009402156},"labels":[],"label_agreement":null},{"id":"W2058533675","doi":"10.1016/j.cageo.2004.10.003","title":"A semi-automatic segmentation procedure for feature extraction in remotely sensed imagery","year":2004,"lang":"en","type":"article","venue":"Computers & Geosciences","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":51,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Resources Canada","funders":"Canadian Forest Service; Chinese Academy of Sciences; Government of Ontario","keywords":"Computer science; Thresholding; Artificial intelligence; Computer vision; Feature extraction; Sample (material); Feature (linguistics); Remote sensing; Segmentation; Edge detection; Image segmentation; Pattern recognition (psychology); Software; Image processing; Image (mathematics); Geology","score_opus":0.014994519292096739,"score_gpt":0.25696013939473944,"score_spread":0.2419656201026427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058533675","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006404798,0.00012590512,0.9890894,0.000033105545,0.000044918637,0.000117226606,0.0002562365,0.0033763293,0.0005520199],"genre_scores_gemma":[0.031993583,0.0001394629,0.9638018,0.000056092947,0.00004046613,0.00024309404,0.0012277571,0.0005413338,0.001956456],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993718,0.00006746151,0.000052087973,0.00018755381,0.00024499523,0.00007616948],"domain_scores_gemma":[0.99907565,0.00029590985,0.00007891076,0.00016771528,0.00034472425,0.00003705039],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006163403,0.0010962286,0.0012697702,0.0023521183,0.0010965844,0.0011902099,0.0013495133,0.0010928758,0.0042396844],"category_scores_gemma":[0.0014189483,0.0008540233,0.0013409895,0.0023524226,0.00070148555,0.000891975,0.0009146098,0.0010710771,0.003384642],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016079712,0.00015315911,0.0005814407,0.00025943853,0.00008168814,0.0001405057,0.00018599856,0.010398222,0.24413906,0.0028943885,0.006139598,0.73486567],"study_design_scores_gemma":[0.000083419465,0.00033372495,0.015244303,0.00007774933,0.00023072006,0.0011221094,0.00018319208,0.6446625,0.28856394,0.011297078,0.03798765,0.00021363815],"about_ca_topic_score_codex":0.0049371393,"about_ca_topic_score_gemma":0.009249218,"teacher_disagreement_score":0.0049371393,"about_ca_system_score_codex":0.0004419945,"about_ca_system_score_gemma":0.0017521514,"threshold_uncertainty_score":0.014183164},"labels":[],"label_agreement":null},{"id":"W2058840065","doi":"10.1109/jstars.2014.2336236","title":"Fast and Efficient Evaluation of Building Damage From Very High Resolution Optical Satellite Images","year":2014,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Computer vision; Satellite; Satellite image; Image resolution; Classifier (UML); Scale (ratio); Remote sensing; Pattern recognition (psychology); Geology; Cartography; Geography; Engineering","score_opus":0.02236946444668536,"score_gpt":0.2331079750206208,"score_spread":0.21073851057393544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058840065","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5573034,0.00058128854,0.433402,0.000104439176,0.000059592323,0.0002453976,0.0011494493,0.004007278,0.003147044],"genre_scores_gemma":[0.80732805,0.00033847315,0.18779676,0.000038803086,0.00004785121,0.000105258354,0.0022700415,0.00014667457,0.0019280665],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994172,0.00005979002,0.000026125259,0.000082941064,0.0003503905,0.00006362855],"domain_scores_gemma":[0.99903,0.00022343545,0.00018425718,0.00014087731,0.00035866443,0.00006274454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057748926,0.00061407295,0.00059023657,0.0026723756,0.00021701532,0.0007238108,0.00051302015,0.0006027521,0.0013425958],"category_scores_gemma":[0.0015073057,0.00020187693,0.00033906492,0.00094288675,0.00022378606,0.0009394935,0.0005143539,0.000345744,0.0011877861],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005674491,0.00039506203,0.03771438,0.00029901095,0.00015248788,0.00020138864,0.00009906814,0.033568513,0.19765648,0.00043636397,0.0027743848,0.72613543],"study_design_scores_gemma":[0.00002838211,0.00043520314,0.1568819,0.000032682317,0.000079411184,0.00058791914,0.00021047838,0.73078644,0.107758075,0.0007156664,0.002434056,0.000049832826],"about_ca_topic_score_codex":0.0015203021,"about_ca_topic_score_gemma":0.0036640654,"teacher_disagreement_score":0.0026723756,"about_ca_system_score_codex":0.00027013305,"about_ca_system_score_gemma":0.0003033445,"threshold_uncertainty_score":0.0044914484},"labels":[],"label_agreement":null},{"id":"W2059392322","doi":"10.1016/j.jag.2013.09.007","title":"A spatial–spectral approach for deriving high signal quality eigenvectors for remote sensing image transformations","year":2013,"lang":"en","type":"article","venue":"International Journal of Applied Earth Observation and Geoinformation","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Česká geologická služba","keywords":"Hyperspectral imaging; Decorrelation; Eigenvalues and eigenvectors; Noise (video); Transformation (genetics); Data set; Set (abstract data type); Computer science; Mathematics; SIGNAL (programming language); Algorithm; Pattern recognition (psychology); Artificial intelligence; Image (mathematics); Remote sensing; Geography; Physics","score_opus":0.021791278580440214,"score_gpt":0.2396908746339343,"score_spread":0.21789959605349407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059392322","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00407948,0.000049629725,0.9950718,0.00003213888,0.0000117821255,0.000018490053,0.000029853658,0.00017807921,0.0005286809],"genre_scores_gemma":[0.09160139,0.00020994617,0.90479314,0.00004714093,0.000049604198,0.0000729833,0.00028519012,0.000190074,0.0027505101],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994809,0.00012614297,0.000033261498,0.00008663869,0.0002343,0.000038807793],"domain_scores_gemma":[0.9992042,0.00020885265,0.000071731505,0.00012282193,0.00035635632,0.000036003566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073521544,0.0007935423,0.00038331444,0.0013922831,0.00048572128,0.0008288508,0.000646812,0.0005900878,0.0033787538],"category_scores_gemma":[0.0021036072,0.000333983,0.00081659056,0.001323582,0.0006112981,0.00090187805,0.0009116026,0.0008290996,0.0016907203],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017121164,0.00028277363,0.0010509451,0.000215958,0.00012128457,0.00014501098,0.00015191978,0.09930033,0.16536534,0.029546285,0.002903488,0.70074546],"study_design_scores_gemma":[0.000015804724,0.00009060769,0.0017985515,0.000013684283,0.000045333774,0.0001658943,0.00006472667,0.95445883,0.025587048,0.01237844,0.0053463057,0.000034808436],"about_ca_topic_score_codex":0.002415296,"about_ca_topic_score_gemma":0.004254452,"teacher_disagreement_score":0.0033787538,"about_ca_system_score_codex":0.00024228504,"about_ca_system_score_gemma":0.00076534005,"threshold_uncertainty_score":0.011303067},"labels":[],"label_agreement":null},{"id":"W2060106671","doi":"10.1109/whispers.2012.6874227","title":"Spectral mixture analysis of hyperspectral data using Genetic Algorithm and Spectral Angle Constraint (GA-SAC)","year":2012,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Hyperspectral imaging; Cuprite; Genetic algorithm; Constraint (computer-aided design); Set (abstract data type); Data set; Algorithm; Noise (video); Computer science; Mathematics; Artificial intelligence; Image (mathematics); Mathematical optimization; Chemistry","score_opus":0.03723358347481041,"score_gpt":0.2609504941243948,"score_spread":0.2237169106495844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060106671","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031142265,0.00007455117,0.96741843,0.00005167423,0.000016563112,0.00003662924,0.000028765922,0.00053827895,0.00069283537],"genre_scores_gemma":[0.3311789,0.000087564964,0.666957,0.000058973696,0.000018896173,0.00013418071,0.00026008108,0.00013806205,0.0011663553],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995005,0.00012806623,0.000022081176,0.00010197572,0.00020208454,0.000045257966],"domain_scores_gemma":[0.99901223,0.00049499393,0.00010258933,0.00006579544,0.00029657222,0.000027911186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010321558,0.00082832255,0.00072326773,0.0012142863,0.00042474226,0.0006194191,0.0008493621,0.0006455591,0.00068911223],"category_scores_gemma":[0.0027577353,0.0003627593,0.0007316439,0.0011859903,0.00047660287,0.00079889473,0.00068309536,0.00076680706,0.0001970993],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011114968,0.00007665148,0.0019539008,0.000048188547,0.00010465822,0.00003681526,0.00008656691,0.81345844,0.0097015,0.0040915255,0.00056497514,0.16976567],"study_design_scores_gemma":[0.000004742189,0.000013455777,0.00024592888,0.0000022966658,0.0000066191774,0.000010281189,0.0000054936536,0.99761546,0.0013131853,0.0005753713,0.00020142987,0.0000056444146],"about_ca_topic_score_codex":0.009949454,"about_ca_topic_score_gemma":0.0084201405,"teacher_disagreement_score":0.009949454,"about_ca_system_score_codex":0.00065468386,"about_ca_system_score_gemma":0.0010981429,"threshold_uncertainty_score":0.01978308},"labels":[],"label_agreement":null},{"id":"W2060590382","doi":"10.1117/1.jrs.6.063597","title":"Supervised machine learning of fused RADAR and optical data for land cover classification","year":2012,"lang":"en","type":"article","venue":"Journal of Applied Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Space Agency; University of California, Irvine; George Mason University","keywords":"Remote sensing; Decision tree; Land cover; Artificial intelligence; Radar; Computer science; Radiometer; Synthetic aperture radar; Machine learning; Decision tree learning; Contextual image classification; Support vector machine; Statistical classification; Geology; Land use; Engineering","score_opus":0.04078477032613125,"score_gpt":0.2569598689022386,"score_spread":0.21617509857610734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060590382","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41424242,0.00041836474,0.5793652,0.00029430247,0.00013153488,0.0002758061,0.00075565366,0.0019595996,0.0025572174],"genre_scores_gemma":[0.81826234,0.00007756613,0.17908704,0.00007098312,0.0000711922,0.00023313364,0.0012498224,0.000034321165,0.00091352715],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982515,0.0008555743,0.00013337584,0.0002471596,0.00039580188,0.0001165708],"domain_scores_gemma":[0.9938591,0.003442737,0.0005133941,0.0008087124,0.0012441857,0.00013191275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034221576,0.00074396445,0.0009759017,0.0011670275,0.0004078432,0.0006309556,0.0011022262,0.00075346197,0.0009844908],"category_scores_gemma":[0.008695603,0.00028996784,0.0007135124,0.0010153551,0.0003966852,0.0009845195,0.00057735306,0.0008494706,0.00056321564],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007191344,0.0012896954,0.015917482,0.00024005506,0.00028829585,0.00016202465,0.0002288569,0.4806359,0.012582821,0.0028901873,0.0040024673,0.48104313],"study_design_scores_gemma":[0.000015177396,0.00007358228,0.0014398759,0.0000070406313,0.000011510589,0.00001774189,0.000019988074,0.99370545,0.0030506907,0.0014107091,0.00024065551,0.0000075052703],"about_ca_topic_score_codex":0.0018237351,"about_ca_topic_score_gemma":0.0023702395,"teacher_disagreement_score":0.0034221576,"about_ca_system_score_codex":0.00057165284,"about_ca_system_score_gemma":0.00083401595,"threshold_uncertainty_score":0.018098295},"labels":[],"label_agreement":null},{"id":"W2067927985","doi":"10.1117/12.487139","title":"Wavelet-based image target detection methods","year":2003,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Military College of Canada","funders":"","keywords":"Wavelet; Artificial intelligence; Computer science; Wavelet transform; Computer vision; Pattern recognition (psychology); Image (mathematics); Image processing","score_opus":0.01337888019217433,"score_gpt":0.24938149365514475,"score_spread":0.2360026134629704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067927985","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011942319,0.00075244886,0.9965654,0.00004628081,0.000047223464,0.000025014528,0.00003534214,0.00028812382,0.0010460794],"genre_scores_gemma":[0.05958418,0.00455002,0.9266763,0.00014748638,0.0002072251,0.00013360879,0.00043515957,0.00022114732,0.008044954],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990238,0.00013100346,0.000056306606,0.00017873463,0.0005533275,0.000056832607],"domain_scores_gemma":[0.9993093,0.00022927747,0.000068509326,0.000099577774,0.00026892923,0.000024367653],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012016388,0.00097632577,0.0011276556,0.002064413,0.00031309784,0.0012421717,0.0016653374,0.0010144453,0.0029175053],"category_scores_gemma":[0.0023720239,0.00046971045,0.00080591347,0.0019909153,0.0005577868,0.0015851952,0.0010686655,0.0012764217,0.0029786627],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008903299,0.00007617574,0.00047781234,0.0004796987,0.00009096928,0.00007546309,0.000097502394,0.04852165,0.035622295,0.031093469,0.0057567684,0.8776192],"study_design_scores_gemma":[0.000024272076,0.000081556485,0.00092111604,0.00006996856,0.000058021247,0.00037920722,0.0000441602,0.91831386,0.029515054,0.018653974,0.03189389,0.000044990567],"about_ca_topic_score_codex":0.00080820866,"about_ca_topic_score_gemma":0.00066915783,"teacher_disagreement_score":0.0029175053,"about_ca_system_score_codex":0.00042397005,"about_ca_system_score_gemma":0.00043118082,"threshold_uncertainty_score":0.009760022},"labels":[],"label_agreement":null},{"id":"W2068287383","doi":"10.1117/12.463106","title":"&lt;title&gt;Extraction of object skeletons in multispectral imagery by the orthogonal regression fitting&lt;/title&gt;","year":2003,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec","funders":"","keywords":"Artificial intelligence; Piecewise; Cluster analysis; Pattern recognition (psychology); Computer science; Topological skeleton; Mathematics; Image segmentation; Graph; Segmentation; Computer vision; Combinatorics; Active shape model","score_opus":0.010248294593413617,"score_gpt":0.234863884996186,"score_spread":0.22461559040277237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068287383","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02152055,0.0018827352,0.9066074,0.0012783534,0.0028551233,0.00036333382,0.002800525,0.015330889,0.047361095],"genre_scores_gemma":[0.10865052,0.0025600675,0.65446424,0.00043232917,0.0012374815,0.00031192318,0.012828055,0.005211853,0.21430352],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997137,0.00002634114,0.000015943162,0.00006253614,0.0001650484,0.000016319813],"domain_scores_gemma":[0.99936825,0.00009153617,0.000059449485,0.0001420578,0.00030109566,0.000037624126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004122802,0.0006486681,0.0006702013,0.001912561,0.00037435157,0.0010598904,0.0007589402,0.00068973936,0.03907079],"category_scores_gemma":[0.001177182,0.00031927117,0.000604317,0.0015374332,0.000470257,0.0011875281,0.0004722452,0.00059801637,0.023797791],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029435108,0.00009048714,0.0007086427,0.00045353,0.00003458495,0.00050319056,0.00006564348,0.015577611,0.12281475,0.014964946,0.09561253,0.74887973],"study_design_scores_gemma":[0.00006939706,0.0003102935,0.009319927,0.00012599485,0.000054532335,0.00147374,0.000078331344,0.339674,0.2533397,0.016109332,0.3792983,0.00014647095],"about_ca_topic_score_codex":0.0020827756,"about_ca_topic_score_gemma":0.003313967,"teacher_disagreement_score":0.03907079,"about_ca_system_score_codex":0.00049671443,"about_ca_system_score_gemma":0.00036645852,"threshold_uncertainty_score":0.13070482},"labels":[],"label_agreement":null},{"id":"W2068405570","doi":"10.1109/icip.2013.6738829","title":"Image segmentation by a robust generalized fuzzy c-means algorithm","year":2013,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Robustness (evolution); Image segmentation; Fuzzy logic; Pattern recognition (psychology); Artificial intelligence; Mathematics; Segmentation; Spatial analysis; Computer science; Algorithm; Statistics","score_opus":0.01145108927963133,"score_gpt":0.2117211201088917,"score_spread":0.20027003082926037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068405570","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035858445,0.0001988865,0.9951106,0.000051692845,0.000023839164,0.000029056768,0.000023216082,0.000531007,0.0004457781],"genre_scores_gemma":[0.10053092,0.00026487897,0.8972135,0.000107729276,0.0000659717,0.00012905808,0.00014373695,0.00013424511,0.0014099171],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880195,0.00017979667,0.000066603614,0.00040788416,0.0004340157,0.00010984023],"domain_scores_gemma":[0.9994728,0.00014345458,0.00007542803,0.00007878434,0.0002103213,0.000019281577],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011191139,0.0010533977,0.0017329224,0.001931734,0.000802123,0.0011006308,0.002245956,0.0023715883,0.0013979785],"category_scores_gemma":[0.0022355183,0.00054346246,0.0019679433,0.0019888198,0.0008985894,0.0012349149,0.001037602,0.0011402707,0.0005897156],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016079369,0.000045430606,0.00048481664,0.00018252381,0.00016123854,0.00011148948,0.00016058526,0.4754063,0.02602186,0.009223915,0.0031851195,0.484856],"study_design_scores_gemma":[0.00000659519,0.000014237054,0.0001501999,0.0000071877294,0.000014314028,0.000036348792,0.0000075119715,0.9934002,0.0028023848,0.0024015787,0.0011433576,0.000015964479],"about_ca_topic_score_codex":0.015872868,"about_ca_topic_score_gemma":0.009991,"teacher_disagreement_score":0.015872868,"about_ca_system_score_codex":0.0013629489,"about_ca_system_score_gemma":0.0018514856,"threshold_uncertainty_score":0.031560957},"labels":[],"label_agreement":null},{"id":"W2069748987","doi":"10.1080/01431161003745590","title":"A method for obtaining and applying classification parameters in object-based urban rooftop extraction from VHR multispectral images","year":2011,"lang":"en","type":"article","venue":"International Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Multispectral image; Extraction (chemistry); Remote sensing; Computer science; Object (grammar); Multispectral pattern recognition; Object based; Artificial intelligence; Pattern recognition (psychology); Computer vision; Geography","score_opus":0.04699599688226821,"score_gpt":0.3061145417061512,"score_spread":0.259118544823883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069748987","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01657061,0.0001501538,0.980186,0.000027928527,0.000029232579,0.00012352529,0.00016077628,0.0018707352,0.0008811381],"genre_scores_gemma":[0.11061586,0.00021214059,0.88690716,0.00002955405,0.000023797724,0.0001912158,0.00037115373,0.0001590371,0.001490098],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996487,0.000038580627,0.000027414202,0.000102206315,0.00014733845,0.00003578307],"domain_scores_gemma":[0.9995264,0.000110022986,0.00005352211,0.00007846074,0.00021290834,0.000018750832],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005469921,0.000719121,0.00061356486,0.0016222332,0.0005640754,0.0011414182,0.00081393216,0.0007227537,0.0017688855],"category_scores_gemma":[0.0012830475,0.00047816962,0.00050772267,0.0012945037,0.0004045619,0.000761938,0.0005935019,0.000695896,0.0018116479],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013746343,0.00014275694,0.0034297858,0.0001355119,0.00006393126,0.00008274108,0.00012918077,0.017700518,0.13491018,0.0015177563,0.0019535297,0.8397966],"study_design_scores_gemma":[0.00005865453,0.00014665192,0.02077983,0.00005648465,0.00015364197,0.0005503046,0.0002831452,0.7517077,0.20887163,0.0028618097,0.014394268,0.00013590314],"about_ca_topic_score_codex":0.0045808386,"about_ca_topic_score_gemma":0.00592325,"teacher_disagreement_score":0.0045808386,"about_ca_system_score_codex":0.00033305772,"about_ca_system_score_gemma":0.0007192252,"threshold_uncertainty_score":0.009108305},"labels":[],"label_agreement":null},{"id":"W2070082445","doi":"10.1117/12.2068854","title":"Local anomaly detection algorithm based on sliding windows in spectral space","year":2014,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Anomaly detection; Computer science; Anomaly (physics); Algorithm; Space (punctuation); Artificial intelligence; Physics; Operating system","score_opus":0.00835900478049547,"score_gpt":0.20605046553168038,"score_spread":0.1976914607511849,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070082445","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016698785,0.00017061406,0.981564,0.00004021344,0.00003748494,0.00003400051,0.000026139947,0.0010405321,0.00038829912],"genre_scores_gemma":[0.28299323,0.00028774817,0.71331173,0.000069951755,0.00007896528,0.0001534727,0.00026219466,0.0002032239,0.002639578],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987985,0.00013167401,0.000082594204,0.00039980173,0.00047614248,0.00011127427],"domain_scores_gemma":[0.9991648,0.00020185528,0.00011340227,0.00014944552,0.0003116459,0.000058947397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008873766,0.00086571823,0.0013593561,0.0016102884,0.0006180433,0.0010386053,0.0015167566,0.0007451086,0.0013543327],"category_scores_gemma":[0.0019975605,0.0003504705,0.0008774102,0.0013000804,0.0006782192,0.002754865,0.0013764998,0.0012068886,0.0006424577],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003336437,0.00015465792,0.0047354605,0.00013881929,0.00016050639,0.00018787499,0.0002932164,0.051534805,0.0769611,0.01189374,0.0028798997,0.8507263],"study_design_scores_gemma":[0.000020168754,0.00015282398,0.0016613196,0.000009550515,0.000041042596,0.00032763122,0.00006913232,0.9497261,0.0397323,0.004752243,0.0034670837,0.00004052832],"about_ca_topic_score_codex":0.0018886719,"about_ca_topic_score_gemma":0.0014953619,"teacher_disagreement_score":0.0018886719,"about_ca_system_score_codex":0.0004873333,"about_ca_system_score_gemma":0.00076079526,"threshold_uncertainty_score":0.0046929717},"labels":[],"label_agreement":null},{"id":"W2070131769","doi":"10.1142/s0218001411008695","title":"BUILDING RECOGNITION BASED ON INDIRECT LOCATION OF PLANAR LANDMARK IN FLIR IMAGE SEQUENCES","year":2011,"lang":"en","type":"article","venue":"International Journal of Pattern Recognition and Artificial Intelligence","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"McMaster University","keywords":"Landmark; Artificial intelligence; Computer vision; Computer science; Image (mathematics); Transformation (genetics); Position (finance); Perspective (graphical); Pattern recognition (psychology)","score_opus":0.11139135805942008,"score_gpt":0.2934519625960439,"score_spread":0.18206060453662382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070131769","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018459154,0.00009882799,0.9797816,0.000037938313,0.000029851568,0.000034392775,0.0000734828,0.0006869672,0.0007977529],"genre_scores_gemma":[0.22671428,0.0002477898,0.7703776,0.00004445542,0.00005718433,0.0000918811,0.00047931817,0.00007848409,0.001909055],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996773,0.00004089288,0.000014910586,0.00010612765,0.000113818176,0.000047048696],"domain_scores_gemma":[0.99970573,0.00005532578,0.00006291777,0.000067725625,0.00009089758,0.000017381259],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024806542,0.000703848,0.00070306234,0.0011335496,0.00023914812,0.00067079114,0.0009853669,0.00053739164,0.0010433726],"category_scores_gemma":[0.00088553823,0.00029616937,0.0005847862,0.0011690363,0.00045912858,0.0010510184,0.00067117484,0.000679723,0.00086681894],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020123378,0.0000832482,0.0026460448,0.00021029552,0.00008503808,0.00023927045,0.00025854187,0.033961274,0.15701519,0.004891268,0.0019807937,0.7984279],"study_design_scores_gemma":[0.00002490442,0.00021886452,0.0073326724,0.000030142946,0.00009518785,0.0011230763,0.00017586458,0.87698364,0.10382216,0.0037717477,0.0063392334,0.00008255218],"about_ca_topic_score_codex":0.0016447251,"about_ca_topic_score_gemma":0.0028461043,"teacher_disagreement_score":0.0016447251,"about_ca_system_score_codex":0.00019794774,"about_ca_system_score_gemma":0.0004869161,"threshold_uncertainty_score":0.003490448},"labels":[],"label_agreement":null},{"id":"W2072085450","doi":"10.1155/asp/2006/76462","title":"Fast Registration of Remotely Sensed Images for Earthquake Damage Estimation","year":2006,"lang":"en","type":"article","venue":"EURASIP Journal on Advances in Signal Processing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; Iran Telecommunication Research Center","keywords":"Multispectral image; Computer science; Remote sensing; Event (particle physics); Computer vision; Artificial intelligence; Real-time computing; Geology","score_opus":0.012731527402270303,"score_gpt":0.2678622281681992,"score_spread":0.2551307007659289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072085450","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10572606,0.001074494,0.889477,0.00014811338,0.00009777082,0.00008799579,0.00017995415,0.0019476388,0.0012609727],"genre_scores_gemma":[0.5366826,0.0007331772,0.45978162,0.00006812473,0.00012410607,0.00009260501,0.0006477082,0.00016712723,0.0017030176],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999335,0.0002007025,0.000027324046,0.00009554162,0.00028650227,0.00005498981],"domain_scores_gemma":[0.9990013,0.00032786393,0.00016992318,0.00024067628,0.00022296565,0.00003723679],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009856748,0.0006352866,0.00061128783,0.0017148384,0.000212591,0.00054037484,0.0005547442,0.0007361591,0.0014042698],"category_scores_gemma":[0.0025474618,0.0003652481,0.0003769482,0.0014109933,0.00025118823,0.00087221124,0.00044212467,0.00059739116,0.0014114918],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008278308,0.00024887134,0.0033279234,0.00021457937,0.0001128499,0.00017981774,0.00007974343,0.06011308,0.25757656,0.002417747,0.0029319273,0.67196906],"study_design_scores_gemma":[0.000054851767,0.00031863514,0.011133563,0.000016785527,0.000059253438,0.00034245805,0.00004266587,0.8500837,0.13123445,0.001718498,0.004936365,0.000058830352],"about_ca_topic_score_codex":0.00055453647,"about_ca_topic_score_gemma":0.000984128,"teacher_disagreement_score":0.0017148384,"about_ca_system_score_codex":0.0001722505,"about_ca_system_score_gemma":0.00029175394,"threshold_uncertainty_score":0.0052128434},"labels":[],"label_agreement":null},{"id":"W2073534752","doi":"10.1109/jstars.2014.2308301","title":"Detection of Buildings in Multispectral Very High Spatial Resolution Images Using the Percentage Occupancy Hit-or-Miss Transform","year":2014,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Panchromatic film; Multispectral image; Computer science; Artificial intelligence; Computer vision; Pixel; Transformation (genetics); Image resolution; Object detection; Multispectral pattern recognition; Pattern recognition (psychology); Remote sensing; Geography","score_opus":0.020207566706533543,"score_gpt":0.2308675912837053,"score_spread":0.21066002457717176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073534752","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27283058,0.00023046175,0.72434944,0.000055367873,0.000025638212,0.000053511118,0.00018384898,0.00082522404,0.0014459457],"genre_scores_gemma":[0.69697297,0.00021075118,0.30174828,0.000021971291,0.000026705558,0.000035657824,0.00032938225,0.000046333564,0.00060792675],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99971205,0.00006713681,0.000016208109,0.00005511432,0.000114191585,0.000035338453],"domain_scores_gemma":[0.9996319,0.000116435804,0.000088760906,0.000056739842,0.00008213921,0.000024081246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049426436,0.00040350942,0.0003453133,0.0018127096,0.00016515817,0.00049289456,0.00032243374,0.00034044965,0.0006302963],"category_scores_gemma":[0.00096384296,0.00020212655,0.0003855823,0.0009384293,0.00035495032,0.0006515389,0.00045883944,0.00027111894,0.00033218565],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000626738,0.00015542694,0.015833586,0.0003354994,0.00016367536,0.00049569126,0.0002705753,0.03784137,0.3413721,0.003997023,0.0011062811,0.5978019],"study_design_scores_gemma":[0.000030823776,0.00040092834,0.068709426,0.00003704692,0.00013889252,0.0019716776,0.00028980637,0.7551089,0.16765285,0.0024389382,0.0031329086,0.00008776154],"about_ca_topic_score_codex":0.0006193819,"about_ca_topic_score_gemma":0.0010223711,"teacher_disagreement_score":0.0018127096,"about_ca_system_score_codex":0.00013522182,"about_ca_system_score_gemma":0.00017899126,"threshold_uncertainty_score":0.0026139617},"labels":[],"label_agreement":null},{"id":"W2075429946","doi":"10.2495/sdp-v1-n3-261-270","title":"Identification of land cover alterations in the Alta Murgia National Park (Italy) with VHR satellite imagery","year":2006,"lang":"en","type":"article","venue":"International Journal of Sustainable Development and Planning","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Remote sensing; Land cover; Multispectral image; Satellite imagery; Land use; Scale (ratio); Pixel; National park; Identification (biology); Satellite; Geography; Segmentation; Cartography; Computer science; Artificial intelligence","score_opus":0.009206520344282562,"score_gpt":0.22875772763423435,"score_spread":0.21955120728995178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075429946","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9964514,0.000119246164,0.0018031858,0.000022567297,0.000004686166,0.000047810252,0.00025140433,0.000070916845,0.0012288651],"genre_scores_gemma":[0.9918562,0.000059283557,0.0070881615,0.0000069679877,0.0000055622136,0.000024105571,0.00049029966,0.0000074252403,0.00046199307],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9998166,0.000047525733,0.000007986629,0.00005367077,0.00004327048,0.000030976054],"domain_scores_gemma":[0.9998696,0.000030764957,0.000037900267,0.000021499902,0.000023097993,0.000017145043],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003158025,0.00022148648,0.00015094345,0.0013195693,0.00014253512,0.0004392335,0.00020891397,0.00020987888,0.00047284676],"category_scores_gemma":[0.00035943874,0.00008288923,0.00021600502,0.00066058786,0.00023225682,0.00017944069,0.00024289358,0.00010951298,0.00014128991],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006383621,0.00055643584,0.6362026,0.00034482506,0.00013807762,0.0018292757,0.0013683628,0.023207983,0.072285816,0.0005476612,0.0016233972,0.26125732],"study_design_scores_gemma":[0.0000127489475,0.00012096212,0.9675596,0.000013841175,0.000030787014,0.0002429268,0.0003144294,0.027489215,0.0029606866,0.000068619396,0.0011771244,0.000009008058],"about_ca_topic_score_codex":0.0097026555,"about_ca_topic_score_gemma":0.017446317,"teacher_disagreement_score":0.0097026555,"about_ca_system_score_codex":0.0002471042,"about_ca_system_score_gemma":0.00019989183,"threshold_uncertainty_score":0.019292355},"labels":[],"label_agreement":null},{"id":"W2077159718","doi":"10.1142/s0129156408005710","title":"3D DECONVOLUTION OF VIBRATION CORRUPTED HYPERSPECTRAL IMAGES","year":2008,"lang":"en","type":"article","venue":"International Journal of High Speed Electronics and Systems","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Defence Research and Development Canada","funders":"Ministère de la Défense Nationale","keywords":"Hyperspectral imaging; Deconvolution; Dimension (graph theory); Pixel; Mathematics; Artificial intelligence; Position (finance); Point (geometry); Track (disk drive); Vibration; Algorithm; Pattern recognition (psychology); Computer science; Physics; Acoustics; Geometry","score_opus":0.012182655265332396,"score_gpt":0.22372372542543972,"score_spread":0.21154107016010731,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077159718","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10094395,0.00006478541,0.89615166,0.0001077589,0.000024838802,0.000016600976,0.0001744881,0.0014155842,0.0011004009],"genre_scores_gemma":[0.42427066,0.00012244142,0.5730703,0.00005624814,0.000011875088,0.000036631605,0.00042170583,0.00019915252,0.0018109661],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997731,0.0000329124,0.000010837265,0.000049866347,0.00010729854,0.000026016343],"domain_scores_gemma":[0.9996094,0.00009849755,0.000054555938,0.00010240933,0.00012190114,0.000013264277],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005357044,0.00049634645,0.00039978168,0.00050323555,0.0002694229,0.0005211281,0.00039474812,0.0005756379,0.0014102175],"category_scores_gemma":[0.0014164195,0.000293742,0.00045176968,0.0004456772,0.00051913364,0.0005926407,0.0005819599,0.0005347092,0.00060025026],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002704816,0.0000817671,0.0041670473,0.00011593951,0.00005783979,0.00018609458,0.00026087833,0.55707604,0.23973332,0.0066397972,0.0014290564,0.18998179],"study_design_scores_gemma":[0.000006553065,0.000014738042,0.0015268975,0.0000045974675,0.000005608759,0.000073753916,0.000021762311,0.92921776,0.06617751,0.0017847094,0.001141951,0.000024122844],"about_ca_topic_score_codex":0.0026889713,"about_ca_topic_score_gemma":0.0025390247,"teacher_disagreement_score":0.0026889713,"about_ca_system_score_codex":0.0003841809,"about_ca_system_score_gemma":0.0007153814,"threshold_uncertainty_score":0.0053465962},"labels":[],"label_agreement":null},{"id":"W208043904","doi":"","title":"Information Content of Very High Resolution SAR Images: Study of Dependency of SAR Image Structure Descriptors with Incidence Angle","year":2012,"lang":"en","type":"article","venue":"elib (German Aerospace Center)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"European Commission; DePaul University","keywords":"Filter (signal processing); Artificial intelligence; Computer science; Synthetic aperture radar; Computer vision; Incidence (geometry); Pattern recognition (psychology); Mathematics; Geometry","score_opus":0.013430565277774267,"score_gpt":0.21811399520757457,"score_spread":0.20468342992980032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W208043904","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9725212,0.0014779893,0.022738555,0.00007864104,0.000030312896,0.00004037576,0.00053441135,0.00030226223,0.002276406],"genre_scores_gemma":[0.9908387,0.00048231828,0.0073188236,0.000013817246,0.000018641465,0.000014609447,0.0008031776,0.000050297025,0.0004596238],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9992275,0.00013379697,0.00005870654,0.00014770722,0.00034642228,0.00008580295],"domain_scores_gemma":[0.99279237,0.005428801,0.0005619521,0.0004886349,0.00061202573,0.00011623432],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00088736345,0.00032600597,0.00039657328,0.001917281,0.00019363128,0.00069192884,0.00018564869,0.0003466035,0.0007653805],"category_scores_gemma":[0.006323811,0.00013430625,0.00043659628,0.0011398173,0.00034324208,0.0008005102,0.00031538878,0.000342983,0.00029800276],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018559431,0.00051946996,0.16290835,0.00093382504,0.00042722817,0.0012679882,0.0006722008,0.07367829,0.41089174,0.0008278753,0.0015956131,0.34442148],"study_design_scores_gemma":[0.00001670537,0.0017069884,0.551882,0.000061927676,0.00028409422,0.0022138495,0.0005506724,0.1954313,0.24419114,0.00080434885,0.0027535516,0.000103403676],"about_ca_topic_score_codex":0.0008144039,"about_ca_topic_score_gemma":0.000909552,"teacher_disagreement_score":0.001917281,"about_ca_system_score_codex":0.00016946877,"about_ca_system_score_gemma":0.00013199779,"threshold_uncertainty_score":0.004692912},"labels":[],"label_agreement":null},{"id":"W2082289875","doi":"10.1016/s0305-9006(03)00068-0","title":"Remote sensing change detection for a watershed in north Sulawesi, Indonesia","year":2003,"lang":"en","type":"article","venue":"Progress in Planning","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; York University","funders":"","keywords":"Watershed; Environmental science; Land cover; Shrubland; Soil carbon; Hydrology (agriculture); Land use; Vegetation (pathology); Precipitation; Physical geography; Soil science; Soil water; Ecosystem; Geology; Geography; Ecology","score_opus":0.04414031763950589,"score_gpt":0.2718268087682892,"score_spread":0.2276864911287833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082289875","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99802786,0.000023465374,0.00042924902,0.000052903644,0.0000029622659,0.000018146111,0.000254812,0.00003516444,0.0011553125],"genre_scores_gemma":[0.9978369,0.000024851008,0.0012159304,0.000007863203,0.0000021162473,0.000010301984,0.00035400953,0.0000036178335,0.00054444483],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9999306,0.0000073405085,0.0000068235486,0.000022273365,0.00001526374,0.000017656519],"domain_scores_gemma":[0.999912,0.000017024597,0.000015680129,0.0000057617112,0.00003093467,0.000018498431],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014161457,0.0002430027,0.0002398716,0.0008610779,0.00049948914,0.00045089738,0.00036579676,0.0002637815,0.0005437409],"category_scores_gemma":[0.00022406595,0.00015254343,0.00020226401,0.0007391178,0.00029867032,0.00028434466,0.00018909905,0.00015815969,0.00013979542],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00072498765,0.0012422383,0.82344913,0.00018081056,0.0001380694,0.0046524117,0.0012436146,0.033364207,0.030956475,0.0006178719,0.0023931314,0.10103703],"study_design_scores_gemma":[0.00003693295,0.00006133566,0.90313804,0.000009509512,0.00006451315,0.0003145675,0.0013387357,0.09024416,0.0037939837,0.00015883672,0.0008229283,0.000016362535],"about_ca_topic_score_codex":0.12212938,"about_ca_topic_score_gemma":0.18664326,"teacher_disagreement_score":0.12212938,"about_ca_system_score_codex":0.0008663037,"about_ca_system_score_gemma":0.0006762739,"threshold_uncertainty_score":0.24283701},"labels":[],"label_agreement":null},{"id":"W2082353960","doi":"10.1109/wacv.2015.86","title":"The Mountain Habitats Segmentation and Change Detection Dataset","year":2015,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Segmentation; Computer science; Ground truth; Artificial intelligence; Change detection; Baseline (sea); Image segmentation; Habitat; Classifier (UML); Computer vision; Pattern recognition (psychology); Remote sensing; Geography; Ecology; Geology","score_opus":0.06172988892440423,"score_gpt":0.26928667493230646,"score_spread":0.20755678600790223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082353960","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10944174,0.0019047775,0.0091808,0.00066245825,0.00022907856,0.0011857797,0.8577514,0.009934349,0.009709654],"genre_scores_gemma":[0.030598283,0.00022808679,0.015029623,0.00010125702,0.000040711366,0.00035373043,0.9519016,0.0001586432,0.0015880828],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990747,0.00007487991,0.00006965929,0.00029905295,0.00030037088,0.00018129036],"domain_scores_gemma":[0.99922323,0.00009475822,0.00006784877,0.00021095452,0.00026419555,0.0001389046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059159106,0.0017328952,0.0011956242,0.0034946331,0.0015755466,0.0012166105,0.0030982324,0.0023805993,0.0046606236],"category_scores_gemma":[0.0013766269,0.0004205494,0.0014490369,0.0049329055,0.00061623816,0.000762997,0.0012511796,0.0014230717,0.0047482518],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011046617,0.0013747881,0.027259832,0.0023329265,0.0005042571,0.0017625075,0.0004794372,0.013998427,0.02255332,0.0019426765,0.7733351,0.15335202],"study_design_scores_gemma":[0.0007923224,0.0004632758,0.25418997,0.00037788792,0.0003117779,0.0035881707,0.0013980208,0.059048656,0.02172825,0.0024781232,0.65533084,0.00029280252],"about_ca_topic_score_codex":0.07403952,"about_ca_topic_score_gemma":0.17532471,"teacher_disagreement_score":0.07403952,"about_ca_system_score_codex":0.0015452728,"about_ca_system_score_gemma":0.0020504538,"threshold_uncertainty_score":0.1472171},"labels":[],"label_agreement":null},{"id":"W2082531791","doi":"10.5589/m07-011","title":"Full fuzzy land cover mapping using remote sensing data based on fuzzy<i>c</i>-means and density estimation","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Fuzzy logic; Artificial intelligence; Support vector machine; Fuzzy classification; Data mining; Vagueness; Pattern recognition (psychology); Computer science; Mathematics; Machine learning; Fuzzy set","score_opus":0.03588684792674715,"score_gpt":0.2448516649296679,"score_spread":0.20896481700292074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082531791","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5103463,0.00036262049,0.4863032,0.00013003469,0.000039162303,0.000082470826,0.0003885619,0.0006869984,0.0016605452],"genre_scores_gemma":[0.8493114,0.00009026785,0.14975667,0.000020350177,0.000012286739,0.00004499024,0.00029504855,0.000013741991,0.0004551716],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996277,0.000067357716,0.000027152706,0.00007699002,0.00017115554,0.0000295927],"domain_scores_gemma":[0.9992447,0.00028021028,0.00008321266,0.00007978684,0.00028390507,0.000028264714],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008004977,0.00036669688,0.0004606261,0.0021706284,0.00030676118,0.0007094483,0.0004942733,0.0003818355,0.000652619],"category_scores_gemma":[0.0019526054,0.00023037138,0.00056480174,0.0011043845,0.00027955562,0.0006851279,0.00034681373,0.00030185792,0.00015012629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006757111,0.0002205035,0.019037444,0.00024728567,0.00013226016,0.00021196598,0.00025979482,0.4345832,0.043117654,0.002541069,0.0010453379,0.4979278],"study_design_scores_gemma":[0.0000044546296,0.000023951385,0.005818525,0.000010819709,0.000010122233,0.000034563986,0.000035357807,0.98804724,0.0051797647,0.00057170907,0.00024968508,0.000013821855],"about_ca_topic_score_codex":0.01118439,"about_ca_topic_score_gemma":0.009716369,"teacher_disagreement_score":0.01118439,"about_ca_system_score_codex":0.0005793825,"about_ca_system_score_gemma":0.00048503352,"threshold_uncertainty_score":0.022238612},"labels":[],"label_agreement":null},{"id":"W2082597751","doi":"10.1007/s00267-003-0270-4","title":"Identification of Land-Cover Changes Through Image Processing and Associated Impacts on Water Reservoir Conditions","year":2005,"lang":"en","type":"article","venue":"Environmental Management","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":48,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Urbanization; Land cover; Watershed; Land use; Water quality; Geography; Orthophoto; Water resource management; Identification (biology); Remote sensing; Environmental science; Hydrology (agriculture); Environmental resource management; Geology","score_opus":0.01038254963582322,"score_gpt":0.22516001222581014,"score_spread":0.21477746258998692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082597751","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98134506,0.000093665054,0.013873023,0.00007985653,0.000012914028,0.00005101531,0.0005162634,0.00017523834,0.0038530277],"genre_scores_gemma":[0.98710304,0.00014181514,0.01098689,0.00003024381,0.000014396715,0.000017399489,0.00042392436,0.000025188087,0.0012572341],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9999263,0.000009753149,0.000004273838,0.000015232932,0.000029896368,0.00001444112],"domain_scores_gemma":[0.99982005,0.000045379376,0.000041437248,0.000011650465,0.00006585342,0.000015499452],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001766252,0.0002188885,0.00016713767,0.0010295607,0.00015497941,0.0005134617,0.0001139069,0.00024070093,0.001033845],"category_scores_gemma":[0.00053987856,0.00010016195,0.0001596351,0.0005872927,0.00014003315,0.00044995383,0.00012921359,0.00017529471,0.0002531313],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00053239,0.00055840204,0.36047736,0.0001927757,0.0001396872,0.00040617987,0.00028017018,0.018618753,0.3051985,0.00064939365,0.0015798418,0.3113666],"study_design_scores_gemma":[0.000014353839,0.00009811735,0.831165,0.000012090499,0.00009891472,0.00019146377,0.00019961096,0.112577915,0.0539392,0.0002912195,0.0013894545,0.000022672606],"about_ca_topic_score_codex":0.0048975167,"about_ca_topic_score_gemma":0.012319448,"teacher_disagreement_score":0.0048975167,"about_ca_system_score_codex":0.00018110078,"about_ca_system_score_gemma":0.00023247261,"threshold_uncertainty_score":0.009737968},"labels":[],"label_agreement":null},{"id":"W2082641726","doi":"10.1016/j.jag.2013.11.013","title":"Quantification of anthropogenic and natural changes in oil sands mining infrastructure land based on RapidEye and SPOT5","year":2014,"lang":"en","type":"article","venue":"International Journal of Applied Earth Observation and Geoinformation","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Energy; Natural Resources Canada","funders":"Canadian Space Agency","keywords":"Extraction (chemistry); Oil sands; Environmental science; Land reclamation; Land cover; Surface mining; Natural (archaeology); Remote sensing; Land use; Geography; Coal mining; Cartography; Asphalt; Coal; Civil engineering; Engineering","score_opus":0.009516759711576962,"score_gpt":0.21672400569397443,"score_spread":0.20720724598239748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082641726","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99714917,0.00004962456,0.000763221,0.000014489095,0.000007872071,0.000006700133,0.0007746956,0.000058653306,0.0011756666],"genre_scores_gemma":[0.9966865,0.000043814587,0.001534476,0.0000054079624,0.0000075971298,0.000007494849,0.0011708895,0.000008029289,0.0005357495],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9998441,0.000010806081,0.000010279559,0.000032682026,0.000057566263,0.000044600023],"domain_scores_gemma":[0.99979573,0.000026975062,0.00004534453,0.000014982558,0.000083557796,0.00003348758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026255753,0.00034132676,0.00022323197,0.0024289154,0.00022845223,0.00047119884,0.00027137497,0.00032747065,0.00080428517],"category_scores_gemma":[0.00023154575,0.00015916486,0.00034172137,0.0015132423,0.00021790688,0.00057623425,0.0002908203,0.00015323007,0.00026443417],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00075364846,0.00032619006,0.8158293,0.00019524341,0.0002198032,0.00062143337,0.0004312189,0.021731334,0.07846841,0.0006313158,0.0019227484,0.07886939],"study_design_scores_gemma":[0.000014147793,0.0000610925,0.9515295,0.000010547713,0.000059629405,0.00010704077,0.00034763865,0.041102003,0.0058179526,0.00008778213,0.00083397154,0.00002871177],"about_ca_topic_score_codex":0.012409511,"about_ca_topic_score_gemma":0.024579518,"teacher_disagreement_score":0.9875905,"about_ca_system_score_codex":0.00028749203,"about_ca_system_score_gemma":0.00037953432,"threshold_uncertainty_score":0.024674535},"labels":[],"label_agreement":null},{"id":"W2084989433","doi":"10.1109/lgrs.2014.2324631","title":"FSPE: Visualization of Hyperspectral Imagery Using Faithful Stochastic Proximity Embedding","year":2014,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University College of the North","funders":"","keywords":"Hyperspectral imaging; Computer science; Visualization; Embedding; Pixel; Artificial intelligence; Dimensionality reduction; Computer vision; Nonlinear system; Data visualization; Metric (unit); Pattern recognition (psychology)","score_opus":0.0158364527475842,"score_gpt":0.24987305839737728,"score_spread":0.2340366056497931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084989433","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018300144,0.00012866693,0.974719,0.00024280713,0.000042936917,0.00005019351,0.00050240586,0.0043960046,0.001617843],"genre_scores_gemma":[0.28386676,0.00040695153,0.7089096,0.00014481708,0.00006606628,0.00015408496,0.0015218063,0.0014627842,0.0034671316],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997526,0.000051842435,0.0000125786955,0.000044438948,0.00012099347,0.000017499986],"domain_scores_gemma":[0.999521,0.00016441323,0.00006240137,0.00009434851,0.00011571336,0.00004215697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037281605,0.0008313298,0.0003224611,0.00088266144,0.00021682565,0.0011491013,0.00065235316,0.00051691564,0.005797948],"category_scores_gemma":[0.0016669283,0.00027720517,0.0004792705,0.0005983516,0.00037435425,0.0016148639,0.0014734897,0.00094882783,0.0009296953],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033018328,0.00015954701,0.0019295665,0.00053065206,0.00016057004,0.00034007072,0.00045707825,0.21094395,0.16388129,0.037073143,0.027498225,0.55669576],"study_design_scores_gemma":[0.000022173439,0.000047077996,0.0010498163,0.00002138296,0.000009321217,0.0002646823,0.00006438132,0.93615615,0.03610352,0.015879327,0.010335595,0.00004656721],"about_ca_topic_score_codex":0.0010805066,"about_ca_topic_score_gemma":0.001494826,"teacher_disagreement_score":0.005797948,"about_ca_system_score_codex":0.000244166,"about_ca_system_score_gemma":0.00037112972,"threshold_uncertainty_score":0.019396067},"labels":[],"label_agreement":null},{"id":"W2085360881","doi":"10.1109/ccece.2006.277335","title":"Advanced Image Exploitation Tools for Surveillance and Target Detection with eo Sensors","year":2006,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Defence Research and Development Canada","funders":"","keywords":"Toolbox; Computer science; Artificial intelligence; Software; Computer vision; Contextual image classification; Image (mathematics); Data mining","score_opus":0.008253270481007019,"score_gpt":0.20286978254083687,"score_spread":0.19461651205982985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2085360881","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034547755,0.00023470874,0.99301046,0.000043860844,0.0000113307005,0.00003509751,0.00005454204,0.0017871083,0.0013680507],"genre_scores_gemma":[0.05291042,0.00046558812,0.94276047,0.00007580075,0.00002364553,0.00009948098,0.00022823167,0.00019840007,0.0032378812],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999526,0.00006952016,0.000022831235,0.00006101361,0.0002963879,0.000024237223],"domain_scores_gemma":[0.99932754,0.00031472425,0.000059016853,0.0001308727,0.00014648773,0.0000213315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00090430886,0.00061462686,0.000508335,0.0013755391,0.0001809223,0.00052198296,0.00090087793,0.0005269412,0.005315754],"category_scores_gemma":[0.0016182684,0.00032770578,0.00055089744,0.0007551598,0.00040641808,0.0012283747,0.00068064185,0.00071085227,0.0015009714],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014628402,0.00009191416,0.00090578356,0.00023367185,0.000048707727,0.00008750351,0.00015971853,0.011495174,0.13463725,0.010318963,0.0036162736,0.83825886],"study_design_scores_gemma":[0.00012932994,0.00045557035,0.0079325875,0.0001481972,0.00010696469,0.0014040018,0.0001445785,0.54620874,0.32712513,0.02406362,0.092170104,0.000111281806],"about_ca_topic_score_codex":0.0005268867,"about_ca_topic_score_gemma":0.00092771597,"teacher_disagreement_score":0.005315754,"about_ca_system_score_codex":0.00022793133,"about_ca_system_score_gemma":0.0002391819,"threshold_uncertainty_score":0.017782986},"labels":[],"label_agreement":null},{"id":"W2085656297","doi":"10.1109/qbsc.2014.6841205","title":"Adaptive LASSO hyperspectral unmixing using ADMM","year":2014,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Hyperspectral imaging; Lasso (programming language); Computer science; Algorithm; Mathematical optimization; Optimization problem; Selection (genetic algorithm); Mean squared error; Artificial intelligence; Mathematics; Pattern recognition (psychology); Statistics","score_opus":0.02422772475945882,"score_gpt":0.22018694762330074,"score_spread":0.19595922286384193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2085656297","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00078082795,0.000081261234,0.9984092,0.00005815376,0.00002004658,0.000012412366,0.000024820341,0.00015773586,0.00045543903],"genre_scores_gemma":[0.05048036,0.0003292125,0.9449952,0.00016725862,0.00008713925,0.00021443707,0.0003552619,0.00015982702,0.0032113628],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99920964,0.00026877626,0.0000410831,0.00020023555,0.00023868075,0.000041530522],"domain_scores_gemma":[0.99939,0.00028004852,0.00010323655,0.00009331618,0.000112034424,0.00002131772],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013336703,0.0015219534,0.0011782337,0.00054250576,0.0004705496,0.0008790888,0.0014976271,0.0016875772,0.002401796],"category_scores_gemma":[0.002027426,0.0005616152,0.0012191655,0.0010842108,0.00073062105,0.0013805433,0.0012737529,0.0029535184,0.0010993703],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010976604,0.00009070777,0.00036079113,0.00032097634,0.00016271688,0.00011569273,0.00013053948,0.7611413,0.0148875015,0.03257752,0.005741534,0.1843609],"study_design_scores_gemma":[0.0000065424797,0.000011500974,0.000042918924,0.0000057327215,0.000006054164,0.000023721122,0.000005248063,0.9929133,0.0015109963,0.003470868,0.001996639,0.000006515469],"about_ca_topic_score_codex":0.0015802748,"about_ca_topic_score_gemma":0.0018341393,"teacher_disagreement_score":0.002401796,"about_ca_system_score_codex":0.00046761168,"about_ca_system_score_gemma":0.0010739216,"threshold_uncertainty_score":0.008034825},"labels":[],"label_agreement":null},{"id":"W2088176914","doi":"10.1109/ccece.2006.277344","title":"AIRIS the Canadian Hyperspectral Imager","year":2006,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Defence Research and Development Canada","funders":"","keywords":"Hyperspectral imaging; Remote sensing; Imaging spectrometer; Flight test; Pixel; Spectrometer; Computer science; Detector; Electromagnetic spectrum; Data processing; Environmental science; Telecommunications; Geography; Artificial intelligence; Optics; Database; Physics; Simulation","score_opus":0.006340271494133426,"score_gpt":0.17434305523708676,"score_spread":0.16800278374295333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2088176914","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03320512,0.0063093407,0.13866198,0.0035201334,0.0016429973,0.0017217553,0.15863006,0.05673133,0.59957725],"genre_scores_gemma":[0.14169723,0.004130217,0.36187196,0.0025919138,0.0004144146,0.0013389364,0.18325599,0.0057342215,0.29896525],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977435,0.00008903485,0.0000267021,0.00029942277,0.0016035547,0.00023781853],"domain_scores_gemma":[0.99785644,0.000037268037,0.0000482883,0.00012918233,0.001809401,0.000119356475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013028962,0.0017061156,0.00081699295,0.0038800063,0.0028837754,0.0021011233,0.0018285853,0.0010329777,0.036557566],"category_scores_gemma":[0.0012381868,0.0005066084,0.00051739893,0.0028290662,0.0006917459,0.0015965026,0.0014798223,0.0013386657,0.017511781],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037109558,0.000081298815,0.004360284,0.00023523603,0.00009858655,0.000093678296,0.00018978643,0.0025772443,0.042662885,0.013111022,0.67184114,0.26437768],"study_design_scores_gemma":[0.00008954389,0.000034988894,0.017806606,0.00007938727,0.000049193353,0.00018739185,0.00014036553,0.021498812,0.018453809,0.002229821,0.9392618,0.00016823139],"about_ca_topic_score_codex":0.6852496,"about_ca_topic_score_gemma":0.8086244,"teacher_disagreement_score":0.31475037,"about_ca_system_score_codex":0.00756337,"about_ca_system_score_gemma":0.010914005,"threshold_uncertainty_score":0.633208},"labels":[],"label_agreement":null},{"id":"W2088715406","doi":"10.1109/rose.2013.6698421","title":"A supervised training and learning method for building identification in remotely sensed imaging","year":2013,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec en Outaouais","funders":"","keywords":"Computer science; Identification (biology); Artificial intelligence; Segmentation; Computer vision; Object (grammar); Region of interest; Support vector machine; Training (meteorology); Precision and recall; Image segmentation; Pattern recognition (psychology); Machine learning; Geography","score_opus":0.024559613220295935,"score_gpt":0.271228264243122,"score_spread":0.2466686510228261,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2088715406","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008106844,0.00009525038,0.9902935,0.00003177907,0.000016417132,0.000046320234,0.000038748505,0.0009714149,0.00039979655],"genre_scores_gemma":[0.19036114,0.00012588616,0.80665797,0.00007940502,0.00006940388,0.00024988392,0.00033713438,0.00012099464,0.001998144],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990221,0.00031755696,0.00004790453,0.00025843823,0.000293992,0.000059997274],"domain_scores_gemma":[0.99843377,0.0007416746,0.00017293637,0.0002527161,0.00036162575,0.000037344762],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012462069,0.00079893775,0.00071610574,0.0012145517,0.00046922133,0.00046327102,0.0012431442,0.0010023682,0.0013682141],"category_scores_gemma":[0.0034523455,0.00036819736,0.0007019272,0.00097630714,0.00059029565,0.0008637757,0.0005171884,0.00085977267,0.0009474128],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013238628,0.00020054693,0.0019043618,0.00013196513,0.000089251305,0.00009165417,0.00011888018,0.118753545,0.018108448,0.0034965416,0.002843975,0.85412854],"study_design_scores_gemma":[0.000007883419,0.00006511107,0.00088702043,0.0000122392585,0.0000167132,0.000120829056,0.000021310925,0.9856424,0.008788151,0.0027392206,0.0016855178,0.0000137754105],"about_ca_topic_score_codex":0.0019763648,"about_ca_topic_score_gemma":0.0032382756,"teacher_disagreement_score":0.0019763648,"about_ca_system_score_codex":0.0003883729,"about_ca_system_score_gemma":0.0006532163,"threshold_uncertainty_score":0.0065906644},"labels":[],"label_agreement":null},{"id":"W2090101503","doi":"10.1109/whispers.2010.5594871","title":"Iterative spatial filtering for reducing intra-class spectral variability and noise","year":2010,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Hyperspectral imaging; Smoothing; Pixel; Noise (video); Weighting; Filter (signal processing); Computer science; Bilateral filter; Mathematics; Artificial intelligence; Pattern recognition (psychology); Algorithm; Computer vision; Image (mathematics); Physics","score_opus":0.009630848343243044,"score_gpt":0.22545113508582057,"score_spread":0.21582028674257753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090101503","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02139164,0.00005764584,0.9777493,0.00003783388,0.000012098941,0.000011890142,0.000013677379,0.0002577692,0.00046813252],"genre_scores_gemma":[0.19636236,0.0001364429,0.80188483,0.00004743467,0.000035257748,0.00006587825,0.00012289814,0.0001324141,0.0012124581],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992949,0.00013330518,0.00004081253,0.00012998626,0.00035467188,0.000046295812],"domain_scores_gemma":[0.9986234,0.000713416,0.00013594037,0.00013902907,0.00036006482,0.000028148985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012951911,0.00055775914,0.00046343246,0.0009983373,0.0004982178,0.00054755155,0.00065385294,0.0005750007,0.0007277643],"category_scores_gemma":[0.0039819013,0.00024240241,0.00078968983,0.0009552926,0.00060014584,0.0008946021,0.0005667158,0.00053335365,0.00028011267],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023230452,0.00012302422,0.004339848,0.00015029192,0.00015659422,0.00012828143,0.0005384044,0.2406918,0.13425437,0.012241921,0.0016610123,0.60548216],"study_design_scores_gemma":[0.000010317326,0.000065169086,0.0029197235,0.000008773545,0.000036463996,0.00011671127,0.000044408072,0.9546324,0.03516262,0.0042634793,0.002710635,0.000029239962],"about_ca_topic_score_codex":0.003793252,"about_ca_topic_score_gemma":0.005888319,"teacher_disagreement_score":0.003793252,"about_ca_system_score_codex":0.00050899223,"about_ca_system_score_gemma":0.00089608296,"threshold_uncertainty_score":0.007542312},"labels":[],"label_agreement":null},{"id":"W2092606521","doi":"10.1016/j.scitotenv.2014.01.006","title":"Unsupervised multiple endmember spectral mixture analysis-based detection of opium poppy fields from an EO-1 Hyperion image in Helmand, Afghanistan","year":2014,"lang":"en","type":"article","venue":"The Science of The Total Environment","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"Canada Research Chairs","keywords":"Endmember; Hyperspectral imaging; Opium Poppy; Opium; Remote sensing; Subpixel rendering; Pixel; Geography; Artificial intelligence; Computer science; Archaeology","score_opus":0.006401432904841494,"score_gpt":0.19404368213266562,"score_spread":0.18764224922782413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2092606521","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9961434,0.00009041816,0.002737596,0.000043897922,0.000010734835,0.000010148477,0.00027012287,0.00008498083,0.0006088854],"genre_scores_gemma":[0.9947897,0.00006202987,0.0042598406,0.000013485423,0.000009294144,0.000008176561,0.00036669907,0.000009973738,0.00048072592],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999242,0.0000080128175,0.000002866534,0.000017647013,0.000018967596,0.000028342203],"domain_scores_gemma":[0.99992645,0.000012192764,0.0000109028515,0.000005081013,0.000033600703,0.000011857279],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018475304,0.00029036147,0.00024446019,0.0015619849,0.00040682356,0.0003213725,0.00032271142,0.0002769893,0.00040225143],"category_scores_gemma":[0.00012643551,0.0001351066,0.0002613084,0.000737612,0.00019340044,0.00022126043,0.00025170535,0.0002162715,0.00019521161],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001356048,0.0005362259,0.22217867,0.00017025459,0.00019604144,0.00092610804,0.0008669914,0.013623043,0.57922405,0.00033493846,0.002279822,0.17830786],"study_design_scores_gemma":[0.000047118647,0.00010557997,0.8571478,0.000022094093,0.00012554371,0.00028613227,0.0009922493,0.10086746,0.038494878,0.00016430332,0.0017110514,0.000035802794],"about_ca_topic_score_codex":0.021536777,"about_ca_topic_score_gemma":0.044970192,"teacher_disagreement_score":0.021536777,"about_ca_system_score_codex":0.0002343815,"about_ca_system_score_gemma":0.0004062192,"threshold_uncertainty_score":0.042822838},"labels":[],"label_agreement":null},{"id":"W2094881545","doi":"10.1117/12.614435","title":"A fuzzy approach to supervised segmentation parameter selection for object-based classification","year":2005,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Segmentation; Artificial intelligence; Scale-space segmentation; Image segmentation; Segmentation-based object categorization; Fuzzy logic; Context (archaeology); Machine learning; Contextual image classification; Pattern recognition (psychology); Computer vision; Data mining; Image (mathematics)","score_opus":0.021040597202789238,"score_gpt":0.24015802138034079,"score_spread":0.21911742417755153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2094881545","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006952785,0.00004562499,0.9922012,0.00003537876,0.0000070652054,0.000027777714,0.000011200554,0.00012217359,0.0005966569],"genre_scores_gemma":[0.23497012,0.000081368285,0.76335293,0.00005713585,0.00003177591,0.00014382183,0.0000647284,0.000046882014,0.0012512516],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99959105,0.00010034515,0.000028483282,0.00008921095,0.0001669881,0.000024035155],"domain_scores_gemma":[0.9993901,0.0002718033,0.0000549443,0.000057545178,0.00020674257,0.000018845865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010613222,0.00035919758,0.00047423414,0.0008569468,0.0005384114,0.00059203076,0.00070460606,0.00063596177,0.0010905048],"category_scores_gemma":[0.002042064,0.00024098245,0.00045490134,0.00053692213,0.00060794846,0.0005427227,0.0003422003,0.00049138453,0.00024393725],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012346926,0.00012219221,0.0012880593,0.00011785285,0.000083457475,0.000104978346,0.00025912636,0.39893553,0.0442867,0.021399409,0.0013833527,0.53189594],"study_design_scores_gemma":[0.0000071949407,0.000038980183,0.00036963148,0.000007631982,0.000012972835,0.000046400168,0.000013969735,0.98663586,0.0060129375,0.0057511735,0.0010905871,0.00001259444],"about_ca_topic_score_codex":0.0021398743,"about_ca_topic_score_gemma":0.003432609,"teacher_disagreement_score":0.0021398743,"about_ca_system_score_codex":0.0007104587,"about_ca_system_score_gemma":0.0006701356,"threshold_uncertainty_score":0.00561285},"labels":[],"label_agreement":null},{"id":"W2097808723","doi":"10.1109/ccece.2008.4564653","title":"Calculation of abundance factors in hyperspectral imaging using genetic algorithm","year":2008,"lang":"en","type":"article","venue":"Conference proceedings - Canadian Conference on Electrical and Computer Engineering","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Hyperspectral imaging; Subpixel rendering; Pixel; Robustness (evolution); Computer science; Algorithm; Image resolution; Genetic algorithm; Abundance estimation; Constraint (computer-aided design); Pattern recognition (psychology); Artificial intelligence; Mathematics; Abundance (ecology); Machine learning","score_opus":0.020394133326600564,"score_gpt":0.1988114008907648,"score_spread":0.17841726756416423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097808723","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029105585,0.00010542822,0.9688544,0.00009128107,0.000015442174,0.00005014332,0.000019657953,0.00037071717,0.0013873088],"genre_scores_gemma":[0.27316475,0.00013977042,0.7246826,0.0000798563,0.000014935428,0.00024015507,0.00009192701,0.00006712606,0.0015188506],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997358,0.00008503325,0.000010905451,0.00005496855,0.00008670509,0.000026488713],"domain_scores_gemma":[0.99942064,0.00036037617,0.00005756796,0.000019591032,0.00012349823,0.000018339997],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007901174,0.00076476985,0.0007965538,0.00095804397,0.000469955,0.00063612056,0.00070741173,0.000927696,0.0010971224],"category_scores_gemma":[0.0022565918,0.00047882437,0.0005548349,0.00063099235,0.0005404261,0.0005897535,0.00048786803,0.0006703173,0.00021230802],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028968638,0.000038246046,0.00067564443,0.00003265697,0.00002792196,0.000033171495,0.000047806876,0.9389978,0.0028502205,0.004110299,0.00024710526,0.05291024],"study_design_scores_gemma":[0.0000053459034,0.000008164046,0.00007955546,0.0000031258542,0.000003550532,0.000006146259,0.0000053149147,0.99826705,0.000483337,0.0009878518,0.00014768024,0.0000028914333],"about_ca_topic_score_codex":0.006214548,"about_ca_topic_score_gemma":0.005016978,"teacher_disagreement_score":0.006214548,"about_ca_system_score_codex":0.00084133015,"about_ca_system_score_gemma":0.0012733187,"threshold_uncertainty_score":0.012356758},"labels":[],"label_agreement":null},{"id":"W2099375160","doi":"10.1109/igarss.2006.76","title":"Advantage of the Remote Sensing Data Utilization in Studying Inundation Risks in Terms of Land-Use","year":2006,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Remote sensing; Land cover; Flood myth; Environmental science; Radar; Cover (algebra); Land use; Geography; Computer science; Engineering; Civil engineering","score_opus":0.14266774619451209,"score_gpt":0.3207496655612381,"score_spread":0.178081919366726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099375160","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.958859,0.00065756164,0.023952557,0.00024464354,0.000029487805,0.00013413648,0.0027729375,0.00017943112,0.013170229],"genre_scores_gemma":[0.97569215,0.0003497713,0.02185607,0.00003976656,0.000024043165,0.00006231935,0.00078382384,0.000012851741,0.0011791307],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9997758,0.00010124351,0.000019519059,0.000027217167,0.00006459556,0.000011552666],"domain_scores_gemma":[0.999241,0.00036863703,0.00012228962,0.00007118487,0.00016509548,0.000031790147],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006081524,0.00042650313,0.00023758587,0.0015483386,0.00015304945,0.00045064065,0.00013898649,0.00021291495,0.0018511314],"category_scores_gemma":[0.0014152344,0.00010534536,0.00022288275,0.0018994423,0.00012016695,0.0004305768,0.00017151234,0.00014808762,0.00033746797],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041664523,0.0005317557,0.40643585,0.00045890416,0.00017985878,0.0006075363,0.00039223154,0.032046117,0.07122402,0.001679717,0.001354043,0.48467335],"study_design_scores_gemma":[0.000054647975,0.0008748105,0.8510205,0.000107471584,0.0003317225,0.0021047776,0.0011173493,0.10346253,0.02802976,0.0024337142,0.010369316,0.000093316936],"about_ca_topic_score_codex":0.0032230297,"about_ca_topic_score_gemma":0.007844814,"teacher_disagreement_score":0.0032230297,"about_ca_system_score_codex":0.00016612207,"about_ca_system_score_gemma":0.00020518484,"threshold_uncertainty_score":0.006408572},"labels":[],"label_agreement":null},{"id":"W2099609584","doi":"10.1109/igarss.2005.1525342","title":"Nonlinear feature extraction of hyperspectral data based on locally linear embedding (LLE)","year":2005,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":42,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Resources Canada; University of Victoria","funders":"","keywords":"Hyperspectral imaging; Feature extraction; Nonlinear system; Embedding; Pattern recognition (psychology); Computer science; Artificial intelligence; Extraction (chemistry); Remote sensing; Geology; Physics; Chemistry","score_opus":0.02833792529402468,"score_gpt":0.2927361114257568,"score_spread":0.2643981861317321,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099609584","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026865505,0.00012806752,0.9714225,0.000109938395,0.000017140606,0.000021932434,0.00010363987,0.00057782227,0.00075347495],"genre_scores_gemma":[0.40101558,0.0003245678,0.59308994,0.00008846026,0.00006035302,0.00013190588,0.0007015979,0.00021551347,0.0043721944],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998392,0.000039334016,0.000010530169,0.000032475004,0.000060946175,0.000017559294],"domain_scores_gemma":[0.9996927,0.000112423535,0.000052257772,0.000049902388,0.000077067314,0.000015544267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023487658,0.00044506456,0.00047086706,0.000532469,0.0001724898,0.0004604033,0.00031317276,0.00027968382,0.0012407936],"category_scores_gemma":[0.00095008843,0.00018426782,0.0003931513,0.0005768503,0.00026762133,0.0009654624,0.000498586,0.00057121547,0.00080202246],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018932346,0.00014044295,0.0012346058,0.0002074613,0.000050779956,0.0001088302,0.00011034969,0.053588394,0.22329211,0.0049512926,0.0033112313,0.7128152],"study_design_scores_gemma":[0.00000907955,0.000068127025,0.0021321974,0.000013497742,0.000019305657,0.000116027426,0.000032894695,0.94578266,0.04618708,0.003332879,0.0022812255,0.000025055793],"about_ca_topic_score_codex":0.0007166704,"about_ca_topic_score_gemma":0.0014477907,"teacher_disagreement_score":0.0012407936,"about_ca_system_score_codex":0.00014872767,"about_ca_system_score_gemma":0.00023092818,"threshold_uncertainty_score":0.0041508675},"labels":[],"label_agreement":null},{"id":"W2100717729","doi":"10.1109/igarss.2006.292","title":"Sensitivity of Spectral Unmixing Analysis to a Spectrally Dependent Gain Error in Hyperspectral Data","year":2006,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Resources Canada","funders":"","keywords":"Hyperspectral imaging; MODTRAN; Remote sensing; Radiance; Sensitivity (control systems); Full spectral imaging; Calibration; Spectral sensitivity; Radiometric calibration; Atmospheric correction; Computer science; Mathematics; Reflectivity; Optics; Statistics; Geology; Physics; Wavelength","score_opus":0.025901645746762163,"score_gpt":0.2595090902318524,"score_spread":0.23360744448509027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100717729","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8353267,0.00021876468,0.16165088,0.00014358037,0.00004564548,0.00015631453,0.0002503456,0.00067639415,0.0015314028],"genre_scores_gemma":[0.91790557,0.00009407596,0.080671564,0.000077512035,0.000012124968,0.0000789871,0.00052169187,0.0001474829,0.00049090903],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99609274,0.0011574087,0.00023907622,0.0009909624,0.0013329744,0.00018678838],"domain_scores_gemma":[0.9853313,0.010157745,0.0012025412,0.0015500451,0.001649658,0.00010880399],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006507321,0.00076049444,0.00045364816,0.00088640855,0.00046702524,0.0010481527,0.0004903951,0.00069488765,0.0005325505],"category_scores_gemma":[0.028376391,0.00032315106,0.00068710453,0.0010177086,0.00093452487,0.001259615,0.001160177,0.0006167364,0.0001855234],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024622704,0.000340979,0.036218967,0.00031908514,0.0004996794,0.00024517238,0.0007647964,0.6634217,0.18529503,0.0019612901,0.00044334505,0.10802772],"study_design_scores_gemma":[0.000048962072,0.0005295388,0.043054495,0.000048763417,0.00010653531,0.00028509673,0.0002832467,0.7261518,0.22628301,0.0019285121,0.0011746796,0.000105382445],"about_ca_topic_score_codex":0.0023495995,"about_ca_topic_score_gemma":0.002478571,"teacher_disagreement_score":0.006507321,"about_ca_system_score_codex":0.00065092725,"about_ca_system_score_gemma":0.00045729848,"threshold_uncertainty_score":0.03441441},"labels":[],"label_agreement":null},{"id":"W2102163346","doi":"10.1109/icassp.2009.4959823","title":"A noiseless code length method (NCLM) to estimate dimensionality of hyperspectral data","year":2009,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Hyperspectral imaging; Curse of dimensionality; Dimensionality reduction; Computer science; Dimension (graph theory); Pattern recognition (psychology); Artificial intelligence; Data set; Intrinsic dimension; Set (abstract data type); Data mining; Algorithm; Mathematics","score_opus":0.05649832009722446,"score_gpt":0.3664950342704845,"score_spread":0.3099967141732601,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102163346","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0046461644,0.00020474076,0.9944271,0.000077633566,0.000029131697,0.000024815454,0.000034014716,0.0002134383,0.00034290866],"genre_scores_gemma":[0.079863794,0.00030443963,0.9167022,0.00016551527,0.0000789683,0.0002160209,0.00028956507,0.00010216802,0.0022772835],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898356,0.00027616214,0.00006174299,0.00020048695,0.0004397393,0.00003825813],"domain_scores_gemma":[0.9976814,0.0010458396,0.00022854362,0.00028137094,0.0006989264,0.000063862186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013629614,0.0007585294,0.0006285758,0.0010355415,0.0005256049,0.00060881965,0.00092445605,0.0008797647,0.00090855977],"category_scores_gemma":[0.0057825404,0.00028803525,0.00052165915,0.000860043,0.00076051947,0.0012662286,0.0009851068,0.0011613584,0.0006002929],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022266335,0.00011011898,0.0020043545,0.00032715398,0.0000901991,0.00013292705,0.00027184337,0.26195437,0.043515258,0.019383026,0.0047707036,0.6672173],"study_design_scores_gemma":[0.000008964796,0.000045876404,0.00048181767,0.00002527158,0.00000978629,0.000103543236,0.000016710712,0.981106,0.012602899,0.002890096,0.0026743284,0.00003486437],"about_ca_topic_score_codex":0.0022523508,"about_ca_topic_score_gemma":0.0026826907,"teacher_disagreement_score":0.0022523508,"about_ca_system_score_codex":0.0006515159,"about_ca_system_score_gemma":0.0010751294,"threshold_uncertainty_score":0.007208109},"labels":[],"label_agreement":null},{"id":"W2102635064","doi":"10.1109/urs.2007.371788","title":"RADARSAT Fine-Beam SAR Data for Land-Cover Mapping and Change Detection in the Rural-Urban Fringe of the Greater Toronto Area","year":2007,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; U.S. Geological Survey","keywords":"Change detection; Land cover; Remote sensing; Land use; Geography; Environmental science; Cartography","score_opus":0.05807302643414383,"score_gpt":0.24333069226545181,"score_spread":0.18525766583130798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102635064","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9912175,0.0004917504,0.0020278941,0.000109192595,0.000008413279,0.000044320845,0.0019437656,0.000058810852,0.004098307],"genre_scores_gemma":[0.9936134,0.00021270225,0.002982627,0.000013914748,0.000006851349,0.0000086973105,0.0017330169,0.0000062408008,0.0014226108],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99987245,0.000026906988,0.000004658251,0.000017086493,0.000056317687,0.00002264603],"domain_scores_gemma":[0.9997634,0.000043106524,0.000043761058,0.000026314277,0.00008364511,0.00003970443],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001919072,0.00021371,0.00009406657,0.0006511367,0.00032209762,0.00031907673,0.00014006266,0.0001158494,0.0010308154],"category_scores_gemma":[0.000559677,0.00010065524,0.00009623556,0.00083005015,0.00013952321,0.00020421464,0.00014491337,0.000096786745,0.0001928995],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004380585,0.0001630917,0.70308024,0.0003733539,0.00014755677,0.00088889984,0.0024498005,0.015480332,0.0822438,0.00095915486,0.0107533,0.18302248],"study_design_scores_gemma":[0.00001098585,0.000047624293,0.9825905,0.000011134244,0.000024555997,0.00012455623,0.00049290835,0.009465696,0.0022111426,0.00006349303,0.0049457764,0.000011757907],"about_ca_topic_score_codex":0.4857628,"about_ca_topic_score_gemma":0.8350551,"teacher_disagreement_score":0.51423717,"about_ca_system_score_codex":0.0014991801,"about_ca_system_score_gemma":0.0009705723,"threshold_uncertainty_score":0.9658707},"labels":[],"label_agreement":null},{"id":"W2103540378","doi":"10.1109/igarss.2007.4423107","title":"Investigation of nonlinearity in hyperspectral remotely sensed imagery &amp;#x2014; a nonlinear time series analysis approach","year":2007,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Natural Resources Canada","funders":"","keywords":"Hyperspectral imaging; Nonlinear system; Computer science; Time series; Remote sensing; Time domain; Statistic; Artificial intelligence; Pattern recognition (psychology); Series (stratigraphy); Independent component analysis; Gaussian process; Gaussian; Data mining; Mathematics; Statistics; Computer vision; Machine learning; Geology","score_opus":0.02261955037291134,"score_gpt":0.23337807761128473,"score_spread":0.2107585272383734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103540378","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66388565,0.00017250073,0.33208203,0.0003103752,0.000015403177,0.000027207456,0.00009908464,0.000116705254,0.003291043],"genre_scores_gemma":[0.9785816,0.00009120642,0.02044923,0.00001798472,0.000010534827,0.0000164982,0.00007339861,0.000009493546,0.00075011334],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99976045,0.00007259329,0.0000115116745,0.000034188535,0.00010165748,0.00001949688],"domain_scores_gemma":[0.99872786,0.0008407861,0.00016675467,0.00006984115,0.00017005106,0.000024693287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005886994,0.00025835005,0.00018652307,0.0005997676,0.00018717031,0.00038627544,0.00017650245,0.00031621434,0.0005175188],"category_scores_gemma":[0.0026543771,0.000101143625,0.00019981047,0.0004219997,0.0005483527,0.00076307193,0.00026579254,0.0003404738,0.000079224796],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049815024,0.00023838007,0.06462447,0.0002803525,0.00013396928,0.0011854853,0.00075870735,0.5230298,0.16956802,0.04115665,0.0008754744,0.19765049],"study_design_scores_gemma":[0.0000018609344,0.000032725035,0.011009701,0.000004025837,0.000003976757,0.00009525077,0.00007289992,0.97794753,0.007676722,0.0028841116,0.000262317,0.000008892274],"about_ca_topic_score_codex":0.0018591161,"about_ca_topic_score_gemma":0.0015546557,"teacher_disagreement_score":0.0018591161,"about_ca_system_score_codex":0.00037302615,"about_ca_system_score_gemma":0.00036197153,"threshold_uncertainty_score":0.0036966205},"labels":[],"label_agreement":null},{"id":"W2103759232","doi":"10.1109/igarss.2008.4779171","title":"Supervised Region-Based Segmentation of Quickbird Multispectral Imagery","year":2008,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Multispectral image; Segmentation; Satellite imagery; Image segmentation; Remote sensing; Computer science; Artificial intelligence; Computer vision; Satellite; Multispectral pattern recognition; Scale-space segmentation; Geology","score_opus":0.02863145745441304,"score_gpt":0.22181896044477897,"score_spread":0.19318750299036594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103759232","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11088342,0.00032362706,0.883936,0.00007217653,0.000019760175,0.00016278049,0.00026154806,0.0017383717,0.0026023702],"genre_scores_gemma":[0.33419597,0.00021353264,0.66200966,0.000050410887,0.000029037568,0.00010397325,0.0007401611,0.00033792297,0.0023193255],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99952185,0.00010269688,0.000023585098,0.0001361411,0.00015273361,0.000062940104],"domain_scores_gemma":[0.99913764,0.00024246218,0.00012104123,0.00018050955,0.00028975063,0.000028544584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006937737,0.000385261,0.000517288,0.0017592743,0.00028667282,0.00079787866,0.0007715119,0.00051266234,0.0011754138],"category_scores_gemma":[0.0011879778,0.00034158689,0.00060418283,0.0007786412,0.00040393104,0.00068545545,0.00046813724,0.00030912485,0.0007680543],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005231806,0.00015685115,0.00531153,0.00032032517,0.000096098964,0.00021938643,0.00091961044,0.13887106,0.31263933,0.0045671933,0.003211694,0.5331638],"study_design_scores_gemma":[0.000025293364,0.00016058999,0.01367321,0.000029329987,0.000058290167,0.00029043463,0.00030472345,0.8405144,0.1344271,0.0038349696,0.0066297282,0.00005187036],"about_ca_topic_score_codex":0.002917772,"about_ca_topic_score_gemma":0.0064138165,"teacher_disagreement_score":0.002917772,"about_ca_system_score_codex":0.00037571072,"about_ca_system_score_gemma":0.0006289779,"threshold_uncertainty_score":0.0058015585},"labels":[],"label_agreement":null},{"id":"W2104673234","doi":"10.1109/tgrs.2003.817218","title":"Comparing Cooccurrence Probabilities and Markov Random Fields for Texture Analysis of SAR Sea Ice Imagery","year":2004,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":167,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Synthetic aperture radar; Segmentation; Computer science; Pattern recognition (psychology); Markov random field; Image segmentation; Image texture; Texture (cosmology); Feature (linguistics); Computer vision; Consistency (knowledge bases); Image (mathematics)","score_opus":0.018978251918311206,"score_gpt":0.2401398014572638,"score_spread":0.2211615495389526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104673234","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6054838,0.0016677778,0.38785788,0.0003546775,0.00010529312,0.00019232873,0.00044050693,0.0010930052,0.0028047415],"genre_scores_gemma":[0.916239,0.0004576286,0.08219561,0.000041322386,0.000080916725,0.00009965199,0.00047772165,0.0000663643,0.0003417981],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971301,0.0013952429,0.00015581597,0.00043798823,0.0007014223,0.00017938191],"domain_scores_gemma":[0.93633777,0.058038615,0.0016959605,0.0013576597,0.0019551956,0.0006147868],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0075470344,0.0007289075,0.0006887134,0.0048733014,0.00044364203,0.0012412564,0.0005482153,0.0011220761,0.00088180316],"category_scores_gemma":[0.03416863,0.00032269114,0.0008236836,0.0021040887,0.00073736324,0.0022055884,0.0008827401,0.0009204245,0.00032876414],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0050303345,0.00057077315,0.10825254,0.0005276947,0.00077246776,0.00026808065,0.00053522334,0.22453588,0.018271666,0.008523503,0.001823052,0.6308889],"study_design_scores_gemma":[0.000058678957,0.0003567065,0.030037027,0.000025808122,0.00010025005,0.00027937628,0.0001372978,0.9581953,0.0048950324,0.005396192,0.00044213,0.000076235025],"about_ca_topic_score_codex":0.0046403348,"about_ca_topic_score_gemma":0.0044900747,"teacher_disagreement_score":0.0075470344,"about_ca_system_score_codex":0.0007809076,"about_ca_system_score_gemma":0.0007524445,"threshold_uncertainty_score":0.039913},"labels":[],"label_agreement":null},{"id":"W2104853399","doi":"10.1109/igarss.1989.575840","title":"Textural Filtering For SAR Image Processing","year":2005,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Artificial intelligence; Pixel; Image texture; Computer vision; Computer science; Texture (cosmology); Pattern recognition (psychology); Feature (linguistics); Image processing; Multispectral image; Image (mathematics)","score_opus":0.01713444493952524,"score_gpt":0.24809678703237814,"score_spread":0.2309623420928529,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104853399","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032141192,0.018335564,0.9614863,0.00067585445,0.00085834385,0.00016592073,0.00049689825,0.001972307,0.012794782],"genre_scores_gemma":[0.08416338,0.027933376,0.8423725,0.00092199066,0.0022087328,0.0005530615,0.0018698964,0.000640855,0.03933625],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925476,0.00013189543,0.0000539116,0.00012495078,0.00040630568,0.000028039074],"domain_scores_gemma":[0.9994186,0.00022918098,0.000070611335,0.00010589306,0.00015830003,0.000017304346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000590727,0.00089299155,0.00059015525,0.0010818172,0.00032956558,0.0014621177,0.00071094744,0.001285221,0.010057504],"category_scores_gemma":[0.0017608629,0.00022664713,0.0006055872,0.00228732,0.00068600994,0.0011727946,0.00058832666,0.001307675,0.0070092524],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015929712,0.0000680226,0.0003523864,0.001292629,0.00009560686,0.0003317331,0.00015085646,0.01941936,0.06658612,0.058545053,0.025951698,0.8270472],"study_design_scores_gemma":[0.000058375485,0.00034081488,0.00381392,0.0006168012,0.00011729833,0.0016876365,0.00015720265,0.30667308,0.048870068,0.12367875,0.51381856,0.00016758154],"about_ca_topic_score_codex":0.0011356117,"about_ca_topic_score_gemma":0.00076340756,"teacher_disagreement_score":0.010057504,"about_ca_system_score_codex":0.00049919257,"about_ca_system_score_gemma":0.00032823515,"threshold_uncertainty_score":0.03364569},"labels":[],"label_agreement":null},{"id":"W2106987108","doi":"10.1109/ccece.1995.526583","title":"Fuzzy vector filters using novel distance criteria","year":2002,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Generalization; Fuzzy logic; Nonlinear system; Flexibility (engineering); Computer science; Filtering theory; Artificial intelligence; Mathematics; Filter (signal processing); Fuzzy set; Pattern recognition (psychology); Algorithm; Computer vision","score_opus":0.05542002825735463,"score_gpt":0.24793559628083023,"score_spread":0.1925155680234756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106987108","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060318355,0.0005042082,0.9922563,0.000056976613,0.000059366495,0.000018227935,0.0000140775865,0.00008047398,0.0009785062],"genre_scores_gemma":[0.23075604,0.0013342535,0.7607683,0.00012629054,0.00019950239,0.00017062815,0.00016087563,0.00007808663,0.0064059496],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99888057,0.00022962365,0.000093536815,0.00020674932,0.0005182998,0.00007115689],"domain_scores_gemma":[0.99898547,0.0003391536,0.000111397356,0.000069678055,0.0004481725,0.000046254303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001477039,0.00072396937,0.0009396417,0.00130768,0.00032229975,0.0015249439,0.00071819813,0.0011540552,0.00095448253],"category_scores_gemma":[0.002904377,0.00024497628,0.00078112335,0.0011594263,0.0006847663,0.0020407361,0.00077390467,0.0009650909,0.00041511172],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026773257,0.00011335992,0.0009542249,0.00039979175,0.00017977715,0.0001086426,0.00017955253,0.1486102,0.06981855,0.17791818,0.0030814903,0.5983684],"study_design_scores_gemma":[0.000035862275,0.00026923008,0.00075789995,0.000036143163,0.000048133952,0.00023772437,0.000038916547,0.94195896,0.017165827,0.028787745,0.01059874,0.00006475328],"about_ca_topic_score_codex":0.0014961916,"about_ca_topic_score_gemma":0.001125683,"teacher_disagreement_score":0.0015249439,"about_ca_system_score_codex":0.0009849867,"about_ca_system_score_gemma":0.00077181164,"threshold_uncertainty_score":0.0078113675},"labels":[],"label_agreement":null},{"id":"W2110844826","doi":"10.5589/m02-085","title":"Spectral unmixing of hyperspectral imagery for mineral exploration: comparison of results from SFSI and AVIRIS","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Hyperspectral imaging; Imaging spectrometer; Remote sensing; Alunite; Radiance; VNIR; Cuprite; Infrared; Spectral bands; Pixel; Geology; Spectrometer; Physics; Optics; Chemistry","score_opus":0.03770267051101854,"score_gpt":0.25016739012265987,"score_spread":0.21246471961164132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110844826","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9092322,0.00040335712,0.081066154,0.000110965644,0.00002723415,0.00011153346,0.0012823927,0.0025524981,0.005213598],"genre_scores_gemma":[0.81670123,0.00025366188,0.17508622,0.0000491799,0.000018013541,0.000082002574,0.004667492,0.00040240132,0.0027397678],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993704,0.000078799785,0.000028111403,0.000108844964,0.00036767247,0.000046247507],"domain_scores_gemma":[0.9989672,0.00024540382,0.000075072756,0.00011724337,0.00055703823,0.00003804255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012698628,0.00051904406,0.00034053597,0.001502485,0.00024925938,0.0005364952,0.0003501025,0.00026250997,0.0015221649],"category_scores_gemma":[0.0027902713,0.00019259883,0.00048637288,0.0009160776,0.00021881505,0.00088569266,0.0004896786,0.00019256928,0.0007032956],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013960133,0.00029909998,0.06091165,0.00048530087,0.00031637895,0.000090014975,0.0009882916,0.028844303,0.38742322,0.00054492994,0.0022902552,0.5164105],"study_design_scores_gemma":[0.00008136581,0.00025443957,0.4549525,0.000066943605,0.00022385812,0.00030099181,0.0010329124,0.29257774,0.24047169,0.0007883515,0.009126209,0.00012303154],"about_ca_topic_score_codex":0.0071598524,"about_ca_topic_score_gemma":0.016655697,"teacher_disagreement_score":0.0071598524,"about_ca_system_score_codex":0.00029994873,"about_ca_system_score_gemma":0.0003108167,"threshold_uncertainty_score":0.014236391},"labels":[],"label_agreement":null},{"id":"W2111829195","doi":"10.1109/igarss.1996.516527","title":"Temporal mixture analysis of SMMR sea ice concentrations","year":2002,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Endmember; Sea ice; Remote sensing; Geology; Northern Hemisphere; Spectral analysis; Oceanography; Climatology; Physics; Hyperspectral imaging","score_opus":0.02064398993078247,"score_gpt":0.22020857653029147,"score_spread":0.199564586599509,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111829195","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027069103,0.00016125315,0.97085255,0.00009693221,0.000040960236,0.000012668238,0.00019918734,0.00033077862,0.0012365477],"genre_scores_gemma":[0.5482822,0.000539578,0.44106284,0.000089655674,0.00016398773,0.00008151713,0.001385546,0.0002603365,0.0081343725],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997651,0.000044510503,0.000014335585,0.000054278673,0.00009549881,0.000026342594],"domain_scores_gemma":[0.99965966,0.00013137968,0.000047336354,0.000049525825,0.00009663737,0.000015535497],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000720951,0.0005034481,0.00031492306,0.0014761665,0.00022258163,0.0006843089,0.00034872643,0.0002875356,0.0012813056],"category_scores_gemma":[0.0015211347,0.00022475555,0.0007230613,0.0011009402,0.00016095354,0.0005533047,0.0005062758,0.00047054287,0.00039281542],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039172592,0.00012078931,0.01659327,0.00009791943,0.00038798826,0.00016655863,0.00016010975,0.26062462,0.07175315,0.03890787,0.0030217236,0.60777426],"study_design_scores_gemma":[0.000003732904,0.0000416952,0.0063501843,0.0000057463176,0.00003710298,0.00010291563,0.000023131703,0.97543633,0.0076414533,0.0062894234,0.0040437686,0.000024474062],"about_ca_topic_score_codex":0.0038934501,"about_ca_topic_score_gemma":0.0054627084,"teacher_disagreement_score":0.0038934501,"about_ca_system_score_codex":0.00030790654,"about_ca_system_score_gemma":0.0002571356,"threshold_uncertainty_score":0.00774163},"labels":[],"label_agreement":null},{"id":"W2112824482","doi":"","title":"Texture-Integrated Classification of Urban Treed Areas in High-Resolution Color-Infrared Imagery","year":2001,"lang":"en","type":"article","venue":"Photogrammetric Engineering & Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":75,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Multispectral image; Artificial intelligence; Computer science; Remote sensing; Texture (cosmology); Pattern recognition (psychology); Variance (accounting); Pixel; Geography; Computer vision; Image (mathematics)","score_opus":0.014151912555960175,"score_gpt":0.21488234734485445,"score_spread":0.20073043478889427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112824482","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6388779,0.00028347856,0.3579978,0.000053612264,0.000023795064,0.00003261936,0.00018438947,0.00074870995,0.0017977259],"genre_scores_gemma":[0.8940222,0.00012176627,0.10457676,0.000015082738,0.000012334086,0.000013855462,0.00034766603,0.00002881567,0.0008614728],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998233,0.000025675474,0.000007469695,0.000030168281,0.00008781167,0.000025612768],"domain_scores_gemma":[0.9997576,0.000053504074,0.000038543014,0.000025580573,0.00010820878,0.000016598831],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025887793,0.00018891072,0.00021421615,0.0013895194,0.000099555,0.00042747718,0.00016074281,0.00020506905,0.00042923505],"category_scores_gemma":[0.00062674703,0.00012333671,0.0002443537,0.00065008097,0.000196349,0.00047298445,0.00017686366,0.00015142365,0.0002550514],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049522496,0.00016000538,0.026158035,0.00019775202,0.000074344585,0.00014447715,0.00012280399,0.03065686,0.40468612,0.0013040686,0.0012306593,0.5347696],"study_design_scores_gemma":[0.000038196973,0.00020321898,0.14865239,0.000016656559,0.00010597073,0.000653783,0.00014068434,0.73461086,0.11247246,0.0010750929,0.0019898121,0.000040834868],"about_ca_topic_score_codex":0.001487142,"about_ca_topic_score_gemma":0.003215685,"teacher_disagreement_score":0.001487142,"about_ca_system_score_codex":0.00017000381,"about_ca_system_score_gemma":0.00013529639,"threshold_uncertainty_score":0.0029569864},"labels":[],"label_agreement":null},{"id":"W2112982660","doi":"10.1109/eorsa.2008.4620334","title":"Investigation of diversity and accuracy in ensemble of classifiers using Bayesian decision rules","year":2008,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Hong Kong Government; University of Hong Kong","keywords":"Artificial intelligence; Classifier (UML); Computer science; Machine learning; Naive Bayes classifier; Random subspace method; Pattern recognition (psychology); Bayesian probability; Majority rule; Test data; Quadratic classifier; Data mining; Support vector machine","score_opus":0.07469978510964467,"score_gpt":0.24971254702352508,"score_spread":0.1750127619138804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112982660","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6850449,0.001308624,0.31024784,0.00023845307,0.00007384853,0.00008798019,0.00019467097,0.00040401611,0.002399794],"genre_scores_gemma":[0.9548043,0.0002455759,0.044352047,0.000026737758,0.0000455368,0.000034703546,0.00019524702,0.000023000443,0.00027291663],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.993828,0.0018722687,0.00056276476,0.0010044142,0.0023070143,0.00042556963],"domain_scores_gemma":[0.97497016,0.016567055,0.0014555141,0.0017110154,0.0049231844,0.0003730546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012309879,0.00089383434,0.0019401669,0.0033096499,0.00076274405,0.0016815347,0.0010638584,0.001339706,0.00038497316],"category_scores_gemma":[0.03019513,0.00045079103,0.0013340057,0.0016913869,0.00048678266,0.0030988615,0.00097016094,0.0009266032,0.00019809428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010743382,0.0002686526,0.09427279,0.00024043335,0.0009513459,0.00035615268,0.0009269244,0.4744516,0.0139447935,0.0029844653,0.0009107354,0.40961775],"study_design_scores_gemma":[0.000011271286,0.00026856348,0.012104689,0.000024269317,0.00014272075,0.00011836581,0.00010694042,0.98054916,0.004828107,0.0014431457,0.00036736432,0.00003542613],"about_ca_topic_score_codex":0.0036825202,"about_ca_topic_score_gemma":0.0021440468,"teacher_disagreement_score":0.012309879,"about_ca_system_score_codex":0.0008373656,"about_ca_system_score_gemma":0.00059076416,"threshold_uncertainty_score":0.06510162},"labels":[],"label_agreement":null},{"id":"W2113075278","doi":"10.1109/icip.2009.5414312","title":"Optimum kernel function design from scale space features for object detection","year":2009,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Quadratic programming; Mathematics; Kernel (algebra); Orthant; Pattern recognition (psychology); Kernel method; Radial basis function kernel; Artificial intelligence; Mathematical optimization; Support vector machine; Computer science; Algorithm; Applied mathematics","score_opus":0.014812827580662682,"score_gpt":0.21499398421583873,"score_spread":0.20018115663517605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113075278","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006653247,0.000058713013,0.9929376,0.000041299758,0.0000042213783,0.000011883695,0.0000092713035,0.00012109213,0.00016274677],"genre_scores_gemma":[0.2661497,0.0001902071,0.7321811,0.000049725397,0.000030496585,0.00017360406,0.00013697137,0.00016054556,0.00092770247],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99929285,0.00024121327,0.000045599623,0.00012463088,0.0002341909,0.00006143894],"domain_scores_gemma":[0.9986187,0.0006185482,0.00018513194,0.00013037017,0.00040169345,0.000045605906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018593621,0.0006629779,0.00093351613,0.0009682794,0.0002361813,0.0007464066,0.00078820094,0.0010206739,0.0011234061],"category_scores_gemma":[0.0056023807,0.00051307713,0.0006175122,0.00086332887,0.00062141474,0.0015254281,0.0007260574,0.00084576505,0.0006235553],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000417771,0.00017383575,0.0013120204,0.00025080965,0.00008523491,0.000081710255,0.00017294927,0.4988032,0.062382005,0.036476776,0.0031234045,0.39672032],"study_design_scores_gemma":[0.000011690025,0.000029294279,0.00019878606,0.0000036356714,0.0000063025673,0.000023518194,0.0000070369524,0.9913163,0.0040742606,0.0038824696,0.00043772926,0.000008921029],"about_ca_topic_score_codex":0.0006964556,"about_ca_topic_score_gemma":0.0005697743,"teacher_disagreement_score":0.0018593621,"about_ca_system_score_codex":0.00062450004,"about_ca_system_score_gemma":0.0006551042,"threshold_uncertainty_score":0.0098333955},"labels":[],"label_agreement":null},{"id":"W2114139922","doi":"10.5194/isprsannals-ii-2-87-2014","title":"An Integrated Method for Mapping Impervious and Pervious Areas in Urban Environments Using Hyperspectral and LiDAR Data","year":2014,"lang":"en","type":"article","venue":"ISPRS annals of the photogrammetry, remote sensing and spatial information sciences","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"TD Bank Group","funders":"","keywords":"Impervious surface; Hyperspectral imaging; Lidar; Remote sensing; Environmental science; Vegetation (pathology); Geospatial analysis; Point cloud; Geography; Computer science","score_opus":0.0686281963827949,"score_gpt":0.318248467616271,"score_spread":0.24962027123347613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114139922","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20140295,0.00028009416,0.7924801,0.00007817159,0.000036826335,0.00026304933,0.00086503034,0.0014902476,0.0031035263],"genre_scores_gemma":[0.3393685,0.00013729757,0.65775913,0.000029411358,0.000013953172,0.000159527,0.0006362628,0.00004423943,0.0018517645],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9997004,0.000036062218,0.0000174143,0.0000695784,0.00014766694,0.000028954815],"domain_scores_gemma":[0.9997223,0.000033767774,0.00003024572,0.000020431286,0.00017812288,0.000014985802],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040946325,0.00047234603,0.00030140844,0.003056128,0.00026566003,0.00060678984,0.00038179022,0.00027809167,0.0011734767],"category_scores_gemma":[0.00042354868,0.00024574783,0.0003866118,0.0015882509,0.0001808028,0.00057936093,0.000495547,0.00025312693,0.00036559504],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015524012,0.00025719192,0.030887362,0.00024319945,0.00014847243,0.00013199418,0.00028999796,0.015058854,0.16433097,0.0012283942,0.0018096418,0.7854586],"study_design_scores_gemma":[0.000039086557,0.00016303005,0.09047134,0.000046443758,0.00014293261,0.0005034972,0.0007298049,0.81113774,0.08771256,0.0011747784,0.0078002773,0.00007857842],"about_ca_topic_score_codex":0.005162647,"about_ca_topic_score_gemma":0.016301354,"teacher_disagreement_score":0.005162647,"about_ca_system_score_codex":0.00029094174,"about_ca_system_score_gemma":0.00058151025,"threshold_uncertainty_score":0.010265231},"labels":[],"label_agreement":null},{"id":"W2114152819","doi":"10.1109/igarss.2000.859676","title":"Statistical characterization of the diffuse attenuation coefficient over tropical corals","year":2002,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Water column; SeaWiFS; Remote sensing; Radiance; Irradiance; Coral; Attenuation; Coral reef; Reef; Environmental science; Geology; Downwelling; Attenuation coefficient; Oceanography; Upwelling; Ecology; Optics; Phytoplankton","score_opus":0.01978399790164029,"score_gpt":0.216881151795499,"score_spread":0.1970971538938587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114152819","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99165815,0.0000635071,0.007418465,0.000025209609,0.0000016259567,0.0000042102097,0.000325247,0.000045486828,0.0004580609],"genre_scores_gemma":[0.9984251,0.000044737277,0.0009014901,0.0000038580934,0.00000436558,0.0000035920216,0.0004989672,0.0000062786708,0.00011168614],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9998528,0.00002575525,0.000011311735,0.000037249974,0.000040862782,0.00003201602],"domain_scores_gemma":[0.998206,0.0008236683,0.00036838517,0.00013896739,0.00035351134,0.00010938896],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058922084,0.000165384,0.00012693091,0.0010696795,0.00010433335,0.0002685535,0.00014714441,0.00012971491,0.0004750329],"category_scores_gemma":[0.002747196,0.000091740454,0.00016041943,0.0007147933,0.00025968556,0.00023387522,0.00016208366,0.00019165191,0.00012090531],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002567572,0.000043528147,0.8348512,0.0000805267,0.00011784228,0.00017509503,0.00025300327,0.03991671,0.049755424,0.0007670901,0.0005512592,0.0732316],"study_design_scores_gemma":[0.0000036199567,0.0000414724,0.9415302,0.00000435215,0.000021586671,0.00020721277,0.000118460244,0.053901307,0.003554392,0.00021373334,0.00038840043,0.000015214621],"about_ca_topic_score_codex":0.00783942,"about_ca_topic_score_gemma":0.0061745984,"teacher_disagreement_score":0.00783942,"about_ca_system_score_codex":0.00019489617,"about_ca_system_score_gemma":0.00020062926,"threshold_uncertainty_score":0.015587568},"labels":[],"label_agreement":null},{"id":"W2114194579","doi":"10.1109/tgrs.2011.2125974","title":"Simultaneous Denoising and Intrinsic Order Selection in Hyperspectral Imaging","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Noise reduction; Hyperspectral imaging; Singular value decomposition; Computer science; Noise (video); Dimensionality reduction; Dimension (graph theory); Pattern recognition (psychology); Minification; Mathematical optimization; Selection (genetic algorithm); Algorithm; Artificial intelligence; Mathematics; Image (mathematics)","score_opus":0.01297791958946163,"score_gpt":0.21324042174033847,"score_spread":0.20026250215087685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114194579","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008781453,0.0003855862,0.98947924,0.00008494602,0.000031436808,0.000013106648,0.000017667426,0.00009382702,0.0011127202],"genre_scores_gemma":[0.18995589,0.0012726348,0.8034293,0.00011422592,0.00012069749,0.0000710807,0.00015677782,0.00017261127,0.0047066864],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906105,0.0001860772,0.00003640955,0.00022615066,0.00043915058,0.000051179773],"domain_scores_gemma":[0.99925846,0.00034160458,0.00011550108,0.00011086295,0.00014574439,0.000027790347],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010727063,0.0008052019,0.0007959711,0.0007553412,0.00039666577,0.000881489,0.0007497665,0.00085261784,0.0005592078],"category_scores_gemma":[0.0019696455,0.00048744038,0.0008758766,0.0007772305,0.001221908,0.0014610501,0.0011874948,0.0011049311,0.00038139752],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020537444,0.00012563859,0.0019336966,0.000513162,0.0001320228,0.0003407689,0.00046898372,0.35864884,0.18691774,0.08632213,0.002003385,0.36238825],"study_design_scores_gemma":[0.0000072480093,0.000049917206,0.00054292614,0.000016315083,0.000023577306,0.00014037114,0.000033646076,0.9404654,0.03773369,0.017942194,0.0030113359,0.000033410484],"about_ca_topic_score_codex":0.0009521177,"about_ca_topic_score_gemma":0.0017326559,"teacher_disagreement_score":0.0010727063,"about_ca_system_score_codex":0.0005299367,"about_ca_system_score_gemma":0.00054132054,"threshold_uncertainty_score":0.005673051},"labels":[],"label_agreement":null},{"id":"W2114388392","doi":"10.1109/pacrim.2009.5291332","title":"The Noiseless code-length concept in subspace estimation for low SNR hyperspectral signals","year":2009,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Hyperspectral imaging; Curse of dimensionality; Noise (video); Subspace topology; Signal subspace; Computer science; A priori and a posteriori; Pattern recognition (psychology); Rank (graph theory); Code (set theory); Artificial intelligence; Algorithm; Mathematics; Image (mathematics)","score_opus":0.012279696151512115,"score_gpt":0.247952902604143,"score_spread":0.23567320645263087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114388392","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008463476,0.0002995696,0.99054575,0.00010050204,0.000015528629,0.000011826656,0.00002607231,0.00008012164,0.00045713797],"genre_scores_gemma":[0.27546135,0.0008824549,0.7205469,0.00017085303,0.00020447532,0.00015662798,0.0002753178,0.00011702959,0.002184883],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99907684,0.00037041376,0.000035203586,0.00013641155,0.00033910293,0.000042035565],"domain_scores_gemma":[0.997248,0.0016870255,0.00030313988,0.00026763405,0.0004248244,0.00006928542],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015896851,0.0006014921,0.00044665972,0.0008936108,0.00036699552,0.00069166935,0.0006452401,0.0007803671,0.00063494523],"category_scores_gemma":[0.008056926,0.00028125537,0.0003038632,0.00090840703,0.0014934835,0.0015863767,0.0008694329,0.0010430521,0.0003842113],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029267906,0.00007581269,0.0017519837,0.000245378,0.000046780126,0.0001364972,0.00022054251,0.58671016,0.03213458,0.12915257,0.0020422405,0.24719079],"study_design_scores_gemma":[0.000007995938,0.000042868684,0.00031199396,0.000017166836,0.000004848889,0.000056559733,0.000012662257,0.9706654,0.006910649,0.020814478,0.0011260584,0.00002928647],"about_ca_topic_score_codex":0.001388358,"about_ca_topic_score_gemma":0.001054023,"teacher_disagreement_score":0.0015896851,"about_ca_system_score_codex":0.0005646532,"about_ca_system_score_gemma":0.00066417886,"threshold_uncertainty_score":0.008407176},"labels":[],"label_agreement":null},{"id":"W2114390005","doi":"10.5194/isprsarchives-xxxix-b7-191-2012","title":"NEW COMBINED PIXEL/OBJECT-BASED TECHNIQUE FOR EFFICIENT URBAN CLASSSIFICATION USING WORLDVIEW-2 DATA","year":2012,"lang":"en","type":"article","venue":"˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Land cover; Remote sensing; Computer science; Confusion; Spectral bands; Similarity (geometry); Object (grammar); Artificial intelligence; Vegetation (pathology); Set (abstract data type); Satellite; Satellite imagery; Pixel; Image resolution; Pattern recognition (psychology); Computer vision; Land use; Geography; Image (mathematics); Engineering; Civil engineering","score_opus":0.03670750681479027,"score_gpt":0.2777056929018421,"score_spread":0.24099818608705184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114390005","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06821993,0.0002406472,0.9192533,0.00012211478,0.00008716355,0.00020778726,0.0016722676,0.006800327,0.0033964429],"genre_scores_gemma":[0.11658985,0.00017114841,0.87741137,0.000050586936,0.000023465887,0.00014188918,0.0029683274,0.0002676628,0.0023756335],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999572,0.000041126536,0.000019904837,0.000108825705,0.00021040137,0.000047697245],"domain_scores_gemma":[0.9995976,0.00003638411,0.00004558083,0.000072125986,0.00022774209,0.000020562728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058923516,0.00059583085,0.00048731518,0.0026188777,0.00026496238,0.0009013566,0.00081010786,0.00041947336,0.0037052755],"category_scores_gemma":[0.0005800671,0.00029743198,0.00059228134,0.0016412861,0.00015671973,0.0010046522,0.0006803507,0.0005951001,0.002735218],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018954031,0.00019224132,0.006261357,0.00018314882,0.0001217145,0.00009977934,0.00013359058,0.0077860225,0.1341317,0.0014002377,0.007401865,0.8420988],"study_design_scores_gemma":[0.000049098093,0.0001585828,0.040939454,0.00004647055,0.000118548734,0.00047763114,0.00032408186,0.6921367,0.23198166,0.0015542177,0.032114986,0.000098598415],"about_ca_topic_score_codex":0.002291554,"about_ca_topic_score_gemma":0.0042422037,"teacher_disagreement_score":0.0037052755,"about_ca_system_score_codex":0.00023455721,"about_ca_system_score_gemma":0.00041270233,"threshold_uncertainty_score":0.012395322},"labels":[],"label_agreement":null},{"id":"W2118178926","doi":"10.1109/icmtma.2010.762","title":"Semisupervised Hyperspectral Image Classification with SVM and PSO","year":2010,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Hyperspectral imaging; Particle swarm optimization; Artificial intelligence; Support vector machine; Pattern recognition (psychology); Computer science; Set (abstract data type); Image (mathematics); Process (computing); Training set; Contextual image classification; Machine learning","score_opus":0.007417285213932561,"score_gpt":0.19874508568001914,"score_spread":0.19132780046608658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118178926","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024245556,0.00019770696,0.97398686,0.00008350429,0.000021440666,0.000024913768,0.000015775979,0.0003090008,0.0011152279],"genre_scores_gemma":[0.49977955,0.00021070054,0.4972926,0.00008330154,0.000082677565,0.00013080823,0.0001343353,0.00007146623,0.0022145307],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994985,0.00018036271,0.000031305055,0.00008755054,0.00017628561,0.00002593437],"domain_scores_gemma":[0.99925643,0.00029890006,0.00015155146,0.000091804875,0.00017735439,0.000023940604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005671116,0.0004330055,0.0007479934,0.00054050365,0.00022678697,0.000517216,0.0005782866,0.00063732394,0.00056493847],"category_scores_gemma":[0.0014778655,0.0002613976,0.00047360978,0.00043660233,0.00040897192,0.0009003643,0.0005052846,0.00058332906,0.0002851439],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029733294,0.00033025508,0.0034024576,0.00024269387,0.00019035133,0.00016081662,0.0001826585,0.37995744,0.04438291,0.011339259,0.002405359,0.55710846],"study_design_scores_gemma":[0.0000062297495,0.000024822937,0.00034136864,0.0000038269995,0.000003942386,0.000028860955,0.0000070017713,0.9959525,0.0020881053,0.0011616932,0.00037678276,0.0000048110032],"about_ca_topic_score_codex":0.00075433165,"about_ca_topic_score_gemma":0.0010057047,"teacher_disagreement_score":0.00075433165,"about_ca_system_score_codex":0.00021861526,"about_ca_system_score_gemma":0.00027223505,"threshold_uncertainty_score":0.0029991865},"labels":[],"label_agreement":null},{"id":"W2118283163","doi":"10.1109/igarss.2007.4423938","title":"New object-oriented approach for urban objects extraction from VHSR images","year":2007,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Pixel; Artificial intelligence; Multispectral image; Computer vision; Object (grammar); Ground truth; Segmentation; Image resolution; Image segmentation; Object detection; Base (topology); Fuzzy logic; Pattern recognition (psychology); Mathematics","score_opus":0.014429296508057275,"score_gpt":0.2450042219127678,"score_spread":0.23057492540471053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118283163","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0062400955,0.0001823098,0.9922341,0.000033638316,0.000013824043,0.0000599426,0.000044105967,0.0005408336,0.0006511435],"genre_scores_gemma":[0.04171923,0.00023430935,0.9559905,0.00004417932,0.000022638995,0.00009072186,0.00023741818,0.000074327516,0.0015867786],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994166,0.000097639524,0.000045662327,0.00013434363,0.0002592625,0.000046565554],"domain_scores_gemma":[0.99958855,0.00009116506,0.000032870947,0.00004821033,0.00022136583,0.00001781302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069998193,0.0005626399,0.00076539547,0.0029911688,0.0003982167,0.0011709087,0.0010056477,0.00058968295,0.0015833012],"category_scores_gemma":[0.0006055246,0.00040553493,0.00091368344,0.001196648,0.0005560141,0.0009834283,0.00041552924,0.0004976333,0.00085699547],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000119493525,0.00015471724,0.0017047367,0.0004078942,0.00013452698,0.00018111564,0.00023416501,0.023280086,0.15225488,0.011219867,0.0018602891,0.80844826],"study_design_scores_gemma":[0.000049306225,0.00025922596,0.012016538,0.00008273334,0.00021632285,0.0011358258,0.000412477,0.798003,0.13851143,0.017310064,0.03185543,0.0001475337],"about_ca_topic_score_codex":0.002333359,"about_ca_topic_score_gemma":0.003681084,"teacher_disagreement_score":0.0029911688,"about_ca_system_score_codex":0.0004902308,"about_ca_system_score_gemma":0.0006090231,"threshold_uncertainty_score":0.005296707},"labels":[],"label_agreement":null},{"id":"W2119241338","doi":"10.1109/rsete.2011.5965626","title":"Urban land-cover classification based on swarm intelligence from high resolution remote sensing imagery","year":2011,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Land cover; Computer science; Remote sensing; Contextual image classification; Classifier (UML); Particle swarm optimization; Artificial intelligence; High resolution; Statistical classification; Pattern recognition (psychology); Land use; Geography; Machine learning; Image (mathematics); Engineering","score_opus":0.045438617417311304,"score_gpt":0.226961048688635,"score_spread":0.1815224312713237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119241338","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4359764,0.00032867526,0.559767,0.0002607659,0.0000538903,0.0001120921,0.00011050055,0.00060847105,0.0027821674],"genre_scores_gemma":[0.8800269,0.00013581513,0.118779086,0.00002741424,0.000024818364,0.00004543297,0.00020939666,0.000021486616,0.00072963734],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998547,0.000038240985,0.0000094689,0.000027277576,0.000056369183,0.000014037382],"domain_scores_gemma":[0.99960464,0.00020953278,0.0000558399,0.000031838805,0.0000816374,0.00001649839],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044319037,0.00027182268,0.0004076961,0.00094685686,0.00020519052,0.0005508712,0.0002224452,0.00025929295,0.00035362868],"category_scores_gemma":[0.0012311918,0.00018134443,0.00037071353,0.00046754928,0.00027659055,0.00054531766,0.00018974347,0.0002772562,0.00014986584],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021084478,0.00021603178,0.020749079,0.00016578873,0.00018027991,0.0002031439,0.00021351577,0.58035547,0.03472921,0.002360881,0.0014881267,0.35912758],"study_design_scores_gemma":[0.000005951393,0.000026703216,0.0031805758,0.0000031406082,0.000008651442,0.00001743263,0.000016497817,0.9944147,0.0017118562,0.00044798933,0.00016271182,0.0000038276075],"about_ca_topic_score_codex":0.002971445,"about_ca_topic_score_gemma":0.0028032893,"teacher_disagreement_score":0.002971445,"about_ca_system_score_codex":0.0002878705,"about_ca_system_score_gemma":0.00015751766,"threshold_uncertainty_score":0.0059083104},"labels":[],"label_agreement":null},{"id":"W2120888261","doi":"10.1080/01431161003777197","title":"The effects of combining classifiers with the same training statistics using Bayesian decision rules","year":2011,"lang":"en","type":"article","venue":"International Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Classifier (UML); Artificial intelligence; Quadratic classifier; Pattern recognition (psychology); Margin classifier; Computer science; Probabilistic classification; Random subspace method; Machine learning; Naive Bayes classifier; Bayes classifier; Support vector machine","score_opus":0.026964945614490816,"score_gpt":0.2552951824018456,"score_spread":0.2283302367873548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120888261","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30429098,0.0033910081,0.6845911,0.0006637831,0.00031069986,0.000560861,0.00016740224,0.00095984177,0.0050643026],"genre_scores_gemma":[0.69730246,0.0011185164,0.2992791,0.0003513121,0.0002871736,0.00034019194,0.0003371868,0.00013109128,0.0008529406],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9791037,0.009994388,0.001994315,0.0030184982,0.0049958383,0.000893162],"domain_scores_gemma":[0.92851925,0.054984186,0.0038531732,0.0054013603,0.0064600767,0.00078189257],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03068539,0.0036824415,0.0036524762,0.0036636512,0.0016129198,0.0033390757,0.0019456595,0.0030472714,0.00093487307],"category_scores_gemma":[0.07344321,0.0016705737,0.0028926437,0.0020359124,0.0012494124,0.0066446685,0.003106584,0.0026584677,0.00082402583],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002519762,0.00095311267,0.040185474,0.0006147182,0.0025746794,0.00031892044,0.0007693859,0.36186975,0.020746768,0.0024968162,0.0011214078,0.5658292],"study_design_scores_gemma":[0.00016660447,0.0028078964,0.015025903,0.0002670548,0.0018935099,0.00048818334,0.00036894318,0.93911153,0.027760118,0.009513007,0.0023215483,0.00027572838],"about_ca_topic_score_codex":0.0028891882,"about_ca_topic_score_gemma":0.0036048258,"teacher_disagreement_score":0.03068539,"about_ca_system_score_codex":0.0009617817,"about_ca_system_score_gemma":0.0010055514,"threshold_uncertainty_score":0.16228181},"labels":[],"label_agreement":null},{"id":"W2121490093","doi":"10.1109/tip.2008.920761","title":"Segmentation by Fusion of Histogram-Based $K$-Means Clusters in Different Color Spaces","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":212,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Artificial intelligence; Segmentation; Scale-space segmentation; Histogram; Image segmentation; Computer science; Segmentation-based object categorization; Pattern recognition (psychology); Cluster analysis; Computer vision; Minimum spanning tree-based segmentation; Partition (number theory); Region growing; Mathematics; Image (mathematics)","score_opus":0.014560373048676122,"score_gpt":0.23042199580236464,"score_spread":0.2158616227536885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121490093","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01565658,0.0001895682,0.98069674,0.000049417504,0.000044366814,0.00006392624,0.000071933384,0.0021107544,0.0011167519],"genre_scores_gemma":[0.15687831,0.00026389046,0.8398632,0.000063966574,0.000047122023,0.000104403895,0.00046306,0.00055472157,0.001761352],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985819,0.00020654422,0.000078794175,0.0003512645,0.000607329,0.00017420905],"domain_scores_gemma":[0.9988642,0.00026204812,0.00010637558,0.00022828556,0.00048941537,0.000049781924],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015259302,0.0013093224,0.0016881716,0.00363949,0.0009723164,0.001962842,0.0014821106,0.001292602,0.001873512],"category_scores_gemma":[0.0032182122,0.00076153694,0.0016853068,0.0032162992,0.0009940634,0.0021559075,0.0016974784,0.0011350093,0.0022589755],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00072010286,0.00018225335,0.0018487079,0.00035349306,0.00031243917,0.00012911047,0.0007156682,0.13385603,0.117307834,0.009096159,0.0043344097,0.7311438],"study_design_scores_gemma":[0.000038954837,0.00015529656,0.003618896,0.000043839136,0.00014476487,0.00019178228,0.0003006381,0.8770409,0.09497193,0.01574296,0.007576464,0.00017348325],"about_ca_topic_score_codex":0.00610824,"about_ca_topic_score_gemma":0.00622152,"teacher_disagreement_score":0.00610824,"about_ca_system_score_codex":0.001023902,"about_ca_system_score_gemma":0.0012162477,"threshold_uncertainty_score":0.0121454},"labels":[],"label_agreement":null},{"id":"W2121819232","doi":"10.1109/ccece.2006.277618","title":"Projection Pursuit Feature Analysis for Pan-Sharpened Multispectral Ikonos Imagery","year":2006,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Multispectral image; Panchromatic film; Clutter; Artificial intelligence; Computer science; Hyperspectral imaging; Preprocessor; Computer vision; Projection (relational algebra); Feature (linguistics); Pattern recognition (psychology); Feature extraction; Projection pursuit; Remote sensing; Geography; Radar","score_opus":0.011966918173778198,"score_gpt":0.2283508240269702,"score_spread":0.216383905853192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121819232","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19055556,0.00012313268,0.8079985,0.000076588214,0.000006370557,0.000026462123,0.00009775726,0.0003142726,0.0008013183],"genre_scores_gemma":[0.66219985,0.00025538635,0.33609945,0.000020468418,0.000012554765,0.00006645937,0.00040663185,0.000052389303,0.00088681816],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998659,0.00003657543,0.000007317877,0.000022394646,0.000056241854,0.000011566925],"domain_scores_gemma":[0.9997596,0.00014424736,0.00003172667,0.000019379297,0.00003716876,0.000007838932],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037767628,0.0004118532,0.00033046133,0.00050286704,0.00012851993,0.00028447673,0.00018145997,0.00016618434,0.00041438168],"category_scores_gemma":[0.0011052144,0.00013019882,0.00033510342,0.00060110615,0.00023787466,0.00036776796,0.00031339438,0.00037388297,0.00014998348],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039251725,0.00012965435,0.003902777,0.00022283588,0.000084831285,0.0002586933,0.00019948716,0.19927153,0.23617305,0.0066702166,0.001030794,0.55166364],"study_design_scores_gemma":[0.0000079850415,0.000073918854,0.0051468867,0.0000037364005,0.000009879402,0.000085050226,0.00002889662,0.97143584,0.020849107,0.0018814602,0.00046423255,0.0000129000455],"about_ca_topic_score_codex":0.0010833014,"about_ca_topic_score_gemma":0.0008732524,"teacher_disagreement_score":0.0010833014,"about_ca_system_score_codex":0.0001511013,"about_ca_system_score_gemma":0.00023736649,"threshold_uncertainty_score":0.0021539927},"labels":[],"label_agreement":null},{"id":"W2121825012","doi":"10.1080/01431160110082444","title":"Spectral and spatial artifacts from the use of desktop scanners for remote sensing","year":2001,"lang":"en","type":"article","venue":"International Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Scanner; Computer science; Remote sensing; Image quality; Computer vision; Computer graphics (images); Artificial intelligence; Image (mathematics); Geology","score_opus":0.04566458276960258,"score_gpt":0.26617463572715927,"score_spread":0.22051005295755668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121825012","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7124898,0.0019953446,0.26750866,0.00031057413,0.0002577376,0.00031631917,0.0003777431,0.0015446998,0.015199084],"genre_scores_gemma":[0.8644076,0.0009143778,0.12828998,0.00029577638,0.00008992702,0.000097858596,0.00033547255,0.00041031832,0.005158744],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9977191,0.00041035216,0.00013325462,0.0001920093,0.0014505204,0.000094691764],"domain_scores_gemma":[0.98730147,0.0075844373,0.0013482632,0.001940866,0.0016951053,0.00012981395],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015803869,0.00044050548,0.0004616732,0.0008276047,0.00046786517,0.0006354937,0.0004222723,0.00060048,0.0025354947],"category_scores_gemma":[0.008692069,0.00021026646,0.00034696585,0.0013265357,0.0007742761,0.0006922942,0.0006277374,0.0006424993,0.00082580664],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010846328,0.00019810311,0.049233317,0.00077405066,0.00013573447,0.002794605,0.0007573152,0.008990511,0.593782,0.002822338,0.002542233,0.3368851],"study_design_scores_gemma":[0.00005140619,0.0018115002,0.12582386,0.00014237317,0.00032003186,0.020741977,0.0007339693,0.015789373,0.8057507,0.0047482965,0.02394186,0.00014457371],"about_ca_topic_score_codex":0.00065708667,"about_ca_topic_score_gemma":0.0012017018,"teacher_disagreement_score":0.0025354947,"about_ca_system_score_codex":0.00027861632,"about_ca_system_score_gemma":0.00030161426,"threshold_uncertainty_score":0.008482039},"labels":[],"label_agreement":null},{"id":"W2122809155","doi":"10.5194/isprsarchives-xl-1-w3-169-2013","title":"KERNEL-BASED UNSUPERVISED CHANGE DETECTION OF AGRICULTURAL LANDS USING MULTI-TEMPORAL POLARIMETRIC SAR DATA","year":2013,"lang":"en","type":"article","venue":"˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Agriculture and Agri-Food Canada; California Institute of Technology; National Aeronautics and Space Administration","keywords":"Cluster analysis; Computer science; Kernel (algebra); Change detection; Initialization; Pattern recognition (psychology); Artificial intelligence; Polarimetry; Remote sensing; Kernel method; Support vector machine; Mathematics; Geography; Scattering","score_opus":0.0454165728787396,"score_gpt":0.26286241457770515,"score_spread":0.21744584169896555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122809155","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41934046,0.00015950784,0.5777918,0.000083284714,0.000033748154,0.000063821055,0.00036997063,0.00091324945,0.0012441584],"genre_scores_gemma":[0.89438343,0.00008822469,0.10337131,0.000014890418,0.000016240776,0.000035231114,0.0009862194,0.000046511814,0.0010580288],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99970394,0.00005789385,0.000020695476,0.0000880845,0.00009081692,0.00003845291],"domain_scores_gemma":[0.9994598,0.00013158137,0.00010386979,0.00007522964,0.00020191487,0.000027549591],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034788533,0.00028268876,0.0003057585,0.0016051113,0.00017259542,0.0005131461,0.00031553104,0.00025001602,0.00040211153],"category_scores_gemma":[0.0009853838,0.00012575017,0.00036336607,0.00087745785,0.00021988711,0.000619872,0.00034932586,0.00030208705,0.000258796],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007102491,0.0004838356,0.037508212,0.00017678959,0.0002541212,0.00036267776,0.00033204653,0.18391208,0.11868762,0.0032025578,0.0027174877,0.6516523],"study_design_scores_gemma":[0.000008146186,0.00005641948,0.025318962,0.000005638029,0.000025915278,0.00011450126,0.00007726543,0.9528388,0.01971525,0.00080982473,0.0010121872,0.000017113523],"about_ca_topic_score_codex":0.0024357454,"about_ca_topic_score_gemma":0.0032719683,"teacher_disagreement_score":0.0024357454,"about_ca_system_score_codex":0.00028097234,"about_ca_system_score_gemma":0.00029775742,"threshold_uncertainty_score":0.004843116},"labels":[],"label_agreement":null},{"id":"W2123284383","doi":"10.1109/ccece.2003.1226093","title":"Genetically derived fuzzy c-means clustering algorithm for segmentation","year":2004,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Cluster analysis; Initialization; Fuzzy clustering; Computer science; Artificial intelligence; Fuzzy logic; Image segmentation; Pattern recognition (psychology); FLAME clustering; Partition (number theory); Algorithm; Canopy clustering algorithm; Segmentation; Data mining; Mathematics","score_opus":0.017243259379318997,"score_gpt":0.2419064050462252,"score_spread":0.2246631456669062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123284383","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005541205,0.00022505663,0.99106896,0.00008630968,0.000046382822,0.00007452027,0.000049016657,0.0005771745,0.002331253],"genre_scores_gemma":[0.077536836,0.00016183755,0.9184472,0.00006665989,0.000025072932,0.00019412841,0.00019385274,0.00011494402,0.0032594753],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993337,0.0001080296,0.000027487358,0.00014140451,0.0003481473,0.00004126412],"domain_scores_gemma":[0.9996158,0.000102437145,0.000032159893,0.00003592728,0.00020177852,0.000011960222],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062862795,0.0007242523,0.00065861177,0.0013661367,0.0009189962,0.0007656647,0.0011135893,0.0011457021,0.0017724524],"category_scores_gemma":[0.001482724,0.00025402196,0.00064721255,0.0013560898,0.00059904746,0.00050894445,0.00042227274,0.0010269505,0.00077655824],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009586761,0.00007868952,0.0008433341,0.00018305423,0.00010607702,0.00010901093,0.00020142825,0.42540625,0.036401995,0.023683086,0.006587251,0.50630397],"study_design_scores_gemma":[0.000010912676,0.000032907166,0.0006752013,0.000020111143,0.000015162573,0.00009296399,0.000021300573,0.97435206,0.011564372,0.0063736993,0.006807102,0.00003417776],"about_ca_topic_score_codex":0.013644868,"about_ca_topic_score_gemma":0.012304031,"teacher_disagreement_score":0.013644868,"about_ca_system_score_codex":0.001330135,"about_ca_system_score_gemma":0.0016389278,"threshold_uncertainty_score":0.027130902},"labels":[],"label_agreement":null},{"id":"W2123930659","doi":"10.5194/isprsarchives-xl-2-w3-35-2014","title":"AN EFFICIENT INITIALIZATION METHOD FOR K-MEANS CLUSTERING OF HYPERSPECTRAL DATA","year":2014,"lang":"en","type":"article","venue":"˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Università degli Studi di Pavia","keywords":"Hyperspectral imaging; Initialization; Cluster analysis; Computer science; Endmember; Thresholding; Pattern recognition (psychology); Confusion matrix; Artificial intelligence; Simplex; Image (mathematics); Mathematics","score_opus":0.028680606404153666,"score_gpt":0.2889958834230084,"score_spread":0.26031527701885476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123930659","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042978935,0.00012686182,0.9937303,0.00003158,0.000043310916,0.00006608928,0.000059057864,0.001143356,0.00050150545],"genre_scores_gemma":[0.056633085,0.00012494155,0.9408187,0.000035659043,0.000024542085,0.00021012178,0.00057028,0.000259128,0.0013234508],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901557,0.00021008961,0.000067343186,0.00021630035,0.0004129765,0.00007768418],"domain_scores_gemma":[0.99914837,0.00016774746,0.00008764601,0.00010763866,0.00045227917,0.000036270703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001032539,0.0013221325,0.0009681147,0.0015345162,0.0009895939,0.0008842023,0.0015412582,0.0010994467,0.002848838],"category_scores_gemma":[0.0027650965,0.0006157162,0.0010753056,0.0016332235,0.0005827978,0.001039415,0.0013251051,0.001434654,0.002412912],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032711946,0.000142119,0.0015898272,0.00037641363,0.00015010244,0.00012025534,0.00039739988,0.21456288,0.03732662,0.009716829,0.011003713,0.72428674],"study_design_scores_gemma":[0.000019694124,0.000032704666,0.0007618187,0.000028689754,0.0000165379,0.0000655393,0.000046647452,0.9756402,0.016678797,0.002446233,0.0042256475,0.00003749465],"about_ca_topic_score_codex":0.007484087,"about_ca_topic_score_gemma":0.009873219,"teacher_disagreement_score":0.007484087,"about_ca_system_score_codex":0.0008959954,"about_ca_system_score_gemma":0.0016055615,"threshold_uncertainty_score":0.014881015},"labels":[],"label_agreement":null},{"id":"W2125114583","doi":"10.1109/cvpr.2001.990662","title":"A model-based road sign identification system","year":2005,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; McGill University; Institut National d'Optique","funders":"","keywords":"Computer science; Modular design; RSS; Artificial intelligence; Traffic sign recognition; Computer vision; Identification (biology); Machine vision; Sign (mathematics); Matching (statistics); Task (project management); Real-time computing; Traffic sign; Engineering","score_opus":0.019471730036392822,"score_gpt":0.22197802173636846,"score_spread":0.20250629169997564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125114583","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022166379,0.00023097266,0.9160828,0.00033697177,0.00025994054,0.00022542951,0.0008236127,0.04349065,0.016383111],"genre_scores_gemma":[0.6886123,0.00040546895,0.27370194,0.00046397507,0.00012725082,0.00055543677,0.003431784,0.0006779527,0.032023862],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99962056,0.000026601067,0.000024104087,0.000111008725,0.00018517103,0.000032547145],"domain_scores_gemma":[0.99971336,0.000026111602,0.00002146123,0.000095318544,0.000115204624,0.000028541454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002504839,0.00052186253,0.0009222878,0.000592368,0.00055976695,0.0013889961,0.001557694,0.0011256047,0.011986066],"category_scores_gemma":[0.0007498479,0.00033264677,0.00041714337,0.0004029461,0.0002453255,0.0012082125,0.001029064,0.00064187107,0.00922217],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00075035845,0.0005438894,0.0030437228,0.0004393626,0.00012949973,0.0007488,0.00019994285,0.19291028,0.17757992,0.017026097,0.046464197,0.5601639],"study_design_scores_gemma":[0.00006083415,0.00020107412,0.0009443457,0.000024393199,0.000048883387,0.0003379851,0.000023224931,0.94315743,0.02247214,0.0034657759,0.029200109,0.00006374428],"about_ca_topic_score_codex":0.0032026765,"about_ca_topic_score_gemma":0.0026391363,"teacher_disagreement_score":0.011986066,"about_ca_system_score_codex":0.0005291899,"about_ca_system_score_gemma":0.0008658766,"threshold_uncertainty_score":0.040097415},"labels":[],"label_agreement":null},{"id":"W2125166870","doi":"10.1109/igarss.2007.4422782","title":"A new nonlinear dimensionality reduction method with application to hyperspectral image analysis","year":2007,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Space Agency","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hyperspectral imaging; Dimensionality reduction; Computer science; Reduction (mathematics); Nonlinear system; Artificial intelligence; Image (mathematics); Pattern recognition (psychology); Computer vision; Mathematics; Physics","score_opus":0.008681483311263534,"score_gpt":0.2780370820972617,"score_spread":0.26935559878599813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125166870","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032767646,0.00018007928,0.9956654,0.00013814929,0.00005167059,0.000023362789,0.000034491404,0.0002628259,0.00036730355],"genre_scores_gemma":[0.041371044,0.00032806405,0.9551955,0.00009625144,0.000102873084,0.00014669189,0.00019179746,0.00011067712,0.002457071],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991906,0.00018040673,0.00004914125,0.00016156063,0.00038292512,0.000035231642],"domain_scores_gemma":[0.99932086,0.00019275678,0.000058876816,0.000110185036,0.0002866715,0.00003071355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007514549,0.0007524775,0.0007541954,0.0013607065,0.0005658816,0.00072748616,0.00069003366,0.0006163756,0.0013623681],"category_scores_gemma":[0.0017879913,0.00031234443,0.0010960209,0.0011724673,0.0007023126,0.0014444676,0.0010950493,0.0010987918,0.00094817264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009022909,0.00011950494,0.0011054409,0.00034848426,0.00017680021,0.00018035746,0.00028684948,0.055338547,0.0771469,0.01600864,0.0062223915,0.84297585],"study_design_scores_gemma":[0.000022636841,0.00010550482,0.0017445624,0.00002551586,0.00004787528,0.0005262032,0.00007161199,0.9287907,0.038107548,0.012101588,0.018356537,0.00009965864],"about_ca_topic_score_codex":0.0012082757,"about_ca_topic_score_gemma":0.0015784528,"teacher_disagreement_score":0.0013623681,"about_ca_system_score_codex":0.00033662945,"about_ca_system_score_gemma":0.00054092135,"threshold_uncertainty_score":0.00455755},"labels":[],"label_agreement":null},{"id":"W2125721005","doi":"10.1016/j.rse.2008.01.016","title":"Continuous wavelets for the improved use of spectral libraries and hyperspectral data","year":2008,"lang":"en","type":"article","venue":"Remote Sensing of Environment","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":174,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Networks of Centres of Excellence of Canada","keywords":"Endmember; Hyperspectral imaging; Wavelet; Context (archaeology); Spectral signature; Computer science; Remote sensing; Spectral line; Sample (material); Pattern recognition (psychology); Artificial intelligence; Geology; Chemistry; Physics","score_opus":0.05406645263418813,"score_gpt":0.21271239953210838,"score_spread":0.15864594689792025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125721005","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017766269,0.00051047467,0.97979283,0.0002010312,0.00009319745,0.00001570938,0.00015637702,0.0006940536,0.0007700928],"genre_scores_gemma":[0.15715158,0.0010401902,0.83798057,0.0001006175,0.00017182897,0.0000672763,0.0005935683,0.00037165053,0.0025226735],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993185,0.00024149982,0.00004096429,0.00009271634,0.00025957054,0.000046775996],"domain_scores_gemma":[0.9979393,0.0008514565,0.00013540593,0.00052450487,0.00047484314,0.0000745935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001529457,0.00070633757,0.0006351495,0.0011300268,0.00028340067,0.0012242928,0.0008084005,0.0007300465,0.0027990097],"category_scores_gemma":[0.0056053563,0.00031033435,0.0005850912,0.002373238,0.00049374875,0.0013537356,0.0010426794,0.0015801919,0.0014518733],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00059929845,0.0002239026,0.0011038618,0.00023516497,0.00009948494,0.000134684,0.00013880635,0.04917353,0.08518642,0.024051849,0.0064540585,0.8325989],"study_design_scores_gemma":[0.000047543992,0.00009552212,0.001210991,0.000032558397,0.00006204407,0.00013681162,0.000031217565,0.94385505,0.036811087,0.010559066,0.007116225,0.000041818967],"about_ca_topic_score_codex":0.0010383273,"about_ca_topic_score_gemma":0.001326839,"teacher_disagreement_score":0.0027990097,"about_ca_system_score_codex":0.00024115507,"about_ca_system_score_gemma":0.00047229946,"threshold_uncertainty_score":0.009363592},"labels":[],"label_agreement":null},{"id":"W2128734552","doi":"10.1109/tnn.2010.2101614","title":"MDS-Based Multiresolution Nonlinear Dimensionality Reduction Model for Color Image Segmentation","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Artificial intelligence; Image segmentation; Pattern recognition (psychology); Computer science; Scale-space segmentation; Cluster analysis; Image texture; Dimensionality reduction; Segmentation-based object categorization; Segmentation; Embedding; Feature extraction; Multiresolution analysis; Computer vision; Wavelet transform; Wavelet","score_opus":0.049319042423821645,"score_gpt":0.257821001767294,"score_spread":0.20850195934347235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128734552","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0044357697,0.00013205985,0.99473107,0.000075687836,0.000012088717,0.000012022632,0.000051609208,0.00017195113,0.00037781714],"genre_scores_gemma":[0.32559198,0.0006840515,0.6684337,0.00012414386,0.000088752924,0.00017945672,0.0004919697,0.00019387751,0.0042120228],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99963844,0.0001047447,0.00001846343,0.000086573375,0.0001234956,0.00002829924],"domain_scores_gemma":[0.9997056,0.00008418187,0.000053660006,0.0000700456,0.00007030506,0.000016251033],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054371037,0.0005639217,0.0008902429,0.00074529636,0.00031624688,0.0006911867,0.00088917767,0.0005887516,0.0015154615],"category_scores_gemma":[0.0013575818,0.00031223218,0.0010010517,0.0009540329,0.00061478326,0.0011288524,0.0008164264,0.0010022116,0.0006888486],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001420733,0.000043445314,0.00058406586,0.00011822574,0.000080144746,0.000108379594,0.00013715772,0.7699872,0.020478213,0.051955674,0.00279724,0.15356816],"study_design_scores_gemma":[0.000001905527,0.000009569159,0.00009220127,0.0000024377734,0.0000038231015,0.000018441573,0.0000049129403,0.9937774,0.001049012,0.0042732777,0.00076129264,0.000005718852],"about_ca_topic_score_codex":0.0034393603,"about_ca_topic_score_gemma":0.0030819348,"teacher_disagreement_score":0.0034393603,"about_ca_system_score_codex":0.00074529985,"about_ca_system_score_gemma":0.0005653886,"threshold_uncertainty_score":0.0068386793},"labels":[],"label_agreement":null},{"id":"W2128899090","doi":"10.1186/1687-6180-2012-118","title":"Multispectral texture characterization: application to computer aided diagnosis on prostatic tissue images","year":2012,"lang":"en","type":"article","venue":"EURASIP Journal on Advances in Signal Processing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Queen's University","keywords":"Multispectral image; Artificial intelligence; Computer science; Pattern recognition (psychology); Spectral bands; Texture (cosmology); Computer vision; Image texture; Image processing; Image (mathematics); Remote sensing; Geography","score_opus":0.009789660375040416,"score_gpt":0.2767334285487104,"score_spread":0.26694376817367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128899090","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52589244,0.001147894,0.46964362,0.00022113335,0.000038467,0.000108968154,0.00020991445,0.0012770023,0.0014605245],"genre_scores_gemma":[0.85891396,0.00031843598,0.1400822,0.00003743024,0.000021677013,0.000027341697,0.00008493598,0.000032758606,0.0004812222],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9998375,0.0000468989,0.000009416275,0.00002483578,0.00006448408,0.000016855078],"domain_scores_gemma":[0.9995876,0.0002020686,0.0000492319,0.00003491847,0.00010426131,0.000021976959],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037963022,0.00026790265,0.0002481733,0.0024000462,0.00012786679,0.0003484167,0.00017732938,0.00038701558,0.0010807202],"category_scores_gemma":[0.00097145257,0.00012181617,0.00026134675,0.0009354148,0.00020136325,0.00018137867,0.00022825778,0.00016619623,0.00020172377],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006399512,0.00015434138,0.0096307285,0.0004940582,0.00007035829,0.00058378954,0.00020964218,0.049061004,0.4552125,0.00095647806,0.00065955677,0.4823275],"study_design_scores_gemma":[0.000026961296,0.00019821733,0.030459892,0.000027510529,0.000072398376,0.0012517051,0.00014989752,0.83358335,0.13194351,0.00083410053,0.00141643,0.000035958627],"about_ca_topic_score_codex":0.0010282412,"about_ca_topic_score_gemma":0.0008985213,"teacher_disagreement_score":0.0024000462,"about_ca_system_score_codex":0.0001524184,"about_ca_system_score_gemma":0.0001417475,"threshold_uncertainty_score":0.0036153793},"labels":[],"label_agreement":null},{"id":"W2129040805","doi":"10.1109/icip.2001.958305","title":"Gabor vs. GMRF features for SAR imagery classification","year":2002,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lockheed Martin (Canada); McGill University","funders":"","keywords":"Artificial intelligence; Pattern recognition (psychology); Clutter; Synthetic aperture radar; Convolution (computer science); Computer science; Radar imaging; Markov random field; Computer vision; Radar; Image (mathematics); Image segmentation; Artificial neural network","score_opus":0.03189530009808209,"score_gpt":0.23483654785279334,"score_spread":0.20294124775471126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129040805","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4991569,0.0038937263,0.48587018,0.0007572125,0.00025758694,0.0001088341,0.0005446871,0.0022300524,0.007180835],"genre_scores_gemma":[0.84208363,0.0011189976,0.15393968,0.00012606665,0.00016985621,0.000049227463,0.0004987084,0.00012612305,0.0018877549],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99934906,0.00020094207,0.00003159904,0.00006990165,0.00028107036,0.00006743245],"domain_scores_gemma":[0.9986835,0.0007466362,0.00010980762,0.00020192975,0.00021564442,0.000042513595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001205201,0.00038314037,0.00041023077,0.0010613833,0.00014192724,0.00059929246,0.0002623801,0.0006705157,0.0010988824],"category_scores_gemma":[0.0038743196,0.000112836,0.00027624267,0.00075410487,0.00028108325,0.00082194415,0.00029892413,0.0003383913,0.00083703856],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025345832,0.00020794116,0.006354558,0.0003672307,0.0001222057,0.00023389758,0.00008693445,0.03614847,0.14421077,0.0035400672,0.003363995,0.8028294],"study_design_scores_gemma":[0.00022299169,0.0017776863,0.039821915,0.00011760602,0.00028051191,0.00166422,0.00013970469,0.78586984,0.15803824,0.005439155,0.0065021687,0.00012596714],"about_ca_topic_score_codex":0.0004318017,"about_ca_topic_score_gemma":0.00047473435,"teacher_disagreement_score":0.001205201,"about_ca_system_score_codex":0.00016172396,"about_ca_system_score_gemma":0.00013860982,"threshold_uncertainty_score":0.0063738227},"labels":[],"label_agreement":null},{"id":"W2129777864","doi":"10.1109/tgrs.2005.848706","title":"An adaptive fuzzy evidential nearest neighbor formulation for classifying remote sensing images","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"k-nearest neighbors algorithm; Fuzzy logic; Pattern recognition (psychology); Computer science; Artificial intelligence; Entropy (arrow of time); Nearest-neighbor chain algorithm; Data mining; Fuzzy set; Mathematics; Fuzzy clustering","score_opus":0.028674704289376685,"score_gpt":0.2719293869634695,"score_spread":0.24325468267409284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129777864","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023514815,0.00021059284,0.9967874,0.00004627399,0.000016995284,0.00002139501,0.000012901237,0.000015070908,0.00053779385],"genre_scores_gemma":[0.22704132,0.00062725507,0.7699328,0.00008772679,0.00016033037,0.00016084725,0.000088865905,0.000018904393,0.0018819554],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882,0.00032562992,0.00008638906,0.00022174857,0.00050414976,0.00004202885],"domain_scores_gemma":[0.9992976,0.00030277553,0.0001000062,0.00006185094,0.0002207721,0.000016906975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018414214,0.00050970935,0.00074522215,0.0009887636,0.000343194,0.0009852819,0.001745772,0.0011534876,0.0008313809],"category_scores_gemma":[0.0030023656,0.00025506504,0.00065995794,0.00093722355,0.0007505175,0.0017085065,0.00070924446,0.0010689878,0.00021249453],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000067516885,0.00008806264,0.0006919526,0.00030338805,0.00009443878,0.00018693299,0.00019911063,0.6027712,0.008570824,0.10226266,0.0013114497,0.2834524],"study_design_scores_gemma":[0.000004268661,0.00004379821,0.00016273257,0.00000996241,0.000012650543,0.0000559856,0.0000121425055,0.982238,0.001104288,0.015031106,0.0013114407,0.000013651562],"about_ca_topic_score_codex":0.0014992137,"about_ca_topic_score_gemma":0.002012627,"teacher_disagreement_score":0.0018414214,"about_ca_system_score_codex":0.0006493305,"about_ca_system_score_gemma":0.0005518253,"threshold_uncertainty_score":0.009738505},"labels":[],"label_agreement":null},{"id":"W2132083814","doi":"10.1109/igarss.2008.4779288","title":"Estimating Dimensionality of Hyperspectral Data Using False Neighbour Method","year":2008,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Resources Canada; University of Victoria","funders":"Natural Resources Canada; National Aeronautics and Space Administration","keywords":"Hyperspectral imaging; Curse of dimensionality; Pattern recognition (psychology); Pixel; Computer science; Artificial intelligence; Land cover; Nonlinear system; Dimensionality reduction; Remote sensing; Mathematics; Data mining; Geography; Land use","score_opus":0.13173696930036963,"score_gpt":0.3355495147851595,"score_spread":0.20381254548478986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132083814","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0836918,0.0001468543,0.915005,0.00006967259,0.000025936832,0.000028035285,0.00007372351,0.000135303,0.00082359114],"genre_scores_gemma":[0.5979756,0.00021007887,0.4003903,0.000028855708,0.000030429406,0.00007342609,0.00028726237,0.000038202164,0.0009657326],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998961,0.00032143865,0.00006548472,0.00017839405,0.00040490855,0.0000687632],"domain_scores_gemma":[0.9965951,0.0020273756,0.00034867012,0.0004322637,0.0005364833,0.0000600864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013750095,0.00039737974,0.000660591,0.001238936,0.00045148702,0.0009998559,0.0007013174,0.0007348428,0.0005395437],"category_scores_gemma":[0.007651951,0.00024244863,0.0005321456,0.0006833574,0.0008730174,0.0018622156,0.0007182779,0.0006895869,0.00021418593],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00088272453,0.00016621356,0.018608004,0.00048244584,0.0002475847,0.00077435933,0.0010655512,0.41387233,0.11190364,0.0545045,0.0025796304,0.39491296],"study_design_scores_gemma":[0.000005913972,0.00003684822,0.003948051,0.000009609427,0.0000115841085,0.000249762,0.00006430656,0.9715588,0.01413096,0.00921182,0.0007229592,0.000049288057],"about_ca_topic_score_codex":0.0011705066,"about_ca_topic_score_gemma":0.0011674584,"teacher_disagreement_score":0.0013750095,"about_ca_system_score_codex":0.00045559875,"about_ca_system_score_gemma":0.00034337642,"threshold_uncertainty_score":0.0072718263},"labels":[],"label_agreement":null},{"id":"W2132308301","doi":"10.1016/j.patcog.2013.04.005","title":"A simple feature combination method based on dominant sets","year":2013,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":47,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University; Universität Wien; University College London; McGill University; National ICT Australia","keywords":"Pattern recognition (psychology); Discriminative model; Artificial intelligence; Weighting; Computer science; Kernel (algebra); Computation; Kernel method; Simple (philosophy); Feature (linguistics); Classifier (UML); Cluster analysis; Support vector machine; Machine learning; Mathematics; Algorithm","score_opus":0.022687374374207685,"score_gpt":0.25909615420916565,"score_spread":0.23640877983495798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132308301","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010363016,0.0006215563,0.98516476,0.00006759498,0.00023191952,0.00015208681,0.00020209156,0.001254684,0.0019421633],"genre_scores_gemma":[0.13324985,0.0006986917,0.8570414,0.0001262368,0.00022490152,0.0003029927,0.0010926172,0.00023049879,0.0070328303],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987418,0.00012354896,0.00008321673,0.00024817188,0.0007117408,0.0000915804],"domain_scores_gemma":[0.99940574,0.00010989352,0.000026477217,0.00009259153,0.0003327824,0.000032571475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092914497,0.0013995162,0.0019530004,0.0029440876,0.00075356895,0.0011254465,0.0011437432,0.0006398265,0.0039284094],"category_scores_gemma":[0.0011732046,0.00049518887,0.0014897841,0.0025302507,0.00033649453,0.0015100843,0.001032803,0.0007589405,0.002729706],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015930177,0.00014744923,0.00056117313,0.00015172987,0.000144948,0.000044132586,0.000027633803,0.0034993435,0.049435694,0.0014409479,0.0038982509,0.9404894],"study_design_scores_gemma":[0.00013585779,0.0008029531,0.015240344,0.00007494584,0.00087315554,0.001482789,0.00013890008,0.80441064,0.13123156,0.009683662,0.035629597,0.0002955662],"about_ca_topic_score_codex":0.0016804282,"about_ca_topic_score_gemma":0.00261033,"teacher_disagreement_score":0.0039284094,"about_ca_system_score_codex":0.0002944755,"about_ca_system_score_gemma":0.0008382781,"threshold_uncertainty_score":0.0131418705},"labels":[],"label_agreement":null},{"id":"W2132816823","doi":"10.5430/air.v1n1p63","title":"Hyperspectral image classification incorporating bacterial foraging-optimized spectral weighting","year":2012,"lang":"en","type":"article","venue":"Artificial Intelligence Research","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Jadavpur University; Purdue University","keywords":"Hyperspectral imaging; Imaging spectrometer; Support vector machine; Benchmark (surveying); Artificial intelligence; Computer science; Kernel (algebra); Pattern recognition (psychology); VNIR; Weighting; Pixel; Remote sensing; Spectrometer; Mathematics; Geography","score_opus":0.15859631677193092,"score_gpt":0.37395208129258334,"score_spread":0.21535576452065242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132816823","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041717663,0.00007121888,0.9571858,0.000048943206,0.000014456771,0.000027019318,0.000012636265,0.0003171431,0.0006051546],"genre_scores_gemma":[0.5059792,0.00008433777,0.49231124,0.000046791,0.000019036564,0.000089273446,0.00008326971,0.000055870638,0.0013309933],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99961627,0.00009060195,0.00002486514,0.000068753405,0.00016201126,0.000037410213],"domain_scores_gemma":[0.9995136,0.00015046544,0.00009373276,0.000056570505,0.00016496911,0.000020592614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007671524,0.0005691349,0.00062539766,0.0005471279,0.00026612394,0.00055355683,0.00053520175,0.0006578909,0.0004149159],"category_scores_gemma":[0.0020446067,0.00026867128,0.00043573754,0.00047257528,0.00036879175,0.0009639059,0.0006012726,0.0005228746,0.00029327415],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014032783,0.0001649242,0.002158066,0.00007574508,0.000051757408,0.000060582028,0.00009637814,0.6767819,0.05791,0.0062915855,0.0006245238,0.2556443],"study_design_scores_gemma":[0.0000014567187,0.000011582114,0.000118935655,0.0000013826149,0.0000014248343,0.0000074182167,0.0000021940486,0.9970702,0.0022114953,0.00044941102,0.00012213257,0.0000022506806],"about_ca_topic_score_codex":0.0014960555,"about_ca_topic_score_gemma":0.0014037811,"teacher_disagreement_score":0.0014960555,"about_ca_system_score_codex":0.0004410492,"about_ca_system_score_gemma":0.0004374495,"threshold_uncertainty_score":0.004057169},"labels":[],"label_agreement":null},{"id":"W2134081259","doi":"10.1109/igarss.1993.322063","title":"An assessment of some small window-based spatial features for land-cover classification","year":2002,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Multispectral image; Window (computing); Land cover; Cover (algebra); Computer science; Artificial intelligence; Pattern recognition (psychology); Spatial analysis; Pixel; Contextual image classification; Cartography; Geography; Remote sensing; Image (mathematics); Land use; Engineering","score_opus":0.03740140460140846,"score_gpt":0.2846642440813523,"score_spread":0.24726283947994387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134081259","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84405565,0.0015943315,0.15120524,0.00022539547,0.000046958066,0.0001574526,0.00028552354,0.00030855532,0.0021208748],"genre_scores_gemma":[0.9448679,0.00030994555,0.05393655,0.00001874207,0.000030463769,0.000059430196,0.00032686704,0.000024585546,0.0004255781],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992093,0.0003534024,0.000054377477,0.00007314219,0.00026556605,0.000044154724],"domain_scores_gemma":[0.9964862,0.0023854696,0.00015879367,0.0001504197,0.0007142605,0.00010482897],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022602268,0.00040226258,0.00031636664,0.0009063921,0.00020679086,0.0006422642,0.00025436754,0.00030132712,0.0009551902],"category_scores_gemma":[0.0063513317,0.00013631005,0.00038338517,0.00079530274,0.00023285217,0.00067136675,0.00025533632,0.0002242675,0.0002479193],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003498398,0.0003791895,0.11379905,0.0003886595,0.00044603576,0.0001521618,0.00019525424,0.03711134,0.07456622,0.0014229943,0.0016764574,0.7663643],"study_design_scores_gemma":[0.00015161275,0.0031009112,0.25645342,0.00009894717,0.0005924551,0.00040912474,0.00043945306,0.68423706,0.04930788,0.0015432088,0.0035866345,0.00007926546],"about_ca_topic_score_codex":0.0023598773,"about_ca_topic_score_gemma":0.0034998583,"teacher_disagreement_score":0.0023598773,"about_ca_system_score_codex":0.00025197185,"about_ca_system_score_gemma":0.00029301085,"threshold_uncertainty_score":0.011953354},"labels":[],"label_agreement":null},{"id":"W2134919630","doi":"10.14358/pers.72.6.653","title":"Time-Series Analysis of Medium-Resolution, Multisensor Satellite Data for Identifying Landscape Change","year":2006,"lang":"en","type":"article","venue":"Photogrammetric Engineering & Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Remote sensing; Geography; Cartography; Series (stratigraphy); Satellite; Change detection; Time series; Physical geography; Computer science; Geology; Engineering","score_opus":0.046205934603700614,"score_gpt":0.26268682085639933,"score_spread":0.2164808862526987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134919630","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92375034,0.0012960131,0.06536915,0.00027394097,0.00016872669,0.00021240934,0.0037151254,0.00043886225,0.0047754385],"genre_scores_gemma":[0.95524174,0.0004027213,0.041203853,0.000032832108,0.00005394027,0.00011041533,0.0022170586,0.000020796917,0.0007166454],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996952,0.00006349407,0.000034872006,0.000049804577,0.00013418308,0.000022426577],"domain_scores_gemma":[0.99957067,0.00013228474,0.00007760246,0.00006115102,0.00012527239,0.000033062137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008022877,0.0003481921,0.0002473024,0.002878028,0.0002034004,0.0005675385,0.00024063115,0.0002444835,0.0010260121],"category_scores_gemma":[0.0014679997,0.00009564256,0.00038072292,0.0030117878,0.00012070407,0.00069642044,0.0002734731,0.00024369362,0.00019052574],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032816431,0.00059653464,0.38732663,0.0004386882,0.00041278795,0.0005574426,0.00046066404,0.032996014,0.043021053,0.0017194628,0.0037939642,0.5283485],"study_design_scores_gemma":[0.000024264036,0.0002529292,0.75147825,0.00006151421,0.00019407795,0.00021970533,0.0008401105,0.22912085,0.009696854,0.0012293697,0.0068046805,0.00007744265],"about_ca_topic_score_codex":0.005581775,"about_ca_topic_score_gemma":0.011784333,"teacher_disagreement_score":0.005581775,"about_ca_system_score_codex":0.0003169813,"about_ca_system_score_gemma":0.0002902541,"threshold_uncertainty_score":0.011098564},"labels":[],"label_agreement":null},{"id":"W2135350092","doi":"10.1109/tgrs.2004.832239","title":"Derivative spectral unmixing of hyperspectral data applied to mixtures of lichen and rock","year":2004,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":84,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Endmember; Hyperspectral imaging; Remote sensing; Subpixel rendering; Spectral signature; Spectral resolution; Pixel; VNIR; Computer science; Spectral bands; Geology; Environmental science; Spectral line; Artificial intelligence; Physics","score_opus":0.022686103288092174,"score_gpt":0.24409790399574827,"score_spread":0.2214118007076561,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135350092","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.083153844,0.00031083907,0.91474515,0.00006334163,0.00002643503,0.00003645961,0.00005845084,0.00069952564,0.00090597325],"genre_scores_gemma":[0.57991475,0.0005692665,0.4166781,0.00004229761,0.00002681911,0.000082991806,0.00028494842,0.00017238535,0.0022284347],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99969053,0.000087665634,0.000016339085,0.00007605503,0.00010849694,0.000021049585],"domain_scores_gemma":[0.9995875,0.0001888065,0.00006212352,0.00007924311,0.000069421076,0.000012935392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085920305,0.00068926037,0.0005246721,0.0013990919,0.0003310125,0.000551704,0.00040707862,0.0003888421,0.0006362197],"category_scores_gemma":[0.0019018919,0.00029270147,0.0006263398,0.0013001547,0.0005828542,0.0011125045,0.00082045177,0.00046394582,0.00029114154],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033413206,0.00012180635,0.0056629176,0.00023463098,0.00013193877,0.00012424988,0.00032811495,0.3069586,0.13597222,0.010661359,0.00068112835,0.538789],"study_design_scores_gemma":[0.0000037878938,0.000033033448,0.002119344,0.000005813726,0.000013780624,0.00006197417,0.000024165205,0.96306497,0.030501014,0.002822584,0.0013324585,0.000017038625],"about_ca_topic_score_codex":0.0021747395,"about_ca_topic_score_gemma":0.0025181489,"teacher_disagreement_score":0.0021747395,"about_ca_system_score_codex":0.0004566392,"about_ca_system_score_gemma":0.0003480892,"threshold_uncertainty_score":0.00454396},"labels":[],"label_agreement":null},{"id":"W2137055879","doi":"10.1109/igarss.2008.4779519","title":"Object-Oriented Classification for Change Detection with Different Spatial Resolution Images","year":2008,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Change detection; Computer science; Aerial image; Image resolution; Artificial intelligence; Wavelet transform; Object (grammar); Object detection; Computer vision; Contextual image classification; Remote sensing; Pattern recognition (psychology); Wavelet; Data mining; Image (mathematics); Geography","score_opus":0.042106855462218866,"score_gpt":0.23475964909126243,"score_spread":0.19265279362904356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137055879","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055156462,0.00076014735,0.93924737,0.0001603913,0.0000857723,0.00019178446,0.00017212283,0.0019838472,0.0022420317],"genre_scores_gemma":[0.27018252,0.0004545971,0.7264079,0.00008798558,0.00007103388,0.00023035641,0.000596627,0.000105484665,0.001863426],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992151,0.0001968422,0.00005849473,0.00012917047,0.00033219735,0.00006815477],"domain_scores_gemma":[0.9991027,0.00033973614,0.00010550191,0.0001357159,0.000281391,0.00003484323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014916103,0.0005591356,0.0006421011,0.0038860268,0.00038881818,0.0009052348,0.0006889891,0.0007305915,0.0018161607],"category_scores_gemma":[0.0023545923,0.0002955818,0.0007046793,0.0026485526,0.00040864182,0.0013280052,0.00041983297,0.00045287822,0.00090542407],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000220215,0.00024216236,0.0044924314,0.00018324827,0.00010052387,0.00017478569,0.00012197006,0.018638644,0.039428536,0.0035865698,0.0024339587,0.93037695],"study_design_scores_gemma":[0.00005962734,0.00015890041,0.017404089,0.00004113695,0.00014495033,0.00041651505,0.0001803671,0.9327246,0.031900477,0.006541317,0.010374369,0.00005368592],"about_ca_topic_score_codex":0.002900742,"about_ca_topic_score_gemma":0.0023854123,"teacher_disagreement_score":0.0038860268,"about_ca_system_score_codex":0.00045802505,"about_ca_system_score_gemma":0.00039881354,"threshold_uncertainty_score":0.007888436},"labels":[],"label_agreement":null},{"id":"W2138849239","doi":"10.1109/tgrs.2008.916223","title":"Comparing Statistical and Neural Network Methods Applied to Very High Resolution Satellite Images Showing Changes in Man-Made Structures at Rocky Flats","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Istituto Nazionale di Geofisica e Vulcanologia; University of British Columbia","keywords":"Satellite; Computer science; Land cover; Remote sensing; Satellite imagery; Parametric statistics; Artificial neural network; Architecture; Demolition; Artificial intelligence; High resolution; Image resolution; Pattern recognition (psychology); Land use; Geology; Geography; Statistics; Mathematics; Archaeology; Engineering; Civil engineering","score_opus":0.034092808252855926,"score_gpt":0.26827585318379427,"score_spread":0.23418304493093833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138849239","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8548737,0.00060168665,0.13871992,0.0003763356,0.00012827433,0.00009434617,0.00023435701,0.00076257763,0.0042086877],"genre_scores_gemma":[0.9404625,0.00024252704,0.057509523,0.000040516188,0.00004287095,0.000051967334,0.00024927984,0.000048646238,0.0013522318],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994492,0.0002155469,0.00004161296,0.00008667809,0.00015577287,0.000051258383],"domain_scores_gemma":[0.9959974,0.002706926,0.00021633961,0.00016590433,0.0008411124,0.00007227268],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028308535,0.0005652905,0.00029232833,0.0020502089,0.00025949746,0.00071200385,0.00041087085,0.000600654,0.0009557005],"category_scores_gemma":[0.00658448,0.00018194316,0.00036470115,0.001207034,0.0003770532,0.0007281392,0.00042129087,0.00034721883,0.0002526705],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013770708,0.00042642496,0.05573452,0.00019978531,0.0003659517,0.00015799377,0.00019672152,0.4348692,0.018719567,0.0016329719,0.0017600175,0.4845598],"study_design_scores_gemma":[0.000014262465,0.0000873497,0.020765461,0.0000072661187,0.000026608845,0.000025639014,0.000073229865,0.9748701,0.0033832677,0.0005060984,0.00022740646,0.000013271265],"about_ca_topic_score_codex":0.013108928,"about_ca_topic_score_gemma":0.019213293,"teacher_disagreement_score":0.013108928,"about_ca_system_score_codex":0.00085149624,"about_ca_system_score_gemma":0.00047686778,"threshold_uncertainty_score":0.02606529},"labels":[],"label_agreement":null},{"id":"W2143265137","doi":"10.1109/igarss.2014.6947090","title":"Sparse hyperspectral unmixing via arctan approximation of L&lt;inf&gt;0&lt;/inf&gt; norm","year":2014,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Hyperspectral imaging; Norm (philosophy); Minification; Algorithm; Inverse trigonometric functions; Computer science; Convergence (economics); Function (biology); Mathematics; Artificial intelligence; Mathematical optimization; Mathematical analysis","score_opus":0.011606113758974714,"score_gpt":0.20144512608525447,"score_spread":0.18983901232627975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143265137","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034155631,0.00010250564,0.9952449,0.000049891747,0.000018478568,0.000013566478,0.000024420802,0.0002283541,0.0009022446],"genre_scores_gemma":[0.075654835,0.00043254165,0.9189693,0.00008570424,0.00004545237,0.00009320371,0.00024958237,0.0002384634,0.004231031],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99967813,0.00007725148,0.000012506663,0.000069269314,0.00014091172,0.000021961978],"domain_scores_gemma":[0.9997515,0.00010048355,0.00003604425,0.000044296812,0.00005699889,0.000010786836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073413237,0.0010179834,0.0005738274,0.00064240594,0.0002608969,0.0007289706,0.0009948385,0.0007184949,0.0025113989],"category_scores_gemma":[0.0012913783,0.0003338658,0.0007696919,0.0010081745,0.0006653224,0.0014139109,0.000848257,0.0013573193,0.0011754585],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000185382,0.00012381207,0.0009627605,0.00038499254,0.00009972157,0.00013191372,0.0002324863,0.48724887,0.04263074,0.074198276,0.0034792393,0.39032188],"study_design_scores_gemma":[0.0000036681677,0.000014723652,0.000102373895,0.0000061837227,0.0000064537926,0.00005653688,0.000010304147,0.9838689,0.008962867,0.0040318076,0.002926304,0.000009929474],"about_ca_topic_score_codex":0.0018302256,"about_ca_topic_score_gemma":0.0022503275,"teacher_disagreement_score":0.0025113989,"about_ca_system_score_codex":0.0005026732,"about_ca_system_score_gemma":0.0008049142,"threshold_uncertainty_score":0.008401513},"labels":[],"label_agreement":null},{"id":"W2144024233","doi":"10.1109/icvgip.2008.52","title":"Change Detection and Object Segmentation: A Histogram of Features-Based Energy Minimization Approach","year":2008,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Artificial intelligence; Minimum bounding box; Histogram; Background subtraction; Computer science; Computer vision; Image segmentation; Change detection; Segmentation; Pattern recognition (psychology); Object detection; Pixel; Energy (signal processing); Image (mathematics); Mathematics","score_opus":0.02658860729271025,"score_gpt":0.20941460454678573,"score_spread":0.18282599725407547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144024233","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038780412,0.00015079972,0.99526656,0.000091156566,0.000011176253,0.00001929824,0.0000169095,0.00015023818,0.00041587057],"genre_scores_gemma":[0.22193003,0.0005142005,0.7734919,0.00015555634,0.00009497494,0.0001635411,0.00019839591,0.00032468993,0.0031265996],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99959403,0.000090668815,0.000020419862,0.000101165555,0.00015406335,0.000039672424],"domain_scores_gemma":[0.999676,0.00014405069,0.00003900703,0.00004522009,0.00007866348,0.000017155036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000825486,0.0005815529,0.0010624516,0.0018336173,0.0003118743,0.0009937827,0.0014240443,0.0014854125,0.0013651132],"category_scores_gemma":[0.0015843033,0.00053360965,0.0009097349,0.0013836912,0.00081628055,0.0013624609,0.0007810657,0.00067664945,0.00046374355],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001465031,0.00012450489,0.0010817343,0.00019417377,0.00016229998,0.00017682435,0.00015996474,0.56116354,0.04312341,0.034226824,0.0024587002,0.35698137],"study_design_scores_gemma":[0.000006479991,0.000024681989,0.00046484682,0.000006919261,0.000013801547,0.000058603146,0.000013654341,0.98531485,0.0036124794,0.009398191,0.0010728365,0.000012535043],"about_ca_topic_score_codex":0.0020348248,"about_ca_topic_score_gemma":0.0016456767,"teacher_disagreement_score":0.0020348248,"about_ca_system_score_codex":0.0007123177,"about_ca_system_score_gemma":0.0006284491,"threshold_uncertainty_score":0.005168259},"labels":[],"label_agreement":null},{"id":"W2144218027","doi":"10.1109/igarss.2004.1369962","title":"The effect of some internal neural network parameters on SAR texture classification performance","year":2004,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec; Institut National de la Recherche Scientifique","funders":"","keywords":"Artificial neural network; Computer science; Backpropagation; Artificial intelligence; Contextual image classification; Data classification; Pattern recognition (psychology); Machine learning; Process (computing); Data mining; Image (mathematics)","score_opus":0.010458614358252622,"score_gpt":0.2165962809908026,"score_spread":0.20613766663254998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144218027","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9550214,0.0004191237,0.042128,0.0001723301,0.000070360715,0.000045395893,0.00007854262,0.00044545167,0.0016193332],"genre_scores_gemma":[0.9922983,0.0001117934,0.0071367593,0.000027146192,0.000009522813,0.00002784364,0.00007744677,0.000059905273,0.0002512029],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898595,0.00031312782,0.000156627,0.00015040392,0.0002227378,0.00017115416],"domain_scores_gemma":[0.9814,0.01425514,0.0010101633,0.0010398396,0.0020163257,0.00027858227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026753282,0.0009675084,0.0006320854,0.0005910788,0.00034481226,0.0010166493,0.0005158869,0.0010196758,0.00068789575],"category_scores_gemma":[0.026370684,0.0003815146,0.00029984297,0.0005216944,0.00082067435,0.0013497756,0.00042122684,0.0010190643,0.00027849525],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033308838,0.00095051574,0.03720019,0.0005850543,0.00024086125,0.0005403903,0.00056477275,0.5630307,0.21128404,0.0011555888,0.0008638596,0.18025315],"study_design_scores_gemma":[0.000108665,0.0012629493,0.024208214,0.0001002329,0.0003341377,0.00037070617,0.00019678549,0.65281177,0.31902465,0.0009760824,0.00049452856,0.00011126187],"about_ca_topic_score_codex":0.0012102949,"about_ca_topic_score_gemma":0.0008290996,"teacher_disagreement_score":0.0026753282,"about_ca_system_score_codex":0.0005495784,"about_ca_system_score_gemma":0.00029671795,"threshold_uncertainty_score":0.014148653},"labels":[],"label_agreement":null},{"id":"W2144884673","doi":"10.1109/72.925566","title":"Eigenpaxels and a neural-network approach to image classification","year":2001,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Centre For Cold Ocean Resources Engineering","funders":"","keywords":"Pattern recognition (psychology); Artificial intelligence; Computer science; Artificial neural network; Principal component analysis; Encoding (memory); Image (mathematics); Contextual image classification; Set (abstract data type); Image processing; Similarity (geometry); Face (sociological concept); Computer vision","score_opus":0.025535360179846357,"score_gpt":0.23256526395032026,"score_spread":0.2070299037704739,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144884673","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0052455133,0.00079985213,0.99173063,0.00020782954,0.00005704884,0.00003254562,0.000038540704,0.00039993715,0.001488083],"genre_scores_gemma":[0.18426628,0.0018208872,0.80258733,0.0002981083,0.00032977824,0.00025390257,0.00026762448,0.00009849929,0.010077586],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99955803,0.00013627786,0.000027282904,0.00009712321,0.00014513996,0.000036144527],"domain_scores_gemma":[0.99954176,0.00022429263,0.000048496462,0.000060390517,0.00010929012,0.00001588038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007603329,0.00056938804,0.00064385956,0.0012076354,0.00039092143,0.001080062,0.00087036693,0.0010114796,0.0024415767],"category_scores_gemma":[0.0017873257,0.00033649086,0.00053950225,0.0012965612,0.0010626399,0.0017136632,0.00079860626,0.0012942528,0.0007734298],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000142058,0.00010038877,0.00082724035,0.00017543981,0.000108024935,0.00013182295,0.0001342784,0.21994944,0.016250147,0.0922006,0.004519007,0.66546154],"study_design_scores_gemma":[0.0000050733543,0.000030021289,0.0003343835,0.000013771842,0.000008464228,0.00007499831,0.000012675364,0.9666385,0.0028280257,0.027184257,0.0028556178,0.000014084094],"about_ca_topic_score_codex":0.002184571,"about_ca_topic_score_gemma":0.0023171129,"teacher_disagreement_score":0.0024415767,"about_ca_system_score_codex":0.00055996596,"about_ca_system_score_gemma":0.00046221746,"threshold_uncertainty_score":0.0081679225},"labels":[],"label_agreement":null},{"id":"W2144929854","doi":"10.5539/jas.v5n3p278","title":"Image Classification for Different Land Use and Land Covers Using Fuzzy Logic for the Improvement of Accuracies","year":2013,"lang":"en","type":"article","venue":"Journal of Agricultural Science","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Impervious surface; Cohen's kappa; Fuzzy logic; Land cover; Confusion matrix; Vegetation (pathology); Pixel; Computer science; Artificial intelligence; Satellite; Pattern recognition (psychology); Contextual image classification; Agricultural land; Mathematics; Remote sensing; Land use; Statistics; Image (mathematics); Geography; Engineering; Ecology; Civil engineering","score_opus":0.047766289890023,"score_gpt":0.2636260450337821,"score_spread":0.2158597551437591,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144929854","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23894198,0.0013219769,0.7463521,0.0003025898,0.00009654449,0.00021581953,0.00054361706,0.0022195475,0.010005759],"genre_scores_gemma":[0.5812761,0.00063144916,0.41390064,0.00008048236,0.00003487475,0.00011747855,0.0005198159,0.00007913613,0.0033600684],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99902546,0.0001258457,0.000088591405,0.00017328077,0.00051186176,0.00007495309],"domain_scores_gemma":[0.99907696,0.00026466954,0.00011431489,0.0000682047,0.00045819022,0.000017581873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010275132,0.0005149836,0.0005691211,0.0020874736,0.00037980234,0.0010937591,0.00050847605,0.0005219927,0.0017207373],"category_scores_gemma":[0.002095794,0.00023467893,0.0007151261,0.0012180645,0.00023803029,0.0008733024,0.00030153577,0.00051932863,0.0006344513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005033891,0.000240343,0.018646752,0.00072719046,0.0001595276,0.00030371046,0.0005383646,0.040402226,0.17122407,0.002150423,0.0023570838,0.7627469],"study_design_scores_gemma":[0.000052545813,0.00054597465,0.059764195,0.00022021889,0.0003086269,0.0008166572,0.0009620304,0.7843452,0.1382805,0.0038731776,0.010692121,0.00013882968],"about_ca_topic_score_codex":0.0033966044,"about_ca_topic_score_gemma":0.0033441512,"teacher_disagreement_score":0.0033966044,"about_ca_system_score_codex":0.00043743075,"about_ca_system_score_gemma":0.0004002652,"threshold_uncertainty_score":0.006753683},"labels":[],"label_agreement":null},{"id":"W2145617653","doi":"10.1109/nafips.2003.1226788","title":"Robust centroid determination of noisy data using FCM and domain specific partitioning","year":2004,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Institute for Biodiagnostics","funders":"","keywords":"Centroid; Pattern recognition (psychology); Noise (video); Computer science; Weighting; Artificial intelligence; Fuzzy logic; Domain (mathematical analysis); Feature (linguistics); Partition (number theory); Metric (unit); Data mining; Mathematics; Image (mathematics)","score_opus":0.08282320723953959,"score_gpt":0.24673394861034856,"score_spread":0.16391074137080897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145617653","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011096299,0.00012287835,0.9881846,0.000044194847,0.000009578428,0.000026762566,0.000024090363,0.00030952808,0.000182083],"genre_scores_gemma":[0.14112227,0.00010819484,0.8579651,0.000033800086,0.000021249734,0.00011013945,0.00020206114,0.000119195494,0.00031790254],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909675,0.0002307971,0.00007959099,0.00025713854,0.00025641467,0.000079367375],"domain_scores_gemma":[0.9976822,0.0009871661,0.00029574413,0.00040411594,0.0005830085,0.000047689504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026985726,0.0011988367,0.0016015635,0.0025104661,0.0009233653,0.0011943744,0.0015518189,0.0014429126,0.0005828444],"category_scores_gemma":[0.011132538,0.0005043816,0.00088958733,0.0023385743,0.00096937176,0.0015672871,0.0010576708,0.0010308021,0.00034181555],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017893425,0.00008105472,0.0014710522,0.00015107084,0.0001575069,0.0001048893,0.00028640337,0.4955226,0.02086943,0.008072872,0.0014422617,0.4716619],"study_design_scores_gemma":[0.0000062738072,0.00002000785,0.0005703064,0.000006764887,0.000013348187,0.000041220097,0.000027411881,0.9872426,0.006133553,0.0052178875,0.0007054793,0.000015181809],"about_ca_topic_score_codex":0.007216515,"about_ca_topic_score_gemma":0.0052125813,"teacher_disagreement_score":0.007216515,"about_ca_system_score_codex":0.0013223334,"about_ca_system_score_gemma":0.0014425527,"threshold_uncertainty_score":0.014349043},"labels":[],"label_agreement":null},{"id":"W2146449740","doi":"10.3390/s8021321","title":"The Successive Projection Algorithm (SPA), an Algorithm with a Spatial Constraint for the Automatic Search of Endmembers in Hyperspectral Data","year":2008,"lang":"en","type":"article","venue":"Sensors","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":99,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; University of Lethbridge","funders":"Networks of Centres of Excellence of Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Endmember; Hyperspectral imaging; Pixel; Algorithm; Adjacency list; Computer science; Spatial analysis; Projection (relational algebra); Pattern recognition (psychology); Mathematics; Artificial intelligence; Remote sensing; Geography","score_opus":0.04154505271190751,"score_gpt":0.27873511034969173,"score_spread":0.23719005763778422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146449740","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030020296,0.00009750649,0.9961008,0.000036857975,0.000011655545,0.000041100084,0.000023732273,0.00039451697,0.00029176736],"genre_scores_gemma":[0.02302129,0.00013950432,0.975593,0.00004027227,0.00001717713,0.00011801364,0.00015521672,0.00016040013,0.0007550406],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99872285,0.0003916061,0.00007298482,0.00026241143,0.0004939382,0.000056107263],"domain_scores_gemma":[0.99812883,0.0011243435,0.00018948923,0.00020383777,0.00030069845,0.000052765685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019585832,0.0016253808,0.0011744922,0.0012092233,0.00082635914,0.001130324,0.0012510445,0.0009994978,0.002075485],"category_scores_gemma":[0.0045374776,0.00081682997,0.0011743943,0.0012874526,0.00134632,0.0016077445,0.0018934717,0.0018047842,0.000989898],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021679007,0.000117252566,0.002215214,0.0003741473,0.00035965646,0.00016778268,0.0003413893,0.23914903,0.04121431,0.030163608,0.0055114655,0.68016934],"study_design_scores_gemma":[0.000026750326,0.00009210368,0.00060269487,0.000022843395,0.000028332115,0.00020461317,0.000045164277,0.9640186,0.017167239,0.010887681,0.0068679694,0.000036150897],"about_ca_topic_score_codex":0.0038215145,"about_ca_topic_score_gemma":0.006864223,"teacher_disagreement_score":0.0038215145,"about_ca_system_score_codex":0.00046760697,"about_ca_system_score_gemma":0.0017213827,"threshold_uncertainty_score":0.010358095},"labels":[],"label_agreement":null},{"id":"W2146479507","doi":"10.1109/crv.2011.44","title":"A Fuzzy C-Means Based Spatial Pixel and Membership Relationships for Image Segmentation","year":2011,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pixel; Robustness (evolution); Artificial intelligence; Fuzzy logic; Segmentation; Image segmentation; Computer science; Pattern recognition (psychology); Cluster analysis; Noise (video); Sensitivity (control systems); Spatial analysis; Image (mathematics); Computer vision; Mathematics; Statistics","score_opus":0.07309874455261064,"score_gpt":0.23669277058084323,"score_spread":0.1635940260282326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146479507","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047415756,0.00032080198,0.993246,0.00010645783,0.000041863874,0.000046191453,0.00004364111,0.0004921716,0.0009613479],"genre_scores_gemma":[0.09306969,0.0003521592,0.9035534,0.00013056796,0.00005849745,0.00017459417,0.0001730941,0.0001027052,0.0023853227],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987375,0.00016161031,0.000054996675,0.0003435141,0.0006164011,0.00008598584],"domain_scores_gemma":[0.99942833,0.00013743187,0.000051034596,0.00005420779,0.00030357213,0.000025464484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010522883,0.00078613026,0.001011483,0.0019172245,0.0011754055,0.0010823486,0.0018811666,0.0021209558,0.0018223381],"category_scores_gemma":[0.0027256382,0.00052900024,0.0012997481,0.0018647637,0.00083845545,0.0014041709,0.0008533994,0.0012346609,0.000711064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017531603,0.000110458925,0.0008683902,0.00026154317,0.00012427608,0.00015424589,0.00023122592,0.4152297,0.028435564,0.016539386,0.005221857,0.532648],"study_design_scores_gemma":[0.000007504292,0.000018999886,0.00021284295,0.000013213041,0.000014067972,0.000051514624,0.000011974362,0.9898156,0.0061509022,0.0016955351,0.0019840081,0.000023880064],"about_ca_topic_score_codex":0.01870672,"about_ca_topic_score_gemma":0.012587431,"teacher_disagreement_score":0.01870672,"about_ca_system_score_codex":0.0015924188,"about_ca_system_score_gemma":0.0025268365,"threshold_uncertainty_score":0.037195623},"labels":[],"label_agreement":null},{"id":"W2148338450","doi":"10.1109/igarss.2002.1026276","title":"Multitemporal change analysis of multispectral imagery using principal components analysis","year":2003,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Multispectral image; Principal component analysis; Normalized Difference Vegetation Index; Multispectral pattern recognition; Change analysis; Remote sensing; Change detection; Ordination; Basis (linear algebra); Computer science; Transformation (genetics); Vegetation (pathology); Spectral analysis; Pattern recognition (psychology); Artificial intelligence; Geology; Mathematics; Geography; Physical geography; Climate change","score_opus":0.08774184250710187,"score_gpt":0.28609639560964284,"score_spread":0.19835455310254096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148338450","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22374284,0.00076003297,0.76634854,0.00024225497,0.000091993206,0.00030228682,0.0010478862,0.0016429374,0.005821318],"genre_scores_gemma":[0.60141873,0.0005782151,0.3947185,0.000033732635,0.000058186237,0.00020526863,0.0011180765,0.00014695484,0.0017222341],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99951863,0.00010416686,0.00003061084,0.00008212018,0.0002278653,0.000036602083],"domain_scores_gemma":[0.99963665,0.00010688602,0.00006381202,0.000053566415,0.00012540464,0.0000137909365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006939281,0.0004303464,0.00036690367,0.003785524,0.00025461527,0.00091502164,0.00027132788,0.00021900143,0.0011715997],"category_scores_gemma":[0.0015738208,0.0001895263,0.00052810175,0.003400553,0.00025387568,0.0008716559,0.00032963944,0.0004352657,0.0003337589],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017221444,0.00029818265,0.030399859,0.00031387666,0.00029840655,0.00020098742,0.00037816312,0.047576226,0.06635653,0.009138131,0.0028618767,0.8420056],"study_design_scores_gemma":[0.00003523109,0.00032379339,0.34142327,0.00005530325,0.00021896716,0.00044604787,0.00062243344,0.57677,0.046977058,0.014160506,0.018819759,0.00014749884],"about_ca_topic_score_codex":0.0034550286,"about_ca_topic_score_gemma":0.004526573,"teacher_disagreement_score":0.003785524,"about_ca_system_score_codex":0.00031953485,"about_ca_system_score_gemma":0.00035395855,"threshold_uncertainty_score":0.0068698525},"labels":[],"label_agreement":null},{"id":"W2153204982","doi":"10.1109/igarss.2001.976571","title":"Accuracy assessment of hyperspectral imagery: atmospheric calibration and image classification considerations","year":2002,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Golder Associates (Canada)","funders":"Stennis Space Center","keywords":"Hyperspectral imaging; Remote sensing; Atmospheric correction; Alunite; Computer science; Ground truth; Image resolution; Image processing; Artificial intelligence; Data processing; Computer vision; Environmental science; Image (mathematics); Geology; Satellite; Engineering","score_opus":0.02990560650331894,"score_gpt":0.26405366837923744,"score_spread":0.2341480618759185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153204982","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08068644,0.008589649,0.87830937,0.0048091314,0.00046519728,0.00027245373,0.00092452776,0.0027459888,0.023197208],"genre_scores_gemma":[0.498587,0.0037372753,0.48826197,0.0009203601,0.0005620431,0.00019970702,0.0009469962,0.0008010581,0.005983574],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98822975,0.0034555125,0.000571201,0.0005997875,0.0068853158,0.00025846207],"domain_scores_gemma":[0.974228,0.011910393,0.0014554447,0.0022700122,0.009996621,0.00013956553],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009129402,0.00077427534,0.0008532839,0.0026832686,0.00069033547,0.0022341232,0.0009574545,0.0013000222,0.001810528],"category_scores_gemma":[0.043913625,0.00026407337,0.0005745547,0.0024666686,0.0011349963,0.002265971,0.001022113,0.0009980891,0.0010978141],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004040108,0.00015263807,0.034248997,0.0008478571,0.00023830919,0.00031429288,0.00059499574,0.094054684,0.040384304,0.015518723,0.011671586,0.80156964],"study_design_scores_gemma":[0.00007361837,0.00047748064,0.12158393,0.00064503273,0.00030656866,0.0022462052,0.0010610307,0.57741874,0.18567516,0.051050823,0.059192803,0.00026860106],"about_ca_topic_score_codex":0.0047420505,"about_ca_topic_score_gemma":0.006039505,"teacher_disagreement_score":0.009129402,"about_ca_system_score_codex":0.0009776284,"about_ca_system_score_gemma":0.0006971841,"threshold_uncertainty_score":0.04828149},"labels":[],"label_agreement":null},{"id":"W2154763362","doi":"10.1109/icdm.2003.1251014","title":"A K-NN associated fuzzy evidential reasoning classifier with adaptive neighbor selection","year":2004,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Università degli Studi di Cagliari","keywords":"k-nearest neighbors algorithm; Pattern recognition (psychology); Artificial intelligence; Fuzzy logic; Fuzzy set; Fuzzy classification; Computer science; Mathematics; Classifier (UML); Data mining","score_opus":0.01325597809926634,"score_gpt":0.20956856621274947,"score_spread":0.19631258811348312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154763362","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010714336,0.0006943267,0.9857261,0.0001384269,0.00012981056,0.00009756979,0.00005888694,0.00034184515,0.0020987806],"genre_scores_gemma":[0.34113455,0.00068984757,0.64997935,0.0003044833,0.00027402834,0.00031519087,0.00038798692,0.000046949757,0.0068676705],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99847585,0.0002325137,0.00012476221,0.00037881872,0.0006740505,0.00011406822],"domain_scores_gemma":[0.9993105,0.00018379305,0.000049162052,0.00007351669,0.00034753932,0.00003554645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014310183,0.00068953465,0.0020363834,0.0012914619,0.0009225119,0.0014609875,0.0022253331,0.0019926983,0.0022608903],"category_scores_gemma":[0.002193955,0.0003894657,0.0010841938,0.0013104535,0.0005045624,0.0015637394,0.0011024273,0.0013020416,0.001165867],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024894433,0.00025294276,0.0014584225,0.0001667652,0.00013476572,0.0001983883,0.000112890215,0.12714897,0.01037842,0.014005535,0.004816309,0.84107757],"study_design_scores_gemma":[0.000017926435,0.00006287249,0.00028226175,0.000010280001,0.00002957721,0.0001229802,0.000012022529,0.99184096,0.0020893407,0.0034153708,0.0020991652,0.000017225615],"about_ca_topic_score_codex":0.0029349923,"about_ca_topic_score_gemma":0.0029254216,"teacher_disagreement_score":0.0029349923,"about_ca_system_score_codex":0.00065264705,"about_ca_system_score_gemma":0.0009465259,"threshold_uncertainty_score":0.0075680614},"labels":[],"label_agreement":null},{"id":"W2155680036","doi":"10.1109/igarss.2006.519","title":"The Future of Imaging Spectroscopy Prospective Technologies and Applications","year":2006,"lang":"en","type":"preprint","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Resources Canada; York University","funders":"Natural Resources Canada; Jet Propulsion Laboratory","keywords":"Focus (optics); Cardinal point; Environmental science; Computer science; Spectroscopy; Emerging technologies; Prime (order theory); Imaging spectroscopy; Remote sensing; Scalability; Systems engineering; Data science; Nanotechnology; Engineering; Materials science; Hyperspectral imaging; Artificial intelligence; Geology; Optics; Physics","score_opus":0.00418833797531146,"score_gpt":0.21870143607829665,"score_spread":0.2145130981029852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155680036","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015725553,0.5373167,0.26080078,0.10185334,0.004282691,0.00008510298,0.00045893228,0.0013837332,0.078093275],"genre_scores_gemma":[0.30765736,0.33013186,0.3099083,0.01169932,0.009742098,0.00018125103,0.0006458851,0.00048449467,0.02954952],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99793756,0.00071034307,0.000075499,0.0002784339,0.0008265262,0.00017154797],"domain_scores_gemma":[0.99307513,0.0037846589,0.00022808778,0.0006975527,0.0017292104,0.00048532305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050625773,0.00072712376,0.00086578913,0.0014510502,0.0007889652,0.0045837113,0.0015847959,0.0041739373,0.008020776],"category_scores_gemma":[0.006506859,0.00042919908,0.00050603895,0.0015399195,0.0031673685,0.009893283,0.0020087643,0.0032123239,0.0022324626],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017459439,0.00011657656,0.001680018,0.0011850687,0.000043543405,0.00022158778,0.00045495137,0.002925546,0.012370243,0.31145307,0.032469366,0.6369055],"study_design_scores_gemma":[0.00003221661,0.0001514484,0.0019558072,0.0006832733,0.00003769752,0.0011710546,0.0006347603,0.01646311,0.0070609115,0.48752457,0.48415622,0.0001288904],"about_ca_topic_score_codex":0.0008508275,"about_ca_topic_score_gemma":0.00051661197,"teacher_disagreement_score":0.008020776,"about_ca_system_score_codex":0.0013583028,"about_ca_system_score_gemma":0.0012625608,"threshold_uncertainty_score":0.026832223},"labels":[],"label_agreement":null},{"id":"W2156220628","doi":"10.1016/j.rse.2007.02.019","title":"Integration of spatial–spectral information for the improved extraction of endmembers","year":2007,"lang":"en","type":"article","venue":"Remote Sensing of Environment","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":243,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Geological Survey of Canada; University of Alberta","funders":"","keywords":"Endmember; Hyperspectral imaging; Pattern recognition (psychology); Contrast (vision); Pixel; Artificial intelligence; Spectral signature; Projection (relational algebra); Mathematics; Computer science; Basis (linear algebra); Singular value decomposition; Set (abstract data type); Remote sensing; Computer vision; Algorithm; Geography","score_opus":0.011494760901427896,"score_gpt":0.22508498633424928,"score_spread":0.21359022543282138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156220628","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054218084,0.00051682803,0.9413011,0.00013340628,0.00009376025,0.00003538672,0.00015583647,0.001319807,0.0022257783],"genre_scores_gemma":[0.2704495,0.0005672049,0.72475743,0.000099171564,0.000070648915,0.00006802636,0.0007410647,0.00029060658,0.0029563217],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999729,0.00004645886,0.000016568514,0.000041873212,0.00013562095,0.000030525556],"domain_scores_gemma":[0.999566,0.00011328152,0.000026502381,0.000060045342,0.00022011883,0.000014064171],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058187393,0.0007074609,0.00053271983,0.0010230697,0.00032069642,0.00067774305,0.00049578445,0.0004938137,0.0022248705],"category_scores_gemma":[0.0012614573,0.00040771766,0.0005587749,0.0012124879,0.00021087864,0.0012697829,0.0006048284,0.000624215,0.0012590709],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023196799,0.00021164397,0.001655475,0.00020901744,0.00012107879,0.0000737924,0.000088165354,0.019031186,0.49967167,0.002115925,0.0016640358,0.474926],"study_design_scores_gemma":[0.000024019097,0.00010631939,0.011141987,0.000034372744,0.00021407702,0.00023526126,0.000044791534,0.6272762,0.34872916,0.0022786916,0.009847298,0.00006780001],"about_ca_topic_score_codex":0.0013060594,"about_ca_topic_score_gemma":0.004056734,"teacher_disagreement_score":0.0022248705,"about_ca_system_score_codex":0.0001461325,"about_ca_system_score_gemma":0.00040825424,"threshold_uncertainty_score":0.0074428916},"labels":[],"label_agreement":null},{"id":"W2156352582","doi":"10.5194/isprsarchives-xl-1-w3-305-2013","title":"MAXIMUM MARGIN CLUSTERING OF HYPERSPECTRAL DATA","year":2013,"lang":"en","type":"article","venue":"˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Margin (machine learning); Cluster analysis; Hyperspectral imaging; Computer science; Support vector machine; Hyperplane; Artificial intelligence; Pattern recognition (psychology); Data mining; Machine learning; Mathematics","score_opus":0.024786184842748627,"score_gpt":0.25038645767935785,"score_spread":0.22560027283660922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156352582","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039412074,0.00035617332,0.9564461,0.00015977483,0.00007613476,0.000086001404,0.00024568682,0.00090519467,0.0023128507],"genre_scores_gemma":[0.44854236,0.000260692,0.54413056,0.00012566349,0.000078366735,0.00020552687,0.0018774623,0.000286681,0.0044926656],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99860734,0.00027980306,0.00008451766,0.00040746684,0.00053547916,0.00008548833],"domain_scores_gemma":[0.9988399,0.00029481063,0.00014341994,0.00020079142,0.00048094787,0.000040265815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011298987,0.0010678107,0.0010964135,0.0020128482,0.0007511059,0.0010742602,0.0010585287,0.0009695044,0.0018833096],"category_scores_gemma":[0.0026993502,0.0003329044,0.0007826903,0.00182864,0.00066323037,0.0013524275,0.0009378466,0.00090201676,0.0010426905],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004921277,0.00023718158,0.0025879203,0.00035405226,0.0001580062,0.00015114098,0.00026123787,0.44397536,0.028775163,0.010061681,0.008478638,0.50446755],"study_design_scores_gemma":[0.0000052966216,0.0000192167,0.00081977894,0.000010312794,0.0000062710988,0.000024516077,0.000033524913,0.9882488,0.005820484,0.0037995735,0.0011999386,0.000012287175],"about_ca_topic_score_codex":0.002580574,"about_ca_topic_score_gemma":0.002295911,"teacher_disagreement_score":0.002580574,"about_ca_system_score_codex":0.0008629836,"about_ca_system_score_gemma":0.0006598422,"threshold_uncertainty_score":0.0063002706},"labels":[],"label_agreement":null},{"id":"W2156999391","doi":"10.1109/tip.2010.2044965","title":"A Label Field Fusion Bayesian Model and Its Penalized Maximum Rand Estimator for Image Segmentation","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":97,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Artificial intelligence; Markov random field; Segmentation; Image segmentation; Scale-space segmentation; Computer science; Pattern recognition (psychology); Segmentation-based object categorization","score_opus":0.01647114196360106,"score_gpt":0.2743005678911878,"score_spread":0.25782942592758673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156999391","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014466413,0.000103296756,0.9978962,0.00007976052,0.000009255519,0.000016541782,0.000018378523,0.00011875423,0.00031127752],"genre_scores_gemma":[0.1686895,0.00043481897,0.8265427,0.00026498543,0.00016123622,0.0002906903,0.00037025742,0.00025376835,0.0029920074],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99677867,0.0015108408,0.00010944745,0.0006690073,0.0007867095,0.00014538075],"domain_scores_gemma":[0.9970426,0.0017634034,0.0003597833,0.0003108055,0.00044134783,0.00008214566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006415865,0.00096211216,0.001690721,0.002241976,0.00070816284,0.0017394057,0.0027911575,0.0029660577,0.0020256494],"category_scores_gemma":[0.011105625,0.0008905631,0.0015360431,0.0015188282,0.0021511088,0.002974846,0.0016285853,0.0020170885,0.0010342519],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002008579,0.00007991557,0.0010188118,0.00016513898,0.000119849465,0.000115895404,0.00020680776,0.7367141,0.0063914564,0.12211962,0.0022716748,0.13059583],"study_design_scores_gemma":[0.000007781768,0.00002168972,0.00018608649,0.000012534899,0.0000118160915,0.000044261124,0.0000051548664,0.9786946,0.0008710024,0.019242652,0.0008808523,0.000021549744],"about_ca_topic_score_codex":0.0028677464,"about_ca_topic_score_gemma":0.0021653324,"teacher_disagreement_score":0.006415865,"about_ca_system_score_codex":0.0015711115,"about_ca_system_score_gemma":0.0010366614,"threshold_uncertainty_score":0.03393072},"labels":[],"label_agreement":null},{"id":"W2157026765","doi":"10.1016/j.isprsjprs.2013.03.006","title":"Change detection from remotely sensed images: From pixel-based to object-based approaches","year":2013,"lang":"en","type":"article","venue":"ISPRS Journal of Photogrammetry and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1478,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Change detection; Computer science; Remote sensing; Pixel; Land cover; Context (archaeology); Earth observation; Object detection; Data mining; Land use; Artificial intelligence; Satellite; Geography; Pattern recognition (psychology)","score_opus":0.037946545567800534,"score_gpt":0.22461449159204114,"score_spread":0.1866679460242406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157026765","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11161256,0.010273014,0.8679517,0.00054319965,0.00022981862,0.0003531716,0.0009097638,0.0020026944,0.006124018],"genre_scores_gemma":[0.5304334,0.008291503,0.45570967,0.00033878308,0.00038224793,0.00021648705,0.0017370327,0.0003613626,0.0025294784],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99840015,0.00033964557,0.00011604074,0.00048608292,0.00054992526,0.00010822243],"domain_scores_gemma":[0.99815744,0.00072890613,0.00024111274,0.00035784097,0.0004429277,0.00007184892],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021053525,0.0015377231,0.0018405434,0.0073359893,0.00035654413,0.0026558582,0.0019268575,0.001423397,0.0014534054],"category_scores_gemma":[0.0036233326,0.0009600858,0.0013833948,0.0059355744,0.0011473201,0.0026690757,0.0013615148,0.0010107037,0.0011278286],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019816312,0.0002398309,0.01576965,0.0004715159,0.00045417043,0.000119401535,0.00015511473,0.014099968,0.017356476,0.0016992064,0.00166303,0.9477735],"study_design_scores_gemma":[0.00007630213,0.0005816721,0.13292773,0.0003668819,0.0011220191,0.0011455416,0.0009219769,0.773722,0.039983425,0.032807283,0.01610072,0.00024441374],"about_ca_topic_score_codex":0.003555454,"about_ca_topic_score_gemma":0.0049847215,"teacher_disagreement_score":0.0073359893,"about_ca_system_score_codex":0.0006074501,"about_ca_system_score_gemma":0.00046684808,"threshold_uncertainty_score":0.011134326},"labels":[],"label_agreement":null},{"id":"W2157290854","doi":"10.1109/tgrs.2010.2102765","title":"Synthesis of Remote Sensing Label Fields Using a Tree-Structured Hierarchical Model","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Jet Propulsion Laboratory","keywords":"Synthetic aperture radar; Computer science; Unavailability; Data mining; Ground truth; Synthetic data; Remote sensing; Tree (set theory); Data modeling; Remote sensing application; Segmentation; Artificial intelligence","score_opus":0.040171860205255074,"score_gpt":0.2447447154909258,"score_spread":0.20457285528567073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157290854","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009852043,0.000029424198,0.9893189,0.000044650304,0.000007861834,0.000024590794,0.000091477305,0.00019895581,0.00043202782],"genre_scores_gemma":[0.3627615,0.0001426624,0.6340915,0.0000927959,0.000030300858,0.00018723971,0.0008463566,0.0001331521,0.0017144362],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996743,0.00009351424,0.000016921673,0.0000817818,0.00010504677,0.000028444014],"domain_scores_gemma":[0.9991947,0.00043234084,0.000104880186,0.00007968773,0.00015569206,0.000032673193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010630697,0.00045358957,0.00040951106,0.000783612,0.00020482363,0.0006766449,0.0007272072,0.0006685147,0.0010442606],"category_scores_gemma":[0.0022767554,0.0003508337,0.0006937972,0.0007238045,0.00040059254,0.0009020864,0.00043967066,0.0005975452,0.00040316358],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007775032,0.00005688601,0.00064052886,0.000076354125,0.000020248834,0.000038128106,0.00008957119,0.88277453,0.014166114,0.01263378,0.0008931594,0.08853295],"study_design_scores_gemma":[0.000003100608,0.000008455796,0.00007670548,0.0000019886932,0.000002161784,0.00000387535,0.0000037243826,0.9970765,0.0008850746,0.001747387,0.00018743829,0.0000036000695],"about_ca_topic_score_codex":0.0041946624,"about_ca_topic_score_gemma":0.006301312,"teacher_disagreement_score":0.0041946624,"about_ca_system_score_codex":0.0007894781,"about_ca_system_score_gemma":0.0008404664,"threshold_uncertainty_score":0.008340538},"labels":[],"label_agreement":null},{"id":"W2157661720","doi":"10.1109/tip.2010.2097272","title":"Homogeneity Localization Using Particle Filters With Application to Noise Estimation","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Homogeneity (statistics); Estimator; Additive white Gaussian noise; Mathematics; Algorithm; Particle filter; Gaussian noise; Noise reduction; Gaussian; White noise; Computer science; Statistics; Artificial intelligence; Kalman filter","score_opus":0.011398353776400971,"score_gpt":0.24669132132902108,"score_spread":0.2352929675526201,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157661720","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021970444,0.00005996647,0.9974166,0.000023421524,0.000013439501,0.0000068724266,0.000004295375,0.00010495698,0.0001733869],"genre_scores_gemma":[0.20970108,0.00039281504,0.7875664,0.000056982513,0.00011934149,0.00008575407,0.00008174841,0.000103303704,0.001892475],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99948645,0.00012954076,0.000026542662,0.000109228335,0.0002137651,0.00003441476],"domain_scores_gemma":[0.9989942,0.0005916572,0.00011316425,0.00009309969,0.00018346644,0.000024448314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089433865,0.0007561752,0.00072848244,0.0010730813,0.0004183462,0.00073673984,0.000723728,0.0008996462,0.00058615586],"category_scores_gemma":[0.0038073289,0.00043875937,0.0007996758,0.00081694394,0.0005210385,0.0010055519,0.00082528393,0.0007468594,0.0002977066],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023335921,0.00007741607,0.0020645782,0.00018906478,0.00014967236,0.00023440486,0.0002000437,0.5580807,0.04310309,0.025957119,0.0013522543,0.36835834],"study_design_scores_gemma":[0.000009526677,0.00003265681,0.00034892777,0.0000056923177,0.00001742198,0.00005146189,0.000008397879,0.98773265,0.007821457,0.002838844,0.0011198459,0.000013121937],"about_ca_topic_score_codex":0.0037139354,"about_ca_topic_score_gemma":0.0024113583,"teacher_disagreement_score":0.0037139354,"about_ca_system_score_codex":0.00054059946,"about_ca_system_score_gemma":0.00059865706,"threshold_uncertainty_score":0.007384658},"labels":[],"label_agreement":null},{"id":"W2158510284","doi":"10.1016/j.isprsjprs.2008.06.005","title":"Region based segmentation of QuickBird multispectral imagery through band ratios and fuzzy comparison","year":2008,"lang":"en","type":"article","venue":"ISPRS Journal of Photogrammetry and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":58,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"BAND foundation","keywords":"Multispectral image; Segmentation; Computer science; Artificial intelligence; Image segmentation; Scale-space segmentation; Segmentation-based object categorization; Satellite imagery; Multispectral pattern recognition; Remote sensing; Satellite; Pattern recognition (psychology); Region growing; Computer vision; Geography","score_opus":0.0297170945567716,"score_gpt":0.2618328504930777,"score_spread":0.2321157559363061,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158510284","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3236229,0.00082737335,0.6652299,0.00011850523,0.00006230112,0.00025428907,0.0005638019,0.0015375989,0.007783305],"genre_scores_gemma":[0.5883244,0.00033201024,0.40757617,0.000035509525,0.000025669015,0.00009435357,0.00047132513,0.00017711519,0.0029634153],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99967897,0.00004585557,0.000027501577,0.00007323452,0.00013081088,0.000043620203],"domain_scores_gemma":[0.9996191,0.0001098604,0.000043909404,0.00003926877,0.00016982018,0.000018051483],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063389045,0.00042775134,0.00048381698,0.003499976,0.0004284939,0.0011386907,0.00061595364,0.0004914227,0.0021332074],"category_scores_gemma":[0.0008950824,0.00038608882,0.00067791843,0.0010549844,0.00033792225,0.0008507602,0.0002977483,0.00022603617,0.0006022172],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009252677,0.00017758057,0.005515427,0.0003888175,0.00014400332,0.00016264069,0.00035232585,0.062054187,0.25623116,0.00489251,0.0017384014,0.66741765],"study_design_scores_gemma":[0.000065493456,0.00026276,0.041268606,0.0000804306,0.00031008403,0.00059170753,0.00040967387,0.74558526,0.19920324,0.0051766355,0.0069364016,0.000109724744],"about_ca_topic_score_codex":0.00608932,"about_ca_topic_score_gemma":0.0068037254,"teacher_disagreement_score":0.00608932,"about_ca_system_score_codex":0.0005429768,"about_ca_system_score_gemma":0.00060116686,"threshold_uncertainty_score":0.0121077895},"labels":[],"label_agreement":null},{"id":"W2159872961","doi":"10.3390/rs71012829","title":"A Hybrid Kernel-Based Change Detection Method for Remotely Sensed Data in a Similarity Space","year":2015,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Change detection; Kernel (algebra); Pattern recognition (psychology); Reproducing kernel Hilbert space; Artificial intelligence; Similarity (geometry); Similarity measure; Cluster analysis; Support vector machine; Algorithm; Hilbert space; Data mining; Mathematics; Image (mathematics)","score_opus":0.14146433734912753,"score_gpt":0.3275773108628515,"score_spread":0.186112973513724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159872961","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010926526,0.00007756377,0.9882768,0.000026372656,0.000018686735,0.000029402174,0.000025973917,0.00041707238,0.00020168822],"genre_scores_gemma":[0.24586098,0.0001503216,0.75155264,0.000055608813,0.000039557453,0.00009828395,0.0002641106,0.00010451722,0.0018740183],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989293,0.0001661048,0.00009242462,0.00034479392,0.00039019441,0.00007707827],"domain_scores_gemma":[0.99914324,0.00018124715,0.00010225951,0.00012186218,0.00040843504,0.00004294188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009216233,0.0005825937,0.0009031921,0.0022750965,0.00034432462,0.0010440045,0.0010149746,0.00075174,0.0009529627],"category_scores_gemma":[0.0021568,0.00033491597,0.0010386573,0.0019940804,0.00048620233,0.0015042644,0.0008705449,0.00075685314,0.00056075247],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002978877,0.00021896302,0.0018835342,0.00021348117,0.00013662102,0.00011959343,0.00017821885,0.061563216,0.08424312,0.008091623,0.0015958691,0.8414579],"study_design_scores_gemma":[0.000013018466,0.000083834464,0.0017779217,0.0000060692832,0.000021240989,0.00014743129,0.00002894607,0.9779247,0.016407607,0.0016497009,0.0018989118,0.000040512412],"about_ca_topic_score_codex":0.0023896499,"about_ca_topic_score_gemma":0.0018272218,"teacher_disagreement_score":0.0023896499,"about_ca_system_score_codex":0.000536039,"about_ca_system_score_gemma":0.00067313056,"threshold_uncertainty_score":0.0048740506},"labels":[],"label_agreement":null},{"id":"W2160179017","doi":"10.1109/ccece.2011.6030597","title":"Information theoretic assessment of correlated noise in hyperspectral signal unmixing","year":2011,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Hyperspectral imaging; Noise (video); Gaussian noise; Full spectral imaging; Computer science; Artificial intelligence; Pattern recognition (psychology); Value noise; White noise; Gradient noise; Noise measurement; Mathematics; Statistics; Noise reduction; Noise floor; Image (mathematics)","score_opus":0.01374405612305165,"score_gpt":0.2186997494073376,"score_spread":0.20495569328428595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160179017","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054426346,0.00063117093,0.9420569,0.00025472112,0.000025095398,0.00003782389,0.00007249913,0.00007036749,0.002425028],"genre_scores_gemma":[0.8848612,0.0011494394,0.11190752,0.00013649976,0.0001318693,0.00015569224,0.00029588366,0.00006871407,0.0012932625],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978423,0.000866505,0.00008630499,0.00021592787,0.00087445957,0.000114455324],"domain_scores_gemma":[0.9844258,0.012787622,0.000844037,0.00055037206,0.0012015345,0.00019065707],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0055567925,0.0010942322,0.0008687691,0.0022571073,0.00050600874,0.0015251399,0.0010294429,0.0012219533,0.0006665289],"category_scores_gemma":[0.02347682,0.00048806597,0.00062332174,0.001405516,0.0028894066,0.0032151896,0.0018823185,0.00096822367,0.00014006093],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014181201,0.00006216809,0.0019546407,0.00015572224,0.00009087868,0.00029979117,0.00011174005,0.86605656,0.0041882684,0.10452958,0.00056461367,0.021844232],"study_design_scores_gemma":[0.0000040165014,0.000021160056,0.0004749723,0.000010500212,0.000009855837,0.000038635142,0.000016245405,0.97990674,0.0012592856,0.018113302,0.00013067159,0.000014573347],"about_ca_topic_score_codex":0.0015247682,"about_ca_topic_score_gemma":0.001150899,"teacher_disagreement_score":0.0055567925,"about_ca_system_score_codex":0.0013668538,"about_ca_system_score_gemma":0.0010317577,"threshold_uncertainty_score":0.029387474},"labels":[],"label_agreement":null},{"id":"W2160934142","doi":"10.3390/rs4082256","title":"Object-Based Classification of Urban Areas Using VHR Imagery and Height Points Ancillary Data","year":2012,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":108,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Impervious surface; Land cover; Computer science; Cohen's kappa; Thematic map; Remote sensing; Support vector machine; Pattern recognition (psychology); Object based; Classifier (UML); Contextual image classification; Artificial intelligence; Object (grammar); Data mining; Cartography; Land use; Image (mathematics); Geography; Machine learning","score_opus":0.05804470664752823,"score_gpt":0.2672405055847475,"score_spread":0.20919579893721926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160934142","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7723969,0.00020399377,0.22197977,0.000050275576,0.000027428494,0.00018344115,0.0006410867,0.0014650766,0.0030520884],"genre_scores_gemma":[0.9188528,0.00007906002,0.079324074,0.000022335445,0.000009504566,0.000041974763,0.0007937789,0.000027328715,0.00084912335],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99967754,0.000041069583,0.000022981243,0.00008983006,0.00011589152,0.000052762156],"domain_scores_gemma":[0.9996474,0.00007883892,0.00004855073,0.000066578665,0.00013259286,0.000026090214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067133864,0.00039824782,0.00042074965,0.002166732,0.000181006,0.00077366055,0.0004154769,0.00031373996,0.00061346544],"category_scores_gemma":[0.0006223714,0.00016043747,0.00052164326,0.0007113005,0.0002738266,0.00045744915,0.0003540598,0.00018374603,0.0004233142],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042805256,0.0004788592,0.07842784,0.000190789,0.00026918214,0.00037642336,0.00040847278,0.10143591,0.14948148,0.001426911,0.0015832682,0.66549283],"study_design_scores_gemma":[0.00002822767,0.00028677046,0.15019505,0.000024901898,0.0001589545,0.00023411775,0.00037248002,0.77586406,0.07006308,0.001015822,0.0016960986,0.00006048984],"about_ca_topic_score_codex":0.005994281,"about_ca_topic_score_gemma":0.005081934,"teacher_disagreement_score":0.005994281,"about_ca_system_score_codex":0.00029529392,"about_ca_system_score_gemma":0.00030321727,"threshold_uncertainty_score":0.011918783},"labels":[],"label_agreement":null},{"id":"W2160989945","doi":"10.1109/igarss.1993.322395","title":"Integration of multispectral and textural analysis applied to SPOT imagery in urban areas","year":2002,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Multispectral image; Panchromatic film; Computer science; Multispectral pattern recognition; Artificial intelligence; Remote sensing; Pattern recognition (psychology); Cartography; Geography","score_opus":0.014551433314038029,"score_gpt":0.21179004478884841,"score_spread":0.1972386114748104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160989945","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16789922,0.002534412,0.7220792,0.00089051883,0.0003569657,0.00043567023,0.0023795546,0.006663569,0.09676088],"genre_scores_gemma":[0.43312517,0.0019039408,0.5277422,0.00030129545,0.00010517348,0.0000992521,0.0016313809,0.000456226,0.034635372],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998274,0.000019006227,0.000006645327,0.000015984591,0.000103209255,0.000027709972],"domain_scores_gemma":[0.9997732,0.000034101868,0.000013574503,0.000021525975,0.00014638627,0.00001118693],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002822821,0.0005548222,0.00022180157,0.00244242,0.00043906755,0.00080288417,0.00031947912,0.00039330087,0.0039482038],"category_scores_gemma":[0.0004059701,0.00017415533,0.0004069467,0.0019200068,0.00034746752,0.00035615006,0.00023674426,0.00019338199,0.0016460402],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018314876,0.00010993375,0.008849146,0.00039395003,0.00008461023,0.0008377595,0.0003781682,0.021265272,0.19742535,0.0040154364,0.0082204845,0.7582367],"study_design_scores_gemma":[0.000035193843,0.00034230313,0.29175764,0.00021186785,0.0003167943,0.0031786077,0.0013494113,0.37633932,0.20961249,0.007688021,0.10892293,0.00024545845],"about_ca_topic_score_codex":0.09573496,"about_ca_topic_score_gemma":0.30842707,"teacher_disagreement_score":0.09573496,"about_ca_system_score_codex":0.00070984964,"about_ca_system_score_gemma":0.00061819825,"threshold_uncertainty_score":0.19035542},"labels":[],"label_agreement":null},{"id":"W2161981835","doi":"","title":"REGO: Rank-based Estimation of Renyi Information using Euclidean Graph Optimization","year":2010,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Copula (linguistics); Estimator; Euclidean distance; Multivariate statistics; Mathematics; Parametric statistics; Graph; Computer science; Statistics; Artificial intelligence; Combinatorics; Econometrics","score_opus":0.009753182820198525,"score_gpt":0.2178105247173453,"score_spread":0.20805734189714678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161981835","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013961381,0.00010852394,0.9975496,0.00005982543,0.000013664413,0.000016197839,0.000048646543,0.0003742621,0.0004331302],"genre_scores_gemma":[0.109615095,0.00044205168,0.8849648,0.00024158233,0.00013273014,0.00020372703,0.000539757,0.0009545663,0.0029057206],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971296,0.0014585273,0.000112306094,0.0003839039,0.00077380287,0.00014185115],"domain_scores_gemma":[0.9963617,0.0018081497,0.00046995914,0.00072772935,0.00052773283,0.00010473732],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004524201,0.0016670132,0.0019110242,0.002829232,0.00048547273,0.0018724923,0.0022840155,0.001369274,0.0025561177],"category_scores_gemma":[0.011716745,0.0009033448,0.0014726166,0.0021119427,0.0015856918,0.0031118547,0.0023816251,0.0021237552,0.0016696912],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018346285,0.00012090432,0.0013950397,0.00031764948,0.0002659894,0.0001445223,0.00016276035,0.5256964,0.007886964,0.107687995,0.006084381,0.35005397],"study_design_scores_gemma":[0.000011932438,0.000035879464,0.00034385553,0.000014210029,0.0000151929735,0.000051438252,0.000012962561,0.9630815,0.0026648343,0.03104353,0.0026851883,0.000039471022],"about_ca_topic_score_codex":0.0021269247,"about_ca_topic_score_gemma":0.0025613715,"teacher_disagreement_score":0.004524201,"about_ca_system_score_codex":0.0010448387,"about_ca_system_score_gemma":0.0014397419,"threshold_uncertainty_score":0.023926556},"labels":[],"label_agreement":null},{"id":"W2162035167","doi":"10.1109/icdsp.2009.5201136","title":"A new adaptive band weighting technique for hydrocarbon detection","year":2009,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"AUG Signals (Canada)","funders":"","keywords":"Constant false alarm rate; Hyperspectral imaging; Weighting; Detector; False alarm; Computer science; Pattern recognition (psychology); Receiver operating characteristic; Artificial intelligence; Algorithm; Physics","score_opus":0.012694383034113826,"score_gpt":0.21651910584060474,"score_spread":0.20382472280649092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162035167","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0068637524,0.0002461187,0.9918127,0.000035055644,0.00005078743,0.000024028683,0.000019972807,0.00033904542,0.00060851994],"genre_scores_gemma":[0.061005548,0.00034585886,0.9354923,0.00006721672,0.000060331862,0.000059288188,0.00011708437,0.00006134873,0.0027909451],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996007,0.000053355157,0.000018824794,0.00007293912,0.00023206526,0.00002221545],"domain_scores_gemma":[0.9996493,0.0000838899,0.000048508893,0.00005223637,0.00015042345,0.000015678728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041496512,0.00052405085,0.00039599568,0.0008833724,0.00021403239,0.000426317,0.00065893255,0.0005751295,0.0017330454],"category_scores_gemma":[0.0007922295,0.0002304988,0.00039645575,0.000880355,0.00026883016,0.00086956704,0.00040127133,0.0005541986,0.0012618323],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001115744,0.000064239,0.0007259403,0.00015037379,0.00005354032,0.000058936774,0.000050583123,0.007647113,0.28389448,0.0047935257,0.0014311117,0.7010186],"study_design_scores_gemma":[0.000038200506,0.000318265,0.004280752,0.000032229924,0.00009789472,0.0013895577,0.000043560372,0.70325786,0.24373679,0.0044921767,0.04221967,0.000093065806],"about_ca_topic_score_codex":0.00054471666,"about_ca_topic_score_gemma":0.0009097856,"teacher_disagreement_score":0.0017330454,"about_ca_system_score_codex":0.00017328355,"about_ca_system_score_gemma":0.0002769769,"threshold_uncertainty_score":0.005797565},"labels":[],"label_agreement":null},{"id":"W2164315346","doi":"10.1186/1687-6180-2012-142","title":"Real-time target detection in hyperspectral images based on spatial-spectral information extraction","year":2012,"lang":"en","type":"article","venue":"EURASIP Journal on Advances in Signal Processing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Hyperspectral imaging; Computer science; Digital signal processing; Software; Image processing; Artificial intelligence; Covariance matrix; Pixel; Computer vision; Pattern recognition (psychology); Computer hardware; Algorithm; Image (mathematics)","score_opus":0.008420047041147433,"score_gpt":0.2565784559468113,"score_spread":0.24815840890566385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164315346","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04927032,0.00011518825,0.94899243,0.00006361524,0.000015738924,0.000026776133,0.000033399607,0.0005098053,0.0009727559],"genre_scores_gemma":[0.32308257,0.00018814087,0.6750013,0.00005972929,0.000017401851,0.000049687947,0.00013502335,0.00005848326,0.0014076184],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997383,0.000042607797,0.00001684566,0.000049908427,0.00013096731,0.000021435972],"domain_scores_gemma":[0.9997414,0.000096597454,0.000033518383,0.000029988114,0.00008865413,0.000009822907],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034816333,0.00037849462,0.00033999167,0.0005965249,0.00017428823,0.0003472349,0.00039015748,0.0002567718,0.0009122256],"category_scores_gemma":[0.00081819395,0.00019937636,0.00029633375,0.0005988893,0.00025915157,0.0007900734,0.0004621148,0.00028441107,0.00035243796],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024975347,0.00013818685,0.0018675289,0.00015581757,0.000043758606,0.00011243784,0.000114211645,0.039255336,0.41392797,0.0047282786,0.0009277698,0.5384789],"study_design_scores_gemma":[0.00001686206,0.00008996851,0.0031474307,0.000008057164,0.00002338751,0.00022579869,0.000032418237,0.7815908,0.21077065,0.0019686944,0.0021009224,0.0000249111],"about_ca_topic_score_codex":0.00041465572,"about_ca_topic_score_gemma":0.00065525185,"teacher_disagreement_score":0.0009122256,"about_ca_system_score_codex":0.00016021152,"about_ca_system_score_gemma":0.00023283597,"threshold_uncertainty_score":0.0030516982},"labels":[],"label_agreement":null},{"id":"W2164534000","doi":"10.1109/igarss.2002.1025002","title":"Hyperspectral linear mixing based on in situ measurements in a coral reef environment","year":2003,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Vancouver Coastal Health","funders":"","keywords":"Endmember; Hyperspectral imaging; Pixel; Coral; Remote sensing; Coral reef; Spectral signature; Benthic zone; Mixing (physics); Environmental science; Geology; Oceanography; Computer science; Physics; Artificial intelligence","score_opus":0.03987167702488098,"score_gpt":0.22628527691471226,"score_spread":0.18641359988983128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164534000","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9877045,0.0000228383,0.010790711,0.000018550523,0.0000034198383,0.000007764903,0.00008388383,0.00012029782,0.0012480306],"genre_scores_gemma":[0.987938,0.00002400849,0.011496814,0.0000076176707,0.0000038045027,0.000004783407,0.00016135034,0.000015896787,0.00034778327],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9999124,0.000017642617,0.0000032866778,0.000022522529,0.000033817443,0.0000102252725],"domain_scores_gemma":[0.99990356,0.000023780745,0.000015383786,0.000012837917,0.00003365811,0.000010766174],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001565029,0.00022825017,0.00011719606,0.0004127991,0.00016167741,0.00030429167,0.00012464469,0.00012906581,0.00064986077],"category_scores_gemma":[0.0004438865,0.00013415201,0.00013986968,0.0003174746,0.00014282245,0.00031544262,0.00019612504,0.00013676847,0.00014909572],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00080449,0.00021842783,0.08874072,0.00008265984,0.00009711328,0.00014436647,0.00030505712,0.022769012,0.7795612,0.00055419357,0.0005352842,0.10618747],"study_design_scores_gemma":[0.000024688796,0.0001702766,0.2952499,0.000013737873,0.000094819356,0.0003265193,0.00023150186,0.46035677,0.24212287,0.00048525844,0.00088379375,0.00003992811],"about_ca_topic_score_codex":0.0029015255,"about_ca_topic_score_gemma":0.0066771586,"teacher_disagreement_score":0.0029015255,"about_ca_system_score_codex":0.00020514044,"about_ca_system_score_gemma":0.000099192635,"threshold_uncertainty_score":0.0057693124},"labels":[],"label_agreement":null},{"id":"W2164595720","doi":"10.1109/igarss.2001.976904","title":"Assessment of Beer's law of logarithmic attenuation for remote sensing of shallow tropical waters","year":2002,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Attenuation; Downwelling; Water column; Irradiance; Logarithm; Beer–Lambert law; Remote sensing; Waves and shallow water; Environmental science; Coral reef; SIGNAL (programming language); Attenuation coefficient; Reef; Oceanography; Geology; Law; Computer science; Mathematics; Optics; Upwelling; Physics","score_opus":0.03098297992905572,"score_gpt":0.2572429081745939,"score_spread":0.22625992824553817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164595720","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39627331,0.0026636852,0.5893931,0.0004872561,0.00009477155,0.0003481276,0.00045185132,0.0018877499,0.008400179],"genre_scores_gemma":[0.9153618,0.0007354131,0.08193778,0.00014765546,0.000052141953,0.00017913367,0.0003558135,0.00019482625,0.0010354863],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99776447,0.00067538803,0.0001366808,0.00031751307,0.00092027336,0.00018569239],"domain_scores_gemma":[0.9822274,0.012599562,0.0014053535,0.0014220604,0.0021382764,0.00020729913],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005713143,0.0005985361,0.0005211249,0.0016948268,0.00047182565,0.0013560472,0.0011354386,0.0008508842,0.0012459412],"category_scores_gemma":[0.03067262,0.00033478122,0.00079370337,0.0012473328,0.0010712495,0.0020690085,0.0007347129,0.0010113925,0.00061779446],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011785426,0.00030998018,0.16838673,0.0010344554,0.00057226967,0.0009374098,0.001181214,0.21099408,0.07922005,0.027394257,0.004192508,0.50459856],"study_design_scores_gemma":[0.000042739022,0.0006523754,0.16031843,0.00014701638,0.00024100857,0.0016000989,0.00058387103,0.77313006,0.030916143,0.022617623,0.009533187,0.00021747306],"about_ca_topic_score_codex":0.0037555883,"about_ca_topic_score_gemma":0.0026815303,"teacher_disagreement_score":0.005713143,"about_ca_system_score_codex":0.001063639,"about_ca_system_score_gemma":0.0008355109,"threshold_uncertainty_score":0.03021437},"labels":[],"label_agreement":null},{"id":"W2165922980","doi":"10.1145/1102351.1102482","title":"Learning from labeled and unlabeled data on a directed graph","year":2005,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":404,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Cluster analysis; Spectral clustering; Directed graph; Graph; Undirected graph; Artificial intelligence; Theoretical computer science; Comparability graph; Clustering coefficient; Labeled data; Algorithm; Pattern recognition (psychology); Line graph; Voltage graph","score_opus":0.02841037829395239,"score_gpt":0.23300747430131044,"score_spread":0.20459709600735804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165922980","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028659229,0.000099462304,0.9960186,0.00017948433,0.00002065047,0.00004306568,0.00015961032,0.00020249713,0.0004107483],"genre_scores_gemma":[0.14426151,0.0006848094,0.85002583,0.00052379275,0.00016974502,0.00041271694,0.0019573416,0.00014032288,0.0018239976],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99575377,0.002000404,0.00019209656,0.0010949399,0.00074540847,0.00021333205],"domain_scores_gemma":[0.99055976,0.0056580994,0.00075753126,0.0017464651,0.000968091,0.0003100511],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049427203,0.001115069,0.0017989118,0.003677754,0.0008754431,0.002136834,0.0039046954,0.002329801,0.0017102504],"category_scores_gemma":[0.013685525,0.0007966088,0.0016256943,0.0036762638,0.0020060625,0.0044656848,0.0023793208,0.0025362594,0.00089831074],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016118985,0.0002620851,0.003492334,0.0005764486,0.00024448254,0.00037266198,0.00025446177,0.49650285,0.004913913,0.18767166,0.0074005015,0.29814747],"study_design_scores_gemma":[0.000017133003,0.000039672253,0.00030708386,0.00002886716,0.000023456081,0.00006728223,0.000042585623,0.8437506,0.0011276805,0.15156929,0.0030041845,0.000022127648],"about_ca_topic_score_codex":0.0039857007,"about_ca_topic_score_gemma":0.0065504704,"teacher_disagreement_score":0.0049427203,"about_ca_system_score_codex":0.0013762128,"about_ca_system_score_gemma":0.0017468709,"threshold_uncertainty_score":0.026139915},"labels":[],"label_agreement":null},{"id":"W2166013665","doi":"10.1109/igarss.1992.576772","title":"A New Clustering Algorithm For Multispectral Remote Sensing Imagery","year":2005,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Multispectral image; Computer science; Cluster analysis; Multispectral pattern recognition; Remote sensing; Artificial intelligence; Algorithm; Geology","score_opus":0.016641293553720425,"score_gpt":0.245928687580172,"score_spread":0.22928739402645157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166013665","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034127661,0.00021548569,0.99424356,0.000062401305,0.0001461542,0.00007028342,0.00008077608,0.0009631443,0.00080531224],"genre_scores_gemma":[0.018536307,0.00014816098,0.9768117,0.000072895295,0.00009007979,0.00011939622,0.00042837285,0.00024275499,0.0035503027],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984946,0.00016396753,0.00008967037,0.0003399071,0.0008282354,0.00008360814],"domain_scores_gemma":[0.9985701,0.00019035164,0.0000730607,0.00022244557,0.000888091,0.00005588322],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009149523,0.0010789776,0.0014179305,0.0024334455,0.0013876111,0.0012890047,0.0027343663,0.0014591188,0.003732933],"category_scores_gemma":[0.0020248736,0.0006726345,0.0012973198,0.0032073883,0.0005832754,0.001689118,0.0012115482,0.0011603069,0.0036582318],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013147699,0.000121646335,0.00050950656,0.00015882429,0.00016856063,0.000045604454,0.0000958656,0.048050087,0.033769064,0.005025855,0.010979941,0.9009436],"study_design_scores_gemma":[0.000055648354,0.00008519205,0.0021289291,0.000025965735,0.00008295085,0.0002884284,0.0000633604,0.9406236,0.025794845,0.0077574165,0.023000304,0.000093304705],"about_ca_topic_score_codex":0.0078726085,"about_ca_topic_score_gemma":0.014042446,"teacher_disagreement_score":0.0078726085,"about_ca_system_score_codex":0.00090824044,"about_ca_system_score_gemma":0.001124467,"threshold_uncertainty_score":0.01565355},"labels":[],"label_agreement":null},{"id":"W2166305686","doi":"10.1109/isidf.2011.6024219","title":"Building Detection from Pan-Sharpened GeoEye-1 Satellite Imagery Using Context Based Multi-Level Image Segmentation","year":2011,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Artificial intelligence; Computer vision; Shadow (psychology); Context (archaeology); Pixel; Image resolution; Segmentation; Remote sensing; Image segmentation; Sobel operator; Edge detection; Satellite imagery; Image processing; Geography; Image (mathematics)","score_opus":0.10083489207689776,"score_gpt":0.2682503157214534,"score_spread":0.16741542364455564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166305686","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6475096,0.00049078243,0.34624505,0.000060818194,0.000022170114,0.00011835462,0.00032345756,0.0023112136,0.0029186083],"genre_scores_gemma":[0.75107247,0.00021781115,0.2474721,0.000021374368,0.000016077482,0.000027526308,0.00052236277,0.000065447246,0.00058486377],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998142,0.000024627741,0.000008025265,0.000048280206,0.00007214045,0.000032775682],"domain_scores_gemma":[0.999826,0.000034358134,0.000032278385,0.00003476529,0.00005691671,0.000015603124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022639723,0.0003824603,0.00039171957,0.0020560806,0.0001714309,0.0004710769,0.0003020073,0.0003105273,0.0007614521],"category_scores_gemma":[0.00038159118,0.00026909815,0.0003896464,0.00076321553,0.00021880669,0.00042005652,0.00042809395,0.00026536055,0.0002481513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00058554474,0.0001280643,0.010502269,0.00028762443,0.00007826637,0.00031287206,0.00016730458,0.033265095,0.5700249,0.00095352053,0.0007774181,0.38291708],"study_design_scores_gemma":[0.000044214226,0.0003520673,0.120248675,0.000043464865,0.0001477034,0.0009267951,0.00017971465,0.63173205,0.2420037,0.0012140466,0.0030393645,0.000068182526],"about_ca_topic_score_codex":0.0021655818,"about_ca_topic_score_gemma":0.0042605223,"teacher_disagreement_score":0.0021655818,"about_ca_system_score_codex":0.00019350318,"about_ca_system_score_gemma":0.00021303802,"threshold_uncertainty_score":0.004305899},"labels":[],"label_agreement":null},{"id":"W2167212773","doi":"10.1109/isda.2009.109","title":"A Comparative Study of Clustering Methods for Urban Areas Segmentation from High Resolution Remote Sensing Image","year":2009,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; Computer science; Image segmentation; Artificial intelligence; Segmentation; Segmentation-based object categorization; Computer vision; Ground truth; Scale-space segmentation; Region growing; Pattern recognition (psychology); Remote sensing; Geography","score_opus":0.04904934019024749,"score_gpt":0.3512833131978402,"score_spread":0.3022339730075927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167212773","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30474073,0.01442929,0.6632475,0.0006623805,0.0003474863,0.0007132105,0.00075784436,0.003053233,0.012048359],"genre_scores_gemma":[0.5030133,0.0024359429,0.4902589,0.000104379644,0.00010681327,0.00021138482,0.0012634896,0.00048066405,0.0021251282],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99255073,0.0031095026,0.00047018312,0.00065265084,0.0029600721,0.00025692166],"domain_scores_gemma":[0.9775869,0.01420912,0.0008940959,0.0012245021,0.0057938993,0.00029142268],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011195158,0.0012558091,0.0013298,0.008818512,0.0011440199,0.0016433994,0.0014244275,0.0016463797,0.001457365],"category_scores_gemma":[0.018568119,0.0004411995,0.0015663309,0.0058461824,0.00065042806,0.001808073,0.00056080776,0.00053375284,0.0006668587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021940742,0.00046458162,0.018067455,0.0018753133,0.001644013,0.00018918565,0.000901356,0.17824975,0.02760056,0.0035596546,0.0053491304,0.7599049],"study_design_scores_gemma":[0.00015026424,0.0013188022,0.054293647,0.00023843978,0.0006127542,0.00073761476,0.00096649694,0.8914486,0.03983348,0.0028783348,0.0072408686,0.00028081518],"about_ca_topic_score_codex":0.007774009,"about_ca_topic_score_gemma":0.010994402,"teacher_disagreement_score":0.011195158,"about_ca_system_score_codex":0.0012554857,"about_ca_system_score_gemma":0.0006850619,"threshold_uncertainty_score":0.059206307},"labels":[],"label_agreement":null},{"id":"W2167361654","doi":"","title":"Urban Land-cover Mapping with High-resolution Spaceborne SAR Data","year":2010,"lang":"en","type":"article","venue":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Remote sensing; Land cover; Cover (algebra); Geography; Synthetic aperture radar; Cartography; Environmental science; Land use; Engineering","score_opus":0.023427611589926033,"score_gpt":0.23201024568681175,"score_spread":0.2085826340968857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167361654","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87839615,0.00046167223,0.11179288,0.00011179811,0.000014912657,0.00018333657,0.0016184897,0.00068070786,0.006740065],"genre_scores_gemma":[0.929158,0.00027067214,0.06730267,0.000017921353,0.00000861945,0.00003790197,0.0016538553,0.000019144034,0.0015312737],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9998374,0.000024356825,0.000008540972,0.00003567573,0.000077257006,0.000016740041],"domain_scores_gemma":[0.99984753,0.000027089018,0.000030324434,0.000026716643,0.000058819372,0.000009604729],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022987726,0.00026539597,0.00014146355,0.0013001245,0.00012403207,0.00045171048,0.0002625758,0.00014189356,0.00053902756],"category_scores_gemma":[0.00059431564,0.00012249796,0.00022037154,0.0012348603,0.00013785639,0.00041128116,0.00025157697,0.00013379916,0.000264774],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016437344,0.00022182333,0.11930775,0.00024167553,0.00017242592,0.00055680156,0.0005111521,0.19009948,0.071204565,0.0012551881,0.0029742818,0.6132905],"study_design_scores_gemma":[0.000024375164,0.00011718247,0.28913146,0.000036474878,0.0000853991,0.0002010257,0.00051542907,0.68303984,0.019725125,0.0009495071,0.0061310465,0.000043162785],"about_ca_topic_score_codex":0.040616397,"about_ca_topic_score_gemma":0.08207759,"teacher_disagreement_score":0.040616397,"about_ca_system_score_codex":0.0004858361,"about_ca_system_score_gemma":0.00041346528,"threshold_uncertainty_score":0.08075994},"labels":[],"label_agreement":null},{"id":"W2167975673","doi":"10.1016/s0924-2716(02)00160-0","title":"A comparative analysis of scanned maps and imagery for mapping applications","year":2003,"lang":"en","type":"article","venue":"ISPRS Journal of Photogrammetry and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":45,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Natural Resources Canada","funders":"","keywords":"Computer science; Raster graphics; Artificial intelligence; Remote sensing; Thresholding; Monochrome; Principal component analysis; Normalized Difference Vegetation Index; Computer vision; Raster data; Hue; Image processing; Feature extraction; Pattern recognition (psychology); Geography; Image (mathematics); Geology","score_opus":0.02338437655625032,"score_gpt":0.26735776757348123,"score_spread":0.24397339101723092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167975673","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94500893,0.0014669835,0.026405402,0.00022820465,0.00004890304,0.00019744645,0.0033863646,0.0004635001,0.022794219],"genre_scores_gemma":[0.97467166,0.0008218656,0.01797382,0.00002687106,0.000026747315,0.00006564386,0.002605989,0.00016319095,0.0036443067],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99930835,0.00014967125,0.000043353833,0.000060637234,0.00038715045,0.000050854695],"domain_scores_gemma":[0.99371284,0.0031003528,0.0002571251,0.00032569972,0.0025147705,0.000089146095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001008125,0.00029793943,0.00025553725,0.006586514,0.00033385245,0.0016339031,0.00043569118,0.00036369183,0.0058053387],"category_scores_gemma":[0.006282039,0.00014718385,0.00050393085,0.0051723123,0.0002512639,0.0015669962,0.00037818536,0.00014399229,0.00090330304],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0041703293,0.0004951975,0.2015258,0.0012917378,0.00054972403,0.0011829976,0.0017203429,0.04200443,0.062434006,0.008021542,0.0061090994,0.6704948],"study_design_scores_gemma":[0.00008044421,0.0012024285,0.79996073,0.00017450664,0.0010105735,0.0013382906,0.0051561957,0.13416839,0.029059516,0.006134704,0.02161535,0.00009892582],"about_ca_topic_score_codex":0.0047483467,"about_ca_topic_score_gemma":0.008662725,"teacher_disagreement_score":0.006586514,"about_ca_system_score_codex":0.00045109924,"about_ca_system_score_gemma":0.000520149,"threshold_uncertainty_score":0.019420803},"labels":[],"label_agreement":null},{"id":"W2170075761","doi":"10.1109/igarss.2004.1369964","title":"Investigation of multiscale product for change detection in difference images","year":2004,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Resources Canada","funders":"","keywords":"Change detection; Monte Carlo method; Scale (ratio); Computer science; Product (mathematics); Range (aeronautics); Noise (video); Measure (data warehouse); Artificial intelligence; Pattern recognition (psychology); Algorithm; Mathematics; Image (mathematics); Data mining; Physics; Statistics; Materials science","score_opus":0.05020830897327603,"score_gpt":0.24301818685483625,"score_spread":0.19280987788156023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170075761","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23673806,0.00038246467,0.7610504,0.00013036652,0.000021480333,0.000055241795,0.0000650913,0.00045721713,0.0010997569],"genre_scores_gemma":[0.7896699,0.00018043426,0.2096604,0.000031968466,0.000028543427,0.00005133218,0.00007439536,0.00006521754,0.00023784886],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988856,0.00033801302,0.00005095593,0.00018392826,0.00048497727,0.000056520024],"domain_scores_gemma":[0.9898925,0.0075129066,0.00088874635,0.00075595506,0.0007175209,0.00023248066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041975016,0.0005542656,0.00072062894,0.0012490525,0.00020881179,0.0010921962,0.0006744183,0.0007424216,0.0009806388],"category_scores_gemma":[0.014559259,0.00030911923,0.00055657595,0.0008223448,0.0010022307,0.002014904,0.00087141927,0.00056591234,0.00018363954],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013273752,0.00025621968,0.014104049,0.00048330994,0.0002681534,0.0005918447,0.00031632915,0.38612753,0.201331,0.053319328,0.00072924886,0.34114578],"study_design_scores_gemma":[0.000010050467,0.00023907585,0.0024833463,0.000006085844,0.000022052032,0.0001881303,0.00000917059,0.97879636,0.014282204,0.0036672477,0.00027742967,0.000018824185],"about_ca_topic_score_codex":0.00035900483,"about_ca_topic_score_gemma":0.0003340352,"teacher_disagreement_score":0.0041975016,"about_ca_system_score_codex":0.0004090029,"about_ca_system_score_gemma":0.00032876915,"threshold_uncertainty_score":0.022198796},"labels":[],"label_agreement":null},{"id":"W2170277041","doi":"10.1109/icip.2005.1529742","title":"Level set curve evolution partitioning of polarimetric images","year":2005,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Polarimetry; Synthetic aperture radar; Smoothness; Artificial intelligence; Image segmentation; Segmentation; Radar imaging; Gaussian; Computer vision; Computer science; Pattern recognition (psychology); Mathematics; Radar; Optics; Scattering; Physics; Mathematical analysis","score_opus":0.03889053809570605,"score_gpt":0.24929844870645748,"score_spread":0.21040791061075143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170277041","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.071115814,0.00011222788,0.9273582,0.00011288266,0.0000081602875,0.000057900736,0.000042331885,0.000277684,0.00091470894],"genre_scores_gemma":[0.44365796,0.00016765649,0.55332565,0.000051538143,0.000022459031,0.000115735675,0.0002668057,0.0002178476,0.0021743414],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996499,0.00008818614,0.000011952715,0.00008833934,0.00012540341,0.000036350495],"domain_scores_gemma":[0.9991516,0.00046321683,0.00008310396,0.00011228159,0.00013775514,0.000051975672],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072533434,0.00060067634,0.00073351094,0.0010541797,0.00042327202,0.0009486054,0.0008279284,0.0009524381,0.0009577186],"category_scores_gemma":[0.0024911608,0.00041085327,0.0005893099,0.00066676363,0.00086942123,0.0010981377,0.0007818722,0.00077429484,0.00035114374],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013447122,0.00007852139,0.0013961148,0.00009589571,0.000046675257,0.000054001037,0.0002099086,0.76193863,0.034839086,0.018254172,0.0005491694,0.18240346],"study_design_scores_gemma":[0.0000023266477,0.000014711698,0.0001735906,0.0000022821425,0.0000021832875,0.000010693887,0.0000060719794,0.9926483,0.004319788,0.00251237,0.00030405665,0.0000036803806],"about_ca_topic_score_codex":0.0028827419,"about_ca_topic_score_gemma":0.0020260024,"teacher_disagreement_score":0.0028827419,"about_ca_system_score_codex":0.0010772127,"about_ca_system_score_gemma":0.00049330795,"threshold_uncertainty_score":0.007815838},"labels":[],"label_agreement":null},{"id":"W2170406089","doi":"10.1109/tgrs.2006.881123","title":"Iterative Spectral Unmixing for Optimizing Per-Pixel Endmember Sets","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":169,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Endmember; Hyperspectral imaging; Pixel; Data set; Algorithm; Pattern recognition (psychology); Computer science; Set (abstract data type); Iterative method; Mathematics; Artificial intelligence","score_opus":0.014888653583515803,"score_gpt":0.23837943282756568,"score_spread":0.2234907792440499,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170406089","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012423565,0.000028432614,0.98649466,0.000013385453,0.0000042725965,0.000030280597,0.00001333543,0.00056146854,0.00043056023],"genre_scores_gemma":[0.06799839,0.000027988297,0.9313131,0.000013832015,0.0000039346196,0.00011243885,0.00006136758,0.000156389,0.00031254112],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992101,0.00018698897,0.000052454183,0.00015556802,0.0003463667,0.00004848721],"domain_scores_gemma":[0.9989741,0.00048339364,0.00011352603,0.0001289574,0.00027710135,0.000022962182],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017023457,0.0013035298,0.0006339442,0.0011274511,0.0007034909,0.0006261536,0.0012056654,0.0007490431,0.001035106],"category_scores_gemma":[0.0036876146,0.00081832806,0.0010980243,0.0006871681,0.00068799115,0.0013264922,0.0011611987,0.0010157155,0.00056095107],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014816738,0.0001699415,0.0022275536,0.00013119093,0.00015168599,0.00004370665,0.00034733443,0.5783646,0.11906752,0.004785858,0.00057660544,0.29398587],"study_design_scores_gemma":[0.0000059711138,0.000029577135,0.0003752181,0.000004831531,0.000010940765,0.000017584725,0.000013861189,0.969737,0.02819676,0.0009578277,0.0006353894,0.000015095418],"about_ca_topic_score_codex":0.0031995284,"about_ca_topic_score_gemma":0.0060502053,"teacher_disagreement_score":0.0031995284,"about_ca_system_score_codex":0.000763268,"about_ca_system_score_gemma":0.0013464777,"threshold_uncertainty_score":0.009002924},"labels":[],"label_agreement":null},{"id":"W2170410701","doi":"10.3233/ifs-141378","title":"Image segmentation by generalized hierarchical fuzzy C-means algorithm","year":2015,"lang":"en","type":"article","venue":"Journal of Intelligent & Fuzzy Systems","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":450,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Fuzzy logic; Image (mathematics); Algorithm; Segmentation","score_opus":0.026953447137633466,"score_gpt":0.2648634887363607,"score_spread":0.2379100415987272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170410701","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0046989755,0.00020518682,0.9933635,0.000038172424,0.0000266871,0.000052495594,0.000037660408,0.0007633902,0.0008139704],"genre_scores_gemma":[0.105698295,0.00029379333,0.89090335,0.00007993746,0.00005123106,0.00015674745,0.00022196212,0.00014911969,0.0024455765],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992612,0.00009346321,0.000039576284,0.00025549944,0.0002688322,0.00008137962],"domain_scores_gemma":[0.999708,0.00006289331,0.000033077053,0.000041422252,0.00014190905,0.000012544544],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055924273,0.00076021295,0.0010956248,0.0014872227,0.0006900317,0.0008437201,0.0013925266,0.0014995171,0.0021277578],"category_scores_gemma":[0.0010632793,0.00048334245,0.0012652973,0.0018087202,0.000598689,0.000842005,0.000737768,0.00075718,0.0007513149],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018816888,0.000051348496,0.0005138475,0.0003297601,0.00014078716,0.00012272544,0.00023585634,0.2979553,0.0444225,0.009773424,0.0051592034,0.64110696],"study_design_scores_gemma":[0.000010053639,0.000020498259,0.00031715233,0.000010282058,0.000021212429,0.000036495043,0.000013682458,0.9885761,0.005950825,0.0029608672,0.002062502,0.000020409796],"about_ca_topic_score_codex":0.014289118,"about_ca_topic_score_gemma":0.010790994,"teacher_disagreement_score":0.014289118,"about_ca_system_score_codex":0.0009369369,"about_ca_system_score_gemma":0.001822935,"threshold_uncertainty_score":0.028411865},"labels":[],"label_agreement":null},{"id":"W2177188361","doi":"10.1016/j.asoc.2015.09.045","title":"Gray Wolf Optimizer for hyperspectral band selection","year":2015,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":195,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Hyperspectral imaging; Computer science; Artificial intelligence; Pattern recognition (psychology); Differential evolution; Curse of dimensionality; Pixel; Benchmark (surveying); Selection (genetic algorithm); Heuristic; Optimization problem; Spectral bands; Algorithm; Remote sensing","score_opus":0.02445991997740743,"score_gpt":0.23607426370304466,"score_spread":0.21161434372563723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2177188361","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012491896,0.00033864472,0.9828469,0.0002489237,0.000055647575,0.00003932836,0.00007225691,0.0006125453,0.0032938137],"genre_scores_gemma":[0.35977292,0.0003758905,0.61679184,0.0004815231,0.00013347818,0.000249952,0.00040730796,0.0006903324,0.021096736],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997228,0.0001004139,0.000014148877,0.000044745248,0.00008130183,0.00003653025],"domain_scores_gemma":[0.9995988,0.00021362405,0.000030195297,0.000043455857,0.00008084372,0.000033224554],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011029053,0.0008041737,0.0010446542,0.00065120275,0.00031822518,0.00082475564,0.000867301,0.001257846,0.0051572593],"category_scores_gemma":[0.0018432585,0.00047663195,0.0005022211,0.00068838923,0.0005989793,0.00066694885,0.0009376629,0.001025762,0.0011622317],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022166941,0.00012491054,0.0005218378,0.0001231889,0.000105047984,0.00012174048,0.0000555587,0.7238617,0.0075139194,0.023377933,0.009016962,0.23495555],"study_design_scores_gemma":[0.000008836311,0.000015242711,0.000066746084,0.0000040358855,0.0000044110934,0.000010285268,0.0000027311921,0.99584454,0.0006163224,0.0030230805,0.00040126883,0.0000025504212],"about_ca_topic_score_codex":0.0031436726,"about_ca_topic_score_gemma":0.003143102,"teacher_disagreement_score":0.0051572593,"about_ca_system_score_codex":0.00054098427,"about_ca_system_score_gemma":0.0010692389,"threshold_uncertainty_score":0.017252743},"labels":[],"label_agreement":null},{"id":"W2184834289","doi":"","title":"THE EFFECT OF FOUR NEW MULTISPECTRAL BANDS OF WORLDVIEW2 ON IMPROVING URBAN LAND COVER CLASSIFICATION","year":2012,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Impervious surface; Land cover; Multispectral image; Spectral bands; Remote sensing; Pattern recognition (psychology); Contextual image classification; Feature (linguistics); Data set; Computer science; Artificial intelligence; Set (abstract data type); Class (philosophy); Geography; Image (mathematics); Land use; Engineering","score_opus":0.015016760580808527,"score_gpt":0.2280172848277662,"score_spread":0.21300052424695767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2184834289","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92895085,0.0010348177,0.06649687,0.00014543204,0.00011769867,0.00012948718,0.0003245515,0.00066251954,0.0021378205],"genre_scores_gemma":[0.83128875,0.0006545797,0.16577287,0.00009382347,0.00005274999,0.000049984385,0.0009848444,0.000108129694,0.0009942844],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992848,0.00018535297,0.00005055471,0.00014800926,0.00024033716,0.00009090593],"domain_scores_gemma":[0.9984285,0.0008347374,0.00015251373,0.00019057892,0.00031194833,0.000081697566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001320406,0.0009959228,0.00042845833,0.0011219436,0.0002334655,0.0007018727,0.00043305976,0.0005436759,0.0006149629],"category_scores_gemma":[0.0033751687,0.00022234193,0.0006030196,0.0007328822,0.00030430823,0.0009828364,0.0006133594,0.00048181455,0.00028980421],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026310545,0.00082848687,0.044017524,0.00049989147,0.00038591248,0.00027416163,0.00027038675,0.055749778,0.30689296,0.00035543396,0.0016256797,0.5864687],"study_design_scores_gemma":[0.00017241987,0.0017668081,0.29321843,0.000069954986,0.0007808879,0.00059566204,0.00043982037,0.37396967,0.32108864,0.00045948036,0.0072802342,0.00015800167],"about_ca_topic_score_codex":0.0023481739,"about_ca_topic_score_gemma":0.0047346586,"teacher_disagreement_score":0.0023481739,"about_ca_system_score_codex":0.00019386607,"about_ca_system_score_gemma":0.00020605887,"threshold_uncertainty_score":0.0069830418},"labels":[],"label_agreement":null},{"id":"W2187279703","doi":"","title":"COMBINATION OF OBJECT-BASED AND PIXEL-BASED IMAGE ANALYSIS FOR CLASSIFICATION OF VHR IMAGERY OVER URBAN AREAS","year":2011,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Land cover; Artificial intelligence; Pattern recognition (psychology); Pixel; Contextual image classification; Image segmentation; Image texture; Set (abstract data type); Computer vision; Segmentation; Image resolution; Computer science; Image (mathematics); Texture (cosmology); Mathematics; Object (grammar); Remote sensing; Geography; Land use","score_opus":0.027831427163174157,"score_gpt":0.23447681039524293,"score_spread":0.20664538323206877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2187279703","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33676657,0.0012084187,0.6546253,0.000120604185,0.0000789183,0.00021005659,0.00040995626,0.0025141693,0.0040660365],"genre_scores_gemma":[0.582448,0.00058611715,0.41497684,0.000065264045,0.000051194103,0.00008038907,0.0005736068,0.00011522355,0.0011034578],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994873,0.00010160103,0.00002801729,0.00010598086,0.00023219011,0.000044898836],"domain_scores_gemma":[0.99960583,0.0001267881,0.000049161386,0.000055358254,0.00013839107,0.000024485902],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087437936,0.0006060858,0.0006658492,0.0032188715,0.00021707595,0.0008184104,0.00039236856,0.00043044405,0.00067794137],"category_scores_gemma":[0.00087103195,0.0002677451,0.0006317171,0.0016264066,0.00027585423,0.00078661845,0.00040490009,0.0003107432,0.0005022371],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004358544,0.00028440298,0.020486264,0.00035450765,0.00040554,0.00021409878,0.0002052964,0.020519068,0.19626763,0.0007299139,0.000888708,0.75920874],"study_design_scores_gemma":[0.00004952887,0.00052672473,0.13124838,0.00005287356,0.0005827749,0.00065654627,0.00037711326,0.7615465,0.09952551,0.0012043313,0.0040782415,0.00015150676],"about_ca_topic_score_codex":0.0015285661,"about_ca_topic_score_gemma":0.0025151526,"teacher_disagreement_score":0.0032188715,"about_ca_system_score_codex":0.00019234116,"about_ca_system_score_gemma":0.00027172992,"threshold_uncertainty_score":0.0046242476},"labels":[],"label_agreement":null},{"id":"W2187380372","doi":"","title":"Mixture of Latent Variable Models for Remotely Sensed Image Processing","year":2014,"lang":"en","type":"dissertation","venue":"UWSpace (University of Waterloo)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; China Scholarship Council; University of Waterloo","keywords":"Latent variable; Variable (mathematics); Image processing; Computer science; Artificial intelligence; Remote sensing; Computer vision; Environmental science; Geography; Image (mathematics); Cartography; Mathematics","score_opus":0.01169294876436274,"score_gpt":0.19294891345203508,"score_spread":0.18125596468767233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2187380372","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000857062,0.0020008755,0.99503666,0.00035790988,0.00007976402,0.000024632707,0.0001631714,0.00020694087,0.0012728963],"genre_scores_gemma":[0.22001027,0.013555616,0.74777573,0.0006993482,0.0011992934,0.0007358918,0.0019508055,0.00044103744,0.01363202],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99833727,0.00081321434,0.00006543709,0.00031273533,0.0003564153,0.0001148621],"domain_scores_gemma":[0.9977457,0.0015106576,0.00024364667,0.00019084403,0.00025092316,0.000058191094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028179474,0.0012707562,0.0011922756,0.0014426454,0.00042803664,0.0023599728,0.0027300008,0.0018415739,0.003969835],"category_scores_gemma":[0.006541335,0.0006978738,0.0021094198,0.0022723197,0.0013323087,0.0023898748,0.0022782767,0.0040099295,0.0017448848],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000073461844,0.000078347824,0.0015348279,0.00041458494,0.0002512758,0.00016175152,0.00027305115,0.33994117,0.0019273529,0.54322267,0.009054064,0.10306744],"study_design_scores_gemma":[0.0000068534523,0.000018214885,0.00031040123,0.0000582968,0.00003005995,0.000046450743,0.000026135545,0.84648836,0.00025992934,0.14408872,0.008640131,0.000026555224],"about_ca_topic_score_codex":0.005542827,"about_ca_topic_score_gemma":0.0048129424,"teacher_disagreement_score":0.005542827,"about_ca_system_score_codex":0.0013281216,"about_ca_system_score_gemma":0.001217085,"threshold_uncertainty_score":0.01490289},"labels":[],"label_agreement":null},{"id":"W2189223122","doi":"","title":"OBJECT-BASED MOVING VEHICLE EXTRACTION FROM WORLDVIEW2 IMAGERY","year":2012,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer vision; Artificial intelligence; Computer science; Remote sensing; Feature extraction; Object detection; Extraction (chemistry); Satellite; Geography; Pattern recognition (psychology); Engineering","score_opus":0.018175432156271445,"score_gpt":0.23942918145098716,"score_spread":0.2212537492947157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2189223122","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62461877,0.00090583175,0.36393204,0.00006040182,0.00010666248,0.00022778666,0.0013404815,0.0028966828,0.0059114248],"genre_scores_gemma":[0.7117503,0.00043280868,0.2796723,0.000033866105,0.000023493827,0.00007272238,0.004855715,0.00018449743,0.0029743356],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999762,0.000024431944,0.000012088174,0.000058038237,0.0000859179,0.000057612782],"domain_scores_gemma":[0.9998234,0.00003305315,0.00002357265,0.000024716697,0.00008446272,0.000010736152],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003816301,0.00056938257,0.00044636664,0.002353936,0.00018419791,0.00072615844,0.00048032586,0.0005544542,0.0013610058],"category_scores_gemma":[0.0005334851,0.00022181976,0.00047520065,0.001007765,0.00014165927,0.000794774,0.000378344,0.00015336982,0.0011354933],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006093524,0.00020315737,0.021578914,0.00031727122,0.00025633318,0.00023859681,0.00010177276,0.01712326,0.29351315,0.00064570515,0.0019753424,0.6634372],"study_design_scores_gemma":[0.000049083577,0.00032905876,0.15120162,0.000032316428,0.00017853544,0.00075993425,0.0002986717,0.3707845,0.46558928,0.00062296214,0.010065182,0.00008879026],"about_ca_topic_score_codex":0.002794993,"about_ca_topic_score_gemma":0.0050459555,"teacher_disagreement_score":0.002794993,"about_ca_system_score_codex":0.00020864006,"about_ca_system_score_gemma":0.00021370755,"threshold_uncertainty_score":0.005557418},"labels":[],"label_agreement":null},{"id":"W2204372902","doi":"10.1038/srep28665","title":"Numerical Demultiplexing of Color Image Sensor Measurements via Non-linear Random Forest Modeling","year":2016,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Ontario Ministry of Research and Innovation; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Multispectral image; Image sensor; Computer science; Demultiplexer; Multiplexing; Optics; Spectral imaging; Computer vision; Wavelength; Filter (signal processing); Artificial intelligence; Remote sensing; Physics; Telecommunications; Geology","score_opus":0.035021993242117286,"score_gpt":0.25264305551491145,"score_spread":0.21762106227279415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2204372902","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0122624645,0.0000366414,0.9872907,0.000040179235,0.0000052543946,0.000014004733,0.000013111288,0.000101078724,0.00023653689],"genre_scores_gemma":[0.5886275,0.00017215022,0.40902823,0.00007473163,0.000023327902,0.00013674752,0.00017772414,0.0000618482,0.0016976882],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99946696,0.00016694683,0.000021799724,0.00011816287,0.00017995395,0.0000462488],"domain_scores_gemma":[0.9986431,0.0007824356,0.0002327701,0.00015670365,0.00014710266,0.000037878697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015946802,0.0006908693,0.00052540377,0.0004176003,0.00024434787,0.0005894023,0.00094729546,0.00063040445,0.0005398366],"category_scores_gemma":[0.0034333055,0.0004250671,0.00075391156,0.00038323077,0.0008388458,0.0012889059,0.00060597836,0.0009691211,0.00019182048],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032333046,0.00003768123,0.0005612469,0.000032364696,0.000025160934,0.00003069153,0.00003429855,0.96397114,0.0076981154,0.00937983,0.0001476358,0.018049385],"study_design_scores_gemma":[8.539174e-7,0.0000033656308,0.00003723281,6.280608e-7,9.648895e-7,0.0000038327557,9.110002e-7,0.9981014,0.00084285985,0.0009693965,0.00003671249,0.0000019267159],"about_ca_topic_score_codex":0.002807047,"about_ca_topic_score_gemma":0.003623174,"teacher_disagreement_score":0.002807047,"about_ca_system_score_codex":0.00081259885,"about_ca_system_score_gemma":0.0007982137,"threshold_uncertainty_score":0.00843358},"labels":[],"label_agreement":null},{"id":"W2206208671","doi":"10.14358/pers.81.8.637","title":"An Unsupervised Urban Change Detection Procedure by Using Luminance and Saturation for Multispectral Remotely Sensed Images","year":2015,"lang":"en","type":"article","venue":"Photogrammetric Engineering & Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Change detection; Multispectral image; Artificial intelligence; Thresholding; Computer science; Pattern recognition (psychology); Markov random field; Multispectral pattern recognition; Remote sensing; Computer vision; Image (mathematics); Geography; Image segmentation","score_opus":0.03646215073078092,"score_gpt":0.24967810781340255,"score_spread":0.21321595708262164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2206208671","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1836244,0.0000914134,0.8127346,0.00007242355,0.000027092556,0.00018208807,0.00016570344,0.0014503557,0.0016519168],"genre_scores_gemma":[0.57379216,0.00009026189,0.42430827,0.000050140952,0.000024882504,0.00013487323,0.00034352762,0.00007779162,0.0011780424],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99964094,0.000054639826,0.000021742702,0.00011111511,0.00013634194,0.000035320878],"domain_scores_gemma":[0.99943525,0.00014085171,0.00011966349,0.00007769635,0.00020021257,0.000026386342],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046267852,0.0004460385,0.00042056822,0.0023461517,0.000382741,0.000416247,0.00053094863,0.00036231193,0.00069383817],"category_scores_gemma":[0.0010119756,0.00022729245,0.0005957485,0.00093961076,0.0004310914,0.0006456714,0.000379123,0.000407382,0.00028823686],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024994652,0.0003262919,0.019935764,0.0002295542,0.00013359205,0.00019380538,0.00040668563,0.034906797,0.19208527,0.002499886,0.001650693,0.7473817],"study_design_scores_gemma":[0.000037438615,0.00027435392,0.070825666,0.000025792924,0.000086672146,0.00065119204,0.00025003258,0.74533457,0.17646967,0.002164511,0.0037523224,0.00012784636],"about_ca_topic_score_codex":0.0025358577,"about_ca_topic_score_gemma":0.005796953,"teacher_disagreement_score":0.0025358577,"about_ca_system_score_codex":0.00032319696,"about_ca_system_score_gemma":0.00061757606,"threshold_uncertainty_score":0.005042255},"labels":[],"label_agreement":null},{"id":"W2243541618","doi":"10.1109/tgrs.2015.2474132","title":"Intrinsic Representation of Hyperspectral Imagery for Unsupervised Feature Extraction","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Canadian Space Agency; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Canada Research Chairs","keywords":"Hyperspectral imaging; Pattern recognition (psychology); Discriminative model; Artificial intelligence; Principal component analysis; Computer science; Feature extraction; Boosting (machine learning); Representation (politics); Feature (linguistics); Mathematics","score_opus":0.03501430792261467,"score_gpt":0.27562590065479603,"score_spread":0.24061159273218136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2243541618","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01024039,0.00006271048,0.98818856,0.000038115424,0.000011256029,0.000025927995,0.0001038237,0.0005068301,0.00082254456],"genre_scores_gemma":[0.20233317,0.00023389736,0.7934943,0.000063026084,0.000034031487,0.00017000952,0.0013299542,0.00019380917,0.0021478124],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99968505,0.000057315385,0.000017093067,0.00007398244,0.00013460893,0.000032005977],"domain_scores_gemma":[0.9995554,0.00009670999,0.000058012243,0.00012332834,0.00015152873,0.0000148934205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045370287,0.00059377885,0.0004176256,0.000842058,0.00019369053,0.0005130297,0.0006534331,0.00034480487,0.0017387153],"category_scores_gemma":[0.0012488116,0.00022375106,0.00071378954,0.0011383308,0.00028207304,0.0010344224,0.00063256995,0.00096990395,0.00101551],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007529484,0.0001550593,0.0014999316,0.00018536764,0.0000723349,0.00009528014,0.00014307226,0.17184174,0.18380044,0.023340592,0.0044191536,0.6143717],"study_design_scores_gemma":[0.0000040993145,0.00003091294,0.0010065631,0.0000074655377,0.000012288359,0.000059136313,0.000018853556,0.96120006,0.030306108,0.0037045402,0.003632602,0.000017347436],"about_ca_topic_score_codex":0.0008475899,"about_ca_topic_score_gemma":0.0013929735,"teacher_disagreement_score":0.0017387153,"about_ca_system_score_codex":0.000250312,"about_ca_system_score_gemma":0.00050400576,"threshold_uncertainty_score":0.0058166385},"labels":[],"label_agreement":null},{"id":"W2253567983","doi":"10.5623/cig2014-407","title":"Revue Des Méthodes De Prétraitement Des Données D’imagerie Hyperspectrale Acquises Depuis Un Drone","year":2014,"lang":"fr","type":"article","venue":"GEOMATICA","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Université Laval","funders":"","keywords":"Humanities; Political science; Physics; Art","score_opus":0.05527522195486674,"score_gpt":0.25414712073903356,"score_spread":0.19887189878416683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2253567983","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030620499,0.002965539,0.9913515,0.00039488683,0.00028222366,0.000049592883,0.00018857051,0.0011590938,0.0005464864],"genre_scores_gemma":[0.043646194,0.004033474,0.9419116,0.00036387777,0.0006132874,0.00017787103,0.0014145989,0.00073683425,0.0071022864],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9937224,0.0015212151,0.00052885246,0.0014192468,0.0025572658,0.0002510766],"domain_scores_gemma":[0.9865324,0.0074679186,0.00037104174,0.0016985844,0.0037042354,0.00022577016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008068793,0.0020750032,0.0025441803,0.0035611736,0.0007277237,0.005676224,0.003076329,0.0029788667,0.0055252234],"category_scores_gemma":[0.019064752,0.0014930406,0.0030992622,0.0020296616,0.0015551146,0.0031982088,0.0019261048,0.0048479857,0.005885422],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021842636,0.000094819254,0.0017385645,0.00074911804,0.00047202935,0.00009965547,0.000245843,0.01749582,0.020669078,0.0060037733,0.0054605417,0.9467524],"study_design_scores_gemma":[0.000101849895,0.00018014191,0.0122182015,0.0006535589,0.00037050492,0.0011353708,0.00045202472,0.82906914,0.043461833,0.021472415,0.09066558,0.00021937586],"about_ca_topic_score_codex":0.012755249,"about_ca_topic_score_gemma":0.01094223,"teacher_disagreement_score":0.012755249,"about_ca_system_score_codex":0.00090306555,"about_ca_system_score_gemma":0.0026807063,"threshold_uncertainty_score":0.042672396},"labels":[],"label_agreement":null},{"id":"W2253789497","doi":"","title":"Kernel-based modified fuzzy possibilistic c-means clustering","year":2013,"lang":"fr","type":"article","venue":"Revue Méditerranéenne des Télécommunications","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Kernel (algebra); Cluster analysis; Fuzzy clustering; Computer science; Fuzzy logic; Focus (optics); Data mining; Euclidean distance; Artificial intelligence; Kernel method; Mathematics; Pattern recognition (psychology); Algorithm; Support vector machine; Discrete mathematics","score_opus":0.05299804173203362,"score_gpt":0.26079949237334643,"score_spread":0.2078014506413128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2253789497","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010007955,0.00021666553,0.988641,0.00006494458,0.000020678855,0.00004554355,0.000042218184,0.00016270221,0.00079833117],"genre_scores_gemma":[0.3785036,0.00037496453,0.6183286,0.00007380237,0.00005248186,0.00026363376,0.00034140193,0.000106467545,0.0019552028],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99810445,0.00045795774,0.00013726487,0.00035772848,0.0008176766,0.00012488195],"domain_scores_gemma":[0.9981281,0.00059622485,0.00017681623,0.00023551394,0.0007959618,0.00006730434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015463665,0.000954122,0.0013778657,0.0020532766,0.0009961064,0.0017387816,0.0030299572,0.0019093741,0.0014905632],"category_scores_gemma":[0.0053561,0.0005384394,0.0014541909,0.0023627428,0.0010245313,0.001928943,0.001400651,0.0012298796,0.0005814989],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026070047,0.00009340233,0.0010273869,0.00032794793,0.00018058246,0.00014179136,0.00024435087,0.7580085,0.0091906525,0.0487638,0.0028122284,0.17894864],"study_design_scores_gemma":[0.000005403909,0.0000149808975,0.00016252625,0.0000062437343,0.000009070996,0.00004684588,0.000008357845,0.99203205,0.0010860141,0.006017385,0.00059362705,0.000017569315],"about_ca_topic_score_codex":0.0061274865,"about_ca_topic_score_gemma":0.004047914,"teacher_disagreement_score":0.0061274865,"about_ca_system_score_codex":0.0013760783,"about_ca_system_score_gemma":0.0015612281,"threshold_uncertainty_score":0.012183607},"labels":[],"label_agreement":null},{"id":"W2261188167","doi":"","title":"Urban Classification Of High Resolution Ikonos Imagery Using Texture","year":2006,"lang":"en","type":"article","venue":"Proceedings of the Joint CIB W78, W102, ICCCBE, ICCC, and DMUCE International Conference on Computing and Decision Making in Civil and Building Engineering, Montreal, Canada, 14-16 June","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Land cover; Remote sensing; Artificial intelligence; Pattern recognition (psychology); Image resolution; Texture (cosmology); Computer science; Geography; Computer vision; Land use; Image (mathematics)","score_opus":0.015421877439330397,"score_gpt":0.2285987706468303,"score_spread":0.21317689320749988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2261188167","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92720336,0.00016053393,0.06642522,0.00013190914,0.00003272296,0.00010140828,0.001925789,0.00083497405,0.0031841593],"genre_scores_gemma":[0.95841646,0.000110981826,0.037628666,0.000024440276,0.000018469278,0.00003100852,0.0029868789,0.00003391078,0.00074911024],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9997726,0.00003365415,0.000014461996,0.00003828397,0.000096601296,0.00004438304],"domain_scores_gemma":[0.9996557,0.00008508396,0.00005767053,0.000051445786,0.0001210406,0.000029049605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031443944,0.00037182987,0.00033457574,0.0026302924,0.00015978543,0.00066185166,0.00021590557,0.00024770806,0.00083421543],"category_scores_gemma":[0.0008840545,0.00012214664,0.00037342147,0.0014252885,0.00024614693,0.00046034297,0.00030946304,0.00019902461,0.0005246461],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017768272,0.00051426183,0.09798178,0.0004352405,0.0001939408,0.00052865536,0.0003407853,0.091701396,0.24310927,0.0013697625,0.005316147,0.5567319],"study_design_scores_gemma":[0.0000843815,0.00022040705,0.24996926,0.000039720453,0.000112014735,0.00037561427,0.00079818256,0.696118,0.047415692,0.0013357651,0.0034666513,0.00006438019],"about_ca_topic_score_codex":0.0075070844,"about_ca_topic_score_gemma":0.009024393,"teacher_disagreement_score":0.0075070844,"about_ca_system_score_codex":0.00035201432,"about_ca_system_score_gemma":0.00019616618,"threshold_uncertainty_score":0.014926791},"labels":[],"label_agreement":null},{"id":"W2268689268","doi":"10.5194/isprsarchives-xl-1-w5-407-2015","title":"UNSUPERVISED CHANGE DETECTION IN SAR IMAGES USING GAUSSIAN MIXTURE MODELS","year":2015,"lang":"en","type":"article","venue":"˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Change detection; Synthetic aperture radar; Artificial intelligence; Computer science; Speckle pattern; Speckle noise; Histogram; Computer vision; Class (philosophy); Pattern recognition (psychology); Remote sensing; Image (mathematics); Geography","score_opus":0.04107828873367574,"score_gpt":0.2612762648911965,"score_spread":0.22019797615752074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2268689268","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03888171,0.00025185655,0.95929974,0.00006225065,0.000036292135,0.000038859584,0.00006265559,0.0008199656,0.0005466511],"genre_scores_gemma":[0.5662361,0.0003725447,0.42903584,0.00009804182,0.00010679163,0.00010271981,0.0007532664,0.00020583074,0.0030888692],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99929583,0.00016711735,0.00003120655,0.00022178378,0.00021936263,0.00006473237],"domain_scores_gemma":[0.99936074,0.00027225813,0.00008618181,0.00008923072,0.00016132207,0.000030377845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087747374,0.0006627318,0.0007724237,0.002110509,0.00029198657,0.00073738466,0.0007258668,0.0006458542,0.00061317056],"category_scores_gemma":[0.0012599665,0.0004390899,0.0012785102,0.0010563008,0.0005477687,0.001071467,0.0005871066,0.0008280689,0.0005515592],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00053863344,0.00039315637,0.014646547,0.00022743166,0.0005455568,0.00026042238,0.0002868077,0.2171879,0.08963138,0.00728417,0.0032927683,0.66570526],"study_design_scores_gemma":[0.000009028918,0.000040553736,0.004394089,0.0000068775166,0.00002874122,0.000085274856,0.000020413627,0.98335916,0.00920691,0.0018388312,0.0009893717,0.000020750802],"about_ca_topic_score_codex":0.0027153804,"about_ca_topic_score_gemma":0.003306031,"teacher_disagreement_score":0.0027153804,"about_ca_system_score_codex":0.00041723266,"about_ca_system_score_gemma":0.00037590327,"threshold_uncertainty_score":0.005399227},"labels":[],"label_agreement":null},{"id":"W2274133811","doi":"","title":"09 - Réduction du nombre de canaux des images multispectrales par approche connexionniste","year":2000,"lang":"fr","type":"article","venue":"Traitement du signal","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Conjugate gradient method; Computer science; Speedup; Artificial neural network; Convergence (economics); Image (mathematics); Rate of convergence; Projection (relational algebra); Artificial intelligence; Algorithm; Pattern recognition (psychology); Data mining; Channel (broadcasting); Telecommunications","score_opus":0.017474685832780595,"score_gpt":0.22075033150057682,"score_spread":0.20327564566779624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2274133811","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06823596,0.00044335745,0.92815703,0.00012845226,0.00010289232,0.00006369456,0.00009786476,0.0007383744,0.0020323866],"genre_scores_gemma":[0.40012896,0.00054750306,0.58588636,0.00007822742,0.00007961891,0.00012469938,0.0005048856,0.00015725446,0.012492543],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993674,0.00008365448,0.000020198546,0.00014905573,0.00032641017,0.000053202584],"domain_scores_gemma":[0.99954045,0.00014532369,0.000037573736,0.0000664987,0.0001956889,0.000014513871],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066657714,0.00068785966,0.0006116454,0.0009577209,0.00033799425,0.0009808602,0.00059681974,0.00056719186,0.0017382007],"category_scores_gemma":[0.0013039124,0.0002582284,0.0005586937,0.0006525466,0.00039585488,0.00068098673,0.00048163938,0.00066514267,0.0007353121],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033574464,0.00010587766,0.0027647763,0.00017709912,0.00010964209,0.00008767294,0.0001065154,0.08470194,0.07778136,0.0025671157,0.0014035116,0.8298587],"study_design_scores_gemma":[0.000034365417,0.00010382763,0.010403548,0.000022625683,0.00007135995,0.0001987927,0.000061935665,0.9154242,0.064804316,0.0018026662,0.007040588,0.00003171681],"about_ca_topic_score_codex":0.0077463174,"about_ca_topic_score_gemma":0.009165689,"teacher_disagreement_score":0.0077463174,"about_ca_system_score_codex":0.0005293223,"about_ca_system_score_gemma":0.0004908361,"threshold_uncertainty_score":0.015402436},"labels":[],"label_agreement":null},{"id":"W2277068403","doi":"10.3390/rs8030187","title":"ℓ0-Norm Sparse Hyperspectral Unmixing Using Arctan Smoothing","year":2016,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Hyperspectral imaging; Smoothing; Norm (philosophy); Mathematical optimization; Computer science; Algorithm; Mathematics; Artificial intelligence; Statistics","score_opus":0.02887641818431834,"score_gpt":0.23755521016802958,"score_spread":0.20867879198371125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2277068403","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005970617,0.00007179435,0.99303436,0.00005888349,0.000011932028,0.00001670064,0.000013974162,0.00031229615,0.00050946634],"genre_scores_gemma":[0.09719277,0.0001868878,0.8998639,0.0000705586,0.000030961386,0.00008519966,0.00016411391,0.00017549655,0.0022301076],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994978,0.00009897343,0.000030605413,0.00014223253,0.00019995756,0.000030396675],"domain_scores_gemma":[0.99933296,0.0002830121,0.00009747311,0.00010918511,0.00015303423,0.000024237766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014234126,0.00090080925,0.00079338124,0.00082142185,0.00037318145,0.00076944183,0.0012452346,0.0009960007,0.0013430741],"category_scores_gemma":[0.00256636,0.00055484235,0.001030569,0.0010702854,0.0008117402,0.0014921679,0.0010925912,0.0014909932,0.00058817497],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018977902,0.00010085405,0.00092242635,0.000199999,0.00011672272,0.00008291772,0.0002678305,0.6043421,0.036000717,0.027459746,0.0023893998,0.32792753],"study_design_scores_gemma":[0.0000054799793,0.000013768038,0.00010014345,0.0000038686007,0.0000062852005,0.000024607485,0.0000066937528,0.9906308,0.004977678,0.0029689884,0.0012520523,0.0000097582815],"about_ca_topic_score_codex":0.002810955,"about_ca_topic_score_gemma":0.003241668,"teacher_disagreement_score":0.002810955,"about_ca_system_score_codex":0.000708891,"about_ca_system_score_gemma":0.001268275,"threshold_uncertainty_score":0.007527828},"labels":[],"label_agreement":null},{"id":"W2280565539","doi":"10.1016/j.isprsjprs.2016.01.018","title":"A targeted change-detection procedure by combining change vector analysis and post-classification approach","year":2016,"lang":"en","type":"article","venue":"ISPRS Journal of Photogrammetry and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":50,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Change detection; Support vector machine; Computer science; Data mining; Workflow; Artificial intelligence; Classifier (UML); Pattern recognition (psychology); One-class classification; Machine learning; Database","score_opus":0.021819796671892627,"score_gpt":0.23105877055387297,"score_spread":0.20923897388198034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2280565539","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01641493,0.000100459445,0.9803233,0.000048423506,0.00007532285,0.00015496452,0.00016519628,0.0018503392,0.00086709054],"genre_scores_gemma":[0.18387108,0.00015786152,0.8108103,0.00007324354,0.00006426858,0.00018468346,0.0010860523,0.00029648785,0.00345604],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987232,0.0001161784,0.00009286634,0.00041857763,0.00046996647,0.00017921637],"domain_scores_gemma":[0.99883765,0.00017022504,0.000095029645,0.00019235697,0.00066225673,0.00004255346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013814317,0.001480193,0.0016358683,0.004272543,0.0007380434,0.0013737044,0.0013331604,0.0011580179,0.0026495466],"category_scores_gemma":[0.0013489261,0.00058576517,0.001663568,0.0030931851,0.00052992353,0.0014376958,0.0011960104,0.00095980545,0.002987288],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020371868,0.00037077893,0.0034386765,0.00017329461,0.00013371848,0.000099054734,0.000102259815,0.008635289,0.1362443,0.0017664573,0.0026478278,0.8461847],"study_design_scores_gemma":[0.00004496474,0.0005188835,0.027456688,0.00003289148,0.00034327357,0.0005940366,0.00015997063,0.7733773,0.17889847,0.0044691265,0.013957048,0.00014735977],"about_ca_topic_score_codex":0.002989656,"about_ca_topic_score_gemma":0.005002614,"teacher_disagreement_score":0.004272543,"about_ca_system_score_codex":0.00032608834,"about_ca_system_score_gemma":0.0011753596,"threshold_uncertainty_score":0.008863628},"labels":[],"label_agreement":null},{"id":"W2283858015","doi":"10.1080/01431161.2015.1129561","title":"Mapping urban land cover based on spatial-spectral classification of hyperspectral remote-sensing data","year":2016,"lang":"en","type":"article","venue":"International Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"Purdue University","keywords":"Hyperspectral imaging; Support vector machine; Land cover; Cohen's kappa; Computer science; Remote sensing; Pattern recognition (psychology); Artificial intelligence; Pixel; Spatial analysis; Data mining; Land use; Geography; Machine learning","score_opus":0.035632988090821945,"score_gpt":0.2653119973228587,"score_spread":0.22967900923203677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2283858015","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1860727,0.00031649682,0.8092563,0.0001500516,0.00002648169,0.000078055076,0.0003867345,0.0008932957,0.0028197907],"genre_scores_gemma":[0.7502011,0.00025638173,0.24745837,0.000048039332,0.000025529802,0.000066342276,0.00085977424,0.0000360144,0.0010484308],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99972373,0.0000371115,0.000013214706,0.00006271163,0.00012435521,0.00003887924],"domain_scores_gemma":[0.9998086,0.000030172443,0.00004121544,0.000026281106,0.00008498716,0.00000879492],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042081022,0.00038322384,0.00027024176,0.00218939,0.00025391395,0.00060344103,0.00037388026,0.00026459002,0.00045422],"category_scores_gemma":[0.00062683935,0.00010393704,0.00039428027,0.0010982157,0.00033993687,0.0007066335,0.00038845235,0.00022932341,0.00021993094],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013010345,0.00023602678,0.031877417,0.00020668161,0.00013844184,0.00016896102,0.00021837174,0.14836921,0.07993268,0.0068872124,0.0021854155,0.7296494],"study_design_scores_gemma":[0.000005264224,0.00004310491,0.035783805,0.000024092009,0.000037866936,0.00015693477,0.00018459736,0.9361599,0.021287937,0.0029785915,0.0033061644,0.000031666477],"about_ca_topic_score_codex":0.009934458,"about_ca_topic_score_gemma":0.020031163,"teacher_disagreement_score":0.009934458,"about_ca_system_score_codex":0.00044708332,"about_ca_system_score_gemma":0.00041345877,"threshold_uncertainty_score":0.019753277},"labels":[],"label_agreement":null},{"id":"W2285984635","doi":"10.5194/isprsarchives-xl-1-w4-415-2015","title":"WORKFLOW FOR BUILDING A HYPERSPECTRAL UAV: CHALLENGES AND OPPORTUNITIES","year":2015,"lang":"en","type":"article","venue":"˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hyperspectral imaging; Photochemical Reflectance Index; Payload (computing); Workflow; Remote sensing; Computer science; Process (computing); Fidelity; Environmental science; Systems engineering; Artificial intelligence; Leaf area index; Engineering; Ecology; Telecommunications; Geography","score_opus":0.056440404317967534,"score_gpt":0.26963348895808253,"score_spread":0.213193084640115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2285984635","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011975524,0.00040449496,0.95398355,0.001502477,0.00018766022,0.0011643884,0.0008767461,0.016713671,0.013191476],"genre_scores_gemma":[0.05804836,0.00035833838,0.9327914,0.00030129682,0.000049011687,0.00042182414,0.0016919954,0.0014537876,0.004883898],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987804,0.00024679885,0.000090400405,0.0002516658,0.00049234316,0.0001384333],"domain_scores_gemma":[0.9969127,0.0005631006,0.00019668421,0.0009155161,0.0010245661,0.00038739966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034248533,0.0012044975,0.0007964214,0.0013542939,0.0013635047,0.003170774,0.001728533,0.001120647,0.014530026],"category_scores_gemma":[0.0040474683,0.000725845,0.0007789402,0.0008969397,0.00058976474,0.0023194598,0.0016208105,0.0017717606,0.012373203],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005187912,0.0004899575,0.006763413,0.00090471713,0.00010255371,0.0016025603,0.0012215527,0.028653843,0.12511699,0.011506402,0.04907834,0.77404094],"study_design_scores_gemma":[0.00019320428,0.0008387346,0.018784383,0.00083481806,0.00010956236,0.0030466155,0.0033439407,0.3724502,0.14552502,0.028883662,0.42558166,0.00040808186],"about_ca_topic_score_codex":0.004861621,"about_ca_topic_score_gemma":0.007401385,"teacher_disagreement_score":0.014530026,"about_ca_system_score_codex":0.0009844557,"about_ca_system_score_gemma":0.0020652069,"threshold_uncertainty_score":0.048607826},"labels":[],"label_agreement":null},{"id":"W2288698354","doi":"","title":"5 - Gradient couleur multiéchelle pour la segmentation d'images","year":2001,"lang":"fr","type":"article","venue":"Traitement du signal","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Multispectral image; Image gradient; Artificial intelligence; Morphological gradient; Computer vision; Computation; Computer science; Segmentation; Color image; Image segmentation; Image processing; Image (mathematics); Scale-space segmentation; Algorithm","score_opus":0.02197268742349523,"score_gpt":0.24560020042776637,"score_spread":0.22362751300427114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2288698354","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037839855,0.0002543038,0.99457633,0.00008452538,0.000041796757,0.000021386411,0.000039536535,0.0004164977,0.0007817417],"genre_scores_gemma":[0.2025973,0.00075901946,0.78011805,0.00017059276,0.00014039029,0.0002181727,0.00026394307,0.00057958375,0.015152958],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99939096,0.00017153032,0.000022996139,0.00011120402,0.00024727377,0.000055950077],"domain_scores_gemma":[0.99960667,0.0001829009,0.000035553596,0.0000454799,0.000101972444,0.000027461012],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00081735814,0.0009771399,0.00071699044,0.0011464899,0.0003607857,0.0014117634,0.0007954543,0.001216125,0.002846386],"category_scores_gemma":[0.0014465097,0.00035242384,0.000870219,0.00065157464,0.00083038723,0.0013583396,0.00063010055,0.0015399173,0.0014647738],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040399795,0.00010812624,0.0014534498,0.00031900348,0.00009761464,0.0004946876,0.00025380714,0.2890241,0.1165535,0.2641158,0.0056634494,0.3215124],"study_design_scores_gemma":[0.000012218088,0.0000412048,0.0003731847,0.0000106675025,0.000005342653,0.00014799369,0.0000126879595,0.9621525,0.015598876,0.011566502,0.01006194,0.000017002021],"about_ca_topic_score_codex":0.0074160527,"about_ca_topic_score_gemma":0.005279273,"teacher_disagreement_score":0.0074160527,"about_ca_system_score_codex":0.0013647842,"about_ca_system_score_gemma":0.00056035205,"threshold_uncertainty_score":0.014745772},"labels":[],"label_agreement":null},{"id":"W2290467607","doi":"10.1201/9781420084368","title":"Adaptive Image Processing","year":2009,"lang":"en","type":"book","venue":"Image processing series","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Image processing; Artificial intelligence; Visual processing; Digital image processing; Computational intelligence; Information processing; Perception; Machine learning; Pattern recognition (psychology); Image (mathematics)","score_opus":0.014260085611604013,"score_gpt":0.2345865646589746,"score_spread":0.22032647904737057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2290467607","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014051668,0.021809416,0.7380503,0.0015325216,0.0030458686,0.00016810563,0.0004331713,0.0032140054,0.23034148],"genre_scores_gemma":[0.045631297,0.034997154,0.51037705,0.0024606024,0.0021990496,0.00031500813,0.0014005443,0.0009011533,0.40171817],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99953806,0.000042178362,0.00001993505,0.000096592354,0.00027842604,0.000024868057],"domain_scores_gemma":[0.9997044,0.00008161387,0.0000149783045,0.000063684114,0.00012147495,0.000013790057],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035229116,0.0008919512,0.0006406323,0.0011834675,0.00044395676,0.0024880583,0.0011432682,0.0013463495,0.0342232],"category_scores_gemma":[0.0011180738,0.00036335585,0.0005480264,0.0014543515,0.0008220632,0.0017448458,0.0012571124,0.0015248415,0.020165868],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037440168,0.000023935987,0.00011883083,0.0006152707,0.000046852547,0.00019905755,0.00012958296,0.0075894874,0.014874219,0.13186999,0.13726747,0.7072279],"study_design_scores_gemma":[0.000009344362,0.00004452193,0.00042117698,0.00017139879,0.000019084471,0.00096142205,0.00006946727,0.03899913,0.008086406,0.062204182,0.8889781,0.000035722554],"about_ca_topic_score_codex":0.0006180792,"about_ca_topic_score_gemma":0.0008076563,"teacher_disagreement_score":0.0342232,"about_ca_system_score_codex":0.00046889335,"about_ca_system_score_gemma":0.00041996627,"threshold_uncertainty_score":0.114488006},"labels":[],"label_agreement":null},{"id":"W2311229452","doi":"","title":"OBJECT-BASED LAND COVER CLASSIFICATION OF URBAN AREAS USING VHR IMAGERY AND PHOTOGRAMMETRICALLY-DERIVED DSM","year":2011,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Land cover; Multispectral image; Remote sensing; Computer science; Lidar; Orthophoto; Geography; Artificial intelligence; Cartography; Land use","score_opus":0.04580082334187916,"score_gpt":0.22960671818361217,"score_spread":0.18380589484173301,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2311229452","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41007522,0.00053457817,0.57831603,0.00009426807,0.00006596254,0.0003306895,0.001026744,0.0024862993,0.007070174],"genre_scores_gemma":[0.70980465,0.00026515932,0.2856792,0.00004495707,0.000024981151,0.000077061784,0.0018093319,0.00005972788,0.0022348296],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997303,0.000027393988,0.000017100137,0.000054115164,0.00013548114,0.000035614907],"domain_scores_gemma":[0.9997949,0.00002291937,0.000026741542,0.000037354825,0.00010218354,0.000016017584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036359337,0.00047684668,0.00041169563,0.0035002972,0.0002497899,0.00086606806,0.0004543406,0.0003404386,0.00077844685],"category_scores_gemma":[0.00036334162,0.00019508284,0.00051549484,0.0011647359,0.0003038832,0.00063346676,0.0005086828,0.00019120655,0.00054491736],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018781456,0.00034217353,0.02944851,0.00026449043,0.00017803865,0.00024325878,0.0003022339,0.057897955,0.12591788,0.0021373269,0.0018904055,0.7811899],"study_design_scores_gemma":[0.00003232994,0.00016192032,0.0971982,0.000038597605,0.00013440858,0.00031493843,0.0005146132,0.84436256,0.050932292,0.0014499857,0.004786358,0.00007371518],"about_ca_topic_score_codex":0.008108286,"about_ca_topic_score_gemma":0.010982068,"teacher_disagreement_score":0.008108286,"about_ca_system_score_codex":0.00043024754,"about_ca_system_score_gemma":0.0003420196,"threshold_uncertainty_score":0.016122162},"labels":[],"label_agreement":null},{"id":"W2313622892","doi":"10.1016/j.jag.2016.03.012","title":"A method to compute the n-dimensional solid spectral angle between vectors and its use for band selection in hyperspectral data","year":2016,"lang":"en","type":"article","venue":"International Journal of Applied Earth Observation and Geoinformation","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Hyperspectral imaging; Selection (genetic algorithm); Remote sensing; Geography; Computer science; Mathematics; Artificial intelligence","score_opus":0.05834053049991584,"score_gpt":0.29383808414667717,"score_spread":0.23549755364676134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2313622892","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026485047,0.000066597306,0.9965306,0.000019816587,0.000036241974,0.000019839334,0.000050690367,0.00034752884,0.00028010932],"genre_scores_gemma":[0.023976257,0.000115583956,0.9742322,0.000018647492,0.000032152326,0.00007599543,0.00022319754,0.00012383425,0.0012021145],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996131,0.00006682662,0.000029260313,0.00008860625,0.00017616851,0.000026080143],"domain_scores_gemma":[0.99929917,0.00022537382,0.000067225665,0.00010155915,0.00026454972,0.00004209491],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005300018,0.00068277935,0.00048782738,0.0012295312,0.0005469585,0.0008380892,0.0008616089,0.000552752,0.0036503526],"category_scores_gemma":[0.0014311478,0.00037166383,0.0006563935,0.0013605335,0.000491351,0.00092508463,0.00083342445,0.0010685297,0.002020849],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021412526,0.00020115475,0.0016244926,0.00020855079,0.0000724133,0.000085513515,0.00013855322,0.03490917,0.08663386,0.023614762,0.0051881163,0.8471094],"study_design_scores_gemma":[0.00004937867,0.00010999692,0.0022046631,0.000036889884,0.00003913419,0.00040384283,0.000087201304,0.9192447,0.048381668,0.011650745,0.017707398,0.00008445845],"about_ca_topic_score_codex":0.0017507201,"about_ca_topic_score_gemma":0.0033058284,"teacher_disagreement_score":0.0036503526,"about_ca_system_score_codex":0.0002216836,"about_ca_system_score_gemma":0.0010296828,"threshold_uncertainty_score":0.01221168},"labels":[],"label_agreement":null},{"id":"W2315349446","doi":"10.5623/cig2014-001","title":"Supervised Change Detection in Satellite Imagery Using Super Pixels and Relevance Feedback","year":2014,"lang":"en","type":"article","venue":"GEOMATICA","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Change detection; Computer science; Relevance feedback; Pixel; Relevance (law); Artificial intelligence; Support vector machine; Data mining; Pattern recognition (psychology); Classifier (UML); Remote sensing; Machine learning; Computer vision; Image (mathematics); Image retrieval; Geography","score_opus":0.027097637296207976,"score_gpt":0.22127680516662818,"score_spread":0.1941791678704202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2315349446","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23358504,0.0010005435,0.7593478,0.00023093613,0.00016953559,0.0002314397,0.0003902741,0.0030643942,0.0019800873],"genre_scores_gemma":[0.75531197,0.00024829005,0.24120381,0.00009909383,0.00016268886,0.00010837342,0.0009034241,0.00011329537,0.0018491056],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994387,0.0001035909,0.000031094198,0.00018732308,0.00017361254,0.00006565126],"domain_scores_gemma":[0.9989827,0.00041442268,0.00013240302,0.00015414925,0.00026914995,0.000047158224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008923264,0.00077098573,0.0011045171,0.0016469643,0.00038148463,0.0005954541,0.00081149006,0.0007159157,0.001197883],"category_scores_gemma":[0.0019428171,0.00037791542,0.0007019345,0.0011105197,0.00044506713,0.00091821013,0.00061347627,0.00066236086,0.00052593485],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00064826844,0.00043820305,0.005014653,0.000281985,0.00016354256,0.00015622955,0.00014242332,0.061862856,0.09161313,0.0009834963,0.0046496373,0.8340457],"study_design_scores_gemma":[0.00004215764,0.00017662274,0.0061967545,0.000012162527,0.00007224249,0.000103075115,0.0000490054,0.964805,0.02543162,0.0019864035,0.0011082761,0.00001674962],"about_ca_topic_score_codex":0.0024913007,"about_ca_topic_score_gemma":0.0053782794,"teacher_disagreement_score":0.0024913007,"about_ca_system_score_codex":0.0002829838,"about_ca_system_score_gemma":0.0006207775,"threshold_uncertainty_score":0.004953563},"labels":[],"label_agreement":null},{"id":"W2323362148","doi":"10.1109/jstars.2015.2450499","title":"Extraction of Endmembers From Hyperspectral Images Using A Weighted Fuzzy Purified-Means Clustering Model","year":2015,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Canadian Space Agency; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Hyperspectral imaging; Artificial intelligence; Pattern recognition (psychology); Computer science; Cluster analysis; Fuzzy logic; Fuzzy clustering; Feature extraction; Extraction (chemistry); Computer vision; Chromatography; Chemistry","score_opus":0.048444000240595426,"score_gpt":0.2536566682840733,"score_spread":0.20521266804347787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2323362148","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009911947,0.000107230844,0.98929197,0.00005001066,0.000009225993,0.00002388098,0.00003344138,0.00011315999,0.00045913682],"genre_scores_gemma":[0.3340848,0.00052062824,0.65978706,0.00013526747,0.00005119535,0.00019759874,0.00041475295,0.0001019655,0.00470676],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99961567,0.0000633469,0.000019247513,0.00011469624,0.00015569097,0.00003124445],"domain_scores_gemma":[0.9997271,0.00008298276,0.000039778486,0.000028513035,0.00010953412,0.000012089792],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006409981,0.0007542418,0.00065173797,0.0008329164,0.00041121492,0.0007365071,0.0014214484,0.0010028429,0.00069684966],"category_scores_gemma":[0.0009974218,0.00042629565,0.0012565659,0.0006677375,0.0005356853,0.001025971,0.00060804177,0.00090950995,0.00036465004],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000097887416,0.00004657541,0.0007521608,0.00011751835,0.0000956402,0.00007999387,0.000148554,0.8662766,0.019438662,0.009049633,0.00090795424,0.102988735],"study_design_scores_gemma":[0.000001721485,0.0000058551564,0.00013208175,0.0000033804122,0.000006067532,0.000014722248,0.000006265798,0.99683255,0.0014873772,0.0012429494,0.0002589475,0.000008007744],"about_ca_topic_score_codex":0.010155239,"about_ca_topic_score_gemma":0.01122763,"teacher_disagreement_score":0.010155239,"about_ca_system_score_codex":0.00072182866,"about_ca_system_score_gemma":0.00088488666,"threshold_uncertainty_score":0.020192266},"labels":[],"label_agreement":null},{"id":"W2328173450","doi":"10.1080/02533839.2008.9671417","title":"Distance weighted multiple classifiers systems applied to remote sensing images classification/data fusion","year":2008,"lang":"en","type":"article","venue":"Journal of the Chinese Institute of Engineers","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Science Council; Jet Propulsion Laboratory; Temple University; Ryerson University","keywords":"Boosting (machine learning); Weighting; Pattern recognition (psychology); Artificial intelligence; Random subspace method; Classifier (UML); Computer science; Fusion; Fuse (electrical); Data mining; Sensor fusion; Machine learning; Engineering","score_opus":0.026188246287054844,"score_gpt":0.23737099492448463,"score_spread":0.21118274863742978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2328173450","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041079998,0.0012894969,0.95529014,0.00019508871,0.0002070882,0.00011063848,0.000021816428,0.0004437089,0.0013620399],"genre_scores_gemma":[0.7014683,0.00056857057,0.29525045,0.00011951667,0.00019877689,0.00013868778,0.00006726097,0.00003851272,0.0021499405],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963362,0.0011347646,0.00040390188,0.00060276664,0.0013651958,0.00015707756],"domain_scores_gemma":[0.9968381,0.0010123306,0.00029698698,0.00032081158,0.0014549519,0.00007675907],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040933224,0.00073266955,0.001509233,0.0017718013,0.0006677051,0.0015462671,0.0011574081,0.0012276418,0.0013419336],"category_scores_gemma":[0.007165573,0.00042908595,0.00070843275,0.0014042318,0.00056995975,0.0015998975,0.0010525956,0.0010281178,0.0006626576],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003812739,0.00018067629,0.0022575334,0.0002433845,0.0003648112,0.000189726,0.0001823356,0.29563496,0.025112148,0.01043519,0.0013603708,0.66365767],"study_design_scores_gemma":[0.000012573085,0.00013021872,0.00060683413,0.000015741003,0.000056797,0.00007230124,0.000020892674,0.9850005,0.008592473,0.004104996,0.001366857,0.000019818115],"about_ca_topic_score_codex":0.0018501601,"about_ca_topic_score_gemma":0.0011142832,"teacher_disagreement_score":0.0040933224,"about_ca_system_score_codex":0.0008757831,"about_ca_system_score_gemma":0.00069166376,"threshold_uncertainty_score":0.021647811},"labels":[],"label_agreement":null},{"id":"W2330207817","doi":"10.5589/m11-008","title":"Comparison of feature extraction methods in dimensionality reduction","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Dimensionality reduction; Pattern recognition (psychology); Feature extraction; Artificial intelligence; Principal component analysis; Linear classifier; Feature vector; Hyperspectral imaging; Mathematics; Feature (linguistics); Classifier (UML); Computer science","score_opus":0.03539607253025156,"score_gpt":0.3500395317496879,"score_spread":0.3146434592194363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2330207817","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1008511,0.004557346,0.8879584,0.00040386917,0.00019831637,0.00037919852,0.00042158226,0.0016838977,0.0035462505],"genre_scores_gemma":[0.23731494,0.002643722,0.7559249,0.000083064224,0.00008474582,0.00052707194,0.0011440807,0.00024636782,0.0020310292],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99604404,0.001239131,0.00038945366,0.00042057649,0.0017395144,0.00016725723],"domain_scores_gemma":[0.99221027,0.004683741,0.0003086285,0.0006651458,0.0020700735,0.000062206556],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0062239137,0.0010769864,0.0010361272,0.0032122692,0.00044936212,0.0011655061,0.0007860257,0.00058364245,0.0014530261],"category_scores_gemma":[0.01440631,0.0003304185,0.0011952133,0.0027370476,0.00041356895,0.0018838625,0.00076725543,0.0006632474,0.0008143705],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005478744,0.0002097786,0.0047313063,0.0005555607,0.00039911433,0.00006718035,0.00024767136,0.017627258,0.021914812,0.0025945539,0.0021888022,0.94891596],"study_design_scores_gemma":[0.0003362027,0.0017951719,0.075835586,0.00043023538,0.00077470444,0.0016625355,0.00079614966,0.68431723,0.18218924,0.012875307,0.038500506,0.00048720592],"about_ca_topic_score_codex":0.0012164738,"about_ca_topic_score_gemma":0.0013333496,"teacher_disagreement_score":0.0062239137,"about_ca_system_score_codex":0.00043570925,"about_ca_system_score_gemma":0.00043283877,"threshold_uncertainty_score":0.032915592},"labels":[],"label_agreement":null},{"id":"W2335884370","doi":"10.1117/12.2223360","title":"Multispectral image analysis for object recognition and classification","year":2016,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec en Outaouais; University of Ottawa","funders":"","keywords":"Multispectral image; Computer science; Support vector machine; Artificial intelligence; Process (computing); Visualization; Computer vision; Cognitive neuroscience of visual object recognition; Pattern recognition (psychology); Electromagnetic spectrum; Contextual image classification; Class (philosophy); Object (grammar); Image (mathematics)","score_opus":0.02190601025455786,"score_gpt":0.23701102683340852,"score_spread":0.21510501657885067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2335884370","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007122362,0.011501539,0.94489026,0.0012045039,0.0008502446,0.00039474657,0.0035480736,0.005948065,0.02454024],"genre_scores_gemma":[0.14026724,0.014114852,0.80211073,0.0009945534,0.0007842694,0.0007962029,0.009976199,0.0008192301,0.03013669],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988105,0.00019639131,0.000091950504,0.00021027136,0.0006256398,0.00006533064],"domain_scores_gemma":[0.9987104,0.00026235334,0.00016500782,0.0003704506,0.00045378605,0.00003799529],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000919877,0.0010496216,0.00086670864,0.0033445437,0.00059333816,0.0018950873,0.0011695687,0.0011657992,0.01659468],"category_scores_gemma":[0.0022614293,0.0003127148,0.0010128451,0.003936065,0.00058579416,0.0015825288,0.0011129656,0.00127682,0.01371468],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010371254,0.00016130475,0.0015359189,0.0009698936,0.00014875006,0.00019315448,0.00011168417,0.008084752,0.043850485,0.017478105,0.059267096,0.8680952],"study_design_scores_gemma":[0.000047492354,0.000234674,0.016566638,0.00082133966,0.00016984502,0.001752624,0.00036965904,0.27386582,0.08040636,0.069723286,0.55583006,0.00021234679],"about_ca_topic_score_codex":0.0017601539,"about_ca_topic_score_gemma":0.0019682504,"teacher_disagreement_score":0.01659468,"about_ca_system_score_codex":0.0005992156,"about_ca_system_score_gemma":0.0008462229,"threshold_uncertainty_score":0.055514753},"labels":[],"label_agreement":null},{"id":"W2336392284","doi":"","title":"Improved Spectral-Spatial Classification Minimum Spanning Forest by Reducing the Spatial Dimensions of Hyperspectral Images","year":2015,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Hyperspectral imaging; Geomatics; Geography; Spatial analysis; Remote sensing; Cartography; Environmental science","score_opus":0.024425352979017604,"score_gpt":0.24133002257097028,"score_spread":0.21690466959195268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2336392284","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11869008,0.00038136553,0.87824667,0.00017064932,0.0000530375,0.0000312448,0.00016510098,0.0007241935,0.0015376356],"genre_scores_gemma":[0.5093838,0.00024481822,0.48694983,0.00009648123,0.00006160511,0.00006119154,0.0010914427,0.00013096679,0.001979852],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99963284,0.00008061312,0.00002314332,0.00006220792,0.00015874824,0.00004248969],"domain_scores_gemma":[0.99957377,0.000109752364,0.00004096565,0.00008270484,0.00017124832,0.000021511916],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047664242,0.0004883752,0.0006791131,0.00068782165,0.0004250592,0.00043227038,0.0006021122,0.0005098111,0.0009525251],"category_scores_gemma":[0.0012382434,0.00021602027,0.00062368903,0.00089328777,0.00019636529,0.0009896938,0.0006047033,0.0005731461,0.0003742991],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003038013,0.00030873498,0.0030906745,0.00015936558,0.0001463142,0.00013307254,0.00013107092,0.20245002,0.08288294,0.0073746173,0.0057700393,0.69724935],"study_design_scores_gemma":[0.0000085724205,0.000020484506,0.00119238,0.0000044735248,0.00002070657,0.00006701127,0.00001547963,0.99067056,0.004927084,0.0022813543,0.00078460196,0.0000073089227],"about_ca_topic_score_codex":0.0032764052,"about_ca_topic_score_gemma":0.00712245,"teacher_disagreement_score":0.0032764052,"about_ca_system_score_codex":0.00020113435,"about_ca_system_score_gemma":0.00075487094,"threshold_uncertainty_score":0.0065146685},"labels":[],"label_agreement":null},{"id":"W2363813582","doi":"10.1117/12.2224379","title":"Emissivity retrieval from indoor hyperspectral imaging of mineral grains","year":2016,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Université Laval","keywords":"Hyperspectral imaging; Radiance; Emissivity; Imaging spectroscopy; Remote sensing; Non-negative matrix factorization; Computer science; Full spectral imaging; Matrix decomposition; Near-infrared spectroscopy; Spectroscopy; Pixel; Infrared; Materials science; Optics; Artificial intelligence; Physics; Geology","score_opus":0.011555524905435557,"score_gpt":0.22080095146163672,"score_spread":0.20924542655620115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2363813582","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21332765,0.00021380388,0.7828088,0.000055655746,0.000023111594,0.00003316786,0.00020098178,0.0008047425,0.0025320575],"genre_scores_gemma":[0.6842429,0.00025287003,0.3127043,0.000034467463,0.000027815135,0.000046225472,0.00058823376,0.00011384665,0.0019893334],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99988294,0.000016793638,0.0000038891717,0.000038522452,0.00004149249,0.000016320178],"domain_scores_gemma":[0.9999107,0.000019257419,0.000018384599,0.000021394386,0.00002581655,0.000004432692],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015864712,0.0005197726,0.0002668483,0.000559685,0.00014387535,0.00034345943,0.00034301847,0.0003103213,0.0006683583],"category_scores_gemma":[0.00039932027,0.00014580098,0.00037843673,0.0004999626,0.0002236154,0.00063669553,0.00031454262,0.00030442284,0.0004189171],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017644654,0.00010830944,0.002688365,0.00020888443,0.00005020168,0.0001017704,0.000109521585,0.05779043,0.6699393,0.0012046836,0.00068807957,0.26693407],"study_design_scores_gemma":[0.00001965932,0.00011188853,0.01562275,0.000017814607,0.00005401193,0.0003032759,0.0001696663,0.64654803,0.33216903,0.0019069283,0.0030342217,0.00004266319],"about_ca_topic_score_codex":0.00090808904,"about_ca_topic_score_gemma":0.0023689733,"teacher_disagreement_score":0.00090808904,"about_ca_system_score_codex":0.00017116174,"about_ca_system_score_gemma":0.00025138518,"threshold_uncertainty_score":0.0022358298},"labels":[],"label_agreement":null},{"id":"W2373523947","doi":"","title":"Land Cover Classification of Hyperspectral Data Using Composite Kernel Support Vector Machines","year":2011,"lang":"en","type":"article","venue":"Beijing Daxue xuebao. Ziran kexue ban","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Support vector machine; Hyperspectral imaging; Kernel (algebra); Pattern recognition (psychology); Land cover; Artificial intelligence; Kernel method; Radial basis function kernel; Computer science; Mathematics; Remote sensing; Data mining; Land use; Geography; Engineering","score_opus":0.09809643875919695,"score_gpt":0.2744029725501956,"score_spread":0.17630653379099864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2373523947","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27158406,0.00039847786,0.72520906,0.00014133674,0.000072510105,0.00004833652,0.00018423348,0.0008742902,0.0014876447],"genre_scores_gemma":[0.8196275,0.00024715645,0.17775261,0.00003260408,0.000050881827,0.00004485349,0.0004853916,0.00004123075,0.0017177596],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99976486,0.000043537293,0.000014141703,0.00004953302,0.00010674967,0.000021114163],"domain_scores_gemma":[0.99964106,0.00008837572,0.000053327552,0.000043451975,0.00015568528,0.000018094519],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036595316,0.00034022125,0.0004274505,0.0010286161,0.00017520548,0.0005002872,0.00026542155,0.00027321716,0.0004474368],"category_scores_gemma":[0.00073073764,0.00012746215,0.0004564127,0.00074682035,0.00019264879,0.0007490841,0.00025924746,0.0003720396,0.00022184452],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039928613,0.0002654477,0.014159011,0.00014899118,0.0001557329,0.0001785105,0.000106545835,0.10338618,0.12519872,0.0025006582,0.002222536,0.75127834],"study_design_scores_gemma":[0.000009422519,0.00007800632,0.009825886,0.0000048296,0.00002413467,0.00007541758,0.00002876611,0.96719414,0.020778209,0.00079900643,0.0011645987,0.00001753333],"about_ca_topic_score_codex":0.0012481356,"about_ca_topic_score_gemma":0.0015133454,"teacher_disagreement_score":0.0012481356,"about_ca_system_score_codex":0.00023055026,"about_ca_system_score_gemma":0.00020080915,"threshold_uncertainty_score":0.002481699},"labels":[],"label_agreement":null},{"id":"W2376569224","doi":"10.1088/1755-1315/34/1/012018","title":"Building change detection using multi-sensor and multi-view- angle imagery","year":2016,"lang":"en","type":"article","venue":"IOP Conference Series Earth and Environmental Science","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Artificial intelligence; Computer vision; Pixel; Change detection; Computer science; Process (computing); Brightness; Matching (statistics); Image registration; Pattern recognition (psychology); Remote sensing; Image (mathematics); Mathematics; Geography; Optics","score_opus":0.04338844440056144,"score_gpt":0.23300632210985167,"score_spread":0.18961787770929023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2376569224","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27875757,0.0012948419,0.70909315,0.00018643099,0.00015521463,0.00021123524,0.00059821655,0.0022868586,0.0074164905],"genre_scores_gemma":[0.68470234,0.0006940542,0.3114683,0.00006586299,0.00009312952,0.00007232676,0.0011236925,0.00014929578,0.0016309709],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921596,0.000093947514,0.00003229076,0.00023783473,0.00032810017,0.00009192311],"domain_scores_gemma":[0.9995766,0.00007135099,0.00010051744,0.00009502434,0.000117689066,0.00003867314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050941284,0.00068956986,0.0006599787,0.004281795,0.00026218258,0.0008885408,0.0006825849,0.00070181047,0.0011116564],"category_scores_gemma":[0.00089444645,0.0003792117,0.0009979255,0.003070752,0.00035947334,0.0014545178,0.0009113312,0.0006528647,0.00076193915],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004004604,0.0003659498,0.020970484,0.0005383981,0.00036223503,0.00049183215,0.00042081313,0.032878097,0.20206386,0.0021372172,0.0020074514,0.7373633],"study_design_scores_gemma":[0.000048385118,0.00049442844,0.13164349,0.00007850235,0.00036772687,0.0018858111,0.00080555014,0.6910238,0.15796341,0.0030865571,0.012442112,0.00016011929],"about_ca_topic_score_codex":0.0014189524,"about_ca_topic_score_gemma":0.002573726,"teacher_disagreement_score":0.004281795,"about_ca_system_score_codex":0.0002336265,"about_ca_system_score_gemma":0.00028532528,"threshold_uncertainty_score":0.003718853},"labels":[],"label_agreement":null},{"id":"W2380707673","doi":"10.6046/gtzyyg.2009.03.07","title":"REMOTE SENSING CHANGE DETECTION BY INCLUSION OF MULTITEMPORAL TEXTURE","year":2009,"lang":"en","type":"article","venue":"Guotu ziyuan yaogan","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Change detection; Variogram; Remote sensing; Texture (cosmology); Computer science; Pattern recognition (psychology); Artificial intelligence; Geology; Kriging; Image (mathematics)","score_opus":0.017195434355585237,"score_gpt":0.23156370300993098,"score_spread":0.21436826865434574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2380707673","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47494164,0.00049781805,0.51958853,0.00023072456,0.00008082608,0.00005402545,0.00019881384,0.00063335,0.0037741843],"genre_scores_gemma":[0.9111676,0.00023183749,0.08767408,0.00003726529,0.000046605834,0.0000228084,0.00015070065,0.000041610634,0.00062749436],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996209,0.00008504035,0.000013956581,0.00006036806,0.00017565419,0.000044108507],"domain_scores_gemma":[0.99952567,0.0001244924,0.00010390615,0.00006729588,0.00014898481,0.000029739136],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044785236,0.00035604124,0.0003944882,0.002155569,0.00015661173,0.0007408938,0.0002112324,0.00029265406,0.0005429803],"category_scores_gemma":[0.0011484891,0.00021207008,0.00040483542,0.0015568257,0.0003682451,0.0009859124,0.00044250776,0.0003272091,0.00015532071],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005960896,0.00017639123,0.034895845,0.00027996383,0.00016912156,0.00030630064,0.00018460202,0.046086032,0.3375571,0.004174324,0.00095283927,0.57462144],"study_design_scores_gemma":[0.000029493463,0.0002294439,0.07311147,0.00002662874,0.00019188534,0.00059498183,0.00016945874,0.8425314,0.07693538,0.0027818305,0.0033162534,0.0000818141],"about_ca_topic_score_codex":0.0012419258,"about_ca_topic_score_gemma":0.0021271675,"teacher_disagreement_score":0.002155569,"about_ca_system_score_codex":0.00022820274,"about_ca_system_score_gemma":0.0002175158,"threshold_uncertainty_score":0.0024693608},"labels":[],"label_agreement":null},{"id":"W2390672234","doi":"10.1117/12.2223362","title":"An improved watershed segmentation algorithm with thermal markers for multispectral image analysis","year":2016,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec en Outaouais; University of Ottawa","funders":"","keywords":"Multispectral image; Watershed; Image segmentation; Computer science; Artificial intelligence; Pixel; Computer vision; Segmentation; Image (mathematics); Object (grammar); Region of interest; Scale-space segmentation; Segmentation-based object categorization; Pattern recognition (psychology)","score_opus":0.0072430582202931025,"score_gpt":0.22033471457918072,"score_spread":0.2130916563588876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2390672234","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0046532145,0.00012777255,0.9938998,0.00006208701,0.000025072122,0.00003579417,0.000026861035,0.0006648985,0.00050445826],"genre_scores_gemma":[0.0436796,0.00018438608,0.95390975,0.000051896903,0.000032949258,0.00007417261,0.00016392587,0.00023732225,0.001665988],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992454,0.00010517157,0.000048601978,0.00020169355,0.00033355568,0.000065589746],"domain_scores_gemma":[0.9995011,0.00012217001,0.000052477964,0.000073780786,0.00021701018,0.00003347746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00093600684,0.00068414985,0.0010373025,0.001663819,0.00056614436,0.0013048551,0.0015099404,0.0014641624,0.0021267405],"category_scores_gemma":[0.0015804822,0.00063772313,0.0011823209,0.002251876,0.0007253745,0.002029962,0.00094702607,0.0012560233,0.0011715913],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001945717,0.00015077248,0.0012680187,0.00023798046,0.00013594814,0.000393057,0.0003133428,0.13558626,0.26814678,0.022363564,0.004964555,0.5662452],"study_design_scores_gemma":[0.000026063522,0.00005345063,0.0009868983,0.000014323643,0.000029779672,0.0002641421,0.00003232874,0.92117274,0.059579466,0.00510246,0.012694876,0.000043527012],"about_ca_topic_score_codex":0.0035443825,"about_ca_topic_score_gemma":0.0055646873,"teacher_disagreement_score":0.0035443825,"about_ca_system_score_codex":0.00088407967,"about_ca_system_score_gemma":0.0011418337,"threshold_uncertainty_score":0.0071147084},"labels":[],"label_agreement":null},{"id":"W2395968533","doi":"10.1080/10106049.2015.1120351","title":"An evaluation of Radarsat-2 individual and combined image dates for land use/cover mapping","year":2015,"lang":"en","type":"article","venue":"Geocarto International","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Space Agency; National Aeronautics and Space Administration; U.S. Department of Agriculture; European Space Agency; U.S. Geological Survey; George Mason University","keywords":"Thematic map; Land cover; Geography; Remote sensing; Cartography; Thematic Mapper; Land use; Contextual image classification; Cover (algebra); Physical geography; Satellite imagery; Image (mathematics); Artificial intelligence; Computer science; Engineering","score_opus":0.09271145703678141,"score_gpt":0.30114470249413594,"score_spread":0.20843324545735453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2395968533","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.985047,0.0007475493,0.009964026,0.000063352054,0.00004654754,0.00007709764,0.00093459396,0.00017902197,0.0029408163],"genre_scores_gemma":[0.9645361,0.00031029037,0.032972407,0.000023086379,0.000030823652,0.000045350247,0.0011302002,0.000054056047,0.0008976473],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986149,0.0005778241,0.00008954257,0.00020975195,0.00043395616,0.00007403607],"domain_scores_gemma":[0.9955682,0.001847537,0.00036044553,0.0003770717,0.0017124331,0.00013430219],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040936377,0.0004249646,0.00033820554,0.0013672203,0.00030921915,0.0010460498,0.00035536356,0.00030304215,0.00061570626],"category_scores_gemma":[0.0059720986,0.00016793994,0.00036117408,0.001083898,0.00013449117,0.0009054616,0.00041077082,0.0002413628,0.00028885226],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004791902,0.0004438125,0.42159793,0.00045770325,0.00084795925,0.0002625225,0.00059951236,0.043840993,0.06282859,0.00063086115,0.0017608117,0.46193743],"study_design_scores_gemma":[0.00013272121,0.0019792723,0.73126036,0.0000894858,0.0007803032,0.00057768635,0.000906045,0.21620081,0.042054024,0.00037520105,0.005527011,0.00011696163],"about_ca_topic_score_codex":0.0033958796,"about_ca_topic_score_gemma":0.010354891,"teacher_disagreement_score":0.0040936377,"about_ca_system_score_codex":0.00036629871,"about_ca_system_score_gemma":0.0002764532,"threshold_uncertainty_score":0.02164948},"labels":[],"label_agreement":null},{"id":"W2406525820","doi":"10.4018/978-1-4666-5202-6.ch003","title":"A New Tree-Based Classifier for Satellite Images","year":2014,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Acadia University","funders":"","keywords":"Classifier (UML); Computer science; Artificial intelligence; Pixel; Pattern recognition (psychology); Multiclass classification; Contextual image classification; Binary classification; Parametric statistics; Remote sensing; Data mining; Geography; Mathematics; Image (mathematics); Support vector machine; Statistics","score_opus":0.02147902782925315,"score_gpt":0.2330910319315854,"score_spread":0.21161200410233225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2406525820","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00872416,0.0019741673,0.9713793,0.00031398275,0.0008332542,0.00028105106,0.0023109957,0.008418319,0.005764734],"genre_scores_gemma":[0.048521146,0.0017343858,0.9158057,0.00033683018,0.0004903705,0.0004452152,0.008360877,0.00074118836,0.023564337],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894696,0.0000994445,0.0000710485,0.0002275882,0.000568219,0.00008670661],"domain_scores_gemma":[0.9989095,0.0003697248,0.000054108546,0.0001247814,0.00048799205,0.000054021773],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010582206,0.0010431246,0.0013762737,0.002724349,0.000831634,0.001916035,0.0021175668,0.0017402023,0.011950283],"category_scores_gemma":[0.0029793156,0.0005164869,0.0012459797,0.0033866353,0.000281213,0.002881714,0.00095862884,0.001993513,0.011687296],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000957309,0.0000911125,0.000709387,0.00015877064,0.00008275067,0.000074464486,0.000042613905,0.010062678,0.009983217,0.002404814,0.04368519,0.9326092],"study_design_scores_gemma":[0.000027661965,0.00009901786,0.0018622765,0.000096277494,0.0001021732,0.00036086867,0.00006240287,0.93668175,0.011047654,0.009279522,0.0403235,0.000056907393],"about_ca_topic_score_codex":0.0064992676,"about_ca_topic_score_gemma":0.01172791,"teacher_disagreement_score":0.011950283,"about_ca_system_score_codex":0.00069221476,"about_ca_system_score_gemma":0.0009436224,"threshold_uncertainty_score":0.03997767},"labels":[],"label_agreement":null},{"id":"W2442332866","doi":"10.1088/1742-6596/720/1/012047","title":"Characteristic variogram for land use in Multispectral Images","year":2016,"lang":"en","type":"article","venue":"Journal of Physics Conference Series","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Multispectral image; Variogram; Remote sensing; Multispectral pattern recognition; Computer science; Data set; Geology; Artificial intelligence; Kriging; Machine learning","score_opus":0.03196729197592782,"score_gpt":0.24104600351479252,"score_spread":0.2090787115388647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2442332866","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23412548,0.00028310582,0.75778234,0.000244257,0.000057372763,0.000071804236,0.00091625785,0.0010812746,0.0054381466],"genre_scores_gemma":[0.9328853,0.00015157854,0.06392524,0.000044760913,0.000032882195,0.00007522425,0.0009176652,0.00012537368,0.0018419101],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99940693,0.00014912477,0.000018506253,0.0001584761,0.00021414105,0.000052958712],"domain_scores_gemma":[0.9988902,0.0004502251,0.00015957696,0.000251034,0.0001993552,0.000049683335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011082398,0.0003234593,0.00021082214,0.0021139141,0.00032305467,0.00092557794,0.00037035267,0.0003896785,0.0018695082],"category_scores_gemma":[0.0028610632,0.0001266067,0.0006490422,0.0023662003,0.00083404814,0.0012587862,0.00055447855,0.0005856052,0.0005386845],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054883346,0.00022385911,0.1683226,0.00035080078,0.0003817622,0.00053631817,0.00092580187,0.10570868,0.078278065,0.11617723,0.006620669,0.5219254],"study_design_scores_gemma":[0.000017967857,0.00017999079,0.20925403,0.00006534931,0.00008953155,0.001301115,0.000605456,0.6822879,0.03137174,0.059094258,0.01558683,0.00014589867],"about_ca_topic_score_codex":0.0015795676,"about_ca_topic_score_gemma":0.0015735758,"teacher_disagreement_score":0.0021139141,"about_ca_system_score_codex":0.0005662704,"about_ca_system_score_gemma":0.0005171798,"threshold_uncertainty_score":0.006254077},"labels":[],"label_agreement":null},{"id":"W2469929894","doi":"10.1007/s11859-016-1152-y","title":"Land cover classification of RADARSAT-2 SAR data using convolutional neural network","year":2016,"lang":"en","type":"article","venue":"Wuhan University Journal of Natural Sciences","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Softmax function; Computer science; Pattern recognition (psychology); Synthetic aperture radar; Convolutional neural network; Artificial intelligence; Feature (linguistics); Land cover; Backpropagation; Feature extraction; Remote sensing; Pooling; Contextual image classification; Artificial neural network; Deep learning; Geology; Image (mathematics); Land use","score_opus":0.05710185858406018,"score_gpt":0.25178247809670407,"score_spread":0.19468061951264387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2469929894","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32848567,0.0016208033,0.66132784,0.00036696237,0.00017339886,0.00009412233,0.0007350581,0.0028821097,0.004313941],"genre_scores_gemma":[0.8735218,0.0007070443,0.12033761,0.00014138539,0.000053290372,0.000065058026,0.0015921459,0.000050884275,0.0035308162],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998258,0.000016717306,0.000010472582,0.000048066035,0.0000627401,0.000036296955],"domain_scores_gemma":[0.9998721,0.000030248695,0.000021421405,0.0000185756,0.000049605274,0.000008068098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025238446,0.00059713755,0.00035981054,0.00072921487,0.00022636312,0.0003368142,0.00046806075,0.00041297937,0.00070548826],"category_scores_gemma":[0.00046344392,0.00020244054,0.00041677232,0.00066615996,0.00017921242,0.00076719443,0.00030429199,0.00031376688,0.00027233266],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025421387,0.00028088706,0.016466085,0.00016291579,0.00022534419,0.00024340935,0.00008461508,0.2475591,0.068377234,0.0021715849,0.0038666197,0.66030794],"study_design_scores_gemma":[0.0000058961145,0.000034526358,0.0051885024,0.0000071973755,0.000025992807,0.000045355868,0.0000131061515,0.9820331,0.011128188,0.00059995643,0.00090753665,0.000010761114],"about_ca_topic_score_codex":0.009033046,"about_ca_topic_score_gemma":0.010121904,"teacher_disagreement_score":0.009033046,"about_ca_system_score_codex":0.00045230787,"about_ca_system_score_gemma":0.00038616903,"threshold_uncertainty_score":0.017960966},"labels":[],"label_agreement":null},{"id":"W2474355323","doi":"10.5194/isprsarchives-xl-1-w5-263-2015","title":"A NEW FRAMEWORK FOR OBJECT-BASED IMAGE ANALYSIS BASED ON SEGMENTATION SCALE SPACE AND RANDOM FOREST CLASSIFIER","year":2015,"lang":"en","type":"article","venue":"˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Artificial intelligence; Segmentation; Computer science; Image segmentation; Scale (ratio); Computer vision; Scale-space segmentation; Segmentation-based object categorization; Scale space; Pixel; Pattern recognition (psychology); Minimum spanning tree-based segmentation; Land cover; Classifier (UML); Object (grammar); Range segmentation; Random forest; Image (mathematics); Image processing; Geography; Cartography; Land use","score_opus":0.019861149172388362,"score_gpt":0.2649953569412115,"score_spread":0.24513420776882316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2474355323","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007557519,0.0001373632,0.9978654,0.000030119227,0.00001827829,0.000039718954,0.00005292763,0.00089198636,0.00020855291],"genre_scores_gemma":[0.047890905,0.0002954191,0.9491801,0.00009636411,0.00010008496,0.00023191735,0.00058769085,0.0002718379,0.0013456009],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983639,0.0002651871,0.000095540934,0.00047185612,0.0006603896,0.00014312606],"domain_scores_gemma":[0.9993063,0.00017292051,0.00007520374,0.000097115044,0.00031103942,0.000037456473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019281721,0.0012050844,0.0017884993,0.0040306267,0.00072946236,0.0016150337,0.0024495625,0.0016490113,0.0021884358],"category_scores_gemma":[0.0018321195,0.000624326,0.0021684088,0.002884992,0.0006931581,0.0017684806,0.0010801723,0.0013738078,0.0015515604],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010083983,0.00017564771,0.0018453767,0.00024253118,0.00026162248,0.0001448981,0.00010358798,0.12954023,0.021138052,0.01977117,0.0075852824,0.8190907],"study_design_scores_gemma":[0.000008386425,0.000032991557,0.0006916977,0.000018630313,0.000034905133,0.00007624382,0.000015158072,0.98430866,0.0031220205,0.007639398,0.0040308144,0.000021138714],"about_ca_topic_score_codex":0.009569635,"about_ca_topic_score_gemma":0.0095125735,"teacher_disagreement_score":0.009569635,"about_ca_system_score_codex":0.0010140844,"about_ca_system_score_gemma":0.0010971115,"threshold_uncertainty_score":0.019027889},"labels":[],"label_agreement":null},{"id":"W2474792379","doi":"10.1007/978-3-319-33618-3_13","title":"Collaborative Unmixing Hyperspectral Imagery via Nonnegative Matrix Factorization","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Hyperspectral imaging; Non-negative matrix factorization; Karush–Kuhn–Tucker conditions; Matrix norm; Matrix decomposition; Computer science; Norm (philosophy); Matrix (chemical analysis); Endmember; Algorithm; Factorization; Pattern recognition (psychology); Artificial intelligence; Mathematics; Mathematical optimization; Physics","score_opus":0.00879871674109706,"score_gpt":0.23158956484056692,"score_spread":0.22279084809946986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2474792379","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025573168,0.0002068643,0.9956214,0.000043988122,0.00004955609,0.000021977927,0.00004388785,0.00026188558,0.0011931916],"genre_scores_gemma":[0.08863339,0.0006469591,0.9038358,0.00012034574,0.00013145263,0.00014367788,0.00054653594,0.00024862864,0.0056933844],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999298,0.00014158663,0.000030098421,0.00018112261,0.0002972101,0.000051937506],"domain_scores_gemma":[0.99942374,0.0002433924,0.000070020375,0.00013555899,0.000103233135,0.000024083443],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000651484,0.0014264244,0.00093487935,0.0005547545,0.00041157944,0.0009735173,0.0010779224,0.0009031438,0.0030367146],"category_scores_gemma":[0.0016668268,0.0006614736,0.0015500048,0.0009903909,0.00061763084,0.0020007875,0.002117891,0.0014670681,0.0019255329],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020139881,0.00016346086,0.0003394153,0.00042577434,0.00018342136,0.00020039432,0.0002250315,0.16493198,0.12731779,0.01805429,0.007721282,0.68023574],"study_design_scores_gemma":[0.000014554287,0.000061520004,0.00029345916,0.000018262966,0.000037394988,0.00020034288,0.000054659027,0.95740235,0.019816719,0.016002016,0.0060654352,0.000033208322],"about_ca_topic_score_codex":0.00090523646,"about_ca_topic_score_gemma":0.0019237313,"teacher_disagreement_score":0.0030367146,"about_ca_system_score_codex":0.00020081126,"about_ca_system_score_gemma":0.00035669375,"threshold_uncertainty_score":0.010158777},"labels":[],"label_agreement":null},{"id":"W2479356191","doi":"10.1016/s0099-1112(16)82059-5","title":"RPC-Based Coregistration of VHR Imagery for Urban Change Detection","year":2016,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Change detection; Computer science; Computer vision; Artificial intelligence; Set (abstract data type); Image (mathematics); Remote sensing; Geography","score_opus":0.04313851018196799,"score_gpt":0.23192984288636964,"score_spread":0.18879133270440165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2479356191","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17297986,0.000186396,0.8190816,0.00008925775,0.000057196426,0.00015949212,0.0002782393,0.00389942,0.0032684566],"genre_scores_gemma":[0.49853724,0.00013883921,0.49923953,0.00003774161,0.00002402249,0.00005681573,0.0007222111,0.00022171973,0.0010218944],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99959105,0.000059883176,0.00001932189,0.000115311654,0.00016300724,0.00005139862],"domain_scores_gemma":[0.9994517,0.000073438576,0.000059731334,0.00014467983,0.00024500498,0.000025481697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047231046,0.0005341424,0.00050195545,0.0023200037,0.00021544863,0.00057933887,0.000519866,0.0003229977,0.0016856646],"category_scores_gemma":[0.0012791131,0.00024915746,0.00045584614,0.0015563197,0.00032319882,0.0007034607,0.0006291649,0.0004568301,0.0009272233],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026176823,0.0002362671,0.0072188987,0.00016710843,0.00009775928,0.00013924546,0.00014323562,0.054193478,0.15498143,0.0021865142,0.0033900428,0.7769842],"study_design_scores_gemma":[0.000027242362,0.00012094785,0.013860506,0.000010741532,0.000058149853,0.00024813716,0.0000803921,0.91736645,0.06389028,0.0006441991,0.0036607317,0.000032209526],"about_ca_topic_score_codex":0.005017756,"about_ca_topic_score_gemma":0.0057868822,"teacher_disagreement_score":0.005017756,"about_ca_system_score_codex":0.0002742802,"about_ca_system_score_gemma":0.0006386142,"threshold_uncertainty_score":0.009977102},"labels":[],"label_agreement":null},{"id":"W2481612658","doi":"10.1109/igarss.1997.615954","title":"Spectral identification of coral biological vigour","year":2002,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Coral; Coral reef; Coral bleaching; Identification (biology); Environmental science; Remote sensing; Ecosystem; Reef; Computer science; Environmental resource management; Oceanography; Ecology; Geology; Biology","score_opus":0.043665899409870694,"score_gpt":0.22668553668949468,"score_spread":0.18301963727962398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2481612658","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8658146,0.0006495244,0.11300998,0.0001442085,0.000041095074,0.00003531317,0.000851688,0.0006311414,0.018822476],"genre_scores_gemma":[0.972645,0.00039124463,0.024963962,0.000037948237,0.000039101684,0.000022320046,0.00055292743,0.00003277035,0.0013147284],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9998666,0.000020930875,0.000005461952,0.00001889501,0.00007322528,0.000014896083],"domain_scores_gemma":[0.99964774,0.00007121065,0.000054120243,0.00004548741,0.00014759313,0.00003380685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027210038,0.00016012935,0.000128822,0.001398958,0.00011154784,0.00036443074,0.00015480144,0.00018699943,0.0009938697],"category_scores_gemma":[0.00087696256,0.00008686856,0.00014335949,0.00068361603,0.00015878059,0.00040695386,0.0002668188,0.00016662624,0.00037769013],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034932766,0.00012047184,0.086065374,0.00021993884,0.00006510743,0.00007349177,0.0001500362,0.0072634113,0.549078,0.0023705952,0.0015361853,0.35270804],"study_design_scores_gemma":[0.0000290737,0.0002962791,0.6729826,0.00006417217,0.000116083604,0.0012518667,0.00037037904,0.15374844,0.15725622,0.0052415724,0.008546374,0.00009699658],"about_ca_topic_score_codex":0.00041359692,"about_ca_topic_score_gemma":0.00073550415,"teacher_disagreement_score":0.001398958,"about_ca_system_score_codex":0.000101426616,"about_ca_system_score_gemma":0.000077921395,"threshold_uncertainty_score":0.0033248663},"labels":[],"label_agreement":null},{"id":"W2484116175","doi":"","title":"EXTRACTION OF ROAD NETWORKS USING PAN-SHARPENED MULTISPECTRAL AND PANCHROMATIC QUICKBIRD IMAGES","year":2005,"lang":"en","type":"article","venue":"GEOMATICA","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of New Brunswick; Université du Québec à Montréal; York University","funders":"","keywords":"Panchromatic film; Cartography; Humanities; Geography; Multispectral image; Forestry; Remote sensing; Art","score_opus":0.012593095002132914,"score_gpt":0.24411953546859233,"score_spread":0.23152644046645943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2484116175","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11345732,0.0011405604,0.8721678,0.00011602089,0.00008082371,0.0002455249,0.0012625768,0.0030257707,0.00850345],"genre_scores_gemma":[0.38148025,0.002538414,0.5914194,0.00006440227,0.000058515983,0.00024313988,0.003709343,0.00039018193,0.020096388],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99972945,0.000019222112,0.000015066587,0.0000839312,0.00010543216,0.00004689517],"domain_scores_gemma":[0.9997751,0.00004572347,0.000035921978,0.00003054159,0.00010209444,0.000010651356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022010002,0.0015508662,0.0005347242,0.003507008,0.0003851505,0.0012072329,0.00051257265,0.00062965025,0.0024595696],"category_scores_gemma":[0.0006934759,0.00051369984,0.0011006476,0.0017065298,0.00024356124,0.0013078543,0.00044507458,0.0005071116,0.0019355366],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001239934,0.000075870346,0.008673583,0.00063030113,0.00014877108,0.0004912893,0.00028505715,0.05716968,0.121818304,0.00304113,0.0021744962,0.80536765],"study_design_scores_gemma":[0.00004291646,0.00026065388,0.09071783,0.00022150076,0.0004332405,0.0019764923,0.0012460243,0.58670825,0.24835178,0.007123689,0.06271842,0.00019920233],"about_ca_topic_score_codex":0.008588838,"about_ca_topic_score_gemma":0.013333803,"teacher_disagreement_score":0.008588838,"about_ca_system_score_codex":0.00046119135,"about_ca_system_score_gemma":0.0007413094,"threshold_uncertainty_score":0.017077744},"labels":[],"label_agreement":null},{"id":"W248591590","doi":"10.5589/m08-013","title":"Noise estimation in a noise-adjusted principal component transformation and hyperspectral image restoration","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Hyperspectral imaging; Principal component analysis; Noise (video); Data striping; Artificial intelligence; Transformation (genetics); Computer science; Linear discriminant analysis; Pattern recognition (psychology); Computer vision; Image noise; Remote sensing; Mathematics; Image (mathematics); Geography","score_opus":0.02179136260568871,"score_gpt":0.21883540558614084,"score_spread":0.19704404298045214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W248591590","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044601172,0.000042717595,0.9544543,0.000063638465,0.00002709638,0.000020643409,0.000018614013,0.00025775103,0.00051399844],"genre_scores_gemma":[0.31825703,0.00011064579,0.67944354,0.00004746542,0.00002573945,0.00007609318,0.0001475527,0.00012648117,0.0017654408],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995839,0.00010955165,0.000015137409,0.00009547559,0.00016665616,0.000029254184],"domain_scores_gemma":[0.9996427,0.0001276295,0.00005205203,0.00007015477,0.00009626258,0.00001116207],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006246188,0.0005996124,0.00032758524,0.00049811933,0.00027847028,0.00044618902,0.0004874908,0.00053542905,0.0006501522],"category_scores_gemma":[0.0025002216,0.0002742023,0.0005034373,0.0006499921,0.0007167147,0.0007390791,0.00043944755,0.0005931465,0.00028419454],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033206647,0.00015925067,0.0045926324,0.000118451535,0.000095160416,0.00025988542,0.00024761434,0.5888457,0.1316225,0.02017433,0.0010997779,0.25245273],"study_design_scores_gemma":[0.000007952572,0.00004098397,0.001205307,0.0000037691748,0.0000098179435,0.000067086614,0.000014726142,0.97292536,0.022560548,0.0022844456,0.00086680526,0.000013258314],"about_ca_topic_score_codex":0.0026019798,"about_ca_topic_score_gemma":0.0029347942,"teacher_disagreement_score":0.0026019798,"about_ca_system_score_codex":0.0002717079,"about_ca_system_score_gemma":0.00047640415,"threshold_uncertainty_score":0.005173683},"labels":[],"label_agreement":null},{"id":"W2492200701","doi":"10.5281/zenodo.832427","title":"Supervised Classification of RADARSAT-2 Polarimetric Data for Different Land Features","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Wishart distribution; Support vector machine; Confusion matrix; Polarimetry; Computer science; Confusion; Remote sensing; Pattern recognition (psychology); Artificial intelligence; Feature (linguistics); Geography; Machine learning; Multivariate statistics; Physics; Scattering","score_opus":0.13094021512394252,"score_gpt":0.21097684571490077,"score_spread":0.08003663059095825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2492200701","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96472996,0.00008610806,0.031330552,0.000037377336,0.000019508037,0.000051220777,0.0010107027,0.00043512258,0.002299251],"genre_scores_gemma":[0.9824541,0.000030857493,0.013628651,0.0000091967695,0.00000659344,0.000032380718,0.0024007666,0.000023701854,0.0014136877],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996087,0.00008042351,0.000027688378,0.00008098489,0.000140131,0.00006212277],"domain_scores_gemma":[0.999091,0.00021929487,0.00010785103,0.00011396055,0.0004220067,0.00004584906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004351106,0.00047768353,0.00031850897,0.0014390999,0.000253111,0.00049069343,0.00024943316,0.0002577151,0.0006935407],"category_scores_gemma":[0.001194693,0.00007402625,0.0002626845,0.00086182606,0.0002577458,0.00027195748,0.00027331302,0.00020256218,0.00046355018],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018535668,0.00095583935,0.19175598,0.00034242283,0.0002823406,0.0003631668,0.0006617806,0.083111614,0.20097859,0.0014685466,0.004661098,0.513565],"study_design_scores_gemma":[0.000027851866,0.0004102875,0.26752964,0.000023876324,0.00007839661,0.00033270408,0.00055540993,0.5787875,0.14808369,0.0012800593,0.0028405534,0.000050115723],"about_ca_topic_score_codex":0.0030911816,"about_ca_topic_score_gemma":0.005865163,"teacher_disagreement_score":0.0030911816,"about_ca_system_score_codex":0.0003007918,"about_ca_system_score_gemma":0.00040130023,"threshold_uncertainty_score":0.0061463714},"labels":[],"label_agreement":null},{"id":"W2495550359","doi":"10.1364/isa.2016.iw1e.4","title":"Experimental Study of Spectral Signature Variability in Hyperspectral Remote Sensing","year":2016,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Defence Research and Development Canada","funders":"","keywords":"Hyperspectral imaging; Robustness (evolution); Spectral signature; Remote sensing; Shadow (psychology); Computer science; Signature (topology); Full spectral imaging; Artificial intelligence; Geology; Mathematics; Geometry","score_opus":0.01474893874597394,"score_gpt":0.24418871753415144,"score_spread":0.2294397787881775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2495550359","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99132884,0.000043675715,0.007604007,0.00002346779,0.000011993583,0.0000148146055,0.00013096276,0.000063181775,0.00077910256],"genre_scores_gemma":[0.9956358,0.000030062336,0.0037608487,0.000015361984,0.0000049118207,0.00002077347,0.00012823998,0.000017118486,0.0003869806],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99964595,0.0000693175,0.000021801008,0.00008061971,0.00012406775,0.000058297584],"domain_scores_gemma":[0.9985738,0.0005866693,0.00016787226,0.00023755792,0.0003510967,0.00008314434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004587983,0.00026817407,0.00017689013,0.00022481965,0.00031776284,0.00026222857,0.00041370458,0.00045797334,0.0014417706],"category_scores_gemma":[0.001119067,0.00014068361,0.00013293643,0.0003560657,0.00045428387,0.0002643404,0.000357752,0.0002760955,0.00018262293],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00063419,0.00025403075,0.0022440318,0.000072009985,0.000016012424,0.000095264804,0.0001198704,0.0039256117,0.9856878,0.00022942896,0.00013189114,0.006590022],"study_design_scores_gemma":[0.000053580177,0.001979442,0.02384308,0.000011854399,0.000028587077,0.00030910134,0.00017860145,0.039363317,0.9330961,0.00028987194,0.000811127,0.000035276433],"about_ca_topic_score_codex":0.00036849847,"about_ca_topic_score_gemma":0.0004397773,"teacher_disagreement_score":0.0014417706,"about_ca_system_score_codex":0.00019490975,"about_ca_system_score_gemma":0.00013352603,"threshold_uncertainty_score":0.004823208},"labels":[],"label_agreement":null},{"id":"W2510660416","doi":"10.1109/icip.2016.7532824","title":"GCE-based model for the fusion of multiples color image segmentations","year":2016,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Segmentation; Scale-space segmentation; Artificial intelligence; Image segmentation; Computer science; Consistency (knowledge bases); Fusion; Segmentation-based object categorization; Image fusion; Pattern recognition (psychology); Fuse (electrical); Energy (signal processing); Image (mathematics); Computer vision; Mathematics; Statistics; Physics","score_opus":0.03350865008580306,"score_gpt":0.25265728152896294,"score_spread":0.21914863144315988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2510660416","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0052596345,0.00017704123,0.9934876,0.0001237805,0.000026704234,0.000026939408,0.000052922256,0.00034159294,0.0005036704],"genre_scores_gemma":[0.48414028,0.0005370198,0.5069405,0.00034439148,0.0001403284,0.000261606,0.0007216774,0.0005290123,0.006385219],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985544,0.00028031305,0.00006939988,0.00043422938,0.00053067546,0.00013095327],"domain_scores_gemma":[0.99847025,0.00060953695,0.00017222803,0.00024674903,0.00043434143,0.000066866436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030975817,0.0009875976,0.0014064984,0.0020571768,0.00047878467,0.0015493267,0.0025633373,0.0026608303,0.0023910573],"category_scores_gemma":[0.005322523,0.0006871033,0.001588572,0.0016443352,0.0014481139,0.0026544149,0.0018569106,0.0018978737,0.0009763672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014812424,0.00006336334,0.0007703401,0.00009400303,0.00010454831,0.0001193625,0.0001461459,0.8744784,0.011618086,0.02213632,0.0011152246,0.08920607],"study_design_scores_gemma":[0.0000025790762,0.000011876746,0.0001218051,0.0000041608005,0.000007028838,0.000027121947,0.000004641961,0.99412644,0.0011058135,0.0041733608,0.00040705723,0.00000803699],"about_ca_topic_score_codex":0.005769309,"about_ca_topic_score_gemma":0.0050488836,"teacher_disagreement_score":0.005769309,"about_ca_system_score_codex":0.001525302,"about_ca_system_score_gemma":0.0009269446,"threshold_uncertainty_score":0.01638174},"labels":[],"label_agreement":null},{"id":"W2514438493","doi":"10.1109/icip.2016.7532825","title":"A new multi-criteria fusion model for color textured image segmentation","year":2016,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Segmentation; Image segmentation; Artificial intelligence; Computer science; Weighting; Robustness (evolution); Ground truth; Cluster analysis; Segmentation-based object categorization; Entropy (arrow of time); Pattern recognition (psychology); Scale-space segmentation; Rand index; Computer vision","score_opus":0.03363506248924973,"score_gpt":0.2850355095268419,"score_spread":0.2514004470375922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2514438493","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028331995,0.00007469381,0.99657285,0.00005430537,0.000007590955,0.000015848665,0.000015857706,0.00010804734,0.0003176669],"genre_scores_gemma":[0.31040883,0.00021133643,0.686257,0.00017114807,0.000060242714,0.00024481976,0.00021181606,0.00023354348,0.0022012219],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984724,0.0003645043,0.000081732105,0.00031375192,0.0006583095,0.00010923048],"domain_scores_gemma":[0.9991059,0.00029667694,0.00012318826,0.0000961551,0.0003298538,0.000048324095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028792417,0.0009566608,0.0015224064,0.0018649918,0.00067092257,0.0017646545,0.002207729,0.0021222127,0.0013495261],"category_scores_gemma":[0.003161657,0.0006324379,0.0017589219,0.001530659,0.0011364996,0.001913936,0.0014661701,0.0011100988,0.00045772412],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009787254,0.000052795654,0.0005993919,0.000109202294,0.000110989604,0.00007300622,0.00014370507,0.8791313,0.014372632,0.015072921,0.0011271926,0.08910897],"study_design_scores_gemma":[0.0000026592447,0.0000149450125,0.00010818835,0.0000044824997,0.0000070084893,0.000016948523,0.000006018715,0.9953387,0.0011444411,0.003074474,0.00027360782,0.000008542775],"about_ca_topic_score_codex":0.003952716,"about_ca_topic_score_gemma":0.003248598,"teacher_disagreement_score":0.003952716,"about_ca_system_score_codex":0.0018194952,"about_ca_system_score_gemma":0.0010863463,"threshold_uncertainty_score":0.015227079},"labels":[],"label_agreement":null},{"id":"W2514478517","doi":"10.1109/eorsa.2016.7552776","title":"Investigating species composition in a temperate grassland using Unmanned Aerial Vehicle-acquired imagery","year":2016,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Remote sensing; Grassland; Vegetation (pathology); Environmental science; Image resolution; Biodiversity; Spatial ecology; Spatial analysis; Aerial survey; Scale (ratio); Computer science; Cartography; Ecology; Geography; Artificial intelligence; Biology","score_opus":0.032312863294869515,"score_gpt":0.23390324392468825,"score_spread":0.20159038062981874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2514478517","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9946911,0.0002930373,0.0034421706,0.000017089134,0.000009043441,0.00002881984,0.00044689327,0.000057898425,0.0010139685],"genre_scores_gemma":[0.9852297,0.00026295046,0.013212449,0.000018346984,0.000010328588,0.000023392458,0.0008289935,0.0000115581515,0.0004022875],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99989223,0.000010109333,0.0000072079815,0.000036359866,0.000028955012,0.000025226942],"domain_scores_gemma":[0.9998857,0.000020174668,0.000032233587,0.000008831783,0.000037599835,0.000015563748],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017589293,0.00031752817,0.00019609531,0.002487593,0.0002515729,0.0003063447,0.0001624626,0.00024668354,0.00036139673],"category_scores_gemma":[0.00018894584,0.000106016014,0.0003172737,0.0012297566,0.00015596421,0.00034409293,0.00017051227,0.00009448856,0.00012249876],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035699556,0.00026831683,0.5824538,0.0004998192,0.00020389598,0.0019603502,0.0017940057,0.012091889,0.18996309,0.00036110918,0.0011008651,0.20894581],"study_design_scores_gemma":[0.0000068399136,0.00012369352,0.95682937,0.00003554053,0.00006808314,0.00047278948,0.0014452128,0.031825166,0.0074658277,0.00013577656,0.001564639,0.00002719691],"about_ca_topic_score_codex":0.005852751,"about_ca_topic_score_gemma":0.013162403,"teacher_disagreement_score":0.005852751,"about_ca_system_score_codex":0.00015225411,"about_ca_system_score_gemma":0.00012670417,"threshold_uncertainty_score":0.01163739},"labels":[],"label_agreement":null},{"id":"W2521581589","doi":"","title":"Evaluation de la sensibilité de l’instrument FCI à bord du nouveau satellite Meteosat Troisième Génération imageur (MTG-I) aux variations de la quantité d’aérosols d’origine désertique dans l’atmosphère","year":2016,"lang":"fr","type":"dissertation","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact","funders":"","keywords":"Physics; Humanities; Meteorological satellite; Forestry; Geography; Art; Satellite; Geostationary orbit","score_opus":0.010618723883780547,"score_gpt":0.2528988805421232,"score_spread":0.24228015665834263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2521581589","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93109417,0.00021245213,0.06504315,0.00008249177,0.000036178346,0.00009164664,0.00031901774,0.00075193006,0.002368919],"genre_scores_gemma":[0.9639141,0.000120755314,0.034965802,0.00003413376,0.0000055464384,0.0000635488,0.00037283686,0.000043588192,0.00047972787],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99936444,0.00017028672,0.000022676895,0.00015074674,0.00022208241,0.00006979901],"domain_scores_gemma":[0.9990884,0.00045503967,0.00010126946,0.00013036608,0.0001952059,0.00002968972],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014230148,0.0006344344,0.00045877422,0.0005714437,0.00028334526,0.0007131134,0.0006409501,0.0009281341,0.000817463],"category_scores_gemma":[0.0025578607,0.00028746214,0.00065294467,0.0004546508,0.00033254246,0.00051617017,0.00047904192,0.000380282,0.00026737188],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011798859,0.00038078811,0.11239743,0.00046778258,0.00050160073,0.00018099435,0.0005879169,0.42561033,0.30096054,0.0014143193,0.0006918919,0.15562649],"study_design_scores_gemma":[0.00007235011,0.0017660361,0.074729435,0.00003972664,0.00016278062,0.000277203,0.00021043411,0.7182133,0.20102848,0.0003133949,0.0030926517,0.00009418127],"about_ca_topic_score_codex":0.0035625617,"about_ca_topic_score_gemma":0.0021179204,"teacher_disagreement_score":0.0035625617,"about_ca_system_score_codex":0.0005776189,"about_ca_system_score_gemma":0.0004366623,"threshold_uncertainty_score":0.007525742},"labels":[],"label_agreement":null},{"id":"W2523265165","doi":"10.3846/20296991.2016.1226388","title":"USING PIXEL-BASED AND OBJECT-BASED METHODS TO CLASSIFY URBAN HYPERSPECTRAL FEATURES","year":2016,"lang":"en","type":"article","venue":"Geodesy and Cartography","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Università degli Studi di Pavia","keywords":"Hyperspectral imaging; Pattern recognition (psychology); Pixel; Artificial intelligence; Support vector machine; Computer science; Segmentation; Feature (linguistics); Feature extraction","score_opus":0.022378460504848405,"score_gpt":0.28236057845737167,"score_spread":0.25998211795252324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2523265165","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25987262,0.00097619166,0.7327964,0.00012214953,0.000082020146,0.00023109629,0.0003914763,0.0012677346,0.0042603184],"genre_scores_gemma":[0.5716883,0.00043866472,0.42448515,0.000076564706,0.000053094485,0.00015351608,0.0010284388,0.00008100237,0.0019952233],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993849,0.000092415634,0.00003714133,0.00017859985,0.00024825166,0.00005858792],"domain_scores_gemma":[0.9994148,0.00015602962,0.00009458613,0.000059778136,0.00024859482,0.00002621542],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009936246,0.0007848346,0.0005531826,0.003633588,0.0002669519,0.0009765914,0.00047463726,0.0006069046,0.00058667955],"category_scores_gemma":[0.0010265998,0.00020355386,0.00069868297,0.0015278944,0.00039190447,0.000990173,0.00046733828,0.00034210912,0.00033614683],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025314256,0.00033602337,0.017902141,0.0003221314,0.00027926793,0.00011322628,0.00023452977,0.04792175,0.07886984,0.0017746924,0.0015109304,0.8504823],"study_design_scores_gemma":[0.000031579282,0.0002290023,0.052304074,0.00005652954,0.00016742825,0.00031455673,0.00034583197,0.87692064,0.06274156,0.0021327925,0.0046770475,0.00007896564],"about_ca_topic_score_codex":0.001593473,"about_ca_topic_score_gemma":0.0027205106,"teacher_disagreement_score":0.003633588,"about_ca_system_score_codex":0.0003618725,"about_ca_system_score_gemma":0.00032525902,"threshold_uncertainty_score":0.0052548647},"labels":[],"label_agreement":null},{"id":"W2529940551","doi":"10.1080/01431161.2016.1244364","title":"Multilayer semantic segmentation of remote-sensing imagery using a hybrid object-based Markov random field model","year":2016,"lang":"en","type":"article","venue":"International Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"Wuhan University; National Natural Science Foundation of China","keywords":"Computer science; Markov random field; Segmentation; Artificial intelligence; Markov chain; Pattern recognition (psychology); Probabilistic logic; Cut; Graph; Field (mathematics); Image segmentation; Inference; Random field; Stochastic matrix; Data mining; Machine learning; Theoretical computer science; Mathematics","score_opus":0.020273454756604456,"score_gpt":0.271200313074044,"score_spread":0.25092685831743955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2529940551","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02479664,0.00019294462,0.9738799,0.0001453133,0.000018401644,0.000030863248,0.00008199333,0.00031495557,0.000539103],"genre_scores_gemma":[0.7639641,0.00037886086,0.23144993,0.00018395411,0.00007053609,0.00019472778,0.0005145873,0.000111070054,0.0031320967],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995634,0.0001070903,0.000025284102,0.0001359647,0.00009910697,0.000069132024],"domain_scores_gemma":[0.9995053,0.00027318916,0.00008798119,0.000037042646,0.000070245,0.000026273736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010745468,0.0006156869,0.0010810338,0.001118842,0.0003949218,0.0007758071,0.0016269308,0.0012049938,0.0011660857],"category_scores_gemma":[0.0015628121,0.00056037045,0.001559835,0.00078169705,0.0007402407,0.0013271278,0.00067561714,0.0007499387,0.00028431864],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009958769,0.000047433048,0.0016297831,0.00006288499,0.00006324078,0.000103460436,0.00007904803,0.943742,0.005347304,0.011296474,0.00049334305,0.037035473],"study_design_scores_gemma":[0.000002333252,0.0000072074104,0.00013590271,0.0000023493708,0.0000059607196,0.000010344323,0.0000022869644,0.9977404,0.00026225357,0.0017450779,0.000080915124,0.000005043911],"about_ca_topic_score_codex":0.011845991,"about_ca_topic_score_gemma":0.010571122,"teacher_disagreement_score":0.011845991,"about_ca_system_score_codex":0.0010600202,"about_ca_system_score_gemma":0.0009075869,"threshold_uncertainty_score":0.023554087},"labels":[],"label_agreement":null},{"id":"W2536986253","doi":"10.1109/aipr.2008.4906461","title":"Temporal structure methods for image-based change analysis","year":2008,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lockheed Martin (Canada)","funders":"","keywords":"Probabilistic latent semantic analysis; Computer science; Change detection; Probabilistic logic; Artificial intelligence; Image (mathematics); Pattern recognition (psychology); Term (time); Latent semantic analysis; Bag-of-words model; Data mining","score_opus":0.06778757712944315,"score_gpt":0.33624013860189494,"score_spread":0.2684525614724518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2536986253","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021829987,0.0004725162,0.99581724,0.00008191633,0.000038275324,0.000030877934,0.00013197366,0.00057591463,0.0006682135],"genre_scores_gemma":[0.12040467,0.0011552935,0.8743811,0.00012411659,0.00030889304,0.00027026975,0.0009162228,0.0002817389,0.002157715],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99918693,0.00017212053,0.000057712186,0.0002037707,0.00032776166,0.000051570267],"domain_scores_gemma":[0.99842834,0.0008095243,0.00024041095,0.0002311787,0.00024213114,0.000048511414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011396952,0.000824611,0.00086531416,0.0042795674,0.00048246834,0.0012197254,0.0010989739,0.0007991327,0.0034174628],"category_scores_gemma":[0.004155786,0.00045536106,0.0011784139,0.0039576963,0.00074970897,0.0018958893,0.0009698115,0.0012773206,0.0013929927],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000117178926,0.000113850896,0.002614224,0.00029845542,0.00020368054,0.00011739526,0.0001507638,0.09593807,0.015489467,0.04826874,0.0051497873,0.8315384],"study_design_scores_gemma":[0.000015178652,0.000035684752,0.0020884585,0.00003077996,0.000039673156,0.00014252083,0.00006300905,0.94241154,0.0038433515,0.043043427,0.008256855,0.000029576366],"about_ca_topic_score_codex":0.0037163552,"about_ca_topic_score_gemma":0.004229201,"teacher_disagreement_score":0.0042795674,"about_ca_system_score_codex":0.00081581326,"about_ca_system_score_gemma":0.00068514294,"threshold_uncertainty_score":0.0114325285},"labels":[],"label_agreement":null},{"id":"W2538611983","doi":"10.5721/eujrs20164933","title":"Tropical Agrarian Landscape Classification using high-resolution GeoEYE data and segmentationbased approach","year":2016,"lang":"en","type":"article","venue":"European Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"United Nations University Institute for Water, Environment, and Health","funders":"Leibniz-Gemeinschaft; Bundesministerium für Bildung und Forschung","keywords":"Segmentation; Geography; Contextual image classification; Object based; Cartography; Image segmentation; Computer science; Set (abstract data type); Identification (biology); Pattern recognition (psychology); Pixel; Data mining; Remote sensing; Artificial intelligence; Image (mathematics)","score_opus":0.053986603144337,"score_gpt":0.24536645434664864,"score_spread":0.19137985120231163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2538611983","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97130257,0.00012488395,0.02414073,0.000050027742,0.0000055812825,0.0000612615,0.0005100314,0.00011861713,0.0036863405],"genre_scores_gemma":[0.9701389,0.000090423426,0.028582226,0.000010484565,0.0000065092136,0.00001916612,0.00066260225,0.000010677659,0.0004790212],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9997589,0.000057629088,0.000015114553,0.00005288141,0.00006623207,0.00004916282],"domain_scores_gemma":[0.9997867,0.00006707302,0.000040659153,0.000028305705,0.000059217935,0.000018069046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037478455,0.00024623497,0.0002043648,0.0017578914,0.00018979974,0.00071762205,0.00026604885,0.00025664744,0.00075600256],"category_scores_gemma":[0.0005506263,0.00010732489,0.00029601975,0.0014975271,0.00024449234,0.0004189586,0.00028414847,0.0001188691,0.00017491638],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00073485204,0.0005176137,0.25171354,0.0003468442,0.0001839674,0.001280137,0.00077284576,0.17557776,0.15179314,0.0038853379,0.001641309,0.41155264],"study_design_scores_gemma":[0.000022793072,0.00028576568,0.37419376,0.00003911139,0.00010489814,0.00038793017,0.0008368271,0.58743405,0.033444483,0.0010008386,0.0021969776,0.000052610856],"about_ca_topic_score_codex":0.010108454,"about_ca_topic_score_gemma":0.012800475,"teacher_disagreement_score":0.010108454,"about_ca_system_score_codex":0.00038181932,"about_ca_system_score_gemma":0.00032903254,"threshold_uncertainty_score":0.020099223},"labels":[],"label_agreement":null},{"id":"W2539990047","doi":"10.1109/tgrs.2016.2605766","title":"A Salient Region Detection and Pattern Matching-Based Algorithm for Center Detection of a Partially Covered Tropical Cyclone in a SAR Image","year":2016,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Program for New Century Excellent Talents in University; Canadian Space Agency; National Oceanic and Atmospheric Administration; National Natural Science Foundation of China","keywords":"Tropical cyclone; Synthetic aperture radar; Remote sensing; Computer science; Particle swarm optimization; Salient; Algorithm; Image resolution; Matching (statistics); Meteorology; Artificial intelligence; Geology; Geography; Mathematics","score_opus":0.0114141863847378,"score_gpt":0.2202281006076056,"score_spread":0.2088139142228678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2539990047","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024794828,0.000117827476,0.97376615,0.000041762694,0.000032879194,0.00007929642,0.00003449264,0.00068741373,0.00044526273],"genre_scores_gemma":[0.26249996,0.0002585824,0.73460996,0.00007671908,0.00005464902,0.00017511034,0.00027903166,0.00008507624,0.001961009],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995907,0.000044327593,0.00002807347,0.00013479532,0.00015531191,0.00004682047],"domain_scores_gemma":[0.99961877,0.000086931475,0.00008188074,0.000050285602,0.0001337321,0.000028382767],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005270796,0.0006162587,0.00079432083,0.0015289307,0.00042975607,0.00048841967,0.00090820965,0.0006762746,0.0009815833],"category_scores_gemma":[0.0012825907,0.00042765224,0.00068563805,0.001038218,0.00039626984,0.00078406726,0.0006246438,0.0004930219,0.00049730163],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033650713,0.00018201287,0.0018940942,0.00013515822,0.00008361815,0.00026625593,0.00015395552,0.04512042,0.14930768,0.0025870886,0.0026849858,0.7972482],"study_design_scores_gemma":[0.000060408638,0.0002677517,0.004542412,0.000012871227,0.000058915375,0.00051536807,0.000047218902,0.9348177,0.05513043,0.0016793234,0.0028295147,0.000038049362],"about_ca_topic_score_codex":0.0024735995,"about_ca_topic_score_gemma":0.0024190743,"teacher_disagreement_score":0.0024735995,"about_ca_system_score_codex":0.000278897,"about_ca_system_score_gemma":0.0008483079,"threshold_uncertainty_score":0.0049183965},"labels":[],"label_agreement":null},{"id":"W2544776797","doi":"10.1109/whispers.2012.6874310","title":"A novel method for automatic minerals identification and their abundance estimation for material type discrimination using hyperspectral data","year":2012,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Jet Propulsion Laboratory; Department of Science and Technology, Ministry of Science and Technology, India","keywords":"Endmember; Hyperspectral imaging; Correlation coefficient; Mean squared error; Computer science; Pixel; Pattern recognition (psychology); Filter (signal processing); Mathematics; Artificial intelligence; Statistics; Remote sensing; Algorithm; Geology; Computer vision","score_opus":0.10943009532530126,"score_gpt":0.3508918049106845,"score_spread":0.24146170958538324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2544776797","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006096707,0.000052029744,0.9925229,0.000027221406,0.000019027379,0.00003529141,0.00007343544,0.00072807807,0.00044522653],"genre_scores_gemma":[0.04874936,0.00006071622,0.9485664,0.000032181626,0.000020074012,0.00009365338,0.00023140055,0.00007148356,0.0021748035],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996593,0.00003135525,0.000015521498,0.000113432536,0.00016114942,0.000019300078],"domain_scores_gemma":[0.99971193,0.000046214278,0.000033628465,0.00004079586,0.00015218885,0.000015218109],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004247925,0.0006353129,0.0004853762,0.0011079963,0.0005320163,0.0005346582,0.0008583148,0.0005656578,0.0018010614],"category_scores_gemma":[0.0006397811,0.0003003001,0.00045543205,0.00064492016,0.00029906697,0.0008657467,0.0004983192,0.000516496,0.00097455486],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013014417,0.00012628209,0.0015823826,0.00018616565,0.000059654503,0.00007082378,0.00008566982,0.02303461,0.2195462,0.0043257084,0.0033231976,0.7475292],"study_design_scores_gemma":[0.000026564967,0.000087899585,0.003359555,0.000012241805,0.00003921228,0.00035903874,0.000036617683,0.84900147,0.13199297,0.0022155636,0.01280937,0.000059492737],"about_ca_topic_score_codex":0.0016586178,"about_ca_topic_score_gemma":0.0036896472,"teacher_disagreement_score":0.0018010614,"about_ca_system_score_codex":0.00033125305,"about_ca_system_score_gemma":0.0011146304,"threshold_uncertainty_score":0.006025195},"labels":[],"label_agreement":null},{"id":"W2547676861","doi":"10.1109/igarss.2016.7729386","title":"A comparative study on Multiple Kernel Learning for remote sensing image classification","year":2016,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Multiple kernel learning; Kernel (algebra); Computer science; Artificial intelligence; Contextual image classification; Machine learning; Selection (genetic algorithm); Pattern recognition (psychology); Statistical classification; Image (mathematics); Support vector machine; Data mining; Kernel method; Mathematics","score_opus":0.06678521257020982,"score_gpt":0.3041694838889226,"score_spread":0.23738427131871281,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2547676861","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15264256,0.028640619,0.8068875,0.0009967678,0.00025068456,0.00011898303,0.000084185296,0.00082903967,0.009549671],"genre_scores_gemma":[0.8266048,0.0063666124,0.16415243,0.0001109794,0.00023217393,0.000054143562,0.00019700812,0.00018157877,0.0021002288],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959728,0.0016008936,0.0002520093,0.00044646463,0.0015783242,0.00014950336],"domain_scores_gemma":[0.99061525,0.0058792084,0.00044907795,0.0006071937,0.0023009647,0.00014829723],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005575332,0.0005518024,0.0011324222,0.0029716738,0.00048632792,0.0020313177,0.0008955888,0.0008351544,0.0015266343],"category_scores_gemma":[0.015024343,0.00019503059,0.0008491725,0.0030611649,0.00070846855,0.0034583043,0.00086214725,0.00067352166,0.0005199208],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008302493,0.0003358957,0.007554699,0.0012428995,0.0003991476,0.00020857759,0.00033655268,0.08151527,0.0132174175,0.021800755,0.0020919603,0.8704666],"study_design_scores_gemma":[0.000027426997,0.00072776753,0.010726052,0.00012345264,0.00017672108,0.0005195736,0.00031397038,0.95127904,0.016843546,0.009870156,0.009295368,0.00009691775],"about_ca_topic_score_codex":0.0009124303,"about_ca_topic_score_gemma":0.0007130631,"teacher_disagreement_score":0.005575332,"about_ca_system_score_codex":0.0008599959,"about_ca_system_score_gemma":0.00040194785,"threshold_uncertainty_score":0.029485524},"labels":[],"label_agreement":null},{"id":"W2547862665","doi":"10.1109/igarss.2016.7729169","title":"Combination of texture and shape analysis for a rapid rivers extraction from high resolution SAR images","year":2016,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Computer Research Institute of Montréal; École de Technologie Supérieure","funders":"","keywords":"Synthetic aperture radar; Computer science; Artificial intelligence; Remote sensing; Robustness (evolution); Pixel; Computer vision; Speckle pattern; Image resolution; Radar imaging; Mathematical morphology; Rectangle; Interferometric synthetic aperture radar; Radar; Geography; Image processing; Image (mathematics); Mathematics","score_opus":0.013171661023646725,"score_gpt":0.22626951766027587,"score_spread":0.21309785663662914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2547862665","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10382903,0.00047726705,0.893074,0.000111627625,0.00003574945,0.00007135404,0.00010188975,0.00082068227,0.0014784845],"genre_scores_gemma":[0.50662845,0.0007113131,0.4901122,0.0000771731,0.00006329702,0.000066694505,0.000378613,0.0001199144,0.0018423735],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99958926,0.000060331215,0.000026823593,0.00006941353,0.00020527064,0.000048855843],"domain_scores_gemma":[0.99959284,0.00012690114,0.00006831722,0.00005435914,0.00013544752,0.00002210943],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000504758,0.00048440124,0.00057297456,0.0020648353,0.00021122274,0.00074121973,0.00033426937,0.00050768885,0.0006740193],"category_scores_gemma":[0.00081170344,0.0002674377,0.0006997538,0.0012269749,0.00030105977,0.00074579084,0.00036935802,0.00033937217,0.00060621236],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002324107,0.00010739221,0.0045906906,0.00020215026,0.000088051274,0.00022345243,0.000085454776,0.009235133,0.40309945,0.00056313863,0.0006859933,0.5808867],"study_design_scores_gemma":[0.00005703913,0.00045773378,0.04317,0.00003829543,0.0002502137,0.0016564657,0.00030529732,0.7097114,0.23566623,0.0016891429,0.006898568,0.000099661665],"about_ca_topic_score_codex":0.0010478826,"about_ca_topic_score_gemma":0.00220337,"teacher_disagreement_score":0.0020648353,"about_ca_system_score_codex":0.00015713496,"about_ca_system_score_gemma":0.00031843703,"threshold_uncertainty_score":0.0026694536},"labels":[],"label_agreement":null},{"id":"W2548390709","doi":"10.1109/igarss.2016.7730652","title":"A self-adapted threshold-based region merging method for remote sensing image segmentation","year":2016,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Segmentation; Image segmentation; Artificial intelligence; Process (computing); Watershed; Region growing; Computer vision; Market segmentation; Image (mathematics); Pattern recognition (psychology); Scale-space segmentation; Segmentation-based object categorization; Workflow; Division (mathematics); Remote sensing; Geography; Mathematics","score_opus":0.024575690501115424,"score_gpt":0.2765941529871175,"score_spread":0.25201846248600207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2548390709","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013162975,0.00015902756,0.9851082,0.00004494738,0.00002786134,0.000045985114,0.000028538541,0.0009226941,0.0004997117],"genre_scores_gemma":[0.12708235,0.00016584143,0.8709046,0.000059515605,0.000034434608,0.0000952151,0.00018161978,0.00021393428,0.0012626174],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99900645,0.00013005661,0.00007745266,0.0002817253,0.0004360098,0.000068368034],"domain_scores_gemma":[0.9992335,0.00016054999,0.00013020843,0.00013468407,0.0003004215,0.000040629333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010545835,0.00058284303,0.0008987542,0.0018341866,0.0005863827,0.0010171802,0.001682486,0.0010307977,0.0013096536],"category_scores_gemma":[0.0017121019,0.00053528696,0.001166319,0.0016987086,0.0005892616,0.0015720356,0.0010989754,0.00071880175,0.0006206896],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020854258,0.00016077622,0.0024352856,0.00021675798,0.00018863159,0.0002151401,0.00054456847,0.09836452,0.2098865,0.00785467,0.002556358,0.6773682],"study_design_scores_gemma":[0.00001900196,0.00009349328,0.0022315735,0.000013021588,0.000060242575,0.00040266858,0.00006135253,0.9344963,0.054703616,0.0020424854,0.005810495,0.00006571948],"about_ca_topic_score_codex":0.002302151,"about_ca_topic_score_gemma":0.0026226193,"teacher_disagreement_score":0.002302151,"about_ca_system_score_codex":0.0006145381,"about_ca_system_score_gemma":0.0009973148,"threshold_uncertainty_score":0.005577266},"labels":[],"label_agreement":null},{"id":"W2551712374","doi":"10.3390/rs8110957","title":"Preface: The Environmental Mapping and Analysis Program (EnMAP) Mission: Preparing for Its Scientific Exploitation","year":2016,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Remote sensing; Environmental science; Computer science; Environmental resource management; Geography","score_opus":0.02740267818765363,"score_gpt":0.2518923050273429,"score_spread":0.22448962683968926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2551712374","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003733532,0.012862968,0.020786416,0.103056155,0.68117005,0.0011033406,0.014684549,0.0024729182,0.1601301],"genre_scores_gemma":[0.0159103,0.016139353,0.01883652,0.01616598,0.34356734,0.00060424267,0.028730666,0.0031992923,0.55684626],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99904996,0.00009707865,0.00006499006,0.000126742,0.00059518265,0.00006596052],"domain_scores_gemma":[0.98624915,0.0008275397,0.00037046982,0.00042577906,0.010510903,0.0016162655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028394174,0.0008799981,0.00059908465,0.0025236295,0.001327567,0.0030546929,0.0011020898,0.0015435492,0.070289016],"category_scores_gemma":[0.006932464,0.00022504033,0.00041268126,0.0013795944,0.0004780527,0.002256128,0.0012460692,0.0030221243,0.07027057],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001360241,0.000015278354,0.00013613112,0.0000651451,0.0000016505106,0.000024016792,0.000022032911,0.00006395103,0.0003902452,0.00042303716,0.9732844,0.02556045],"study_design_scores_gemma":[0.0000028560278,0.000020907217,0.0007038269,0.00005572552,0.0000017392823,0.000047668156,0.0000429545,0.00012497403,0.00025651613,0.0005966816,0.9981395,0.0000067573656],"about_ca_topic_score_codex":0.0024232191,"about_ca_topic_score_gemma":0.002966011,"teacher_disagreement_score":0.070289016,"about_ca_system_score_codex":0.0010500796,"about_ca_system_score_gemma":0.0022558514,"threshold_uncertainty_score":0.2351402},"labels":[],"label_agreement":null},{"id":"W2555870105","doi":"10.3990/2.432","title":"Object-based VHSR image classification using multiband compact texture unit descriptor","year":2016,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Panchromatic film; Multispectral image; Artificial intelligence; Computer science; Pattern recognition (psychology); Pixel; Computer vision; Image texture; Image resolution; Texture (cosmology); Feature extraction; Multispectral pattern recognition; Context (archaeology); Contextual image classification; Spectral bands; Segmentation; Image segmentation; Remote sensing; Image (mathematics); Geography","score_opus":0.05602288968623317,"score_gpt":0.26865250520579703,"score_spread":0.21262961551956386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2555870105","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20512916,0.00080044946,0.78756535,0.00018923613,0.00010935532,0.00016230681,0.00037129197,0.0017274034,0.0039454536],"genre_scores_gemma":[0.8223496,0.00056064094,0.17340225,0.0000734155,0.00008733326,0.00009714117,0.0009925063,0.00009595077,0.002341127],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99952936,0.00005019137,0.00003130095,0.00008573578,0.00023182463,0.00007149883],"domain_scores_gemma":[0.99963176,0.0000842248,0.00007564023,0.000055467703,0.0001321143,0.00002070849],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055082445,0.00039674155,0.0009901819,0.0029500313,0.0002090977,0.0011858558,0.0005710119,0.00054309994,0.001716417],"category_scores_gemma":[0.00095153245,0.00013581186,0.0007251996,0.0016809705,0.0003712334,0.0011426504,0.0005298692,0.0003649331,0.00068368966],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00059963163,0.00024533228,0.004132868,0.00022444183,0.0001251759,0.00012872937,0.000116147436,0.04387614,0.10522403,0.0036442787,0.001870207,0.839813],"study_design_scores_gemma":[0.00003313534,0.00030229473,0.011015976,0.0000277625,0.00008437489,0.00029590214,0.00016336546,0.943481,0.040074423,0.0020102507,0.002471662,0.00003986158],"about_ca_topic_score_codex":0.001973622,"about_ca_topic_score_gemma":0.0012248096,"teacher_disagreement_score":0.0029500313,"about_ca_system_score_codex":0.00045030957,"about_ca_system_score_gemma":0.0003044356,"threshold_uncertainty_score":0.005741954},"labels":[],"label_agreement":null},{"id":"W2569333680","doi":"10.1167/16.12.403","title":"The role of category-specific global orientation statistics for scene categorization","year":2016,"lang":"en","type":"article","venue":"Journal of Vision","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Categorization; Artificial intelligence; Orientation (vector space); Naturalness; Normalization (sociology); Coherence (philosophical gambling strategy); Scene statistics; Pattern recognition (psychology); Mathematics; Computer vision; Computer science; Rotation (mathematics); Statistics; Perception; Psychology; Geometry","score_opus":0.009964916668540632,"score_gpt":0.2604293982981312,"score_spread":0.25046448162959056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2569333680","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94890344,0.00030852816,0.04865204,0.00008929496,0.000022102495,0.00002335357,0.000092450304,0.0001849042,0.0017238773],"genre_scores_gemma":[0.9949366,0.000058566657,0.004763866,0.000012130669,0.0000039941065,0.0000065764257,0.0000652153,0.00003740406,0.00011564348],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9990804,0.00018584938,0.000063014864,0.00028109452,0.00031134064,0.00007824719],"domain_scores_gemma":[0.9927088,0.0026445065,0.001756667,0.001823018,0.00068863225,0.00037841377],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013166111,0.00040159834,0.00034001403,0.00053926243,0.00020356532,0.0012529506,0.00042863563,0.0004671421,0.0007015046],"category_scores_gemma":[0.010282563,0.00029530883,0.00027809752,0.00030061806,0.0009555179,0.001853504,0.00066883396,0.00056317565,0.00015394416],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004294079,0.00009168083,0.056211017,0.00014571102,0.0001094408,0.00009551498,0.0005615176,0.0033885161,0.8582887,0.002192397,0.00015225392,0.078333735],"study_design_scores_gemma":[0.000033272914,0.0006781718,0.7660676,0.00003930552,0.00011113524,0.000559626,0.00048381276,0.03499995,0.188414,0.007610652,0.0008791039,0.00012335384],"about_ca_topic_score_codex":0.0011101548,"about_ca_topic_score_gemma":0.0011293327,"teacher_disagreement_score":0.0013166111,"about_ca_system_score_codex":0.00036506832,"about_ca_system_score_gemma":0.00031065612,"threshold_uncertainty_score":0.006962955},"labels":[],"label_agreement":null},{"id":"W2570117975","doi":"10.1109/stratus.2016.7811138","title":"A simple and effective semi-supervised learning framework for hyperspectral image classification","year":2016,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Università degli Studi di Pavia; Purdue University","keywords":"Hyperspectral imaging; Cluster analysis; Pattern recognition (psychology); Artificial intelligence; Computer science; Classifier (UML); Fuzzy logic; Ground truth; Benchmark (surveying); Fuzzy clustering; Support vector machine; Spectral clustering; Machine learning; Data mining","score_opus":0.014433216368845621,"score_gpt":0.25342506952311694,"score_spread":0.23899185315427132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2570117975","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021834837,0.00012338278,0.99662435,0.00004790856,0.00001533101,0.00005258641,0.000061801,0.00044335038,0.0004478825],"genre_scores_gemma":[0.12848735,0.0002695949,0.8675662,0.00013452294,0.00011343707,0.00033311438,0.0005569433,0.00013011518,0.0024087469],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983176,0.00052951335,0.000087650165,0.00036873846,0.00063227816,0.00006413877],"domain_scores_gemma":[0.99878305,0.0002969391,0.00016090041,0.00022736735,0.00047956256,0.000052256746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015408525,0.00096672255,0.0011179172,0.0015450927,0.00067999354,0.00080183445,0.0016501318,0.0010021811,0.0015377281],"category_scores_gemma":[0.0026559657,0.00033319902,0.00090847886,0.0012182293,0.0009110959,0.0013738719,0.0012001301,0.0013948407,0.0012242479],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019118722,0.00037779548,0.0013946391,0.0004781174,0.00020417287,0.00018597086,0.0002655729,0.16288191,0.055328995,0.025560705,0.010692172,0.7424388],"study_design_scores_gemma":[0.000011788413,0.00008198074,0.00068828586,0.000018274677,0.000015498665,0.0002293563,0.000035581834,0.9694514,0.009949629,0.013169112,0.0063097267,0.000039289684],"about_ca_topic_score_codex":0.0016516369,"about_ca_topic_score_gemma":0.0035206738,"teacher_disagreement_score":0.0016516369,"about_ca_system_score_codex":0.00054475194,"about_ca_system_score_gemma":0.0011806694,"threshold_uncertainty_score":0.008148909},"labels":[],"label_agreement":null},{"id":"W2576410327","doi":"10.4236/ars.2017.61001","title":"Building Change Detection Improvement Using Topographic Correction Models","year":2017,"lang":"en","type":"article","venue":"Advances in Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Change detection; Brightness; Pixel; Remote sensing; Nadir; Computer science; Computer vision; Artificial intelligence; Brightness temperature; Geology; Optics; Physics; Satellite","score_opus":0.03985178315254148,"score_gpt":0.294565496400842,"score_spread":0.2547137132483005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2576410327","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12624963,0.0004243967,0.8674637,0.000113149785,0.00006538224,0.0000823092,0.00012526786,0.0025908065,0.002885474],"genre_scores_gemma":[0.76971966,0.00043047447,0.22686182,0.00004513664,0.00002963082,0.000038373295,0.00039124058,0.00020308146,0.002280559],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99966395,0.00004540034,0.000015706555,0.00010245927,0.00013191007,0.000040567098],"domain_scores_gemma":[0.99952245,0.00010298706,0.00008030865,0.00007955385,0.00020144743,0.000013195575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046129726,0.00063450244,0.00040754513,0.0012384775,0.00019466644,0.0006708509,0.0005965116,0.0003558616,0.00086600747],"category_scores_gemma":[0.0015862626,0.00027389894,0.00076966657,0.0010387542,0.00020888489,0.0009241765,0.00039179315,0.0004869899,0.0005673054],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015366443,0.00012633631,0.010646181,0.0001718708,0.00013948593,0.00022281957,0.00016641378,0.3520232,0.050901562,0.0019830687,0.0017141501,0.5817513],"study_design_scores_gemma":[0.00000421048,0.000036820707,0.0040329145,0.0000055120113,0.00003426547,0.00010491254,0.000028105695,0.9812258,0.012596754,0.00036269307,0.0015515512,0.000016573948],"about_ca_topic_score_codex":0.00643931,"about_ca_topic_score_gemma":0.009200842,"teacher_disagreement_score":0.00643931,"about_ca_system_score_codex":0.0002903648,"about_ca_system_score_gemma":0.0005326914,"threshold_uncertainty_score":0.012803614},"labels":[],"label_agreement":null},{"id":"W2579656072","doi":"10.3390/rs9010088","title":"The Need for Accurate Geometric and Radiometric Corrections of Drone-Borne Hyperspectral Data for Mineral Exploration: MEPHySTo—A Toolbox for Pre-Processing Drone-Borne Hyperspectral Data","year":2017,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":196,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Rio Tinto; Česká geologická služba","keywords":"Hyperspectral imaging; Drone; Remote sensing; Computer science; Terrain; Photogrammetry; Toolbox; Computer vision; Artificial intelligence; Geology; Geography; Cartography","score_opus":0.10463175704393649,"score_gpt":0.3335407806333736,"score_spread":0.22890902358943713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2579656072","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009021385,0.00019580132,0.94916874,0.000103314545,0.00006771832,0.00008681209,0.0029555263,0.03569727,0.0027034886],"genre_scores_gemma":[0.07476119,0.0006319355,0.89265764,0.00015031271,0.00005538747,0.00033494757,0.014651105,0.008808579,0.007948998],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999696,0.000033568682,0.000020707195,0.00007302013,0.0001460133,0.000030712483],"domain_scores_gemma":[0.9994247,0.00012669878,0.000055189776,0.0001751711,0.00017921694,0.000039149298],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005275287,0.0010643937,0.00041971332,0.0011595942,0.00030910596,0.0009337825,0.0009284928,0.00045196997,0.012776449],"category_scores_gemma":[0.0019501704,0.0004667344,0.0006715018,0.0006677598,0.00035025174,0.001187703,0.0012430743,0.0012268698,0.011260205],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037181005,0.0001217685,0.0030215627,0.00076063874,0.00017049057,0.00064555166,0.00054106506,0.043341428,0.12855244,0.012099029,0.065632604,0.7447416],"study_design_scores_gemma":[0.00013360327,0.00012210045,0.008808194,0.00022213797,0.0000511759,0.0013049413,0.0002964627,0.47685364,0.20881768,0.014355354,0.2888445,0.00019021916],"about_ca_topic_score_codex":0.0020738128,"about_ca_topic_score_gemma":0.0030691673,"teacher_disagreement_score":0.012776449,"about_ca_system_score_codex":0.00022073659,"about_ca_system_score_gemma":0.0005999248,"threshold_uncertainty_score":0.042741537},"labels":[],"label_agreement":null},{"id":"W2588217599","doi":"10.5194/isprsarchives-xl-1-w5-37-2015","title":"A COMPARISON STUDY OF DIFFERENT MARKER SELECTION METHODS FOR SPECTRAL-SPATIAL CLASSIFICATION OF HYPERSPECTRAL IMAGES","year":2015,"lang":"en","type":"article","venue":"˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Purdue University","keywords":"Pattern recognition (psychology); Hyperspectral imaging; Artificial intelligence; Support vector machine; Computer science; Segmentation; Benchmark (surveying); Image segmentation; Pixel; Cluster analysis; Scale-space segmentation; Selection (genetic algorithm); Geography; Cartography","score_opus":0.0423487683217518,"score_gpt":0.3227572754962461,"score_spread":0.2804085071744943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2588217599","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68684393,0.0048692585,0.30221254,0.00025098317,0.0001423567,0.00019703539,0.00037093472,0.002154348,0.0029586514],"genre_scores_gemma":[0.8390399,0.0006836731,0.15844278,0.000051869112,0.000039906583,0.00006544002,0.00081673404,0.000111698995,0.00074792287],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99863356,0.00045195883,0.0000960151,0.00024683055,0.0004759817,0.00009558533],"domain_scores_gemma":[0.99750817,0.0011811943,0.0002068036,0.00017266124,0.0008493643,0.00008174955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027220245,0.00074535,0.00079014676,0.0026846307,0.000378441,0.0007641081,0.00063541165,0.0006303804,0.00054419535],"category_scores_gemma":[0.003916073,0.00014576428,0.00058953627,0.001599146,0.00024613168,0.00100952,0.00034664138,0.00035661162,0.00028575948],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015818145,0.0005077776,0.020379387,0.00044842617,0.00045065244,0.0000921133,0.00017911122,0.037693173,0.032411657,0.00094883936,0.0024620655,0.90284497],"study_design_scores_gemma":[0.00007127973,0.00073703215,0.038400736,0.00006054465,0.0002795776,0.00025797833,0.00029459715,0.9099967,0.046566032,0.0008318538,0.0024603505,0.00004323359],"about_ca_topic_score_codex":0.002242324,"about_ca_topic_score_gemma":0.002858541,"teacher_disagreement_score":0.0027220245,"about_ca_system_score_codex":0.00034599888,"about_ca_system_score_gemma":0.00039910842,"threshold_uncertainty_score":0.014395595},"labels":[],"label_agreement":null},{"id":"W2591084634","doi":"10.1109/jstars.2017.2662484","title":"Similarity-Based Multiple Kernel Learning Algorithms for Classification of Remotely Sensed Images","year":2017,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Purdue University","keywords":"Multiple kernel learning; Kernel (algebra); Computer science; Artificial intelligence; Algorithm; Support vector machine; Heuristic; Similarity (geometry); Optimization problem; Pattern recognition (psychology); Similarity measure; Kernel method; Machine learning; Mathematics; Image (mathematics)","score_opus":0.05584373348749552,"score_gpt":0.27049773742356487,"score_spread":0.21465400393606934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2591084634","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004281316,0.00043163207,0.9945345,0.00006737537,0.000019287614,0.00003541694,0.000017848337,0.00032487782,0.0002876872],"genre_scores_gemma":[0.27330974,0.0008344648,0.72284,0.00011447533,0.00010232704,0.0002770157,0.00032719274,0.00017526967,0.0020195753],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974986,0.00074327656,0.00022156548,0.0004923199,0.00090642285,0.00013787352],"domain_scores_gemma":[0.99691296,0.0011724394,0.0004944675,0.0004034639,0.00094533677,0.00007126306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027853623,0.0011610886,0.0020043422,0.0024845365,0.00062017847,0.0014500493,0.0021722917,0.0012276792,0.001165762],"category_scores_gemma":[0.007652798,0.0005560213,0.0013188795,0.0030278163,0.0010866051,0.0030483145,0.0015858194,0.002054902,0.0010348142],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001746243,0.00022941457,0.001251773,0.00030586438,0.0002106592,0.000058566107,0.00015765057,0.33123064,0.0097251935,0.02816496,0.002800136,0.6256905],"study_design_scores_gemma":[0.0000067802657,0.000028825434,0.00025862732,0.00000652147,0.000009796395,0.00002944006,0.000009572703,0.9914044,0.0023191196,0.005088395,0.00082135055,0.00001714149],"about_ca_topic_score_codex":0.0024469437,"about_ca_topic_score_gemma":0.0016814212,"teacher_disagreement_score":0.0027853623,"about_ca_system_score_codex":0.0013773587,"about_ca_system_score_gemma":0.0010733237,"threshold_uncertainty_score":0.014730632},"labels":[],"label_agreement":null},{"id":"W2594058371","doi":"10.1016/j.corsci.2017.02.015","title":"Atmospheric corrosion assessed from corrosion images using fuzzy Kolmogorov–Sinai entropy","year":2017,"lang":"en","type":"article","venue":"Corrosion Science","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Corrosion; Entropy (arrow of time); Fuzzy logic; Mathematics; Materials science; Metallurgy; Thermodynamics; Physics; Computer science; Artificial intelligence","score_opus":0.03235354886750323,"score_gpt":0.28853241416960373,"score_spread":0.2561788653021005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2594058371","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83205634,0.0004373713,0.16276339,0.000074962976,0.000056915265,0.000043609078,0.00036265462,0.00036419084,0.003840486],"genre_scores_gemma":[0.98839134,0.00010386541,0.011000924,0.0000066487387,0.000018836126,0.000009071254,0.00015600598,0.000008367556,0.0003049323],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9997763,0.000025571857,0.0000186194,0.00003873554,0.00011479216,0.000025994206],"domain_scores_gemma":[0.99962795,0.00009765086,0.00007166673,0.000026200389,0.00015641289,0.000020100339],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047441974,0.00044449582,0.0003625581,0.0020524287,0.00021125135,0.000592995,0.00023908704,0.00040748803,0.0005313448],"category_scores_gemma":[0.0009714998,0.00012210646,0.00048161412,0.0007696669,0.00030837068,0.00068662374,0.00032593514,0.0002686544,0.00013556097],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013495767,0.00035913917,0.10121218,0.00066592905,0.00044542213,0.00059009576,0.00046378607,0.13088615,0.2952353,0.00606536,0.0027819949,0.45994508],"study_design_scores_gemma":[0.000017842889,0.00018967292,0.13424398,0.000024978905,0.00017582912,0.00030356174,0.00018687893,0.8066376,0.054996252,0.0021144021,0.0010213325,0.000087694374],"about_ca_topic_score_codex":0.001742428,"about_ca_topic_score_gemma":0.0018852996,"teacher_disagreement_score":0.0020524287,"about_ca_system_score_codex":0.0002754151,"about_ca_system_score_gemma":0.00021669731,"threshold_uncertainty_score":0.0034645796},"labels":[],"label_agreement":null},{"id":"W2600004689","doi":"10.1080/01431161.2017.1302107","title":"Segmentation parameter selection for object-based land-cover mapping from ultra high resolution spectral and elevation data","year":2017,"lang":"en","type":"article","venue":"International Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Segmentation; Computer science; Elevation (ballistics); Artificial intelligence; Image segmentation; Land cover; Scale-space segmentation; Segmentation-based object categorization; Minimum spanning tree-based segmentation; Pattern recognition (psychology); Aerial image; Computer vision; Object (grammar); Remote sensing; Image (mathematics); Mathematics; Geography; Land use","score_opus":0.041557390753503044,"score_gpt":0.2877838556931378,"score_spread":0.24622646493963476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2600004689","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07675165,0.0005341015,0.9199428,0.000081331345,0.000020839645,0.00009619232,0.00011192109,0.0016406531,0.00082038256],"genre_scores_gemma":[0.42058805,0.00040612285,0.5772845,0.000064447915,0.000028234528,0.00012649229,0.00068281026,0.0002295624,0.0005897481],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999624,0.00008094359,0.00003280641,0.00009881389,0.00011655843,0.000046951616],"domain_scores_gemma":[0.99965954,0.00013119387,0.00005332452,0.00005148024,0.00008386213,0.000020590182],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000781918,0.0007259667,0.00089833554,0.0026259804,0.00045733422,0.00080457184,0.0007068386,0.0008516309,0.0007587966],"category_scores_gemma":[0.0014070114,0.00031708315,0.00061197777,0.0015716621,0.00048694463,0.0010660782,0.0005165297,0.00049178465,0.0005835129],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032225638,0.00025262442,0.0074867825,0.00027541927,0.000155855,0.0002329828,0.00037879864,0.087586224,0.14738835,0.002392237,0.0022889972,0.75123954],"study_design_scores_gemma":[0.000026599493,0.00006265125,0.0105902,0.000022165928,0.00007571409,0.00023455903,0.00021203782,0.9221205,0.06004312,0.0036615788,0.0028995143,0.000051374067],"about_ca_topic_score_codex":0.002330446,"about_ca_topic_score_gemma":0.0033569376,"teacher_disagreement_score":0.0026259804,"about_ca_system_score_codex":0.00037299664,"about_ca_system_score_gemma":0.0006069295,"threshold_uncertainty_score":0.0046337247},"labels":[],"label_agreement":null},{"id":"W2602079573","doi":"10.1117/1.jrs.11.015026","title":"Spectral-analysis-based extraction of land disturbances arising from oil and gas development in diverse landscapes","year":2017,"lang":"en","type":"article","venue":"Journal of Applied Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Natural Resources Canada","funders":"Canadian Space Agency","keywords":"Remote sensing; Environmental science; Satellite imagery; Land use; Scale (ratio); Agricultural land; Geographic information system; Computer science; Geography; Cartography; Ecology","score_opus":0.015348840983323717,"score_gpt":0.24037451563939788,"score_spread":0.22502567465607415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2602079573","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.901062,0.00013305443,0.095479585,0.000048710175,0.000006964848,0.00005691729,0.00039820423,0.00059273833,0.002221844],"genre_scores_gemma":[0.9554581,0.00009616439,0.043388426,0.0000124972175,0.0000044190665,0.000019556219,0.0005673507,0.000026044701,0.00042744903],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99990726,0.000012853019,0.000005109712,0.000021249736,0.00003516933,0.00001835556],"domain_scores_gemma":[0.99979454,0.000052896205,0.000032451946,0.00002561179,0.0000779058,0.000016581947],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025176725,0.0002720607,0.00020913301,0.0017784169,0.00016222824,0.0003736857,0.00023987913,0.00018168226,0.00033709756],"category_scores_gemma":[0.0003272372,0.00011709931,0.00018395322,0.0010161061,0.00022604846,0.00034554905,0.0002290579,0.00012868879,0.00017684308],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00061020476,0.00031800388,0.0692402,0.00023963639,0.00008169516,0.00033003784,0.0005348951,0.07952054,0.29814318,0.00070983166,0.0013813497,0.5488904],"study_design_scores_gemma":[0.000024798224,0.00009382953,0.2664897,0.000015579515,0.00006784196,0.00035406742,0.0005664522,0.6937996,0.036491793,0.0006134978,0.0014496094,0.000033252247],"about_ca_topic_score_codex":0.011285212,"about_ca_topic_score_gemma":0.020559724,"teacher_disagreement_score":0.011285212,"about_ca_system_score_codex":0.00028133258,"about_ca_system_score_gemma":0.00026432402,"threshold_uncertainty_score":0.022439063},"labels":[],"label_agreement":null},{"id":"W2604260836","doi":"","title":"Binary Image Segmentation Using Classification Methods: Support Vector Machines, Artificial Neural Networks and Kth Nearest Neighbours","year":2017,"lang":"en","type":"article","venue":"Global Society of Scientific Research and Researchers - International Journal of Computer","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Support vector machine; Pattern recognition (psychology); Artificial intelligence; Artificial neural network; Kernel (algebra); Radial basis function; Computer science; Pixel; Quadratic function; Hyperparameter optimization; Discriminative model; Mathematics; Quadratic equation","score_opus":0.15257039710470194,"score_gpt":0.44471315370141384,"score_spread":0.2921427565967119,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2604260836","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09692067,0.0021848292,0.89624876,0.00024852905,0.00013267997,0.00012577711,0.00013555786,0.0015848766,0.00241824],"genre_scores_gemma":[0.57982504,0.0008586133,0.41667432,0.000054089865,0.00006315152,0.00019658971,0.00023059455,0.000100849466,0.0019967575],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987307,0.00036486745,0.000121276345,0.0002337375,0.00046677495,0.0000824755],"domain_scores_gemma":[0.9986137,0.00062515127,0.0002675575,0.00010664791,0.0003587801,0.000028029881],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001703089,0.00083858205,0.0010216064,0.0021127225,0.00042271454,0.0011778774,0.0008038974,0.001170496,0.00091300945],"category_scores_gemma":[0.004627596,0.00035492392,0.0006061915,0.0021305934,0.00059737463,0.0014753845,0.00053807074,0.0005521799,0.00048679265],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00089290243,0.00022824897,0.0053609824,0.00095103186,0.0001715326,0.000230173,0.00023086836,0.17252411,0.048567716,0.005140161,0.0018773548,0.76382494],"study_design_scores_gemma":[0.000019696923,0.00016392242,0.004335996,0.00005634941,0.00004019916,0.00027503358,0.00009004095,0.9601297,0.03021305,0.0029089605,0.0017246989,0.000042322336],"about_ca_topic_score_codex":0.0024483942,"about_ca_topic_score_gemma":0.0023014995,"teacher_disagreement_score":0.0024483942,"about_ca_system_score_codex":0.00062044093,"about_ca_system_score_gemma":0.00058520207,"threshold_uncertainty_score":0.009006858},"labels":[],"label_agreement":null},{"id":"W2605327034","doi":"10.1109/jstars.2017.2684132","title":"Smooth and Sparse Regularization for NMF Hyperspectral Unmixing","year":2017,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":53,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Non-negative matrix factorization; Hyperspectral imaging; Computer science; Matrix norm; Matrix decomposition; Pattern recognition (psychology); Inverse trigonometric functions; Mathematics; Algorithm; Artificial intelligence; Eigenvalues and eigenvectors; Physics","score_opus":0.03356192672564947,"score_gpt":0.24105756736317516,"score_spread":0.20749564063752568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2605327034","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001574126,0.000096585754,0.9978421,0.000056744593,0.00001963013,0.000012734609,0.000022316775,0.00012788775,0.0002479178],"genre_scores_gemma":[0.050197255,0.00033168003,0.9473206,0.000101013255,0.00008933759,0.000114021976,0.0002988329,0.00013422726,0.0014130683],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99910384,0.00022206348,0.000036545047,0.00021212394,0.00037059092,0.000054773725],"domain_scores_gemma":[0.9993094,0.00030690173,0.00008686489,0.00010294576,0.00016708471,0.000026760541],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013045259,0.001261706,0.0008924149,0.0009850365,0.0005572232,0.000603708,0.0011314038,0.001381558,0.001269541],"category_scores_gemma":[0.0024053312,0.0004833125,0.0013322872,0.0012071363,0.0009233852,0.0015710517,0.0009466823,0.001891104,0.0007239853],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000115024566,0.00014300057,0.00072576816,0.00037711256,0.00015724287,0.000112140995,0.00021071051,0.55068374,0.047344208,0.035193685,0.005614437,0.35932288],"study_design_scores_gemma":[0.0000049774494,0.000010924047,0.00011734931,0.0000052671567,0.000005817453,0.000027886277,0.000007938286,0.9902266,0.0033281802,0.0043351315,0.0019171287,0.0000128221645],"about_ca_topic_score_codex":0.0033169722,"about_ca_topic_score_gemma":0.003656598,"teacher_disagreement_score":0.0033169722,"about_ca_system_score_codex":0.00063289225,"about_ca_system_score_gemma":0.0008580168,"threshold_uncertainty_score":0.006899059},"labels":[],"label_agreement":null},{"id":"W2605486153","doi":"10.1109/tgrs.2017.2689018","title":"Superpixel-Based Multiple Local CNN for Panchromatic and Multispectral Image Classification","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":135,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Panchromatic film; Multispectral image; Artificial intelligence; Computer science; Computer vision; Contextual image classification; Multispectral pattern recognition; Pattern recognition (psychology); Remote sensing; Image (mathematics); Geology","score_opus":0.02544551525432839,"score_gpt":0.2574967378916121,"score_spread":0.2320512226372837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2605486153","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.090023875,0.0025650368,0.89317524,0.0004094793,0.00022888386,0.00014748033,0.00080954906,0.005190028,0.0074504376],"genre_scores_gemma":[0.7291043,0.0014561147,0.25198773,0.00042417788,0.00014130925,0.0001748783,0.0026779918,0.00024576517,0.013787737],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99967444,0.000021154781,0.000013989618,0.000121771955,0.00009689804,0.000071762595],"domain_scores_gemma":[0.99984086,0.000019500754,0.00002521872,0.000038019294,0.00005910531,0.00001721162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034598814,0.0011530113,0.000765718,0.0009173458,0.000283582,0.0005776665,0.0016587363,0.00073732843,0.002918546],"category_scores_gemma":[0.00047502742,0.00045155935,0.0009429331,0.0011220542,0.00032329254,0.0013927779,0.00076890126,0.0008442019,0.00077778357],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002948221,0.00022099145,0.003151852,0.00024001003,0.0002476976,0.00023770252,0.00008961338,0.24213469,0.082261994,0.0048909285,0.009638569,0.6565911],"study_design_scores_gemma":[0.000004292214,0.00003135088,0.0008543173,0.0000066457496,0.000026140062,0.000039492155,0.000009239125,0.98949707,0.0074807485,0.0009787824,0.0010629838,0.000008905336],"about_ca_topic_score_codex":0.017781856,"about_ca_topic_score_gemma":0.023115022,"teacher_disagreement_score":0.017781856,"about_ca_system_score_codex":0.0012641853,"about_ca_system_score_gemma":0.00086462515,"threshold_uncertainty_score":0.0353567},"labels":[],"label_agreement":null},{"id":"W2608922915","doi":"10.3390/rs9060586","title":"Exploiting Deep Matching and SAR Data for the Geo-Localization Accuracy Improvement of Optical Satellite Images","year":2017,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":116,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Remote sensing; Artificial intelligence; Satellite; Synthetic aperture radar; Computer vision; Matching (statistics); Geology; Mathematics","score_opus":0.04560480712519072,"score_gpt":0.29373051169321396,"score_spread":0.24812570456802324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2608922915","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30558747,0.00049644586,0.69028074,0.00027676485,0.000069909576,0.000027079044,0.00013468871,0.0010419611,0.0020849651],"genre_scores_gemma":[0.92791545,0.00015046936,0.07022299,0.00006623219,0.000021331081,0.00001230519,0.00029110303,0.000026933505,0.0012930734],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99979216,0.00004247596,0.0000108865715,0.000056044322,0.000067183944,0.000031276533],"domain_scores_gemma":[0.999684,0.00008640048,0.00007246801,0.00006627234,0.00007422659,0.000016687825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005425112,0.0004335011,0.0003095138,0.00049779296,0.00012899088,0.00037348075,0.000507795,0.0004976473,0.0006867609],"category_scores_gemma":[0.0011761732,0.00016283264,0.00030447566,0.0006505675,0.00030953652,0.0007400111,0.0005977725,0.00054486515,0.00027911193],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030930026,0.00023552222,0.00575362,0.000104024555,0.00011493559,0.00013548406,0.000069393434,0.46360126,0.061301656,0.0035661014,0.0019870123,0.4628217],"study_design_scores_gemma":[0.00000326868,0.00003668183,0.0013553053,0.000002786196,0.000009345454,0.000019121791,0.000007990405,0.98951846,0.007871031,0.00079280074,0.0003787655,0.0000043923824],"about_ca_topic_score_codex":0.0029532544,"about_ca_topic_score_gemma":0.0034661188,"teacher_disagreement_score":0.0029532544,"about_ca_system_score_codex":0.00029766202,"about_ca_system_score_gemma":0.00031699764,"threshold_uncertainty_score":0.0058721304},"labels":[],"label_agreement":null},{"id":"W2611882615","doi":"10.1117/12.2264580","title":"The role of the continuous wavelet transform in mineral identification using hyperspectral imaging in the long-wave infrared by using SVM classifier","year":2017,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Université Laval","keywords":"Hyperspectral imaging; Artificial intelligence; Support vector machine; Computer science; Wavelet; Pattern recognition (psychology); Remote sensing; Imaging spectrometer; Feature extraction; Infrared; Materials science; Spectrometer; Optics; Geology; Physics","score_opus":0.014094674224309366,"score_gpt":0.23181749354817188,"score_spread":0.2177228193238625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2611882615","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18774855,0.0010410484,0.80647993,0.00044849323,0.00017054494,0.00007967686,0.00012293782,0.0008429973,0.003065776],"genre_scores_gemma":[0.7796212,0.00069003477,0.21593232,0.00008576649,0.00011752082,0.00006312973,0.0003651751,0.000063661224,0.0030611155],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993236,0.00016208217,0.000056002355,0.00013689074,0.00024808352,0.00007340361],"domain_scores_gemma":[0.99891746,0.00043945486,0.000092392234,0.000066672954,0.00043529336,0.000048783542],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001381787,0.0005334022,0.000515233,0.0010761116,0.0002670514,0.0010143341,0.000497218,0.00073025975,0.0007871606],"category_scores_gemma":[0.0024164233,0.00016067491,0.00053975015,0.00079179363,0.00027747537,0.0012831289,0.00029571707,0.00069724326,0.00061944034],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044630293,0.00052967796,0.016402248,0.00018622939,0.0001460611,0.00019799868,0.000121791665,0.10275731,0.06741325,0.0031693403,0.003327234,0.80530256],"study_design_scores_gemma":[0.000004265376,0.00006666217,0.0030314457,0.0000106737825,0.000019408311,0.000043023138,0.000037460122,0.98674345,0.008870773,0.0005235426,0.00063918805,0.000010117411],"about_ca_topic_score_codex":0.0018278611,"about_ca_topic_score_gemma":0.0010693388,"teacher_disagreement_score":0.0018278611,"about_ca_system_score_codex":0.00027321064,"about_ca_system_score_gemma":0.00051134685,"threshold_uncertainty_score":0.0073076487},"labels":[],"label_agreement":null},{"id":"W2612601779","doi":"10.1080/01431161.2017.1317933","title":"Accurate crop-type classification using multi-temporal optical and multi-polarization SAR data in an object-based image analysis framework","year":2017,"lang":"en","type":"article","venue":"International Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Agriculture and Agri-Food Canada","funders":"Canadian Space Agency","keywords":"Remote sensing; Computer science; Object based; Pattern recognition (psychology); Contextual image classification; Artificial intelligence; Optical image; Object (grammar); Data mining; Computer vision; Image (mathematics); Geology","score_opus":0.10495525452031046,"score_gpt":0.37848541891255827,"score_spread":0.2735301643922478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2612601779","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1432965,0.0005403764,0.85226655,0.00015200798,0.000058298483,0.00010918735,0.00033751345,0.001386821,0.0018527656],"genre_scores_gemma":[0.46601892,0.0004404598,0.53090626,0.000097001284,0.00007324283,0.00009116174,0.0008338347,0.00008767399,0.0014515192],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996136,0.000052105395,0.000025546367,0.00010936409,0.00014237658,0.000057062654],"domain_scores_gemma":[0.9996131,0.000057140987,0.00006802293,0.00005368718,0.00018345428,0.000024549141],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00088065746,0.0006475908,0.00067991414,0.0022689202,0.00025051663,0.0010991676,0.0006177627,0.0005710588,0.0004009175],"category_scores_gemma":[0.0006407281,0.00027296224,0.00083237997,0.0011687096,0.00028884923,0.0012319097,0.00043441408,0.00040998994,0.0003970036],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022464317,0.00028424137,0.016989615,0.00021992199,0.00022704204,0.00032366638,0.00018633735,0.095264375,0.18156122,0.0023359049,0.0019457709,0.7004372],"study_design_scores_gemma":[0.00001585993,0.00009868042,0.021987515,0.000023964481,0.0001280427,0.00022548529,0.00016878937,0.9308458,0.041426733,0.0018213674,0.003211125,0.000046704015],"about_ca_topic_score_codex":0.0040418804,"about_ca_topic_score_gemma":0.0059183026,"teacher_disagreement_score":0.0040418804,"about_ca_system_score_codex":0.0003794531,"about_ca_system_score_gemma":0.0006359905,"threshold_uncertainty_score":0.008036733},"labels":[],"label_agreement":null},{"id":"W2620065579","doi":"10.1007/978-3-319-59876-5_66","title":"Non-dictionary Aided Sparse Unmixing of Hyperspectral Images via Weighted Nonnegative Matrix Factorization","year":2017,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Hyperspectral imaging; Computer science; Non-negative matrix factorization; Multiplicative function; Pattern recognition (psychology); Matrix decomposition; Pixel; Matrix (chemical analysis); Set (abstract data type); Artificial intelligence; Multiplicative noise; Sparse matrix; Noise (video); Algorithm; Image (mathematics); Mathematics","score_opus":0.013698609520878922,"score_gpt":0.24022965815926867,"score_spread":0.22653104863838974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2620065579","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047718966,0.0002567654,0.9930669,0.00007169639,0.000057723675,0.000021432583,0.00006564816,0.00019755705,0.0014904002],"genre_scores_gemma":[0.07715761,0.0007993401,0.9142348,0.00010497738,0.000093767325,0.00011079386,0.0006687258,0.00023780476,0.0065921736],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99964845,0.000074091,0.000015330013,0.00007256017,0.00016167459,0.000027859267],"domain_scores_gemma":[0.9996228,0.00016020898,0.00004279075,0.000074069954,0.00008424436,0.00001590196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043392778,0.0010127467,0.00072819786,0.00040176112,0.00024820736,0.00075264316,0.0008610344,0.0006895278,0.00293337],"category_scores_gemma":[0.0013306615,0.00042681166,0.0009317181,0.0008615617,0.0004907084,0.0018702148,0.0015696095,0.0014287982,0.0014547269],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022823273,0.00015421608,0.0003168382,0.00055402407,0.00011613706,0.0001554772,0.00021237943,0.1410968,0.15589726,0.036252752,0.008811988,0.656204],"study_design_scores_gemma":[0.000009599693,0.00005639455,0.00020792973,0.000019491219,0.00001956258,0.00016878358,0.000040430947,0.960492,0.018790064,0.014439139,0.0057352274,0.000021367836],"about_ca_topic_score_codex":0.00070354185,"about_ca_topic_score_gemma":0.0017029081,"teacher_disagreement_score":0.00293337,"about_ca_system_score_codex":0.00018456604,"about_ca_system_score_gemma":0.00041256403,"threshold_uncertainty_score":0.00981313},"labels":[],"label_agreement":null},{"id":"W2620830647","doi":"10.1109/jstars.2017.2706190","title":"Spectral–Spatial Semisupervised Hyperspectral Classification Using Adaptive Neighborhood","year":2017,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Università degli Studi di Pavia","keywords":"Hyperspectral imaging; Pattern recognition (psychology); Spatial analysis; Artificial intelligence; Pixel; Computer science; Graph; Support vector machine; Contextual image classification; Mathematics; Computer vision; Image (mathematics); Statistics","score_opus":0.05358431907304996,"score_gpt":0.25235600803791886,"score_spread":0.1987716889648689,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2620830647","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034892544,0.00029594544,0.9625066,0.000110470464,0.000024383318,0.000054344335,0.00008612536,0.00082869764,0.0012008193],"genre_scores_gemma":[0.60324425,0.0003088187,0.3922566,0.00020429393,0.00010115559,0.00020685609,0.0008057566,0.0001906611,0.0026815184],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993339,0.0002218356,0.000037396225,0.00018854055,0.00017947891,0.000038771497],"domain_scores_gemma":[0.9988851,0.000358726,0.0001980884,0.00020489046,0.0003116487,0.000041527488],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007471627,0.0006028067,0.000747962,0.0012741103,0.0004202626,0.00053611695,0.0010559276,0.0006858727,0.000713421],"category_scores_gemma":[0.0016120349,0.00023886739,0.00070842775,0.0009476881,0.0006874924,0.0012630876,0.000804215,0.0004515372,0.00036685998],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003249979,0.00026267552,0.0062100925,0.00033377283,0.00028097027,0.00021526948,0.0002737057,0.23881353,0.038440987,0.016928788,0.007651796,0.69026345],"study_design_scores_gemma":[0.0000097720185,0.000034747325,0.0008136751,0.0000074775267,0.00001776474,0.00008143656,0.00003266473,0.98802406,0.004519187,0.0051399665,0.0013061202,0.0000131278875],"about_ca_topic_score_codex":0.0019615877,"about_ca_topic_score_gemma":0.0037147542,"teacher_disagreement_score":0.0019615877,"about_ca_system_score_codex":0.00040407412,"about_ca_system_score_gemma":0.0004950171,"threshold_uncertainty_score":0.0039514303},"labels":[],"label_agreement":null},{"id":"W2724081917","doi":"10.1109/jstars.2017.2711360","title":"Domain Adaptation Using Representation Learning for the Classification of Remote Sensing Images","year":2017,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":78,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Domain adaptation; Machine learning; Hyperspectral imaging; Principal component analysis; Contextual image classification; Feature learning; Invariant (physics); Artificial neural network; Representation (politics); Kernel (algebra); Deep learning; Image (mathematics); Classifier (UML); Mathematics","score_opus":0.07332054899123384,"score_gpt":0.2873958585733739,"score_spread":0.21407530958214005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2724081917","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025219208,0.0005516456,0.97257936,0.00016731516,0.00003471736,0.0000257756,0.00004480446,0.00036254994,0.001014768],"genre_scores_gemma":[0.7140678,0.0009499661,0.28156158,0.00016751658,0.0000924707,0.000098116914,0.0004738576,0.00007815732,0.0025105812],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99964654,0.00011863116,0.0000125166,0.00009411464,0.00008891064,0.000039297083],"domain_scores_gemma":[0.9994523,0.00025504216,0.00007937813,0.00010643365,0.00008624299,0.000020670683],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007924145,0.00047630427,0.00042190377,0.0004482207,0.00016500674,0.0004951915,0.00052856683,0.000526306,0.0006890006],"category_scores_gemma":[0.0018392439,0.00014871407,0.0005933744,0.0006170568,0.0005036617,0.0008397343,0.00071526755,0.0011918588,0.00032567608],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015058284,0.00014711327,0.0015850035,0.000106148305,0.00008105567,0.00009725001,0.00011110592,0.5903775,0.021174734,0.01620031,0.0031787178,0.36679035],"study_design_scores_gemma":[0.0000016305737,0.000018375542,0.00021264055,0.0000037942937,0.000004934911,0.000017318767,0.000007714668,0.993204,0.0023214114,0.0036145533,0.00058883976,0.00000474503],"about_ca_topic_score_codex":0.0014452375,"about_ca_topic_score_gemma":0.0011742265,"teacher_disagreement_score":0.0014452375,"about_ca_system_score_codex":0.00037967018,"about_ca_system_score_gemma":0.00041594735,"threshold_uncertainty_score":0.004190743},"labels":[],"label_agreement":null},{"id":"W2728080634","doi":"10.29252/jgit.5.1.89","title":"Evaluation of SLIC superpixel and DBSCAN clustering algorithms in segmentation of ultra-high resolution remote sensing imageryover urban areas","year":2017,"lang":"en","type":"article","venue":"Journal of Geospatial Information Technology","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"DBSCAN; Cluster analysis; Computer science; Segmentation; Remote sensing; Artificial intelligence; High resolution; Pattern recognition (psychology); Resolution (logic); Computer vision; Geography; Fuzzy clustering; Canopy clustering algorithm","score_opus":0.016737421502684154,"score_gpt":0.2595445872286255,"score_spread":0.24280716572594135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2728080634","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8700142,0.0030156018,0.119528554,0.00026876433,0.00020038117,0.00028005656,0.00064119895,0.0019523514,0.004098985],"genre_scores_gemma":[0.9062247,0.00072473113,0.0893614,0.000070263275,0.000035673736,0.00007112875,0.0017893844,0.00020698275,0.0015157436],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981018,0.0005166247,0.0001444052,0.00029991617,0.0007556621,0.00018155687],"domain_scores_gemma":[0.99681926,0.0012409063,0.00019149104,0.00025454667,0.0013020595,0.00019180686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029150278,0.0014033114,0.0011795543,0.0032886425,0.0008760105,0.0017693301,0.0014924848,0.0012856066,0.0018685119],"category_scores_gemma":[0.004981934,0.0003275106,0.0007664498,0.002625562,0.0005858964,0.0012319167,0.0007779807,0.00043211505,0.00037809327],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0051876423,0.0010314364,0.01835947,0.0009244299,0.00068675197,0.00023372714,0.00047921846,0.4862291,0.02541888,0.0031947948,0.004635092,0.45361954],"study_design_scores_gemma":[0.000037616566,0.0003607901,0.006671057,0.000015151966,0.00007510148,0.000061828425,0.00021860749,0.98134077,0.010037113,0.00052723126,0.0006300923,0.000024671002],"about_ca_topic_score_codex":0.031486176,"about_ca_topic_score_gemma":0.029091341,"teacher_disagreement_score":0.031486176,"about_ca_system_score_codex":0.0014689419,"about_ca_system_score_gemma":0.0012757903,"threshold_uncertainty_score":0.0626058},"labels":[],"label_agreement":null},{"id":"W2730843485","doi":"10.3390/rs9070696","title":"Fusion of Multispectral Imagery and Spectrometer Data in UAV Remote Sensing","year":2017,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"A&L Canada Laboratories (Canada); Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Remote sensing; Multispectral image; Imaging spectrometer; Sensor fusion; Spectrometer; Environmental science; Computer science; Geology; Artificial intelligence; Optics; Physics","score_opus":0.038469004454926035,"score_gpt":0.27848361957543666,"score_spread":0.24001461512051062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2730843485","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83448595,0.00015865476,0.16385567,0.00005258932,0.000034806788,0.000054720073,0.000084018335,0.0002928674,0.0009806822],"genre_scores_gemma":[0.93800807,0.000032021515,0.06168727,0.000009499282,0.0000035115515,0.000020123218,0.00008395372,0.000013275315,0.0001423896],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99950933,0.00013900573,0.000028889817,0.00008287866,0.00018715094,0.000052776115],"domain_scores_gemma":[0.999673,0.00012312683,0.000047449532,0.000037774367,0.000104246355,0.000014384275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079416035,0.0005062785,0.00031506634,0.000583,0.00023361291,0.00035334847,0.00030564572,0.00046398918,0.00031918532],"category_scores_gemma":[0.0011186976,0.00025665993,0.00054403825,0.00066208094,0.00029215,0.0006038947,0.00036724735,0.0002555114,0.00010520411],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005610391,0.00025838468,0.016612802,0.00013123652,0.00013021214,0.00030536987,0.00017688375,0.8177771,0.08215349,0.0007902368,0.00037049825,0.080732726],"study_design_scores_gemma":[0.000012221772,0.0001440282,0.007652689,0.000005156555,0.000019786314,0.00004081488,0.00003818002,0.957162,0.034403026,0.00023985741,0.00026860833,0.0000136403405],"about_ca_topic_score_codex":0.0038124633,"about_ca_topic_score_gemma":0.003280651,"teacher_disagreement_score":0.0038124633,"about_ca_system_score_codex":0.00043635268,"about_ca_system_score_gemma":0.0002797145,"threshold_uncertainty_score":0.0075805187},"labels":[],"label_agreement":null},{"id":"W2734499646","doi":"10.22075/mseee.2015.249","title":"Improving the RX Anomaly Detection Algorithm for Hyperspectral Images using FFT","year":2015,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Hyperspectral imaging; Fast Fourier transform; Detector; Computer science; Algorithm; Anomaly detection; Dimensionality reduction; Reduction (mathematics); Artificial intelligence; Imaging spectrometer; Computer vision; Spectrometer; Mathematics; Optics; Telecommunications; Physics","score_opus":0.03392966991321122,"score_gpt":0.24241987386962183,"score_spread":0.2084902039564106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2734499646","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032966163,0.00017503684,0.96319556,0.00009356644,0.00004646054,0.00004494606,0.00006848622,0.0027895726,0.0006201442],"genre_scores_gemma":[0.11237812,0.00019217805,0.885286,0.000043406755,0.000044230597,0.00007190763,0.0003749705,0.0001847813,0.0014244306],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99934894,0.000078073266,0.000057387988,0.00016689846,0.0002982682,0.000050346825],"domain_scores_gemma":[0.99887246,0.00036363228,0.00013202906,0.00014228364,0.0004563736,0.000033104203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009851763,0.0009489241,0.00089005585,0.0018174388,0.0004280762,0.00071953435,0.0009041184,0.000539937,0.001662978],"category_scores_gemma":[0.0030693333,0.0002906268,0.0008441424,0.0011583009,0.00037813885,0.0015317949,0.00069519033,0.001038213,0.0010044752],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018942764,0.00013573152,0.0042699515,0.00013844186,0.000088507855,0.00009878135,0.00012740974,0.040110707,0.09074073,0.00292521,0.0026807457,0.8584943],"study_design_scores_gemma":[0.000027488897,0.00009180293,0.0035658346,0.000009929307,0.000028768938,0.00028133226,0.000044949626,0.94527227,0.045368228,0.0014607453,0.0038194158,0.000029333863],"about_ca_topic_score_codex":0.0025699146,"about_ca_topic_score_gemma":0.0022704112,"teacher_disagreement_score":0.0025699146,"about_ca_system_score_codex":0.00041195468,"about_ca_system_score_gemma":0.0007412201,"threshold_uncertainty_score":0.0055631995},"labels":[],"label_agreement":null},{"id":"W2735042947","doi":"10.1016/j.isprsjprs.2017.06.013","title":"Change detection using landsat time series: A review of frequencies, preprocessing, algorithms, and applications","year":2017,"lang":"en","type":"review","venue":"ISPRS Journal of Photogrammetry and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":843,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Wageningen University and Research; U.S. Geological Survey; University of British Columbia","keywords":"Change detection; Computer science; Algorithm; Thresholding; Preprocessor; Pixel; Series (stratigraphy); Univariate; Artificial intelligence; Time series; Remote sensing; Segmentation; Multivariate statistics; Image (mathematics); Machine learning; Geology","score_opus":0.07904503923903336,"score_gpt":0.3333358998317321,"score_spread":0.2542908605926988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2735042947","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012779133,0.98622966,0.009099424,0.00052685355,0.0005485616,0.000037804002,0.00045229783,0.00011653061,0.0017109194],"genre_scores_gemma":[0.004895076,0.98061186,0.011954621,0.00033044902,0.0007191039,0.000038633898,0.00057499437,0.0000325443,0.0008427619],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993327,0.000066061926,0.00010548494,0.00018434502,0.00027969835,0.00003169625],"domain_scores_gemma":[0.9979018,0.001086485,0.0001948445,0.0000930323,0.0006802986,0.0000434997],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016542933,0.0014105573,0.001996822,0.0054565235,0.00029009915,0.0015829336,0.00148481,0.0010713231,0.0021670186],"category_scores_gemma":[0.0027565814,0.0005107723,0.0011892386,0.008688334,0.00057371065,0.0023933311,0.00058682327,0.0010300081,0.001670639],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003954517,0.00005295929,0.00075551996,0.0073215947,0.00009245359,0.000037767462,0.000029628729,0.00060821173,0.0018082478,0.0012020299,0.008272271,0.9797799],"study_design_scores_gemma":[0.00003330123,0.00037048222,0.012316176,0.007894559,0.0010515918,0.0022625807,0.0003270408,0.0057810727,0.010810843,0.009550794,0.9493554,0.00024612428],"about_ca_topic_score_codex":0.0027937016,"about_ca_topic_score_gemma":0.0035356006,"teacher_disagreement_score":0.0054565235,"about_ca_system_score_codex":0.0005585603,"about_ca_system_score_gemma":0.0013524102,"threshold_uncertainty_score":0.008748889},"labels":[],"label_agreement":null},{"id":"W2745252301","doi":"10.1109/igarss.2017.8127330","title":"Deep residual networks for hyperspectral image classification","year":2017,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":117,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Residual; Computer science; Artificial intelligence; Convolutional neural network; Normalization (sociology); Hyperspectral imaging; Deep learning; Pattern recognition (psychology); Contextual image classification; Embedding; Regularization (linguistics); Deep neural networks; Dimensionality reduction; Feature learning; Image (mathematics); Algorithm","score_opus":0.03160568644587343,"score_gpt":0.2710259716334991,"score_spread":0.2394202851876257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2745252301","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056906182,0.0019669016,0.93351513,0.00044206696,0.00009468024,0.000055247358,0.00044218564,0.0032022018,0.003375384],"genre_scores_gemma":[0.6880141,0.0012400803,0.30061802,0.00024599588,0.0000880854,0.00013069827,0.001979667,0.00021731098,0.007465971],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999686,0.000064365195,0.000019102421,0.00008162941,0.000107209526,0.000041731884],"domain_scores_gemma":[0.9996247,0.00012203583,0.00006531734,0.00006444799,0.00010703735,0.000016490887],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007099251,0.0008386269,0.00046628213,0.0005664382,0.000228149,0.0005707211,0.0008211543,0.00059427007,0.001766939],"category_scores_gemma":[0.00147063,0.00026168535,0.00055894564,0.0006792668,0.0003548346,0.0010170368,0.0006179841,0.0012003679,0.00071330374],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017388006,0.00019785423,0.0024603955,0.000161394,0.00013697447,0.0000919747,0.00007085834,0.44274297,0.028633757,0.010134876,0.006520733,0.5086743],"study_design_scores_gemma":[0.000003189624,0.000024367337,0.000440958,0.000007746209,0.000007805787,0.000013520803,0.000008246064,0.98968315,0.005520069,0.0032320353,0.0010519609,0.000006849984],"about_ca_topic_score_codex":0.006155328,"about_ca_topic_score_gemma":0.0076432554,"teacher_disagreement_score":0.006155328,"about_ca_system_score_codex":0.0006061257,"about_ca_system_score_gemma":0.0005676886,"threshold_uncertainty_score":0.012239039},"labels":[],"label_agreement":null},{"id":"W2745791577","doi":"10.3390/rs9090872","title":"Multiscale Union Regions Adaptive Sparse Representation for Hyperspectral Image Classification","year":2017,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"Università degli Studi di Pavia; National Natural Science Foundation of China; Jet Propulsion Laboratory; Purdue University; National Aeronautics and Space Administration","keywords":"Pattern recognition (psychology); Sparse approximation; Computer science; Hyperspectral imaging; Pixel; Artificial intelligence; Classifier (UML); Representation (politics)","score_opus":0.0771561299403723,"score_gpt":0.30757235059211085,"score_spread":0.23041622065173856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2745791577","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013223573,0.00034957987,0.9853672,0.0001131509,0.00002114928,0.000019072195,0.00005187698,0.0002921604,0.00056220306],"genre_scores_gemma":[0.44905692,0.0009021505,0.5462308,0.00022544549,0.00016351444,0.00013265996,0.00072058046,0.000121675504,0.002446174],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994936,0.00012739706,0.000023067956,0.00011509047,0.00019377717,0.000047017897],"domain_scores_gemma":[0.9994349,0.00022457298,0.0000976105,0.000076535165,0.00014278035,0.000023689172],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007273572,0.00045915227,0.000755403,0.00084254803,0.00024291487,0.00042813047,0.0007335946,0.00061370904,0.0010516184],"category_scores_gemma":[0.0019716364,0.00021192375,0.00071241474,0.0012361776,0.00040136755,0.0009578089,0.000709139,0.0007759735,0.00039411962],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024520946,0.00013664945,0.0016680622,0.00017069555,0.00010351264,0.00015959115,0.0001703482,0.22083934,0.055312973,0.018179828,0.0074134646,0.6956003],"study_design_scores_gemma":[0.0000068841823,0.000037315334,0.00044208497,0.00000590537,0.000015786569,0.00006217677,0.000017486442,0.99048376,0.0047620106,0.0028244574,0.0013336055,0.000008458109],"about_ca_topic_score_codex":0.001962473,"about_ca_topic_score_gemma":0.001795156,"teacher_disagreement_score":0.001962473,"about_ca_system_score_codex":0.00031681455,"about_ca_system_score_gemma":0.00038350542,"threshold_uncertainty_score":0.0039021373},"labels":[],"label_agreement":null},{"id":"W2760542128","doi":"10.5194/isprs-archives-xlii-4-w4-91-2017","title":"GRAPH-BASED SEMI-SUPERVISED HYPERSPECTRAL IMAGE CLASSIFICATION USING SPATIAL INFORMATION","year":2017,"lang":"en","type":"article","venue":"˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Hyperspectral imaging; Pattern recognition (psychology); Computer science; Graph; Spatial analysis; Artificial intelligence; Support vector machine; Contextual image classification; Data mining; Mathematics; Image (mathematics); Statistics","score_opus":0.027495732507284713,"score_gpt":0.26556162822964946,"score_spread":0.23806589572236475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2760542128","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08421417,0.00030676118,0.9106241,0.00024243018,0.000046399182,0.000093209426,0.0002446538,0.0022491424,0.0019791303],"genre_scores_gemma":[0.76301146,0.00019507285,0.23225996,0.0001881954,0.00005683602,0.00013117559,0.0012544594,0.00015307225,0.0027497686],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993224,0.00019186849,0.00003196445,0.00018812028,0.0002176825,0.000048090333],"domain_scores_gemma":[0.9988555,0.00035827738,0.00017710714,0.00015383285,0.00040655606,0.000048820442],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006169948,0.00071809854,0.00081147876,0.001632628,0.00037319798,0.0006338324,0.0009468424,0.0005609617,0.0011227352],"category_scores_gemma":[0.0014381915,0.00024187464,0.0008777413,0.000990413,0.0005912131,0.0011057267,0.0006207908,0.0005651957,0.00046099484],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033938207,0.00030570978,0.004670633,0.00030418488,0.00025235326,0.00014138459,0.00020172074,0.35457295,0.03554929,0.0056540784,0.006304772,0.5917036],"study_design_scores_gemma":[0.000005286219,0.000025341516,0.00067409803,0.0000049347796,0.000011483437,0.000029075507,0.000021395981,0.9938834,0.0031613975,0.0017598093,0.0004158185,0.000008072321],"about_ca_topic_score_codex":0.0034500363,"about_ca_topic_score_gemma":0.005311351,"teacher_disagreement_score":0.0034500363,"about_ca_system_score_codex":0.00059120666,"about_ca_system_score_gemma":0.00060389494,"threshold_uncertainty_score":0.0068598986},"labels":[],"label_agreement":null},{"id":"W2766372927","doi":"10.1109/tgrs.2017.2758359","title":"An Energy-Based Model Encoding Nonlocal Pairwise Pixel Interactions for Multisensor Change Detection","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":76,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Centre National d’Etudes Spatiales","keywords":"Computer science; Artificial intelligence; Robustness (evolution); Change detection; Pattern recognition (psychology); Pixel; Pairwise comparison; Thresholding; Segmentation; Feature (linguistics); Computer vision; Image (mathematics)","score_opus":0.056068904789857814,"score_gpt":0.28756743490183356,"score_spread":0.23149853011197574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766372927","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063946643,0.00017547516,0.9927651,0.00008118111,0.000018129042,0.000017044275,0.000029176741,0.00007508182,0.00044405038],"genre_scores_gemma":[0.69795114,0.0008252199,0.29420996,0.00023506118,0.00010244531,0.00031504137,0.00034164396,0.00017772462,0.0058416743],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99958295,0.0000978663,0.000024802783,0.00013382989,0.0001233655,0.00003719449],"domain_scores_gemma":[0.9994665,0.00027123754,0.000088861656,0.000073000854,0.000081242084,0.000019133997],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007772379,0.00077103754,0.0008348198,0.00068123016,0.000260311,0.0008521281,0.001921151,0.0013671643,0.00133568],"category_scores_gemma":[0.0022253594,0.00047296556,0.00079828553,0.001051088,0.0007337162,0.0020446049,0.0009975382,0.0011422123,0.0004187436],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060362203,0.000055734843,0.0006072915,0.00009683153,0.000058708556,0.00011422586,0.00008191991,0.9174789,0.008968679,0.013789172,0.0005424538,0.05814567],"study_design_scores_gemma":[0.000001043531,0.000008271911,0.0000845079,0.0000020969248,0.0000044665508,0.000014925108,0.000004013879,0.99762946,0.000463439,0.0015833772,0.00020025739,0.0000042088927],"about_ca_topic_score_codex":0.0029320342,"about_ca_topic_score_gemma":0.0029112133,"teacher_disagreement_score":0.0029320342,"about_ca_system_score_codex":0.00069460855,"about_ca_system_score_gemma":0.00053453515,"threshold_uncertainty_score":0.0058299303},"labels":[],"label_agreement":null},{"id":"W2767819622","doi":"10.1109/tgrs.2017.2762597","title":"Multiple Kernel Learning for Remote Sensing Image Classification","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Multiple kernel learning; Computer science; Kernel (algebra); Artificial intelligence; Context (archaeology); Selection (genetic algorithm); Feature selection; Machine learning; Pattern recognition (psychology); Categorization; Support vector machine; Kernel method; Mathematics","score_opus":0.03166235808655278,"score_gpt":0.268625322168372,"score_spread":0.23696296408181922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2767819622","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004031807,0.0015354345,0.9932254,0.0002006324,0.000036346242,0.000018469547,0.000026321311,0.00028187913,0.00064378703],"genre_scores_gemma":[0.44454753,0.002698232,0.54830337,0.00020485968,0.00025806556,0.0001359919,0.0003422173,0.0001859335,0.0033237678],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99844223,0.00056160736,0.00009580885,0.0002882098,0.00050492556,0.00010723473],"domain_scores_gemma":[0.99812895,0.00091335335,0.00022894681,0.00028773988,0.00039368856,0.000047295343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019875956,0.0007809968,0.0011660602,0.001373314,0.0004131477,0.0014668844,0.0013120826,0.0010728479,0.0012903363],"category_scores_gemma":[0.0064556217,0.0003170605,0.00082730065,0.0019258189,0.00095692504,0.0024156522,0.0015134716,0.0015801964,0.0010299045],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018037438,0.00012554978,0.0012350128,0.0005907048,0.00017751004,0.00012596557,0.00017227177,0.36200663,0.013422567,0.089211576,0.0045965714,0.5281553],"study_design_scores_gemma":[0.0000030750805,0.000021023743,0.00024136425,0.000009577847,0.0000094785655,0.000038580285,0.000012040127,0.9783167,0.002141581,0.017502395,0.0016895954,0.000014523831],"about_ca_topic_score_codex":0.0016414962,"about_ca_topic_score_gemma":0.00081139454,"teacher_disagreement_score":0.0019875956,"about_ca_system_score_codex":0.0010927488,"about_ca_system_score_gemma":0.00062661147,"threshold_uncertainty_score":0.0105115175},"labels":[],"label_agreement":null},{"id":"W2771668473","doi":"10.15353/vsnl.v3i1.178","title":"Hyperspectral image classification using deep convolutional neural networks","year":2017,"lang":"en","type":"article","venue":"Journal of Computational Vision and Imaging Systems","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Hyperspectral imaging; Artificial intelligence; Pixel; Convolutional neural network; Pattern recognition (psychology); Computer science; Deep learning; Curse of dimensionality; Process (computing); Feature (linguistics); Spectral signature; Remote sensing; Geography","score_opus":0.021865555687465024,"score_gpt":0.2844800363320834,"score_spread":0.2626144806446184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2771668473","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.109532505,0.0019198221,0.87853426,0.00040375622,0.00013281911,0.000108178865,0.0004823227,0.003192836,0.005693523],"genre_scores_gemma":[0.77069014,0.0013595776,0.21838653,0.00023344465,0.00009606698,0.00010604732,0.0017924012,0.00008699429,0.007248775],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99973077,0.000029826762,0.0000145914455,0.000080744205,0.0000952287,0.000048907237],"domain_scores_gemma":[0.99978954,0.00004937351,0.00004201568,0.00003363393,0.00007457709,0.00001080376],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000412485,0.0008092884,0.00040969046,0.0010912134,0.00022472406,0.00070352847,0.0006016197,0.0005584957,0.0011468896],"category_scores_gemma":[0.0006950198,0.00024105092,0.0005378044,0.0008415029,0.00034244178,0.0010894404,0.0006274242,0.00070863066,0.00060880627],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018252141,0.00026132024,0.004246481,0.00018722884,0.00017691022,0.00010474679,0.000063955544,0.22073226,0.055457614,0.0049986886,0.0058375252,0.7077507],"study_design_scores_gemma":[0.0000028634663,0.000021005031,0.0010258654,0.000009974502,0.000011961985,0.000018135743,0.000010078142,0.9874958,0.009045468,0.0013303199,0.0010210993,0.000007419833],"about_ca_topic_score_codex":0.008175384,"about_ca_topic_score_gemma":0.009479895,"teacher_disagreement_score":0.008175384,"about_ca_system_score_codex":0.0007110504,"about_ca_system_score_gemma":0.00054080534,"threshold_uncertainty_score":0.016255558},"labels":[],"label_agreement":null},{"id":"W2774189425","doi":"10.23977/jeis.2017.22012","title":"A Novel Histogram-Based Fuzzy Clustering Method for Multispectral Image Segmentation","year":2017,"lang":"en","type":"article","venue":"Journal of Electronics and Information Science","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Artificial intelligence; Cluster analysis; Pattern recognition (psychology); Multispectral image; Histogram; Computer science; Pixel; Computer vision; Fuzzy clustering; Multispectral pattern recognition; Image segmentation; Region growing; Fuzzy logic; FLAME clustering; Segmentation; Scale-space segmentation; Image (mathematics); Canopy clustering algorithm","score_opus":0.018093363041182458,"score_gpt":0.30534812130956873,"score_spread":0.28725475826838626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2774189425","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036129733,0.00033008767,0.9941399,0.000057430807,0.00006055868,0.000040262177,0.000051981333,0.00067053834,0.0010362198],"genre_scores_gemma":[0.11141751,0.0005668292,0.88298935,0.000104701365,0.00011007206,0.00013773331,0.00029228276,0.00017262979,0.004208928],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992902,0.00006345904,0.000037208185,0.00017685756,0.00038345958,0.000048845046],"domain_scores_gemma":[0.9996419,0.00006151293,0.000034712943,0.000036715508,0.0002058335,0.00001943346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047090295,0.000654589,0.00087093195,0.0021121546,0.0006464553,0.00073318114,0.0015112853,0.0009606933,0.002592905],"category_scores_gemma":[0.00075255247,0.00038417688,0.00096133153,0.0018133001,0.00050721504,0.0011890653,0.0005479768,0.00065459247,0.0011311728],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015046829,0.0000937703,0.0006562721,0.0003637293,0.00011781413,0.000115958836,0.00015887618,0.07613237,0.080094814,0.0069276,0.0048711738,0.830317],"study_design_scores_gemma":[0.000028197832,0.00007831611,0.0015041855,0.000023526847,0.00004970503,0.00035748942,0.00006149342,0.9423782,0.040660694,0.0037642976,0.011007297,0.0000865636],"about_ca_topic_score_codex":0.006498692,"about_ca_topic_score_gemma":0.006867933,"teacher_disagreement_score":0.006498692,"about_ca_system_score_codex":0.0008461915,"about_ca_system_score_gemma":0.0010867873,"threshold_uncertainty_score":0.012921751},"labels":[],"label_agreement":null},{"id":"W2783096881","doi":"10.1080/10095020.2017.1399674","title":"Object-based classification of hyperspectral data using Random Forest algorithm","year":2018,"lang":"en","type":"article","venue":"Geo-spatial Information Science","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":108,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"University of Zanjan; University of Houston; National Science Foundation","keywords":"Hyperspectral imaging; Random forest; Computer science; Pixel; Support vector machine; Artificial intelligence; Pattern recognition (psychology); Segmentation; Classifier (UML); Land cover; Imaging spectrometer; Remote sensing; Spectrometer; Land use; Geography","score_opus":0.049820347733402555,"score_gpt":0.28974459558745647,"score_spread":0.23992424785405392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2783096881","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013238682,0.00048812735,0.98434997,0.000051500912,0.000039772764,0.000057608526,0.00009498412,0.0012078203,0.00047155967],"genre_scores_gemma":[0.22375412,0.00074452645,0.7720937,0.00010389605,0.00013737303,0.00024407788,0.0012890334,0.00014271708,0.0014906634],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990545,0.00015631557,0.00006222745,0.00025238196,0.00035519575,0.000119538076],"domain_scores_gemma":[0.99947506,0.00018014875,0.000084132924,0.000050135448,0.00019140523,0.000019187702],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012886573,0.0011522109,0.0015872258,0.0030671502,0.00045958534,0.00073506235,0.0011634374,0.0009851308,0.00086583913],"category_scores_gemma":[0.0014055676,0.0003345917,0.0015295468,0.0021697858,0.00043487834,0.0013945146,0.0004914824,0.0007838192,0.0006350424],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019789152,0.0002120658,0.0036018335,0.00023369458,0.00022780323,0.0001519775,0.000101897414,0.1743818,0.02430431,0.0035880185,0.0035294977,0.7894693],"study_design_scores_gemma":[0.000015784877,0.00004556429,0.0012419032,0.000019485517,0.000031515207,0.000080732876,0.000020842956,0.9909276,0.0041343966,0.0020985247,0.0013635384,0.00002014789],"about_ca_topic_score_codex":0.004809303,"about_ca_topic_score_gemma":0.00392008,"teacher_disagreement_score":0.004809303,"about_ca_system_score_codex":0.00043956295,"about_ca_system_score_gemma":0.00062412425,"threshold_uncertainty_score":0.009562612},"labels":[],"label_agreement":null},{"id":"W2790433324","doi":"10.1109/ipta.2017.8310138","title":"A new change detector in heterogeneous remote sensing imagery","year":2017,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Computer Research Institute of Montréal","funders":"","keywords":"Robustness (evolution); Thresholding; Computer science; Artificial intelligence; Change detection; Pattern recognition (psychology); Computer vision; Detector; Modality (human–computer interaction); Image (mathematics)","score_opus":0.047297501355186324,"score_gpt":0.26088879052364866,"score_spread":0.21359128916846234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2790433324","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025556028,0.0001706501,0.97331864,0.000081944745,0.00004481731,0.00006124322,0.00004970082,0.00025025543,0.00046669765],"genre_scores_gemma":[0.2439558,0.00016684612,0.75381243,0.00013658032,0.00008760969,0.00013671872,0.0001783145,0.00006616255,0.0014595643],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991492,0.00012694235,0.000036885718,0.00023868612,0.00038819914,0.00006010399],"domain_scores_gemma":[0.9993079,0.00024354806,0.00008655482,0.0000644009,0.0002398232,0.000057726662],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012442435,0.0005095833,0.0009725782,0.0018224292,0.000283224,0.0008082784,0.0009513194,0.0012180627,0.00068681914],"category_scores_gemma":[0.0019499608,0.00029737668,0.0006403435,0.0010196004,0.0007991773,0.0013605588,0.0007970788,0.00075535517,0.00033607648],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042947687,0.00022857217,0.003207638,0.00030496277,0.00016036269,0.00034456965,0.00014085483,0.07201293,0.27646634,0.01075877,0.0023996115,0.6335459],"study_design_scores_gemma":[0.000017019873,0.00018220735,0.0029489612,0.00000971748,0.000043069376,0.00033259875,0.00002948147,0.9425412,0.048354357,0.0025959907,0.0029049187,0.00004054971],"about_ca_topic_score_codex":0.0005481521,"about_ca_topic_score_gemma":0.0007650527,"teacher_disagreement_score":0.0018224292,"about_ca_system_score_codex":0.0004215552,"about_ca_system_score_gemma":0.00041311048,"threshold_uncertainty_score":0.006580293},"labels":[],"label_agreement":null},{"id":"W2790694152","doi":"10.1109/tgrs.2018.2809912","title":"Learning Spatial–Spectral Features for Hyperspectral Image Classification","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Hyperspectral imaging; Pattern recognition (psychology); Principal component analysis; Feature (linguistics); Artificial intelligence; Computer science; Spatial analysis; Full spectral imaging; Contextual image classification; Spectral bands; Feature extraction; Feature learning; Remote sensing; Image (mathematics); Geography","score_opus":0.015761966516694766,"score_gpt":0.24852859421338036,"score_spread":0.2327666276966856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2790694152","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01977916,0.00024876394,0.977829,0.00010620418,0.000027248527,0.000032469277,0.00013659168,0.0010680889,0.00077243487],"genre_scores_gemma":[0.40463755,0.00036924524,0.59181064,0.00011714821,0.00010731461,0.00013957861,0.0012226399,0.00014680762,0.0014491342],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99958175,0.000073969284,0.00002153785,0.00010222949,0.0001803055,0.000040220966],"domain_scores_gemma":[0.9996088,0.0001221925,0.0000699565,0.00007653769,0.000106885396,0.000015693502],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046695463,0.0007168142,0.0005185975,0.0013722263,0.0003614191,0.00043992954,0.00070650154,0.00057065743,0.0011194929],"category_scores_gemma":[0.0012819695,0.00023948538,0.0007545311,0.0015037684,0.00042847774,0.0010440308,0.0006683319,0.00077675475,0.0007079766],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009745539,0.00016390882,0.0018272443,0.00010892858,0.00006833082,0.00007806631,0.000049274702,0.08281747,0.048512887,0.004636385,0.0039138333,0.8577262],"study_design_scores_gemma":[0.0000069846265,0.000037711106,0.0016363743,0.000008566725,0.000021471224,0.00007702351,0.000029004857,0.9692134,0.019646049,0.0066150567,0.00269139,0.000016956377],"about_ca_topic_score_codex":0.0013340914,"about_ca_topic_score_gemma":0.0019596012,"teacher_disagreement_score":0.0013722263,"about_ca_system_score_codex":0.00028788808,"about_ca_system_score_gemma":0.00039961573,"threshold_uncertainty_score":0.003745079},"labels":[],"label_agreement":null},{"id":"W2791075437","doi":"10.5623/cig2017-401","title":"Building Extraction From Fused LiDAR and Hyperspectral Data using Random Forest Algorithm","year":2017,"lang":"en","type":"article","venue":"GEOMATICA","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Centre For Cold Ocean Resources Engineering; Memorial University of Newfoundland","funders":"","keywords":"Lidar; Hyperspectral imaging; Ranging; Remote sensing; Random forest; Extraction (chemistry); Computer science; Linear discriminant analysis; Algorithm; Fusion; Artificial intelligence; Geology","score_opus":0.05049766309727408,"score_gpt":0.29899538212019555,"score_spread":0.24849771902292148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2791075437","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016838469,0.00019906083,0.97889894,0.000042267737,0.00003221119,0.000039070917,0.00021940525,0.002793758,0.0009367797],"genre_scores_gemma":[0.1933049,0.00029735238,0.801699,0.0000565205,0.00004448563,0.00009629289,0.0020568124,0.00026891514,0.00217566],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995091,0.000036765985,0.000030035379,0.00014036552,0.00020564526,0.000078071935],"domain_scores_gemma":[0.9996475,0.00007767906,0.00003894864,0.00006257041,0.00015653072,0.00001669664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041331217,0.0012372396,0.0012446127,0.0025138524,0.000527749,0.0007884988,0.0010013779,0.00091341225,0.0022751181],"category_scores_gemma":[0.0008146309,0.0006856896,0.0017301398,0.0019113682,0.0002830615,0.0010469342,0.0007374061,0.00087425817,0.002706736],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017824532,0.00017445485,0.0018484581,0.00020776165,0.00013429971,0.00014929358,0.00006293529,0.09167709,0.069151,0.0020972537,0.0040246677,0.83029455],"study_design_scores_gemma":[0.000019959572,0.000045558994,0.0022437193,0.00002195308,0.00009717092,0.00019818255,0.00003321873,0.96284735,0.029108735,0.0023154647,0.003037091,0.000031493],"about_ca_topic_score_codex":0.0042676525,"about_ca_topic_score_gemma":0.0074473997,"teacher_disagreement_score":0.0042676525,"about_ca_system_score_codex":0.00025439422,"about_ca_system_score_gemma":0.0010309524,"threshold_uncertainty_score":0.008485615},"labels":[],"label_agreement":null},{"id":"W2792816540","doi":"10.3390/rs10020231","title":"The Correlation Coefficient as a Simple Tool for the Localization of Errors in Spectroscopic Imaging Data","year":2018,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; National Research Council Canada","funders":"","keywords":"Hyperspectral imaging; Remote sensing; Pixel; Correlation coefficient; Sensitivity (control systems); Imaging spectrometer; Noise (video); Region of interest; Spectrometer; Computer science; Environmental science; Optics; Artificial intelligence; Physics; Mathematics; Geology; Image (mathematics); Statistics","score_opus":0.02229379491987256,"score_gpt":0.28276922805487026,"score_spread":0.2604754331349977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792816540","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047908273,0.0012698907,0.94337666,0.00020345765,0.00028176027,0.00023139863,0.0007616228,0.002097706,0.0038692914],"genre_scores_gemma":[0.5340905,0.0006707072,0.46063495,0.00017343917,0.00018416745,0.00052789756,0.0011250988,0.0006504493,0.0019427963],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9843412,0.005672257,0.001429133,0.0028109502,0.005333595,0.00041291583],"domain_scores_gemma":[0.9654096,0.021619232,0.00346455,0.004271092,0.0049517145,0.00028381185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0120804235,0.0015783776,0.0012347014,0.008161358,0.00095142453,0.0021636381,0.0014112828,0.0014499002,0.0015607546],"category_scores_gemma":[0.040821586,0.00052088057,0.0013459943,0.008656139,0.0025191405,0.002274799,0.0021861733,0.0020131443,0.0008313036],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008528262,0.0002961458,0.11474029,0.0017639955,0.0017892318,0.0022756308,0.0020689366,0.16113244,0.10807288,0.09452905,0.012082926,0.50039566],"study_design_scores_gemma":[0.00007517819,0.0010773041,0.100459464,0.00041912755,0.00047119954,0.0038175778,0.00069220446,0.71965367,0.08358938,0.047752943,0.041295163,0.00069670373],"about_ca_topic_score_codex":0.0032397737,"about_ca_topic_score_gemma":0.0025122187,"teacher_disagreement_score":0.0120804235,"about_ca_system_score_codex":0.0011321424,"about_ca_system_score_gemma":0.0019540119,"threshold_uncertainty_score":0.06388813},"labels":[],"label_agreement":null},{"id":"W2801826172","doi":"10.3390/drones2020016","title":"Use of UAV-Borne Spectrometer for Land Cover Classification","year":2018,"lang":"en","type":"article","venue":"Drones","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; York University","keywords":"Remote sensing; Spectrometer; Hyperspectral imaging; Imaging spectrometer; Land cover; RGB color model; Environmental science; Computer science; Artificial intelligence; Geography; Land use; Physics; Optics; Engineering","score_opus":0.061122523724231256,"score_gpt":0.2594598692163722,"score_spread":0.19833734549214094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801826172","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8669645,0.0007276393,0.12628055,0.000071839466,0.000045716144,0.000066692926,0.00043860235,0.0009170029,0.0044874265],"genre_scores_gemma":[0.91981095,0.00022682837,0.078466624,0.000021876149,0.000009833702,0.00001482998,0.00034945208,0.000021236037,0.0010783527],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99985445,0.000026645534,0.0000052110863,0.000041851956,0.00005922076,0.000012546454],"domain_scores_gemma":[0.99984944,0.000034185774,0.000029084815,0.00002159939,0.00005510271,0.000010642563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002094463,0.0003620136,0.00020751533,0.0005668603,0.0001672472,0.0003536201,0.00021252695,0.00019423499,0.00067703746],"category_scores_gemma":[0.00021936695,0.00009372614,0.00013888157,0.00040958115,0.000107881446,0.0003588387,0.00016455,0.00011312343,0.00030249284],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004210321,0.00020553172,0.04044479,0.00023390494,0.00008846286,0.00026168194,0.0001368224,0.02272328,0.57460505,0.00071553,0.0012748964,0.35888898],"study_design_scores_gemma":[0.000045620865,0.00095746625,0.11551107,0.000056837518,0.00010908531,0.00085624785,0.00042278724,0.56097406,0.310314,0.0005969296,0.010102478,0.00005341968],"about_ca_topic_score_codex":0.0021371422,"about_ca_topic_score_gemma":0.0035527102,"teacher_disagreement_score":0.0021371422,"about_ca_system_score_codex":0.00017317223,"about_ca_system_score_gemma":0.00010954232,"threshold_uncertainty_score":0.004249394},"labels":[],"label_agreement":null},{"id":"W2803948506","doi":"10.1109/tgrs.2018.2829400","title":"Hyperspectral Image Classification With Stacking Spectral Patches and Convolutional Neural Networks","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Hyperspectral imaging; Pattern recognition (psychology); Convolutional neural network; Computer science; Artificial intelligence; Principal component analysis; Spectral bands; Multispectral image; Artificial neural network; Feature extraction; Remote sensing; Geology","score_opus":0.016042450399193556,"score_gpt":0.22395427646730473,"score_spread":0.20791182606811118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2803948506","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0887771,0.0005982811,0.90500706,0.00022376417,0.00007304965,0.00005495524,0.00016249332,0.0023719901,0.00273133],"genre_scores_gemma":[0.5573142,0.0006006984,0.43478078,0.00021434808,0.00008728978,0.000092356895,0.00078465935,0.000117860705,0.0060078353],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997645,0.000024951454,0.000011332233,0.000078016696,0.00007483312,0.000046411267],"domain_scores_gemma":[0.99981683,0.00003723386,0.000034817862,0.000043367785,0.000052900057,0.000014850492],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035586616,0.00090442604,0.0005132933,0.0009956914,0.00026312063,0.0006344888,0.0007359897,0.00063847756,0.0010854573],"category_scores_gemma":[0.000584925,0.00042856293,0.00074825826,0.0008833265,0.00047113324,0.0013103005,0.0009204118,0.00067319145,0.00042895137],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023909957,0.00017452773,0.0031754745,0.000100650606,0.00017410531,0.00013780459,0.0000937463,0.22337085,0.094716966,0.0057723625,0.0033355374,0.6687089],"study_design_scores_gemma":[0.0000030822468,0.00002253609,0.0009038659,0.0000049986456,0.000019693909,0.000023643848,0.000012818823,0.9839588,0.0124959415,0.0017742463,0.0007706228,0.000009646194],"about_ca_topic_score_codex":0.007108871,"about_ca_topic_score_gemma":0.010810037,"teacher_disagreement_score":0.007108871,"about_ca_system_score_codex":0.0006490561,"about_ca_system_score_gemma":0.00050854584,"threshold_uncertainty_score":0.014135003},"labels":[],"label_agreement":null},{"id":"W2804254536","doi":"10.1007/s12524-018-0752-8","title":"Collaborative Representation-Based Binary Hypothesis Model with Multi-features Learning for Target Detection in Hyperspectral Imagery","year":2018,"lang":"en","type":"article","venue":"Journal of the Indian Society of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Hyperspectral imaging; Artificial intelligence; Pattern recognition (psychology); Representation (politics); Computer science; Binary number; Pixel; Similarity (geometry); Feature (linguistics); Feature learning; Binary classification; Image (mathematics); Support vector machine; Machine learning; Mathematics","score_opus":0.01627304783246722,"score_gpt":0.24735024790920696,"score_spread":0.23107720007673974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2804254536","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025943322,0.00037879436,0.97241277,0.00020485545,0.000052915253,0.000032408512,0.00006151698,0.0003386764,0.0005746886],"genre_scores_gemma":[0.8228184,0.0003279902,0.17219213,0.0002902539,0.0001511375,0.00020915916,0.0005844727,0.00008408075,0.00334229],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99862933,0.0004723801,0.000074459655,0.00036513794,0.00026500673,0.00019382706],"domain_scores_gemma":[0.9970018,0.0019034917,0.00026367133,0.00029316085,0.00043459056,0.00010330659],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002605111,0.00079131545,0.0020653512,0.0007914783,0.00060862245,0.0013811653,0.0030414013,0.0016653427,0.0018749286],"category_scores_gemma":[0.0053758076,0.00069425855,0.0016047957,0.0010868789,0.0009802324,0.0024848378,0.0020613992,0.0024598294,0.00058971834],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00053276966,0.00046873404,0.0016993874,0.00016331702,0.00028023694,0.00012175179,0.00018781511,0.70278376,0.0052867024,0.011741434,0.0030970455,0.27363712],"study_design_scores_gemma":[0.000004822575,0.00002975749,0.00009557469,0.0000021995588,0.000010168067,0.000007725645,0.0000049032965,0.99790645,0.00039241978,0.0014772641,0.00006427992,0.00000451538],"about_ca_topic_score_codex":0.0047079236,"about_ca_topic_score_gemma":0.0034487462,"teacher_disagreement_score":0.0047079236,"about_ca_system_score_codex":0.000700011,"about_ca_system_score_gemma":0.0011093963,"threshold_uncertainty_score":0.013777316},"labels":[],"label_agreement":null},{"id":"W2807570627","doi":"10.1109/jstars.2018.2838449","title":"Evaluation of Unmixing Methods for Impervious Surface Area Extraction From Simulated EnMAP Imagery","year":2018,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Endmember; Hyperspectral imaging; Non-negative matrix factorization; Computer science; Pattern recognition (psychology); Remote sensing; Artificial intelligence; Matrix decomposition; Geography","score_opus":0.06993007167078207,"score_gpt":0.33287312756266346,"score_spread":0.2629430558918814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2807570627","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7074104,0.0007998365,0.2866232,0.00015529111,0.00009580465,0.0002366164,0.0004752438,0.0014701833,0.002733452],"genre_scores_gemma":[0.75501263,0.00030417833,0.2428159,0.00004714512,0.000018765144,0.00015209055,0.00086517213,0.00014811948,0.0006359422],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99936956,0.00017677262,0.000048271442,0.00013577584,0.00021125359,0.000058475045],"domain_scores_gemma":[0.99856853,0.00075909536,0.00010166341,0.00014161853,0.00038573268,0.000043370183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024426533,0.0013236841,0.00041013805,0.0012286332,0.00028432434,0.00053016277,0.00070258375,0.0007008654,0.0007587011],"category_scores_gemma":[0.004106915,0.00027704053,0.0006858615,0.0007050208,0.00038371698,0.0010276937,0.0005409512,0.000555414,0.00021044578],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011279015,0.00062171835,0.009791246,0.00063893537,0.00033722614,0.0001552471,0.00029907882,0.5936704,0.057910394,0.0016807261,0.0013533061,0.33241373],"study_design_scores_gemma":[0.000016919723,0.00009473736,0.002377059,0.000009387053,0.000018802211,0.000018605322,0.00003462242,0.98370475,0.013231462,0.0001817363,0.00029927868,0.000012695354],"about_ca_topic_score_codex":0.004136853,"about_ca_topic_score_gemma":0.004057969,"teacher_disagreement_score":0.004136853,"about_ca_system_score_codex":0.0003168067,"about_ca_system_score_gemma":0.00043959502,"threshold_uncertainty_score":0.012918174},"labels":[],"label_agreement":null},{"id":"W2809597898","doi":"","title":"The Impact of Sensor Characteristics and Data Availability on Remote Sensing Based Change Detection","year":2014,"lang":"en","type":"dissertation","venue":"bonndoc (University of Bonn)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Change detection; Remote sensing; Computer science; Geography","score_opus":0.03374648065228874,"score_gpt":0.2487851867401895,"score_spread":0.21503870608790077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2809597898","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.72985256,0.011429423,0.22767699,0.0063850177,0.00063019176,0.00027948822,0.002304329,0.00080083415,0.020641193],"genre_scores_gemma":[0.9505637,0.0016995524,0.04548136,0.0003583081,0.00016140619,0.00008918654,0.00071633066,0.00015844742,0.00077167153],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98620725,0.0065452885,0.000839051,0.0024801672,0.0033976703,0.0005305765],"domain_scores_gemma":[0.7689352,0.20555781,0.008520253,0.007810701,0.008582591,0.00059341424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016899206,0.00062772806,0.00076141657,0.0012355585,0.0006375447,0.002221936,0.0013673166,0.0013741571,0.001431049],"category_scores_gemma":[0.09285457,0.00071548985,0.00061659445,0.0025024714,0.0012660186,0.0042502503,0.0013333363,0.0013307083,0.00056017446],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002463963,0.00052021706,0.29170358,0.002332738,0.0007939811,0.0013031543,0.0012899217,0.29813933,0.034073766,0.013824627,0.004533982,0.34902072],"study_design_scores_gemma":[0.00013613587,0.000984466,0.28597665,0.0005076739,0.00036425074,0.0024785541,0.0019887881,0.6380348,0.03970065,0.017792216,0.011677208,0.00035855465],"about_ca_topic_score_codex":0.0054580187,"about_ca_topic_score_gemma":0.0037629101,"teacher_disagreement_score":0.016899206,"about_ca_system_score_codex":0.0011024993,"about_ca_system_score_gemma":0.0006518526,"threshold_uncertainty_score":0.089372635},"labels":[],"label_agreement":null},{"id":"W2811244448","doi":"10.1109/jstars.2018.2846178","title":"Deep Convolutional Neural Network for Complex Wetland Classification Using Optical Remote Sensing Imagery","year":2018,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":241,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre For Cold Ocean Resources Engineering; Memorial University of Newfoundland; University of New Brunswick","funders":"Research and Development Corporation of Newfoundland and Labrador","keywords":"Convolutional neural network; Computer science; Remote sensing; Land cover; Random forest; Artificial intelligence; Deep learning; Satellite imagery; Contextual image classification; Thematic map; Pattern recognition (psychology); Feature extraction; Land use; Image (mathematics); Cartography","score_opus":0.06331301919100238,"score_gpt":0.2662183573009876,"score_spread":0.2029053381099852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2811244448","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31536773,0.0044155144,0.6683029,0.0005860145,0.00033717192,0.00015429483,0.00089226296,0.003243001,0.006701137],"genre_scores_gemma":[0.8601609,0.0015675017,0.13034055,0.00012642446,0.00007514908,0.00008377227,0.0017999712,0.00006497145,0.0057808217],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998766,0.00001542883,0.000007357409,0.000029803334,0.000044140583,0.000026689611],"domain_scores_gemma":[0.99987435,0.00003395541,0.000019413988,0.000014106369,0.000048901293,0.0000092547825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003903636,0.0006786275,0.00035965964,0.0006461725,0.00018403938,0.00032820136,0.000542178,0.00035459807,0.000919195],"category_scores_gemma":[0.0005244841,0.00020179417,0.00046567226,0.00062357425,0.00016121066,0.0005639343,0.00034195636,0.0005660855,0.00029025716],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028897583,0.00023537948,0.0068980283,0.00020129091,0.00019603243,0.00024422503,0.00006592956,0.26063493,0.040642433,0.0023476994,0.007147369,0.6810978],"study_design_scores_gemma":[0.0000059935187,0.000044972534,0.0018284512,0.000009310437,0.000030830564,0.000031298223,0.000011965331,0.98831856,0.007776355,0.0006516435,0.0012823573,0.000008212688],"about_ca_topic_score_codex":0.011590313,"about_ca_topic_score_gemma":0.014323513,"teacher_disagreement_score":0.011590313,"about_ca_system_score_codex":0.000503503,"about_ca_system_score_gemma":0.0006473705,"threshold_uncertainty_score":0.023045659},"labels":[],"label_agreement":null},{"id":"W2867276684","doi":"10.3390/sym10070272","title":"Incremental Spectral Clustering via Fastfood Features and Its Application to Stream Image Segmentation","year":2018,"lang":"en","type":"article","venue":"Symmetry","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Cluster analysis; Computer science; Pattern recognition (psychology); Spectral clustering; Data stream clustering; Kernel (algebra); Artificial intelligence; Eigendecomposition of a matrix; Segmentation; Data point; Mathematics; Eigenvalues and eigenvectors; Correlation clustering; CURE data clustering algorithm","score_opus":0.007648303984092919,"score_gpt":0.2419720340942735,"score_spread":0.2343237301101806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2867276684","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022172187,0.0001485832,0.9763647,0.00008087,0.000029753872,0.000033569315,0.000054217697,0.00071998197,0.0003961399],"genre_scores_gemma":[0.33968675,0.00024551502,0.65760314,0.00009158866,0.000057313413,0.00010764954,0.000446537,0.00023586326,0.0015257013],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995223,0.00008977337,0.000028411847,0.00012827791,0.00016401365,0.00006725286],"domain_scores_gemma":[0.99920565,0.00021337636,0.00008560982,0.0001429896,0.00030170716,0.000050595365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007422857,0.0007019175,0.0009930818,0.0018005454,0.0005884172,0.0009493948,0.0011730326,0.00092945574,0.0011239761],"category_scores_gemma":[0.0028059017,0.00042490507,0.0009003857,0.0018385953,0.00072686217,0.0015854026,0.0010500571,0.00081245136,0.00056400156],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039594277,0.00022204361,0.0038475033,0.00016402366,0.00013458857,0.00027563842,0.00037410643,0.3666768,0.037011985,0.013052222,0.0047613624,0.5730837],"study_design_scores_gemma":[0.000005652913,0.000022283712,0.00033205815,0.0000032720322,0.0000061945875,0.00004838128,0.00002377474,0.9925815,0.0036716633,0.0026189107,0.00067634735,0.000009971957],"about_ca_topic_score_codex":0.005426758,"about_ca_topic_score_gemma":0.005230042,"teacher_disagreement_score":0.005426758,"about_ca_system_score_codex":0.000634454,"about_ca_system_score_gemma":0.0008676581,"threshold_uncertainty_score":0.010790348},"labels":[],"label_agreement":null},{"id":"W2883831062","doi":"10.1364/ao.57.006219","title":"Continuum removal for ground-based LWIR hyperspectral infrared imagery applying non-negative matrix factorization","year":2018,"lang":"en","type":"article","venue":"Applied Optics","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Hyperspectral imaging; Non-negative matrix factorization; Radiance; Matrix decomposition; Computer science; Remote sensing; Optics; Pattern recognition (psychology); Algorithm; Mathematics; Artificial intelligence; Physics; Eigenvalues and eigenvectors; Geology","score_opus":0.015077951071799435,"score_gpt":0.2455445984946564,"score_spread":0.23046664742285697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2883831062","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10248489,0.0002614305,0.8919038,0.00012417103,0.00005754928,0.0000565188,0.00019224263,0.001577634,0.0033417759],"genre_scores_gemma":[0.3295054,0.00027261395,0.66582596,0.00007560598,0.000028209543,0.00007697419,0.00075711036,0.00020361738,0.003254458],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996258,0.00004791766,0.00001028466,0.000067380395,0.00021723854,0.00003135509],"domain_scores_gemma":[0.999762,0.00005690173,0.000048185324,0.00003240172,0.00009173236,0.0000087241815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004747769,0.0008095699,0.00028878948,0.0008825512,0.00043135817,0.00048339635,0.0004415123,0.00042109872,0.0011119202],"category_scores_gemma":[0.00066118495,0.00016749359,0.0005928323,0.0005959586,0.0002830982,0.0007853317,0.00036565086,0.00049775856,0.0007147068],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019467025,0.00028437152,0.005433512,0.00028679598,0.00006921794,0.00020216545,0.00018584584,0.09865276,0.3173245,0.0043554115,0.0048437,0.56816715],"study_design_scores_gemma":[0.0000108517515,0.000064493506,0.006426845,0.000013168907,0.000017491062,0.00010062456,0.00006184006,0.89192146,0.09567781,0.0016466983,0.004028456,0.000030315923],"about_ca_topic_score_codex":0.0034511841,"about_ca_topic_score_gemma":0.0061681,"teacher_disagreement_score":0.0034511841,"about_ca_system_score_codex":0.00045321014,"about_ca_system_score_gemma":0.0005996885,"threshold_uncertainty_score":0.006862223},"labels":[],"label_agreement":null},{"id":"W2884060925","doi":"10.1016/j.infrared.2018.06.026","title":"Comparison assessment of low rank sparse-PCA based-clustering/classification for automatic mineral identification in long wave infrared hyperspectral imagery","year":2018,"lang":"en","type":"article","venue":"Infrared Physics & Technology","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":37,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Fonds de recherche du Québec – Nature et technologies","keywords":"Hyperspectral imaging; Principal component analysis; Artificial intelligence; Pattern recognition (psychology); Cluster analysis; Computer science; Extreme learning machine; Kernel (algebra); Remote sensing; Mathematics; Geology; Artificial neural network","score_opus":0.02956818770377964,"score_gpt":0.2993651332641623,"score_spread":0.2697969455603827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884060925","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65347224,0.001509421,0.33493727,0.00036962694,0.00016272142,0.00017858912,0.00084261596,0.0018472845,0.0066802334],"genre_scores_gemma":[0.8710217,0.00049060915,0.12370004,0.00007225588,0.000048376838,0.000062165695,0.0014136572,0.00009554428,0.0030955954],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991744,0.00019616834,0.000041014395,0.00010557802,0.0003979718,0.00008485787],"domain_scores_gemma":[0.9986461,0.00029674498,0.000092139526,0.00012881466,0.00078743615,0.000048827715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014598616,0.0005251056,0.00044794352,0.0013492447,0.00048173143,0.0009202168,0.00064221985,0.0006348051,0.0017322947],"category_scores_gemma":[0.0026178902,0.00014765392,0.0006306268,0.0008116466,0.00031641067,0.00096431334,0.0005255896,0.0003368738,0.0007216539],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003232422,0.0008016291,0.012630919,0.0006220056,0.00035688287,0.0001004174,0.0002530886,0.15314338,0.05833467,0.003374125,0.006344285,0.7608062],"study_design_scores_gemma":[0.000036030488,0.00031720608,0.015262201,0.000016810009,0.00010004262,0.00006762505,0.00017839509,0.9641995,0.018058978,0.00080502656,0.0009285831,0.000029617442],"about_ca_topic_score_codex":0.007459104,"about_ca_topic_score_gemma":0.012205396,"teacher_disagreement_score":0.007459104,"about_ca_system_score_codex":0.0004358528,"about_ca_system_score_gemma":0.00070808723,"threshold_uncertainty_score":0.014831364},"labels":[],"label_agreement":null},{"id":"W2884821113","doi":"10.3390/rs10071119","title":"Very Deep Convolutional Neural Networks for Complex Land Cover Mapping Using Multispectral Remote Sensing Imagery","year":2018,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":430,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of New Brunswick; Centre For Cold Ocean Resources Engineering; Memorial University of Newfoundland","funders":"Research and Development Corporation of Newfoundland and Labrador; Natural Sciences and Engineering Research Council of Canada; Department of Environment and Conservation, Government of Newfoundland and Labrador; Government of Canada","keywords":"Multispectral image; Convolutional neural network; Random forest; Computer science; Artificial intelligence; Support vector machine; Remote sensing; Deep learning; Pattern recognition (psychology); Satellite imagery; Contextual image classification; Image (mathematics); Geology","score_opus":0.042367044891957674,"score_gpt":0.26131337174869973,"score_spread":0.21894632685674206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884821113","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3669043,0.0063205855,0.6033982,0.00087261724,0.0002707889,0.00011889009,0.0022815405,0.007782587,0.012050585],"genre_scores_gemma":[0.86686,0.0014931886,0.12296368,0.00021265012,0.00004545021,0.000052324245,0.0036422242,0.0001502499,0.0045802314],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998242,0.000027281998,0.00000963919,0.00004084334,0.00006545373,0.00003256116],"domain_scores_gemma":[0.999833,0.0000565169,0.000031326286,0.000027188706,0.000041856405,0.00001015343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000389141,0.00077893876,0.00030703883,0.0008709681,0.00016384327,0.0005089646,0.00061434985,0.00039825353,0.0017338812],"category_scores_gemma":[0.00081068627,0.00022128153,0.00052326446,0.000779258,0.00023226858,0.0009834948,0.0004659529,0.00065294624,0.0006073282],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000274531,0.00019984622,0.007827939,0.00026982767,0.0002447246,0.0002636957,0.000096891534,0.40883452,0.030394614,0.0040030954,0.009070338,0.53852004],"study_design_scores_gemma":[0.0000070913134,0.00003794586,0.003204265,0.000025653133,0.00002848564,0.00005562186,0.00003327813,0.9824479,0.009055473,0.0025626214,0.0025258404,0.000015845668],"about_ca_topic_score_codex":0.011826928,"about_ca_topic_score_gemma":0.020448606,"teacher_disagreement_score":0.011826928,"about_ca_system_score_codex":0.0005618757,"about_ca_system_score_gemma":0.0005920895,"threshold_uncertainty_score":0.023516178},"labels":[],"label_agreement":null},{"id":"W2886056129","doi":"10.1109/jstars.2018.2830178","title":"Corrections to “Image Classification Using RapidEye Data: Integration of Spectral and Textual Features in a Random Forest Classifier” [Dec 17 5334-5349]","year":2018,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Agriculture and Agri-Food Canada","funders":"","keywords":"Random forest; Classifier (UML); Computer science; Pattern recognition (psychology); Artificial intelligence; Remote sensing; Contextual image classification; Geography; Image (mathematics)","score_opus":0.053817384474924984,"score_gpt":0.2778071603788449,"score_spread":0.2239897759039199,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2886056129","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020242885,0.001537252,0.027904367,0.11206041,0.7845061,0.00030332443,0.025511641,0.016753824,0.029398782],"genre_scores_gemma":[0.052129414,0.0049814344,0.09380497,0.13471356,0.14622582,0.0010569105,0.05391357,0.022589453,0.49058494],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98701805,0.0020794787,0.0017616383,0.00097305747,0.007348582,0.00081926637],"domain_scores_gemma":[0.8884663,0.013989944,0.005833637,0.0063764695,0.08378661,0.0015471122],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0076106396,0.0023542205,0.0016800561,0.005115095,0.0047175228,0.005589159,0.004095763,0.0066749677,0.094924115],"category_scores_gemma":[0.094887376,0.0018791069,0.0025660745,0.0052222777,0.0018898849,0.0040297173,0.0031267605,0.0102274185,0.08896136],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006326607,0.000026103524,0.00017583062,0.00007726619,0.0000136050885,0.00010796676,0.000037833164,0.00018561125,0.0005008406,0.0008384822,0.9908166,0.0071565523],"study_design_scores_gemma":[0.000037823283,0.000048510738,0.0017581017,0.00018563074,0.000028319226,0.00015113522,0.00013404095,0.0012447212,0.002270304,0.001976585,0.9920884,0.000076493125],"about_ca_topic_score_codex":0.03847966,"about_ca_topic_score_gemma":0.063407056,"teacher_disagreement_score":0.094924115,"about_ca_system_score_codex":0.0040361485,"about_ca_system_score_gemma":0.0071284752,"threshold_uncertainty_score":0.3175528},"labels":[],"label_agreement":null},{"id":"W2887260487","doi":"10.1049/iet-ipr.2018.5600","title":"Modified mean shift algorithm","year":2018,"lang":"en","type":"article","venue":"IET Image Processing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Rehabilitation Institute; University of Toronto","funders":"","keywords":"Algorithm; Convergence (economics); Sequence (biology); Monotonic function; Mathematics; A priori and a posteriori; Iterative method; Function (biology); Mean-shift; Contrast (vision); Freivalds' algorithm; Computer science; Mathematical optimization; Pattern recognition (psychology); Artificial intelligence","score_opus":0.01682197372924092,"score_gpt":0.2514979409369103,"score_spread":0.23467596720766937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2887260487","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003235669,0.000354117,0.9938029,0.000102312224,0.00015340792,0.000055373832,0.00008566094,0.0005205262,0.0016899665],"genre_scores_gemma":[0.08876845,0.00060212426,0.8953514,0.0003022142,0.00021968086,0.00027910422,0.0006390292,0.00033683496,0.013501164],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99842644,0.00029897122,0.00009367225,0.00040836236,0.0006245177,0.00014801971],"domain_scores_gemma":[0.9987218,0.00029019543,0.0000817579,0.00022656079,0.0006218962,0.000057679325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009987002,0.00093892217,0.0015852208,0.0013858626,0.00074174016,0.001612824,0.002586077,0.0021011862,0.0068785474],"category_scores_gemma":[0.0035683755,0.00054327986,0.0014994857,0.001644978,0.0008108914,0.001537961,0.0016826085,0.0014818967,0.0040890872],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047566244,0.00008719684,0.0012449966,0.0002734824,0.00024228574,0.00020668434,0.0001854759,0.1840016,0.02337473,0.03623081,0.014170445,0.7395066],"study_design_scores_gemma":[0.000079343685,0.000116512936,0.0006403523,0.000030401146,0.00005364164,0.00036656638,0.00003865218,0.9406524,0.010649653,0.018515045,0.028795304,0.00006206383],"about_ca_topic_score_codex":0.0033818106,"about_ca_topic_score_gemma":0.0033235697,"teacher_disagreement_score":0.0068785474,"about_ca_system_score_codex":0.0007741174,"about_ca_system_score_gemma":0.0017906746,"threshold_uncertainty_score":0.023011029},"labels":[],"label_agreement":null},{"id":"W2890554472","doi":"10.1109/jstars.2018.2866284","title":"Multilevel Building Detection Framework in Remote Sensing Images Based on Convolutional Neural Networks","year":2018,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint Mary's University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Convolutional neural network; Pyramid (geometry); Artificial intelligence; Object detection; Pattern recognition (psychology); Construct (python library); Gaussian; Building model; Deep learning; Data mining; Mathematics; Simulation","score_opus":0.02280661416842588,"score_gpt":0.2422030179042765,"score_spread":0.21939640373585062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890554472","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036396276,0.0005547705,0.9586021,0.00016868956,0.000041459494,0.00005493617,0.00032701885,0.0022734615,0.0015812588],"genre_scores_gemma":[0.6170662,0.00077150186,0.37572455,0.00023626086,0.00008916293,0.00011401492,0.0013930732,0.00014944091,0.004455856],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996718,0.000025136329,0.000011314035,0.00012093801,0.00010556079,0.00006525479],"domain_scores_gemma":[0.99983585,0.00003047579,0.0000346055,0.000031585296,0.000053918262,0.0000136451845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035611427,0.0010151588,0.00070785783,0.0015160476,0.00022692022,0.0006840028,0.001564899,0.0008324046,0.0016436715],"category_scores_gemma":[0.0006084713,0.00041997025,0.0008518378,0.00090906024,0.00035894153,0.0012502951,0.0008828094,0.00083261484,0.00058178796],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020926652,0.00019401446,0.0045090234,0.00020371206,0.0001742119,0.00023483433,0.000081257014,0.4643676,0.04020059,0.008314669,0.0034311134,0.47807968],"study_design_scores_gemma":[0.0000025031582,0.000017369994,0.00065921835,0.0000048339075,0.0000145506465,0.000032662614,0.000005572832,0.99379903,0.0037779897,0.0012025415,0.00047767305,0.0000060868792],"about_ca_topic_score_codex":0.015865883,"about_ca_topic_score_gemma":0.020638956,"teacher_disagreement_score":0.015865883,"about_ca_system_score_codex":0.0009951656,"about_ca_system_score_gemma":0.00081765465,"threshold_uncertainty_score":0.03154707},"labels":[],"label_agreement":null},{"id":"W2890790222","doi":"10.1080/22797254.2018.1503565","title":"Gaussian mixture model and Markov random fields for hyperspectral image classification","year":2018,"lang":"en","type":"article","venue":"European Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Università degli Studi di Pavia","keywords":"Hyperspectral imaging; Pattern recognition (psychology); Markov random field; Artificial intelligence; Mixture model; Spatial analysis; Computer science; Bayesian probability; Benchmark (surveying); Random field; Gaussian; Segmentation; Image segmentation; Mathematics; Geography; Statistics; Cartography","score_opus":0.019424554161108845,"score_gpt":0.237965501551318,"score_spread":0.21854094739020913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890790222","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031409462,0.00089612714,0.9949713,0.00011002933,0.000040853396,0.000016632139,0.000049938284,0.00037413053,0.0004000702],"genre_scores_gemma":[0.34375525,0.0028616164,0.64722395,0.00028225878,0.00038289206,0.00019949838,0.0007866005,0.00021171682,0.004296213],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99903286,0.00030500942,0.00003961504,0.0002155759,0.00031913057,0.00008779548],"domain_scores_gemma":[0.9991749,0.00044486625,0.00011082154,0.00009320458,0.00014721933,0.000029020737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019016014,0.0008890803,0.00094169495,0.0018876422,0.0003420196,0.0008169058,0.0012743542,0.0012863544,0.0011112605],"category_scores_gemma":[0.0027933165,0.00043503696,0.0012040586,0.0016750833,0.0006996261,0.0013411005,0.0007084723,0.00151042,0.000738877],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002192807,0.000115403695,0.0018061819,0.00022987984,0.00018918463,0.00013761393,0.00011956723,0.52717495,0.010855248,0.043503795,0.003997741,0.41165125],"study_design_scores_gemma":[0.0000036789977,0.000015329597,0.00032761556,0.000010074827,0.000013377599,0.0000327507,0.0000065506338,0.9895481,0.0010068758,0.00799783,0.0010218177,0.000015981128],"about_ca_topic_score_codex":0.007510706,"about_ca_topic_score_gemma":0.005380029,"teacher_disagreement_score":0.007510706,"about_ca_system_score_codex":0.0008247572,"about_ca_system_score_gemma":0.0008948117,"threshold_uncertainty_score":0.014933944},"labels":[],"label_agreement":null},{"id":"W2891243836","doi":"10.1016/s1018-3639(18)30853-5","title":"The Potential of Radarsat Imagery for Population Estimation: Riyadh Case","year":2008,"lang":"en","type":"article","venue":"Journal of King Saud University - Engineering Sciences","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Population; Aerial photography; Remote sensing; Synthetic aperture radar; Satellite imagery; Geography; Photography; Computer science","score_opus":0.013529843546655044,"score_gpt":0.20463522291915326,"score_spread":0.19110537937249822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891243836","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9751473,0.0006865435,0.007059565,0.00088346243,0.000017460714,0.00010294343,0.0004317743,0.000046116224,0.015624824],"genre_scores_gemma":[0.99390185,0.00033444742,0.0045293374,0.00003129718,0.000012408548,0.000022616845,0.00019163365,0.000006470387,0.00097002235],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990206,0.0005061314,0.000034822562,0.00009288408,0.00017219762,0.00017341136],"domain_scores_gemma":[0.9973717,0.0016363888,0.00022128139,0.0003190338,0.0003630584,0.00008852686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016640527,0.00042055617,0.00025061314,0.0011193233,0.00047551398,0.0012859335,0.00094245793,0.00072283467,0.00080016284],"category_scores_gemma":[0.005587874,0.0002498928,0.0005110801,0.0013068302,0.00081186084,0.0006250145,0.0007747182,0.00046294832,0.00024680895],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011561455,0.000379205,0.56905097,0.00021029687,0.00033746575,0.016768496,0.0021294774,0.29784837,0.0048964485,0.025540452,0.0059780856,0.07570464],"study_design_scores_gemma":[0.00015420951,0.00038968356,0.14393096,0.00008826764,0.00038188774,0.00519477,0.0028540408,0.82790834,0.0058122324,0.004295254,0.008862401,0.00012794102],"about_ca_topic_score_codex":0.14752151,"about_ca_topic_score_gemma":0.11563568,"teacher_disagreement_score":0.14752151,"about_ca_system_score_codex":0.0014137689,"about_ca_system_score_gemma":0.00081925455,"threshold_uncertainty_score":0.29332566},"labels":[],"label_agreement":null},{"id":"W2894165434","doi":"10.1109/mgrs.2018.2854840","title":"New Frontiers in Spectral-Spatial Hyperspectral Image Classification: The Latest Advances Based on Mathematical Morphology, Markov Random Fields, Segmentation, Sparse Representation, and Deep Learning","year":2018,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Magazine","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":323,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Foothills Medical Centre; University of Calgary","funders":"Department of Science, Information Technology and Innovation, Queensland Government; University of Houston; Università degli Studi di Pavia; European Commission; Department of Science and Technology, Ministry of Science and Technology, India; Purdue University","keywords":"Hyperspectral imaging; Remote sensing; Pattern recognition (psychology); Computer science; Artificial intelligence; Image resolution; Spatial analysis; Mathematical morphology; Markov chain; Segmentation; Land cover; Contextual image classification; Image processing; Geography; Image (mathematics); Machine learning; Land use; Engineering","score_opus":0.011776080000251618,"score_gpt":0.24518029872500588,"score_spread":0.23340421872475425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2894165434","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011444745,0.105169035,0.8586478,0.013879093,0.0008546564,0.0000366494,0.00020829758,0.00069632527,0.009063382],"genre_scores_gemma":[0.29880446,0.1673455,0.5121267,0.0043986402,0.0073471824,0.00012812343,0.001120515,0.00053515565,0.00819372],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992059,0.0001782021,0.000039444778,0.00016330302,0.00036342096,0.000049792732],"domain_scores_gemma":[0.9977448,0.0011994289,0.00017117463,0.00018573637,0.0005664099,0.00013252175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019725573,0.0008260132,0.0011413287,0.0015367138,0.00033911955,0.0019024234,0.0010522116,0.0012366935,0.0020774356],"category_scores_gemma":[0.0031858906,0.00032446894,0.00078456016,0.0027369212,0.0021936868,0.0047710226,0.0014246412,0.0037331334,0.00085687614],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001269338,0.00019323867,0.002421732,0.00068207877,0.00008751823,0.000111425965,0.0001922681,0.017721476,0.011223047,0.089829214,0.021866841,0.85554427],"study_design_scores_gemma":[0.000029930747,0.0001860636,0.0052419,0.00047876503,0.00007250882,0.0005883659,0.00034652263,0.50186473,0.01107385,0.32784837,0.15212339,0.00014557627],"about_ca_topic_score_codex":0.0014875089,"about_ca_topic_score_gemma":0.0014959871,"teacher_disagreement_score":0.0020774356,"about_ca_system_score_codex":0.00075875607,"about_ca_system_score_gemma":0.0008229383,"threshold_uncertainty_score":0.010432005},"labels":[],"label_agreement":null},{"id":"W2896979109","doi":"10.1117/12.2326694","title":"Unsupervised sparsity-based unmixing of hyperspectral imaging data using an online sparse coding dictionary","year":2018,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Hyperspectral imaging; Pixel; Computer science; Data cube; Endmember; Artificial intelligence; Pattern recognition (psychology); Sparse approximation; Neural coding; Basis (linear algebra); Coding (social sciences); Cube (algebra); Computer vision; Mathematics; Data mining","score_opus":0.15016921114706272,"score_gpt":0.29941990433434973,"score_spread":0.149250693187287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2896979109","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011399166,0.00007343911,0.98746544,0.00005852379,0.000019332994,0.000025430585,0.000066093206,0.00020436125,0.000688273],"genre_scores_gemma":[0.21538685,0.0003853338,0.7786412,0.00013212278,0.00007122788,0.000198434,0.0011521032,0.00015001788,0.003882618],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99948573,0.00009617222,0.000028507373,0.00013708802,0.00020950365,0.000043027816],"domain_scores_gemma":[0.9992768,0.00026478813,0.00008945011,0.00012818039,0.00020959513,0.00003120126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005442675,0.0005812642,0.0007191035,0.0006538265,0.00026096654,0.0005718054,0.00078327267,0.0006125479,0.0009734004],"category_scores_gemma":[0.0016329436,0.00032635644,0.0008292845,0.0009437815,0.0006295518,0.0014706411,0.0012240363,0.0014569431,0.00050465646],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003388054,0.00023476782,0.0015003913,0.0003460368,0.00015018594,0.00023468166,0.00044285462,0.3562,0.13375482,0.031639125,0.004762907,0.4703954],"study_design_scores_gemma":[0.000010081629,0.000037695205,0.00028231854,0.000008461599,0.000008592554,0.00006535322,0.000024144976,0.9834636,0.011383466,0.0030356792,0.0016666907,0.00001394212],"about_ca_topic_score_codex":0.0016958605,"about_ca_topic_score_gemma":0.0022358033,"teacher_disagreement_score":0.0016958605,"about_ca_system_score_codex":0.00030898929,"about_ca_system_score_gemma":0.0007052311,"threshold_uncertainty_score":0.0033720136},"labels":[],"label_agreement":null},{"id":"W2897049417","doi":"10.1109/mmsp.2018.8547095","title":"A Cloud Detection Algorithm for Remote Sensing Images Using Fully Convolutional Neural Networks","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Jaccard index; Convolutional neural network; Computer science; Cloud computing; Artificial intelligence; Deep learning; Pixel; Identification (biology); Set (abstract data type); Precision and recall; Remote sensing; Artificial neural network; Process (computing); Data set; Measure (data warehouse); Pattern recognition (psychology); Data mining; Geography","score_opus":0.028474768932136744,"score_gpt":0.25918090847966324,"score_spread":0.2307061395475265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2897049417","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026791489,0.00039914306,0.96871424,0.000117484786,0.00007113278,0.000119254575,0.0002577548,0.0023848834,0.0011446459],"genre_scores_gemma":[0.16717283,0.00033511245,0.828325,0.00012195563,0.00006924187,0.00009849912,0.00096908154,0.00018247432,0.002725855],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99958223,0.00002950113,0.000024991337,0.00012824158,0.00016886821,0.00006618948],"domain_scores_gemma":[0.9996737,0.00006282762,0.00006413469,0.0000536931,0.000117137344,0.000028506782],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006163345,0.0010081754,0.0008620889,0.0020917829,0.0005051548,0.0008672924,0.001161551,0.00090334954,0.00136274],"category_scores_gemma":[0.0008868348,0.00043569162,0.0009088642,0.0014672505,0.00036345076,0.0011124345,0.0008919809,0.0009246899,0.0010456936],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018830094,0.00016232696,0.0030317688,0.00015150894,0.00012382263,0.0001349219,0.000046887504,0.06807602,0.07299452,0.003322483,0.006690408,0.84507704],"study_design_scores_gemma":[0.000012931534,0.00003522985,0.0020287314,0.000016566806,0.000021722248,0.00011049051,0.000013722829,0.96979684,0.023354048,0.0020230222,0.002570247,0.00001645694],"about_ca_topic_score_codex":0.008515963,"about_ca_topic_score_gemma":0.010877192,"teacher_disagreement_score":0.008515963,"about_ca_system_score_codex":0.0009880112,"about_ca_system_score_gemma":0.0009499251,"threshold_uncertainty_score":0.016932786},"labels":[],"label_agreement":null},{"id":"W2897160171","doi":"10.3390/s18103587","title":"Hyperspectral Remote Sensing Image Classification Based on Maximum Overlap Pooling Convolutional Neural Network","year":2018,"lang":"en","type":"article","venue":"Sensors","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Fundamental Research Funds for the Central Universities; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Pooling; Convolutional neural network; Hyperspectral imaging; Artificial intelligence; Pattern recognition (psychology); Computer science; Kernel (algebra); Contextual image classification; Image (mathematics); Remote sensing; Artificial neural network; Computer vision; Mathematics; Geography","score_opus":0.020285484473557547,"score_gpt":0.2399135230176408,"score_spread":0.21962803854408325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2897160171","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27259722,0.0010862091,0.7161065,0.00029987388,0.000116201394,0.00017229836,0.00045094927,0.003943757,0.005226994],"genre_scores_gemma":[0.84420377,0.000412041,0.1499128,0.0001349453,0.000050886723,0.00012404432,0.0010682772,0.00006900375,0.0040242183],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995461,0.00004134132,0.000023333801,0.000138396,0.00016528407,0.00008552782],"domain_scores_gemma":[0.9997131,0.00007270757,0.000048197122,0.000043589418,0.00010498555,0.000017359322],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064862415,0.0009867793,0.00072434417,0.0009005505,0.00036157557,0.0005831245,0.0009262084,0.0006452334,0.00092162594],"category_scores_gemma":[0.000932409,0.00032548298,0.00067063904,0.0008914129,0.00036271766,0.0011701833,0.00064166647,0.0005697588,0.00034339147],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00065371743,0.0004337742,0.0051979586,0.00016457295,0.0002735314,0.0002474518,0.000101751866,0.25786415,0.10302523,0.0023325055,0.0045967004,0.6251087],"study_design_scores_gemma":[0.000005645851,0.000036887584,0.0017744964,0.0000040944324,0.000021419683,0.0000307335,0.000006828471,0.9852248,0.012169439,0.00033330623,0.00038173227,0.0000106015095],"about_ca_topic_score_codex":0.010524775,"about_ca_topic_score_gemma":0.009360099,"teacher_disagreement_score":0.010524775,"about_ca_system_score_codex":0.00069962983,"about_ca_system_score_gemma":0.000578294,"threshold_uncertainty_score":0.020927012},"labels":[],"label_agreement":null},{"id":"W2897552941","doi":"10.3390/rs10101664","title":"Change Detection Based on Multi-Feature Clustering Using Differential Evolution for Landsat Imagery","year":2018,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Key Research and Development Program of China; National Aeronautics and Space Administration; Natural Science Foundation of Hubei Province; China University of Mining and Technology; National Natural Science Foundation of China; U.S. Geological Survey","keywords":"Cluster analysis; Computer science; Remote sensing; Change detection; Pattern recognition (psychology); Land cover; Normalized Difference Vegetation Index; Differential evolution; Artificial intelligence; Data mining; Geology; Land use","score_opus":0.04586090318448567,"score_gpt":0.2653971008221552,"score_spread":0.21953619763766952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2897552941","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.094272785,0.00016673893,0.9038214,0.00007422346,0.00003124142,0.00008272033,0.00005776109,0.0007484603,0.00074468396],"genre_scores_gemma":[0.49354908,0.00013409945,0.5048446,0.00004979399,0.000020387857,0.00011142741,0.0002763062,0.000071743976,0.00094252854],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993693,0.000060637987,0.000036413283,0.00019930917,0.0002891376,0.00004511233],"domain_scores_gemma":[0.9995158,0.00013535445,0.000072275274,0.000061853825,0.00019159327,0.000023064156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005237772,0.000525891,0.00063047657,0.0018004494,0.0004634775,0.0005714216,0.0008427744,0.00048710481,0.00034359974],"category_scores_gemma":[0.001271849,0.0002925079,0.00084711646,0.0015079991,0.00039086424,0.0007673523,0.00047267077,0.00045306823,0.00013319743],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021983452,0.00020519069,0.0064640087,0.00015440129,0.0002081046,0.00020516153,0.00031064026,0.16649733,0.099478856,0.002555261,0.0012379104,0.72246325],"study_design_scores_gemma":[0.000009178747,0.000039833638,0.0048584477,0.0000038800117,0.000019446219,0.0000998231,0.000026003509,0.9765534,0.017222935,0.0005972443,0.000542069,0.00002779386],"about_ca_topic_score_codex":0.005361142,"about_ca_topic_score_gemma":0.004854802,"teacher_disagreement_score":0.005361142,"about_ca_system_score_codex":0.0007309334,"about_ca_system_score_gemma":0.00043726916,"threshold_uncertainty_score":0.0106598735},"labels":[],"label_agreement":null},{"id":"W2900579266","doi":"10.1109/igarss.2018.8518619","title":"Deep Learning Neural Networks for Land Use Land Cover Mapping","year":2018,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Winnipeg","funders":"","keywords":"Land cover; Computer science; Satellite imagery; Cover (algebra); Deep learning; Artificial neural network; Focus (optics); Land use; Satellite; Process (computing); Remote sensing; Artificial intelligence; Land information system; Machine learning; Geography; Land management; Engineering; Civil engineering","score_opus":0.02607688411989789,"score_gpt":0.22698918335751747,"score_spread":0.20091229923761958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900579266","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.070497036,0.012847834,0.897662,0.0016229346,0.00029780346,0.00006828367,0.0011158511,0.0021574951,0.013730833],"genre_scores_gemma":[0.7788931,0.0054533,0.19862537,0.00023600069,0.000121578945,0.000105849955,0.0012933344,0.00010232147,0.015169222],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.99990404,0.000022750437,0.000006328989,0.000018787314,0.000034894598,0.000013168549],"domain_scores_gemma":[0.9998429,0.00006999878,0.000019369141,0.000016052407,0.000045745892,0.0000058440205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033251173,0.0003911809,0.0002591684,0.00040711666,0.00015586491,0.0005398317,0.00037874008,0.0004627994,0.0018554732],"category_scores_gemma":[0.00093268265,0.00018384977,0.00024506787,0.0008074855,0.00019499657,0.000535216,0.00036503907,0.00066861825,0.00051188376],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053346903,0.00006572046,0.0025854807,0.00015397799,0.00008264808,0.00007966522,0.000043606793,0.60082084,0.0057745716,0.011170816,0.005650994,0.37351823],"study_design_scores_gemma":[0.000001875075,0.000008379941,0.000660482,0.000012427498,0.000005712989,0.00001002484,0.000009007908,0.98942393,0.001165651,0.006455934,0.0022418671,0.000004737427],"about_ca_topic_score_codex":0.012726876,"about_ca_topic_score_gemma":0.014240086,"teacher_disagreement_score":0.012726876,"about_ca_system_score_codex":0.00057964126,"about_ca_system_score_gemma":0.00048349085,"threshold_uncertainty_score":0.02530557},"labels":[],"label_agreement":null},{"id":"W2901098095","doi":"10.4095/297517","title":"Influence of sample distribution and prior probability adjustment on land cover classification","year":2016,"lang":"en","type":"report","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Resources Canada","funders":"","keywords":"Land cover; Cover (algebra); Sample (material); Distribution (mathematics); Environmental science; Statistics; Probability distribution; Geography; Physical geography; Mathematics; Land use; Ecology; Biology; Engineering; Physics","score_opus":0.03717087840950935,"score_gpt":0.26843201109923326,"score_spread":0.23126113268972393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901098095","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.511228,0.0016559458,0.4816673,0.0006762114,0.00013109394,0.00038318097,0.00015671468,0.0010855314,0.0030160306],"genre_scores_gemma":[0.9620956,0.00018637495,0.036787767,0.0001030949,0.00003188019,0.000071724826,0.00020228226,0.00012288945,0.00039832364],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9924117,0.0036785665,0.0003829177,0.0014599138,0.0017203786,0.0003464831],"domain_scores_gemma":[0.91413784,0.07368104,0.002515056,0.0051995073,0.004093356,0.000373201],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019407457,0.0005719556,0.00073072553,0.0009148054,0.00058822264,0.001427869,0.0009967231,0.0009246472,0.00055287534],"category_scores_gemma":[0.09455724,0.0004031928,0.0009339249,0.00073809293,0.0013308092,0.002250018,0.000918523,0.0012482485,0.00022279203],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012103573,0.0003304373,0.10011722,0.00029159625,0.000408012,0.00038093972,0.00071532134,0.6443157,0.011971792,0.00865787,0.0016014985,0.22999924],"study_design_scores_gemma":[0.000037619415,0.00024687243,0.031213563,0.000048866226,0.0001208677,0.0002217689,0.000106497966,0.9503434,0.011151667,0.0048656547,0.0015826204,0.000060652586],"about_ca_topic_score_codex":0.0078705605,"about_ca_topic_score_gemma":0.0052111624,"teacher_disagreement_score":0.019407457,"about_ca_system_score_codex":0.0012949008,"about_ca_system_score_gemma":0.0008628795,"threshold_uncertainty_score":0.10263765},"labels":[],"label_agreement":null},{"id":"W2901144234","doi":"10.1109/lgrs.2018.2877734","title":"Constrained Nonnegative Tensor Factorization for Spectral Unmixing of Hyperspectral Images: A Case Study of Urban Impervious Surface Extraction","year":2018,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hyperspectral imaging; Non-negative matrix factorization; Matrix decomposition; Multilinear map; Data cube; Endmember; Pixel; Pattern recognition (psychology); Artificial intelligence; Computer science; Mathematics; Tensor (intrinsic definition); Tucker decomposition; Cube (algebra); Spectral signature; Remote sensing; Geography; Data mining; Combinatorics; Tensor decomposition","score_opus":0.019037908194198854,"score_gpt":0.260746831285241,"score_spread":0.24170892309104217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901144234","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.089189194,0.0012710404,0.9049913,0.0004872851,0.00006194582,0.00007364265,0.00021202095,0.00030392836,0.0034096423],"genre_scores_gemma":[0.5413166,0.0012470315,0.452899,0.00008968024,0.000080574435,0.00008344422,0.000520477,0.00012339915,0.0036397232],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993567,0.00016539576,0.000037861544,0.00013619025,0.00022667022,0.00007712941],"domain_scores_gemma":[0.99937433,0.00031551678,0.00006393323,0.00007048891,0.00015186306,0.00002380627],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011633697,0.0010764874,0.00081514334,0.0010926104,0.0006435515,0.000872284,0.00058300945,0.0012254793,0.00096875976],"category_scores_gemma":[0.0015604226,0.0002788515,0.0011903968,0.0019471572,0.0007955935,0.0012191683,0.00058634556,0.0008032049,0.0002889638],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033661502,0.00022682975,0.0075592687,0.0007949086,0.00015715814,0.003234768,0.000667371,0.48590013,0.05922696,0.031161988,0.006767638,0.4039663],"study_design_scores_gemma":[0.0000073230217,0.000033231147,0.0015418134,0.000016955692,0.000029531458,0.00047937056,0.0001421883,0.9754352,0.011677106,0.0065598125,0.0040466296,0.00003083119],"about_ca_topic_score_codex":0.0051191226,"about_ca_topic_score_gemma":0.00798407,"teacher_disagreement_score":0.0051191226,"about_ca_system_score_codex":0.0005777356,"about_ca_system_score_gemma":0.0005314233,"threshold_uncertainty_score":0.010178626},"labels":[],"label_agreement":null},{"id":"W2901231628","doi":"10.1109/igarss.2018.8517919","title":"Wetland Classification Using Deep Convolutional Neural Network","year":2018,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick; Centre For Cold Ocean Resources Engineering; Memorial University of Newfoundland","funders":"","keywords":"Convolutional neural network; Computer science; Random forest; Artificial intelligence; Deep learning; Thematic map; Contextual image classification; Pattern recognition (psychology); Land cover; Remote sensing; Satellite imagery; Feature extraction; Land use; Image (mathematics); Cartography; Geography","score_opus":0.039928923843167465,"score_gpt":0.25307908507139,"score_spread":0.21315016122822253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901231628","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29601827,0.0008462827,0.6953308,0.00026016988,0.00008754274,0.00008476328,0.00065819494,0.0024059108,0.0043080575],"genre_scores_gemma":[0.8938862,0.00026137594,0.10197972,0.00006302356,0.000031362164,0.000041817595,0.00087615004,0.000030240799,0.0028301382],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99986196,0.000014809609,0.0000069608122,0.000045196037,0.00004009003,0.000031055224],"domain_scores_gemma":[0.99986935,0.000032702395,0.000025074276,0.000017979364,0.00004515204,0.0000097579705],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031849864,0.0006073282,0.0003524816,0.0010147962,0.00019214962,0.00042131115,0.00058251346,0.00039038796,0.00074599695],"category_scores_gemma":[0.0003807144,0.00019994366,0.00052084634,0.00064950844,0.00018904352,0.0006464595,0.00045223933,0.00035022284,0.00024867046],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022500475,0.00022597633,0.013040088,0.00011872737,0.00016733441,0.00022329125,0.000067205125,0.36042187,0.05982031,0.0028151558,0.0035640534,0.55931103],"study_design_scores_gemma":[0.0000024418316,0.000018060286,0.0018909555,0.0000040107393,0.000011844881,0.000023570516,0.000008929192,0.9914308,0.0055233026,0.000622029,0.00045814333,0.0000058914993],"about_ca_topic_score_codex":0.009725168,"about_ca_topic_score_gemma":0.013216098,"teacher_disagreement_score":0.009725168,"about_ca_system_score_codex":0.0005531339,"about_ca_system_score_gemma":0.00043032444,"threshold_uncertainty_score":0.019337118},"labels":[],"label_agreement":null},{"id":"W2901437370","doi":"10.1016/j.isprsjprs.2018.11.014","title":"Multispectral change detection using multivariate Kullback-Leibler distance","year":2018,"lang":"en","type":"article","venue":"ISPRS Journal of Photogrammetry and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":38,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"U.S. Geological Survey","keywords":"Multispectral image; Change detection; Kullback–Leibler divergence; Multivariate statistics; Divergence (linguistics); Computer science; Pattern recognition (psychology); Similarity (geometry); Artificial intelligence; Probability density function; Gaussian; Range (aeronautics); Remote sensing; Mathematics; Statistics; Image (mathematics); Machine learning; Geography","score_opus":0.036346597461770054,"score_gpt":0.2737272819393622,"score_spread":0.23738068447759214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901437370","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.070187986,0.0004329249,0.9260326,0.00013089449,0.00006491189,0.000053361113,0.00031927164,0.0009319377,0.0018461265],"genre_scores_gemma":[0.6904824,0.0005072057,0.30417556,0.00009743435,0.00010093803,0.000102017264,0.0010141706,0.00012510628,0.003395323],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991001,0.00014122606,0.00007254444,0.00021664877,0.00040277763,0.000066699016],"domain_scores_gemma":[0.9992373,0.0001761075,0.00014748456,0.00012056078,0.0002793933,0.000039161227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008006404,0.00065959425,0.00078078214,0.0028450587,0.00044048345,0.0017676279,0.00068421796,0.0005884133,0.0012882383],"category_scores_gemma":[0.0018813781,0.00021933203,0.0007669265,0.0018253876,0.0004539326,0.0016796731,0.0010103418,0.0006102383,0.0007759657],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037432555,0.0003261869,0.008274359,0.00025119595,0.00026500708,0.00024510617,0.00012449129,0.07554859,0.050811917,0.009611257,0.004103954,0.8500636],"study_design_scores_gemma":[0.00001423007,0.00014979388,0.009862614,0.000024465751,0.000076729426,0.00044074297,0.000089787696,0.9583025,0.021451734,0.007092885,0.0024192769,0.00007524462],"about_ca_topic_score_codex":0.0020152752,"about_ca_topic_score_gemma":0.002372545,"teacher_disagreement_score":0.0028450587,"about_ca_system_score_codex":0.00041381424,"about_ca_system_score_gemma":0.00074889924,"threshold_uncertainty_score":0.0043095946},"labels":[],"label_agreement":null},{"id":"W2901866006","doi":"10.1109/igarss.2018.8518540","title":"Hierarchical Band Selection Using the N-Dimensional Solid Spectral Angle Method to Address Inter- and Intra- Class Spectral Variability","year":2018,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Hyperspectral imaging; Computer science; Selection (genetic algorithm); Spectral bands; Pattern recognition (psychology); Endmember; Class (philosophy); Artificial intelligence; Remote sensing; Geology","score_opus":0.023417140415809976,"score_gpt":0.29730840614245563,"score_spread":0.2738912657266456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901866006","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06335691,0.00008936005,0.93485343,0.00003088445,0.000021266205,0.00006805153,0.00006302351,0.0005484182,0.0009685975],"genre_scores_gemma":[0.3357118,0.000094009476,0.6626239,0.00003955526,0.00002142527,0.00013256475,0.00042800896,0.000090503185,0.0008582647],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993861,0.0001373532,0.00004690867,0.00013049025,0.00023933039,0.000059740854],"domain_scores_gemma":[0.99927336,0.00021653739,0.000084956475,0.00008743622,0.00030485308,0.000032857664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00086272456,0.00068539236,0.0005188504,0.0019888121,0.0004599855,0.0006071181,0.00048643758,0.00031106835,0.00087980117],"category_scores_gemma":[0.0013816481,0.00018378001,0.0008125613,0.0011602996,0.0005322681,0.0008298114,0.00068379624,0.0004367724,0.00031509937],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040508693,0.00034989815,0.009130474,0.00014508209,0.0001689762,0.000093927156,0.0004254416,0.12016634,0.16028222,0.006941585,0.0019275828,0.69996333],"study_design_scores_gemma":[0.00002789894,0.00009390864,0.006094773,0.000010679831,0.00005792234,0.00008293267,0.00012336574,0.95015806,0.036331445,0.0043215384,0.0026545527,0.000042937467],"about_ca_topic_score_codex":0.0025390282,"about_ca_topic_score_gemma":0.0047489507,"teacher_disagreement_score":0.0025390282,"about_ca_system_score_codex":0.00027215644,"about_ca_system_score_gemma":0.0008970646,"threshold_uncertainty_score":0.0050485134},"labels":[],"label_agreement":null},{"id":"W2902905019","doi":"10.1109/mmsp.2018.8547139","title":"Deep Transfer Learning for Hyperspectral Image Classification","year":2018,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Hyperspectral imaging; Transfer of learning; Computer science; Artificial intelligence; Redundancy (engineering); Pattern recognition (psychology); A priori and a posteriori; Contextual image classification; Divergence (linguistics); Machine learning; Image (mathematics)","score_opus":0.022708730581837994,"score_gpt":0.24836975699604408,"score_spread":0.22566102641420607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902905019","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034075316,0.00084762333,0.9612268,0.00038838567,0.000060804803,0.000048992406,0.00010487608,0.0013094004,0.0019378316],"genre_scores_gemma":[0.81965363,0.00063905056,0.17117774,0.0002546177,0.00014285103,0.00018435293,0.00063354557,0.00011158922,0.007202585],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99968266,0.000087657754,0.000014593208,0.00007391096,0.00009021289,0.000051020426],"domain_scores_gemma":[0.9994972,0.00021221755,0.00005945602,0.000080572514,0.000118965065,0.000031648786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008724748,0.0007225465,0.0005930473,0.000758119,0.00033832085,0.0005960626,0.0012687201,0.0009830849,0.0018884435],"category_scores_gemma":[0.0021139574,0.00023511116,0.00053852046,0.00096284493,0.0006605211,0.0012780664,0.0013862428,0.0016870381,0.0005841606],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015052709,0.0002544432,0.0015185917,0.00013196123,0.0000961743,0.0001263252,0.000113707916,0.5119581,0.010193996,0.013194603,0.0057801437,0.4564814],"study_design_scores_gemma":[0.0000021036956,0.000010568815,0.000116983945,0.000002342761,0.0000026009052,0.000006864691,0.000006393411,0.9936845,0.0010031516,0.004888337,0.00027318357,0.0000029539033],"about_ca_topic_score_codex":0.0041627046,"about_ca_topic_score_gemma":0.0025556765,"teacher_disagreement_score":0.0041627046,"about_ca_system_score_codex":0.000923105,"about_ca_system_score_gemma":0.0007095281,"threshold_uncertainty_score":0.008276939},"labels":[],"label_agreement":null},{"id":"W2903333076","doi":"10.1007/978-3-030-05481-6_6","title":"Spectral Band Selection Using Binary Gray Wolf Optimizer and Signal to Noise Ration Measure","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thales (Canada); Université de Sherbrooke","funders":"","keywords":"Hyperspectral imaging; Artificial intelligence; Fitness function; Pattern recognition (psychology); Computer science; Binary number; Classifier (UML); Support vector machine; Selection (genetic algorithm); Measure (data warehouse); Machine learning; Mathematics; Data mining; Genetic algorithm","score_opus":0.01897810205345548,"score_gpt":0.21594782580580762,"score_spread":0.19696972375235214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903333076","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009528548,0.00020221072,0.98740155,0.00008816905,0.000030981315,0.00001679065,0.00002205511,0.00030075165,0.002408967],"genre_scores_gemma":[0.25804585,0.0003377948,0.73085284,0.00018880972,0.0001112263,0.000119321,0.00014598615,0.00055979885,0.009638382],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997049,0.00012167756,0.000016326812,0.000052653566,0.00007453665,0.000029890374],"domain_scores_gemma":[0.9996563,0.00017943584,0.000028038015,0.00004183002,0.000071117334,0.000023292529],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009963111,0.0009388013,0.0011293703,0.0008160962,0.00031500595,0.0009885841,0.0006480381,0.0010370278,0.0036996065],"category_scores_gemma":[0.0017514079,0.0003778718,0.0005980566,0.00062032475,0.0006246438,0.0009181665,0.0009226073,0.00068257935,0.00093430764],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044756793,0.00016757846,0.0007353131,0.00022103742,0.00014089119,0.0001325416,0.00009152773,0.45676345,0.03447449,0.06324478,0.0073410976,0.43623966],"study_design_scores_gemma":[0.000008809415,0.000033105556,0.00014367964,0.000009729961,0.000012037011,0.00003930497,0.000006335103,0.989268,0.0024945003,0.0074373866,0.0005406507,0.000006477424],"about_ca_topic_score_codex":0.000640653,"about_ca_topic_score_gemma":0.00063257717,"teacher_disagreement_score":0.0036996065,"about_ca_system_score_codex":0.00036665317,"about_ca_system_score_gemma":0.0004191765,"threshold_uncertainty_score":0.012376368},"labels":[],"label_agreement":null},{"id":"W2904790741","doi":"10.1109/jstars.2018.2871373","title":"Radiometric Normalization of Multitemporal and Multisensor Remote Sensing Images Based on a Gaussian Mixture Model and Error Ellipse","year":2018,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"National Foundation of Elites; University of Ottawa","keywords":"Normalization (sociology); Pixel; Ellipse; Computer science; Artificial intelligence; Remote sensing; Change detection; Computer vision; Satellite; Gaussian; Gaussian process; Histogram; Mixture model; Pattern recognition (psychology); Image (mathematics); Geology; Mathematics","score_opus":0.02703722379004014,"score_gpt":0.2431886133147018,"score_spread":0.21615138952466165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2904790741","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014541057,0.00021490031,0.98420745,0.00004212991,0.000040105057,0.000025265494,0.000028121634,0.0004762614,0.00042473737],"genre_scores_gemma":[0.399306,0.0007005293,0.59611136,0.00009209711,0.000087436936,0.00012133422,0.00043772167,0.00029807538,0.0028454084],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99842393,0.00029369886,0.000088842804,0.00053976564,0.00054709055,0.00010669132],"domain_scores_gemma":[0.9992853,0.00017424833,0.000113999566,0.00015383169,0.0002478288,0.000024882951],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018422751,0.0010048964,0.00086243235,0.0018178989,0.00038141588,0.0009213955,0.001022964,0.0007836766,0.00063518854],"category_scores_gemma":[0.0028686558,0.00049288286,0.0012383845,0.0015628454,0.0007722648,0.0018342983,0.00091936317,0.0009600057,0.00047240817],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000315856,0.00017095031,0.0065637776,0.00021995799,0.00032809956,0.00018076229,0.0003558323,0.2152094,0.06617076,0.01321755,0.0018123033,0.69545484],"study_design_scores_gemma":[0.000008389876,0.00006430076,0.0067647104,0.00001363303,0.000067160974,0.00018363933,0.000051434134,0.9646349,0.021808757,0.0030463708,0.0032930702,0.000063640975],"about_ca_topic_score_codex":0.004839458,"about_ca_topic_score_gemma":0.005311356,"teacher_disagreement_score":0.004839458,"about_ca_system_score_codex":0.0006487265,"about_ca_system_score_gemma":0.00069276383,"threshold_uncertainty_score":0.009742975},"labels":[],"label_agreement":null},{"id":"W2909129887","doi":"10.1109/euvip.2018.8611652","title":"RBF Neural Network for Landmine Detection in H Yperspectral Imaging","year":2018,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Rimouski","funders":"","keywords":"Hyperspectral imaging; Artificial intelligence; Computer science; Pattern recognition (psychology); Artificial neural network; Radial basis function; Computer vision","score_opus":0.012132844597935729,"score_gpt":0.23364468848057293,"score_spread":0.2215118438826372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2909129887","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18815893,0.0021734382,0.8055897,0.00021093054,0.00007235292,0.000052376236,0.00007469552,0.00137323,0.0022943344],"genre_scores_gemma":[0.8406924,0.0006248981,0.15678084,0.0000682689,0.000024629479,0.000044843327,0.000112093316,0.000045799625,0.0016062331],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996356,0.0001239404,0.00001887964,0.000056260335,0.00013029065,0.000035189296],"domain_scores_gemma":[0.9994862,0.00021381541,0.00005362449,0.0000294554,0.0002034121,0.0000135134205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010933768,0.0005163412,0.00051585416,0.00052174943,0.00016830432,0.00044960933,0.00050309143,0.00084310333,0.00062973524],"category_scores_gemma":[0.0018729799,0.0001506675,0.0003063263,0.0004458289,0.00021432688,0.000706169,0.00028330693,0.00046958734,0.00032937116],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008368658,0.0002989109,0.0038320266,0.0003118496,0.00013592477,0.0001422085,0.00009459677,0.53517526,0.06126181,0.0017482799,0.0012173059,0.39494497],"study_design_scores_gemma":[0.0000037467266,0.000045856174,0.000610903,0.0000054514862,0.000008860425,0.000021831602,0.000009102727,0.99309933,0.005843755,0.00017582055,0.0001697338,0.000005582559],"about_ca_topic_score_codex":0.002645022,"about_ca_topic_score_gemma":0.0015639858,"teacher_disagreement_score":0.002645022,"about_ca_system_score_codex":0.00034764546,"about_ca_system_score_gemma":0.00024818914,"threshold_uncertainty_score":0.005782366},"labels":[],"label_agreement":null},{"id":"W2913607312","doi":"10.1109/lgrs.2019.2895629","title":"Subpixel Mapping Based on Hopfield Neural Network With More Prior Information","year":2019,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Fundamental Research Funds for the Central Universities; National Aerospace Science Foundation of China; National Natural Science Foundation of China","keywords":"Subpixel rendering; Computer science; Hyperspectral imaging; Pixel; Artificial neural network; Artificial intelligence; Cover (algebra); Image (mathematics); Land cover; Pattern recognition (psychology); Path (computing); Image resolution; Computer vision; Land use","score_opus":0.007447326311286747,"score_gpt":0.1848755595556099,"score_spread":0.17742823324432314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913607312","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.062737435,0.00049680664,0.932329,0.00012274367,0.000051575862,0.00004180917,0.00006447388,0.0005979103,0.003558244],"genre_scores_gemma":[0.78199023,0.00041834748,0.21317701,0.00010116017,0.000046061577,0.000071991395,0.00015416069,0.000039446302,0.004001573],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99980766,0.00002625638,0.000010478097,0.00005935963,0.0000704395,0.000025791249],"domain_scores_gemma":[0.99982613,0.000060879393,0.000020721229,0.000026809385,0.0000541985,0.000011197108],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038551673,0.00051422475,0.0005332456,0.0004880069,0.0002834036,0.00050992926,0.00070207904,0.00048577847,0.0014620258],"category_scores_gemma":[0.00077670143,0.00023924759,0.00040247696,0.00051796983,0.00030605015,0.001236664,0.00045809493,0.00048568862,0.00019613326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015276496,0.000069215515,0.0014286235,0.00010687173,0.00007677857,0.0001295476,0.00011516095,0.50983596,0.022700423,0.0058006775,0.0014591699,0.45812488],"study_design_scores_gemma":[0.000004650308,0.000015676735,0.00026634606,0.0000028371023,0.000008290409,0.000021188178,0.0000061143346,0.99566615,0.0023680215,0.0013470557,0.00028704412,0.0000065658887],"about_ca_topic_score_codex":0.009704008,"about_ca_topic_score_gemma":0.009167968,"teacher_disagreement_score":0.009704008,"about_ca_system_score_codex":0.0006414729,"about_ca_system_score_gemma":0.0006017668,"threshold_uncertainty_score":0.019295037},"labels":[],"label_agreement":null},{"id":"W2914834436","doi":"10.1109/igarss.2019.8898776","title":"Cloud-Net: An End-To-End Cloud Detection Algorithm for Landsat 8 Imagery","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Cloud computing; Jaccard index; Computer science; Benchmark (surveying); Remote sensing; End-to-end principle; Algorithm; Convolutional neural network; Deep learning; Satellite imagery; Image (mathematics); Artificial intelligence; Data mining; Pattern recognition (psychology); Geography; Cartography","score_opus":0.02072242895538633,"score_gpt":0.25161459669403036,"score_spread":0.23089216773864402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914834436","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09468265,0.0012459027,0.8697784,0.0002734159,0.00039582097,0.00060012063,0.0033497317,0.02410814,0.0055658054],"genre_scores_gemma":[0.21180382,0.0004469025,0.7651598,0.00027563193,0.000102157144,0.00026061464,0.00957395,0.00080439,0.011572793],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99972266,0.000016548749,0.000013222369,0.00007084153,0.00012637736,0.00005042573],"domain_scores_gemma":[0.9998357,0.000019768453,0.000030483434,0.00003014519,0.00006491953,0.000018871322],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043819696,0.0012949593,0.0007229628,0.0014501343,0.00049055356,0.0006224716,0.001633103,0.0007731407,0.0029186155],"category_scores_gemma":[0.000589222,0.00036519638,0.00049496803,0.0010192911,0.00025082566,0.0009650049,0.0009386064,0.0008209492,0.0020341752],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005900662,0.00041491527,0.004170116,0.00018780802,0.00021117736,0.0002036606,0.000042849802,0.043518025,0.044813782,0.0019944252,0.035698783,0.8681544],"study_design_scores_gemma":[0.000056461315,0.00011007112,0.0029079276,0.00001828592,0.00002395922,0.00020752611,0.000021581987,0.94266266,0.04243085,0.0017459826,0.00978801,0.000026823738],"about_ca_topic_score_codex":0.008167844,"about_ca_topic_score_gemma":0.017876502,"teacher_disagreement_score":0.008167844,"about_ca_system_score_codex":0.00064915075,"about_ca_system_score_gemma":0.0008000554,"threshold_uncertainty_score":0.016240597},"labels":[],"label_agreement":null},{"id":"W2921479503","doi":"10.1117/12.2503907","title":"Hyperspectral imaging for intraoperative diagnosis of colon cancer metastasis in a liver","year":2019,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Photon Etc (Canada)","funders":"","keywords":"Hyperspectral imaging; H&E stain; Cancer; Metastasis; Medicine; Colorectal cancer; Liver cancer; Radiology; Colonic cancer; Pathology; Internal medicine; Artificial intelligence; Immunohistochemistry; Computer science","score_opus":0.015228404330085338,"score_gpt":0.2520446995068575,"score_spread":0.23681629517677213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2921479503","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90321076,0.0014162101,0.09319094,0.00018999582,0.000029724906,0.000056268644,0.00014277197,0.00024042354,0.0015228501],"genre_scores_gemma":[0.9452139,0.0006280112,0.053500596,0.000032509794,0.000014175293,0.000021332362,0.00008572831,0.000011877663,0.00049189216],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99987805,0.00003664843,0.0000051510324,0.000019092979,0.000048457383,0.00001257893],"domain_scores_gemma":[0.9998617,0.000054644028,0.00002277487,0.000007899375,0.00003842107,0.000014556094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036539853,0.0002748663,0.000130525,0.00065025606,0.00012330966,0.00016932387,0.00010963889,0.00022920297,0.0005865515],"category_scores_gemma":[0.00039866203,0.00012452577,0.00012992225,0.00020440806,0.00015078751,0.0002630271,0.00018882085,0.00025607675,0.00018574431],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034369755,0.000054878525,0.015687594,0.000106570726,0.000023924564,0.0002520671,0.00007256695,0.0011457017,0.9355162,0.0001689944,0.00018879947,0.046438962],"study_design_scores_gemma":[0.000026339203,0.000626307,0.107348755,0.000037284342,0.0001379294,0.0038596902,0.0003531767,0.14144348,0.7433798,0.00055231457,0.0021701348,0.00006496227],"about_ca_topic_score_codex":0.00037351155,"about_ca_topic_score_gemma":0.0012082936,"teacher_disagreement_score":0.00065025606,"about_ca_system_score_codex":0.00007734249,"about_ca_system_score_gemma":0.00014559676,"threshold_uncertainty_score":0.001962185},"labels":[],"label_agreement":null},{"id":"W2922146558","doi":"10.1016/j.jag.2019.03.002","title":"Hyperspectral band selection using the N-dimensional Spectral Solid Angle method for the improved discrimination of spectrally similar targets","year":2019,"lang":"en","type":"article","venue":"International Journal of Applied Earth Observation and Geoinformation","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"University of Alberta","keywords":"Hyperspectral imaging; Spectral bands; Computer science; Selection (genetic algorithm); Dimensionality reduction; Pattern recognition (psychology); Feature selection; Curse of dimensionality; Wavelength; Remote sensing; Artificial intelligence; Geology; Physics; Optics","score_opus":0.01710694957487697,"score_gpt":0.25869980619306066,"score_spread":0.2415928566181837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2922146558","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3321961,0.00052152737,0.66178936,0.00014010372,0.00006838172,0.00005418991,0.00026701434,0.0007389097,0.004224396],"genre_scores_gemma":[0.6761753,0.0005665277,0.31974688,0.000070408656,0.000055235825,0.000061840896,0.00067693944,0.00010221134,0.0025446494],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999801,0.00004510333,0.000008054487,0.000035057972,0.00008729578,0.000023503611],"domain_scores_gemma":[0.9998111,0.000048059643,0.000022793252,0.000025021363,0.00007641598,0.000016694883],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033807062,0.00040896994,0.00028254327,0.00084652053,0.0002364697,0.0003579671,0.00031683902,0.00020967089,0.001105316],"category_scores_gemma":[0.0004009488,0.00011571283,0.00036054812,0.00070292497,0.00028045313,0.0005915042,0.0004521178,0.00032954017,0.0004924719],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00056217104,0.00025540972,0.0044708904,0.000116356576,0.000070522154,0.0000841845,0.00010456398,0.014545727,0.5435299,0.0032723555,0.0020784475,0.4309095],"study_design_scores_gemma":[0.000032216343,0.00013844155,0.018047778,0.000015961576,0.00010041568,0.0003683846,0.000098985685,0.79118735,0.18326144,0.0016786285,0.0050153793,0.000055073553],"about_ca_topic_score_codex":0.0010437812,"about_ca_topic_score_gemma":0.0022026247,"teacher_disagreement_score":0.001105316,"about_ca_system_score_codex":0.00010106284,"about_ca_system_score_gemma":0.0003723822,"threshold_uncertainty_score":0.0036976337},"labels":[],"label_agreement":null},{"id":"W2924420510","doi":"10.1016/j.jglr.2019.03.005","title":"Evaluating visible derivative spectroscopy by varimax-rotated, principal component analysis of aerial hyperspectral images from the western basin of Lake Erie","year":2019,"lang":"en","type":"article","venue":"Journal of Great Lakes Research","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Ohio Sea Grant College, Ohio State University; National Aeronautics and Space Administration","keywords":"Hyperspectral imaging; Remote sensing; Principal component analysis; Multispectral image; Smoothing; Noise (video); Imaging spectroscopy; Residual; Computer science; Artificial intelligence; Environmental science; Computer vision; Geology; Image (mathematics); Algorithm","score_opus":0.06485872670062508,"score_gpt":0.36890459235509837,"score_spread":0.3040458656544733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2924420510","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99543285,0.000046121866,0.0033176579,0.000015966341,0.0000023174075,0.000008994627,0.00014347442,0.0000646807,0.000967986],"genre_scores_gemma":[0.9901636,0.00007014041,0.008689137,0.000008838588,0.00000179691,0.000009729543,0.0003528448,0.000018874833,0.00068513624],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999008,0.000010858016,0.0000062702848,0.000021839283,0.000042513853,0.000017610877],"domain_scores_gemma":[0.9999194,0.000017325736,0.000009043297,0.00000515923,0.00004444259,0.0000045495667],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021908706,0.00020229854,0.00012270418,0.00089132163,0.00018586477,0.0004078483,0.000113912334,0.00014926643,0.0005073374],"category_scores_gemma":[0.0004371479,0.00010268326,0.00015906972,0.0007226322,0.00014056479,0.00022237182,0.00016295037,0.0001120381,0.00016880623],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043267204,0.00022104595,0.2130622,0.00018839944,0.00018699802,0.00024876508,0.00076119055,0.015874794,0.5454684,0.00045796458,0.001460209,0.22163732],"study_design_scores_gemma":[0.000013261067,0.000053821615,0.8940588,0.000009311295,0.00006755998,0.00007791494,0.00043397414,0.059748568,0.043891877,0.00008407968,0.0015383894,0.00002236782],"about_ca_topic_score_codex":0.028202938,"about_ca_topic_score_gemma":0.06317181,"teacher_disagreement_score":0.028202938,"about_ca_system_score_codex":0.00028164606,"about_ca_system_score_gemma":0.0003229783,"threshold_uncertainty_score":0.0560776},"labels":[],"label_agreement":null},{"id":"W2937864594","doi":"","title":"Detecting change in disturbed areas in Grasslands National Park using remote sensing techniques","year":2005,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Parks Canada; University of Saskatchewan","keywords":"Remote sensing; National park; Geography; Change detection; Environmental science; Environmental resource management; Forestry; Archaeology","score_opus":0.04483141289552283,"score_gpt":0.2883004819562403,"score_spread":0.24346906906071747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2937864594","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.998271,0.00005594347,0.0010004967,0.000015266203,0.0000042619554,0.00001267619,0.000097730575,0.00003989286,0.0005026466],"genre_scores_gemma":[0.9968033,0.000036429683,0.002730553,0.000007290086,0.0000073304377,0.000007074863,0.00021128176,0.0000038480703,0.00019286711],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9998235,0.000030162362,0.000016125607,0.000041003597,0.000055977813,0.00003324302],"domain_scores_gemma":[0.9994578,0.00014179223,0.00014565061,0.00002879742,0.0001561328,0.00006994193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036077833,0.00021216899,0.00023083927,0.0020638658,0.0002896277,0.0004431152,0.00027702894,0.00034813018,0.0004882409],"category_scores_gemma":[0.00072483334,0.00017431399,0.00019843965,0.000898214,0.00022265803,0.000390116,0.00020261241,0.00016655508,0.00014808748],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00052507134,0.00023915237,0.88826805,0.00009223075,0.00011537917,0.0003473647,0.00049383217,0.0040284293,0.040267415,0.00011633846,0.0005304669,0.06497613],"study_design_scores_gemma":[0.000019130324,0.000067429806,0.97672063,0.00000627238,0.00003953159,0.00016937034,0.00028777556,0.020342363,0.001996131,0.00005326217,0.00029125635,0.000006790091],"about_ca_topic_score_codex":0.015809612,"about_ca_topic_score_gemma":0.035254873,"teacher_disagreement_score":0.9841904,"about_ca_system_score_codex":0.00028993658,"about_ca_system_score_gemma":0.00021412098,"threshold_uncertainty_score":0.03143519},"labels":[],"label_agreement":null},{"id":"W2940368062","doi":"10.1080/01431161.2019.1602792","title":"Unsupervised change detection of VHR remote sensing images based on multi-resolution Markov Random Field in wavelet domain","year":2019,"lang":"en","type":"article","venue":"International Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Wavelet; Change detection; Markov random field; Artificial intelligence; Pattern recognition (psychology); Computer science; Wavelet transform; Scale (ratio); Robustness (evolution); Feature (linguistics); Remote sensing; Computer vision; Image (mathematics); Geography; Image segmentation","score_opus":0.01769889526432237,"score_gpt":0.25048266273721864,"score_spread":0.23278376747289628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2940368062","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01762777,0.00013477205,0.98140275,0.000054963668,0.000018244808,0.000033951346,0.00004471396,0.00034053365,0.00034229658],"genre_scores_gemma":[0.4382055,0.0005273451,0.55827,0.0001280657,0.00012429575,0.00015081308,0.00058363297,0.00018118175,0.0018291518],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916875,0.00014749877,0.000041296047,0.00027130888,0.00029260322,0.000078418685],"domain_scores_gemma":[0.9990823,0.00034363123,0.00020633049,0.00011106234,0.00021408622,0.00004257903],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095689454,0.0006709446,0.00097088725,0.002154117,0.00033240646,0.000713713,0.0011800696,0.0006815042,0.00046034492],"category_scores_gemma":[0.0019425413,0.00045025744,0.001401872,0.000971428,0.0006021851,0.0013934599,0.0005584118,0.00096006383,0.00028879746],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026701187,0.0002844851,0.010266954,0.00031234598,0.00029568205,0.00034129,0.00030507208,0.25878736,0.07234887,0.011008933,0.0025232555,0.6432588],"study_design_scores_gemma":[0.000009558316,0.000044229335,0.0032540937,0.000009955004,0.000032907312,0.0001730851,0.000028263748,0.9856857,0.0075587425,0.0023797217,0.0007948282,0.000028924955],"about_ca_topic_score_codex":0.0031782642,"about_ca_topic_score_gemma":0.0035661485,"teacher_disagreement_score":0.0031782642,"about_ca_system_score_codex":0.00052527984,"about_ca_system_score_gemma":0.00057030644,"threshold_uncertainty_score":0.006319523},"labels":[],"label_agreement":null},{"id":"W2943446949","doi":"10.1109/jstars.2019.2910539","title":"Subpixel Land Cover Mapping Based on Dual Processing Paths for Hyperspectral Image","year":2019,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Subpixel rendering; Hyperspectral imaging; Computer science; Image resolution; Artificial intelligence; Computer vision; Multispectral image; Image processing; Pixel; Pattern recognition (psychology); Remote sensing; Image (mathematics); Geology","score_opus":0.020063973198561798,"score_gpt":0.2197904687513987,"score_spread":0.19972649555283692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2943446949","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03883503,0.00027976756,0.9581767,0.000119854914,0.00003118722,0.000043655502,0.00011299201,0.0007682617,0.0016325484],"genre_scores_gemma":[0.30428508,0.0005001062,0.6917673,0.000095270414,0.000046710225,0.000109797256,0.00053594564,0.00012500853,0.0025348293],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997868,0.000029072926,0.0000072070284,0.00006353164,0.00009086152,0.000022667988],"domain_scores_gemma":[0.9998441,0.000038805832,0.000021895998,0.000035330144,0.00004877401,0.000011064429],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024882436,0.00070287473,0.00035020747,0.0008752538,0.00026959224,0.00047677485,0.00057859364,0.00038156952,0.0012605877],"category_scores_gemma":[0.00051017693,0.00027090628,0.0005721238,0.0009782135,0.00039003533,0.0015307086,0.0007613073,0.00065199303,0.00034947123],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022432135,0.000115938936,0.002072209,0.00020414488,0.00008908364,0.00022390927,0.0002349021,0.103908636,0.14753357,0.009425517,0.0030331968,0.7329346],"study_design_scores_gemma":[0.000016502247,0.00006638214,0.001891451,0.00000938836,0.00003144355,0.00022517567,0.00004743602,0.9450332,0.04095533,0.007076479,0.004617171,0.000030079764],"about_ca_topic_score_codex":0.0020076383,"about_ca_topic_score_gemma":0.0029304202,"teacher_disagreement_score":0.0020076383,"about_ca_system_score_codex":0.00031482853,"about_ca_system_score_gemma":0.0005181318,"threshold_uncertainty_score":0.0042170286},"labels":[],"label_agreement":null},{"id":"W2944413439","doi":"10.1109/tcyb.2019.2915094","title":"Generative Adversarial Networks and Conditional Random Fields for Hyperspectral Image Classification","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Cybernetics","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":164,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"China Scholarship Council; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Discriminative model; Conditional random field; Artificial intelligence; Pattern recognition (psychology); Softmax function; CRFS; Computer science; Hyperspectral imaging; Machine learning; Deep learning","score_opus":0.013554960345590495,"score_gpt":0.2282175832358199,"score_spread":0.2146626228902294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2944413439","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0074093756,0.00047542172,0.98973316,0.000294271,0.00003716684,0.000025557141,0.00011413243,0.0005557326,0.0013552264],"genre_scores_gemma":[0.7352395,0.00097000855,0.25505722,0.0006619682,0.00021710692,0.00019927828,0.0010530065,0.00027188385,0.0063300473],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990754,0.00042365986,0.000025436613,0.00022019717,0.00016514606,0.00009007954],"domain_scores_gemma":[0.99789125,0.001455719,0.00020345175,0.00021777037,0.00016827667,0.00006347968],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017838251,0.0011935931,0.001009773,0.0007672288,0.0002751264,0.0006295678,0.0015114149,0.0008748598,0.0017315997],"category_scores_gemma":[0.0032884174,0.00042808437,0.0008501987,0.0008483454,0.0011853753,0.0011989126,0.0010569099,0.0023695247,0.0005276888],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055254706,0.000044971996,0.0005532064,0.0000485053,0.000043124433,0.000044968478,0.000037164773,0.93495804,0.0012416783,0.021099875,0.0021711558,0.039702035],"study_design_scores_gemma":[0.0000016491352,0.00000589456,0.000060234535,0.0000030206722,0.0000022196618,0.000007760958,0.0000017122702,0.9934683,0.00024180688,0.005959226,0.00024473446,0.0000034314662],"about_ca_topic_score_codex":0.0043572946,"about_ca_topic_score_gemma":0.004806141,"teacher_disagreement_score":0.0043572946,"about_ca_system_score_codex":0.0011700217,"about_ca_system_score_gemma":0.0006998742,"threshold_uncertainty_score":0.009433866},"labels":[],"label_agreement":null},{"id":"W2945493762","doi":"10.1109/jstars.2019.2912826","title":"Sparse-SpatialCEM for Hyperspectral Target Detection","year":2019,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Higher Education Discipline Innovation Project","keywords":"Hyperspectral imaging; Pixel; Computer science; Object detection; Artificial intelligence; Minification; Pattern recognition (psychology); Algorithm; Energy minimization; Computer vision","score_opus":0.02109966377647141,"score_gpt":0.21515118841527478,"score_spread":0.19405152463880337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945493762","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016052409,0.00015562265,0.9968851,0.00013090814,0.000030637286,0.000024482146,0.00004232403,0.00015768115,0.0009680005],"genre_scores_gemma":[0.10566449,0.0005108352,0.88926625,0.0003197222,0.00011124767,0.00019289451,0.00039088546,0.00013694911,0.0034067752],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999627,0.00012602215,0.000014833434,0.000068978414,0.0001396767,0.000023546318],"domain_scores_gemma":[0.9993081,0.0003277264,0.00009267621,0.00007886156,0.00016372658,0.000028927225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008463935,0.00089675514,0.00048487494,0.0005940724,0.00030885264,0.00059447705,0.0009696706,0.0010618268,0.0026395104],"category_scores_gemma":[0.00306223,0.0002786275,0.00051583303,0.0011093583,0.00067398045,0.0010883404,0.0011611942,0.0012844354,0.00089771143],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001617016,0.00010409767,0.00073484494,0.0003910226,0.00006238041,0.00021671293,0.000119493314,0.545686,0.029185254,0.07817296,0.011997671,0.33316788],"study_design_scores_gemma":[0.0000061582623,0.000017162103,0.000115809686,0.0000074330515,0.000003568302,0.0000891999,0.000011347439,0.9816896,0.004699575,0.009628588,0.0037221075,0.000009385958],"about_ca_topic_score_codex":0.001093446,"about_ca_topic_score_gemma":0.0015800317,"teacher_disagreement_score":0.0026395104,"about_ca_system_score_codex":0.00045749012,"about_ca_system_score_gemma":0.00088400516,"threshold_uncertainty_score":0.008830011},"labels":[],"label_agreement":null},{"id":"W2951287817","doi":"10.48550/arxiv.1902.08347","title":"A laboratory-created dataset with ground-truth for hyperspectral unmixing evaluation","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Hyperspectral imaging; Ground truth; Pixel; Computer science; Ranging; Artificial intelligence; Remote sensing; Pattern recognition (psychology); Geology","score_opus":0.07943654343078144,"score_gpt":0.2037060634413369,"score_spread":0.12426952001055547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951287817","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1415577,0.0035609945,0.0724316,0.0012117032,0.001569603,0.001857757,0.72820824,0.022455523,0.027146915],"genre_scores_gemma":[0.042647917,0.00040014004,0.056688458,0.00026916602,0.00008321533,0.0007746922,0.89517117,0.0005143207,0.0034508824],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99705637,0.00045022607,0.00023354759,0.00092739303,0.0010302914,0.00030219788],"domain_scores_gemma":[0.9978649,0.0003789001,0.00015376562,0.00071774895,0.0007579588,0.0001266803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020128903,0.0031232892,0.0013778993,0.003629461,0.0011624597,0.0015900825,0.0029682314,0.0023106742,0.0054782433],"category_scores_gemma":[0.0032286935,0.00037368017,0.0016704331,0.0036172848,0.0010391284,0.0016488933,0.0019488455,0.0018723613,0.0075908466],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010261489,0.0024417888,0.014946585,0.0030402166,0.00054950075,0.0007898482,0.00022337794,0.034912154,0.023874667,0.0039058006,0.6819196,0.23237032],"study_design_scores_gemma":[0.0007809656,0.0008342404,0.06426481,0.0008744661,0.0003536179,0.0027694197,0.0011959512,0.19036475,0.07167471,0.009290657,0.6571626,0.0004337649],"about_ca_topic_score_codex":0.009329596,"about_ca_topic_score_gemma":0.022623764,"teacher_disagreement_score":0.009329596,"about_ca_system_score_codex":0.0015133158,"about_ca_system_score_gemma":0.0013029217,"threshold_uncertainty_score":0.018550575},"labels":[],"label_agreement":null},{"id":"W2953225243","doi":"10.48550/arxiv.1612.01594","title":"Object Classification with Joint Projection and Low-rank Dictionary Learning","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Artificial intelligence; Outlier; Redundancy (engineering); Pattern recognition (psychology); Graph; Rank (graph theory); Projection (relational algebra); Dictionary learning; Machine learning; Class (philosophy); Classifier (UML); Data mining; Sparse approximation; Mathematics; Algorithm; Theoretical computer science","score_opus":0.05295534679842595,"score_gpt":0.16703666754636887,"score_spread":0.11408132074794292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2953225243","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005330388,0.00016013545,0.99310875,0.00012333979,0.0000276787,0.00002900039,0.00006047683,0.0006215346,0.0005387289],"genre_scores_gemma":[0.25770947,0.00053802255,0.7330179,0.00043275015,0.00018339702,0.000310457,0.0013961974,0.00027195865,0.0061398037],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873227,0.0003004381,0.00006123307,0.0003815528,0.00038734113,0.00013721295],"domain_scores_gemma":[0.9986375,0.00047388856,0.00014261148,0.00034028987,0.00029717627,0.00010858336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009816501,0.0012648718,0.0017743321,0.0010801387,0.00042011682,0.001541849,0.0020698495,0.0016296314,0.0024862636],"category_scores_gemma":[0.0038780686,0.0006464463,0.001007368,0.0019273133,0.0012317061,0.0023811236,0.0023803092,0.0027310553,0.0017153176],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002583605,0.000198237,0.00088182633,0.0002051847,0.00011508627,0.00013975489,0.00012532854,0.34833914,0.01269516,0.025373776,0.009554591,0.6021135],"study_design_scores_gemma":[0.000011567709,0.000034070505,0.000073795956,0.0000043050777,0.0000048229945,0.00002979972,0.000008802968,0.9907499,0.0014238693,0.0069653196,0.00068449177,0.00000928276],"about_ca_topic_score_codex":0.0050570876,"about_ca_topic_score_gemma":0.0046967026,"teacher_disagreement_score":0.0050570876,"about_ca_system_score_codex":0.00062800094,"about_ca_system_score_gemma":0.0011429944,"threshold_uncertainty_score":0.010055304},"labels":[],"label_agreement":null},{"id":"W2954521826","doi":"10.1109/lgrs.2019.2919918","title":"Subpixel Land-Cover Mapping Based on Extended Random Walker","year":2019,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"East China Normal University; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Subpixel rendering; Artificial intelligence; Computer vision; Upsampling; Image resolution; Computer science; Interpolation (computer graphics); Segmentation; Image segmentation; Object (grammar); Pixel; Pattern recognition (psychology); Principal component analysis; Image (mathematics)","score_opus":0.009663894096296633,"score_gpt":0.19900572645959413,"score_spread":0.1893418323632975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2954521826","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047533825,0.00019868024,0.9505114,0.00006361075,0.000032733584,0.00002776442,0.00005483391,0.0005849221,0.0009922507],"genre_scores_gemma":[0.5837245,0.00028326927,0.41210312,0.00008007716,0.000045858316,0.00011554932,0.00037646497,0.00012674912,0.003144325],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997403,0.00005825018,0.000011618171,0.00007066997,0.000093837385,0.000025447474],"domain_scores_gemma":[0.99980265,0.000064084634,0.000026399719,0.00003930374,0.000047523525,0.000019951436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003130656,0.00040773785,0.00078859343,0.0008553488,0.00024922064,0.00042703707,0.00076213735,0.0004527289,0.0009471461],"category_scores_gemma":[0.0007489174,0.00027842462,0.00044617816,0.0009591468,0.0003003339,0.0010855363,0.0005981136,0.00038355167,0.0004326647],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024395237,0.00011117816,0.0033343877,0.0001916124,0.00013280548,0.00036627948,0.00018742449,0.4183189,0.08233015,0.024595486,0.002229041,0.4679587],"study_design_scores_gemma":[0.000004507542,0.000016052352,0.00034533592,0.0000018606437,0.0000043496034,0.000059370017,0.0000066001858,0.99356514,0.0027293246,0.0026072422,0.0006515927,0.000008557973],"about_ca_topic_score_codex":0.0018371239,"about_ca_topic_score_gemma":0.0020485255,"teacher_disagreement_score":0.0018371239,"about_ca_system_score_codex":0.00024316793,"about_ca_system_score_gemma":0.0003126188,"threshold_uncertainty_score":0.0036528707},"labels":[],"label_agreement":null},{"id":"W2956786564","doi":"10.1007/s00521-019-04349-9","title":"A deep learning framework for land-use/land-cover mapping and analysis using multispectral satellite imagery","year":2019,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":101,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Multispectral image; Computer science; Land cover; Deep learning; Artificial intelligence; Satellite imagery; Context (archaeology); Satellite; Remote sensing; Pixel; Pattern recognition (psychology); Field (mathematics); Contextual image classification; Convolutional neural network; Scale (ratio); Land use; Image (mathematics); Cartography; Geography; Mathematics","score_opus":0.02146645467919889,"score_gpt":0.2638803138753766,"score_spread":0.2424138591961777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2956786564","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019557368,0.00047745765,0.97692126,0.00028165997,0.0000592171,0.00003631608,0.00036829783,0.0011100258,0.0011884605],"genre_scores_gemma":[0.4544278,0.00075383653,0.5315948,0.00032300645,0.00013159555,0.00016385563,0.0015987739,0.0001759558,0.010830373],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998559,0.000027330048,0.000008480838,0.000035533914,0.000046588688,0.000026221764],"domain_scores_gemma":[0.99981695,0.00005251047,0.000017938073,0.000023370592,0.00007213246,0.00001707118],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053019106,0.00048434487,0.0005282142,0.00051493966,0.00030343648,0.0006773521,0.0011594545,0.0007255442,0.0018391624],"category_scores_gemma":[0.000765374,0.00038220224,0.0007111961,0.0006496369,0.0002829452,0.0007445297,0.00095743896,0.00105436,0.000526595],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000938835,0.00021283099,0.001251349,0.000077830664,0.00013073036,0.000084451116,0.000042585423,0.5629469,0.00973997,0.013894048,0.006169012,0.40535635],"study_design_scores_gemma":[0.0000018579836,0.0000071627173,0.000134711,0.000002659982,0.0000046359464,0.000005521043,0.000002067477,0.99694103,0.00057145744,0.0019174031,0.00040913452,0.000002337262],"about_ca_topic_score_codex":0.023581935,"about_ca_topic_score_gemma":0.032734595,"teacher_disagreement_score":0.023581935,"about_ca_system_score_codex":0.00070473365,"about_ca_system_score_gemma":0.0011263802,"threshold_uncertainty_score":0.046889305},"labels":[],"label_agreement":null},{"id":"W2959844068","doi":"10.1364/hise.2019.htu3b.4","title":"Material identification using fuzzy-classification of high resolution hyperspectral imagery of an urban area","year":2019,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Hyperspectral imaging; Remote sensing; Image resolution; Computer science; Geographic information system; Environmental science; Identification (biology); Geography; Computer vision","score_opus":0.022101200009156143,"score_gpt":0.2323141818823002,"score_spread":0.21021298187314408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2959844068","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61952853,0.00029394095,0.37123907,0.00016157766,0.00006693731,0.00016108791,0.00039140767,0.0005760029,0.0075814766],"genre_scores_gemma":[0.9162825,0.00009919248,0.08174216,0.00003845378,0.000022178812,0.000043206106,0.0003843809,0.000013340063,0.0013747014],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99981457,0.000017340135,0.00001619483,0.000042673837,0.00008104476,0.00002821096],"domain_scores_gemma":[0.9997491,0.000056566838,0.000040441842,0.000018680894,0.00012064577,0.000014603938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035422458,0.00032118932,0.0002474713,0.0017184732,0.00036501003,0.0006568293,0.00039088377,0.0005561098,0.00074387545],"category_scores_gemma":[0.0006086427,0.000118598284,0.00042500105,0.00058801216,0.00030045648,0.00040628738,0.00018997102,0.00017168855,0.00026169085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006509683,0.00043288307,0.027585555,0.00030838343,0.00014042495,0.00041657477,0.0003276513,0.18884617,0.11779669,0.0019381149,0.0034179708,0.6581386],"study_design_scores_gemma":[0.00000988496,0.00009102175,0.01755235,0.000023904808,0.000044322103,0.000104303115,0.00016239307,0.9633428,0.016756685,0.000870076,0.0010209505,0.00002132955],"about_ca_topic_score_codex":0.0091366945,"about_ca_topic_score_gemma":0.012703263,"teacher_disagreement_score":0.0091366945,"about_ca_system_score_codex":0.0005057614,"about_ca_system_score_gemma":0.00034835376,"threshold_uncertainty_score":0.018167078},"labels":[],"label_agreement":null},{"id":"W2963462769","doi":"10.1609/aaai.v32i1.12146","title":"Generative Adversarial Networks and Probabilistic Graph Models for Hyperspectral Image Classification","year":2018,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Hyperspectral imaging; Pattern recognition (psychology); Computer science; Discriminative model; Artificial intelligence; Probabilistic logic; Discriminator; Machine learning","score_opus":0.08009929386753985,"score_gpt":0.28090356263237165,"score_spread":0.20080426876483182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963462769","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011920516,0.0004942212,0.9850662,0.0004816289,0.000039009246,0.000027347145,0.00013043893,0.00050992944,0.001330731],"genre_scores_gemma":[0.7956619,0.0009846587,0.19484423,0.0005113017,0.00020739269,0.00022118921,0.0009884221,0.00021197382,0.0063688313],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993279,0.00029992085,0.000021371274,0.00015628261,0.00013503133,0.000059637652],"domain_scores_gemma":[0.99748284,0.0018892888,0.00021974703,0.00019078537,0.00015255727,0.0000647672],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001452196,0.0010740147,0.0009082145,0.0008807674,0.00032308887,0.00074342865,0.0014354502,0.00096420816,0.0016560678],"category_scores_gemma":[0.0037941441,0.0005542154,0.00091928,0.0009251023,0.0011777355,0.0011891202,0.0012999492,0.002664836,0.00041900255],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026833512,0.00002168539,0.00030595905,0.000020748324,0.000025700123,0.000030044654,0.000025065548,0.97095484,0.00047328472,0.012188742,0.00084936037,0.0150777595],"study_design_scores_gemma":[0.000001070264,0.0000026274877,0.000036354566,0.0000016575467,0.0000014388894,0.00000389093,0.0000011573308,0.99344057,0.000096053576,0.006310851,0.000102276,0.0000019862696],"about_ca_topic_score_codex":0.004642093,"about_ca_topic_score_gemma":0.0050685327,"teacher_disagreement_score":0.004642093,"about_ca_system_score_codex":0.0012830988,"about_ca_system_score_gemma":0.0005294883,"threshold_uncertainty_score":0.00930953},"labels":[],"label_agreement":null},{"id":"W2964287450","doi":"10.3390/rs11141713","title":"Comparing Deep Neural Networks, Ensemble Classifiers, and Support Vector Machine Algorithms for Object-Based Urban Land Use/Land Cover Classification","year":2019,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":229,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Autoencoder; Support vector machine; Computer science; Pattern recognition (psychology); Land cover; Random forest; Classifier (UML); Contextual image classification; Artificial neural network; Boosting (machine learning); Machine learning; Land use; Image (mathematics)","score_opus":0.031035162874435373,"score_gpt":0.23970417958071746,"score_spread":0.2086690167062821,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964287450","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7368438,0.018501509,0.22865638,0.0012576687,0.0011595435,0.00042294187,0.0012788656,0.0022475785,0.009631706],"genre_scores_gemma":[0.9073161,0.0024724104,0.08547839,0.00024397696,0.00020464197,0.00020984924,0.0021287203,0.000104674014,0.0018413116],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976914,0.0007012759,0.00022257604,0.0004280441,0.0007291066,0.00022775566],"domain_scores_gemma":[0.9940362,0.003180891,0.00035128003,0.00050914515,0.0017201982,0.000202241],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0059608966,0.0018959092,0.0018201874,0.0023882405,0.0005008994,0.0011618969,0.0015265928,0.001382045,0.0008654976],"category_scores_gemma":[0.00977923,0.00036894117,0.0009020731,0.001617275,0.0003919306,0.0027678302,0.0011705004,0.0015571668,0.00042174634],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017856013,0.0008783519,0.019912245,0.00047533048,0.00076899,0.00006956521,0.0001218911,0.46068224,0.0020671561,0.0018842252,0.0045974213,0.506757],"study_design_scores_gemma":[0.000022845921,0.0003314671,0.0024989224,0.000031223753,0.00007713683,0.0000217281,0.000058314625,0.9940526,0.0014584956,0.0009245096,0.0005088706,0.0000139839285],"about_ca_topic_score_codex":0.008755219,"about_ca_topic_score_gemma":0.008095193,"teacher_disagreement_score":0.008755219,"about_ca_system_score_codex":0.0011677581,"about_ca_system_score_gemma":0.000940007,"threshold_uncertainty_score":0.0315246},"labels":[],"label_agreement":null},{"id":"W2964536579","doi":"10.1109/crv.2019.00014","title":"On Building Classification from Remote Sensor Imagery Using Deep Neural Networks and the Relation Between Classification and Reconstruction Accuracy Using Border Localization as Proxy","year":2019,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Jaccard index; Computer science; Artificial intelligence; Convolutional neural network; Pattern recognition (psychology); Feature (linguistics); Segmentation; Weighting; Redundancy (engineering); Contextual image classification; Context (archaeology); Feature extraction; Data mining; Image (mathematics)","score_opus":0.02497976691915137,"score_gpt":0.27226681690071297,"score_spread":0.2472870499815616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964536579","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8194532,0.0044400487,0.1641803,0.0010577658,0.00021426131,0.00014299681,0.0014282896,0.0027090118,0.006374118],"genre_scores_gemma":[0.93846613,0.0007720538,0.052791614,0.00014845013,0.00011748839,0.0000512151,0.0047345813,0.00013189383,0.0027865209],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99847573,0.0004151148,0.000110641384,0.0003897319,0.00043034196,0.00017849627],"domain_scores_gemma":[0.995284,0.0028688295,0.0005840602,0.0005354618,0.00060328026,0.00012424341],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031005545,0.0016384567,0.0010522612,0.002450015,0.0005336842,0.0014172615,0.0015126206,0.0019061946,0.001207597],"category_scores_gemma":[0.009542565,0.0002877709,0.00058632594,0.002231045,0.0008523356,0.002337142,0.0011020524,0.0012439092,0.00089254626],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007860093,0.0004692357,0.024310412,0.00023819346,0.0003186399,0.00016962289,0.00011784985,0.56138134,0.0060542016,0.002455107,0.006389735,0.3973097],"study_design_scores_gemma":[0.000009141947,0.00005526455,0.0028862157,0.000020164225,0.000018583916,0.00003763439,0.00003158609,0.9919126,0.003311367,0.0013991336,0.0003073345,0.0000109299435],"about_ca_topic_score_codex":0.009587513,"about_ca_topic_score_gemma":0.013331952,"teacher_disagreement_score":0.009587513,"about_ca_system_score_codex":0.0011765744,"about_ca_system_score_gemma":0.0006048993,"threshold_uncertainty_score":0.019063413},"labels":[],"label_agreement":null},{"id":"W2965516077","doi":"10.5897/jgrp.9000034","title":"Comparison of object-based and pixel based infrared airborne image classification methods using DEM thematic layer","year":2007,"lang":"en","type":"article","venue":"Journal of Geography and Regional Planning","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Thematic map; Land cover; Pixel; Object (grammar); Geography; Remote sensing; Artificial intelligence; Segmentation; Cartography; Object based; Contextual image classification; Computer science; Cover (algebra); Pattern recognition (psychology); Computer vision; Image (mathematics); Land use; Engineering","score_opus":0.08041880365613424,"score_gpt":0.3720888075945139,"score_spread":0.29167000393837966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2965516077","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7348032,0.0007323506,0.24499774,0.00022646008,0.00008852586,0.00029394912,0.0012346614,0.0022341984,0.015388802],"genre_scores_gemma":[0.77438504,0.00046571784,0.21941832,0.00007685982,0.000020475623,0.00010098553,0.0012303424,0.00013974612,0.0041624987],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991013,0.000206286,0.0000541991,0.00011005173,0.0004742825,0.000053907894],"domain_scores_gemma":[0.99780697,0.00071642443,0.0001213412,0.00014044195,0.0011738227,0.00004111818],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019274307,0.000425362,0.00029349566,0.0022349686,0.00027258205,0.0008271355,0.00054627156,0.00034206445,0.0013396076],"category_scores_gemma":[0.0035244448,0.00018665829,0.00030306814,0.0014703437,0.0002404046,0.0006621387,0.00029329286,0.00018424515,0.00066925224],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00081223674,0.00022863415,0.08482889,0.0005278913,0.00035446405,0.00016903649,0.0008374846,0.018894507,0.0490186,0.0014250599,0.0030384318,0.8398647],"study_design_scores_gemma":[0.00016140439,0.0005426684,0.34420362,0.00013260401,0.00054182543,0.0009328479,0.0016520544,0.5573298,0.07983908,0.0014702766,0.013021848,0.00017200883],"about_ca_topic_score_codex":0.021016445,"about_ca_topic_score_gemma":0.03552166,"teacher_disagreement_score":0.021016445,"about_ca_system_score_codex":0.0007070171,"about_ca_system_score_gemma":0.0004352406,"threshold_uncertainty_score":0.04178822},"labels":[],"label_agreement":null},{"id":"W2967626412","doi":"10.3390/rs11161854","title":"A PolSAR Change Detection Index Based on Neighborhood Information for Flood Mapping","year":2019,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":58,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre For Cold Ocean Resources Engineering; Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Change detection; Neighbourhood (mathematics); Wishart distribution; Synthetic aperture radar; Remote sensing; Statistics; Computer science; Environmental science; Cartography; Mathematics; Geography; Multivariate statistics","score_opus":0.018779455395332295,"score_gpt":0.21044936605630726,"score_spread":0.19166991066097497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2967626412","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.794188,0.00047603715,0.19732182,0.00006595027,0.000071984316,0.00017967519,0.0007887228,0.0007946617,0.0061131204],"genre_scores_gemma":[0.94508034,0.0001221211,0.053378414,0.000015609601,0.000027969678,0.000056466746,0.0006906422,0.000026340413,0.0006020624],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996669,0.000068846515,0.00003873961,0.000074983196,0.000128735,0.000021777196],"domain_scores_gemma":[0.99951696,0.00014136302,0.00009593173,0.000051049738,0.000169022,0.000025644022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065965264,0.0003076143,0.0003443622,0.0025770061,0.00024620304,0.00055579556,0.00024331846,0.00021367434,0.00080992794],"category_scores_gemma":[0.0013937869,0.00010211915,0.00030366483,0.0016332943,0.00022965205,0.00072378624,0.00036820647,0.00018896944,0.00020428882],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00066285883,0.00034905694,0.21550754,0.0003222849,0.00034901768,0.00038267008,0.0003129556,0.042249806,0.077662796,0.0033881213,0.0030896259,0.65572333],"study_design_scores_gemma":[0.00004153615,0.00055584905,0.36406824,0.000037663354,0.00028189254,0.00093291607,0.00034236655,0.59795815,0.028578155,0.0017217989,0.005371058,0.00011029747],"about_ca_topic_score_codex":0.0010172233,"about_ca_topic_score_gemma":0.0019127441,"teacher_disagreement_score":0.0025770061,"about_ca_system_score_codex":0.00023145504,"about_ca_system_score_gemma":0.00019647299,"threshold_uncertainty_score":0.0034886599},"labels":[],"label_agreement":null},{"id":"W2971056223","doi":"10.5194/isprs-archives-xlii-3-w8-167-2019","title":"APPLICATION OF OFF-NADIR SATELLITE IMAGERY IN EARTHQUAKE DAMAGE ASSESSMENT USING OBJECT-BASED HOG FEATURE DESCRIPTOR","year":2019,"lang":"en","type":"article","venue":"˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; DigitalGlobe Foundation; World Bank Group; National Science Foundation","keywords":"Computer science; Computer vision; Artificial intelligence; Change detection; Remote sensing; Histogram; Satellite; Satellite imagery; Process (computing); Distortion (music); Image (mathematics); Geology; Engineering","score_opus":0.013789586938817927,"score_gpt":0.24968829001595802,"score_spread":0.2358987030771401,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2971056223","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7720388,0.00096615526,0.22096495,0.00018222268,0.00014433502,0.00019386572,0.0005155519,0.0010181832,0.0039759893],"genre_scores_gemma":[0.9384282,0.0003611635,0.05944222,0.00004528249,0.000021958514,0.000029339359,0.00041978827,0.00002456141,0.0012275671],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99979085,0.000030393328,0.0000113179185,0.000047075497,0.00008847945,0.000031938198],"domain_scores_gemma":[0.99983084,0.000028210017,0.000020740545,0.000021370492,0.000080862024,0.000018030185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036106457,0.00039261812,0.00036217135,0.0021452224,0.00012818872,0.000497848,0.00027656156,0.0003068264,0.0008184349],"category_scores_gemma":[0.0003978477,0.00015045903,0.00039258949,0.0010061532,0.0001788681,0.0004009026,0.00034740177,0.00020242066,0.00032745002],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005534795,0.00068845385,0.024604462,0.00029522198,0.00020011641,0.00037866968,0.00015535964,0.046895202,0.19006255,0.0006141839,0.0027517388,0.73280054],"study_design_scores_gemma":[0.000039854374,0.00049695285,0.0814403,0.000032954085,0.00011707029,0.00035732932,0.00025802504,0.8428053,0.07170369,0.00041911128,0.0022731284,0.000056394278],"about_ca_topic_score_codex":0.0025660256,"about_ca_topic_score_gemma":0.0034701002,"teacher_disagreement_score":0.0025660256,"about_ca_system_score_codex":0.00017463605,"about_ca_system_score_gemma":0.00026760832,"threshold_uncertainty_score":0.005102217},"labels":[],"label_agreement":null},{"id":"W2971209209","doi":"10.1007/s11042-019-07920-7","title":"A multivariable optical remote sensing image feature discretization method applied to marine vessel targets recognition","year":2019,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Hainan University; Natural Science Foundation of Hainan Province; Beijing University of Posts and Telecommunications; National Natural Science Foundation of China; St. Francis Xavier University; Major Science and Technology Project of Hainan Province; Politecnico di Torino; McMaster University","keywords":"Computer science; Discretization; Remote sensing; Mutual information; Feature extraction; Data mining; Rough set; Feature (linguistics); Artificial intelligence; Pattern recognition (psychology); Computer vision; Mathematics","score_opus":0.01342476305400475,"score_gpt":0.24761089727519625,"score_spread":0.2341861342211915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2971209209","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018968683,0.00012952765,0.979761,0.00004618464,0.000034096887,0.000025292835,0.000031328356,0.00025896722,0.00074499217],"genre_scores_gemma":[0.6580189,0.00026917344,0.3401129,0.000059507733,0.000036175523,0.000088066416,0.00015822669,0.000028742954,0.0012283828],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99974746,0.000034472203,0.000023112578,0.000070955466,0.00010343581,0.000020499469],"domain_scores_gemma":[0.9997931,0.00006787588,0.000030404353,0.00003297011,0.000065485154,0.000010266007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002667491,0.00024901162,0.00039337584,0.00043643694,0.00022491955,0.00039328248,0.00048796574,0.00024822465,0.0007110575],"category_scores_gemma":[0.0008927947,0.0001464003,0.00048663124,0.00057516573,0.00022876498,0.00049251225,0.00035681465,0.0003244374,0.000108933884],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016153886,0.00008461591,0.0032172077,0.00018332321,0.000069391586,0.00019269908,0.0002089695,0.29034522,0.05397817,0.00815427,0.0015552118,0.6418494],"study_design_scores_gemma":[0.000009657992,0.000049193583,0.0010172961,0.0000046056966,0.000012396662,0.00008360779,0.000022730432,0.99116534,0.005066141,0.0013609721,0.0011947277,0.000013404575],"about_ca_topic_score_codex":0.004058844,"about_ca_topic_score_gemma":0.0025280036,"teacher_disagreement_score":0.004058844,"about_ca_system_score_codex":0.00027660478,"about_ca_system_score_gemma":0.0003609639,"threshold_uncertainty_score":0.008070409},"labels":[],"label_agreement":null},{"id":"W2971438317","doi":"10.1016/j.jag.2019.101957","title":"Incorporating band selection in the spatial selection of spectral endmembers","year":2019,"lang":"en","type":"article","venue":"International Journal of Applied Earth Observation and Geoinformation","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"China Scholarship Council; University of Alberta","keywords":"Endmember; Hyperspectral imaging; Computer science; Selection (genetic algorithm); Pattern recognition (psychology); Artificial intelligence; Feature selection; Spectral bands; Set (abstract data type); Remote sensing; Geology","score_opus":0.00899900703918599,"score_gpt":0.20388856370195965,"score_spread":0.19488955666277366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2971438317","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11754305,0.00039452082,0.87897223,0.00013511154,0.00009306444,0.000057271234,0.00019266744,0.0008753311,0.0017367206],"genre_scores_gemma":[0.459517,0.00044836494,0.53590286,0.00014947657,0.00009416596,0.00008353111,0.0006096538,0.0002064675,0.0029884283],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99966574,0.00011170883,0.00001959199,0.00005541978,0.00009738486,0.000050279476],"domain_scores_gemma":[0.9994072,0.00018960421,0.00003965332,0.00007882697,0.00025976473,0.000024962523],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001105733,0.0006202018,0.0004084798,0.00081746763,0.0004269384,0.00076922035,0.00040020037,0.0005007068,0.0010043771],"category_scores_gemma":[0.0017884142,0.00025604744,0.00058120384,0.0008062741,0.0002569589,0.0007814316,0.00053254113,0.00041887854,0.0007079671],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007238101,0.00042788737,0.011634142,0.00018396591,0.0002415319,0.000113077265,0.00022211275,0.1333412,0.17214274,0.0030159939,0.0032918067,0.6746618],"study_design_scores_gemma":[0.000032659504,0.00009838278,0.011973474,0.000028067394,0.00017653171,0.00011182729,0.0000669858,0.93660575,0.044588294,0.0025384785,0.003739906,0.00003969553],"about_ca_topic_score_codex":0.0033187065,"about_ca_topic_score_gemma":0.008765107,"teacher_disagreement_score":0.0033187065,"about_ca_system_score_codex":0.00013914629,"about_ca_system_score_gemma":0.00071443303,"threshold_uncertainty_score":0.0065987706},"labels":[],"label_agreement":null},{"id":"W2973476437","doi":"10.1007/s11760-019-01562-w","title":"Kronecker least angle regression for unsupervised unmixing of hyperspectral imaging data","year":2019,"lang":"en","type":"article","venue":"Signal Image and Video Processing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Hyperspectral imaging; Underdetermined system; Regularization (linguistics); Computer science; Pixel; Basis pursuit; Algorithm; Data set; Optimization problem; Pattern recognition (psychology); Basis function; Basis (linear algebra); Artificial intelligence; Compressed sensing; Mathematics; Matching pursuit","score_opus":0.025714296597427837,"score_gpt":0.26896258389682165,"score_spread":0.24324828729939382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2973476437","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005159682,0.00012774306,0.994042,0.000043983473,0.000018124336,0.000013974966,0.00006275857,0.00027593345,0.00025570244],"genre_scores_gemma":[0.1689513,0.00066478504,0.8211127,0.00009052383,0.00006657631,0.00017055614,0.0008912051,0.00044245052,0.0076098833],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990398,0.00040090526,0.00006124866,0.00016778956,0.000275191,0.000055010074],"domain_scores_gemma":[0.99858,0.000633389,0.000173381,0.0002812797,0.00029538502,0.000036682482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014301097,0.00082039984,0.00069286913,0.00059427484,0.0003095516,0.0009037985,0.00069289556,0.0005997736,0.0014050591],"category_scores_gemma":[0.003935944,0.0004643593,0.00072464446,0.0011786697,0.0007553757,0.0011410046,0.0010136922,0.0018615685,0.0014273884],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022277284,0.00025138774,0.0013338465,0.0003278717,0.00019384173,0.00007868306,0.00021958842,0.40558743,0.05551696,0.036673367,0.0052556167,0.4943387],"study_design_scores_gemma":[0.0000056578656,0.00002495927,0.0005280523,0.00001043489,0.000010911096,0.000029674262,0.00001639614,0.9846453,0.006528864,0.006485028,0.0016982125,0.000016602235],"about_ca_topic_score_codex":0.0024923922,"about_ca_topic_score_gemma":0.0041472656,"teacher_disagreement_score":0.0024923922,"about_ca_system_score_codex":0.00031056133,"about_ca_system_score_gemma":0.0011458576,"threshold_uncertainty_score":0.0075632334},"labels":[],"label_agreement":null},{"id":"W2974097761","doi":"10.1038/s41598-019-49730-9","title":"Comparing Remote Sensing Methods for Monitoring Karst Rocky Desertification at Sub-pixel Scales in a Highly Heterogeneous Karst Region","year":2019,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Algoma University","funders":"National Key Research and Development Program of China; Chinese Academy of Sciences; National Natural Science Foundation of China","keywords":"Endmember; Karst; Remote sensing; Pixel; Land cover; Satellite imagery; Environmental science; Terrain; Multispectral image; Satellite; Geology; Geography; Computer science; Cartography; Land use; Hyperspectral imaging; Artificial intelligence","score_opus":0.04755832742775898,"score_gpt":0.30033750466373005,"score_spread":0.2527791772359711,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2974097761","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8988759,0.0011511733,0.09499368,0.000121520956,0.000042769727,0.00009036149,0.00047762337,0.0004351069,0.003811899],"genre_scores_gemma":[0.9511394,0.00032012138,0.047445662,0.00004133915,0.000019806199,0.000049378865,0.00040300353,0.000021061664,0.0005602687],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99963367,0.00006994744,0.000023534307,0.0001104011,0.00012408433,0.000038474373],"domain_scores_gemma":[0.99969006,0.000084717736,0.000051690306,0.00004694218,0.00010355472,0.000023057248],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00081669725,0.0005128889,0.00026250724,0.0020102512,0.00020676087,0.0006712993,0.00025418837,0.00037415177,0.00049281237],"category_scores_gemma":[0.000856475,0.00014596093,0.00038047566,0.00090126245,0.00016517502,0.000702785,0.000347946,0.00017256761,0.00020072302],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005029335,0.0004120257,0.2771289,0.00039997598,0.0006239614,0.00013190134,0.0002968678,0.0646191,0.10583751,0.0011808433,0.0012851923,0.5475809],"study_design_scores_gemma":[0.00003547751,0.00020919512,0.3431162,0.000034831854,0.0002788163,0.00016461869,0.00037917838,0.62476385,0.027273918,0.00084570004,0.0028513323,0.00004692841],"about_ca_topic_score_codex":0.0042878496,"about_ca_topic_score_gemma":0.009624485,"teacher_disagreement_score":0.0042878496,"about_ca_system_score_codex":0.00023262782,"about_ca_system_score_gemma":0.00028075624,"threshold_uncertainty_score":0.008525789},"labels":[],"label_agreement":null},{"id":"W2974391216","doi":"10.3390/rs11182149","title":"KLUM: An Urban VNIR and SWIR Spectral Library Consisting of Building Materials","year":2019,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Deutscher Akademischer Austauschdienst; Karlsruhe Institute of Technology","keywords":"VNIR; Remote sensing; Hyperspectral imaging; Facade; Imaging spectroscopy; Environmental science; Spectral line; Computer science; Geology; Physics; Engineering; Civil engineering","score_opus":0.009358529045104166,"score_gpt":0.20781272347089016,"score_spread":0.198454194425786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2974391216","genre_codex":"empirical","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38085613,0.0036090172,0.22726043,0.0003307007,0.00038830907,0.0008874245,0.2794726,0.06672077,0.040474672],"genre_scores_gemma":[0.33581313,0.0014339607,0.25199625,0.0003656143,0.00012584357,0.0011849321,0.3906313,0.008211219,0.010237707],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993181,0.00006462341,0.000034953395,0.00020570775,0.00028007914,0.00009663614],"domain_scores_gemma":[0.9995528,0.000054859098,0.000052902633,0.00011906397,0.00017307982,0.000047242906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059116917,0.0018577036,0.0009314079,0.005446996,0.00071989896,0.00096354773,0.0012746528,0.00081206905,0.007540333],"category_scores_gemma":[0.0006657271,0.0005867886,0.0011681702,0.0051651997,0.0004266127,0.0014866634,0.001317838,0.000624022,0.008491311],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023040185,0.0011370084,0.033990026,0.004019234,0.0006799548,0.0018698839,0.0010109013,0.0280018,0.26586512,0.0027168742,0.15297376,0.5054314],"study_design_scores_gemma":[0.00034626215,0.00066035177,0.26676366,0.00063055084,0.0006568157,0.0029346603,0.0011671736,0.105714604,0.20011127,0.0036736184,0.41665965,0.0006813779],"about_ca_topic_score_codex":0.002783187,"about_ca_topic_score_gemma":0.0068890965,"teacher_disagreement_score":0.007540333,"about_ca_system_score_codex":0.00036037972,"about_ca_system_score_gemma":0.0005913115,"threshold_uncertainty_score":0.025224984},"labels":[],"label_agreement":null},{"id":"W2978950899","doi":"10.3390/rs11192289","title":"TCANet for Domain Adaptation of Hyperspectral Images","year":2019,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"European Social Fund; European Regional Development Fund; Università degli Studi di Pavia; European Commission; Xunta de Galicia; University of Guelph","keywords":"Computer science; Artificial intelligence; Hyperspectral imaging; Pattern recognition (psychology); Normalization (sociology); Convolutional neural network; Robustness (evolution)","score_opus":0.014601867361681745,"score_gpt":0.22410657393259417,"score_spread":0.2095047065709124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2978950899","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037106305,0.0005516864,0.9424554,0.00021345953,0.0002624851,0.00012957772,0.0008021851,0.009360137,0.00911884],"genre_scores_gemma":[0.39103562,0.0005090037,0.58428216,0.00031863805,0.00007960867,0.00027638077,0.0048755854,0.00057653984,0.018046534],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99985206,0.000015879008,0.000005790008,0.000052119114,0.000050415092,0.000023704846],"domain_scores_gemma":[0.9998522,0.000024005281,0.000017783495,0.000037610487,0.000057935024,0.000010519304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028378027,0.0006659003,0.00031618177,0.00051472866,0.00021226694,0.0004642407,0.00084173994,0.0005193215,0.0050333044],"category_scores_gemma":[0.00060257403,0.0002035624,0.0005261219,0.00063524995,0.0002275327,0.00061466027,0.0007006463,0.0008875474,0.0014570672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023726722,0.00019439765,0.0017347853,0.00020243016,0.00013035133,0.00030074906,0.00006466171,0.2401543,0.07818679,0.013461816,0.028160721,0.6371718],"study_design_scores_gemma":[0.0000060647976,0.00002618228,0.0005672566,0.0000070327465,0.000008185084,0.00006612065,0.000009507413,0.9737385,0.015971415,0.0023075172,0.007283059,0.000009256218],"about_ca_topic_score_codex":0.0055769808,"about_ca_topic_score_gemma":0.008116908,"teacher_disagreement_score":0.0055769808,"about_ca_system_score_codex":0.00053200865,"about_ca_system_score_gemma":0.0006123541,"threshold_uncertainty_score":0.016838133},"labels":[],"label_agreement":null},{"id":"W2980345032","doi":"10.48550/arxiv.1910.06391","title":"Building Information Modeling and Classification by Visual Learning At A City Scale","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Metadata; Task (project management); Building information modeling; Scale (ratio); Artificial intelligence; Geospatial analysis; Architecture; Deep learning; Retrofitting; Machine learning; Engineering; Systems engineering; World Wide Web; Cartography; Geography","score_opus":0.04542063884964868,"score_gpt":0.18763664733212937,"score_spread":0.1422160084824807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2980345032","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.080042586,0.0007428885,0.91009897,0.0006635899,0.000089411275,0.00007334906,0.00080514146,0.0033969579,0.004087064],"genre_scores_gemma":[0.6319872,0.0008157656,0.35679296,0.00019338564,0.00008234675,0.00008428137,0.0033414264,0.00020931421,0.0064932466],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997259,0.00004849869,0.000013885039,0.00010547613,0.000062587846,0.000043580665],"domain_scores_gemma":[0.99968565,0.000064605636,0.000030878862,0.00011200976,0.00008603334,0.00002079449],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005565218,0.0005593006,0.0005396802,0.0013582839,0.00023772706,0.0015300084,0.00087295705,0.0006531152,0.0022058096],"category_scores_gemma":[0.0011707586,0.000287441,0.0007820134,0.0013867868,0.00043642198,0.0014357256,0.0008760402,0.00074717624,0.0010379076],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011477534,0.00015661186,0.0042752167,0.00006950246,0.00007985826,0.00007897449,0.000086174776,0.21464045,0.011237842,0.007445164,0.008480483,0.753335],"study_design_scores_gemma":[0.000002333992,0.00001063947,0.00094084634,0.000005102727,0.000007161876,0.000013407544,0.00002575286,0.99149936,0.0019855655,0.004031873,0.0014727211,0.00000529674],"about_ca_topic_score_codex":0.019260889,"about_ca_topic_score_gemma":0.024986034,"teacher_disagreement_score":0.019260889,"about_ca_system_score_codex":0.0010154262,"about_ca_system_score_gemma":0.0005322194,"threshold_uncertainty_score":0.038297534},"labels":[],"label_agreement":null},{"id":"W2981418484","doi":"10.4095/219634","title":"Combining Diverse Spectral, Spatial and Contextual Attributes in Segment-Based Image Classification","year":2000,"lang":"en","type":"report","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Resources Canada","funders":"","keywords":"Pattern recognition (psychology); Computer science; Image (mathematics); Contextual image classification; Artificial intelligence; Spatial contextual awareness; Geography; Cartography","score_opus":0.04976956524229113,"score_gpt":0.27112796863309974,"score_spread":0.2213584033908086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2981418484","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061107885,0.00035662172,0.9360677,0.00012806783,0.000015851037,0.00009611982,0.00010712556,0.00034607443,0.0017746127],"genre_scores_gemma":[0.40188017,0.00053164054,0.5948672,0.000052068935,0.000044815606,0.000113244685,0.0006233033,0.000055027915,0.0018325452],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989373,0.00037104078,0.000052724088,0.000121197365,0.00046221228,0.000055589837],"domain_scores_gemma":[0.99865156,0.0007483788,0.00010472515,0.00023335396,0.00021784798,0.000044164855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002763113,0.00037730325,0.0004601144,0.0015485885,0.000373214,0.0009788745,0.00055137835,0.000660647,0.0011025092],"category_scores_gemma":[0.00410901,0.00028605416,0.00044711935,0.0018857457,0.0007470716,0.0020788694,0.0005974276,0.00054349634,0.0005590226],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017852777,0.00021176107,0.008030556,0.00016716664,0.000102553124,0.00015898181,0.0003086312,0.1371312,0.04727262,0.016617266,0.002007532,0.7878132],"study_design_scores_gemma":[0.00002185839,0.0004062029,0.014737026,0.00005315711,0.00017839915,0.00032390538,0.00021184333,0.8539987,0.041633334,0.07855216,0.00979875,0.000084688734],"about_ca_topic_score_codex":0.0010921349,"about_ca_topic_score_gemma":0.0030778358,"teacher_disagreement_score":0.002763113,"about_ca_system_score_codex":0.00036282866,"about_ca_system_score_gemma":0.00039391566,"threshold_uncertainty_score":0.014612913},"labels":[],"label_agreement":null},{"id":"W2981577683","doi":"10.5194/isprs-archives-xlii-4-w18-1107-2019","title":"FULL POLARIMETRIC UAVSAR IMAGE CHANGE DETECTION BASED ON CHANGE INDICES","year":2019,"lang":"en","type":"article","venue":"˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"California Institute of Technology; National Aeronautics and Space Administration","keywords":"Change detection; Cluster analysis; Kernel (algebra); Synthetic aperture radar; Remote sensing; Artificial intelligence; Pattern recognition (psychology); Dimension (graph theory); Computer science; Geography; Polarimetry; Mathematics","score_opus":0.02227770854059042,"score_gpt":0.2449088599256483,"score_spread":0.22263115138505787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2981577683","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.678788,0.00038478328,0.3081987,0.000106663734,0.00010265227,0.00020148506,0.0010695888,0.002212388,0.008935787],"genre_scores_gemma":[0.8978983,0.00015735987,0.09951647,0.00004008528,0.000024747505,0.00005017723,0.0010408309,0.00006453738,0.001207522],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997191,0.0000412053,0.000018721923,0.0000777282,0.00011465912,0.000028648543],"domain_scores_gemma":[0.99929607,0.00009150573,0.000115129194,0.000080641934,0.000390035,0.00002665555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042888167,0.0003956191,0.00026574032,0.0022322033,0.00017605133,0.00059177296,0.00020273049,0.00018602292,0.00085465173],"category_scores_gemma":[0.000897106,0.00012517818,0.00024762802,0.0010713771,0.00019767068,0.0005168237,0.0002471994,0.00026736732,0.0005037049],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043161144,0.0002330315,0.099969275,0.00032838804,0.00025007583,0.00022918046,0.00034212443,0.030976038,0.24723388,0.0013335055,0.004884886,0.61378807],"study_design_scores_gemma":[0.000026769607,0.00018010828,0.29456747,0.000044015742,0.00013800047,0.00049487164,0.00035737906,0.5653033,0.13234296,0.00091809675,0.0055662026,0.00006086517],"about_ca_topic_score_codex":0.0014983987,"about_ca_topic_score_gemma":0.0026516744,"teacher_disagreement_score":0.0022322033,"about_ca_system_score_codex":0.00021742456,"about_ca_system_score_gemma":0.00019043982,"threshold_uncertainty_score":0.0029793382},"labels":[],"label_agreement":null},{"id":"W2981664452","doi":"10.3390/ijgi8110474","title":"GEOBIA Achievements and Spatial Opportunities in the Era of Big Earth Observation Data","year":2019,"lang":"en","type":"article","venue":"ISPRS International Journal of Geo-Information","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Österreichische Forschungsförderungsgesellschaft; Austrian Science Fund; European Commission","keywords":"Big data; Context (archaeology); Computer science; Data science; Geographic information system; Analytics; Spatial analysis; Earth observation; Spatial contextual awareness; Object (grammar); Inference; Data mining; Remote sensing; Cartography; Geography; Artificial intelligence; Engineering","score_opus":0.05059172061919632,"score_gpt":0.25405441795142286,"score_spread":0.20346269733222655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2981664452","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047688108,0.29537058,0.50286084,0.06923625,0.002288816,0.00009056018,0.0009907376,0.00070287724,0.080771215],"genre_scores_gemma":[0.5369458,0.206343,0.23777087,0.0046285917,0.0050433595,0.00014267123,0.0009967227,0.00028209976,0.007846862],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989213,0.00040236255,0.000059425387,0.00017607446,0.0003724446,0.000068396446],"domain_scores_gemma":[0.9972531,0.0014510809,0.00021371461,0.000345908,0.0006146845,0.000121441786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003647203,0.0005083954,0.0005054221,0.0025670645,0.0006626753,0.0050940756,0.000792703,0.0011242128,0.0014681505],"category_scores_gemma":[0.004772096,0.00030367207,0.00042681204,0.0038513716,0.003173351,0.009556357,0.0028497183,0.0016931616,0.0006010841],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042605363,0.000024930154,0.0042450656,0.0008112554,0.000036318645,0.00018727688,0.0010493817,0.0056347875,0.0014848039,0.78654975,0.008707233,0.1912266],"study_design_scores_gemma":[0.0000056769295,0.000055862347,0.005383495,0.0005422454,0.000038023412,0.00053650537,0.0028461646,0.022914506,0.0019476382,0.53197384,0.43370485,0.000051110357],"about_ca_topic_score_codex":0.0021063376,"about_ca_topic_score_gemma":0.0023117154,"teacher_disagreement_score":0.0050940756,"about_ca_system_score_codex":0.0012276997,"about_ca_system_score_gemma":0.0012102915,"threshold_uncertainty_score":0.01928854},"labels":[],"label_agreement":null},{"id":"W2981939930","doi":"10.1145/3343031.3351047","title":"Band and Quality Selection for Efficient Transmission of Hyperspectral Images","year":2019,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Hyperspectral imaging; Computer science; Bandwidth (computing); Artificial intelligence; Pixel; Remote sensing; Transmission (telecommunications); Full spectral imaging; Pattern recognition (psychology); Computer vision; Data mining; Telecommunications; Geography","score_opus":0.016150876359705614,"score_gpt":0.2542429653761034,"score_spread":0.2380920890163978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2981939930","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043189183,0.0005444887,0.95339155,0.00017546877,0.00005491233,0.00007115962,0.00007389282,0.00080389023,0.0016955193],"genre_scores_gemma":[0.45399854,0.0007357709,0.54106987,0.00021149278,0.00015510774,0.00014357013,0.00045775445,0.00033584976,0.0028920323],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992754,0.00013631249,0.00003817024,0.0001481019,0.0002979128,0.00010413655],"domain_scores_gemma":[0.9991911,0.00023626466,0.00011998664,0.00011205914,0.00028744867,0.000053225216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009021603,0.0010153746,0.00081496517,0.0012002301,0.00047182204,0.0007891911,0.0008621772,0.0006284126,0.0016092232],"category_scores_gemma":[0.0021859985,0.0003671117,0.0006129602,0.000859095,0.0005806911,0.0014223711,0.0007499966,0.00096684415,0.00089906086],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00064197887,0.0004592904,0.0027596073,0.00023397687,0.00008873937,0.0001998335,0.00032875978,0.12902176,0.20151064,0.0052630273,0.00747021,0.6520222],"study_design_scores_gemma":[0.000045440065,0.00008778621,0.0013916214,0.00001698373,0.000053286833,0.00019864638,0.00009530775,0.95148116,0.040915657,0.0032102964,0.0024747828,0.00002907737],"about_ca_topic_score_codex":0.002307324,"about_ca_topic_score_gemma":0.004088165,"teacher_disagreement_score":0.002307324,"about_ca_system_score_codex":0.00044218625,"about_ca_system_score_gemma":0.00089536,"threshold_uncertainty_score":0.005383432},"labels":[],"label_agreement":null},{"id":"W2985544900","doi":"10.1109/igarss.2019.8898036","title":"Patch-Based and Tensor-Patch-Based Dimension Reduction Methods for Hyperspectral Images","year":2019,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Adjacency matrix; Tensor (intrinsic definition); Hyperspectral imaging; Dimensionality reduction; Dimension (graph theory); Adjacency list; Computation; Reduction (mathematics); Mathematics; Matrix (chemical analysis); Computer science; Graph; Pattern recognition (psychology); Algorithm; Topology (electrical circuits); Artificial intelligence; Discrete mathematics; Combinatorics; Pure mathematics","score_opus":0.015539873353809847,"score_gpt":0.2864386852655436,"score_spread":0.27089881191173376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2985544900","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010833924,0.0008025113,0.98579025,0.00014416115,0.00008965386,0.000057713674,0.00017276157,0.0007723367,0.0013367231],"genre_scores_gemma":[0.09715539,0.0014089497,0.8963141,0.000102551036,0.00012533927,0.00012907216,0.0007601917,0.00028389823,0.0037205373],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99945337,0.00009370727,0.000027618522,0.0001524612,0.00024036557,0.000032554366],"domain_scores_gemma":[0.9992835,0.0001661613,0.000090358684,0.00016673577,0.00026669417,0.000026467844],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049903436,0.0009858424,0.0005686073,0.0018953804,0.00042083993,0.00082964613,0.0006627416,0.00040240024,0.0021001198],"category_scores_gemma":[0.0013608393,0.00032022255,0.0010939024,0.0016673823,0.0005069156,0.0012757406,0.0006177194,0.0010228744,0.00090421713],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006455815,0.00010275048,0.0016349907,0.00037915082,0.00017463799,0.000060462156,0.000205552,0.034237817,0.056123044,0.012913122,0.0070797293,0.88702416],"study_design_scores_gemma":[0.00001996185,0.00012600765,0.007304535,0.00005157209,0.00012960241,0.00047423682,0.00019361726,0.8723554,0.072166175,0.015742805,0.03129734,0.00013884087],"about_ca_topic_score_codex":0.0020495532,"about_ca_topic_score_gemma":0.004232958,"teacher_disagreement_score":0.0021001198,"about_ca_system_score_codex":0.00034223113,"about_ca_system_score_gemma":0.0004438004,"threshold_uncertainty_score":0.00702554},"labels":[],"label_agreement":null},{"id":"W2988289684","doi":"10.3390/rs11222627","title":"Purifying SLIC Superpixels to Optimize Superpixel-Based Classification of High Spatial Resolution Remote Sensing Image","year":2019,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"National Natural Science Foundation of China","keywords":"Computer science; Pattern recognition (psychology); Artificial intelligence; Cluster analysis; Pixel; Contextual image classification; Segmentation; Remote sensing; Image (mathematics)","score_opus":0.01863949118982053,"score_gpt":0.23712312052287846,"score_spread":0.21848362933305793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2988289684","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.080864444,0.00055140007,0.91332114,0.00011557036,0.000061004775,0.00014115847,0.0001738557,0.0033944962,0.0013769616],"genre_scores_gemma":[0.32521826,0.00025048625,0.67106366,0.00019782201,0.000037115708,0.00012727834,0.0009121917,0.0006198465,0.001573313],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991968,0.00009694452,0.00004716406,0.00023613717,0.0003032787,0.00011969851],"domain_scores_gemma":[0.99895585,0.00017879102,0.00012160147,0.0001809465,0.00049613893,0.00006672375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011261909,0.0009849605,0.0011088866,0.0015837754,0.000665246,0.00092832476,0.0013263375,0.0008065715,0.0014521644],"category_scores_gemma":[0.002200512,0.00047612222,0.000942106,0.0015122498,0.0007405363,0.001384604,0.00079947355,0.0008700984,0.00081329176],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005320684,0.00019397427,0.0067808256,0.00031744334,0.00016597258,0.00021724605,0.00046800234,0.14655907,0.2135139,0.0037485384,0.006987877,0.62051505],"study_design_scores_gemma":[0.000022719494,0.000057487916,0.0028390626,0.000015282707,0.000047241614,0.000115252646,0.000113935006,0.9477244,0.044575714,0.0021396987,0.002327334,0.000021920838],"about_ca_topic_score_codex":0.01261821,"about_ca_topic_score_gemma":0.019173747,"teacher_disagreement_score":0.01261821,"about_ca_system_score_codex":0.00096831773,"about_ca_system_score_gemma":0.0012339114,"threshold_uncertainty_score":0.025089562},"labels":[],"label_agreement":null},{"id":"W2990138672","doi":"10.1109/smc.2019.8913846","title":"NSGA2-based method for band selection for supervised segmentation in hyperspectral imaging","year":2019,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Hyperspectral imaging; Artificial intelligence; Computer science; Selection (genetic algorithm); Segmentation; Pattern recognition (psychology); Image segmentation; Computer vision","score_opus":0.013956606298695209,"score_gpt":0.2742070912389161,"score_spread":0.2602504849402209,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990138672","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06552762,0.0005031942,0.9270694,0.0002748914,0.00012274318,0.00029492532,0.00021257711,0.0019823192,0.004012344],"genre_scores_gemma":[0.37833542,0.0002568568,0.61278623,0.00044327977,0.00005429481,0.0012131465,0.0010273468,0.00031901398,0.0055643474],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995789,0.0001358587,0.000025660902,0.00008642123,0.00009751188,0.00007568725],"domain_scores_gemma":[0.9995161,0.0002610248,0.000038731476,0.000021887168,0.00013714436,0.000025131649],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009848858,0.0015872016,0.0012478669,0.0015080767,0.00064690516,0.000712204,0.0012260887,0.0013535608,0.0036990477],"category_scores_gemma":[0.0014012927,0.0005656166,0.0012590758,0.00092102546,0.0005722487,0.0006169663,0.00062803685,0.001090109,0.0005705275],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013052889,0.00015066986,0.0012688589,0.000112907,0.000110567235,0.00010080231,0.0001094326,0.881778,0.0041597136,0.002336473,0.0031870038,0.10655506],"study_design_scores_gemma":[0.0000140056845,0.000020622494,0.00019706,0.0000065450286,0.000011756853,0.000011443803,0.000014601936,0.99787664,0.00066907745,0.0006630652,0.00050952204,0.000005556299],"about_ca_topic_score_codex":0.0145908715,"about_ca_topic_score_gemma":0.01972517,"teacher_disagreement_score":0.0145908715,"about_ca_system_score_codex":0.0010440268,"about_ca_system_score_gemma":0.0020926602,"threshold_uncertainty_score":0.029011846},"labels":[],"label_agreement":null},{"id":"W2993351627","doi":"10.3390/rs11232878","title":"An Object-Based Markov Random Field Model with Anisotropic Penalty for Semantic Segmentation of High Spatial Resolution Remote Sensing Imagery","year":2019,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"Wuhan University; National Natural Science Foundation of China","keywords":"Markov random field; Computer science; Segmentation; Inference; Markov chain; Random field; Artificial intelligence; Maximum a posteriori estimation; A priori and a posteriori; Pattern recognition (psychology); Image segmentation; Mathematics; Machine learning; Statistics","score_opus":0.010635746724961528,"score_gpt":0.23217614876689677,"score_spread":0.22154040204193523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2993351627","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013823454,0.00015054108,0.9853012,0.00011486776,0.000017632181,0.000018080294,0.00003832215,0.00019724153,0.00033871937],"genre_scores_gemma":[0.63023466,0.0005312026,0.36509696,0.00022519707,0.00013245473,0.00016668311,0.0005486008,0.00020574866,0.0028584898],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994823,0.00016712303,0.00002648268,0.00013474881,0.00012582402,0.00006357464],"domain_scores_gemma":[0.99939,0.00032853903,0.00010556133,0.000055695764,0.00008568287,0.000034535155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014040539,0.0006088066,0.00082406343,0.00089330523,0.00032796836,0.0006794287,0.0014160392,0.0010476161,0.00072978006],"category_scores_gemma":[0.0023299626,0.00046892132,0.0012178412,0.00077461964,0.00072388106,0.0012542802,0.00063630036,0.0011416696,0.00021319548],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009264865,0.000034390123,0.00085354986,0.000065985936,0.00004912866,0.0000832937,0.000058817473,0.9296517,0.005001985,0.01595894,0.00070288277,0.04744667],"study_design_scores_gemma":[0.0000019392849,0.000004542695,0.00007435667,0.0000015240971,0.0000033380388,0.00000877059,0.0000012524072,0.9978751,0.00022581198,0.0016877243,0.00011142677,0.000004136143],"about_ca_topic_score_codex":0.009870269,"about_ca_topic_score_gemma":0.008552798,"teacher_disagreement_score":0.009870269,"about_ca_system_score_codex":0.0007282694,"about_ca_system_score_gemma":0.001049604,"threshold_uncertainty_score":0.019625604},"labels":[],"label_agreement":null},{"id":"W2995009850","doi":"10.18280/ts.360504","title":"Spatial-Spectral Random Patches Network for Classification of Hyperspectral Images","year":2019,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Hyperspectral imaging; Pattern recognition (psychology); Artificial intelligence; Computer science; Remote sensing; Geography","score_opus":0.015563047652262666,"score_gpt":0.21911099382345753,"score_spread":0.20354794617119487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995009850","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11500387,0.0013291885,0.87611246,0.00044601967,0.00016113924,0.00011441903,0.00039850353,0.0023105664,0.0041237846],"genre_scores_gemma":[0.88478625,0.00049956795,0.10763442,0.00018808249,0.00010218839,0.00012363924,0.0010003176,0.00008148762,0.0055840528],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997522,0.00006309062,0.00001029331,0.000080646896,0.000056423807,0.00003744889],"domain_scores_gemma":[0.99976593,0.00009635306,0.00003464759,0.000029853993,0.000059353868,0.00001380912],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000516197,0.0006409862,0.00054590456,0.00058867387,0.00019425999,0.00039818557,0.0007720628,0.0005898527,0.0015072225],"category_scores_gemma":[0.00092899357,0.00020446109,0.0005197181,0.0006234664,0.00037139942,0.0008236078,0.00046229435,0.0006872523,0.00042408623],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043719893,0.00024241055,0.0036024998,0.00014573915,0.00017231688,0.00018166866,0.00006734654,0.52299005,0.016592609,0.00731887,0.0068830363,0.4413663],"study_design_scores_gemma":[0.000003595455,0.000024834062,0.00032399196,0.0000028992856,0.000008189912,0.000017851977,0.000005577891,0.99666303,0.0014092115,0.0012456641,0.00029189477,0.000003177414],"about_ca_topic_score_codex":0.003663082,"about_ca_topic_score_gemma":0.0033186106,"teacher_disagreement_score":0.003663082,"about_ca_system_score_codex":0.00050828606,"about_ca_system_score_gemma":0.00033613545,"threshold_uncertainty_score":0.0072835684},"labels":[],"label_agreement":null},{"id":"W2997824220","doi":"10.3390/su12010274","title":"Uncertainty Problems in Image Change Detection","year":2019,"lang":"en","type":"article","venue":"Sustainability","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Key Research and Development Program of China; Wuhan University","keywords":"Stratified sampling; Thresholding; Sampling (signal processing); Change detection; Variance (accounting); Binary number; Computer science; Systematic sampling; Random forest; Statistics; Set (abstract data type); Land cover; Image (mathematics); Data mining; Artificial intelligence; Mathematics; Land use; Computer vision","score_opus":0.010557940926165172,"score_gpt":0.22759451500140476,"score_spread":0.2170365740752396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997824220","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046845265,0.0023112118,0.9466097,0.0006273688,0.00008280178,0.0001165983,0.00019303578,0.00028563984,0.0029284044],"genre_scores_gemma":[0.72064745,0.0010276085,0.2766646,0.0002401679,0.00014714978,0.0001745092,0.00035976878,0.000089142224,0.0006496408],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98296666,0.0059535047,0.0013434964,0.0026621355,0.006554985,0.0005192375],"domain_scores_gemma":[0.9444454,0.041952614,0.004998891,0.0031483232,0.005211401,0.00024341041],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017697686,0.0008248841,0.0011803922,0.004194499,0.0009448482,0.003044701,0.0014126282,0.0013711635,0.0006227971],"category_scores_gemma":[0.08026872,0.00053237873,0.00082522014,0.0035128468,0.0030969663,0.003396914,0.0019110788,0.0012400481,0.00017759165],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036967976,0.00008786461,0.048507046,0.0011813344,0.00049128936,0.000635338,0.0016618408,0.23870121,0.010011589,0.08286565,0.0031424006,0.6123448],"study_design_scores_gemma":[0.000029128718,0.00018945898,0.037971146,0.00029604236,0.0001842996,0.0010389969,0.0007763322,0.7330688,0.022248333,0.19402464,0.009935402,0.00023736933],"about_ca_topic_score_codex":0.005157105,"about_ca_topic_score_gemma":0.0028442848,"teacher_disagreement_score":0.017697686,"about_ca_system_score_codex":0.0018809466,"about_ca_system_score_gemma":0.00092610903,"threshold_uncertainty_score":0.093595445},"labels":[],"label_agreement":null},{"id":"W3003526188","doi":"10.1080/07038992.2019.1704622","title":"Object-Based Thermal Remote-Sensing Analysis for Fault Detection in Mashhad County, Iran","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Geography; Object based; Remote sensing; Fault (geology); Object (grammar); Cartography; Computer science; Geology; Artificial intelligence; Seismology","score_opus":0.0164992383543721,"score_gpt":0.22158518210974967,"score_spread":0.2050859437553776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3003526188","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9979366,0.00007455041,0.001218663,0.00003105374,0.0000055938144,0.0000143087655,0.00032266724,0.000054857643,0.00034181],"genre_scores_gemma":[0.9971945,0.00005011464,0.0019249537,0.0000061302762,0.000006973715,0.000010564083,0.0005708858,0.0000039488386,0.0002317777],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99984574,0.000019933448,0.000013747805,0.00003542454,0.0000462377,0.000038914484],"domain_scores_gemma":[0.999785,0.000035070854,0.000051832598,0.0000191232,0.000088703324,0.000020259007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033529193,0.00030137278,0.00032577637,0.0018263725,0.000260382,0.00040406318,0.00035036393,0.000278968,0.00042186817],"category_scores_gemma":[0.0004136975,0.00013282112,0.00033001773,0.001403002,0.00013489446,0.0003172743,0.0001719538,0.00014001525,0.00014845593],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028773284,0.0004838142,0.8371524,0.00014429617,0.000154226,0.0006667267,0.0006663964,0.035438314,0.009413177,0.0003606157,0.0022211615,0.11301109],"study_design_scores_gemma":[0.00001897079,0.000059020305,0.8812354,0.000011513742,0.000057488778,0.000103709295,0.0009218543,0.11514427,0.0016199134,0.00015891896,0.0006513304,0.000017574552],"about_ca_topic_score_codex":0.0560311,"about_ca_topic_score_gemma":0.06278014,"teacher_disagreement_score":0.0560311,"about_ca_system_score_codex":0.0007025834,"about_ca_system_score_gemma":0.0005633802,"threshold_uncertainty_score":0.11140996},"labels":[],"label_agreement":null},{"id":"W3004169754","doi":"10.1109/globalsip45357.2019.8969169","title":"Finite Inverted Dirichlet Mixture Optimal Pixel Predictor","year":2019,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Pixel; Clutter; Artificial intelligence; Computer science; Pattern recognition (psychology); Image (mathematics); Mixture model; Dirichlet distribution; Gaussian; Computer vision; Mathematics; Algorithm; Radar","score_opus":0.008885351492323036,"score_gpt":0.1953049116213183,"score_spread":0.18641956012899527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3004169754","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009084335,0.00040451382,0.9878471,0.0003232079,0.00007251586,0.000022456674,0.000078782665,0.000384434,0.0017826655],"genre_scores_gemma":[0.6350369,0.0010617668,0.34675843,0.0005116315,0.0002762565,0.0002191254,0.00067153224,0.00024971837,0.0152147105],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925524,0.0002608977,0.00003431704,0.00014010549,0.0001942538,0.00011509386],"domain_scores_gemma":[0.9964449,0.0026961067,0.0001284463,0.0001467923,0.0004811661,0.00010260144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016451989,0.00085550116,0.0015925211,0.0006054989,0.0005734991,0.0011423653,0.0014296576,0.0014791547,0.0049745454],"category_scores_gemma":[0.006861113,0.00066386844,0.00072323263,0.00071398926,0.0014304066,0.0019561322,0.0013942178,0.002627607,0.0012361505],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020979308,0.000067532455,0.0014343401,0.00011429861,0.000046277273,0.00012209472,0.000069718306,0.89428025,0.0024069776,0.038758226,0.0031649668,0.05932559],"study_design_scores_gemma":[0.0000028574523,0.000005771023,0.000045870216,0.000004946019,0.0000026477594,0.000010053399,0.0000029705548,0.9953295,0.0004317481,0.0039720503,0.00018775032,0.0000038042779],"about_ca_topic_score_codex":0.005851206,"about_ca_topic_score_gemma":0.0079203835,"teacher_disagreement_score":0.005851206,"about_ca_system_score_codex":0.0013143703,"about_ca_system_score_gemma":0.0022260193,"threshold_uncertainty_score":0.016641498},"labels":[],"label_agreement":null},{"id":"W3007310740","doi":"10.3390/rs12040641","title":"Characterizing and Mitigating Sensor Generated Spatial Correlations in Airborne Hyperspectral Imaging Data","year":2020,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hyperspectral imaging; Pixel; Deconvolution; Spatial correlation; Image resolution; Remote sensing; Point spread function; Computer science; Artificial intelligence; Spatial analysis; Image sensor; Spatial variability; Computer vision; Pattern recognition (psychology); Geography; Mathematics; Algorithm; Statistics","score_opus":0.034555646088081426,"score_gpt":0.23998277508921062,"score_spread":0.2054271290011292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3007310740","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66930765,0.00038022126,0.32812852,0.00015485962,0.000038145994,0.00007676166,0.00028242488,0.0006081205,0.001023355],"genre_scores_gemma":[0.82526904,0.0002999833,0.17315747,0.00008745403,0.00002259204,0.000043591717,0.00065358926,0.000108297,0.0003579663],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991788,0.00014688137,0.000042698633,0.00013905096,0.00041467126,0.000077994715],"domain_scores_gemma":[0.9976866,0.001061163,0.00036057198,0.00027227527,0.00057561795,0.000043735672],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015397363,0.00063813204,0.00035818625,0.0008113555,0.00035200175,0.0006655894,0.0004929808,0.00050268444,0.00026582574],"category_scores_gemma":[0.004617648,0.00019933684,0.00051148824,0.0009045813,0.00047067384,0.0009226359,0.00081254623,0.0008142382,0.0001265355],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046874632,0.00031235005,0.034830492,0.0005111953,0.0002697135,0.0009381871,0.0008829522,0.43869835,0.27395108,0.004555717,0.0016705912,0.24291064],"study_design_scores_gemma":[0.000028168568,0.00024253766,0.0366293,0.000044567638,0.000100491634,0.0005326695,0.0002947069,0.7896336,0.16709468,0.0023734749,0.0029461442,0.00007967911],"about_ca_topic_score_codex":0.0029295483,"about_ca_topic_score_gemma":0.0040329373,"teacher_disagreement_score":0.0029295483,"about_ca_system_score_codex":0.00044093566,"about_ca_system_score_gemma":0.00095989363,"threshold_uncertainty_score":0.008143008},"labels":[],"label_agreement":null},{"id":"W3013641226","doi":"10.1080/07038992.2020.1726735","title":"Fast Unmixing of Noisy Hyperspectral Images Based on Vertex Component Analysis and Singular Spectrum Analysis Algorithms","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Endmember; Hyperspectral imaging; Noise reduction; Independent component analysis; Pattern recognition (psychology); Noise (video); Artificial intelligence; Singular spectrum analysis; Mathematics; Vertex (graph theory); Algorithm; Computer science; Image (mathematics); Singular value decomposition; Graph","score_opus":0.011593286315806674,"score_gpt":0.20344666611699153,"score_spread":0.19185337980118486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013641226","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0071463664,0.000116339805,0.9921044,0.00002130465,0.00001775755,0.000019963712,0.00001321498,0.00025129638,0.00030932573],"genre_scores_gemma":[0.07644544,0.0002690961,0.92214763,0.000016416676,0.000026137726,0.00005625825,0.00012452262,0.00009748423,0.00081699295],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994011,0.00009781453,0.00003493737,0.00012796436,0.00030023817,0.00003803593],"domain_scores_gemma":[0.9995296,0.00016531996,0.00005815643,0.000066108594,0.00015872397,0.000022124863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061817287,0.0009731409,0.0008591359,0.0017616627,0.00050545245,0.00091903115,0.0006814211,0.00061597716,0.0008070398],"category_scores_gemma":[0.0013577305,0.0004103927,0.0010504794,0.0016119964,0.0006392271,0.0014817612,0.0008046159,0.0010468912,0.00043252777],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023883818,0.00010789124,0.0013262494,0.00029574765,0.00017217116,0.00014876304,0.00026966832,0.10512384,0.20100237,0.01797584,0.0011571107,0.6721814],"study_design_scores_gemma":[0.000009209773,0.000045597844,0.00061185466,0.000010823797,0.000026406999,0.00013040355,0.000038261252,0.95132923,0.040656995,0.0053081345,0.0018004018,0.00003275281],"about_ca_topic_score_codex":0.0017445774,"about_ca_topic_score_gemma":0.0023697366,"teacher_disagreement_score":0.0017616627,"about_ca_system_score_codex":0.00034688832,"about_ca_system_score_gemma":0.00064876577,"threshold_uncertainty_score":0.0034688115},"labels":[],"label_agreement":null},{"id":"W3013803529","doi":"10.1109/tgrs.2020.2969577","title":"Estimation of Mineral Abundance From Hyperspectral Data Using a New Supervised Neighbor-Band Ratio Unmixing Approach","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Endmember; Hyperspectral imaging; Cuprite; Robustness (evolution); Remote sensing; Atmospheric radiative transfer codes; Environmental science; Radiative transfer; Pattern recognition (psychology); Computer science; Artificial intelligence; Geology; Chemistry; Physics","score_opus":0.05925417055106901,"score_gpt":0.2547149451345797,"score_spread":0.1954607745835107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013803529","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17893107,0.00024104775,0.81725216,0.000053917003,0.000020767122,0.00006014578,0.00013071862,0.0017448264,0.0015652633],"genre_scores_gemma":[0.5645471,0.00019477085,0.43297338,0.000033286397,0.000019825555,0.00008930978,0.0005414593,0.00017164879,0.0014292148],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99955755,0.00008693469,0.000025690837,0.00015771067,0.0001496913,0.00002241468],"domain_scores_gemma":[0.999537,0.00016463693,0.000082876526,0.0000831368,0.00011902371,0.000013241325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092223776,0.00074823154,0.00048587483,0.0009584748,0.00025813066,0.000442582,0.0007050648,0.00039000984,0.00052555377],"category_scores_gemma":[0.0016325318,0.0003420907,0.00078155746,0.0004296717,0.00034437337,0.0013549816,0.00054980005,0.00044846605,0.0003559035],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042521767,0.00038751675,0.010464976,0.0002934381,0.00036915517,0.00006662239,0.00033021686,0.3081414,0.13967703,0.0022644724,0.00090125174,0.5366786],"study_design_scores_gemma":[0.000009919605,0.000051132247,0.00308921,0.0000046003747,0.000036470152,0.00005779137,0.000027806482,0.9762639,0.019185407,0.0005408447,0.0007113766,0.000021629374],"about_ca_topic_score_codex":0.0033334137,"about_ca_topic_score_gemma":0.0068733115,"teacher_disagreement_score":0.0033334137,"about_ca_system_score_codex":0.0003282505,"about_ca_system_score_gemma":0.00044630643,"threshold_uncertainty_score":0.0066280365},"labels":[],"label_agreement":null},{"id":"W3015059946","doi":"10.3390/s20072008","title":"Wavelength-Resolution SAR Ground Scene Prediction Based on Image Stack","year":2020,"lang":"en","type":"article","venue":"Sensors","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico; Saab; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Constant false alarm rate; Artificial intelligence; Image (mathematics); Computer science; Computer vision; Remote sensing; False alarm; Synthetic aperture radar; Wavelength; Mean-shift; Pattern recognition (psychology); Geography; Physics; Optics","score_opus":0.02205347935894183,"score_gpt":0.2139314350740968,"score_spread":0.19187795571515495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015059946","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30129114,0.00018625951,0.6941755,0.000051551022,0.000024974277,0.000052367326,0.00031394564,0.002637856,0.0012664384],"genre_scores_gemma":[0.7198222,0.00013915496,0.27890417,0.000015709356,0.000013386008,0.000034884157,0.00047116546,0.000129643,0.0004696588],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99977523,0.00003703912,0.000009853253,0.000049206774,0.00009702414,0.000031611733],"domain_scores_gemma":[0.9996307,0.000093300296,0.00007209082,0.00006535979,0.00012307373,0.00001540566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056608254,0.0005260562,0.0003821746,0.000853852,0.00016286867,0.0005083963,0.00042507704,0.00022684861,0.00046651353],"category_scores_gemma":[0.0011880101,0.00023016917,0.0004597788,0.0005395617,0.00019833997,0.0006657042,0.00030688755,0.0003579456,0.0003152989],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00059813383,0.00014672891,0.02908938,0.00013953957,0.00019055034,0.00011743833,0.00012724515,0.2858676,0.0953,0.0015400284,0.0011521257,0.5857312],"study_design_scores_gemma":[0.0000065623594,0.000073142706,0.014973233,0.00000872397,0.000039140352,0.000081748396,0.000026016241,0.95483744,0.028874576,0.00045820256,0.00059580884,0.000025370546],"about_ca_topic_score_codex":0.0024081306,"about_ca_topic_score_gemma":0.0033278405,"teacher_disagreement_score":0.0024081306,"about_ca_system_score_codex":0.0003004433,"about_ca_system_score_gemma":0.00039706944,"threshold_uncertainty_score":0.0047882795},"labels":[],"label_agreement":null},{"id":"W3024375956","doi":"","title":"Evaluating long short-term memory networks for modeling land cover change","year":2019,"lang":"en","type":"dissertation","venue":"Summit (Simon Fraser University)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Term (time); Land cover; Computer science; Cover (algebra); Land use; Engineering; Civil engineering; Physics","score_opus":0.05145140454603579,"score_gpt":0.27066345294426686,"score_spread":0.21921204839823105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3024375956","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9546506,0.0017390451,0.03578115,0.0010447365,0.00012772295,0.00013958417,0.00091277476,0.00050118566,0.0051032817],"genre_scores_gemma":[0.97824144,0.0004946756,0.018476278,0.000090910515,0.000030148782,0.00008728108,0.0011545058,0.000033323886,0.0013913347],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997303,0.000102915,0.000021380287,0.00006957549,0.00004230968,0.000033620876],"domain_scores_gemma":[0.9979644,0.0015639963,0.00010156654,0.00007616354,0.00022651767,0.00006732193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021987632,0.0011819426,0.00044916535,0.0005865756,0.00026405853,0.0009024015,0.0006156754,0.001084542,0.001469487],"category_scores_gemma":[0.0051870253,0.00030327338,0.00049972365,0.00050757144,0.00029155792,0.0011724846,0.0005917027,0.0011949827,0.00026463016],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016802305,0.00017516178,0.004484295,0.00006896994,0.00010133555,0.000023399982,0.000026411346,0.9566493,0.0006378835,0.0005727805,0.0005980454,0.036494363],"study_design_scores_gemma":[0.000004265182,0.000037174534,0.00036323414,0.0000047349777,0.0000076148285,0.0000011503779,0.000011195603,0.99899036,0.00032571124,0.00020572405,0.00004707249,0.0000018608017],"about_ca_topic_score_codex":0.040974714,"about_ca_topic_score_gemma":0.03274044,"teacher_disagreement_score":0.040974714,"about_ca_system_score_codex":0.0015000548,"about_ca_system_score_gemma":0.0011480214,"threshold_uncertainty_score":0.0814724},"labels":[],"label_agreement":null},{"id":"W3024521712","doi":"10.1016/j.neucom.2020.04.138","title":"Hyperspectral image classification based on sparse modeling of spectral blocks","year":2020,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Hyperspectral imaging; Discriminative model; Computer science; Benchmark (surveying); Pattern recognition (psychology); Artificial intelligence; Full spectral imaging; Exploit; Sparse approximation; Spatial analysis; Remote sensing","score_opus":0.04120244498329782,"score_gpt":0.2334189012969485,"score_spread":0.1922164563136507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3024521712","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031619683,0.00014187611,0.9666489,0.00012812123,0.000024051831,0.000018041359,0.000095151336,0.00024837136,0.0010757388],"genre_scores_gemma":[0.67224544,0.0005334424,0.32199723,0.00015218991,0.00011362768,0.000098821576,0.00082097447,0.000090855436,0.003947344],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99981695,0.000042504,0.0000069378207,0.00003306716,0.00007710439,0.00002350874],"domain_scores_gemma":[0.9997199,0.000094292525,0.00004652943,0.00004816905,0.000075101816,0.000016013571],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023136391,0.0003749872,0.00047060187,0.00048564168,0.000198497,0.00047759406,0.00044640663,0.00044236964,0.0010613449],"category_scores_gemma":[0.0009147139,0.0001895106,0.00047182135,0.0006403902,0.00028718245,0.0008848386,0.00043684003,0.0006163248,0.00052030024],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027287216,0.00022136541,0.0015699824,0.00012249239,0.00009512246,0.0000866946,0.00011585916,0.43164736,0.10092795,0.017989766,0.0035104186,0.4434402],"study_design_scores_gemma":[0.0000016887722,0.000012617025,0.0002030568,0.0000021971068,0.000005031597,0.000017514549,0.0000047711137,0.9957261,0.0020711424,0.0016663562,0.00028657945,0.0000030744927],"about_ca_topic_score_codex":0.0018520145,"about_ca_topic_score_gemma":0.002890866,"teacher_disagreement_score":0.0018520145,"about_ca_system_score_codex":0.00020031443,"about_ca_system_score_gemma":0.0003479102,"threshold_uncertainty_score":0.0036824942},"labels":[],"label_agreement":null},{"id":"W3032994530","doi":"10.1109/jstars.2020.3000284","title":"Hyperspectral Image Dimension Reduction Using Weight Modified Tensor-Patch-Based Methods","year":2020,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Dimensionality reduction; Tensor (intrinsic definition); Hyperspectral imaging; Adjacency list; Adjacency matrix; Embedding; Mathematics; Computer science; Pattern recognition (psychology); Graph; Artificial intelligence; Algorithm; Theoretical computer science; Pure mathematics","score_opus":0.050025551944149205,"score_gpt":0.27280022025286954,"score_spread":0.22277466830872034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3032994530","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009184232,0.00020945202,0.98930126,0.00009028639,0.00003651346,0.00002772528,0.000073028124,0.0004747934,0.0006027321],"genre_scores_gemma":[0.1436072,0.00060520164,0.85174876,0.00013245502,0.000106780855,0.000113496906,0.0006463237,0.00028407303,0.0027557795],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994966,0.000118288364,0.000027375834,0.00011886032,0.00019564225,0.000043180014],"domain_scores_gemma":[0.99925226,0.00019011254,0.00010584727,0.0001545803,0.00026182938,0.000035253852],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005042299,0.0010853796,0.0007379805,0.00120846,0.0003087331,0.0008289069,0.0008418626,0.0005122447,0.0014965914],"category_scores_gemma":[0.0019457095,0.00031553826,0.0011141602,0.0012841607,0.00051068026,0.0015794277,0.0009586452,0.0010832368,0.0007140229],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014941223,0.00014133159,0.0014524411,0.00026606335,0.0002107635,0.00013081873,0.00026145176,0.22644608,0.04276612,0.027123518,0.009875361,0.6911767],"study_design_scores_gemma":[0.000007739009,0.000028432656,0.00047887038,0.000006578392,0.000022780707,0.00006190448,0.00003094317,0.9855802,0.005133668,0.006123961,0.0025044254,0.000020591688],"about_ca_topic_score_codex":0.0026897704,"about_ca_topic_score_gemma":0.0034669887,"teacher_disagreement_score":0.0026897704,"about_ca_system_score_codex":0.00035059178,"about_ca_system_score_gemma":0.0006258213,"threshold_uncertainty_score":0.005348265},"labels":[],"label_agreement":null},{"id":"W3032997645","doi":"10.3390/rs12111746","title":"A Novel Active Contours Model for Environmental Change Detection from Multitemporal Synthetic Aperture Radar Images","year":2020,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Synthetic aperture radar; Artificial intelligence; Thresholding; Pattern recognition (psychology); Benchmark (surveying); Change detection; Image (mathematics); Remote sensing; Computer vision; Geology","score_opus":0.04217188850840395,"score_gpt":0.2225602195000561,"score_spread":0.18038833099165216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3032997645","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003527681,0.00017698611,0.9955461,0.00006545602,0.00002898685,0.000022333774,0.000028144685,0.00022594507,0.00037832654],"genre_scores_gemma":[0.3990207,0.0011289922,0.59414196,0.0002557797,0.00015887176,0.00029005826,0.00054547185,0.00025043509,0.004207708],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995721,0.00007759924,0.000023461305,0.0001308473,0.00016199808,0.000033926535],"domain_scores_gemma":[0.999564,0.0001909584,0.00005529953,0.00004425616,0.00012750254,0.000017956845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085507525,0.00088173046,0.0007301923,0.0013251095,0.00029107824,0.0010357995,0.0017143526,0.0012868206,0.0009335072],"category_scores_gemma":[0.0014229679,0.0005490983,0.0011832566,0.00096392154,0.0005775762,0.0022541261,0.0005792599,0.0012025326,0.00051243004],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016438308,0.00015116321,0.002408834,0.0001809173,0.00015280832,0.00020629035,0.00019159385,0.5907817,0.024154589,0.013690301,0.0023812642,0.36553615],"study_design_scores_gemma":[0.0000032548328,0.000014827266,0.00023491554,0.0000047307203,0.000008901175,0.00003356041,0.0000074040486,0.99512595,0.0019121161,0.0016266926,0.001019576,0.000008224952],"about_ca_topic_score_codex":0.0036611075,"about_ca_topic_score_gemma":0.0036879932,"teacher_disagreement_score":0.0036611075,"about_ca_system_score_codex":0.0005475317,"about_ca_system_score_gemma":0.0005172966,"threshold_uncertainty_score":0.007279575},"labels":[],"label_agreement":null},{"id":"W3033894069","doi":"10.48550/arxiv.2006.04435","title":"CAST: A Correlation-based Adaptive Spectral Clustering Algorithm on Multi-scale Data","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Spectral clustering; Cluster analysis; Similarity (geometry); Correlation clustering; CURE data clustering algorithm; Computer science; Scale (ratio); Pattern recognition (psychology); Matrix (chemical analysis); k-medians clustering; TRACE (psycholinguistics); Cluster (spacecraft); Single-linkage clustering; Fuzzy clustering; Coefficient matrix; Clustering high-dimensional data; Algorithm; Data mining; Mathematics; Artificial intelligence; Physics; Image (mathematics)","score_opus":0.16655819170653563,"score_gpt":0.21007026069220827,"score_spread":0.04351206898567264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033894069","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005001931,0.00015626934,0.9933247,0.00012027896,0.00005448604,0.00004781192,0.000086012304,0.00077241426,0.00043620085],"genre_scores_gemma":[0.13113183,0.00031686097,0.8645283,0.00024071145,0.00016701699,0.00023449156,0.00092896266,0.00033236606,0.0021194883],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882823,0.000305572,0.000047927584,0.00024691282,0.00046975285,0.000101527934],"domain_scores_gemma":[0.9981818,0.0005314596,0.00020351159,0.0003596325,0.000597145,0.00012652745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016852011,0.0014065217,0.0019059941,0.0022136108,0.0012207546,0.0014407735,0.0027089294,0.0014099831,0.0014666518],"category_scores_gemma":[0.0060410565,0.0006476874,0.001209115,0.0033930598,0.0010839873,0.0017714639,0.002383729,0.0023626685,0.0011609719],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003808427,0.00023276529,0.0020013812,0.00023217437,0.0002706711,0.00012962057,0.000267096,0.47482306,0.009965993,0.019671582,0.01400626,0.4780186],"study_design_scores_gemma":[0.000020115296,0.00002873072,0.00018251361,0.000007705523,0.000009470157,0.00003979253,0.000028069348,0.9901731,0.0010297869,0.007042848,0.0014251685,0.000012642053],"about_ca_topic_score_codex":0.0050449306,"about_ca_topic_score_gemma":0.005931761,"teacher_disagreement_score":0.0050449306,"about_ca_system_score_codex":0.0007615765,"about_ca_system_score_gemma":0.0017077178,"threshold_uncertainty_score":0.010031164},"labels":[],"label_agreement":null},{"id":"W3036270649","doi":"10.1080/01431161.2020.1750732","title":"Geometrical constrained independent component analysis for hyperspectral unmixing","year":2020,"lang":"en","type":"article","venue":"International Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Endmember; Hyperspectral imaging; Independent component analysis; Pixel; Computer science; Imaging spectrometer; Blind signal separation; Pattern recognition (psychology); Remote sensing; Artificial intelligence; Principal component analysis; Data set; Set (abstract data type); Spectrometer; Geography","score_opus":0.032210628721360504,"score_gpt":0.2686846749666232,"score_spread":0.2364740462452627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3036270649","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001211075,0.00033831145,0.9971762,0.00006476222,0.000033468907,0.000031678686,0.00005528398,0.00032545757,0.00076386577],"genre_scores_gemma":[0.0774629,0.0016046776,0.9167042,0.00011701198,0.0001293628,0.00036400507,0.00087365875,0.00025997948,0.0024841127],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991886,0.0002292056,0.000042614432,0.00017990194,0.000319033,0.000040683382],"domain_scores_gemma":[0.99947697,0.00019419742,0.00007327994,0.000070256276,0.00016923215,0.000016110367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067085,0.0016746043,0.0006164085,0.0014628586,0.0004668416,0.0007672643,0.00085041864,0.0009262375,0.002429595],"category_scores_gemma":[0.0021439388,0.00041589857,0.0013055153,0.002245739,0.0008637774,0.00088534417,0.0008991084,0.0017869208,0.0014089684],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009865627,0.000081390455,0.00058826053,0.00044969155,0.0002010075,0.00016536619,0.0001370348,0.36813304,0.046647746,0.040887248,0.007873804,0.53473675],"study_design_scores_gemma":[0.000005603308,0.000018234834,0.00040703968,0.000017778737,0.00002123178,0.000054637476,0.000016968634,0.9741356,0.0069255005,0.0103229275,0.008045578,0.000028908778],"about_ca_topic_score_codex":0.0031449534,"about_ca_topic_score_gemma":0.003191157,"teacher_disagreement_score":0.0031449534,"about_ca_system_score_codex":0.0005564197,"about_ca_system_score_gemma":0.0010187882,"threshold_uncertainty_score":0.008127809},"labels":[],"label_agreement":null},{"id":"W3036922662","doi":"10.1109/cvprw50498.2020.00339","title":"Forgery Detection in Hyperspectral Document Images using Graph Orthogonal Nonnegative Matrix Factorization","year":2020,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Hyperspectral imaging; Non-negative matrix factorization; Orthogonality; Computer science; Graph; Matrix decomposition; Artificial intelligence; Pattern recognition (psychology); Cluster analysis; Exploit; Algorithm; Theoretical computer science; Mathematics; Eigenvalues and eigenvectors","score_opus":0.020896145038818474,"score_gpt":0.24645460776080677,"score_spread":0.2255584627219883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3036922662","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025812719,0.00023873207,0.97274315,0.00013949002,0.000041953295,0.000042108226,0.00008638835,0.00034199283,0.0005535045],"genre_scores_gemma":[0.32818785,0.0005232343,0.66835797,0.0001338275,0.00009012902,0.00009497831,0.00057903636,0.00007883461,0.0019540663],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999338,0.00015498725,0.000027971566,0.0002003799,0.00021012012,0.0000685177],"domain_scores_gemma":[0.99928975,0.00024177146,0.00015527033,0.00010503771,0.00017324598,0.0000349436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079914794,0.0010945883,0.0007841756,0.0009001267,0.0003378947,0.0006733387,0.0008524855,0.0008762108,0.0007505092],"category_scores_gemma":[0.001870585,0.00025381157,0.0010493611,0.00073943345,0.0006415112,0.0011839224,0.00057753606,0.0010086932,0.00044931416],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047952292,0.0002599328,0.0032974156,0.00039122484,0.00019304614,0.0003728447,0.00025686627,0.24961703,0.11054822,0.011870801,0.0071486197,0.61556447],"study_design_scores_gemma":[0.0000073714627,0.000033380824,0.00072326895,0.000007867067,0.00001357605,0.00009656621,0.000029387567,0.98847187,0.007287873,0.0024833498,0.0008296753,0.00001582662],"about_ca_topic_score_codex":0.0030069293,"about_ca_topic_score_gemma":0.0046647307,"teacher_disagreement_score":0.0030069293,"about_ca_system_score_codex":0.00039067352,"about_ca_system_score_gemma":0.00063520635,"threshold_uncertainty_score":0.0059788823},"labels":[],"label_agreement":null},{"id":"W3037656662","doi":"10.3390/rs12122012","title":"Geographic Object-Based Image Analysis: A Primer and Future Directions","year":2020,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":94,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates; University of Calgary","keywords":"Workflow; Data science; Pixel; Computer science; Cartography; Remote sensing; Geography; Artificial intelligence; Database","score_opus":0.01004682603476901,"score_gpt":0.2157431422271481,"score_spread":0.2056963161923791,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037656662","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001709855,0.4217084,0.46798527,0.07396638,0.00614585,0.00026848726,0.0005377584,0.00076276803,0.026915206],"genre_scores_gemma":[0.020889373,0.51165557,0.4194675,0.0151444515,0.013605037,0.00075059873,0.0010402894,0.00060265505,0.016844584],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99838614,0.00062225544,0.0001883533,0.00029388946,0.00043158807,0.00007779443],"domain_scores_gemma":[0.99276286,0.004505471,0.00033014826,0.0006366743,0.0014772307,0.00028759846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0069121993,0.0011093963,0.00086778955,0.0043759,0.0008462673,0.0062005753,0.0031803045,0.004188594,0.00870758],"category_scores_gemma":[0.008884988,0.0010115731,0.0010747004,0.005291123,0.0050410214,0.011962631,0.0030061333,0.0070181563,0.005501455],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006126926,0.00014255763,0.0018799339,0.0028164687,0.00006442215,0.00031507402,0.0012934923,0.002668296,0.0014359416,0.39793223,0.07155996,0.51983035],"study_design_scores_gemma":[0.000006616743,0.000056036675,0.0009839663,0.0027548834,0.000022716367,0.0007706825,0.0005696246,0.006002866,0.0009082272,0.21765956,0.7701974,0.00006749258],"about_ca_topic_score_codex":0.0034627358,"about_ca_topic_score_gemma":0.003157896,"teacher_disagreement_score":0.00870758,"about_ca_system_score_codex":0.0021635508,"about_ca_system_score_gemma":0.0024378863,"threshold_uncertainty_score":0.036555648},"labels":[],"label_agreement":null},{"id":"W3040419708","doi":"10.71781/13167","title":"Identification of urban surface materials using high-resolution hyperspectral aerial imagery","year":2019,"lang":"en","type":"dissertation","venue":"Papyrus : Institutional Repository (Université de Montréal)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Hyperspectral imaging; Remote sensing; Identification (biology); Aerial imagery; High resolution; Geography; Artificial intelligence; Cartography; Geology; Computer vision; Computer science; Biology","score_opus":0.006539727518120906,"score_gpt":0.17642816364146585,"score_spread":0.16988843612334495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3040419708","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80005205,0.0011878109,0.17635332,0.00021031412,0.000038601225,0.00028343804,0.0029382457,0.002754809,0.016181415],"genre_scores_gemma":[0.83112484,0.0010661882,0.15263689,0.00009579076,0.000018862751,0.00011248441,0.0036742247,0.00025138492,0.011019301],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.999752,0.000014737144,0.000006500197,0.000053326043,0.00012708243,0.000046377503],"domain_scores_gemma":[0.99983454,0.000026406,0.000020521775,0.000021656202,0.00008686222,0.000010014867],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026063557,0.0007030991,0.00027933446,0.0026564784,0.00032399353,0.0011580294,0.00039869983,0.00047175528,0.0017169864],"category_scores_gemma":[0.00030491053,0.00026628104,0.0005237994,0.0012322976,0.0003204513,0.00056810625,0.00040031923,0.00028638516,0.0010809015],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002739629,0.00018268514,0.04873495,0.0007834216,0.0001794891,0.0006470718,0.0008399719,0.03465326,0.5767928,0.0015463228,0.0029778224,0.33238837],"study_design_scores_gemma":[0.000036052348,0.00019850484,0.3496653,0.00013759336,0.00018891592,0.0008496464,0.0022006049,0.2146265,0.39732623,0.0015296479,0.0330938,0.0001471673],"about_ca_topic_score_codex":0.025017755,"about_ca_topic_score_gemma":0.0678062,"teacher_disagreement_score":0.025017755,"about_ca_system_score_codex":0.0006172842,"about_ca_system_score_gemma":0.000645005,"threshold_uncertainty_score":0.049744308},"labels":[],"label_agreement":null},{"id":"W3040517328","doi":"10.1080/07038992.2020.1780572","title":"Hyperspectral Image Classification Based on Multilayer Perceptron Trained with Eigenvalue Decay","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Support vector machine; Overfitting; Artificial intelligence; Hyperspectral imaging; Convolutional neural network; Pattern recognition (psychology); Computer science; Regularization (linguistics); Classifier (UML); Multilayer perceptron; Decision boundary; Eigenvalues and eigenvectors; Artificial neural network; Pixel; Machine learning","score_opus":0.02657391402883131,"score_gpt":0.2206400455802466,"score_spread":0.1940661315514153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3040517328","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2053599,0.0006990251,0.78966355,0.00023197681,0.00007722128,0.00006179494,0.00008797779,0.0015686072,0.0022498572],"genre_scores_gemma":[0.84154207,0.0002748623,0.1547902,0.000085882755,0.000026438756,0.00006604646,0.0002318799,0.000049442453,0.0029331604],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994698,0.00012653135,0.000041440988,0.00011912426,0.00017238187,0.0000706336],"domain_scores_gemma":[0.99914443,0.00035580967,0.00010181435,0.00008176973,0.0002820847,0.00003405066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016160305,0.00062206807,0.0007871725,0.0007052698,0.00032271174,0.00054634624,0.00075437623,0.0006872824,0.00087796256],"category_scores_gemma":[0.002328037,0.00030682844,0.00075617625,0.00057203195,0.00037366524,0.0013834876,0.0005552177,0.0008585606,0.00031623154],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005239597,0.00039081048,0.01171814,0.00019808505,0.0002680888,0.00014638982,0.00018803889,0.45438212,0.032533195,0.004047868,0.0026296508,0.49297357],"study_design_scores_gemma":[0.0000024891003,0.000026479853,0.00079007284,0.0000031508025,0.000007081245,0.000015920923,0.000007878581,0.99626297,0.0024492105,0.0003243258,0.00010517515,0.0000051872903],"about_ca_topic_score_codex":0.0037005346,"about_ca_topic_score_gemma":0.003861751,"teacher_disagreement_score":0.0037005346,"about_ca_system_score_codex":0.0006633072,"about_ca_system_score_gemma":0.0005523291,"threshold_uncertainty_score":0.008546472},"labels":[],"label_agreement":null},{"id":"W3041461260","doi":"10.48550/arxiv.2006.05612","title":"Deep Learning for Change Detection in Remote Sensing Images: Comprehensive Review and Meta-Analysis","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Deep learning; Computer science; Artificial intelligence; Change detection; Transfer of learning; Machine learning; Focus (optics); Unsupervised learning; Data science","score_opus":0.19782168022023747,"score_gpt":0.2361523111723816,"score_spread":0.038330630952144146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3041461260","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001483818,0.98141116,0.014342691,0.0011559608,0.0001823784,0.00003276717,0.00023503276,0.00007110589,0.0010850929],"genre_scores_gemma":[0.036793638,0.94341016,0.017187525,0.0008189413,0.00051857374,0.000120457014,0.00060210074,0.00006560718,0.00048301462],"study_design_codex":"design_other","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9979728,0.0006911034,0.00033237814,0.00044351144,0.0004798041,0.000080429],"domain_scores_gemma":[0.9864232,0.010715933,0.0008453436,0.0006172892,0.0012965915,0.000101683705],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008553534,0.0018232169,0.0027452335,0.00769315,0.00025141824,0.0027664418,0.0019678148,0.0013490039,0.0017720762],"category_scores_gemma":[0.020466069,0.0007713395,0.0032558416,0.006228336,0.0010208713,0.0033126904,0.0016465856,0.0018009996,0.0005012937],"study_design_candidate":"meta_analysis","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016560836,0.00008489673,0.005167149,0.051061016,0.006096887,0.000080511796,0.0001921587,0.012111915,0.0006562305,0.012680239,0.007566591,0.9041368],"study_design_scores_gemma":[0.00016878692,0.0010823653,0.029994097,0.1501737,0.042715862,0.0010887139,0.00085326727,0.07389849,0.011937029,0.101922676,0.5855918,0.00057322375],"about_ca_topic_score_codex":0.0043111104,"about_ca_topic_score_gemma":0.0048931288,"teacher_disagreement_score":0.008553534,"about_ca_system_score_codex":0.0018355035,"about_ca_system_score_gemma":0.0028422,"threshold_uncertainty_score":0.045235932},"labels":[],"label_agreement":null},{"id":"W3043411116","doi":"10.1080/07038992.2020.1791693","title":"Urban Land Cover Mapping from Airborne Hyperspectral Imagery Using a Fast Jointly Sparse Spectral Mixture Analysis Method","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Science and Technology Major Project; National Science Foundation","keywords":"Hyperspectral imaging; Remote sensing; Land cover; Cover (algebra); Geography; Environmental science; Cartography; Land use; Engineering","score_opus":0.026547212440283765,"score_gpt":0.22587328468163223,"score_spread":0.19932607224134846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3043411116","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015672738,0.000092988914,0.9827529,0.000068489986,0.000016856264,0.00002416995,0.000048589878,0.00080968847,0.0005135522],"genre_scores_gemma":[0.20880878,0.00025967526,0.7870731,0.00006851949,0.00005023254,0.00010062544,0.0006823281,0.00022353533,0.0027332883],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996908,0.0000562452,0.00001405402,0.00006495236,0.00013587066,0.000038162],"domain_scores_gemma":[0.9997222,0.00008983072,0.0000286711,0.000044178316,0.00009763828,0.000017486593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043653412,0.0007797705,0.0006095643,0.0012840194,0.00032145096,0.0005113271,0.00060490106,0.00045420442,0.001344441],"category_scores_gemma":[0.00079868693,0.0004821667,0.0012252891,0.0009782312,0.00029017552,0.000993369,0.0008544148,0.0007626042,0.0006767184],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023088476,0.00013417879,0.0018583429,0.00010876092,0.00019804202,0.000154739,0.00015467481,0.35764506,0.06367432,0.0043689786,0.003454848,0.5680172],"study_design_scores_gemma":[0.000005930875,0.000009021065,0.00031938884,0.0000017356275,0.000011356961,0.000030452573,0.000008961933,0.9956357,0.0027887973,0.00057008065,0.0006114694,0.000007053191],"about_ca_topic_score_codex":0.0069085155,"about_ca_topic_score_gemma":0.008192927,"teacher_disagreement_score":0.0069085155,"about_ca_system_score_codex":0.00024965752,"about_ca_system_score_gemma":0.0006874976,"threshold_uncertainty_score":0.013736606},"labels":[],"label_agreement":null},{"id":"W3046027728","doi":"10.1109/mgrs.2020.2979764","title":"Feature Extraction for Hyperspectral Imagery: The Evolution From Shallow to Deep: Overview and Toolbox","year":2020,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Magazine","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":519,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Hyperspectral imaging; Toolbox; Curse of dimensionality; Pattern recognition (psychology); Feature extraction; Feature (linguistics); Dimensionality reduction","score_opus":0.023963720327364844,"score_gpt":0.25044696464809635,"score_spread":0.2264832443207315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3046027728","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0064789876,0.4243211,0.5507783,0.005097759,0.0007043298,0.00017859499,0.0005790098,0.0010643651,0.010797535],"genre_scores_gemma":[0.04954926,0.45576617,0.47766253,0.0018951554,0.0020549826,0.00035466757,0.0018072667,0.00049501803,0.010415029],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99931157,0.00009067182,0.00005571747,0.00017768229,0.0003279817,0.000036367175],"domain_scores_gemma":[0.9989108,0.00042772532,0.00007264478,0.000114927854,0.00041278003,0.00006120216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016203538,0.0012968496,0.000989157,0.002350018,0.00030551286,0.0023358546,0.001500437,0.0013753434,0.002358598],"category_scores_gemma":[0.002228339,0.0011165688,0.0009490416,0.0030409228,0.0011314006,0.0042093275,0.0014467514,0.0027319854,0.0019309142],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000650033,0.00009733801,0.0011479687,0.0016288749,0.00008246533,0.00007588938,0.00013786211,0.0047594053,0.008111142,0.021975357,0.014618403,0.94730026],"study_design_scores_gemma":[0.000041232088,0.00050660985,0.0065503186,0.0022787228,0.00015542688,0.0016435642,0.00038034093,0.11638485,0.028288893,0.12894297,0.714502,0.00032511938],"about_ca_topic_score_codex":0.0018602419,"about_ca_topic_score_gemma":0.0013575695,"teacher_disagreement_score":0.002358598,"about_ca_system_score_codex":0.0007334016,"about_ca_system_score_gemma":0.000828175,"threshold_uncertainty_score":0.00856936},"labels":[],"label_agreement":null},{"id":"W3046734871","doi":"10.1145/3377929.3398124","title":"Colour quantisation using self-organizing migrating algorithm","year":2020,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"Russian Foundation for Basic Research","keywords":"Soma; Computer science; Benchmark (surveying); Palette (painting); Artificial intelligence; Task (project management); Set (abstract data type); Population; Process (computing); Image (mathematics); Algorithm; Pattern recognition (psychology); Computer vision; Engineering; Geography","score_opus":0.03586851623628173,"score_gpt":0.2269769122194041,"score_spread":0.19110839598312238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3046734871","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035487045,0.000270253,0.9609427,0.000106065796,0.000075253374,0.000082208266,0.000030898595,0.0009962568,0.0020092423],"genre_scores_gemma":[0.46987727,0.00025391096,0.5255366,0.00017199334,0.000053020965,0.00019086894,0.00014638931,0.00014632956,0.0036235608],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996605,0.000049386817,0.0000196826,0.00008106605,0.00014953477,0.000039852348],"domain_scores_gemma":[0.9993181,0.00018488176,0.00008045213,0.000092882234,0.00028341005,0.00004031384],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000695826,0.00060340477,0.0007096847,0.0011762539,0.0004979743,0.0008882445,0.0013409192,0.0006075725,0.0014111573],"category_scores_gemma":[0.001771856,0.00022110227,0.0005963808,0.0010371562,0.00062868034,0.0010288291,0.00087812106,0.0006570353,0.0003674009],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024314162,0.00012478999,0.0016314824,0.00014786723,0.000082159975,0.00007371498,0.00024965676,0.25573978,0.064880684,0.008984907,0.0037950634,0.66404676],"study_design_scores_gemma":[0.000022772436,0.000057217687,0.00055379124,0.000008232777,0.000017853146,0.00003837873,0.000039693525,0.98266244,0.0115025295,0.0033091542,0.0017706268,0.000017316259],"about_ca_topic_score_codex":0.0022468818,"about_ca_topic_score_gemma":0.0017891676,"teacher_disagreement_score":0.0022468818,"about_ca_system_score_codex":0.0006289536,"about_ca_system_score_gemma":0.0006082956,"threshold_uncertainty_score":0.004720807},"labels":[],"label_agreement":null},{"id":"W3047061183","doi":"10.5194/isprs-annals-v-3-2020-269-2020","title":"A CAUSAL HIERARCHICAL MARKOV FRAMEWORK FOR THE CLASSIFICATION OF MULTIRESOLUTION AND MULTISENSOR REMOTE SENSING IMAGES","year":2020,"lang":"en","type":"article","venue":"ISPRS annals of the photogrammetry, remote sensing and spatial information sciences","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Agence Nationale de la Recherche","keywords":"Panchromatic film; Computer science; Markov chain; Multispectral image; Artificial intelligence; Quadtree; Inference; Pixel; Multiresolution analysis; Markov model; Pattern recognition (psychology); Data mining; Algorithm; Machine learning","score_opus":0.07107445620535217,"score_gpt":0.3139083260556057,"score_spread":0.24283386985025351,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3047061183","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033057935,0.0001335823,0.9960718,0.000096277494,0.000013785624,0.000017638877,0.00006172522,0.00009326152,0.00020605316],"genre_scores_gemma":[0.39525762,0.0005470779,0.600133,0.00021014463,0.00019122049,0.00025450625,0.00073517865,0.00009482536,0.0025765155],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885774,0.0004279139,0.000058850765,0.00028030516,0.00022884889,0.0001463725],"domain_scores_gemma":[0.9980482,0.0011305155,0.00027903076,0.0001729852,0.00027515573,0.00009410873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002818569,0.0005365658,0.0008282106,0.0016432835,0.00064637297,0.0011717489,0.0021518387,0.0011239247,0.0021440806],"category_scores_gemma":[0.00442174,0.0005473979,0.0013186139,0.0013244667,0.0010559835,0.0016912597,0.0012214059,0.0013658259,0.00046595535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000958538,0.00009899089,0.0030711812,0.00016484696,0.0001344026,0.00014137055,0.00016534842,0.6760483,0.0036817042,0.17773557,0.002027516,0.13663489],"study_design_scores_gemma":[0.0000022454833,0.000010119965,0.00022884377,0.000005746513,0.000006227991,0.000010169345,0.0000058168634,0.9824735,0.0001908345,0.016760534,0.00030036888,0.0000055882856],"about_ca_topic_score_codex":0.013118974,"about_ca_topic_score_gemma":0.014878703,"teacher_disagreement_score":0.013118974,"about_ca_system_score_codex":0.0018270776,"about_ca_system_score_gemma":0.0016155472,"threshold_uncertainty_score":0.026085258},"labels":[],"label_agreement":null},{"id":"W3047532104","doi":"10.5194/isprs-annals-v-3-2020-241-2020","title":"TREE SPECIES CLASSIFICATION BASED ON NEUTROSOPHIC LOGIC AND DEMPSTER-SHAFER THEORY","year":2020,"lang":"en","type":"article","venue":"ISPRS annals of the photogrammetry, remote sensing and spatial information sciences","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"York University","funders":"CAS Key Laboratory of Digital Earth Science; Chinese Academy of Sciences; Ministry of Agriculture, Food and Rural Affairs; York University; Natural Sciences and Engineering Research Council of Canada; Ontario Ministry of Agriculture, Food and Rural Affairs","keywords":"Artificial intelligence; Multispectral image; Pattern recognition (psychology); Panchromatic film; Support vector machine; Computer science; Decision tree; Feature (linguistics); Dempster–Shafer theory; Remote sensing; Mathematics; Geography","score_opus":0.09428315560035072,"score_gpt":0.28151264450816776,"score_spread":0.18722948890781704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3047532104","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.107246146,0.0008209669,0.88655144,0.00028424777,0.00004248149,0.00012250063,0.00010631961,0.00012318997,0.004702784],"genre_scores_gemma":[0.8069717,0.0004194832,0.19156648,0.000104567,0.00003467076,0.00009105531,0.00011210734,0.0000053676054,0.0006945486],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991258,0.00026510865,0.00007245449,0.00009340928,0.0004008232,0.000042507927],"domain_scores_gemma":[0.999191,0.00042923485,0.000092909584,0.000023201404,0.00023700688,0.000026686042],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016446358,0.0004978765,0.000533053,0.0031216773,0.00039750233,0.0010210581,0.00050878536,0.0004887671,0.0007798668],"category_scores_gemma":[0.0022179235,0.0001636584,0.0006301987,0.001235964,0.00046227165,0.0012323932,0.0003408135,0.00041853567,0.00012882579],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040427182,0.00032917474,0.015638111,0.0006402752,0.0003959012,0.00072032545,0.00062188867,0.4084308,0.021802964,0.045692448,0.0027789394,0.50254494],"study_design_scores_gemma":[0.000010651627,0.00007243203,0.0022776874,0.000031515334,0.00002901192,0.00011856436,0.00010406178,0.98371917,0.0023036948,0.010665213,0.0006476671,0.000020338752],"about_ca_topic_score_codex":0.0028154524,"about_ca_topic_score_gemma":0.002493604,"teacher_disagreement_score":0.0031216773,"about_ca_system_score_codex":0.001098098,"about_ca_system_score_gemma":0.00059696427,"threshold_uncertainty_score":0.008697808},"labels":[],"label_agreement":null},{"id":"W3047878169","doi":"10.1080/01431161.2020.1763512","title":"Assessing the use of cross-orbit Sentinel-1 images in land cover classification","year":2020,"lang":"en","type":"article","venue":"International Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Land cover; Support vector machine; Orbit (dynamics); Remote sensing; Computer science; Contextual image classification; Cover (algebra); Land use; Artificial intelligence; Pattern recognition (psychology); Geography; Image (mathematics)","score_opus":0.0840876935383386,"score_gpt":0.333687312960648,"score_spread":0.2495996194223094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3047878169","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9619735,0.00077874935,0.031173212,0.00019533397,0.00006559099,0.00009745415,0.0007840398,0.00025071524,0.004681477],"genre_scores_gemma":[0.9686085,0.000308364,0.029740002,0.00004385991,0.000020092159,0.000031569605,0.0007583562,0.000023042167,0.00046621248],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988733,0.0003643253,0.00007106075,0.00015827191,0.00041389093,0.00011913199],"domain_scores_gemma":[0.998128,0.0006529942,0.00029830495,0.00018757244,0.00067601755,0.00005719807],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030469222,0.00075315905,0.00037237507,0.001446396,0.0003012984,0.0010871508,0.00031213844,0.0005523241,0.0004978314],"category_scores_gemma":[0.0038027125,0.00013027954,0.00027788256,0.0011443496,0.0002812481,0.0010915925,0.0004720519,0.00023563449,0.00034507253],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000525801,0.00046394908,0.5827988,0.000407364,0.000401043,0.00026598794,0.00040319786,0.029602753,0.0650709,0.0008368963,0.0029859645,0.31623745],"study_design_scores_gemma":[0.000027066953,0.0009080741,0.6318255,0.00011914617,0.00039456427,0.00049630535,0.001654663,0.3011528,0.05636046,0.0010048267,0.0059871934,0.00006932828],"about_ca_topic_score_codex":0.0026702592,"about_ca_topic_score_gemma":0.006979886,"teacher_disagreement_score":0.0030469222,"about_ca_system_score_codex":0.0002876823,"about_ca_system_score_gemma":0.00029213695,"threshold_uncertainty_score":0.016113818},"labels":[],"label_agreement":null},{"id":"W3047889481","doi":"10.1080/01431161.2020.1766146","title":"Unsupervised dimensionality reduction of hyperspectral images using representations of reflectance spectra","year":2020,"lang":"en","type":"article","venue":"International Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"Jet Propulsion Laboratory; National Aeronautics and Space Administration","keywords":"Hyperspectral imaging; Dimensionality reduction; Remote sensing; Reflectivity; Reduction (mathematics); Curse of dimensionality; Computer science; Artificial intelligence; Spectral line; Pattern recognition (psychology); Environmental science; Geology; Mathematics; Optics; Physics","score_opus":0.04145658259472484,"score_gpt":0.3066954782531256,"score_spread":0.26523889565840075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3047889481","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053158622,0.00021534051,0.9447983,0.00010338647,0.000033495948,0.000087440225,0.00020684325,0.0007170567,0.00067944516],"genre_scores_gemma":[0.29701865,0.00033025676,0.69926536,0.000073188494,0.000052108542,0.000263463,0.0016352941,0.0001581781,0.0012034582],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99929225,0.00014822451,0.000057292866,0.00017783837,0.00025659674,0.00006780959],"domain_scores_gemma":[0.9992514,0.00020445429,0.00012708858,0.00014944619,0.00024443128,0.00002307231],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006397034,0.0010181284,0.00087072654,0.001824697,0.00043393314,0.0007192951,0.00060200144,0.00042081825,0.00053796946],"category_scores_gemma":[0.0017982227,0.0002732776,0.0014284926,0.0013289631,0.0004898088,0.0011643337,0.0007825415,0.00080653845,0.00032464068],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017349159,0.00032957067,0.0037583008,0.0002855254,0.00025799425,0.00018049631,0.00032414103,0.13376932,0.13070738,0.008440868,0.00430897,0.7174639],"study_design_scores_gemma":[0.00001879541,0.00011483944,0.0058456645,0.000020799345,0.00005859939,0.00023377093,0.00014943884,0.9311529,0.050615836,0.008074286,0.0036541712,0.000060894108],"about_ca_topic_score_codex":0.0015453169,"about_ca_topic_score_gemma":0.0019624534,"teacher_disagreement_score":0.001824697,"about_ca_system_score_codex":0.00036176245,"about_ca_system_score_gemma":0.0007778839,"threshold_uncertainty_score":0.0033831596},"labels":[],"label_agreement":null},{"id":"W3048021468","doi":"10.5194/isprs-archives-xliii-b1-2020-85-2020","title":"SPATIAL RESOLUTION ENHANCEMENT OF LAND COVER MAPPING USING DEEP CONVOLUTIONAL NETS","year":2020,"lang":"en","type":"article","venue":"˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Land cover; Remote sensing; Ground truth; Multispectral image; Satellite; Image resolution; Convolutional neural network; Satellite imagery; Scale (ratio); Computer science; Earth observation; Sensor fusion; Environmental science; Land use; Cartography; Artificial intelligence; Geography","score_opus":0.026490474114842736,"score_gpt":0.24531528372982353,"score_spread":0.2188248096149808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3048021468","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34256098,0.0009146148,0.64779204,0.00030602925,0.00014283677,0.000042811116,0.00072946376,0.003120672,0.004390587],"genre_scores_gemma":[0.88869375,0.00018609146,0.10857006,0.00007517212,0.000028708822,0.000014236586,0.0007244892,0.000058886682,0.0016486312],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998759,0.000016468435,0.0000063543084,0.000030460507,0.000044020864,0.000026796686],"domain_scores_gemma":[0.999808,0.000045693585,0.000022542308,0.000038875398,0.00007369688,0.000011220806],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040455456,0.0005064544,0.0002740635,0.00074716884,0.0001359593,0.00038349317,0.00042229486,0.00027290892,0.0008772509],"category_scores_gemma":[0.0006125791,0.00019936649,0.00037688573,0.00063130964,0.00014269394,0.000689884,0.00061730976,0.0004381314,0.0002723602],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019931255,0.00017677186,0.0065429057,0.00008535453,0.00019584896,0.0001707259,0.000078980855,0.425473,0.05797467,0.0022781917,0.0041790972,0.5026452],"study_design_scores_gemma":[0.000002741212,0.000011498846,0.0014158182,0.0000032101393,0.000012307153,0.00001648908,0.000007454451,0.9918854,0.005611861,0.0005081437,0.0005211776,0.00000388368],"about_ca_topic_score_codex":0.007338959,"about_ca_topic_score_gemma":0.010270851,"teacher_disagreement_score":0.007338959,"about_ca_system_score_codex":0.00037789682,"about_ca_system_score_gemma":0.00031684595,"threshold_uncertainty_score":0.014592528},"labels":[],"label_agreement":null},{"id":"W3080805846","doi":"10.5194/isprs-archives-xliii-b3-2020-1507-2020","title":"EVALUATION OF UNet AND UNet++ ARCHITECTURES IN HIGH RESOLUTION IMAGE CHANGE DETECTION APPLICATIONS","year":2020,"lang":"en","type":"article","venue":"˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; York University","keywords":"Computer science; Change detection; Artificial intelligence; Segmentation; Deep learning; Convolutional neural network; Cross entropy; Dice; Task (project management); Hinge loss; Machine learning; Pattern recognition (psychology)","score_opus":0.03058053254671939,"score_gpt":0.2616409753011994,"score_spread":0.23106044275448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3080805846","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.959945,0.0013631796,0.026394458,0.00056528073,0.00026917696,0.00022069878,0.0011837768,0.0025057856,0.0075527085],"genre_scores_gemma":[0.95172936,0.00039852905,0.039573804,0.00025054094,0.000041380223,0.00016404822,0.00376865,0.00014763068,0.0039260876],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99949205,0.0001108803,0.00003923054,0.00013892513,0.00013179083,0.000087156106],"domain_scores_gemma":[0.99853814,0.00046727704,0.00010807236,0.00019761249,0.000586149,0.00010280502],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017188307,0.0012159992,0.0005431214,0.0006150063,0.00032179774,0.00067097205,0.0012782989,0.001152212,0.0022491994],"category_scores_gemma":[0.004324538,0.00033070904,0.00051156187,0.0004890822,0.0004175036,0.0011973788,0.0008129443,0.0010127134,0.0006630234],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001923662,0.0011800188,0.015455873,0.0006089334,0.0005099278,0.00035140233,0.000087961744,0.64965665,0.019726226,0.0012345122,0.011013579,0.2982513],"study_design_scores_gemma":[0.00008943873,0.0008023861,0.00541655,0.000033676606,0.000058228925,0.00009004853,0.000041245625,0.98046094,0.011281031,0.00042016347,0.001289408,0.000016963146],"about_ca_topic_score_codex":0.010672783,"about_ca_topic_score_gemma":0.014631349,"teacher_disagreement_score":0.010672783,"about_ca_system_score_codex":0.00091154437,"about_ca_system_score_gemma":0.00079936424,"threshold_uncertainty_score":0.02122134},"labels":[],"label_agreement":null},{"id":"W3082621301","doi":"10.3390/rs12172815","title":"Editorial for the Special Issue “Advanced Machine Learning for Time Series Remote Sensing Data Analysis”","year":2020,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Computer science; Big data; Series (stratigraphy); Principal (computer security); Data science; Remote sensing; Time series; Machine learning; Data mining; Computer security; Geology","score_opus":0.023264386534962357,"score_gpt":0.261539312900463,"score_spread":0.23827492636550066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3082621301","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000068300054,0.0016389614,0.00028335626,0.012691525,0.9839506,0.000021715909,0.00008988478,0.000083838895,0.0011717095],"genre_scores_gemma":[0.00036788185,0.0014397993,0.0001214485,0.005170002,0.9859167,0.000020485953,0.00007497396,0.00005632474,0.00683241],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969183,0.00037860096,0.00037936174,0.00061470055,0.0014961754,0.00021278276],"domain_scores_gemma":[0.98057574,0.0054281796,0.001218013,0.00052801915,0.009550685,0.0026992601],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044690203,0.0029097523,0.0030682918,0.0028840906,0.0017816841,0.0064049102,0.002586274,0.0055652466,0.031868476],"category_scores_gemma":[0.015291342,0.0008802606,0.0026506898,0.0010281476,0.0011817771,0.0033134746,0.0011926515,0.009290949,0.02337612],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052788597,0.000016659864,0.00004053383,0.0001457558,0.000016120382,0.000058919926,0.0000060890306,0.000030952153,0.00014077185,0.00019097215,0.9935381,0.005762459],"study_design_scores_gemma":[0.00007234917,0.000098262644,0.0007220036,0.00031854532,0.00005699999,0.00031869966,0.00003362406,0.0004220076,0.00040898653,0.0011270263,0.99639744,0.000024023617],"about_ca_topic_score_codex":0.00039892585,"about_ca_topic_score_gemma":0.00096842326,"teacher_disagreement_score":0.031868476,"about_ca_system_score_codex":0.0011294376,"about_ca_system_score_gemma":0.0016525271,"threshold_uncertainty_score":0.106610715},"labels":[],"label_agreement":null},{"id":"W3082700671","doi":"10.1016/j.patrec.2020.08.020","title":"Fused 3-D spectral-spatial deep neural networks and spectral clustering for hyperspectral image classification","year":2020,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":68,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Hyperspectral imaging; Pattern recognition (psychology); Artificial intelligence; Spectral bands; Dimensionality reduction; Computer science; Redundancy (engineering); Curse of dimensionality; Cluster analysis; Contextual image classification; Spectral clustering; Artificial neural network; Mathematics; Image (mathematics); Remote sensing; Geography","score_opus":0.03257109190918889,"score_gpt":0.22449476668214907,"score_spread":0.19192367477296018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3082700671","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08182236,0.00076557294,0.91184485,0.00041070615,0.00011772719,0.00003379074,0.000360838,0.0018425856,0.0028014926],"genre_scores_gemma":[0.7643432,0.00040991718,0.22898777,0.00025565748,0.00007421795,0.000062810934,0.00082372106,0.00013971969,0.004902972],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997938,0.00003417175,0.000009842045,0.000049874656,0.00006832568,0.000043971395],"domain_scores_gemma":[0.9997125,0.00007206662,0.00003132556,0.00004868149,0.000113630864,0.000021780932],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038652445,0.0007067517,0.00057015073,0.00061220326,0.0003004052,0.00063534774,0.000990107,0.0008970355,0.0016414602],"category_scores_gemma":[0.00088744465,0.00037227533,0.00079828635,0.0009237794,0.00037879474,0.0010367443,0.000985866,0.0010243469,0.00066620717],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003561707,0.0002508291,0.0019715335,0.00009516649,0.00016403293,0.000072899005,0.00009224073,0.5277789,0.029146627,0.007568328,0.005976475,0.42652678],"study_design_scores_gemma":[0.0000014053915,0.000006697916,0.00016668807,0.000001778697,0.0000043750783,0.0000056966196,0.0000051897405,0.99700266,0.0016166774,0.0010167436,0.00016902409,0.0000031198176],"about_ca_topic_score_codex":0.010897182,"about_ca_topic_score_gemma":0.018029504,"teacher_disagreement_score":0.010897182,"about_ca_system_score_codex":0.00064230245,"about_ca_system_score_gemma":0.0009147353,"threshold_uncertainty_score":0.02166754},"labels":[],"label_agreement":null},{"id":"W3085310384","doi":"10.1080/22797254.2020.1777802","title":"Introduction to the special issue on deep learning for remote sensing environments","year":2020,"lang":"en","type":"article","venue":"European Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Deep learning; Remote sensing; Data science; Computer science; Geography; Artificial intelligence","score_opus":0.01679963975665049,"score_gpt":0.21510704549236337,"score_spread":0.19830740573571287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3085310384","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009402032,0.13506901,0.07459559,0.07697617,0.6552632,0.0001589785,0.0022155426,0.0016829221,0.0530984],"genre_scores_gemma":[0.0072068456,0.10995058,0.025360392,0.029623166,0.54931366,0.00020054558,0.0038564245,0.0024457166,0.27204263],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988696,0.00012526393,0.000105801184,0.00029825934,0.00050249137,0.00009844671],"domain_scores_gemma":[0.9960049,0.0014294864,0.00015854587,0.00031169245,0.0014357693,0.000659666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019852407,0.0014723825,0.0016700537,0.0024002998,0.000753802,0.0037033998,0.0016611931,0.0027414034,0.061063346],"category_scores_gemma":[0.0051225964,0.00059685507,0.0013038217,0.0024828564,0.0009429061,0.0043049543,0.002241187,0.007076292,0.036590245],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002549749,0.0000302878,0.00014765382,0.0003216244,0.000025263576,0.00005396995,0.000016709131,0.0006279103,0.00053288386,0.005089839,0.9027913,0.09033704],"study_design_scores_gemma":[0.0000059984086,0.000027055916,0.0002713671,0.00021589782,0.0000117424315,0.0001476401,0.000010774577,0.0012531803,0.00026999327,0.0068277596,0.99094045,0.000018141234],"about_ca_topic_score_codex":0.0010815565,"about_ca_topic_score_gemma":0.0020671673,"teacher_disagreement_score":0.061063346,"about_ca_system_score_codex":0.0011140534,"about_ca_system_score_gemma":0.001537139,"threshold_uncertainty_score":0.20427728},"labels":[],"label_agreement":null},{"id":"W3087010089","doi":"10.1109/tip.2020.3023613","title":"MSdB-NMF: MultiSpectral Document Image Binarization Framework via Non-Negative Matrix Factorization Approach","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Non-negative matrix factorization; Computer science; Pattern recognition (psychology); Multispectral image; Artificial intelligence; Feature extraction; Hyperspectral imaging; Pixel; Matrix decomposition; Robustness (evolution); Feature vector","score_opus":0.012737189442607972,"score_gpt":0.2518734884020667,"score_spread":0.23913629895945873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3087010089","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022990692,0.00043305906,0.99587643,0.000082893894,0.00005012903,0.00003610459,0.00009173742,0.00050559576,0.0006248665],"genre_scores_gemma":[0.056703217,0.00063441996,0.93742925,0.00018919438,0.00011491209,0.00014570812,0.0007839354,0.00023858662,0.0037608363],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916434,0.00014614582,0.000037908736,0.000196303,0.0003827179,0.00007269608],"domain_scores_gemma":[0.9994042,0.0001471596,0.00007528538,0.000107405016,0.00022925332,0.000036700545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087812735,0.0011742584,0.0009344384,0.001345287,0.00050889695,0.00085690967,0.0013153508,0.001039832,0.0030676357],"category_scores_gemma":[0.0017273913,0.00034367625,0.0011016353,0.0011205797,0.0006095547,0.0015399681,0.00081030664,0.001450093,0.0019718327],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028379593,0.00012560839,0.00070213916,0.00032801097,0.00012585204,0.00013730385,0.000127178,0.07735568,0.07336469,0.014388534,0.009679591,0.82338154],"study_design_scores_gemma":[0.00003687457,0.00010744358,0.0015141466,0.000039379323,0.000046317728,0.00039683166,0.00006816224,0.93604386,0.031708892,0.009510844,0.020467436,0.00005984763],"about_ca_topic_score_codex":0.0046914984,"about_ca_topic_score_gemma":0.005663121,"teacher_disagreement_score":0.0046914984,"about_ca_system_score_codex":0.00061486795,"about_ca_system_score_gemma":0.00079099875,"threshold_uncertainty_score":0.0102623105},"labels":[],"label_agreement":null},{"id":"W3088162569","doi":"10.1109/jstars.2020.3026724","title":"Support Vector Machine Versus Random Forest for Remote Sensing Image Classification: A Meta-Analysis and Systematic Review","year":2020,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1055,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Institut National de la Recherche Scientifique; Centre For Cold Ocean Resources Engineering; Memorial University of Newfoundland","funders":"Innovation and Networks Executive Agency; European Commission","keywords":"Random forest; Support vector machine; Computer science; Contextual image classification; Remote sensing; Artificial intelligence; Pattern recognition (psychology); Statistical classification; Machine learning; Image (mathematics); Data mining; Geology","score_opus":0.07531220790302398,"score_gpt":0.271330975073877,"score_spread":0.196018767170853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088162569","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007981559,0.99700457,0.0011438476,0.0004558624,0.000093038856,0.00006558405,0.00025472074,0.00001076773,0.00017341066],"genre_scores_gemma":[0.024085663,0.96997404,0.0042538783,0.0005791064,0.0002348659,0.0003015209,0.00046892013,0.000018781328,0.00008309644],"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9901924,0.004104143,0.0027489671,0.0011774686,0.0015857782,0.00019131758],"domain_scores_gemma":[0.915463,0.07195742,0.00584511,0.0014269595,0.004908592,0.00039890283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02274283,0.001847688,0.007440731,0.018412152,0.0005357448,0.0040755244,0.0019595947,0.0017184787,0.0025453568],"category_scores_gemma":[0.068404526,0.0008510728,0.012189314,0.016394364,0.00097392086,0.0033447915,0.001127777,0.0016322108,0.00037621122],"study_design_candidate":"meta_analysis","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005875998,0.00009065675,0.008995379,0.5742811,0.06515119,0.00013106017,0.00033282794,0.0016459093,0.00037413734,0.002014514,0.0040297853,0.34236583],"study_design_scores_gemma":[0.00037278928,0.0009121339,0.019121323,0.5644231,0.3410396,0.0007926805,0.000894774,0.0028603387,0.001149066,0.006314122,0.0618993,0.00022081452],"about_ca_topic_score_codex":0.0064479867,"about_ca_topic_score_gemma":0.011155958,"teacher_disagreement_score":0.02274283,"about_ca_system_score_codex":0.0028712936,"about_ca_system_score_gemma":0.007592715,"threshold_uncertainty_score":0.12027699},"labels":[],"label_agreement":null},{"id":"W3091775311","doi":"10.1007/s11042-020-09809-2","title":"Color object segmentation and tracking using flexible statistical model and level-set","year":2020,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Artificial intelligence; Segmentation; Expectation–maximization algorithm; Image segmentation; Computer vision; Mixture model; Pattern recognition (psychology); Frame (networking); Feature (linguistics); Object (grammar); Scale-space segmentation; Tracking (education); Video tracking; Segmentation-based object categorization; Maximum likelihood; Mathematics","score_opus":0.14417067047631515,"score_gpt":0.3084002129739715,"score_spread":0.16422954249765637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3091775311","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005456141,0.00004383018,0.9937936,0.00003653912,0.0000073585193,0.000014830167,0.000031620617,0.00042246672,0.00019356255],"genre_scores_gemma":[0.299437,0.00017224584,0.69775784,0.00009565546,0.000029853189,0.00012425288,0.00043532404,0.00036050624,0.0015872912],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993136,0.000103469334,0.000036059333,0.00023476935,0.00023055151,0.000081521765],"domain_scores_gemma":[0.9992374,0.00026895246,0.00009004647,0.00019383764,0.00015892125,0.000050882085],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011327178,0.0007200584,0.0015109234,0.0016019433,0.0007389322,0.0017637938,0.002160045,0.0011990851,0.001279528],"category_scores_gemma":[0.00199838,0.00096611155,0.0018301969,0.001787992,0.0009404728,0.0021939154,0.001700406,0.0013778297,0.00065913546],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023150204,0.00016745094,0.0021609347,0.00010767683,0.00021513317,0.00008773521,0.0001089117,0.60833824,0.033032574,0.029871486,0.0015997462,0.32407865],"study_design_scores_gemma":[0.0000022337997,0.000007355498,0.00015578637,0.0000014141908,0.0000066066814,0.000011603804,0.0000022388758,0.99478006,0.0020267707,0.0028568327,0.00014255164,0.000006625319],"about_ca_topic_score_codex":0.008820805,"about_ca_topic_score_gemma":0.010904878,"teacher_disagreement_score":0.008820805,"about_ca_system_score_codex":0.0016333619,"about_ca_system_score_gemma":0.0017695382,"threshold_uncertainty_score":0.017538905},"labels":[],"label_agreement":null},{"id":"W3092922674","doi":"10.48550/arxiv.2010.06497","title":"Satellite Image Classification with Deep Learning","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lockheed Martin (Canada)","funders":"","keywords":"Computer science; Artificial intelligence; Deep learning; Convolutional neural network; Satellite imagery; Machine learning; Python (programming language); Automation; Metadata; Contextual image classification; Feature extraction; Artificial neural network; Remote sensing; Image (mathematics); World Wide Web; Operating system","score_opus":0.06620866626672732,"score_gpt":0.17260109513844676,"score_spread":0.10639242887171944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092922674","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022179147,0.0016842149,0.9569327,0.0008208952,0.00023057555,0.00013532117,0.001792558,0.010569644,0.0056549287],"genre_scores_gemma":[0.4558552,0.0022296733,0.51535594,0.0006733865,0.00039670285,0.00034013164,0.010958075,0.00048064653,0.013710329],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994832,0.00007439338,0.000031066356,0.00015614256,0.00019497245,0.000060171635],"domain_scores_gemma":[0.9994313,0.00013033609,0.000075975375,0.00015775466,0.00017758635,0.000026973126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007267711,0.0011181696,0.00070130837,0.0015106249,0.00030232908,0.001074514,0.0012296378,0.0010942823,0.0040598987],"category_scores_gemma":[0.0023891826,0.0004800702,0.0010155806,0.0023486083,0.00050119456,0.0013129709,0.0011388985,0.0015651144,0.0035313412],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010898154,0.00015818252,0.0024161257,0.00018310615,0.00018903373,0.00006722526,0.000050986542,0.27191702,0.0067320024,0.0075555793,0.024300832,0.6863209],"study_design_scores_gemma":[0.0000058922246,0.000016183163,0.00048560585,0.000016153788,0.000010217902,0.000016212485,0.000009457776,0.9863788,0.0021738817,0.0075322003,0.0033472872,0.0000080326445],"about_ca_topic_score_codex":0.010940872,"about_ca_topic_score_gemma":0.010811006,"teacher_disagreement_score":0.010940872,"about_ca_system_score_codex":0.0010739507,"about_ca_system_score_gemma":0.0008491967,"threshold_uncertainty_score":0.021754384},"labels":[],"label_agreement":null},{"id":"W3094695322","doi":"10.1109/lgrs.2020.3033149","title":"Depthwise Separable ResNet in the MAP Framework for Hyperspectral Image Classification","year":2020,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Hyperspectral imaging; Overfitting; Convolution (computer science); Residual neural network; Contextual image classification; Convolutional neural network; Pointwise; Spatial analysis; Decision boundary; Artificial neural network; Image (mathematics); Mathematics; Remote sensing; Support vector machine; Geography","score_opus":0.033813172268694805,"score_gpt":0.26071737466259626,"score_spread":0.22690420239390147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094695322","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032849196,0.0006589303,0.9593852,0.00030659325,0.00009379441,0.000060789265,0.00032725526,0.0026990671,0.0036191538],"genre_scores_gemma":[0.5648614,0.00065621675,0.4185562,0.00035588598,0.00015759277,0.0002401889,0.001497821,0.00033491623,0.013339821],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99983585,0.00004137721,0.0000055982478,0.00004385167,0.00004640356,0.000026888918],"domain_scores_gemma":[0.9998165,0.00006203118,0.000023730012,0.00003351927,0.000051781906,0.000012601185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047581436,0.0009638467,0.00054452533,0.0006534449,0.00027274035,0.00052482117,0.0011597394,0.00073430274,0.0027663696],"category_scores_gemma":[0.0008476635,0.0002886758,0.000549459,0.0005682706,0.00042955822,0.0013046633,0.00060985546,0.0010598404,0.0009235471],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018241986,0.00013337635,0.00068059604,0.00009974091,0.00008997093,0.00013658265,0.00007153508,0.6471002,0.009263255,0.020199,0.007234479,0.31480882],"study_design_scores_gemma":[0.0000033870585,0.000020956957,0.00010142694,0.0000037436157,0.0000041059616,0.000015410527,0.000006285726,0.9931552,0.0018850509,0.0038441103,0.0009558537,0.0000044674393],"about_ca_topic_score_codex":0.009269765,"about_ca_topic_score_gemma":0.013656779,"teacher_disagreement_score":0.009269765,"about_ca_system_score_codex":0.0007004678,"about_ca_system_score_gemma":0.0006517761,"threshold_uncertainty_score":0.018431664},"labels":[],"label_agreement":null},{"id":"W3100231084","doi":"10.1109/tgrs.2020.3033293","title":"Multigranularity Multiclass-Layer Markov Random Field Model for Semantic Segmentation of Remote Sensing Images","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"National Natural Science Foundation of China","keywords":"Computer science; Markov random field; Artificial intelligence; Segmentation; Image segmentation; Granularity; Pattern recognition (psychology); Pixel; Graph; Scale-space segmentation; Semantics (computer science); Computer vision; Theoretical computer science","score_opus":0.029701708667863255,"score_gpt":0.2620758276135057,"score_spread":0.23237411894564242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3100231084","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010329315,0.0005589987,0.9874042,0.00022539479,0.000043561464,0.000030652507,0.000109720604,0.00046625632,0.0008319519],"genre_scores_gemma":[0.65724045,0.0011547243,0.33309358,0.0003708791,0.00019093533,0.00024072442,0.0008340826,0.00021525474,0.0066593424],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99946934,0.00013805597,0.00002576227,0.00017788142,0.0001136663,0.00007532325],"domain_scores_gemma":[0.9994604,0.0002984073,0.00008418948,0.000043398897,0.00008819625,0.00002540912],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011304477,0.0008109632,0.0010090455,0.0010877723,0.00037483653,0.00092930574,0.0018534668,0.0013749079,0.0016747708],"category_scores_gemma":[0.0018708585,0.00048172456,0.0015357878,0.0008555863,0.0007195474,0.0015488812,0.000518079,0.0014333698,0.00045496144],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012763796,0.000056915804,0.0012527152,0.00011624994,0.0000887874,0.00013606065,0.00011698186,0.89297605,0.004386046,0.023504585,0.001703072,0.07553491],"study_design_scores_gemma":[0.0000027374042,0.000005615455,0.00011041554,0.0000032082246,0.0000072930575,0.000011632852,0.0000024928602,0.9963483,0.0002553126,0.0030294468,0.00021868953,0.0000049230575],"about_ca_topic_score_codex":0.015353363,"about_ca_topic_score_gemma":0.013517141,"teacher_disagreement_score":0.015353363,"about_ca_system_score_codex":0.0014810468,"about_ca_system_score_gemma":0.0009794566,"threshold_uncertainty_score":0.03052795},"labels":[],"label_agreement":null},{"id":"W3111097319","doi":"10.18280/ts.370510","title":"Clustering-Based Band Selection Using Structural Similarity Index and Entropy for Hyperspectral Image Classification","year":2020,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Hyperspectral imaging; Pattern recognition (psychology); Artificial intelligence; Cluster analysis; Entropy (arrow of time); Classifier (UML); Computer science; Dimensionality reduction; Mathematics; Feature selection; Spectral bands; Remote sensing; Geography","score_opus":0.037400030562466616,"score_gpt":0.25300174749176535,"score_spread":0.21560171692929875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111097319","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09666595,0.00056178245,0.90016454,0.00011159285,0.000039464012,0.00009241831,0.000082047234,0.0006427221,0.0016393977],"genre_scores_gemma":[0.639087,0.00043166618,0.35832185,0.000057146593,0.00006764422,0.00014480672,0.00041255844,0.00008013737,0.00139714],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99946755,0.00009144832,0.00003772995,0.00010948334,0.0002421454,0.0000517033],"domain_scores_gemma":[0.99957126,0.0001296494,0.000079695565,0.000034928224,0.00016323722,0.000021164964],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068577786,0.0006431518,0.0006158087,0.002326713,0.00045029927,0.00053262897,0.00046195337,0.0003934379,0.0005691268],"category_scores_gemma":[0.0011056267,0.00016348684,0.0007296952,0.0015255429,0.00040731562,0.00063716696,0.00039399433,0.00038189287,0.00023756867],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036480676,0.00023346697,0.006644912,0.00021560167,0.00018901234,0.00014098168,0.00024503836,0.12213967,0.089558855,0.0043176757,0.002745615,0.7732044],"study_design_scores_gemma":[0.000015093291,0.000087295266,0.008871603,0.000017370563,0.00006901009,0.00015920581,0.00007846619,0.9548193,0.031664744,0.002442587,0.0017356764,0.000039614344],"about_ca_topic_score_codex":0.002098672,"about_ca_topic_score_gemma":0.0024525824,"teacher_disagreement_score":0.002326713,"about_ca_system_score_codex":0.00037714414,"about_ca_system_score_gemma":0.00062377576,"threshold_uncertainty_score":0.004172921},"labels":[],"label_agreement":null},{"id":"W3111117988","doi":"10.1109/smc42975.2020.9283349","title":"A Hybrid Approach Based on SVM and Bernoulli Mixture Model for Binary Vectors Classification","year":2020,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Support vector machine; Artificial intelligence; Computer science; Discriminative model; Pattern recognition (psychology); Binary number; Bernoulli's principle; Binary classification; Probabilistic logic; Machine learning; Data classification; Divergence (linguistics); Generative model; Mixture model; Generative grammar; Mathematics; Engineering","score_opus":0.04421118144375227,"score_gpt":0.2272244597159448,"score_spread":0.18301327827219252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111117988","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004667599,0.0004913869,0.9938221,0.000098555574,0.000053773863,0.00002464705,0.000020308651,0.00038735964,0.00043431998],"genre_scores_gemma":[0.32167837,0.0011605406,0.6713567,0.0002972398,0.00031683542,0.00022901982,0.00041807996,0.0001855601,0.0043576634],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978137,0.0005708517,0.00016372607,0.0004531886,0.0008471746,0.00015139762],"domain_scores_gemma":[0.99893206,0.00041064422,0.0000769104,0.000135206,0.00037701163,0.00006808603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020433879,0.0009441808,0.0018763301,0.0031804997,0.0005176108,0.0013342916,0.0018553223,0.0013718774,0.001411678],"category_scores_gemma":[0.002757861,0.0005461328,0.0014721742,0.0026117456,0.00073448365,0.0028122596,0.0013770217,0.0015843592,0.0009104698],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030116216,0.00028676807,0.0041835415,0.00024671634,0.00027245822,0.00011475915,0.00018097952,0.139291,0.018272933,0.03427967,0.0050558816,0.79751426],"study_design_scores_gemma":[0.0000073678266,0.000047415026,0.0003745722,0.000009039828,0.00001927476,0.00007365104,0.00001177656,0.98913443,0.0017242279,0.007165378,0.0014119871,0.000020811549],"about_ca_topic_score_codex":0.0021740494,"about_ca_topic_score_gemma":0.0015857017,"teacher_disagreement_score":0.0031804997,"about_ca_system_score_codex":0.00065943925,"about_ca_system_score_gemma":0.00072971295,"threshold_uncertainty_score":0.0108065605},"labels":[],"label_agreement":null},{"id":"W3112695593","doi":"10.18280/ts.370514","title":"Superpixel-Based Minimum Noise Fraction Feature Extraction for Classification of Hyperspectral Images","year":2020,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Hyperspectral imaging; Pattern recognition (psychology); Artificial intelligence; Feature extraction; Classifier (UML); Support vector machine; Covariance matrix; Dimensionality reduction; Principal component analysis; Computer science; Mathematics; Noise (video); Transformation (genetics); Transformation matrix; Image (mathematics); Statistics; Chemistry","score_opus":0.029420904915406495,"score_gpt":0.25324804986625676,"score_spread":0.22382714495085027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3112695593","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026234897,0.00044090967,0.9716532,0.0000750879,0.000031720618,0.000032957465,0.00010401644,0.00074989244,0.00067730964],"genre_scores_gemma":[0.33628374,0.00056094566,0.66015434,0.000068569345,0.00007348738,0.00009699326,0.0007660117,0.00016222587,0.0018336787],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995701,0.000056188983,0.000020433494,0.000102468024,0.00019845899,0.000052314936],"domain_scores_gemma":[0.9997228,0.00008010566,0.000048356014,0.000042115007,0.00009178082,0.000014791923],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004496265,0.0006968786,0.0009844952,0.0014451494,0.000319868,0.0005351316,0.0006175825,0.0005584874,0.0010971909],"category_scores_gemma":[0.00093450386,0.00025587808,0.0008843354,0.0013585525,0.00033728592,0.0011690246,0.00039691335,0.0005366594,0.00049427897],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022867555,0.00009938903,0.0023355603,0.00017059731,0.00007936773,0.00017307227,0.00008890477,0.03564793,0.16670342,0.0029044652,0.0025610556,0.78900754],"study_design_scores_gemma":[0.000013175395,0.00009472372,0.008917172,0.000016385804,0.00005141991,0.00045220248,0.000048969945,0.9262906,0.0561299,0.0024958458,0.0054545254,0.000035046207],"about_ca_topic_score_codex":0.0018951116,"about_ca_topic_score_gemma":0.0024642784,"teacher_disagreement_score":0.0018951116,"about_ca_system_score_codex":0.0003394545,"about_ca_system_score_gemma":0.0004335606,"threshold_uncertainty_score":0.0037682056},"labels":[],"label_agreement":null},{"id":"W3112925912","doi":"10.1016/j.isprsjprs.2020.11.013","title":"Improving hyperspectral image segmentation by applying inverse noise weighting and outlier removal for optimal scale selection","year":2020,"lang":"en","type":"article","venue":"ISPRS Journal of Photogrammetry and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":44,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ontario Institute of Technology; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Weighting; Hyperspectral imaging; Outlier; Artificial intelligence; Selection (genetic algorithm); Pattern recognition (psychology); Scale (ratio); Segmentation; Computer science; Noise (video); Computer vision; Image (mathematics); Geography; Cartography","score_opus":0.010751265447569963,"score_gpt":0.22698017141414914,"score_spread":0.21622890596657918,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3112925912","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047488738,0.0002009415,0.9497285,0.00008691674,0.000055512715,0.000036005706,0.00006439483,0.0013962252,0.0009427387],"genre_scores_gemma":[0.23774932,0.0002726967,0.7587175,0.00007915125,0.000052831598,0.000052297622,0.00048664233,0.0005580808,0.0020315493],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99939525,0.0000678798,0.000040761395,0.00013959028,0.00027847072,0.000078110024],"domain_scores_gemma":[0.9995454,0.00008345557,0.000051631487,0.00007808437,0.00022230891,0.000019153053],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006012695,0.0010493451,0.0009799841,0.0014899785,0.0005069695,0.0010954676,0.0006939767,0.0006970616,0.001365831],"category_scores_gemma":[0.0013645828,0.00033600634,0.0010343372,0.0015862483,0.00047001638,0.0009919466,0.0008029913,0.00061676017,0.00094858016],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023953589,0.00019006529,0.002724344,0.00019278626,0.00012148654,0.00013399316,0.00023607246,0.045848895,0.2862953,0.0028856464,0.0028325142,0.6582993],"study_design_scores_gemma":[0.000020001613,0.00006311522,0.0056191944,0.000012914345,0.000083630664,0.00014503305,0.00008380823,0.89729553,0.0900878,0.002381011,0.0041725286,0.000035389032],"about_ca_topic_score_codex":0.0037207592,"about_ca_topic_score_gemma":0.0065770135,"teacher_disagreement_score":0.0037207592,"about_ca_system_score_codex":0.00029354435,"about_ca_system_score_gemma":0.0009498545,"threshold_uncertainty_score":0.007398188},"labels":[],"label_agreement":null},{"id":"W3114371502","doi":"10.1016/j.knosys.2020.106549","title":"Feature-reduction fuzzy co-clustering approach for hyper-spectral image analysis","year":2020,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Cluster analysis; Pattern recognition (psychology); Fuzzy clustering; Artificial intelligence; Data mining; Correlation clustering; Computer science; FLAME clustering; Canopy clustering algorithm; Feature (linguistics); CURE data clustering algorithm; Dimensionality reduction; Mathematics","score_opus":0.031094224580665537,"score_gpt":0.2568405872903086,"score_spread":0.22574636270964307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3114371502","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0066247894,0.00031704875,0.9917739,0.000053013373,0.000032077663,0.000027053893,0.00004009368,0.00018704502,0.000944971],"genre_scores_gemma":[0.35247797,0.00053398864,0.64144343,0.000085509986,0.0000890916,0.00018150262,0.00038922558,0.00010607794,0.00469322],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99935216,0.000097074124,0.000039796912,0.00015345428,0.00030506618,0.00005248015],"domain_scores_gemma":[0.99948525,0.000091222246,0.00003565837,0.00006210076,0.00030976822,0.000015942469],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005491888,0.0005082117,0.00086007785,0.001824506,0.00089865277,0.0008414292,0.0011386165,0.0007437847,0.0014928508],"category_scores_gemma":[0.0010385746,0.00020560258,0.0012302762,0.0016804058,0.00045250903,0.00068999844,0.00066010765,0.0006239539,0.00069308677],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017780662,0.00020466566,0.0011976399,0.00032861147,0.00032105276,0.00015743691,0.00027796463,0.19046205,0.045358397,0.018846659,0.0042348932,0.73843277],"study_design_scores_gemma":[0.0000049541945,0.00003706883,0.0012877777,0.0000126489285,0.000052939373,0.00009962085,0.00005064737,0.9822503,0.0074913735,0.0062953723,0.0023905754,0.000026681882],"about_ca_topic_score_codex":0.008128483,"about_ca_topic_score_gemma":0.0075581996,"teacher_disagreement_score":0.008128483,"about_ca_system_score_codex":0.00059357745,"about_ca_system_score_gemma":0.0009049614,"threshold_uncertainty_score":0.016162336},"labels":[],"label_agreement":null},{"id":"W3120662950","doi":"10.1080/01431161.2020.1862437","title":"Building change detection in very high-resolution remote sensing image based on pseudo-orthorectification","year":2021,"lang":"en","type":"article","venue":"International Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China; Ministry of Natural Resources","keywords":"Orthophoto; Computer science; Aerial image; Shadow (psychology); Computer vision; Remote sensing; Artificial intelligence; Change detection; Facade; Satellite; Line (geometry); Consistency (knowledge bases); Constraint (computer-aided design); Elevation (ballistics); Roof; Photogrammetry; Image (mathematics); Geography; Mathematics","score_opus":0.02225516031754784,"score_gpt":0.26414349224268413,"score_spread":0.24188833192513629,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3120662950","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16217113,0.0006450589,0.83099985,0.00009080983,0.0000929315,0.00011675089,0.00031106253,0.0022442718,0.0033281336],"genre_scores_gemma":[0.58433104,0.00085681194,0.4106075,0.00013373821,0.00008182352,0.00012678913,0.0014453002,0.00017930525,0.0022376922],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990865,0.00008462462,0.000033120647,0.00020355446,0.00049045146,0.00010174418],"domain_scores_gemma":[0.99967206,0.000048950886,0.000049386734,0.00006839695,0.0001409743,0.000020306816],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004464485,0.00066258974,0.00069434155,0.0022020095,0.00030905352,0.0007832073,0.0007438662,0.00053677807,0.0008595351],"category_scores_gemma":[0.0007501188,0.00042324193,0.0008740591,0.0016188555,0.00042784287,0.0012055753,0.0006237984,0.0005004904,0.0005377721],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002462401,0.00016381225,0.011769032,0.0004602253,0.00019457527,0.0003772494,0.00025791914,0.02838179,0.22590479,0.0014029903,0.0029076594,0.72793376],"study_design_scores_gemma":[0.000071346556,0.0002272567,0.08142178,0.000042540043,0.0002657117,0.0020138035,0.0003260189,0.77186644,0.13410471,0.0019608615,0.0075362944,0.00016331591],"about_ca_topic_score_codex":0.0027472798,"about_ca_topic_score_gemma":0.0046679974,"teacher_disagreement_score":0.0027472798,"about_ca_system_score_codex":0.00018205041,"about_ca_system_score_gemma":0.0004869862,"threshold_uncertainty_score":0.005462587},"labels":[],"label_agreement":null},{"id":"W3120854878","doi":"10.3390/rs13010158","title":"Identification and Evaluation of Urban Construction Waste with VHR Remote Sensing Using Multi-Feature Analysis and a Hierarchical Segmentation Method","year":2021,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Construction waste; Remote sensing; Computer science; Context (archaeology); Feature (linguistics); Segmentation; Confusion; Urbanization; Identification (biology); Environmental science; Artificial intelligence; Geography; Engineering; Waste management","score_opus":0.028732145785169815,"score_gpt":0.3035041897567786,"score_spread":0.2747720439716088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3120854878","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5211835,0.00019700898,0.4759854,0.000057034602,0.000018200102,0.00010612224,0.00017904773,0.0008197982,0.001453922],"genre_scores_gemma":[0.8116238,0.00012394351,0.18732451,0.000024014922,0.000010891348,0.000055963028,0.00026263797,0.00003888112,0.0005352034],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99946755,0.000077622586,0.00004814936,0.00010459575,0.00022884842,0.000073187126],"domain_scores_gemma":[0.99953663,0.00011727071,0.000081133585,0.000043975342,0.00019290231,0.000028052415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007058148,0.00054425217,0.00048495192,0.0043179872,0.00030582878,0.00073773926,0.00040484004,0.0005162285,0.0004373298],"category_scores_gemma":[0.001011605,0.0002815266,0.00069621176,0.0016652192,0.00039386968,0.0008261581,0.0004433672,0.00019673712,0.00015892767],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045547364,0.0003945841,0.037670676,0.00036603937,0.00014785111,0.00041993684,0.00042589303,0.12743264,0.33524492,0.0017206363,0.00067894533,0.49504238],"study_design_scores_gemma":[0.000024503628,0.00015582326,0.05325303,0.000017472967,0.000088346125,0.00018816766,0.00024583619,0.8759595,0.06873896,0.0006099189,0.00065999385,0.000058458187],"about_ca_topic_score_codex":0.005744391,"about_ca_topic_score_gemma":0.0048500495,"teacher_disagreement_score":0.005744391,"about_ca_system_score_codex":0.00042450748,"about_ca_system_score_gemma":0.0004765472,"threshold_uncertainty_score":0.011421919},"labels":[],"label_agreement":null},{"id":"W3121081157","doi":"10.12000/jr20118","title":"Change Detection Method Based on Fusion Difference Map in Flood Disaster","year":2020,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Change detection; Synthetic aperture radar; Flood myth; Remote sensing; Markov random field; Entropy (arrow of time); Computer science; Cluster analysis; Segmentation; Image segmentation; Geography; Artificial intelligence","score_opus":0.3268293949460406,"score_gpt":0.5079570978776721,"score_spread":0.1811277029316315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3121081157","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18326247,0.00022005959,0.8136502,0.00009492523,0.00006566017,0.000085328684,0.0000745587,0.0011152318,0.0014315796],"genre_scores_gemma":[0.7891084,0.00015481582,0.20917656,0.000041123716,0.000031470863,0.00006815675,0.0001682463,0.00006390308,0.0011873282],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99927086,0.00009319309,0.00004324171,0.00019107397,0.00032057302,0.00008108293],"domain_scores_gemma":[0.9992086,0.0002613821,0.00007643988,0.00008471652,0.0003196107,0.00004928312],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010392858,0.00040425733,0.00063385593,0.0024963075,0.00048563333,0.00076976704,0.0007328326,0.00058027776,0.0008105904],"category_scores_gemma":[0.0023563404,0.0003958096,0.0006575139,0.0012604592,0.00052569027,0.001560725,0.0009914387,0.0004502263,0.00023705956],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008033106,0.00018882743,0.01748787,0.00021945054,0.00015096932,0.00060707337,0.00077723846,0.113339216,0.065026194,0.0056852107,0.0017975433,0.79391706],"study_design_scores_gemma":[0.0000422559,0.00015876781,0.0124039035,0.00001190803,0.000057727008,0.00045213304,0.00015199557,0.95101184,0.030759975,0.003077902,0.0018083564,0.00006330326],"about_ca_topic_score_codex":0.0022675195,"about_ca_topic_score_gemma":0.0012962834,"teacher_disagreement_score":0.0024963075,"about_ca_system_score_codex":0.00043935076,"about_ca_system_score_gemma":0.00048251986,"threshold_uncertainty_score":0.005496323},"labels":[],"label_agreement":null},{"id":"W3123794525","doi":"10.3390/rs13020324","title":"Triple-Attention-Based Parallel Network for Hyperspectral Image Classification","year":2021,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China","keywords":"Computer science; Hyperspectral imaging; Pattern recognition (psychology); Overfitting; Artificial intelligence; Convolutional neural network; Data mining; Artificial neural network","score_opus":0.026136893349546744,"score_gpt":0.25430557628218026,"score_spread":0.2281686829326335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3123794525","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11866118,0.0010368797,0.8692836,0.00036366275,0.00013996655,0.0001016814,0.0003547341,0.0039320514,0.0061262343],"genre_scores_gemma":[0.8333334,0.00042090568,0.15604301,0.0003341879,0.00009193297,0.00016059181,0.0011114967,0.00014380181,0.008360708],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9997683,0.000025931651,0.000009016734,0.000089991016,0.000051457468,0.000055221757],"domain_scores_gemma":[0.99969745,0.000089544104,0.00003370143,0.000046974954,0.0001060442,0.000026328906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044195805,0.0009930113,0.0006518526,0.00066216994,0.00046008546,0.000573478,0.0015078599,0.00068020646,0.0022217394],"category_scores_gemma":[0.0008560206,0.00031278693,0.00054361654,0.0007795725,0.00046295804,0.0014064756,0.00096190226,0.0010431568,0.00057278376],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004096401,0.00039018353,0.0029639516,0.00015371255,0.00015909788,0.00017447307,0.00011677208,0.3558411,0.034150716,0.0060066115,0.0068120672,0.5928217],"study_design_scores_gemma":[0.0000072213747,0.000045290064,0.00036334476,0.0000044284925,0.000025295954,0.000031921536,0.000011407371,0.99060833,0.0060545458,0.0021678314,0.0006739685,0.000006420025],"about_ca_topic_score_codex":0.009717153,"about_ca_topic_score_gemma":0.015163711,"teacher_disagreement_score":0.009717153,"about_ca_system_score_codex":0.0010104188,"about_ca_system_score_gemma":0.0009376348,"threshold_uncertainty_score":0.019321203},"labels":[],"label_agreement":null},{"id":"W3128031893","doi":"10.3390/rs13030492","title":"Landscape Similarity Analysis Using Texture Encoded Deep-Learning Features on Unclassified Remote Sensing Imagery","year":2021,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Discriminative model; Computer science; Artificial intelligence; Convolutional neural network; Pattern recognition (psychology); Concatenation (mathematics); Generalization; Feature (linguistics); Similarity (geometry); Deep learning; Contextual image classification; Transfer of learning; Computer vision; Image (mathematics); Mathematics","score_opus":0.018800325282185767,"score_gpt":0.24930497298543883,"score_spread":0.23050464770325307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3128031893","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8047534,0.0004768326,0.18481593,0.00022935783,0.00007818674,0.000099583995,0.0013756746,0.0025004502,0.0056706145],"genre_scores_gemma":[0.96071357,0.00010159249,0.035913654,0.00006237516,0.000021170694,0.000023115861,0.0018601115,0.000066526874,0.0012379279],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998747,0.000011144278,0.0000059711297,0.000041011135,0.000037798673,0.000029345863],"domain_scores_gemma":[0.9998273,0.00002941525,0.000031584543,0.000032646614,0.000062219784,0.000016807104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020745995,0.0004304145,0.00033489775,0.0015259039,0.00013085712,0.000496977,0.00042446784,0.00025731733,0.0010856558],"category_scores_gemma":[0.0007230741,0.00013852527,0.00058709853,0.0008803986,0.00020899923,0.0007397904,0.0005437015,0.0003915133,0.0003892187],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005041216,0.0003224437,0.027303832,0.00019855578,0.0002521898,0.0005384885,0.00016977126,0.3152122,0.10991134,0.0032734552,0.0069002714,0.53541327],"study_design_scores_gemma":[0.000010441305,0.000045670033,0.012160083,0.000008770118,0.000022607852,0.00008360301,0.000050116072,0.9758769,0.009590235,0.0013438379,0.00079714967,0.000010592511],"about_ca_topic_score_codex":0.0067401165,"about_ca_topic_score_gemma":0.008881549,"teacher_disagreement_score":0.0067401165,"about_ca_system_score_codex":0.00042612705,"about_ca_system_score_gemma":0.00026867594,"threshold_uncertainty_score":0.013401806},"labels":[],"label_agreement":null},{"id":"W3134023526","doi":"","title":"طبقه بندی مبتنی بر هدف با استفاده از قطعه بندی هرمی و الگوریتم ژنتیک وزن دار","year":2020,"lang":"fa","type":"article","venue":"کاربرد سنجش از دور و سیستم اطلاعات جغرافیایی در برنامه ریزی","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Geography","score_opus":0.0433465092212936,"score_gpt":0.1989462972802485,"score_spread":0.1555997880589549,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134023526","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34773287,0.013671432,0.14579393,0.0043177293,0.0029167277,0.00080977264,0.0029944663,0.0017635915,0.47999942],"genre_scores_gemma":[0.54756385,0.011623818,0.10313392,0.0015406879,0.0003832443,0.0009248541,0.003502649,0.0014567929,0.3298702],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889344,0.00011691295,0.000085762484,0.00023354584,0.0004923904,0.00017804837],"domain_scores_gemma":[0.9988225,0.00015780538,0.00018823984,0.00011356132,0.0006073033,0.00011064794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079168356,0.00086748245,0.00052509183,0.0010822404,0.001408366,0.002833315,0.000593276,0.0013080449,0.040043842],"category_scores_gemma":[0.0016070128,0.0007209153,0.00064018276,0.0013082549,0.001321118,0.0021029806,0.0013951255,0.0019980483,0.023085585],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019975975,0.00034453085,0.0059706816,0.0024131534,0.00012890603,0.0033450145,0.0040712105,0.0028534285,0.6202914,0.07654575,0.019335952,0.26270238],"study_design_scores_gemma":[0.00009077057,0.0005632003,0.015759794,0.00044545543,0.00014280008,0.0021137088,0.006954098,0.0026520053,0.4741526,0.024114612,0.47277394,0.00023710112],"about_ca_topic_score_codex":0.0034879262,"about_ca_topic_score_gemma":0.0038477874,"teacher_disagreement_score":0.040043842,"about_ca_system_score_codex":0.0013667744,"about_ca_system_score_gemma":0.0023690725,"threshold_uncertainty_score":0.13395995},"labels":[],"label_agreement":null},{"id":"W3137634992","doi":"10.1109/jstars.2021.3065569","title":"A Meta-Analysis of Convolutional Neural Networks for Remote Sensing Applications","year":2021,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Centre For Cold Ocean Resources Engineering; Memorial University of Newfoundland; Université Laval","funders":"","keywords":"Computer science; Convolutional neural network; Process (computing); Artificial intelligence; Machine learning; Deep learning; Data science; Data mining","score_opus":0.06855435287909702,"score_gpt":0.2602914432046109,"score_spread":0.1917370903255139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3137634992","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02050806,0.8252109,0.12043517,0.005679228,0.0011620232,0.00023651357,0.0036156739,0.0005670112,0.022585372],"genre_scores_gemma":[0.27615386,0.5887566,0.116479844,0.0024644898,0.001412697,0.000559257,0.006265312,0.00046428546,0.00744368],"study_design_codex":"design_other","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9980379,0.0006813342,0.00025584458,0.00031853252,0.0006175114,0.00008900712],"domain_scores_gemma":[0.9906853,0.0058503235,0.0005404265,0.0008696161,0.0019454843,0.000108845954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006033194,0.0010760992,0.00085920753,0.0060172267,0.00027275595,0.002531529,0.001158168,0.0006366968,0.0021700696],"category_scores_gemma":[0.019894168,0.00043576537,0.0024995236,0.004459516,0.0003902495,0.0024954989,0.0007556165,0.001065329,0.0005718319],"study_design_candidate":"meta_analysis","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045732458,0.00009907303,0.013332287,0.02744477,0.0079478575,0.0002888292,0.00028753732,0.041201938,0.004659225,0.0840098,0.022563992,0.7977075],"study_design_scores_gemma":[0.00011851002,0.0009985757,0.025738427,0.036008943,0.022727992,0.0010253396,0.0004734566,0.16180769,0.018511908,0.15233216,0.58000827,0.00024871688],"about_ca_topic_score_codex":0.0049040415,"about_ca_topic_score_gemma":0.008967947,"teacher_disagreement_score":0.006033194,"about_ca_system_score_codex":0.0022950973,"about_ca_system_score_gemma":0.002997341,"threshold_uncertainty_score":0.031906962},"labels":[],"label_agreement":null},{"id":"W3138288887","doi":"10.3390/rs13061123","title":"Fast and Accurate Terrain Image Classification for ASTER Remote Sensing by Data Stream Mining and Evolutionary-EAC Instance-Learning-Based Algorithm","year":2021,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"Guangdong Provincial Applied Science and Technology Research and Development Program","keywords":"Computer science; Data stream; Data stream mining; Data mining; Algorithm; Machine learning; Artificial intelligence","score_opus":0.02953703006046598,"score_gpt":0.26586577484994517,"score_spread":0.23632874478947918,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3138288887","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031637944,0.00024016415,0.9656412,0.00018072182,0.000036113386,0.00009446574,0.000104379826,0.0009065161,0.0011584931],"genre_scores_gemma":[0.3916347,0.0003150172,0.6044485,0.00013928422,0.00007067742,0.000279351,0.0007920785,0.00009071249,0.0022296265],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996531,0.000047647423,0.000028590159,0.00010914324,0.00011099307,0.000050577877],"domain_scores_gemma":[0.9996253,0.00013933243,0.00005247868,0.000047062764,0.00010512701,0.00003071564],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006519653,0.0007149381,0.0010483689,0.0011878285,0.00034244685,0.0008851991,0.0017476792,0.00089329714,0.0010299344],"category_scores_gemma":[0.001452362,0.00035002088,0.0008474636,0.0016695227,0.0003158097,0.0011064975,0.000714512,0.0012891833,0.00030632076],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011034976,0.00015424842,0.0025514043,0.000069987895,0.000061055995,0.00011002485,0.00006865221,0.574912,0.0046744337,0.0044533135,0.0036990612,0.40913546],"study_design_scores_gemma":[0.0000023201096,0.000005075246,0.00008568433,9.919972e-7,0.000001850868,0.0000066083308,0.0000032237192,0.9990163,0.00032759193,0.00040084423,0.00014803385,0.0000014933595],"about_ca_topic_score_codex":0.008925849,"about_ca_topic_score_gemma":0.005842137,"teacher_disagreement_score":0.008925849,"about_ca_system_score_codex":0.0007728728,"about_ca_system_score_gemma":0.0011247493,"threshold_uncertainty_score":0.01774782},"labels":[],"label_agreement":null},{"id":"W3140087211","doi":"","title":"A study on the effects of compression on hyperspectral image classification.","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Hyperspectral imaging; Pixel; Artificial intelligence; Computer science; Compression (physics); Pattern recognition (psychology); Image compression; Image resolution; Data compression; Computer vision; Remote sensing; Image (mathematics); Geography; Image processing","score_opus":0.0757105908847432,"score_gpt":0.19989702089210182,"score_spread":0.12418643000735861,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3140087211","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6529445,0.014157685,0.31735715,0.0015329582,0.0005116417,0.00044907184,0.0010198127,0.00084121275,0.011185928],"genre_scores_gemma":[0.8686684,0.0061911466,0.11935048,0.00037999227,0.00028654694,0.00016942635,0.0014645655,0.00018474678,0.003304654],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985513,0.00032883327,0.00011885124,0.00020282318,0.0007257561,0.00007240026],"domain_scores_gemma":[0.98839474,0.008374823,0.0008197108,0.0010426842,0.001272536,0.00009554739],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001933278,0.00068663264,0.0004243675,0.0008823112,0.0003949258,0.0007440995,0.000495365,0.00056077354,0.0014752405],"category_scores_gemma":[0.014084324,0.00016060431,0.00038435034,0.0013919418,0.0006233702,0.0017352493,0.00047682598,0.0007593188,0.00039555368],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009391077,0.00050480565,0.013370866,0.0011641758,0.00032999215,0.0003594878,0.00033118296,0.07249696,0.14480014,0.0036207535,0.0030439887,0.75903857],"study_design_scores_gemma":[0.00006155974,0.0019402525,0.0543874,0.0003178315,0.0003346581,0.002226648,0.00045649844,0.5270227,0.39143038,0.005676322,0.016015429,0.000130316],"about_ca_topic_score_codex":0.0011430144,"about_ca_topic_score_gemma":0.0011499433,"teacher_disagreement_score":0.001933278,"about_ca_system_score_codex":0.00039720495,"about_ca_system_score_gemma":0.00026747133,"threshold_uncertainty_score":0.010224283},"labels":[],"label_agreement":null},{"id":"W3141690430","doi":"10.3390/rs13071323","title":"Feature-Level Fusion of Polarized SAR and Optical Images Based on Random Forest and Conditional Random Fields","year":2021,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Science and Technology Major Project; National Natural Science Foundation of China","keywords":"Random forest; Conditional random field; Synthetic aperture radar; Computer science; Feature (linguistics); Artificial intelligence; Pattern recognition (psychology); Fusion; Pairwise comparison; Remote sensing; Random field; Fuse (electrical); Contextual image classification; Image (mathematics); Mathematics; Statistics; Geography; Physics","score_opus":0.014918696557579601,"score_gpt":0.22856276181777163,"score_spread":0.21364406526019203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3141690430","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07427919,0.0002567236,0.9229157,0.00012632445,0.00006396807,0.000050234066,0.00023856605,0.0012085807,0.0008607594],"genre_scores_gemma":[0.8326034,0.00015916667,0.16492684,0.00008041641,0.00005947011,0.00006252322,0.0011189411,0.00006695912,0.00092233706],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992435,0.00015423981,0.000039920837,0.00021737923,0.00022609015,0.00011890572],"domain_scores_gemma":[0.9990897,0.00034104235,0.00011713079,0.00013329765,0.00027940745,0.000039419283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00179648,0.0007143108,0.0009508817,0.0016777306,0.00034241096,0.00053679163,0.000863477,0.00057526823,0.0006588626],"category_scores_gemma":[0.0022074129,0.00024791813,0.0015747142,0.0012329574,0.00041829274,0.0013876964,0.00054143515,0.0007402703,0.0003219905],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00060860993,0.00033080616,0.010783044,0.00015811413,0.00024377697,0.00019472421,0.00012337686,0.5320029,0.02814279,0.0057641617,0.0032336363,0.4184141],"study_design_scores_gemma":[0.0000055595356,0.000047924204,0.0021268916,0.00000633654,0.000026927999,0.000060307484,0.0000120684235,0.99073035,0.004673872,0.0019041148,0.000384331,0.000021285514],"about_ca_topic_score_codex":0.0072137793,"about_ca_topic_score_gemma":0.005165604,"teacher_disagreement_score":0.0072137793,"about_ca_system_score_codex":0.0006000284,"about_ca_system_score_gemma":0.00069355784,"threshold_uncertainty_score":0.01434356},"labels":[],"label_agreement":null},{"id":"W3142102071","doi":"10.3390/rs13071253","title":"Hyperspectral Image Classification via Multi-Feature-Based Correlation Adaptive Representation","year":2021,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Science and Technology Department of Henan Province","keywords":"Classifier (UML); Computer science; Pattern recognition (psychology); Artificial intelligence; Hyperspectral imaging; Correlation; Regularization (linguistics); Sparse approximation; Feature selection; Tikhonov regularization; Mathematics","score_opus":0.035489995073546755,"score_gpt":0.2663929774890574,"score_spread":0.23090298241551063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3142102071","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019148663,0.00043140346,0.9784226,0.0002060372,0.00004289017,0.000037851816,0.00005374894,0.00046226018,0.0011945559],"genre_scores_gemma":[0.47858015,0.0011551268,0.51414263,0.00040575652,0.0002049721,0.000194174,0.0007566496,0.00014173205,0.0044187945],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991654,0.00014090649,0.000034665805,0.00019662359,0.00038097272,0.000081379425],"domain_scores_gemma":[0.9993272,0.00018666929,0.0001126927,0.00009581214,0.00024851112,0.000029172517],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008606977,0.00068364665,0.0009181193,0.0011038292,0.00038519196,0.0007793,0.0010319828,0.00088296214,0.001005333],"category_scores_gemma":[0.0019785329,0.00024422584,0.0009210631,0.0017799565,0.00053301343,0.0013504416,0.00091527926,0.0012346602,0.0006095579],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020434058,0.00023735456,0.0024054279,0.0001734413,0.0001491503,0.0001774834,0.00014826097,0.15430585,0.0711893,0.014039444,0.0072130403,0.7497569],"study_design_scores_gemma":[0.0000059837644,0.00004340842,0.0005405716,0.000007064476,0.00001943829,0.00008643488,0.000014043373,0.9898504,0.006378301,0.0015989975,0.0014398871,0.000015483789],"about_ca_topic_score_codex":0.0023421673,"about_ca_topic_score_gemma":0.0022497836,"teacher_disagreement_score":0.0023421673,"about_ca_system_score_codex":0.0004125324,"about_ca_system_score_gemma":0.00083678454,"threshold_uncertainty_score":0.0046570897},"labels":[],"label_agreement":null},{"id":"W3143886733","doi":"","title":"1 - Segmentation bathymétrique d'images multispectrales SPOT","year":2001,"lang":"fr","type":"article","venue":"Traitement du signal","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Bathymetry; Segmentation; Inversion (geology); Computer science; Context (archaeology); Hydrography; Artificial intelligence; Scale (ratio); Pattern recognition (psychology); Image segmentation; Bathymetric chart; Markov process; Data mining; Geography; Geology; Cartography; Mathematics; Statistics; Geomorphology","score_opus":0.021302063740141524,"score_gpt":0.24419679237649386,"score_spread":0.22289472863635235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3143886733","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19417009,0.00018271011,0.80062586,0.00009818474,0.000023018516,0.00006516394,0.00053372217,0.0013799458,0.0029213538],"genre_scores_gemma":[0.70128566,0.0001990823,0.29261833,0.00003389598,0.000017896453,0.000062189974,0.0009133783,0.00023838716,0.004631198],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9997497,0.000027456874,0.000009732789,0.000068021654,0.00011013681,0.000034904053],"domain_scores_gemma":[0.99983704,0.00003777195,0.00002282423,0.000027328178,0.00006654368,0.000008551303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024639114,0.00027443137,0.00025483506,0.0008363724,0.00019197674,0.00061663706,0.00019279541,0.00027857674,0.0019449004],"category_scores_gemma":[0.0004669373,0.00016837397,0.0002548912,0.00042556543,0.00033095983,0.0004177072,0.00028501588,0.00019621107,0.0006621485],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022078458,0.00007044273,0.016971324,0.00019256915,0.000047522775,0.00022170747,0.00034805448,0.11341316,0.34707177,0.011306617,0.0022413025,0.5078947],"study_design_scores_gemma":[0.000016033557,0.00006998496,0.067083,0.000024771927,0.000024252817,0.00050319306,0.0001663409,0.7655022,0.14829382,0.006108638,0.012160341,0.000047541755],"about_ca_topic_score_codex":0.0067919646,"about_ca_topic_score_gemma":0.006764789,"teacher_disagreement_score":0.0067919646,"about_ca_system_score_codex":0.000389905,"about_ca_system_score_gemma":0.0005789249,"threshold_uncertainty_score":0.013504863},"labels":[],"label_agreement":null},{"id":"W3145588843","doi":"10.2478/jee-2021-0006","title":"Multiscale filter-based hyperspectral image classification with PCA and SVM","year":2021,"lang":"en","type":"article","venue":"Journal of Electrical Engineering","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Hyperspectral imaging; Principal component analysis; Artificial intelligence; Pattern recognition (psychology); Support vector machine; Data cube; Computer science; Filter (signal processing); Pixel; Convolution (computer science); Curse of dimensionality; Cube (algebra); Image (mathematics); Computer vision; Mathematics; Data mining; Artificial neural network","score_opus":0.009805388016247989,"score_gpt":0.20151542486935123,"score_spread":0.19171003685310323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3145588843","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040925153,0.00017689176,0.95630217,0.000103825594,0.000046565117,0.000037468402,0.00005843951,0.0016864125,0.00066308957],"genre_scores_gemma":[0.49756902,0.00016841662,0.5001758,0.000058256035,0.0000676766,0.00008485512,0.0002710094,0.00009322979,0.0015117385],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99946016,0.00008562632,0.000033915006,0.00012985214,0.00023784816,0.00005257154],"domain_scores_gemma":[0.99948275,0.00015336547,0.00007201846,0.00006973608,0.00019849275,0.000023649134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006617712,0.0005990806,0.0007079995,0.0011151088,0.00028671327,0.0005714287,0.0006009781,0.00056899415,0.0013054985],"category_scores_gemma":[0.0013346768,0.00022348965,0.00076367974,0.0010386246,0.00031507172,0.0008491575,0.0005123248,0.0006410555,0.0005229406],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019553262,0.00017970549,0.0033253497,0.000107044376,0.00013815776,0.000080672435,0.00007176907,0.14445014,0.0543811,0.003169186,0.0038176842,0.79008365],"study_design_scores_gemma":[0.00000230432,0.0000146838975,0.0007728088,0.000002154047,0.000006513586,0.00001771571,0.00000608873,0.9944351,0.0039640917,0.00044420428,0.00032977186,0.000004590697],"about_ca_topic_score_codex":0.0028180666,"about_ca_topic_score_gemma":0.0020088465,"teacher_disagreement_score":0.0028180666,"about_ca_system_score_codex":0.00040784886,"about_ca_system_score_gemma":0.00045552163,"threshold_uncertainty_score":0.0056033134},"labels":[],"label_agreement":null},{"id":"W3147179755","doi":"10.3390/rs13071349","title":"Performance Evaluation of Sentinel-2 and Landsat 8 OLI Data for Land Cover/Use Classification Using a Comparison between Machine Learning Algorithms","year":2021,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":149,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ministry of Forests","funders":"","keywords":"Land cover; Support vector machine; Computer science; Confusion matrix; Algorithm; Mahalanobis distance; Remote sensing; Artificial intelligence; Artificial neural network; Data mining; Machine learning; Land use; Geology","score_opus":0.17921855723786909,"score_gpt":0.34153129312559205,"score_spread":0.16231273588772296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3147179755","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9526102,0.0019648287,0.03729217,0.00038417193,0.0003519535,0.00013028833,0.0019661745,0.0017968793,0.003503369],"genre_scores_gemma":[0.94661885,0.00040463178,0.04718928,0.00011156394,0.00006997357,0.00009396784,0.004590408,0.000093444345,0.0008278462],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99722606,0.00064925605,0.0003284335,0.00057196437,0.0009972968,0.00022700208],"domain_scores_gemma":[0.9940055,0.0027887714,0.0004999586,0.00036721476,0.0020967321,0.0002418071],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0061712726,0.0010252642,0.0010443198,0.0029300232,0.00046934612,0.0014278956,0.0009534849,0.0011471611,0.0006179576],"category_scores_gemma":[0.009474648,0.00021136881,0.0008703235,0.0015448807,0.00038670213,0.0016372442,0.0006693294,0.00069360976,0.00058665266],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031936648,0.0015937022,0.22225016,0.00092584564,0.0010907364,0.00024742298,0.00051115354,0.2735166,0.018198136,0.0021749616,0.00995329,0.46634436],"study_design_scores_gemma":[0.000043912947,0.0004472961,0.042946234,0.00005086855,0.00007084336,0.0000899948,0.00025529295,0.9442518,0.010160863,0.00046334963,0.0011714202,0.000048044672],"about_ca_topic_score_codex":0.0074815196,"about_ca_topic_score_gemma":0.0048204875,"teacher_disagreement_score":0.0074815196,"about_ca_system_score_codex":0.00087227486,"about_ca_system_score_gemma":0.00069136027,"threshold_uncertainty_score":0.03263718},"labels":[],"label_agreement":null},{"id":"W3148982675","doi":"","title":"A maximum noise fraction transform with improved noise estimation for hyperspectral images","year":2009,"lang":"zh","type":"article","venue":"中国科学(F辑:信息科学)(英文版)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Hyperspectral imaging; Pattern recognition (psychology); Artificial intelligence; Noise (video); Feature extraction; Mathematics; Feature (linguistics); Dimension (graph theory); Computer science; Computer vision; Image (mathematics)","score_opus":0.01047621223596638,"score_gpt":0.2374630567744401,"score_spread":0.22698684453847373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3148982675","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0105346665,0.00018185214,0.98851424,0.000079809135,0.000033687196,0.000012800639,0.00003006147,0.0002451987,0.00036762602],"genre_scores_gemma":[0.16454051,0.00034703946,0.8331809,0.00007262968,0.000111684516,0.0000697797,0.00031602176,0.00008604981,0.0012753732],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99930584,0.00013132318,0.000040585845,0.00013723284,0.00035222722,0.00003274724],"domain_scores_gemma":[0.99937004,0.00025790697,0.00008651284,0.000080274054,0.00018824662,0.000017051836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011857231,0.0007628883,0.00068236305,0.0010596965,0.00030850185,0.00054223405,0.0006149456,0.00083270686,0.00080619275],"category_scores_gemma":[0.0037115847,0.0002642013,0.00063522364,0.0014356552,0.00066198694,0.0015339237,0.00042872,0.0007276585,0.00045498507],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041944033,0.00018443145,0.002022442,0.00027403448,0.00010130636,0.0003279019,0.00019926815,0.19608986,0.17725977,0.021781482,0.0032423849,0.5980977],"study_design_scores_gemma":[0.000012496241,0.00004111149,0.0009216444,0.000007717882,0.000014825011,0.00020646887,0.000009202708,0.96311074,0.030445654,0.0023079135,0.0028925808,0.000029547968],"about_ca_topic_score_codex":0.0015874027,"about_ca_topic_score_gemma":0.0015281346,"teacher_disagreement_score":0.0015874027,"about_ca_system_score_codex":0.00044136884,"about_ca_system_score_gemma":0.00051243056,"threshold_uncertainty_score":0.006270826},"labels":[],"label_agreement":null},{"id":"W3150881149","doi":"10.18280/ts.380103","title":"Classification of Remote Sensing Images Through Reweighted Sparse Subspace Representation Using Compressed Data","year":2021,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Linear subspace; Cluster analysis; Compressed sensing; Hyperspectral imaging; Computer science; Spectral clustering; Artificial intelligence; Subspace topology; Sparse approximation; Pattern recognition (psychology); K-SVD; Data cube; Algorithm; Mathematics; Data mining","score_opus":0.12561483138635562,"score_gpt":0.3149136607050378,"score_spread":0.18929882931868217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3150881149","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03253225,0.00014850052,0.96622866,0.000155023,0.00002449914,0.000038878283,0.000069661684,0.00027549,0.000526998],"genre_scores_gemma":[0.46306023,0.00033360752,0.53398544,0.00012807614,0.000077703,0.0001197009,0.0006727639,0.000070396585,0.0015520703],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995148,0.00011358044,0.000024317083,0.0001203865,0.00018107193,0.000045846995],"domain_scores_gemma":[0.9993424,0.00021479132,0.000095219126,0.000119930664,0.00020278264,0.000024969382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006502461,0.0006854466,0.0006026582,0.0011961181,0.0003313026,0.00066905544,0.00076405203,0.00062068255,0.00046356747],"category_scores_gemma":[0.002126624,0.00021598156,0.000507297,0.0012440569,0.0006191995,0.0012270316,0.00063875143,0.00090049685,0.00026776834],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002859162,0.00017764432,0.0021553047,0.0001457672,0.000094432384,0.00014772998,0.00032926316,0.5032784,0.052212674,0.015190766,0.00304778,0.42293426],"study_design_scores_gemma":[0.0000034452987,0.000025752972,0.00031038027,0.000004203059,0.0000051303673,0.000027412641,0.000033352033,0.991532,0.0043591177,0.0031880115,0.00050235953,0.000008847107],"about_ca_topic_score_codex":0.0030680718,"about_ca_topic_score_gemma":0.0032171141,"teacher_disagreement_score":0.0030680718,"about_ca_system_score_codex":0.0004602287,"about_ca_system_score_gemma":0.00055486953,"threshold_uncertainty_score":0.006100416},"labels":[],"label_agreement":null},{"id":"W3156804984","doi":"10.1111/mice.12698","title":"Similarity learning to enable building searches in post‐event image data","year":2021,"lang":"en","type":"article","venue":"Computer-Aided Civil and Infrastructure Engineering","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Research Foundation of Korea","keywords":"Metadata; Similarity (geometry); Rank (graph theory); Convolutional neural network; Computer science; Event (particle physics); Image (mathematics); Information retrieval; Global Positioning System; Data mining; Artificial intelligence; World Wide Web; Mathematics","score_opus":0.011599002426912298,"score_gpt":0.22724785405918807,"score_spread":0.21564885163227576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3156804984","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09971588,0.00035218484,0.8872883,0.00019828674,0.00012847596,0.000175257,0.0012570459,0.007481255,0.0034032909],"genre_scores_gemma":[0.6001863,0.0001906933,0.39117682,0.00013452927,0.00010352866,0.00012217798,0.004530171,0.0003035746,0.0032523037],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999374,0.000076186865,0.000043269276,0.00018435808,0.00023658166,0.000085656575],"domain_scores_gemma":[0.9990195,0.0002472146,0.00010421915,0.00025695516,0.00031544958,0.000056662753],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007550195,0.00045545524,0.0007187,0.0023168097,0.00044644004,0.001036772,0.0013255595,0.0010874801,0.0035373885],"category_scores_gemma":[0.0029863664,0.0002631761,0.0007894657,0.0022253809,0.0003661207,0.0019231819,0.0014797985,0.00080997887,0.0024493309],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044411415,0.0008202099,0.00946711,0.00018922216,0.00016273295,0.00017679327,0.00019595561,0.060219903,0.05702017,0.0070613185,0.014774315,0.8494681],"study_design_scores_gemma":[0.000019051946,0.000099556375,0.003360823,0.000010037162,0.000026630436,0.00012904813,0.000095429124,0.968304,0.01865824,0.0052454476,0.004035188,0.000016480191],"about_ca_topic_score_codex":0.0043971413,"about_ca_topic_score_gemma":0.0072902613,"teacher_disagreement_score":0.0043971413,"about_ca_system_score_codex":0.00047355585,"about_ca_system_score_gemma":0.0007490741,"threshold_uncertainty_score":0.011833727},"labels":[],"label_agreement":null},{"id":"W3159134235","doi":"10.1109/icpr48806.2021.9412168","title":"A Distinct Discriminant Canonical Correlation Analysis Network based Deep Information Quality Representation for Image Classification","year":2021,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Pattern recognition (psychology); Artificial intelligence; Linear discriminant analysis; Canonical correlation; Discriminant; Computer science; Feature (linguistics); Face (sociological concept); Representation (politics); Contextual image classification; Feature extraction; Correlation; Class (philosophy); Facial recognition system; Image (mathematics); Data mining; Mathematics","score_opus":0.039846466086463674,"score_gpt":0.3087110716101136,"score_spread":0.2688646055236499,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3159134235","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026267026,0.0007003039,0.9691491,0.00040209046,0.00008129188,0.0000691154,0.00025625396,0.0006951218,0.0023797026],"genre_scores_gemma":[0.6846325,0.0010025391,0.30358127,0.0005845183,0.0001749354,0.00033168646,0.0018507414,0.00018394964,0.007657927],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995258,0.000121203084,0.000019870215,0.00013269526,0.00013617966,0.000064222084],"domain_scores_gemma":[0.9993954,0.00014966672,0.00006439068,0.000090416215,0.00025094976,0.000049304177],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008733036,0.0011368061,0.00090795447,0.0011391677,0.00041479093,0.0009623469,0.0013810035,0.0009027649,0.0019859418],"category_scores_gemma":[0.0021627212,0.00030511786,0.0007107445,0.0013468529,0.00069770153,0.0016548391,0.0013274647,0.0014168877,0.000590876],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031116564,0.00025192904,0.004404077,0.00020057608,0.00019373224,0.00015748368,0.0001427046,0.34653392,0.01596601,0.04951674,0.015173686,0.5671479],"study_design_scores_gemma":[0.000004361771,0.00003267581,0.00026974903,0.0000067008273,0.0000161357,0.00002587232,0.0000085425645,0.99189913,0.0013086045,0.005663662,0.00075635884,0.000008192818],"about_ca_topic_score_codex":0.007073213,"about_ca_topic_score_gemma":0.0076813973,"teacher_disagreement_score":0.007073213,"about_ca_system_score_codex":0.0012243196,"about_ca_system_score_gemma":0.0012916101,"threshold_uncertainty_score":0.014064133},"labels":[],"label_agreement":null},{"id":"W3161152678","doi":"10.18280/ts.380224","title":"Object Recognition in Remote Sensing Images Based on Modified Backpropagation Neural Network","year":2021,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Robustness (evolution); Backpropagation; Artificial intelligence; Artificial neural network; Benchmark (surveying); Deep learning; Convolutional neural network; Pattern recognition (psychology); Remote sensing","score_opus":0.028195574252967464,"score_gpt":0.22771646312519456,"score_spread":0.1995208888722271,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3161152678","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0736096,0.0012911471,0.9161646,0.00034437404,0.0002292956,0.00015848661,0.00022143403,0.0051798234,0.002801341],"genre_scores_gemma":[0.5979885,0.0011608099,0.391046,0.00033839277,0.000130301,0.00020861675,0.00081912614,0.0001529646,0.008155231],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999423,0.000055911485,0.00004615433,0.00019330317,0.00022897599,0.000052682055],"domain_scores_gemma":[0.99954283,0.00012734103,0.000061261795,0.00006069052,0.00019365203,0.000014329255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007883534,0.0009242416,0.0007208734,0.0010863241,0.00031419133,0.00074196816,0.0010455701,0.00095962477,0.0011479941],"category_scores_gemma":[0.0015139485,0.00034120673,0.00071211846,0.00090034376,0.00039549352,0.0012828063,0.0004919478,0.0009531766,0.0006468845],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002568036,0.00020896712,0.0026862095,0.00015254295,0.00015854351,0.00019779854,0.00009085262,0.17069076,0.034781434,0.0014467242,0.0034152674,0.785914],"study_design_scores_gemma":[0.000008761364,0.00004475497,0.0013600521,0.000008346165,0.00001984971,0.00006890578,0.000009647911,0.98624146,0.010666985,0.00080477627,0.00075419864,0.000012251511],"about_ca_topic_score_codex":0.009240881,"about_ca_topic_score_gemma":0.006187554,"teacher_disagreement_score":0.009240881,"about_ca_system_score_codex":0.0006978964,"about_ca_system_score_gemma":0.00053747435,"threshold_uncertainty_score":0.018374145},"labels":[],"label_agreement":null},{"id":"W3162787987","doi":"10.1109/icassp39728.2021.9414358","title":"Augmented Gaussian Linear Mixture Model for Spectral Variability in Hyperspectral Unmixing","year":2021,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Mitacs","keywords":"Hyperspectral imaging; Endmember; Mixture model; Gaussian; Multiplicative function; Computer science; Algorithm; Pattern recognition (psychology); Convergence (economics); Gaussian process; Mathematics; Artificial intelligence; Mathematical optimization","score_opus":0.019901459416810693,"score_gpt":0.24850896112427456,"score_spread":0.22860750170746386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3162787987","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030684597,0.00025406276,0.99592483,0.00006118826,0.000028192522,0.000010803605,0.00004226141,0.0003279205,0.0002823026],"genre_scores_gemma":[0.34292895,0.0012832123,0.647789,0.0002838298,0.00018766572,0.00022081404,0.0009100961,0.00045879075,0.00593766],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990226,0.00032520466,0.0000389384,0.00026099494,0.0002834568,0.00006883673],"domain_scores_gemma":[0.9994307,0.00025726523,0.000069822345,0.0000930563,0.0001314471,0.00001765823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013228176,0.0011107869,0.0009154615,0.00079228013,0.00037606835,0.0009879392,0.0017309159,0.0012703768,0.001248714],"category_scores_gemma":[0.0026030962,0.0005698639,0.0013226866,0.0012634824,0.0008002776,0.0022668692,0.0012346944,0.0021951539,0.0011571451],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002024565,0.00009539493,0.0011613395,0.0002067706,0.00018101123,0.00015245813,0.00022392225,0.71800256,0.020920554,0.028561391,0.002830717,0.22746131],"study_design_scores_gemma":[0.0000029228877,0.000010220041,0.00013491156,0.000004964859,0.000008493901,0.00002221281,0.000006276032,0.9926804,0.0015983299,0.004323526,0.0011966001,0.000011154633],"about_ca_topic_score_codex":0.003917878,"about_ca_topic_score_gemma":0.0042064283,"teacher_disagreement_score":0.003917878,"about_ca_system_score_codex":0.00058930204,"about_ca_system_score_gemma":0.00070500735,"threshold_uncertainty_score":0.0077901483},"labels":[],"label_agreement":null},{"id":"W3164802645","doi":"10.3390/rs13091732","title":"Distance Transform-Based Spectral-Spatial Feature Vector for Hyperspectral Image Classification with Stacked Autoencoder","year":2021,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hyperspectral imaging; Pixel; Artificial intelligence; Pattern recognition (psychology); Computer science; Feature (linguistics); Feature vector; Autoencoder; Spatial analysis; Support vector machine; Remote sensing; Deep learning; Geography","score_opus":0.013538754933879184,"score_gpt":0.23160788509270427,"score_spread":0.2180691301588251,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3164802645","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039431892,0.000622994,0.95534694,0.0001928288,0.00009135564,0.00006239207,0.0003908345,0.0027700178,0.0010907017],"genre_scores_gemma":[0.5305448,0.0006327975,0.45819324,0.0002684958,0.00009024447,0.00023251318,0.0034936136,0.00018934021,0.006354969],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996183,0.00005834347,0.000028176706,0.00011162697,0.00013399681,0.00004969855],"domain_scores_gemma":[0.9996306,0.000093210634,0.000041135696,0.00004882442,0.00016749633,0.00001875105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000602483,0.000950696,0.00082756806,0.00076934905,0.00024311275,0.0004899559,0.000986113,0.00074319704,0.0015582066],"category_scores_gemma":[0.0010453206,0.00029350488,0.00080528593,0.0010732015,0.0003154757,0.0010322202,0.0006768794,0.00148634,0.0007583101],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001852867,0.00026546622,0.0013810816,0.00011268835,0.0001746229,0.000059892413,0.00005904163,0.28101394,0.020668998,0.0029606342,0.0062610433,0.68685734],"study_design_scores_gemma":[0.0000038980456,0.000023676153,0.00033811378,0.0000051719217,0.000010133106,0.00001409851,0.000007830541,0.99438334,0.0038682437,0.000848124,0.00049071683,0.0000067180454],"about_ca_topic_score_codex":0.009307466,"about_ca_topic_score_gemma":0.008909375,"teacher_disagreement_score":0.009307466,"about_ca_system_score_codex":0.0007355465,"about_ca_system_score_gemma":0.0008586625,"threshold_uncertainty_score":0.018506587},"labels":[],"label_agreement":null},{"id":"W3165739532","doi":"10.3390/s21113738","title":"Calibration of a Hyper-Spectral Imaging System Using a Low-Cost Reference","year":2021,"lang":"en","type":"article","venue":"Sensors","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Hyperspectral imaging; Calibration; Remote sensing; Full spectral imaging; Spectral imaging; Asphalt; Environmental science; Spectral power distribution; Radiant intensity; Principal component analysis; Optics; Spectral sensitivity; Materials science; Geology; Computer science; Artificial intelligence; Mathematics; Physics; Wavelength","score_opus":0.0252940560242713,"score_gpt":0.23380164776359652,"score_spread":0.20850759173932523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3165739532","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09884186,0.00063711,0.89287996,0.00025550582,0.00019712349,0.00030045665,0.0001608372,0.00321675,0.003510422],"genre_scores_gemma":[0.3452871,0.00049243146,0.64625555,0.00044201128,0.00009015675,0.0003378475,0.0005067851,0.0003160767,0.006271924],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983822,0.00024183195,0.000059735397,0.00045167728,0.00079581677,0.00006869839],"domain_scores_gemma":[0.9987664,0.00026356932,0.00012273488,0.0003236206,0.00047472937,0.000048984213],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016278481,0.0006449334,0.0005851954,0.0010864452,0.0005054084,0.00084006443,0.0017320393,0.001476312,0.002945727],"category_scores_gemma":[0.0021825545,0.00035593638,0.00032592984,0.00074481254,0.0005927001,0.0013801516,0.0008632734,0.00078285555,0.0027200216],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023752074,0.00015567336,0.0033073907,0.00026660744,0.000036447258,0.00015321895,0.00014007911,0.0030033598,0.83570284,0.0017843207,0.0014654093,0.15374711],"study_design_scores_gemma":[0.00004545373,0.0007908963,0.009725047,0.00005786958,0.0000940258,0.001328672,0.00010450455,0.053302824,0.91405827,0.00059700554,0.019793767,0.00010159935],"about_ca_topic_score_codex":0.0006308724,"about_ca_topic_score_gemma":0.0009444319,"teacher_disagreement_score":0.002945727,"about_ca_system_score_codex":0.00051039655,"about_ca_system_score_gemma":0.0006312684,"threshold_uncertainty_score":0.009854436},"labels":[],"label_agreement":null},{"id":"W3166557876","doi":"10.3390/rs13112125","title":"Unsupervised Identification of Targeted Spectra Applying Rank1-NMF and FCC Algorithms in Long-Wave Hyperspectral Infrared Imagery","year":2021,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds de recherche du Québec – Nature et technologies; Université Laval","keywords":"Hyperspectral imaging; Cluster analysis; Non-negative matrix factorization; Pattern recognition (psychology); Artificial intelligence; Computer science; Principal component analysis; Spectral clustering; Projection (relational algebra); Algorithm; Mathematics; Matrix decomposition; Physics; Eigenvalues and eigenvectors","score_opus":0.016074496440781023,"score_gpt":0.22508628516758383,"score_spread":0.20901178872680282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3166557876","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1416835,0.0005445495,0.8504259,0.00020019905,0.00009628704,0.00017084996,0.0006087882,0.0032271612,0.003042783],"genre_scores_gemma":[0.3036774,0.00022078135,0.69144964,0.000072285344,0.000043076532,0.00015812936,0.0017245518,0.00034311446,0.0023110155],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990515,0.00017834066,0.000049476483,0.00029642778,0.0003069981,0.00011728313],"domain_scores_gemma":[0.99883896,0.00027499849,0.00016287605,0.00016502102,0.00051590794,0.00004218095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001415591,0.0011218848,0.00062270096,0.002807661,0.00086996524,0.0009831444,0.00088663574,0.00094429957,0.0012332434],"category_scores_gemma":[0.002923943,0.0002212174,0.0011416211,0.001698774,0.00059240946,0.0010160775,0.0005052504,0.00072791445,0.0010394205],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004282268,0.00030390132,0.009439498,0.0004520605,0.00018819414,0.00018983304,0.0005329709,0.122215636,0.08297345,0.005343978,0.007241108,0.77069116],"study_design_scores_gemma":[0.000027760594,0.000095013645,0.012114997,0.000035350145,0.00004985369,0.00022471044,0.00033779503,0.9144785,0.06262787,0.0039300043,0.005989839,0.000088423374],"about_ca_topic_score_codex":0.008495809,"about_ca_topic_score_gemma":0.011578591,"teacher_disagreement_score":0.008495809,"about_ca_system_score_codex":0.00064291555,"about_ca_system_score_gemma":0.0011447383,"threshold_uncertainty_score":0.016892731},"labels":[],"label_agreement":null},{"id":"W3173126040","doi":"10.1016/j.jenvman.2021.112891","title":"An integrated geospatial correlation analysis and human health risk assessment approach for investigating abandoned industrial sites","year":2021,"lang":"en","type":"article","venue":"Journal of Environmental Management","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":28,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Northern British Columbia; Okanagan University College; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Geospatial analysis; Human health; Risk assessment; Environmental science; Environmental resource management; Environmental planning; Geography; Environmental health; Computer science; Remote sensing; Medicine","score_opus":0.0230798689943659,"score_gpt":0.2597990011368106,"score_spread":0.2367191321424447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173126040","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29453215,0.0003899532,0.6996987,0.00019125092,0.000023752073,0.00018152987,0.00080802146,0.00048696247,0.003687757],"genre_scores_gemma":[0.8819651,0.00022930707,0.115704164,0.00003144593,0.000027800681,0.000099300996,0.0005646799,0.0000283027,0.0013499869],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996,0.00010307169,0.00002634661,0.00007086352,0.0001508181,0.000048934333],"domain_scores_gemma":[0.999537,0.00017530544,0.000080631,0.00004028815,0.00014042997,0.000026291062],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007545944,0.0005825293,0.00058847864,0.004555975,0.0003776075,0.0011907541,0.0006815123,0.0005089025,0.0012721053],"category_scores_gemma":[0.0012106069,0.00024634134,0.0009663804,0.003146522,0.00028320833,0.00063859683,0.00081969344,0.00034700375,0.00021340112],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003353545,0.0010638158,0.1797416,0.0002524,0.0010640929,0.00091645465,0.00031101384,0.37016794,0.02149475,0.012006277,0.0026691891,0.4099771],"study_design_scores_gemma":[0.0000106596335,0.00007293561,0.034757283,0.000010631785,0.00017333352,0.0001624688,0.00022084694,0.95903796,0.0016692928,0.0031122605,0.00074935943,0.000022963803],"about_ca_topic_score_codex":0.012411529,"about_ca_topic_score_gemma":0.021277066,"teacher_disagreement_score":0.012411529,"about_ca_system_score_codex":0.0005152026,"about_ca_system_score_gemma":0.0012847431,"threshold_uncertainty_score":0.024678588},"labels":[],"label_agreement":null},{"id":"W3173994423","doi":"10.1109/tgrs.2021.3080580","title":"BDANet: Multiscale Convolutional Neural Network With Cross-Directional Attention for Building Damage Assessment From Satellite Images","year":2021,"lang":"en","type":"preprint","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ministry of Natural Resources and Forestry","funders":"Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou); National Natural Science Foundation of China","keywords":"Convolutional neural network; Computer science; Deep learning; Satellite; Artificial intelligence; Stage (stratigraphy); Artificial neural network; Satellite imagery; Scale (ratio); Feature (linguistics); Representation (politics); Remote sensing; Data mining; Machine learning; Cartography; Geography; Engineering; Geology","score_opus":0.017994249951820737,"score_gpt":0.274101724573745,"score_spread":0.25610747462192424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173994423","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21466479,0.0032909652,0.7519307,0.00089010375,0.00042250918,0.0002659586,0.003708449,0.018775936,0.006050616],"genre_scores_gemma":[0.6586879,0.00087439176,0.3152743,0.00055561075,0.00014976508,0.00024058759,0.012089436,0.00032034397,0.011807646],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997849,0.000023860883,0.000010469977,0.000080749036,0.000056440393,0.000043521766],"domain_scores_gemma":[0.99982065,0.00004921577,0.000026163287,0.00003710462,0.000047116966,0.000019752777],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046822897,0.0011480806,0.0006388659,0.0007098169,0.00025880244,0.0004445727,0.0015516055,0.00087105436,0.0019107122],"category_scores_gemma":[0.00083192135,0.00037478327,0.00073534646,0.0007983959,0.00027529776,0.0009838837,0.0009885441,0.0011794206,0.00064178143],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046407094,0.0003909759,0.0032724526,0.0001582573,0.00031134745,0.00025717748,0.000056700796,0.28362855,0.029369675,0.0025065688,0.026745232,0.65283895],"study_design_scores_gemma":[0.0000113831375,0.000033515822,0.0006755886,0.000004927181,0.000016870597,0.00002639689,0.00000397653,0.9946221,0.0029006605,0.0007605643,0.00093678274,0.0000071307127],"about_ca_topic_score_codex":0.018609984,"about_ca_topic_score_gemma":0.02574938,"teacher_disagreement_score":0.018609984,"about_ca_system_score_codex":0.00092842994,"about_ca_system_score_gemma":0.0007608051,"threshold_uncertainty_score":0.03700328},"labels":[],"label_agreement":null},{"id":"W3174299795","doi":"10.3390/rs13132501","title":"An Efficient Multi-Sensor Remote Sensing Image Clustering in Urban Areas via Boosted Convolutional Autoencoder (BCAE)","year":2021,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; York University; Institut National de la Recherche Scientifique","funders":"University of Houston","keywords":"Autoencoder; Computer science; Artificial intelligence; Pattern recognition (psychology); Cluster analysis; Feature (linguistics); Deep learning","score_opus":0.019821858566046614,"score_gpt":0.2534926158621273,"score_spread":0.23367075729608067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174299795","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04883326,0.00021752328,0.9486058,0.000107360574,0.000037729973,0.000041412826,0.000094255105,0.0011342592,0.0009283414],"genre_scores_gemma":[0.53456825,0.00029100993,0.460342,0.000162816,0.000035359564,0.00007073851,0.00069157185,0.00014511058,0.003693142],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99965775,0.000040839193,0.000015970361,0.0001448219,0.000087510896,0.000053152104],"domain_scores_gemma":[0.9997466,0.00005372324,0.000028096008,0.000046077297,0.000108032196,0.000017450835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005201299,0.0007613915,0.00063221133,0.0006960857,0.00032317018,0.00046535366,0.00092409755,0.00064727117,0.0006068222],"category_scores_gemma":[0.0007913686,0.00044752742,0.0008864149,0.0007243007,0.00034506695,0.0008832041,0.0006776155,0.0007773156,0.00035249672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002116025,0.00011325931,0.002691869,0.000114777904,0.0001717386,0.00014106618,0.00015660236,0.5115642,0.052757498,0.0023480277,0.00235339,0.427376],"study_design_scores_gemma":[0.0000029360363,0.00001453433,0.0007020482,0.0000031084392,0.000009695923,0.00002230799,0.000009755971,0.9923079,0.006040761,0.0005268752,0.00035240536,0.00000763498],"about_ca_topic_score_codex":0.009884979,"about_ca_topic_score_gemma":0.01124339,"teacher_disagreement_score":0.009884979,"about_ca_system_score_codex":0.0005752825,"about_ca_system_score_gemma":0.00067168736,"threshold_uncertainty_score":0.01965487},"labels":[],"label_agreement":null},{"id":"W3174867596","doi":"10.3390/rs13132524","title":"Self-Attention in Reconstruction Bias U-Net for Semantic Segmentation of Building Rooftops in Optical Remote Sensing Images","year":2021,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":74,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Science Foundation of Fujian Province; National Natural Science Foundation of China","keywords":"Computer science; Decoding methods; Segmentation; Encoding (memory); Deep learning; Artificial intelligence; Salient; Pattern recognition (psychology); Telecommunications","score_opus":0.022524173731872692,"score_gpt":0.26072731185549713,"score_spread":0.23820313812362445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174867596","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20250863,0.002141393,0.7707869,0.0009308202,0.00028871428,0.00026666615,0.0007495839,0.013741073,0.008586251],"genre_scores_gemma":[0.7291459,0.00071499404,0.253451,0.0010700498,0.00016011365,0.00019826004,0.002862765,0.00042539797,0.011971597],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996915,0.00003613701,0.000016350263,0.00011929326,0.0000646049,0.00007218726],"domain_scores_gemma":[0.9997602,0.0000637172,0.000030420206,0.000049053855,0.000071772105,0.000024866778],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006474032,0.0012552615,0.000937759,0.0010900077,0.00051473506,0.0009522443,0.0017303661,0.0014763206,0.0026590822],"category_scores_gemma":[0.0010008814,0.00048106906,0.0010172674,0.00094638474,0.0007098331,0.0019167144,0.0012686398,0.0012724426,0.0011347797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00064660935,0.00043754865,0.0049532433,0.00019069783,0.00019005312,0.00021833964,0.00019630327,0.17638624,0.023968624,0.0058367033,0.0114567205,0.7755189],"study_design_scores_gemma":[0.000021161615,0.00007579791,0.0009677935,0.000017088223,0.000048570797,0.00005490586,0.000033273835,0.9810253,0.0126364855,0.0031958937,0.0019083828,0.000015384836],"about_ca_topic_score_codex":0.009054195,"about_ca_topic_score_gemma":0.014221168,"teacher_disagreement_score":0.009054195,"about_ca_system_score_codex":0.0009972098,"about_ca_system_score_gemma":0.0010506335,"threshold_uncertainty_score":0.018002987},"labels":[],"label_agreement":null},{"id":"W3174951629","doi":"10.5194/isprs-archives-xliii-b3-2021-829-2021","title":"EVALUATION OF SEMI-SUPERVISED LEARNING FOR CNN-BASED CHANGE DETECTION","year":2021,"lang":"en","type":"article","venue":"˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; York University","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Change detection; Consistency (knowledge bases); Segmentation; Machine learning; Supervised learning; Pattern recognition (psychology); Image (mathematics); Deep learning; Artificial neural network","score_opus":0.04011460378438498,"score_gpt":0.2738229588430396,"score_spread":0.23370835505865462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174951629","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65117425,0.0026313125,0.32363546,0.0005478055,0.0005008066,0.000748362,0.0015209927,0.013255965,0.005985],"genre_scores_gemma":[0.9306671,0.00019283334,0.0630753,0.00017496262,0.000053787822,0.00018024095,0.0035939517,0.00024009254,0.0018217047],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975068,0.0010286137,0.00015959458,0.0006197084,0.000514799,0.00017049945],"domain_scores_gemma":[0.9918188,0.003717038,0.00071374106,0.0010864659,0.0023407845,0.00032315074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056274547,0.0016503455,0.0010746154,0.0009862793,0.00050745584,0.00084383594,0.0023079035,0.0015492655,0.0017116757],"category_scores_gemma":[0.012129633,0.00046602727,0.0008360541,0.00061590056,0.00082660373,0.0015918002,0.0011343093,0.0013369343,0.0008050381],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002396712,0.0013389131,0.018047089,0.0007976832,0.0008579465,0.00020441411,0.00016565046,0.61740947,0.013616884,0.0012157836,0.008105785,0.33584368],"study_design_scores_gemma":[0.000020357294,0.0001532615,0.001099012,0.000012584249,0.000019491796,0.000036235677,0.000014173865,0.9937534,0.004357019,0.00027817787,0.00024957283,0.0000067616465],"about_ca_topic_score_codex":0.007417545,"about_ca_topic_score_gemma":0.010125598,"teacher_disagreement_score":0.007417545,"about_ca_system_score_codex":0.0013717297,"about_ca_system_score_gemma":0.0013148711,"threshold_uncertainty_score":0.029761195},"labels":[],"label_agreement":null},{"id":"W3175455394","doi":"10.1109/icetci51973.2021.9574057","title":"AVHYAS: A Free and Open Source QGIS Plugin for Advanced Hyperspectral Image Analysis","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Indian Space Research Organisation; Speech-Language and Audiology Canada","keywords":"Plug-in; Hyperspectral imaging; Computer science; Software; Open source; Process (computing); Image processing; Remote sensing; Open source software; Data processing; Image (mathematics); Artificial intelligence; Database; Operating system; Geology","score_opus":0.01947983031668418,"score_gpt":0.2690659450299604,"score_spread":0.2495861147132762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3175455394","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034460174,0.00014960495,0.321978,0.00020967041,0.00015128012,0.000198173,0.016553132,0.64886945,0.008444543],"genre_scores_gemma":[0.080852605,0.0006374738,0.51609415,0.0010959372,0.00017725842,0.0018158222,0.10312328,0.25787508,0.03832839],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994912,0.00004639566,0.00003263897,0.00013329947,0.00023398489,0.00006237797],"domain_scores_gemma":[0.9994062,0.00017780236,0.00004427687,0.0001403077,0.00017768353,0.00005372933],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00077907793,0.0013537556,0.000620729,0.0015335403,0.00043929464,0.0016122612,0.0017911419,0.0006538754,0.044225227],"category_scores_gemma":[0.0025109448,0.00088806846,0.0010967797,0.0011638397,0.00045468443,0.0016697388,0.0020796123,0.0014594718,0.038906418],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042098164,0.00015856203,0.004862766,0.0007521461,0.00021268187,0.0002608318,0.00043140614,0.007999146,0.017255325,0.007158913,0.68889326,0.2715939],"study_design_scores_gemma":[0.00019597715,0.0000800571,0.010799569,0.00018402468,0.000062008934,0.000559036,0.0001793595,0.13706754,0.049612813,0.022057699,0.77896523,0.0002366455],"about_ca_topic_score_codex":0.004576783,"about_ca_topic_score_gemma":0.0044154865,"teacher_disagreement_score":0.9982089,"about_ca_system_score_codex":0.0004098557,"about_ca_system_score_gemma":0.00096334534,"threshold_uncertainty_score":0.14794809},"labels":[],"label_agreement":null},{"id":"W3180321043","doi":"10.1080/07038992.2021.1931786","title":"CJRS’ Special Issue on Deep Learning for Environmental Applications of Remote Sensing Data","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal; Institut National de la Recherche Scientifique; Centre For Cold Ocean Resources Engineering; Memorial University of Newfoundland","funders":"","keywords":"Geography; Remote sensing; Data science; Deep learning; Cartography; Computer science; Artificial intelligence","score_opus":0.02173943176397656,"score_gpt":0.23392469919597897,"score_spread":0.21218526743200242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3180321043","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022785477,0.06661517,0.07377609,0.053423725,0.7326952,0.00043770732,0.0041210563,0.004237652,0.06241489],"genre_scores_gemma":[0.014172097,0.05947371,0.032289505,0.017375784,0.47151726,0.00038335702,0.012594856,0.005371816,0.38682154],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972983,0.00034817721,0.00018622495,0.000570103,0.0013155405,0.00028177004],"domain_scores_gemma":[0.99136364,0.003005321,0.00033367894,0.00073592557,0.0030251404,0.0015362484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047252914,0.0020444947,0.002300908,0.0029561485,0.0012203918,0.0050920313,0.0038167667,0.0035324942,0.08839553],"category_scores_gemma":[0.008874601,0.0007337543,0.0015951373,0.002707039,0.0011525984,0.0060446765,0.0034797236,0.005784435,0.035826582],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057570804,0.00004821123,0.0001346607,0.00031026258,0.000044179935,0.00006351616,0.00001333375,0.00079182844,0.00065228523,0.0026771608,0.9339355,0.061271355],"study_design_scores_gemma":[0.00003305006,0.00011696252,0.0005574622,0.00025728773,0.00003465374,0.00024446877,0.000021047763,0.008027271,0.0013130199,0.008544562,0.98081034,0.000039790317],"about_ca_topic_score_codex":0.002103369,"about_ca_topic_score_gemma":0.0045006266,"teacher_disagreement_score":0.08839553,"about_ca_system_score_codex":0.0014003316,"about_ca_system_score_gemma":0.0027603684,"threshold_uncertainty_score":0.29571253},"labels":[],"label_agreement":null},{"id":"W3181950296","doi":"10.3390/rs13142658","title":"Leveraging Deep Neural Networks to Map Caribou Lichen in High-Resolution Satellite Images Based on a Small-Scale, Noisy UAV-Derived Map","year":2021,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Natural Resources Canada; Queen's University","funders":"Natural Resources Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Lichen; Computer science; Remote sensing; Robustness (evolution); Scale (ratio); Artificial intelligence; Classifier (UML); Image resolution; Pattern recognition (psychology); Environmental science; Cartography; Geography; Ecology","score_opus":0.014284292907779472,"score_gpt":0.21326535378545014,"score_spread":0.19898106087767067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3181950296","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69703627,0.00086369924,0.28731617,0.00039783266,0.00015983704,0.000081756436,0.0011423447,0.007144406,0.005857643],"genre_scores_gemma":[0.939724,0.00019545335,0.055254795,0.0001465262,0.000041091138,0.000043119853,0.001954334,0.00009729365,0.0025434322],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997955,0.00002585282,0.000007982333,0.00007326387,0.000048034057,0.000049404138],"domain_scores_gemma":[0.9997061,0.0000698657,0.000030144041,0.000050424125,0.000120085926,0.000023345105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003207432,0.0009544725,0.00040637702,0.0009405289,0.00028227994,0.0006139714,0.00085003907,0.00054408045,0.0007027026],"category_scores_gemma":[0.00096824527,0.00027983187,0.0004954207,0.0008128502,0.0003188058,0.0007992549,0.0006772423,0.0005928532,0.00045851522],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024877358,0.00030259142,0.018280338,0.00013309973,0.0002273245,0.00034794296,0.00021135923,0.5157426,0.03496707,0.00076473725,0.0049660434,0.42380813],"study_design_scores_gemma":[0.000004513705,0.00001718697,0.0024397231,0.000007043288,0.000015169533,0.000017755458,0.000037595113,0.9928544,0.0037975786,0.00034282345,0.00045946124,0.0000066921634],"about_ca_topic_score_codex":0.026829382,"about_ca_topic_score_gemma":0.046332873,"teacher_disagreement_score":0.026829382,"about_ca_system_score_codex":0.00054779794,"about_ca_system_score_gemma":0.00062759407,"threshold_uncertainty_score":0.053346455},"labels":[],"label_agreement":null},{"id":"W318364127","doi":"10.1016/j.isprsjprs.2015.04.010","title":"Scale parameter selection by spatial statistics for GeOBIA: Using mean-shift based multi-scale segmentation as an example","year":2015,"lang":"en","type":"article","venue":"ISPRS Journal of Photogrammetry and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":160,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Segmentation; Panchromatic film; Computer science; Spatial analysis; Scale-space segmentation; Scale (ratio); Image segmentation; Pattern recognition (psychology); Artificial intelligence; Histogram; Segmentation-based object categorization; Data mining; Image resolution; Computer vision; Remote sensing; Image (mathematics); Cartography; Geology; Geography","score_opus":0.048084262968525325,"score_gpt":0.29184471301459813,"score_spread":0.2437604500460728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W318364127","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13774677,0.0006583103,0.85621387,0.00038652704,0.000066947374,0.00007475354,0.0002874316,0.0022051318,0.0023603332],"genre_scores_gemma":[0.5716231,0.00043933772,0.4249051,0.000089488574,0.000055081913,0.000053139032,0.00062276586,0.0007163553,0.0014956819],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99968123,0.000099741075,0.000021720882,0.00008116459,0.00006048771,0.000055680972],"domain_scores_gemma":[0.9994142,0.00025988297,0.000051190735,0.000087034125,0.0001591417,0.000028471779],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011594307,0.001003447,0.0011536496,0.0025667336,0.00066329516,0.0014894501,0.00064077147,0.0012298784,0.0012655715],"category_scores_gemma":[0.0022762485,0.00041224068,0.0011471388,0.0022338277,0.00045492328,0.00091899483,0.00056416664,0.000668001,0.0007347125],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00093855336,0.00026477454,0.01129472,0.00028681892,0.00025330298,0.0006003694,0.00028413098,0.3452687,0.07282051,0.008103245,0.0043284353,0.5555564],"study_design_scores_gemma":[0.000019296102,0.00003641909,0.0039723404,0.000013196272,0.00004167791,0.00008665902,0.00007199601,0.98283845,0.008446502,0.0031303256,0.0013207215,0.000022459608],"about_ca_topic_score_codex":0.008222648,"about_ca_topic_score_gemma":0.011180757,"teacher_disagreement_score":0.008222648,"about_ca_system_score_codex":0.00040074458,"about_ca_system_score_gemma":0.00083433825,"threshold_uncertainty_score":0.016349554},"labels":[],"label_agreement":null},{"id":"W3185635920","doi":"10.1145/3458305.3459594","title":"Enabling hyperspectral imaging in diverse illumination conditions for indoor applications","year":2021,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Hyperspectral imaging; Computer science; Artificial intelligence; Computer vision; Noise (video); Remote sensing; Electromagnetic spectrum; Ground truth; Full spectral imaging; Identification (biology); Image (mathematics); Optics; Geography","score_opus":0.016087917995523397,"score_gpt":0.25598636646342793,"score_spread":0.23989844846790453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3185635920","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08041538,0.0007880576,0.9092431,0.0004440658,0.00010583514,0.00007993489,0.0003679229,0.0031418987,0.0054138238],"genre_scores_gemma":[0.51179135,0.001074369,0.48138434,0.00045327964,0.000121847355,0.00011503953,0.0010680107,0.00036385056,0.0036278686],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996513,0.000056737103,0.000009492343,0.000096562864,0.00013930364,0.000046500732],"domain_scores_gemma":[0.999703,0.00006832259,0.000047034027,0.000072492265,0.000084620086,0.000024516276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040528717,0.000811131,0.00038403354,0.00061246444,0.00034154468,0.00075253344,0.0006698575,0.0006739374,0.0014162502],"category_scores_gemma":[0.0006079322,0.00024175501,0.000518933,0.0005372543,0.00049766724,0.0010547603,0.00091663416,0.00102097,0.0008384758],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026662007,0.00037803355,0.0036338235,0.0004365113,0.0001046324,0.00026297107,0.00020206004,0.09403875,0.37524575,0.003079921,0.008766402,0.51358443],"study_design_scores_gemma":[0.000019663406,0.0000916697,0.004869426,0.000038492366,0.000044467834,0.00040785025,0.00014535488,0.80081135,0.18058483,0.0037081968,0.009223906,0.000054755452],"about_ca_topic_score_codex":0.0013490211,"about_ca_topic_score_gemma":0.004028152,"teacher_disagreement_score":0.0014162502,"about_ca_system_score_codex":0.00029779374,"about_ca_system_score_gemma":0.0003531636,"threshold_uncertainty_score":0.0047377944},"labels":[],"label_agreement":null},{"id":"W3186410859","doi":"10.3390/rs13152927","title":"A Building Roof Identification CNN Based on Interior-Edge-Adjacency Features Using Hyperspectral Imagery","year":2021,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Hyperspectral imaging; Adjacency list; Computer science; Convolutional neural network; Roof; Artificial intelligence; Pattern recognition (psychology); Remote sensing; Enhanced Data Rates for GSM Evolution; Identification (biology); Computer vision; Geology; Algorithm; Geography","score_opus":0.01978793797607799,"score_gpt":0.25927535696303383,"score_spread":0.23948741898695583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3186410859","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26908502,0.0008144273,0.7107903,0.00039846226,0.0002523488,0.00018502775,0.0013495781,0.006259644,0.010865256],"genre_scores_gemma":[0.83191323,0.00045183013,0.15360911,0.00025717783,0.000046178226,0.00010964697,0.0030512747,0.000111474495,0.010450008],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99987626,0.000006594627,0.0000034267432,0.000045112836,0.000034618286,0.000033998374],"domain_scores_gemma":[0.9999094,0.000010500801,0.000011989273,0.000018324676,0.000041197116,0.000008523815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019211811,0.0007125608,0.00030472365,0.00047106817,0.00024758364,0.00034916122,0.00084689324,0.00042293884,0.0017935606],"category_scores_gemma":[0.00031091154,0.0003319071,0.00048573536,0.00045957393,0.00022457606,0.00089006434,0.0005805076,0.0005527723,0.0006340511],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002177289,0.00022399602,0.010119027,0.00016135805,0.00024253502,0.0003116129,0.00008013692,0.27321962,0.13279955,0.0026095668,0.012381277,0.5676336],"study_design_scores_gemma":[0.0000050245258,0.000035393932,0.0031985822,0.000010982247,0.00003259871,0.000065601984,0.000020288679,0.9698676,0.024692267,0.0003788747,0.0016802053,0.000012540016],"about_ca_topic_score_codex":0.019353794,"about_ca_topic_score_gemma":0.035298105,"teacher_disagreement_score":0.019353794,"about_ca_system_score_codex":0.0006249591,"about_ca_system_score_gemma":0.00064413546,"threshold_uncertainty_score":0.03848231},"labels":[],"label_agreement":null},{"id":"W3186478549","doi":"10.3390/rs13152869","title":"A Systematic Review of Landsat Data for Change Detection Applications: 50 Years of Monitoring the Earth","year":2021,"lang":"en","type":"review","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":230,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre For Cold Ocean Resources Engineering; Memorial University of Newfoundland","funders":"Natural Resources Canada","keywords":"Change detection; Remote sensing; Earth observation; Cloud computing; Scopus; Computer science; Data science; Trend analysis; Geography; Satellite; Political science","score_opus":0.12865999809936352,"score_gpt":0.3448903786845038,"score_spread":0.21623038058514027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3186478549","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030928713,0.992266,0.0004234879,0.00065755146,0.00025650088,0.00046413162,0.0021971478,0.000016717122,0.0006255913],"genre_scores_gemma":[0.015946036,0.9784239,0.0018029395,0.0010212264,0.00013574859,0.0009780184,0.0014457041,0.000019106548,0.00022744693],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9782592,0.0045994385,0.011064832,0.0013704501,0.004310212,0.00039596867],"domain_scores_gemma":[0.88492644,0.07833659,0.019797228,0.002176879,0.013854647,0.00090820354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017691065,0.0012754622,0.0046535307,0.038097583,0.0010620387,0.003941088,0.0023369608,0.0016924283,0.0034506724],"category_scores_gemma":[0.07533684,0.0010915872,0.0043736924,0.044914365,0.0014760717,0.0045861774,0.002191226,0.0010917733,0.00057516346],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015619198,0.000020830226,0.0023921474,0.9134507,0.0031444277,0.00030866155,0.001048288,0.000084294865,0.00044499434,0.0004829824,0.005450448,0.07301612],"study_design_scores_gemma":[0.000057844085,0.00012821845,0.008853657,0.9282143,0.013880456,0.0004895879,0.0010460834,0.00006891418,0.0003655507,0.00035368642,0.046498373,0.0000433088],"about_ca_topic_score_codex":0.008374005,"about_ca_topic_score_gemma":0.03582681,"teacher_disagreement_score":0.038097583,"about_ca_system_score_codex":0.005319421,"about_ca_system_score_gemma":0.020897154,"threshold_uncertainty_score":0.0935604},"labels":[],"label_agreement":null},{"id":"W3188841658","doi":"10.1007/978-3-030-84522-3_11","title":"A Comparable Study on Dimensionality Reduction Methods for Endmember Extraction","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Endmember; Hyperspectral imaging; Dimensionality reduction; Principal component analysis; Pattern recognition (psychology); Artificial intelligence; Computer science; Curse of dimensionality; Feature extraction; Extraction (chemistry); Mathematics; Chromatography; Chemistry","score_opus":0.063088422999893,"score_gpt":0.3597475841231494,"score_spread":0.2966591611232564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3188841658","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07500926,0.022847587,0.8678785,0.00087451376,0.0010658306,0.0003876725,0.0007012596,0.00097260077,0.030262861],"genre_scores_gemma":[0.2401782,0.019369485,0.6633344,0.0006672779,0.0012589536,0.0002756056,0.0035508336,0.00078100123,0.07058426],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99878937,0.00028535738,0.00009011354,0.00026019328,0.0005176476,0.000057227564],"domain_scores_gemma":[0.99693966,0.0014846842,0.00006186544,0.0006627246,0.00081425154,0.000036812573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011325042,0.0008126179,0.0010973107,0.0016620109,0.0008272306,0.0016178117,0.00061961275,0.00070093625,0.0060901595],"category_scores_gemma":[0.004300286,0.00023608156,0.001315037,0.002498877,0.00051564083,0.0021066163,0.00079361565,0.00078359514,0.002231648],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034730273,0.0003786953,0.0014154129,0.00093841885,0.00022494896,0.00013665148,0.00024258312,0.009965719,0.04950752,0.010674875,0.010879218,0.91528857],"study_design_scores_gemma":[0.000102788574,0.0017539414,0.033084717,0.00053428713,0.00066085736,0.0024616732,0.0010795805,0.5472917,0.19479352,0.028517798,0.18945256,0.00026653652],"about_ca_topic_score_codex":0.0026741363,"about_ca_topic_score_gemma":0.003446513,"teacher_disagreement_score":0.0060901595,"about_ca_system_score_codex":0.00042406743,"about_ca_system_score_gemma":0.00045778003,"threshold_uncertainty_score":0.020373642},"labels":[],"label_agreement":null},{"id":"W3190415999","doi":"10.18287/2412-6179-co-814","title":"Evaluation of the change in synthetic aperture radar imaging using transfer learning and residual network","year":2021,"lang":"en","type":"article","venue":"Computer Optics","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Synthetic aperture radar; Computer science; Artificial intelligence; Speckle noise; Ground truth; Residual; Remote sensing; Convolutional neural network; Radar imaging; Change detection; Inverse synthetic aperture radar; Speckle pattern; Metric (unit); Radar; Computer vision; Pattern recognition (psychology); Geology; Algorithm; Telecommunications; Engineering","score_opus":0.041129299543974485,"score_gpt":0.25999354570929906,"score_spread":0.21886424616532457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3190415999","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82924145,0.0007890781,0.16601756,0.00029474645,0.00008177799,0.000095764924,0.00024157867,0.00089391536,0.0023440684],"genre_scores_gemma":[0.96931565,0.00016394375,0.02932223,0.00003759084,0.000017886554,0.000023271781,0.00041438194,0.000032529555,0.00067254377],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99953735,0.000097817414,0.00003242937,0.00011013063,0.00015958566,0.000062802996],"domain_scores_gemma":[0.9991534,0.00032382322,0.00012973121,0.00007141817,0.0002794434,0.000042267162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015672245,0.00073192763,0.00052921585,0.0012637211,0.00018509722,0.00062120066,0.00059409306,0.0007772571,0.0005563561],"category_scores_gemma":[0.002929983,0.00015492916,0.00044831005,0.0005392915,0.0004010488,0.0008691132,0.00039633748,0.00048052985,0.00015288025],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011283093,0.00045963682,0.032474265,0.0002878986,0.000338375,0.00039392718,0.0001491504,0.57769305,0.050672337,0.0012000767,0.0015135655,0.33368933],"study_design_scores_gemma":[0.0000060531333,0.0001129703,0.0060235434,0.0000049105297,0.00001943998,0.000040180283,0.000025335563,0.9866866,0.006799159,0.00013156026,0.00014295295,0.0000072918556],"about_ca_topic_score_codex":0.0055496064,"about_ca_topic_score_gemma":0.0053472184,"teacher_disagreement_score":0.0055496064,"about_ca_system_score_codex":0.00061729446,"about_ca_system_score_gemma":0.0003549957,"threshold_uncertainty_score":0.011034608},"labels":[],"label_agreement":null},{"id":"W3191464973","doi":"10.1088/1742-6596/1994/1/012010","title":"Unsupervised feature learning for data classification","year":2021,"lang":"en","type":"article","venue":"Journal of Physics Conference Series","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Autoencoder; Feature learning; Discriminative model; Artificial intelligence; Computer science; Feature (linguistics); Dimension (graph theory); Representation (politics); Task (project management); Pattern recognition (psychology); Dimensionality reduction; Machine learning; Linear classifier; Artificial neural network; Support vector machine; Mathematics; Engineering","score_opus":0.08697433770375344,"score_gpt":0.28132451510262607,"score_spread":0.19435017739887261,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3191464973","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012278784,0.00018670897,0.9852282,0.00016185382,0.000030795778,0.00004270419,0.0002261772,0.0014067966,0.00043803133],"genre_scores_gemma":[0.44273034,0.00026373344,0.55202943,0.00021596834,0.00014498446,0.00032239885,0.0021675169,0.00020723756,0.0019184666],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99876356,0.00036045312,0.00008868575,0.00041699363,0.00027486368,0.000095370764],"domain_scores_gemma":[0.9974039,0.0012806936,0.00023427066,0.00056181307,0.0004567717,0.00006250075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015420017,0.0009805023,0.0009413639,0.0014130997,0.00040052764,0.0007440616,0.0012709419,0.000928442,0.0015982257],"category_scores_gemma":[0.004472798,0.0003103808,0.0010556409,0.0014148254,0.0007862456,0.0014682275,0.0011692953,0.0015788145,0.00080031046],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021091211,0.00025687556,0.004310433,0.00019961578,0.00018748557,0.00013692713,0.00009134937,0.1836827,0.020322867,0.01160113,0.006562121,0.7724376],"study_design_scores_gemma":[0.000007501169,0.00003985378,0.00074502407,0.00001020301,0.000011722322,0.000037339036,0.000011501414,0.9836271,0.005054005,0.009133912,0.0013120417,0.000009699331],"about_ca_topic_score_codex":0.001530665,"about_ca_topic_score_gemma":0.001820391,"teacher_disagreement_score":0.0015982257,"about_ca_system_score_codex":0.0006729269,"about_ca_system_score_gemma":0.00078350597,"threshold_uncertainty_score":0.008154988},"labels":[],"label_agreement":null},{"id":"W3193503404","doi":"10.2478/cait-2021-0018","title":"Performance Evaluation of Change Detection in SAR Images Based on Hybrid Antlion DWT Fuzzy c-Means Clustering","year":2021,"lang":"en","type":"article","venue":"Cybernetics and Information Technologies","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Computer science; Synthetic aperture radar; Fuzzy logic; Pattern recognition (psychology); Cluster analysis; Image fusion; Filter (signal processing); Pixel; Ground truth; Sensitivity (control systems); Image (mathematics); Wavelet; Computer vision","score_opus":0.029697824483838717,"score_gpt":0.23232506330643457,"score_spread":0.20262723882259587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3193503404","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7743406,0.0007333564,0.21968906,0.00025283595,0.00010065649,0.000097933334,0.00012341599,0.0011738923,0.0034881698],"genre_scores_gemma":[0.9217973,0.0001337667,0.07697949,0.000030344578,0.000013788933,0.000030618703,0.00017257492,0.00003206711,0.00081006286],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901867,0.00021800767,0.00008110476,0.00020523115,0.0003928107,0.0000842516],"domain_scores_gemma":[0.99849916,0.00048971805,0.00013919298,0.00009351635,0.00071936095,0.000059035454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017491566,0.0005775972,0.0006809082,0.002329854,0.00042091915,0.0009433455,0.0005846053,0.0008189872,0.000563797],"category_scores_gemma":[0.0035039731,0.0001786833,0.00052110205,0.001035362,0.00032452092,0.00066028663,0.00034412544,0.0002999147,0.00024603336],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021759132,0.0005180825,0.031011278,0.00032419048,0.0004750372,0.00021564108,0.0003450437,0.3531624,0.06339634,0.0013112477,0.0018818509,0.545183],"study_design_scores_gemma":[0.00001078256,0.00011683443,0.0061424174,0.0000059555923,0.000029000517,0.00006001487,0.000052911397,0.98254514,0.010721187,0.00012152798,0.00017945313,0.000014769388],"about_ca_topic_score_codex":0.0102297515,"about_ca_topic_score_gemma":0.0063630217,"teacher_disagreement_score":0.0102297515,"about_ca_system_score_codex":0.0007879884,"about_ca_system_score_gemma":0.00049103756,"threshold_uncertainty_score":0.020340443},"labels":[],"label_agreement":null},{"id":"W3197014985","doi":"10.1190/int-2020-0140.1","title":"Hyperspectral fluorescence imaging: Robust detection of petroleum in porous sedimentary rock formations","year":2021,"lang":"en","type":"article","venue":"Interpretation","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Oil sands; Hyperspectral imaging; Asphalt; Geology; API gravity; Petroleum; Remote sensing; Mineralogy; Environmental science; Materials science","score_opus":0.007739103801937398,"score_gpt":0.2087846378289867,"score_spread":0.2010455340270493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3197014985","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96560085,0.00010357081,0.032674685,0.000054528035,0.0000043657697,0.00003052626,0.00017327105,0.00028094754,0.0010773286],"genre_scores_gemma":[0.95783544,0.00009265013,0.04115581,0.000020051255,0.0000036145323,0.000015643314,0.00013326168,0.000014657058,0.0007288154],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9999043,0.000009425367,0.000002198563,0.000024024213,0.000044677894,0.000015419238],"domain_scores_gemma":[0.9999167,0.00001821716,0.000020686695,0.0000067046726,0.000029547215,0.000008060244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017138808,0.00018418086,0.000083119725,0.0004494174,0.00013908673,0.00021306463,0.00026182784,0.00020042104,0.00039780824],"category_scores_gemma":[0.00024078654,0.00009558147,0.0000859645,0.00022349351,0.00030029667,0.0002155372,0.00019390174,0.00015157895,0.00010960115],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010770308,0.000049768663,0.012035953,0.000035813602,0.0000109716,0.00004618617,0.000053449057,0.00841744,0.94166446,0.00017834286,0.00021579448,0.03718419],"study_design_scores_gemma":[0.000015397509,0.000111636866,0.1224054,0.000009726546,0.00001481699,0.00019048424,0.0001460333,0.30238238,0.5731901,0.00023164613,0.0012787427,0.000023639395],"about_ca_topic_score_codex":0.015316612,"about_ca_topic_score_gemma":0.025195284,"teacher_disagreement_score":0.015316612,"about_ca_system_score_codex":0.00040866868,"about_ca_system_score_gemma":0.00028858308,"threshold_uncertainty_score":0.030454934},"labels":[],"label_agreement":null},{"id":"W3200742127","doi":"10.1109/lgrs.2021.3112198","title":"Exploiting Spectral–Spatial Information Using Deep Random Forest for Hyperspectral Imagery Classification","year":2021,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Space Agency","keywords":"Hyperspectral imaging; Random forest; Artificial intelligence; Overfitting; Computer science; Pattern recognition (psychology); Spatial analysis; Convolutional neural network; Contextual image classification; Deep learning; Support vector machine; Remote sensing; Artificial neural network; Image (mathematics); Geography","score_opus":0.02148102911426475,"score_gpt":0.23063478739438908,"score_spread":0.20915375828012434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200742127","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042750724,0.0009206958,0.95282763,0.00019497126,0.000048448157,0.00003133575,0.00016215407,0.0017334183,0.0013305418],"genre_scores_gemma":[0.615178,0.0008427925,0.3790767,0.00026546844,0.00010380528,0.000082184815,0.0015208013,0.00015633344,0.002773956],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99966085,0.000060137176,0.000017067116,0.000092281196,0.000101159676,0.00006846661],"domain_scores_gemma":[0.9996743,0.00010141983,0.00005194973,0.00005747767,0.000094960335,0.000019833786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000703795,0.0010045622,0.00079693645,0.0013901746,0.00033996993,0.0004485208,0.0008560646,0.0007073814,0.0009893384],"category_scores_gemma":[0.0008656304,0.0002672167,0.0009299452,0.0014726825,0.00036824544,0.0011399221,0.00052694,0.00086398027,0.00049421255],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020697889,0.00023874777,0.004370077,0.00013707268,0.00013970755,0.00012756926,0.000078729834,0.22969064,0.027633753,0.0036919767,0.005958182,0.72772664],"study_design_scores_gemma":[0.0000057020466,0.000018686362,0.00057812186,0.000005838263,0.000015676302,0.00003591987,0.000009234589,0.9933861,0.0034703454,0.0017520463,0.0007129659,0.000009393155],"about_ca_topic_score_codex":0.006372906,"about_ca_topic_score_gemma":0.009313272,"teacher_disagreement_score":0.006372906,"about_ca_system_score_codex":0.000434306,"about_ca_system_score_gemma":0.00059372454,"threshold_uncertainty_score":0.01267159},"labels":[],"label_agreement":null},{"id":"W3201321969","doi":"10.5281/zenodo.5533518","title":"Comparison of Linear Unmixing Methods on Paintings Data Set","year":2021,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"European Commission","keywords":"Humanities; Hyperspectral imaging; Art; Computer science; Artificial intelligence","score_opus":0.0800703670625266,"score_gpt":0.3463582140925186,"score_spread":0.266287847029992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3201321969","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7300032,0.016202532,0.22630274,0.0010367897,0.00094193366,0.0005261927,0.004661054,0.009380758,0.010944806],"genre_scores_gemma":[0.6715433,0.0049329842,0.2933716,0.00031798205,0.00026076005,0.00039297497,0.02155993,0.0012840667,0.00633647],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980155,0.0004783726,0.00018758886,0.0005441695,0.0005872911,0.00018700602],"domain_scores_gemma":[0.9974306,0.0013009144,0.00010644875,0.000334762,0.0007130139,0.00011425077],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004215498,0.00233355,0.0012279155,0.0031938339,0.00078701955,0.0014641288,0.0010106893,0.0015008893,0.0018706154],"category_scores_gemma":[0.0068926923,0.0002945412,0.0015393485,0.0022188544,0.00056097296,0.0020692842,0.001270588,0.0012753165,0.0014938477],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031406274,0.0007757712,0.008675756,0.001646893,0.0012634941,0.00019565265,0.0003882296,0.117974594,0.029243091,0.00096889224,0.01002629,0.82570076],"study_design_scores_gemma":[0.00020614751,0.00067706907,0.032778915,0.00016240997,0.00036282322,0.00022932829,0.000658193,0.919885,0.035942208,0.002073309,0.0068945093,0.00013007886],"about_ca_topic_score_codex":0.005436,"about_ca_topic_score_gemma":0.0070310114,"teacher_disagreement_score":0.005436,"about_ca_system_score_codex":0.00042412928,"about_ca_system_score_gemma":0.0007562126,"threshold_uncertainty_score":0.022293925},"labels":[],"label_agreement":null},{"id":"W3201998047","doi":"10.18280/ts.380434","title":"An Effective Turkey Marble Classification System: Convolutional Neural Network with Genetic Algorithm -Wavelet Kernel - Extreme Learning Machine","year":2021,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Extreme learning machine; Artificial intelligence; Convolutional neural network; Computer science; Pattern recognition (psychology); Kernel (algebra); Genetic algorithm; Support vector machine; Wavelet; Artificial neural network; Algorithm; Machine learning; Mathematics","score_opus":0.013648255640724485,"score_gpt":0.20146051696150416,"score_spread":0.18781226132077966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3201998047","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16976537,0.00064469606,0.82053554,0.0002950221,0.00014312123,0.00011310048,0.0001755109,0.004371421,0.0039562653],"genre_scores_gemma":[0.8495791,0.00027031355,0.14238995,0.0001338144,0.000029999997,0.000095782714,0.00057786074,0.000060805847,0.006862446],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99975425,0.000028414835,0.000013435704,0.00007510096,0.00008785552,0.00004091588],"domain_scores_gemma":[0.9998417,0.000022034135,0.000020383066,0.00001949562,0.00008495471,0.000011347708],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041273597,0.0006332491,0.0005346256,0.0006381375,0.0003106801,0.0005238047,0.0007935018,0.00065079855,0.001013415],"category_scores_gemma":[0.00064645463,0.00024398981,0.0004326323,0.0004260712,0.00019800513,0.0007468769,0.00041908285,0.0005373435,0.0003893228],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003254759,0.00025777853,0.006048291,0.00011623023,0.0001643736,0.00028178797,0.00006503965,0.23239376,0.06231997,0.0035874997,0.005601343,0.6888385],"study_design_scores_gemma":[0.0000066471885,0.000048036076,0.0012676072,0.0000042132397,0.00001608717,0.000056756762,0.0000059211998,0.98698634,0.010551358,0.00035834004,0.00068774226,0.000010922143],"about_ca_topic_score_codex":0.008288392,"about_ca_topic_score_gemma":0.008352164,"teacher_disagreement_score":0.008288392,"about_ca_system_score_codex":0.000796922,"about_ca_system_score_gemma":0.0007641205,"threshold_uncertainty_score":0.016480267},"labels":[],"label_agreement":null},{"id":"W3205465097","doi":"10.1109/igarss47720.2021.9554051","title":"Semantic Segmentation of Land Use / Land Cover (LU/LC) Types Using F-CNNS on Multi-Sensor (Radar-Ir-Optical) Image Data","year":2021,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Remote sensing; Computer science; RGB color model; Segmentation; Convolutional neural network; Artificial intelligence; Normalized Difference Vegetation Index; Synthetic aperture radar; Land cover; Image resolution; Image segmentation; Pattern recognition (psychology); Computer vision; Geology; Land use","score_opus":0.07614318867150226,"score_gpt":0.2930926354499511,"score_spread":0.21694944677844885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205465097","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75333774,0.0014463165,0.23168236,0.00030720845,0.0001928958,0.00013874775,0.002047207,0.0038635717,0.006983889],"genre_scores_gemma":[0.91338485,0.0004744329,0.07709387,0.00015143042,0.000040010276,0.00006447661,0.0041199895,0.00009801019,0.004573001],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999818,0.000015181642,0.000009912365,0.000068654575,0.000027684355,0.000060580398],"domain_scores_gemma":[0.99985075,0.00003083434,0.000028206383,0.000022302023,0.000055323886,0.000012589797],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031522076,0.0009857739,0.0004288549,0.00093272666,0.00024113784,0.00063997717,0.00056805724,0.0006032208,0.0011202311],"category_scores_gemma":[0.0005787756,0.00024376939,0.00074946677,0.000658516,0.00023841551,0.0008477588,0.00046953632,0.0004141459,0.0006076197],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00064028276,0.0002861068,0.012503784,0.00023524584,0.0002863522,0.0004159337,0.0002298617,0.2710717,0.0820803,0.0013574684,0.004817575,0.6260753],"study_design_scores_gemma":[0.0000055135692,0.00007858766,0.0069452818,0.000025034304,0.000055263383,0.00006753348,0.00008583261,0.96875185,0.021748032,0.00092930335,0.0012948206,0.000012999695],"about_ca_topic_score_codex":0.015684888,"about_ca_topic_score_gemma":0.019102952,"teacher_disagreement_score":0.015684888,"about_ca_system_score_codex":0.00073635275,"about_ca_system_score_gemma":0.00048157008,"threshold_uncertainty_score":0.031187236},"labels":[],"label_agreement":null},{"id":"W3205562958","doi":"10.1109/igarss47720.2021.9553563","title":"SAR Image Change Detection Method Based on Neural-CRF Structure","year":2021,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Unary operation; Computer science; Artificial intelligence; Pattern recognition (psychology); Transformer; Subtraction; Recurrent neural network; Pairwise comparison; Pixel; Image (mathematics); Artificial neural network; Mathematics","score_opus":0.024635973309736024,"score_gpt":0.26111603887188944,"score_spread":0.23648006556215342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205562958","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045869935,0.00067975954,0.93989193,0.00027645883,0.00014624286,0.0001804894,0.000832576,0.00834244,0.0037801766],"genre_scores_gemma":[0.50329244,0.00051658944,0.48333144,0.0003213978,0.00018093167,0.00020976696,0.0040559173,0.00049288257,0.007598575],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999273,0.000053503743,0.00003802467,0.0003760675,0.00018189843,0.00007747998],"domain_scores_gemma":[0.99937785,0.00014142384,0.0000722157,0.00010349967,0.00027779667,0.000027144159],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007173308,0.00076822925,0.0010414401,0.0016413463,0.0005914394,0.00046696758,0.0018907278,0.00082660414,0.0023611675],"category_scores_gemma":[0.0015597645,0.00048562337,0.0011377855,0.0014240735,0.00041967072,0.0015788879,0.00056377205,0.0012099613,0.0010246236],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028398176,0.00019106989,0.0047818823,0.00022903232,0.0001296031,0.0002782114,0.00016309209,0.1442758,0.033521015,0.0034240612,0.017369734,0.7953526],"study_design_scores_gemma":[0.000022426537,0.000034288965,0.0022889937,0.000008464658,0.000042877276,0.00015128076,0.000020616382,0.983761,0.009490117,0.0015544359,0.0026018475,0.000023662917],"about_ca_topic_score_codex":0.017391074,"about_ca_topic_score_gemma":0.017794743,"teacher_disagreement_score":0.017391074,"about_ca_system_score_codex":0.00084905955,"about_ca_system_score_gemma":0.0010778552,"threshold_uncertainty_score":0.034579694},"labels":[],"label_agreement":null},{"id":"W3205581890","doi":"10.3390/rs13204102","title":"Archetypal Analysis and Structured Sparse Representation for Hyperspectral Anomaly Detection","year":2021,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Endmember; Hyperspectral imaging; Anomaly detection; Pattern recognition (psychology); Sparse approximation; Computer science; Pixel; Artificial intelligence; Representation (politics); Spectral signature; Anomaly (physics); Remote sensing; Physics; Geography","score_opus":0.022531333427492268,"score_gpt":0.25523584086349377,"score_spread":0.2327045074360015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205581890","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008957198,0.00012237855,0.98997307,0.00008069757,0.000015153519,0.000015479858,0.000039426577,0.00022737726,0.00056920236],"genre_scores_gemma":[0.2943819,0.00057588547,0.7012595,0.00018484623,0.00011794032,0.0001083476,0.00074995036,0.00009900156,0.0025226215],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995838,0.00008917177,0.000018111472,0.00009195712,0.00018306162,0.000033996246],"domain_scores_gemma":[0.99952924,0.00016747393,0.00007996201,0.00007598369,0.00012366219,0.000023698956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049897947,0.00058542663,0.00045717775,0.0008710059,0.00024651425,0.00046711002,0.00054501294,0.0005787825,0.0009169237],"category_scores_gemma":[0.0014013435,0.00018146793,0.00054931396,0.001013364,0.00052438764,0.00087820133,0.00091775146,0.0010638396,0.0004940508],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016451356,0.00019831487,0.002000211,0.00019053702,0.0001014649,0.00013315119,0.00015645863,0.20994739,0.07748146,0.031204488,0.0044476804,0.6739743],"study_design_scores_gemma":[0.0000042424927,0.00002639123,0.0003715205,0.000005259965,0.000008304155,0.000055805853,0.000014453645,0.9864699,0.0065827714,0.005341152,0.0011110392,0.000009222102],"about_ca_topic_score_codex":0.0013505445,"about_ca_topic_score_gemma":0.0015480409,"teacher_disagreement_score":0.0013505445,"about_ca_system_score_codex":0.00027336046,"about_ca_system_score_gemma":0.000499076,"threshold_uncertainty_score":0.0030674338},"labels":[],"label_agreement":null},{"id":"W3205619972","doi":"10.1109/igarss47720.2021.9553172","title":"Building Change Detection in Off-Nadir Images Using Deep Learning","year":2021,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Nadir; Deep learning; Ground truth; Change detection; Computer science; Footprint; Remote sensing; Satellite; Artificial intelligence; Tracking (education); Satellite imagery; Computer vision; Geology; Engineering","score_opus":0.03239892195790438,"score_gpt":0.254495889791729,"score_spread":0.2220969678338246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205619972","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67893034,0.00068283634,0.30311182,0.00029329266,0.00014582735,0.00013256335,0.0014730701,0.006589473,0.008640792],"genre_scores_gemma":[0.90623873,0.0001914917,0.088279024,0.000109568005,0.000028964514,0.000035484747,0.0021477798,0.00010548141,0.002863436],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99974793,0.000017561042,0.000009241849,0.00009879589,0.00006215815,0.00006416326],"domain_scores_gemma":[0.9998455,0.000024029401,0.000025712876,0.000029601237,0.000060499267,0.000014535147],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026751368,0.00076137047,0.00047597318,0.0014850278,0.00024766274,0.0006055347,0.00072485063,0.00043357964,0.0012585189],"category_scores_gemma":[0.00045624893,0.00030118466,0.00070778665,0.001020989,0.00029756557,0.00068600406,0.00059953524,0.0006561277,0.000659333],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003238207,0.0004611722,0.03360862,0.00015563448,0.00022444197,0.00031293277,0.00020304932,0.23327664,0.05545866,0.0010505343,0.00594384,0.66898066],"study_design_scores_gemma":[0.000006911757,0.000032985718,0.012876702,0.000010490477,0.0000242599,0.00004578413,0.00006802495,0.97305864,0.012110417,0.0004761137,0.0012785259,0.000011102109],"about_ca_topic_score_codex":0.02136633,"about_ca_topic_score_gemma":0.04683775,"teacher_disagreement_score":0.02136633,"about_ca_system_score_codex":0.0006227864,"about_ca_system_score_gemma":0.00043962686,"threshold_uncertainty_score":0.042483926},"labels":[],"label_agreement":null},{"id":"W3206141882","doi":"10.1109/igarss47720.2021.9553254","title":"Ship Detection and Classification in EO/IR VHR Satellite Imagery","year":2021,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Defence Research and Development Canada; Centre For Cold Ocean Resources Engineering","funders":"Defence Research and Development Canada","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Pattern recognition (psychology); Thresholding; Contextual image classification; Satellite; Support vector machine; Linear discriminant analysis; False alarm; False positive paradox; Remote sensing; Masking (illustration); Object detection; Image (mathematics)","score_opus":0.024125374310378655,"score_gpt":0.2282214933229447,"score_spread":0.20409611901256605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3206141882","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8081915,0.00028198198,0.18354113,0.00009732281,0.00005473035,0.000122036516,0.000564339,0.0013740098,0.005773058],"genre_scores_gemma":[0.87992275,0.00020503053,0.11598904,0.000047872963,0.0000191268,0.000040384883,0.0007781521,0.000061445484,0.0029362042],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997547,0.000029045557,0.00001181949,0.000071664814,0.000087428045,0.000045289515],"domain_scores_gemma":[0.9997148,0.00008501978,0.000044113072,0.000037180314,0.000100048615,0.000018838167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005674558,0.0004383083,0.00028452446,0.001418951,0.00016050586,0.0005081151,0.0003147421,0.0003996182,0.00090894767],"category_scores_gemma":[0.0007062232,0.00019116592,0.00037209867,0.0007023561,0.00022655983,0.00046469408,0.0002885286,0.00030825782,0.00056679035],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007051128,0.00032170088,0.05008611,0.00035011204,0.0001557278,0.0003992933,0.00031836046,0.05562298,0.33681518,0.0011737931,0.0027926571,0.551259],"study_design_scores_gemma":[0.000024258235,0.00030262113,0.17622423,0.000031395182,0.000077023135,0.00039496046,0.00023429206,0.6672897,0.15204893,0.0007601853,0.0025791046,0.000033386263],"about_ca_topic_score_codex":0.0028610548,"about_ca_topic_score_gemma":0.0040600374,"teacher_disagreement_score":0.0028610548,"about_ca_system_score_codex":0.00022539636,"about_ca_system_score_gemma":0.00018025903,"threshold_uncertainty_score":0.005688846},"labels":[],"label_agreement":null},{"id":"W3207200417","doi":"10.1109/igarss47720.2021.9553499","title":"Global land use / land cover with Sentinel 2 and deep learning","year":2021,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1249,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact","funders":"National Geographic Society","keywords":"Geospatial analysis; Land cover; Remote sensing; Computer science; Deep learning; Satellite imagery; Big data; Cloud computing; Data science; Geomatics; Earth observation; Land use; Artificial intelligence; Satellite; Cartography; Geography; Data mining; Engineering","score_opus":0.010026119463231054,"score_gpt":0.2014934866961274,"score_spread":0.19146736723289634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3207200417","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55194294,0.001242276,0.2968688,0.0018365305,0.00092550216,0.00042519576,0.08361704,0.0372859,0.02585578],"genre_scores_gemma":[0.6574888,0.00041459227,0.1984728,0.00073338486,0.0001462685,0.000260263,0.1328743,0.0009996869,0.008609834],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997826,0.00002253486,0.000009364999,0.000083893814,0.00006197581,0.000039549457],"domain_scores_gemma":[0.99981743,0.000023971574,0.000024424702,0.000044050794,0.00006750968,0.000022671751],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033319616,0.0007850717,0.00026129742,0.00071577175,0.00021449981,0.00049010816,0.00078845443,0.000509107,0.0023195448],"category_scores_gemma":[0.00079060165,0.00023881959,0.00062404666,0.0008689935,0.0003067524,0.0008080343,0.000775165,0.0007681912,0.001434361],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037187763,0.0008028548,0.04393335,0.0003242699,0.00037274486,0.00045027502,0.00028082548,0.4137268,0.036868803,0.005929811,0.15890378,0.33803466],"study_design_scores_gemma":[0.000027228773,0.00007473848,0.011001408,0.00002778862,0.000024474048,0.000064277374,0.000086462576,0.95783895,0.010801043,0.0039869947,0.016029138,0.00003750235],"about_ca_topic_score_codex":0.019983526,"about_ca_topic_score_gemma":0.038386934,"teacher_disagreement_score":0.019983526,"about_ca_system_score_codex":0.0005545013,"about_ca_system_score_gemma":0.00066667184,"threshold_uncertainty_score":0.039734423},"labels":[],"label_agreement":null},{"id":"W3207491876","doi":"10.1109/igarss47720.2021.9553720","title":"Building Damage Detection in Post-Event High-Resolution Imagery Using Deep Transfer Learning","year":2021,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Orthophoto; Computer science; Event (particle physics); Deep learning; Artificial intelligence; Geospatial analysis; Transfer of learning; Residual; Image resolution; Remote sensing; Convolutional neural network; Computer vision; Geography","score_opus":0.012885833517018818,"score_gpt":0.23147466877252043,"score_spread":0.2185888352555016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3207491876","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.72445524,0.00061855017,0.26597303,0.00032716527,0.000095528994,0.0000984852,0.00053501024,0.003454918,0.004442064],"genre_scores_gemma":[0.96742076,0.00011376172,0.029636564,0.00006160499,0.000021392447,0.000023775314,0.00077782857,0.00003180087,0.0019125824],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998641,0.000015434303,0.000005152061,0.000039933177,0.00003463302,0.000040698033],"domain_scores_gemma":[0.99978834,0.000049596954,0.000035337274,0.00004172605,0.000065727225,0.000019378784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035093023,0.000656012,0.00031067713,0.0007878795,0.00019448482,0.0003956255,0.00077363005,0.0005173548,0.0010242815],"category_scores_gemma":[0.0007518629,0.00020378613,0.00041526274,0.0004451902,0.00027791806,0.0007164921,0.0005618618,0.0007325177,0.0004979178],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003602388,0.00056892453,0.013274267,0.00010634035,0.00013740244,0.0004885171,0.00017069184,0.48253188,0.03452689,0.0008265741,0.0035977014,0.46341062],"study_design_scores_gemma":[0.000005614802,0.000052188807,0.0058007673,0.000007559059,0.000012205749,0.00004288294,0.00003695422,0.98764765,0.005436878,0.0006080377,0.00034226713,0.0000070978294],"about_ca_topic_score_codex":0.006083136,"about_ca_topic_score_gemma":0.010430252,"teacher_disagreement_score":0.006083136,"about_ca_system_score_codex":0.00046902994,"about_ca_system_score_gemma":0.00037527346,"threshold_uncertainty_score":0.012095451},"labels":[],"label_agreement":null},{"id":"W3209230671","doi":"10.1007/s11042-021-11691-5","title":"Hyperspectral face recognition with histogram of oriented gradient features and collaborative representation-based classifier","year":2021,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Hyperspectral imaging; Computer science; Artificial intelligence; Pattern recognition (psychology); Classifier (UML); Minimum bounding box; Histogram; Facial recognition system; Dimensionality reduction; Bounding overwatch; Histogram of oriented gradients; Three-dimensional face recognition; Computer vision; Face detection; Image (mathematics)","score_opus":0.020997458124832474,"score_gpt":0.24361695668383435,"score_spread":0.22261949855900187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209230671","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04561047,0.0002622053,0.95050484,0.00012904925,0.00009575942,0.00008303521,0.00010956435,0.00080241374,0.0024026998],"genre_scores_gemma":[0.57289696,0.00032005802,0.42008287,0.00016824233,0.00016825003,0.0001867393,0.0005624451,0.00009362194,0.00552083],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991768,0.00012472484,0.00003296563,0.00022170514,0.00034725512,0.00009654419],"domain_scores_gemma":[0.9994524,0.0001150086,0.000056171488,0.000117348434,0.00022521522,0.000033934153],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007503637,0.0004901911,0.0009788199,0.0011640453,0.0005147483,0.00087214477,0.0009469249,0.0007304254,0.00184609],"category_scores_gemma":[0.0013586509,0.00023629257,0.0009638205,0.001096507,0.00038186193,0.0013411645,0.0009808013,0.00071396574,0.001111115],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022463502,0.00047135682,0.0023563164,0.00005748306,0.00013070669,0.00005293265,0.00007767347,0.030034197,0.04622117,0.003324841,0.004475654,0.91257304],"study_design_scores_gemma":[0.000014942135,0.00012081937,0.0026247131,0.000007753209,0.000058189056,0.00014312178,0.000046580953,0.97223526,0.021311631,0.0021006716,0.0013138115,0.000022664883],"about_ca_topic_score_codex":0.0032904812,"about_ca_topic_score_gemma":0.00340851,"teacher_disagreement_score":0.0032904812,"about_ca_system_score_codex":0.00035972343,"about_ca_system_score_gemma":0.00065231277,"threshold_uncertainty_score":0.006542623},"labels":[],"label_agreement":null},{"id":"W3209733456","doi":"10.3390/rs13214405","title":"Bagging and Boosting Ensemble Classifiers for Classification of Multispectral, Hyperspectral and PolSAR Data: A Comparative Evaluation","year":2021,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":186,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Centre For Cold Ocean Resources Engineering; Memorial University of Newfoundland","funders":"","keywords":"Boosting (machine learning); AdaBoost; Computer science; Artificial intelligence; Multispectral image; Hyperspectral imaging; Random forest; Gradient boosting; Classifier (UML); Decision tree; Statistical classification; Contextual image classification; Machine learning; Pattern recognition (psychology); Ensemble learning; Remote sensing; Image (mathematics); Geography","score_opus":0.1489573791084855,"score_gpt":0.34385137172798336,"score_spread":0.19489399261949786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209733456","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3895563,0.10596239,0.47661126,0.0015376405,0.002686479,0.0006515086,0.0017607459,0.0050976085,0.016136007],"genre_scores_gemma":[0.806825,0.018594926,0.16463062,0.00044141622,0.0009865251,0.0003559844,0.0036827489,0.00029450265,0.0041882717],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99575895,0.0011438406,0.00029177574,0.0005271554,0.0020471471,0.00023109531],"domain_scores_gemma":[0.99490994,0.00229667,0.00023030779,0.00042062678,0.0019668438,0.00017563652],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0081902845,0.0018128813,0.0029808925,0.004844685,0.0008308083,0.0016133753,0.001410198,0.0013966697,0.0012585063],"category_scores_gemma":[0.008043518,0.00035765822,0.0016640843,0.003573012,0.00043394658,0.0025106226,0.0010020741,0.0013383082,0.00082983036],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001108464,0.00052576396,0.013166695,0.00090034155,0.0009167413,0.00009848362,0.00017708044,0.11027523,0.0024380928,0.0017354273,0.008443388,0.86021435],"study_design_scores_gemma":[0.00007291714,0.0010847007,0.014224379,0.00017036306,0.0007195785,0.0002680399,0.00023838371,0.966023,0.005305961,0.0023984464,0.00939889,0.00009525256],"about_ca_topic_score_codex":0.0040985025,"about_ca_topic_score_gemma":0.003383632,"teacher_disagreement_score":0.0081902845,"about_ca_system_score_codex":0.0006602999,"about_ca_system_score_gemma":0.0009608096,"threshold_uncertainty_score":0.043314934},"labels":[],"label_agreement":null},{"id":"W3211822504","doi":"10.3390/rs13224604","title":"Remote Sensing Imagery Segmentation: A Hybrid Approach","year":2021,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Cuckoo search; Thresholding; Computer science; Segmentation; Artificial intelligence; Entropy (arrow of time); Image segmentation; Balanced histogram thresholding; Pattern recognition (psychology); Otsu's method; Computer vision; Algorithm; Image (mathematics); Image processing; Particle swarm optimization","score_opus":0.021547343333981717,"score_gpt":0.23690457590802785,"score_spread":0.21535723257404613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211822504","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013546197,0.0005775636,0.98254997,0.00009964192,0.00003517101,0.00006833858,0.00004213017,0.0006774333,0.0024035068],"genre_scores_gemma":[0.30899125,0.00070503453,0.68463755,0.00019131892,0.00011011508,0.00018885516,0.0002636618,0.00030043427,0.004611701],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992335,0.0000939627,0.00004831852,0.0002287968,0.00031558846,0.00007983131],"domain_scores_gemma":[0.99960715,0.00011875789,0.00006158716,0.00005391734,0.00013412868,0.000024406341],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000732392,0.0010617529,0.0012064271,0.003707938,0.0005197602,0.0017276503,0.0014398635,0.0015938841,0.0016886154],"category_scores_gemma":[0.0011229331,0.0007024813,0.0014555599,0.0022499154,0.0006621649,0.0015758857,0.0012211272,0.0005218899,0.0006923649],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028246726,0.00016911248,0.0024548308,0.0005201813,0.00040483242,0.00032688744,0.0004334216,0.25360096,0.11911942,0.014418516,0.002192262,0.60607713],"study_design_scores_gemma":[0.0000089434525,0.00007508699,0.0010082641,0.000026104948,0.00006551602,0.00022597736,0.000067947774,0.9804349,0.0105897095,0.0047762822,0.0026863066,0.000034907236],"about_ca_topic_score_codex":0.0021530862,"about_ca_topic_score_gemma":0.0028282178,"teacher_disagreement_score":0.003707938,"about_ca_system_score_codex":0.0006505517,"about_ca_system_score_gemma":0.00066494365,"threshold_uncertainty_score":0.00564903},"labels":[],"label_agreement":null},{"id":"W3212006298","doi":"10.1109/jstars.2021.3127728","title":"Identifying Building Rooftops in Hyperspectral Imagery Using CNN With Pure Pixel Index","year":2021,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Major International Joint Research Programme; Chinese Academy of Sciences; National Natural Science Foundation of China","keywords":"Hyperspectral imaging; Artificial intelligence; Computer science; Convolutional neural network; Pattern recognition (psychology); Support vector machine; Pixel; Feature extraction; Deep learning; Classifier (UML); Remote sensing; Kernel (algebra); Computer vision; Mathematics; Geography","score_opus":0.030373942082022865,"score_gpt":0.24117760993739296,"score_spread":0.21080366785537008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212006298","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48576793,0.0008165604,0.49755394,0.00031055536,0.00011122958,0.00010127791,0.0012381948,0.004012193,0.01008817],"genre_scores_gemma":[0.8385833,0.00047257656,0.1543714,0.00022013989,0.000032741194,0.00007105007,0.0022963595,0.00008731918,0.0038650166],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99983454,0.000011196924,0.0000063170805,0.000054454482,0.00005582484,0.000037628724],"domain_scores_gemma":[0.9998561,0.000023491462,0.000031647596,0.00002642244,0.000052496554,0.000009742843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002638592,0.0008051205,0.00031006846,0.00078441476,0.0001785074,0.0004930193,0.00058335107,0.0003955914,0.0010368717],"category_scores_gemma":[0.0004905889,0.00027088303,0.00052935915,0.0005987167,0.00031605127,0.0008704686,0.00055039173,0.00039932388,0.00042417823],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041132036,0.00025895415,0.019676957,0.00026749165,0.00023804876,0.00036554207,0.00014361339,0.23965003,0.18030673,0.002209935,0.005423607,0.5510478],"study_design_scores_gemma":[0.0000061926335,0.000042276697,0.007992066,0.000016423444,0.00003545523,0.00008207777,0.0000542111,0.95175225,0.038128752,0.0007276176,0.0011477305,0.000015008422],"about_ca_topic_score_codex":0.008024206,"about_ca_topic_score_gemma":0.0155891115,"teacher_disagreement_score":0.008024206,"about_ca_system_score_codex":0.00046809262,"about_ca_system_score_gemma":0.00036630975,"threshold_uncertainty_score":0.01595503},"labels":[],"label_agreement":null},{"id":"W3212886268","doi":"10.1109/lgrs.2021.3127964","title":"Change Detection Approach for SAR Imagery Based on Arc-Tangential Difference Image and <i>k</i> -Means++","year":2021,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Filter (signal processing); Cluster analysis; Background subtraction; Synthetic aperture radar; Artificial intelligence; Gaussian; Mathematics; Logarithm; Histogram; Pattern recognition (psychology); Computer science; Image (mathematics); Computer vision; Pixel; Mathematical analysis; Physics","score_opus":0.02337900442998098,"score_gpt":0.21867176000906927,"score_spread":0.1952927555790883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212886268","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021262871,0.00034266184,0.9754871,0.00009425539,0.000092881295,0.00008297805,0.000103189384,0.0009731254,0.0015609703],"genre_scores_gemma":[0.18766226,0.0004084908,0.8064101,0.00013539514,0.0001186625,0.00019903848,0.00071588176,0.0001839059,0.004166328],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99940217,0.000060477003,0.000044121825,0.00023772847,0.0002061941,0.000049359653],"domain_scores_gemma":[0.99968994,0.000060354556,0.000052481122,0.000049680024,0.00013068639,0.000016888469],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045167128,0.00068035035,0.00081274525,0.0019014123,0.00051830296,0.0010873238,0.0011302899,0.0006405275,0.001516797],"category_scores_gemma":[0.00087700604,0.00038768895,0.0011814805,0.0017282063,0.00046269112,0.000964987,0.00055984646,0.0007080977,0.0009458394],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019995363,0.00018147862,0.0029159694,0.00025714375,0.00017560464,0.00017864803,0.00021482726,0.04727351,0.063270696,0.008096058,0.003631572,0.8736046],"study_design_scores_gemma":[0.0000259381,0.00017805121,0.00737281,0.000020323723,0.00008993548,0.00050553726,0.00010803976,0.9226286,0.05032614,0.0055268663,0.0131256245,0.00009221445],"about_ca_topic_score_codex":0.0027906427,"about_ca_topic_score_gemma":0.0044816653,"teacher_disagreement_score":0.0027906427,"about_ca_system_score_codex":0.0006609352,"about_ca_system_score_gemma":0.0007508411,"threshold_uncertainty_score":0.005548775},"labels":[],"label_agreement":null},{"id":"W3213292025","doi":"10.1364/hise.2021.htu2c.4","title":"Application of Spectral-Spatial Classification on Hyperspectral Imagery to Map Coastal Endmembers in Manicouagan Peninsula","year":2021,"lang":"en","type":"article","venue":"OSA Optical Sensors and Sensing Congress 2021 (AIS, FTS, HISE, SENSORS, ES)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; Université du Québec à Rimouski","funders":"","keywords":"Hyperspectral imaging; Probabilistic logic; Peninsula; Pixel; Remote sensing; Computer science; Artificial intelligence; Regularization (linguistics); Pattern recognition (psychology); Bayesian probability; Contextual image classification; Geology; Cartography; Geography; Image (mathematics)","score_opus":0.011178598958162662,"score_gpt":0.22948252484731596,"score_spread":0.2183039258891533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3213292025","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9764797,0.00016461372,0.01991959,0.00014038553,0.000011467383,0.00004295594,0.00032618054,0.000134017,0.0027810205],"genre_scores_gemma":[0.9859029,0.000053807875,0.01281268,0.00001161526,0.0000036877839,0.000012710866,0.00030902404,0.0000063720836,0.00088725536],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9999145,0.000014452054,0.000002574386,0.000027826209,0.000022172804,0.000018358898],"domain_scores_gemma":[0.9999225,0.000010122587,0.000008655509,0.000008112144,0.00004239214,0.0000081183825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023459725,0.0003112603,0.00009897277,0.00063975423,0.00028797454,0.00033428593,0.00023250763,0.00014638061,0.00029227286],"category_scores_gemma":[0.00023371674,0.00008767539,0.0001322726,0.00047612222,0.00021873036,0.00010490268,0.00026221256,0.00011421275,0.000081147125],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003269262,0.00019852255,0.29372063,0.00014495399,0.00016674938,0.00039386417,0.00053664256,0.17096573,0.11180425,0.0019622326,0.0024748258,0.4173047],"study_design_scores_gemma":[0.00001179372,0.00004941453,0.36188293,0.000018689076,0.00004324113,0.000088245724,0.0005938748,0.61689526,0.017695611,0.0004088531,0.002287987,0.000024017512],"about_ca_topic_score_codex":0.13528022,"about_ca_topic_score_gemma":0.27788374,"teacher_disagreement_score":0.86471975,"about_ca_system_score_codex":0.0006750022,"about_ca_system_score_gemma":0.0009993721,"threshold_uncertainty_score":0.26898563},"labels":[],"label_agreement":null},{"id":"W3213677683","doi":"10.1364/hise.2021.hth4h.2","title":"Hyperspectral image classification with minimum noise fraction, 2D spatial filtering and SVM","year":2021,"lang":"en","type":"article","venue":"OSA Optical Sensors and Sensing Congress 2021 (AIS, FTS, HISE, SENSORS, ES)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Canadian Space Agency","funders":"","keywords":"Hyperspectral imaging; Support vector machine; Cube (algebra); Data cube; Artificial intelligence; Pattern recognition (psychology); Noise (video); Computer science; Curse of dimensionality; Fraction (chemistry); Image (mathematics); Spatial analysis; Median filter; Computer vision; Mathematics; Data mining; Image processing; Statistics","score_opus":0.011269933330486735,"score_gpt":0.21856670909647843,"score_spread":0.2072967757659917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3213677683","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022592373,0.00043052743,0.9745394,0.00012260785,0.00008988507,0.00005182545,0.000106599146,0.0011297152,0.00093698583],"genre_scores_gemma":[0.30069688,0.0005976938,0.6931734,0.00017930164,0.00018614714,0.00019848453,0.0009427861,0.00013222777,0.0038930583],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990509,0.000109567605,0.00007777944,0.00020654057,0.00046402722,0.00009116243],"domain_scores_gemma":[0.999553,0.000104709885,0.000073877,0.00006196542,0.00018062748,0.00002574016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000630142,0.0008803059,0.0012618263,0.0015700669,0.00048084327,0.0010069665,0.0009080924,0.001032591,0.0012071226],"category_scores_gemma":[0.0011318447,0.00037099922,0.0011957216,0.0016179674,0.00041009742,0.0014685316,0.00080536766,0.00077096844,0.00077815156],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026004683,0.00025072866,0.0023704001,0.00018256683,0.00013563113,0.00008971743,0.00007007273,0.04185815,0.066122465,0.0025764888,0.0038456614,0.8822381],"study_design_scores_gemma":[0.000010328441,0.00007363437,0.0019841618,0.000009233604,0.00003090218,0.00011361497,0.0000213042,0.9782883,0.016540453,0.0011215722,0.00178477,0.000021637463],"about_ca_topic_score_codex":0.0027560333,"about_ca_topic_score_gemma":0.0024815071,"teacher_disagreement_score":0.0027560333,"about_ca_system_score_codex":0.00041812853,"about_ca_system_score_gemma":0.00064561446,"threshold_uncertainty_score":0.005480051},"labels":[],"label_agreement":null},{"id":"W3214387023","doi":"10.1109/taes.2021.3127143","title":"An Image-Based Radar Detector Approaching Optimal Likelihood Ratio Detector","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Aerospace and Electronic Systems","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Natural Science Foundation of China","keywords":"Detector; Constant false alarm rate; False alarm; Statistical power; Noise power; Gaussian noise; Likelihood-ratio test; Algorithm; Noise (video); Radar; Signal-to-noise ratio (imaging); Mathematics; Computer science; Power (physics); Statistics; Artificial intelligence; Physics; Optics; Image (mathematics); Telecommunications","score_opus":0.008472984045454001,"score_gpt":0.2117029521930433,"score_spread":0.2032299681475893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214387023","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008143016,0.00034149212,0.98969424,0.00008278845,0.00004583735,0.000020346137,0.00002152617,0.00030532439,0.00134543],"genre_scores_gemma":[0.31594336,0.00063601986,0.67913467,0.00040050485,0.00018182107,0.00009410101,0.00018609254,0.00008799984,0.0033354883],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988494,0.00025585075,0.000043066702,0.0002725502,0.00048179325,0.00009733864],"domain_scores_gemma":[0.99878687,0.00048891525,0.00008978974,0.00012221107,0.00045799295,0.00005420189],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010634713,0.000531185,0.001078438,0.00082234794,0.0002903039,0.0009129786,0.0009896919,0.0011096923,0.0010656442],"category_scores_gemma":[0.0035638092,0.00033033,0.0005533593,0.0006928873,0.0006375633,0.001374756,0.001106933,0.00088761334,0.00084300735],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006335053,0.00018836257,0.005240558,0.00030055674,0.00014530093,0.00051703834,0.0001770073,0.09867166,0.16365711,0.0781583,0.0059715244,0.64633906],"study_design_scores_gemma":[0.000027203134,0.00013027801,0.0006208688,0.000011212051,0.000029592575,0.0008859859,0.000018168263,0.9573296,0.028749844,0.007251334,0.004903808,0.000042095406],"about_ca_topic_score_codex":0.000562479,"about_ca_topic_score_gemma":0.00044661967,"teacher_disagreement_score":0.0011096923,"about_ca_system_score_codex":0.00045154023,"about_ca_system_score_gemma":0.00073948625,"threshold_uncertainty_score":0.0056242347},"labels":[],"label_agreement":null},{"id":"W3215578321","doi":"10.18280/ts.380529","title":"Design and Application of a Slow Feature Algorithm Coupling Visual Selectivity and Multiple Long Short-Term Memory Networks","year":2021,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Science and Technology Infrastructure Program","keywords":"Basis (linear algebra); Basis function; Algorithm; Computer science; Pattern recognition (psychology); Artificial intelligence; Feature (linguistics); Feature vector; Term (time); Pruning; Polynomial; Mathematics","score_opus":0.011303989679329681,"score_gpt":0.22735919851730407,"score_spread":0.21605520883797438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215578321","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025984006,0.00029362304,0.9687724,0.00017441907,0.0000928034,0.00015404061,0.00006471522,0.0027421296,0.0017218322],"genre_scores_gemma":[0.42504403,0.0002718973,0.57020235,0.00031813062,0.000081371145,0.0004789682,0.00031786226,0.00018251134,0.0031028052],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995914,0.000040095776,0.00003183431,0.00016402591,0.000115087576,0.00005754722],"domain_scores_gemma":[0.9995907,0.000087564134,0.000042233794,0.00006236603,0.00017778362,0.000039436643],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006874153,0.000950145,0.0008028689,0.0008020175,0.0005163823,0.00074140244,0.002018962,0.0011011988,0.0017339853],"category_scores_gemma":[0.0014076212,0.0004104927,0.0007135655,0.00066336314,0.00060033234,0.0018122974,0.00096731546,0.0011435552,0.0005787274],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025798977,0.00020626275,0.0018124094,0.00013859241,0.00015379746,0.00020656156,0.00009472784,0.19047952,0.054164737,0.011406723,0.003843815,0.7372349],"study_design_scores_gemma":[0.000024111427,0.00009228859,0.00024964445,0.0000054874477,0.000027393864,0.000061268154,0.00000998632,0.98606503,0.0097788,0.0024725245,0.0012031744,0.000010387359],"about_ca_topic_score_codex":0.0042659245,"about_ca_topic_score_gemma":0.004129928,"teacher_disagreement_score":0.0042659245,"about_ca_system_score_codex":0.00087813026,"about_ca_system_score_gemma":0.0015031126,"threshold_uncertainty_score":0.008482218},"labels":[],"label_agreement":null},{"id":"W3217586766","doi":"10.3390/s21238083","title":"Deep Transfer Learning for Land Use and Land Cover Classification: A Comparative Study","year":2021,"lang":"en","type":"article","venue":"Sensors","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":186,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Transfer of learning; Computer science; Artificial intelligence; Convolutional neural network; Deep learning; Contextual image classification; Land cover; Remote sensing; Residual; Pattern recognition (psychology); Machine learning; Clipping (morphology); Artificial neural network; Land use; Image (mathematics); Geography; Algorithm; Engineering","score_opus":0.06235099648868551,"score_gpt":0.2757454833334606,"score_spread":0.2133944868447751,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3217586766","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8346177,0.018414287,0.12196851,0.0011017614,0.00045968167,0.00025009472,0.0016172209,0.0028557533,0.0187151],"genre_scores_gemma":[0.96767366,0.0017787354,0.023732644,0.00010151427,0.00008020184,0.000059936214,0.0024462347,0.000092166425,0.004035083],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922407,0.00020943882,0.00004970833,0.00015267763,0.00025414512,0.00010993444],"domain_scores_gemma":[0.998863,0.00052101637,0.00006291343,0.00015682398,0.0003302816,0.00006597504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024327035,0.0009830615,0.00072330254,0.0016832832,0.00030536085,0.0007737188,0.00093588856,0.0009380226,0.0018929753],"category_scores_gemma":[0.0031369063,0.00016504011,0.0006071606,0.0015451808,0.00037064144,0.0016623812,0.0008541486,0.00081481686,0.0007194226],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010951887,0.000819441,0.018105382,0.0005463271,0.00044362817,0.00017056626,0.00012195914,0.23830612,0.004934061,0.0020501406,0.008392648,0.72501457],"study_design_scores_gemma":[0.000031417756,0.000301203,0.0120697925,0.00003629792,0.000083601655,0.00006279678,0.00012973174,0.9783277,0.0046346406,0.0014919669,0.0028085879,0.000022256098],"about_ca_topic_score_codex":0.01179151,"about_ca_topic_score_gemma":0.0071042953,"teacher_disagreement_score":0.01179151,"about_ca_system_score_codex":0.0009817072,"about_ca_system_score_gemma":0.00066977285,"threshold_uncertainty_score":0.023445725},"labels":[],"label_agreement":null},{"id":"W33961824","doi":"10.1016/j.envres.2021.111205","title":"Change Detection Methods for Hyperspectral Imagery","year":2007,"lang":"en","type":"article","venue":"Environmental Research","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Canadian Institutes of Health Research","keywords":"Hyperspectral imaging; Remote sensing; Change detection; Artificial intelligence; Computer science; Computer vision; Environmental science; Geography","score_opus":0.11978323510161594,"score_gpt":0.40825681106739,"score_spread":0.28847357596577405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W33961824","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007597849,0.0032580993,0.96741253,0.00053864124,0.00045031027,0.0005655705,0.006492732,0.0041665067,0.009517784],"genre_scores_gemma":[0.10945168,0.0036269901,0.86759317,0.00045161246,0.00025933798,0.0020427995,0.008831222,0.0011608442,0.006582272],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981198,0.00052282016,0.00018424,0.0004513969,0.00062651816,0.00009526921],"domain_scores_gemma":[0.9967194,0.001842232,0.00038599098,0.00033432955,0.0006726748,0.000045390854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031829495,0.001092217,0.00085313554,0.0053714495,0.0005251657,0.0023671663,0.0015273498,0.001161359,0.014901968],"category_scores_gemma":[0.01363304,0.00051753456,0.002307863,0.0049267984,0.0005304276,0.0021101998,0.001695477,0.0015758901,0.005575627],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024487593,0.0001662577,0.0068628844,0.0026899094,0.00059502554,0.00019714709,0.00048229948,0.049279302,0.0059419456,0.026232969,0.036128078,0.8711793],"study_design_scores_gemma":[0.000111594156,0.00016399055,0.018954279,0.0009549192,0.00025477324,0.0005725198,0.00092687504,0.6810909,0.011901703,0.09638765,0.18846716,0.00021369134],"about_ca_topic_score_codex":0.0068915826,"about_ca_topic_score_gemma":0.0061683455,"teacher_disagreement_score":0.014901968,"about_ca_system_score_codex":0.0009081054,"about_ca_system_score_gemma":0.0011090746,"threshold_uncertainty_score":0.049852014},"labels":[],"label_agreement":null},{"id":"W4200129293","doi":"10.1016/j.mex.2021.101601","title":"Water column compensation workflow for hyperspectral imaging data","year":2021,"lang":"en","type":"article","venue":"MethodsX","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"National Research Council Canada; McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Fonds Québécois de la Recherche sur la Nature et les Technologies; Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Hyperspectral imaging; Workflow; Principal component analysis; Curse of dimensionality; Invariant (physics); Computer science; Column (typography); Data mining; Water column; Pattern recognition (psychology); Artificial intelligence; Dimensionality reduction; Remote sensing; Mathematics; Geology; Database","score_opus":0.08549218817000291,"score_gpt":0.326927112343925,"score_spread":0.2414349241739221,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200129293","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011407872,0.00017816463,0.8117071,0.00045536453,0.00016821829,0.0011080744,0.02490965,0.14031811,0.009747461],"genre_scores_gemma":[0.04747736,0.0002539647,0.8631672,0.00065482274,0.00006455729,0.002003038,0.061015792,0.013863424,0.011499809],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99903774,0.00005468545,0.000088992434,0.00031974015,0.00039179495,0.000107052365],"domain_scores_gemma":[0.9984334,0.00021444661,0.00009826596,0.0003536325,0.000799882,0.000100392615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015075324,0.0013921652,0.00075793476,0.0016215723,0.0010100309,0.001717082,0.0014472909,0.0006062773,0.01725605],"category_scores_gemma":[0.0027649018,0.00072894286,0.0014066992,0.0011341225,0.00046684852,0.0009689965,0.0015816371,0.0015769002,0.016636519],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00077479344,0.00034625767,0.011459586,0.0011380464,0.00024004864,0.00122316,0.0014886826,0.024526538,0.19099422,0.012416359,0.23551738,0.519875],"study_design_scores_gemma":[0.00024609696,0.00016565793,0.021510046,0.00024397651,0.00008669823,0.0009316672,0.0007306752,0.22222592,0.3053025,0.029248994,0.41888088,0.0004268902],"about_ca_topic_score_codex":0.008136484,"about_ca_topic_score_gemma":0.011430737,"teacher_disagreement_score":0.01725605,"about_ca_system_score_codex":0.0012191045,"about_ca_system_score_gemma":0.002331567,"threshold_uncertainty_score":0.057727218},"labels":[],"label_agreement":null},{"id":"W4200631461","doi":"","title":"Hierarchical Markov Random Fields for High Resolution Land Cover Classification of Multisensor and Multiresolution Image Time Series","year":2021,"lang":"en","type":"book-chapter","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Series (stratigraphy); Land cover; Markov chain; Cover (algebra); Pattern recognition (psychology); Markov random field; Artificial intelligence; Time series; Computer science; Mathematics; Geography; Remote sensing; Image (mathematics); Statistics; Geology; Land use; Image segmentation; Engineering","score_opus":0.0111932540082127,"score_gpt":0.2040978561599915,"score_spread":0.1929046021517788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200631461","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006670088,0.0019644434,0.98928714,0.00021433111,0.00008369524,0.000023042216,0.00028112772,0.0005312659,0.0009448656],"genre_scores_gemma":[0.34020934,0.0054203407,0.6347358,0.00028369317,0.00053404196,0.00024427802,0.002709257,0.00042905484,0.0154341655],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99973506,0.00009566586,0.000017424307,0.000054750395,0.000070940034,0.000026187408],"domain_scores_gemma":[0.99879396,0.0009460656,0.00006323751,0.00009299542,0.000079683574,0.000024119965],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009947361,0.00043994715,0.0007627859,0.0007349335,0.00026455143,0.0005474701,0.0010450333,0.00085625995,0.002897435],"category_scores_gemma":[0.0021904774,0.00048796853,0.001086188,0.0009985366,0.00042081022,0.0009388238,0.00055879354,0.0012837241,0.0009211382],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007104297,0.00006176913,0.0006204772,0.00017900785,0.000081093865,0.000066097746,0.00006727162,0.64151514,0.005003989,0.048304074,0.006356883,0.29767308],"study_design_scores_gemma":[0.0000017661448,0.0000073293318,0.00030843442,0.000006026799,0.0000045684706,0.00000863039,0.0000032991052,0.9817094,0.00025814763,0.016990423,0.0006964585,0.0000054320994],"about_ca_topic_score_codex":0.010154549,"about_ca_topic_score_gemma":0.013533327,"teacher_disagreement_score":0.010154549,"about_ca_system_score_codex":0.0009058465,"about_ca_system_score_gemma":0.00046345254,"threshold_uncertainty_score":0.020190895},"labels":[],"label_agreement":null},{"id":"W4206799607","doi":"10.3390/rs14030438","title":"TCD-Net: A Novel Deep Learning Framework for Fully Polarimetric Change Detection Using Transfer Learning","year":2022,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre For Cold Ocean Resources Engineering; Memorial University of Newfoundland","funders":"","keywords":"Computer science; Synthetic aperture radar; Artificial intelligence; Change detection; Residual; Transfer of learning; Remote sensing; Artificial neural network; Block (permutation group theory); Pattern recognition (psychology); Fuzzy logic; Radar; Scale (ratio); Algorithm; Geography; Mathematics; Cartography","score_opus":0.045046589096840964,"score_gpt":0.2554952642508691,"score_spread":0.21044867515402815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206799607","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026586408,0.0005264264,0.9658473,0.00020494423,0.00009746318,0.00006746758,0.00046898064,0.003945101,0.0022559955],"genre_scores_gemma":[0.60004205,0.0006748454,0.38088968,0.0005949901,0.0001322081,0.000298985,0.0038829283,0.00032650778,0.013157765],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99985254,0.000018600196,0.000006896698,0.0000485331,0.000042404336,0.00003092684],"domain_scores_gemma":[0.9998447,0.00004043923,0.000020941396,0.000020509166,0.00005401869,0.000019340769],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000376189,0.0010164217,0.00055108755,0.00064936484,0.00027090602,0.000572787,0.0018433242,0.00078195974,0.0021299315],"category_scores_gemma":[0.00060541433,0.0003318283,0.00059246086,0.0006608952,0.00038709087,0.0010232837,0.0009676436,0.0011220418,0.0006798866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023673297,0.00025881507,0.0023250354,0.00011094203,0.00016660456,0.0001580871,0.000047959096,0.43339896,0.0117670195,0.005320636,0.010904532,0.5353047],"study_design_scores_gemma":[0.000004439507,0.000021322521,0.00016985221,0.0000030541191,0.000006358051,0.000013007895,0.0000037932145,0.9961026,0.0014656006,0.0015045016,0.00070132065,0.0000042253937],"about_ca_topic_score_codex":0.008351184,"about_ca_topic_score_gemma":0.011186742,"teacher_disagreement_score":0.008351184,"about_ca_system_score_codex":0.00078238087,"about_ca_system_score_gemma":0.0009304256,"threshold_uncertainty_score":0.016605139},"labels":[],"label_agreement":null},{"id":"W4207037158","doi":"10.3390/rs14030530","title":"DA-IMRN: Dual-Attention-Guided Interactive Multi-Scale Residual Network for Hyperspectral Image Classification","year":2022,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Fundamental Research Funds for the Central Universities","keywords":"Hyperspectral imaging; Computer science; Artificial intelligence; Residual; Pattern recognition (psychology); Feature (linguistics); Benchmark (surveying); Feature extraction; Scale (ratio); Spatial analysis; Feature learning; Pixel; Remote sensing; Geology; Algorithm; Cartography; Geography","score_opus":0.04051239353254007,"score_gpt":0.28633811164289125,"score_spread":0.24582571811035117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4207037158","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06535463,0.0015320398,0.9239904,0.00036906617,0.00012545455,0.00008560276,0.00035398823,0.004813955,0.0033747687],"genre_scores_gemma":[0.7366153,0.0006869306,0.24985173,0.0006315134,0.00013775623,0.000180674,0.0019393875,0.0003364928,0.009620215],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996008,0.0000708477,0.0000149879115,0.00014104736,0.00009477956,0.00007755509],"domain_scores_gemma":[0.9996867,0.00009464733,0.00004430028,0.000055025852,0.00009019382,0.000029115852],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069195416,0.0013386549,0.0009089135,0.0006339306,0.00031254283,0.0005302391,0.0021626737,0.00087220635,0.0017742114],"category_scores_gemma":[0.001264337,0.00035747077,0.0009156282,0.000673069,0.0004574969,0.0014737479,0.0012376098,0.0012771733,0.000638434],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038311395,0.0004343144,0.0033441056,0.00023305122,0.0002477108,0.00022053673,0.00016191028,0.25362766,0.04291194,0.0049492484,0.013143742,0.6803427],"study_design_scores_gemma":[0.000011618,0.000050397226,0.00043957893,0.0000075771986,0.000027553397,0.000037465685,0.00001314783,0.9926138,0.004381234,0.0015608738,0.0008465925,0.000010040838],"about_ca_topic_score_codex":0.0074090636,"about_ca_topic_score_gemma":0.011415465,"teacher_disagreement_score":0.0074090636,"about_ca_system_score_codex":0.0006298354,"about_ca_system_score_gemma":0.00067918916,"threshold_uncertainty_score":0.014731884},"labels":[],"label_agreement":null},{"id":"W4210348940","doi":"10.3390/electronics11030431","title":"Change Detection in Remote Sensing Image Data Comparing Algebraic and Machine Learning Methods","year":2022,"lang":"en","type":"article","venue":"Electronics","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":131,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Change detection; Computer science; Pixel; Artificial intelligence; Remote sensing; Decision tree; Tree (set theory); Computation; Computer vision; Algorithm; Mathematics; Geography","score_opus":0.059105308973740424,"score_gpt":0.3009998463596283,"score_spread":0.24189453738588787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210348940","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3082298,0.0012921992,0.68443686,0.00021026014,0.00013949545,0.00025041983,0.0002681713,0.0013593293,0.003813439],"genre_scores_gemma":[0.7347125,0.00047988462,0.2630069,0.000042357402,0.00006263374,0.00012674053,0.0004851477,0.00007812816,0.0010056876],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971488,0.0008835583,0.00023124336,0.000495537,0.0011083445,0.00013255618],"domain_scores_gemma":[0.9936708,0.003749291,0.00055513426,0.00045659617,0.0014950081,0.00007319102],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036644377,0.0005399982,0.000667657,0.004360736,0.0003612391,0.0013578513,0.0005922678,0.0005171186,0.0010557988],"category_scores_gemma":[0.010728365,0.00020388173,0.00059608556,0.0034597078,0.0008348695,0.0018207724,0.0008531725,0.0005338689,0.0003280587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00083283905,0.00032973665,0.031113029,0.0007359258,0.0002954765,0.00022373251,0.0005461975,0.08063428,0.033744585,0.0073946835,0.0015264386,0.8426231],"study_design_scores_gemma":[0.00005150121,0.0005065175,0.048532687,0.00006483949,0.00013757408,0.00035029824,0.00058428355,0.89296085,0.04633397,0.0055684685,0.00481363,0.000095322874],"about_ca_topic_score_codex":0.0019787797,"about_ca_topic_score_gemma":0.0013587556,"teacher_disagreement_score":0.004360736,"about_ca_system_score_codex":0.00061750045,"about_ca_system_score_gemma":0.00043346098,"threshold_uncertainty_score":0.019379616},"labels":[],"label_agreement":null},{"id":"W4210987640","doi":"10.1109/tgrs.2022.3151004","title":"BCUN: Bayesian Fully Convolutional Neural Network for Hyperspectral Spectral Unmixing","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hyperspectral imaging; Artificial intelligence; Computer science; Pattern recognition (psychology); Convolutional neural network; Context (archaeology); Abundance estimation; Abundance (ecology)","score_opus":0.01502962300378783,"score_gpt":0.22335993069752327,"score_spread":0.20833030769373545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210987640","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013108655,0.0012201056,0.97639513,0.00042220487,0.000117284326,0.000048262875,0.00047299743,0.0034231371,0.004792151],"genre_scores_gemma":[0.49908787,0.0020549358,0.4662669,0.0009001976,0.00014287484,0.00026002165,0.00345389,0.0005178239,0.027315512],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997533,0.00003269352,0.000009785269,0.000060541533,0.000099135636,0.000044485878],"domain_scores_gemma":[0.99981755,0.000044240212,0.00002863424,0.000023374641,0.000068976246,0.000017198634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004561404,0.0009366888,0.00045466315,0.00040564223,0.0003143987,0.0005151262,0.0014288635,0.00091763254,0.0026033921],"category_scores_gemma":[0.0010117558,0.00041162295,0.00039790478,0.000557622,0.00038423968,0.0008290886,0.0009774328,0.0013252503,0.000888783],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021882009,0.00013121532,0.0010390797,0.00014474556,0.00013343594,0.00010898225,0.00005992969,0.5205075,0.016019687,0.019557195,0.015297703,0.42678168],"study_design_scores_gemma":[0.0000026566656,0.000008162794,0.00013578862,0.000005937783,0.0000049094065,0.00001167813,0.0000022433644,0.9947849,0.0016880129,0.0019532267,0.0013968577,0.000005666737],"about_ca_topic_score_codex":0.026968654,"about_ca_topic_score_gemma":0.03886161,"teacher_disagreement_score":0.026968654,"about_ca_system_score_codex":0.0012233055,"about_ca_system_score_gemma":0.0013519053,"threshold_uncertainty_score":0.05362338},"labels":[],"label_agreement":null},{"id":"W4213027311","doi":"10.23919/oceans44145.2021.9705752","title":"Classifying Glare Intensity in Airborne Imagery Acquired during Marine Megafauna Survey","year":2021,"lang":"en","type":"article","venue":"OCEANS 2021: San Diego – Porto","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Fisheries and Oceans Canada; National Research Council Canada; University of New Brunswick","funders":"","keywords":"Megafauna; Remote sensing; GLARE; Environmental science; Intensity (physics); Computer science; Geology; Optics; Materials science; Physics","score_opus":0.020084380588540944,"score_gpt":0.22920188104535885,"score_spread":0.2091175004568179,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213027311","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9592845,0.00012209984,0.0377448,0.000041757623,0.000021358686,0.00005007146,0.00033477333,0.00056797866,0.0018325739],"genre_scores_gemma":[0.9710878,0.00010445638,0.027359642,0.000021570473,0.000013608,0.000018309032,0.00077713834,0.000016421835,0.0006008694],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998852,0.000011567954,0.0000074852474,0.000023975712,0.000042840205,0.000028898754],"domain_scores_gemma":[0.9997404,0.00006713352,0.000047712885,0.000022292525,0.00010218422,0.000020330837],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021826912,0.00021129948,0.00018380507,0.0014534994,0.00015787777,0.00031732357,0.00018490935,0.00022974316,0.0005276177],"category_scores_gemma":[0.0006666636,0.000078182944,0.00020449386,0.00066755747,0.00010196278,0.00023080847,0.00014336249,0.00013374991,0.00027607367],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032310895,0.00018933846,0.383046,0.00013690679,0.000114030474,0.00021189853,0.00029417122,0.017190322,0.081620626,0.00025585716,0.0020903286,0.51452744],"study_design_scores_gemma":[0.00001698729,0.00023300156,0.76207453,0.00003586376,0.00007922521,0.00036985282,0.0005375139,0.20892696,0.025588071,0.00021937999,0.0018899362,0.000028597611],"about_ca_topic_score_codex":0.008207438,"about_ca_topic_score_gemma":0.015209833,"teacher_disagreement_score":0.008207438,"about_ca_system_score_codex":0.00014311404,"about_ca_system_score_gemma":0.0001469924,"threshold_uncertainty_score":0.016319335},"labels":[],"label_agreement":null},{"id":"W4213264000","doi":"10.3390/rs14040879","title":"ClassHyPer: ClassMix-Based Hybrid Perturbations for Deep Semi-Supervised Semantic Segmentation of Remote Sensing Imagery","year":2022,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Segmentation; Robustness (evolution); Artificial intelligence; Data mining; Machine learning","score_opus":0.020528482142238,"score_gpt":0.2406610819771091,"score_spread":0.2201325998348711,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213264000","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013258496,0.00015682958,0.98113406,0.0001216951,0.00005081936,0.0000774831,0.00010800401,0.0043187146,0.00077396247],"genre_scores_gemma":[0.39685652,0.0002124962,0.5940411,0.00052024773,0.000103899416,0.00033330815,0.0012927587,0.0012607484,0.0053789443],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992163,0.00016941277,0.000027027803,0.00030167497,0.00022085247,0.0000647297],"domain_scores_gemma":[0.9993488,0.00018696375,0.00007786929,0.00017324563,0.00015221079,0.000060804963],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001320723,0.0016926224,0.00094289216,0.0007305691,0.0005426466,0.0009449566,0.0024425758,0.0014362959,0.0020405157],"category_scores_gemma":[0.002451234,0.0006681058,0.0008927075,0.0005602078,0.0013076819,0.002355213,0.0027351568,0.0025444115,0.0010383065],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006321547,0.00027136723,0.001804484,0.00020957619,0.00017779174,0.00018084541,0.00033250827,0.40516484,0.056180384,0.013898968,0.008814281,0.51233286],"study_design_scores_gemma":[0.000008467644,0.000031288142,0.00012092075,0.0000043850864,0.0000051986417,0.000022927794,0.000011538377,0.9886204,0.006903851,0.0034134504,0.0008488428,0.000008703745],"about_ca_topic_score_codex":0.003435016,"about_ca_topic_score_gemma":0.005886887,"teacher_disagreement_score":0.003435016,"about_ca_system_score_codex":0.0010452888,"about_ca_system_score_gemma":0.001175827,"threshold_uncertainty_score":0.007584095},"labels":[],"label_agreement":null},{"id":"W42142495","doi":"10.1007/978-3-642-21596-4_31","title":"Multiple Classifier System for Urban Area’s Extraction from High Resolution Remote Sensing Imagery","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Classifier (UML); Computer science; Artificial intelligence; Particle swarm optimization; Pattern recognition (psychology); Land cover; Thematic map; Feature extraction; Machine learning; Geography; Land use; Engineering; Cartography","score_opus":0.03281128768504257,"score_gpt":0.22638569657220373,"score_spread":0.19357440888716115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W42142495","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.086818285,0.002007946,0.89457333,0.00021911121,0.00052943407,0.0002123976,0.0013735114,0.008428828,0.005837229],"genre_scores_gemma":[0.3719998,0.0012942094,0.6053812,0.00024810113,0.00027088405,0.00027829848,0.0035413885,0.00026627345,0.016719831],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99963546,0.000022139468,0.00002349257,0.0001234446,0.00014109598,0.000054387907],"domain_scores_gemma":[0.9997111,0.000046845227,0.000019705722,0.00003385875,0.00016940084,0.000019172769],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046678112,0.00062848895,0.00094247994,0.0016330618,0.00057195645,0.0007137416,0.0009838387,0.00089129276,0.003526584],"category_scores_gemma":[0.00057189213,0.00031663215,0.00064019585,0.0011752644,0.00012399092,0.00083663105,0.00057776563,0.00056638697,0.0027236224],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023349097,0.00013676038,0.0023517322,0.00012701382,0.000070874885,0.00016833722,0.000061969986,0.004832003,0.09196081,0.0006692379,0.008111974,0.89127594],"study_design_scores_gemma":[0.000038617218,0.00029344537,0.022430126,0.000056541314,0.0002882602,0.000798995,0.00018088147,0.82469493,0.12582046,0.0020939677,0.023204425,0.00009935535],"about_ca_topic_score_codex":0.0035943438,"about_ca_topic_score_gemma":0.0065025412,"teacher_disagreement_score":0.0035943438,"about_ca_system_score_codex":0.0003764801,"about_ca_system_score_gemma":0.00049813784,"threshold_uncertainty_score":0.011797667},"labels":[],"label_agreement":null},{"id":"W4214647988","doi":"10.3390/s22051817","title":"Extending Effective Dynamic Range of Hyperspectral Line Cameras for Short Wave Infrared Imaging","year":2022,"lang":"en","type":"article","venue":"Sensors","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Hyperspectral imaging; Artificial intelligence; Computer science; Principal component analysis; Computer vision; Sorting; Support vector machine; Data set; Dynamic range; High dynamic range; Remote sensing; Pattern recognition (psychology); Algorithm; Geology","score_opus":0.01144463708852683,"score_gpt":0.24229891369728643,"score_spread":0.2308542766087596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214647988","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16065136,0.0031256932,0.8285756,0.00029639364,0.00011121262,0.00009951177,0.000114607494,0.0012902004,0.005735517],"genre_scores_gemma":[0.5348005,0.0016412555,0.45866662,0.00036935203,0.00010629581,0.00010909616,0.00023344602,0.000117601405,0.0039557805],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99936765,0.00011016152,0.000027314567,0.00015475141,0.0002937447,0.000046358215],"domain_scores_gemma":[0.99929166,0.00025228254,0.00011752676,0.00010003632,0.00021226764,0.000026139473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005424351,0.0005905694,0.00028357687,0.00070769497,0.00018260465,0.0004897663,0.0005825884,0.00060102023,0.001609531],"category_scores_gemma":[0.00078296,0.00029444855,0.00037811956,0.0004102918,0.00031570438,0.0012074974,0.00053984637,0.0006697949,0.00070524967],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014594829,0.00011216334,0.0016090816,0.0002727422,0.000043459208,0.000114713985,0.0001277113,0.0046849526,0.7494456,0.0011382377,0.00086991355,0.24143542],"study_design_scores_gemma":[0.0000214276,0.00035746468,0.0070458828,0.000036814923,0.00006160919,0.0010226793,0.00009992113,0.12332154,0.8520293,0.00084915146,0.015076653,0.00007746162],"about_ca_topic_score_codex":0.00027164497,"about_ca_topic_score_gemma":0.00069976883,"teacher_disagreement_score":0.001609531,"about_ca_system_score_codex":0.00024969107,"about_ca_system_score_gemma":0.00016744697,"threshold_uncertainty_score":0.005384445},"labels":[],"label_agreement":null},{"id":"W4220842188","doi":"10.18280/ria.360117","title":"Remote Sensing Image Classification Using CNN-LSTM Model","year":2022,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Contextual image classification; Image (mathematics); Curse of dimensionality; Pattern recognition (psychology); Remote sensing; Deep learning; Geography","score_opus":0.07790132935591941,"score_gpt":0.2827085985862119,"score_spread":0.20480726923029247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220842188","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17544639,0.0024267903,0.7951239,0.0012443356,0.0008523557,0.00020037542,0.0013589595,0.008228522,0.015118372],"genre_scores_gemma":[0.89235765,0.0009644338,0.090609424,0.00046371142,0.00016326712,0.0001414507,0.0021060049,0.00012190185,0.013072143],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999879,0.000008054039,0.0000069325756,0.00004568088,0.000030389136,0.000029974544],"domain_scores_gemma":[0.99989843,0.000016971404,0.000014757728,0.000012019732,0.00004931357,0.000008440533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017228482,0.00086825684,0.0004504897,0.00046003543,0.00020224086,0.0004831218,0.0008471261,0.000697954,0.0024382016],"category_scores_gemma":[0.00043763634,0.00024007566,0.00068728306,0.0005284713,0.00018016383,0.00086716755,0.00037181214,0.00076495763,0.0009795331],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003250672,0.00028142688,0.0031821474,0.00023803278,0.00016082758,0.00033817213,0.00008344078,0.37008017,0.061639816,0.0032640377,0.012108413,0.5482984],"study_design_scores_gemma":[0.00000366525,0.000027315073,0.00041706476,0.0000061272895,0.000013612784,0.000028814142,0.000006872797,0.992998,0.0051840805,0.0007080661,0.00060029986,0.0000060142634],"about_ca_topic_score_codex":0.010255831,"about_ca_topic_score_gemma":0.00813346,"teacher_disagreement_score":0.010255831,"about_ca_system_score_codex":0.0005761536,"about_ca_system_score_gemma":0.00048911315,"threshold_uncertainty_score":0.020392299},"labels":[],"label_agreement":null},{"id":"W4221151155","doi":"10.1109/tgrs.2024.3357589","title":"Hyperspectral Pixel Unmixing With Latent Dirichlet Variational Autoencoder","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Endmember; Hyperspectral imaging; Pixel; Autoencoder; Pattern recognition (psychology); Dirichlet distribution; Artificial intelligence; Computer science; Remote sensing; Abundance estimation; Mixing (physics); Mathematics; Geography; Artificial neural network; Physics; Abundance (ecology)","score_opus":0.012642039298875543,"score_gpt":0.21892778431409643,"score_spread":0.2062857450152209,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221151155","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029701102,0.00018138863,0.99500245,0.00011139438,0.000031459684,0.000028997141,0.00013649769,0.00078350544,0.00075419014],"genre_scores_gemma":[0.13903911,0.00035286738,0.85026824,0.00032028582,0.00011645308,0.00025896038,0.0017812835,0.0006255711,0.007237197],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99935204,0.00017853641,0.00002866628,0.00019960378,0.00018711436,0.000053972926],"domain_scores_gemma":[0.9995241,0.0002103666,0.000043936063,0.000098194854,0.00009932988,0.00002399324],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011406613,0.0013571545,0.0009967468,0.0006584925,0.0003857511,0.0009605143,0.0020471127,0.0013808189,0.002210325],"category_scores_gemma":[0.002056284,0.001003164,0.0016790944,0.0007484497,0.00092241616,0.0014916635,0.0016657336,0.0033231007,0.0011930629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012399978,0.00009176872,0.00068128965,0.00014985284,0.00020893368,0.00009191859,0.00016066333,0.737114,0.011806533,0.021281512,0.005818863,0.22247066],"study_design_scores_gemma":[0.000004212426,0.0000053409653,0.0000492932,0.0000044005033,0.000004307545,0.000011681316,0.00000421141,0.9933449,0.0015626247,0.004044649,0.00095875846,0.000005715949],"about_ca_topic_score_codex":0.006880763,"about_ca_topic_score_gemma":0.012265161,"teacher_disagreement_score":0.006880763,"about_ca_system_score_codex":0.0010881657,"about_ca_system_score_gemma":0.0012367117,"threshold_uncertainty_score":0.013681412},"labels":[],"label_agreement":null},{"id":"W4223609001","doi":"10.5772/acrt.02","title":"MRF Models Based on a Neighborhood Adaptive Class Conditional Likelihood For Multimodal Change Detection","year":2022,"lang":"en","type":"article","venue":"AI Computer Science and Robotics Technology","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Segmentation; Pixel; Change detection; Context (archaeology); Pattern recognition (psychology); Statistical model; Estimator; Bayesian probability; Image segmentation; Markov random field; Modality (human–computer interaction); Markov process; Mathematics; Statistics; Geography","score_opus":0.022469881611816827,"score_gpt":0.22935691942199082,"score_spread":0.206887037810174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4223609001","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0065988186,0.000121940444,0.9927181,0.000078162986,0.000009657978,0.000016029266,0.000030166204,0.00015461062,0.0002725244],"genre_scores_gemma":[0.56381303,0.0006054518,0.43060517,0.00023342577,0.00016907218,0.00026099526,0.00041647066,0.00028717832,0.003609232],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993679,0.00023873356,0.00002898192,0.00014682232,0.00015622479,0.00006137819],"domain_scores_gemma":[0.9977315,0.001502322,0.00027209645,0.00018739406,0.00025032158,0.00005626059],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021881098,0.0005652242,0.0008838704,0.0010937221,0.00032374283,0.0008341677,0.0018668515,0.0013192333,0.0018857403],"category_scores_gemma":[0.006556754,0.00047527315,0.0009350075,0.00084802415,0.000960303,0.0017369401,0.00084645406,0.001335402,0.0006089772],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011168022,0.0000697113,0.0014627557,0.00007252382,0.000083121224,0.000074327625,0.00010881998,0.8644989,0.004065121,0.028515717,0.0010051595,0.09993217],"study_design_scores_gemma":[0.0000019672048,0.0000071125205,0.00015613946,0.0000025874158,0.0000042566453,0.000010988398,0.00000259597,0.99711466,0.00022458579,0.0023025323,0.00016705612,0.0000054841294],"about_ca_topic_score_codex":0.006815293,"about_ca_topic_score_gemma":0.006714197,"teacher_disagreement_score":0.006815293,"about_ca_system_score_codex":0.00077138026,"about_ca_system_score_gemma":0.0007548447,"threshold_uncertainty_score":0.013551235},"labels":[],"label_agreement":null},{"id":"W4224231559","doi":"10.1080/07038992.2022.2056434","title":"Object-Oriented Unsupervised Change Detection Based on Neighborhood Correlation Images and <i>k</i>-Means Clustering for the Multispectral and High Spatial Resolution Images","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; China Postdoctoral Science Foundation","keywords":"Change detection; Beijing; Principal component analysis; Pattern recognition (psychology); Cluster analysis; McNemar's test; Artificial intelligence; Multispectral image; Computer science; Cohen's kappa; Remote sensing; Geography; Mathematics; Statistics; Machine learning","score_opus":0.014311820507796006,"score_gpt":0.20258372977880337,"score_spread":0.18827190927100737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224231559","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07010353,0.00023187851,0.9269832,0.000088457215,0.000034247874,0.00008926602,0.000060229344,0.000680552,0.0017286978],"genre_scores_gemma":[0.5077323,0.00031945386,0.48983583,0.00005820423,0.000055245575,0.00014077012,0.00021990653,0.00011122512,0.0015270042],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992823,0.00010495823,0.000037472113,0.00020874232,0.0003041734,0.00006232224],"domain_scores_gemma":[0.9994362,0.00012569601,0.0001280128,0.00006014023,0.00022617819,0.000023809287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005770617,0.00047828202,0.0005605021,0.0020659892,0.0005263609,0.00068668986,0.0006430853,0.00044810455,0.0005931553],"category_scores_gemma":[0.0012936218,0.00026662502,0.0009172933,0.0013979458,0.00059276336,0.00087483274,0.00038410164,0.00040512357,0.00024367828],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018812466,0.00021828647,0.016919214,0.0003455123,0.00026921244,0.00030342615,0.00054340594,0.08944677,0.10389519,0.009095913,0.0030063596,0.7757687],"study_design_scores_gemma":[0.000018361046,0.00009134029,0.02618224,0.00002629291,0.000085663094,0.00042696108,0.00022039635,0.91494536,0.049963202,0.0041468297,0.0038175343,0.000075836426],"about_ca_topic_score_codex":0.005758289,"about_ca_topic_score_gemma":0.009326339,"teacher_disagreement_score":0.005758289,"about_ca_system_score_codex":0.0005831295,"about_ca_system_score_gemma":0.00084568973,"threshold_uncertainty_score":0.011449516},"labels":[],"label_agreement":null},{"id":"W4224988789","doi":"10.3390/rs14092097","title":"Optimum Feature and Classifier Selection for Accurate Urban Land Use/Cover Mapping from Very High Resolution Satellite Imagery","year":2022,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Resources Canada; Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Support vector machine; Feature selection; Classifier (UML); Random forest; Particle swarm optimization; Land cover; Cascading classifiers; Data mining; Machine learning; Random subspace method; Land use","score_opus":0.023466260006299974,"score_gpt":0.2191316873339582,"score_spread":0.19566542732765824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224988789","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16611838,0.00038499892,0.8313357,0.00010818056,0.000022045873,0.00010250402,0.00012835482,0.0006690747,0.001130779],"genre_scores_gemma":[0.6145917,0.00021519566,0.38340378,0.00004089832,0.000029959916,0.00015665616,0.00053700985,0.000075501805,0.000949294],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994184,0.0001259168,0.000042664167,0.0001246173,0.00022096834,0.00006740215],"domain_scores_gemma":[0.9995592,0.00015218143,0.00005606467,0.00004058142,0.00017601224,0.000015901009],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00093129335,0.00070015044,0.00073378574,0.0014084472,0.0003675414,0.0006292963,0.000400537,0.00048646543,0.0006934531],"category_scores_gemma":[0.0017757752,0.0002579678,0.00074803265,0.00071612623,0.00022785485,0.0007093759,0.00026036013,0.00039487495,0.00042438388],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034032896,0.0003166679,0.011443026,0.0002015307,0.0001399524,0.00032933842,0.0001654513,0.12786487,0.13449405,0.0022822758,0.0027233642,0.7196992],"study_design_scores_gemma":[0.00002438031,0.00023051281,0.014021341,0.000025300838,0.00010083168,0.00019643833,0.00011646902,0.9327819,0.048131354,0.0018223053,0.0025103935,0.000038799597],"about_ca_topic_score_codex":0.0015476783,"about_ca_topic_score_gemma":0.0017530166,"teacher_disagreement_score":0.0015476783,"about_ca_system_score_codex":0.00028786776,"about_ca_system_score_gemma":0.00061705214,"threshold_uncertainty_score":0.0049251914},"labels":[],"label_agreement":null},{"id":"W4225308848","doi":"10.36227/techrxiv.19400612.v1","title":"Anomaly Detection Based on Sigmoid Metric and Object Area Filtering in Hyperspectral Images","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Hyperspectral imaging; Pixel; Metric (unit); Sigmoid function; Mean squared error; Artificial intelligence; Window (computing); Object (grammar); Anomaly (physics); Pattern recognition (psychology); Mathematics; Image (mathematics); Anomaly detection; Computer science; Computer vision; Statistics; Physics; Artificial neural network","score_opus":0.01801771498601864,"score_gpt":0.22534106970973614,"score_spread":0.2073233547237175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225308848","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.071183026,0.00040295834,0.92695373,0.000061887375,0.000038356262,0.00003421016,0.00006267185,0.00058254774,0.0006806508],"genre_scores_gemma":[0.62973475,0.00056656555,0.367437,0.0000676921,0.00009090102,0.000068167086,0.00033703246,0.00011172521,0.0015861683],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908876,0.00013691939,0.00006637388,0.00025377213,0.00036929757,0.00008493593],"domain_scores_gemma":[0.9989164,0.00030635268,0.00019848532,0.000121929355,0.0003886276,0.000068172674],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011584207,0.00086252845,0.0009842517,0.0018564572,0.00032636232,0.0011011773,0.00084526476,0.00066458253,0.00042255805],"category_scores_gemma":[0.0022579783,0.00022171406,0.00073081703,0.0018004641,0.0008242771,0.0016329561,0.0008217002,0.00068441813,0.0002735771],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043438835,0.00018718034,0.013485801,0.00026769217,0.00020668552,0.0002839098,0.00032105081,0.14378877,0.11595094,0.0118716005,0.0016977775,0.71150416],"study_design_scores_gemma":[0.000005930595,0.000097890996,0.005797801,0.000009318309,0.000022873654,0.00024655886,0.00004042481,0.96086663,0.027776878,0.0038496964,0.0012533399,0.000032616594],"about_ca_topic_score_codex":0.0020687527,"about_ca_topic_score_gemma":0.0016109033,"teacher_disagreement_score":0.0020687527,"about_ca_system_score_codex":0.00061291904,"about_ca_system_score_gemma":0.00058277225,"threshold_uncertainty_score":0.006126344},"labels":[],"label_agreement":null},{"id":"W4225319952","doi":"10.36227/techrxiv.19400612","title":"Anomaly Detection Based on Sigmoid Metric and Object Area Filtering in Hyperspectral Images","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Hyperspectral imaging; Pixel; Sigmoid function; Metric (unit); Mean squared error; Object (grammar); Artificial intelligence; Pattern recognition (psychology); Window (computing); Anomaly (physics); Mathematics; Image (mathematics); Computer science; Function (biology); Computer vision; Algorithm; Statistics; Physics","score_opus":0.01801771498601864,"score_gpt":0.22534106970973614,"score_spread":0.2073233547237175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225319952","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08611792,0.00037977245,0.9115253,0.00009258009,0.00004606877,0.000037108133,0.00007659592,0.00086567755,0.00085901044],"genre_scores_gemma":[0.5937853,0.0004798694,0.4025717,0.000081033664,0.0000862385,0.000055902747,0.00040311288,0.0001584829,0.0023784125],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993193,0.00011855828,0.000045711076,0.00019312227,0.00025634197,0.00006688107],"domain_scores_gemma":[0.99915123,0.00021362331,0.00014148378,0.000115766896,0.00032106144,0.000056798457],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010200999,0.00073219073,0.00096563215,0.0014791173,0.0002812575,0.0010674618,0.00081142125,0.0006313779,0.00068064354],"category_scores_gemma":[0.001858295,0.00020838519,0.0006968633,0.0014037438,0.0007014126,0.0013320259,0.00072145485,0.0006704454,0.0003722189],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038333642,0.00016497521,0.007614741,0.00017515222,0.00015256928,0.0001943264,0.00020412539,0.14262795,0.10300772,0.008269646,0.0018673213,0.7353381],"study_design_scores_gemma":[0.000003981527,0.000050070845,0.0032459572,0.000005597162,0.000012693392,0.00010589834,0.000020491558,0.97547626,0.018073665,0.0022094864,0.0007779054,0.000018016053],"about_ca_topic_score_codex":0.0031435606,"about_ca_topic_score_gemma":0.0025706356,"teacher_disagreement_score":0.0031435606,"about_ca_system_score_codex":0.0006569104,"about_ca_system_score_gemma":0.00060428825,"threshold_uncertainty_score":0.0062505007},"labels":[],"label_agreement":null},{"id":"W4226183927","doi":"10.1109/access.2022.3163535","title":"RSI-Net: Two-Stream Deep Neural Network for Remote Sensing Images-Based Semantic Segmentation","year":2022,"lang":"en","type":"article","venue":"IEEE Access","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Priority Academic Program Development of Jiangsu Higher Education Institutions; Government of Jiangsu Province; Shenzhen-Hong Kong Institute of Brain Science; Six Talent Peaks Project in Jiangsu Province; National Natural Science Foundation of China","keywords":"Computer science; Segmentation; Graph; Artificial intelligence; Convolutional neural network; Convolution (computer science); Pattern recognition (psychology); Image segmentation; Residual; Artificial neural network; Algorithm; Theoretical computer science","score_opus":0.027070020671400057,"score_gpt":0.2903443056792131,"score_spread":0.263274285007813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226183927","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08806477,0.0020310488,0.8686834,0.0006749777,0.00038628417,0.0003314532,0.004487745,0.02580262,0.009537681],"genre_scores_gemma":[0.5275432,0.0011268643,0.4358306,0.00094405824,0.00015109398,0.00039499038,0.0183295,0.0007690915,0.014910656],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996948,0.000026411679,0.000015602207,0.000115339906,0.00009313266,0.000054742133],"domain_scores_gemma":[0.99980336,0.00003374376,0.000030478841,0.000036573874,0.00007580611,0.000020026426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047014473,0.0016599937,0.000897533,0.0012939636,0.00034770428,0.0008040656,0.0020029596,0.0011000684,0.0026433608],"category_scores_gemma":[0.0009346308,0.0004896575,0.0010091878,0.0011692323,0.000451253,0.0014885108,0.0011864913,0.0012069495,0.0014198681],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005779497,0.00039192202,0.004184287,0.00035937273,0.00034941707,0.00027079173,0.0001441399,0.3071664,0.03145485,0.0049748854,0.026746867,0.6233791],"study_design_scores_gemma":[0.00001633967,0.000042339503,0.0008067946,0.000014737089,0.000030296622,0.000052214644,0.000025328842,0.9852328,0.008879377,0.00245372,0.0024267007,0.000019349123],"about_ca_topic_score_codex":0.01636931,"about_ca_topic_score_gemma":0.021552542,"teacher_disagreement_score":0.01636931,"about_ca_system_score_codex":0.0012051683,"about_ca_system_score_gemma":0.001228305,"threshold_uncertainty_score":0.03254807},"labels":[],"label_agreement":null},{"id":"W4229444393","doi":"10.18280/ts.390240","title":"Combined Spatial-Spectral Hyperspectral Image Classification Based on Adaptive Guided Filtering","year":2022,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Hyperspectral imaging; Artificial intelligence; Pattern recognition (psychology); Support vector machine; Local binary patterns; Computer science; Classifier (UML); Contextual image classification; Discriminative model; Pixel; Computer vision; Histogram; Image (mathematics)","score_opus":0.030597357912230522,"score_gpt":0.22974707391085145,"score_spread":0.1991497159986209,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229444393","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052398294,0.00053807785,0.9441143,0.00013963699,0.000058569523,0.000046755402,0.000045240722,0.0010024619,0.0016566582],"genre_scores_gemma":[0.44122714,0.0005064154,0.5544907,0.0001977394,0.000081275786,0.00009025266,0.00021818525,0.00010879885,0.003079487],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991547,0.00010260415,0.00004090952,0.00016676802,0.00045307958,0.00008202909],"domain_scores_gemma":[0.9994481,0.00014508843,0.00006910388,0.00009810221,0.00021881766,0.0000207437],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064383866,0.00062232924,0.0008276961,0.0013467169,0.00032921924,0.0007308418,0.0007587112,0.00079313933,0.00065328734],"category_scores_gemma":[0.0009822404,0.00022160605,0.0007209503,0.000934471,0.0004630953,0.0010003843,0.00052045303,0.00059417094,0.00063751376],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023587301,0.0001707672,0.002302613,0.00015251242,0.00013373641,0.00007794254,0.00010855692,0.023077806,0.18346709,0.0017843292,0.0016635464,0.78682524],"study_design_scores_gemma":[0.000013385822,0.00016171418,0.004888921,0.000018790228,0.000078316814,0.00034572667,0.00007201197,0.90584904,0.08239562,0.0023190537,0.003813704,0.0000435922],"about_ca_topic_score_codex":0.002103569,"about_ca_topic_score_gemma":0.0036452438,"teacher_disagreement_score":0.002103569,"about_ca_system_score_codex":0.00029961436,"about_ca_system_score_gemma":0.00037986645,"threshold_uncertainty_score":0.0041826367},"labels":[],"label_agreement":null},{"id":"W4235641647","doi":"10.32920/14636655.v2","title":"Comprehensive Analysis of Edge Detection in Color Image Processing","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Toronto Metropolitan University","funders":"","keywords":"Edge detection; Detector; Euclidean distance; Enhanced Data Rates for GSM Evolution; Noise (video); Computer science; Monochrome; Artificial intelligence; Mathematics; Instrumentation (computer programming); Operator (biology); Computer vision; Color space; Pattern recognition (psychology); Image processing; Image (mathematics); Telecommunications","score_opus":0.02325212392721943,"score_gpt":0.26364606599166285,"score_spread":0.24039394206444342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235641647","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013462566,0.0155537315,0.9655507,0.00022254548,0.00010198615,0.000038642742,0.00007173966,0.00036894216,0.0046290923],"genre_scores_gemma":[0.20926872,0.03681286,0.7406726,0.00031271772,0.00053320837,0.00012472348,0.00055541744,0.00025490392,0.011464962],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991391,0.00012318426,0.000056342113,0.000111785186,0.0005332708,0.000036407884],"domain_scores_gemma":[0.99855083,0.00066293246,0.00011102157,0.00010925667,0.0005402705,0.00002554587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094796304,0.0006932836,0.0007413116,0.0028229926,0.0002759955,0.0013216736,0.0005962319,0.00082235894,0.0021896951],"category_scores_gemma":[0.0026761654,0.00034525731,0.00053978385,0.0028951382,0.0005371783,0.0018348729,0.00036777215,0.00064489036,0.0007329565],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009386974,0.00009655069,0.0013436766,0.0009407833,0.000120015204,0.00017110714,0.00011637509,0.050881278,0.044550817,0.03692903,0.0033886891,0.86136776],"study_design_scores_gemma":[0.000014566486,0.0003714679,0.008623008,0.00031562877,0.00016425663,0.0014371199,0.0001210679,0.7705974,0.080099754,0.07823869,0.05987209,0.00014484569],"about_ca_topic_score_codex":0.0007151138,"about_ca_topic_score_gemma":0.00066439004,"teacher_disagreement_score":0.0028229926,"about_ca_system_score_codex":0.00039267523,"about_ca_system_score_gemma":0.00035720877,"threshold_uncertainty_score":0.0073252916},"labels":[],"label_agreement":null},{"id":"W4238666703","doi":"10.32920/ryerson.14657394.v1","title":"Environmental monitoring of landfill sites using multi-temporal remote sensing images","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Environmental science; Landfill gas; Remote sensing; Methane; Hydrology (agriculture); Environmental engineering; Municipal solid waste; Geology; Waste management; Geotechnical engineering; Engineering","score_opus":0.046133418947166625,"score_gpt":0.26625375100174564,"score_spread":0.220120332054579,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4238666703","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9937078,0.00007350474,0.0040950645,0.000023885174,0.0000035991607,0.000017617196,0.0006937452,0.00012351236,0.0012611811],"genre_scores_gemma":[0.99024886,0.00006786112,0.008347514,0.000008011293,0.000004076807,0.000013120708,0.00078127376,0.0000073042925,0.0005219349],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99987483,0.000017946128,0.000007675592,0.000025453082,0.000050751416,0.00002332136],"domain_scores_gemma":[0.9998467,0.000015880665,0.00006311097,0.000013767445,0.00004661728,0.0000140081565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018539431,0.00023594519,0.000116511554,0.0012189244,0.00018980753,0.00035851885,0.00018096114,0.00016678585,0.00041164632],"category_scores_gemma":[0.00019114185,0.000082537605,0.00014537755,0.0015308523,0.00012479014,0.00030331328,0.00014580972,0.00008186974,0.000098532066],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047833403,0.00032397616,0.613553,0.00018691375,0.00014208506,0.00061894616,0.00051586895,0.024202017,0.20704523,0.0003238282,0.00091925607,0.15169054],"study_design_scores_gemma":[0.000015791507,0.00008540098,0.9074258,0.000015905742,0.000059480233,0.00021750185,0.00081469706,0.04587193,0.043121096,0.000097057586,0.0022459428,0.000029402765],"about_ca_topic_score_codex":0.020252287,"about_ca_topic_score_gemma":0.08472082,"teacher_disagreement_score":0.020252287,"about_ca_system_score_codex":0.0003612517,"about_ca_system_score_gemma":0.00042349237,"threshold_uncertainty_score":0.04026884},"labels":[],"label_agreement":null},{"id":"W4239215490","doi":"10.32920/ryerson.14644335","title":"Fuzzy Similarity Measure and its Application to High Resolution Colour Remote Sensing Image Processing","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Measure (data warehouse); Computer science; Fuzzy logic; Artificial intelligence; Similarity measure; Cluster analysis; Similarity (geometry); Multivariate statistics; Pattern recognition (psychology); Fuzzy clustering; Data mining; Focus (optics); Computer vision; Image (mathematics); Remote sensing; Geography; Machine learning","score_opus":0.02194577558023064,"score_gpt":0.24989570805743236,"score_spread":0.22794993247720172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239215490","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015596414,0.0013040602,0.9801631,0.00018126082,0.00007052816,0.00003545506,0.00003930162,0.000112584865,0.0024973818],"genre_scores_gemma":[0.4290951,0.0018631198,0.5659743,0.000118164295,0.0002431634,0.00010314546,0.00015087205,0.000048283127,0.0024039065],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99887115,0.00024920492,0.00009027275,0.0001879428,0.00056006876,0.000041263986],"domain_scores_gemma":[0.99890804,0.0005138145,0.00012847997,0.00009285094,0.00031466235,0.000042242078],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011854848,0.0003251837,0.0006107227,0.0027062474,0.00040366332,0.001358101,0.00060377555,0.0009432296,0.0011147939],"category_scores_gemma":[0.0041265343,0.0001708319,0.0008095245,0.0027802784,0.0009407485,0.0012194831,0.00063002843,0.0007445311,0.00033584939],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017155844,0.000114080016,0.0029052768,0.0005954539,0.0001797941,0.0005590097,0.0004989539,0.1552074,0.049497213,0.16333413,0.0027522785,0.6241849],"study_design_scores_gemma":[0.0000107006035,0.00013500881,0.003972619,0.00004292681,0.000039060564,0.00084831635,0.000112700865,0.9084419,0.01188841,0.06835005,0.0061047217,0.00005357144],"about_ca_topic_score_codex":0.0014257032,"about_ca_topic_score_gemma":0.0008023886,"teacher_disagreement_score":0.0027062474,"about_ca_system_score_codex":0.00056159485,"about_ca_system_score_gemma":0.00047424473,"threshold_uncertainty_score":0.006269574},"labels":[],"label_agreement":null},{"id":"W4241788017","doi":"10.32920/ryerson.14665284.v1","title":"Detection of waste dumping locations in landfill using multi-temporal landsat thermal images","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Leachate; Environmental science; Borehole; Municipal solid waste; Hazardous waste; Dumping; Waste management; Flux (metallurgy); Groundwater; Heat flux; Environmental engineering; Hydrology (agriculture); Remote sensing; Geology; Geotechnical engineering; Engineering; Heat transfer","score_opus":0.03973313514843431,"score_gpt":0.2621654223927929,"score_spread":0.2224322872443586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4241788017","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9968911,0.000036789515,0.0021654528,0.000011981831,0.0000023660525,0.000014234519,0.0003050323,0.000087391054,0.00048562186],"genre_scores_gemma":[0.9937551,0.00004898129,0.0055537177,0.0000050922354,0.0000031038956,0.000009253645,0.00037832325,0.000005106811,0.0002413465],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9999099,0.0000122440415,0.000008171659,0.000020572958,0.000025485455,0.000023512652],"domain_scores_gemma":[0.99986434,0.00001147443,0.000053393105,0.000010133085,0.000043139087,0.000017451723],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022313005,0.00030229133,0.00012313458,0.0016696046,0.00016610132,0.00033862688,0.00021055738,0.00025089597,0.00032070067],"category_scores_gemma":[0.00023255819,0.00014731161,0.00019420315,0.0011123911,0.00013163907,0.00027266782,0.00015193941,0.00010025712,0.0001363111],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00073009916,0.00029291312,0.5402771,0.00020796139,0.00012010186,0.0015156505,0.0012059379,0.018324334,0.33061966,0.00029294495,0.00084343203,0.105569884],"study_design_scores_gemma":[0.000007825903,0.0000936918,0.90846825,0.000018396775,0.000070601796,0.0004523889,0.0011640757,0.05601693,0.03282225,0.000062129286,0.0007980537,0.00002542205],"about_ca_topic_score_codex":0.0139821,"about_ca_topic_score_gemma":0.039660353,"teacher_disagreement_score":0.0139821,"about_ca_system_score_codex":0.0002874246,"about_ca_system_score_gemma":0.0002763515,"threshold_uncertainty_score":0.027801394},"labels":[],"label_agreement":null},{"id":"W4242987060","doi":"10.32920/14636655","title":"Comprehensive Analysis of Edge Detection in Color Image Processing","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Toronto Metropolitan University","funders":"","keywords":"Edge detection; Detector; Euclidean distance; Noise (video); Enhanced Data Rates for GSM Evolution; Monochrome; Computer science; Mathematics; Instrumentation (computer programming); Operator (biology); Artificial intelligence; Color space; Computer vision; Pattern recognition (psychology); Image processing; Image (mathematics); Telecommunications","score_opus":0.02325212392721943,"score_gpt":0.26364606599166285,"score_spread":0.24039394206444342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4242987060","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013462566,0.0155537315,0.9655507,0.00022254548,0.00010198615,0.000038642742,0.00007173966,0.00036894216,0.0046290923],"genre_scores_gemma":[0.20926872,0.03681286,0.7406726,0.00031271772,0.00053320837,0.00012472348,0.00055541744,0.00025490392,0.011464962],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991391,0.00012318426,0.000056342113,0.000111785186,0.0005332708,0.000036407884],"domain_scores_gemma":[0.99855083,0.00066293246,0.00011102157,0.00010925667,0.0005402705,0.00002554587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094796304,0.0006932836,0.0007413116,0.0028229926,0.0002759955,0.0013216736,0.0005962319,0.00082235894,0.0021896951],"category_scores_gemma":[0.0026761654,0.00034525731,0.00053978385,0.0028951382,0.0005371783,0.0018348729,0.00036777215,0.00064489036,0.0007329565],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009386974,0.00009655069,0.0013436766,0.0009407833,0.000120015204,0.00017110714,0.00011637509,0.050881278,0.044550817,0.03692903,0.0033886891,0.86136776],"study_design_scores_gemma":[0.000014566486,0.0003714679,0.008623008,0.00031562877,0.00016425663,0.0014371199,0.0001210679,0.7705974,0.080099754,0.07823869,0.05987209,0.00014484569],"about_ca_topic_score_codex":0.0007151138,"about_ca_topic_score_gemma":0.00066439004,"teacher_disagreement_score":0.0028229926,"about_ca_system_score_codex":0.00039267523,"about_ca_system_score_gemma":0.00035720877,"threshold_uncertainty_score":0.0073252916},"labels":[],"label_agreement":null},{"id":"W4243295358","doi":"10.5194/isprs-archives-xlii-4-w18-41-2019","title":"SPECTRAL-SPATIAL CLASSIFICATION OF HYPERSPECTRAL IMAGERY USING A HYBRID FRAMEWORK","year":2019,"lang":"en","type":"article","venue":"˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Hyperspectral imaging; Pattern recognition (psychology); Computer science; Artificial intelligence; Support vector machine; Perceptron; Artificial neural network; Dimensionality reduction; Multilayer perceptron; Curse of dimensionality","score_opus":0.019402636101995087,"score_gpt":0.25342322484240415,"score_spread":0.23402058874040907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4243295358","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06795298,0.0005066891,0.92754036,0.00018649775,0.000029808296,0.00006019213,0.00020815471,0.0011296758,0.0023856317],"genre_scores_gemma":[0.60994583,0.00025400956,0.38398725,0.00014785447,0.00008305861,0.00013546711,0.0009481309,0.00009702,0.0044014268],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999529,0.0000928495,0.000024343555,0.0001270468,0.00017221214,0.00005468375],"domain_scores_gemma":[0.99968004,0.000047153535,0.000041441563,0.000034104316,0.00017430652,0.000022920214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000802989,0.00059451646,0.0005937379,0.002175765,0.000366404,0.0010283171,0.00085741316,0.0005920206,0.0013365077],"category_scores_gemma":[0.00057657546,0.00018511381,0.00094121066,0.0012803193,0.00042020975,0.0009278127,0.0007301296,0.00039413315,0.0005196544],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029509232,0.00040724408,0.005924426,0.0001530316,0.00025566234,0.00011473983,0.00016688625,0.26410347,0.05330931,0.0115136355,0.003687295,0.6600691],"study_design_scores_gemma":[0.0000028115305,0.000023092429,0.0011274847,0.000005305163,0.000013319614,0.000021033777,0.000027769116,0.99437743,0.0024692805,0.0013254241,0.00060073717,0.0000061981896],"about_ca_topic_score_codex":0.0079937475,"about_ca_topic_score_gemma":0.012462451,"teacher_disagreement_score":0.0079937475,"about_ca_system_score_codex":0.0007478736,"about_ca_system_score_gemma":0.0006601199,"threshold_uncertainty_score":0.015894473},"labels":[],"label_agreement":null},{"id":"W4243373931","doi":"10.32920/ryerson.14657394","title":"Environmental monitoring of landfill sites using multi-temporal remote sensing images","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Environmental science; Remote sensing; Landfill gas; Methane; Hydrology (agriculture); Environmental engineering; Geology; Municipal solid waste; Waste management; Geotechnical engineering; Engineering","score_opus":0.046133418947166625,"score_gpt":0.26625375100174564,"score_spread":0.220120332054579,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4243373931","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9937078,0.00007350474,0.0040950645,0.000023885174,0.0000035991607,0.000017617196,0.0006937452,0.00012351236,0.0012611811],"genre_scores_gemma":[0.99024886,0.00006786112,0.008347514,0.000008011293,0.000004076807,0.000013120708,0.00078127376,0.0000073042925,0.0005219349],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99987483,0.000017946128,0.000007675592,0.000025453082,0.000050751416,0.00002332136],"domain_scores_gemma":[0.9998467,0.000015880665,0.00006311097,0.000013767445,0.00004661728,0.0000140081565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018539431,0.00023594519,0.000116511554,0.0012189244,0.00018980753,0.00035851885,0.00018096114,0.00016678585,0.00041164632],"category_scores_gemma":[0.00019114185,0.000082537605,0.00014537755,0.0015308523,0.00012479014,0.00030331328,0.00014580972,0.00008186974,0.000098532066],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047833403,0.00032397616,0.613553,0.00018691375,0.00014208506,0.00061894616,0.00051586895,0.024202017,0.20704523,0.0003238282,0.00091925607,0.15169054],"study_design_scores_gemma":[0.000015791507,0.00008540098,0.9074258,0.000015905742,0.000059480233,0.00021750185,0.00081469706,0.04587193,0.043121096,0.000097057586,0.0022459428,0.000029402765],"about_ca_topic_score_codex":0.020252287,"about_ca_topic_score_gemma":0.08472082,"teacher_disagreement_score":0.020252287,"about_ca_system_score_codex":0.0003612517,"about_ca_system_score_gemma":0.00042349237,"threshold_uncertainty_score":0.04026884},"labels":[],"label_agreement":null},{"id":"W4245696332","doi":"10.4095/220089","title":"From At-Sensor observation to At-Surface reflectance - calibration steps for earth observation hyperspectral sensors","year":2004,"lang":"en","type":"report","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Natural Resources Canada","funders":"","keywords":"Hyperspectral imaging; Remote sensing; Reflectivity; Earth observation; Calibration; Earth (classical element); Environmental science; Geology; Optics; Engineering; Physics; Satellite; Aerospace engineering; Astronomy","score_opus":0.08425453962082359,"score_gpt":0.2920664580616692,"score_spread":0.20781191844084562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245696332","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17000093,0.0007629263,0.77875257,0.0006679072,0.00019223714,0.0017827632,0.00391079,0.0070368913,0.036892973],"genre_scores_gemma":[0.19740543,0.0006622901,0.78201395,0.0002076012,0.000065146814,0.0004993229,0.0058327573,0.0008758907,0.012437651],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99827886,0.00015211383,0.000048994578,0.0001768979,0.001260347,0.000082725324],"domain_scores_gemma":[0.99869126,0.00011453074,0.000075153584,0.00025191274,0.0008027276,0.000064398235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009896471,0.0007660902,0.0005800129,0.0013398252,0.0009246181,0.0010710352,0.0010605636,0.00057043124,0.0045543667],"category_scores_gemma":[0.0014793249,0.00039654152,0.00047883828,0.0013613487,0.00040471504,0.0010249101,0.0009627324,0.0012186901,0.0039269133],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019636535,0.000596748,0.017629419,0.0003736136,0.00006528782,0.00017579194,0.00038004626,0.021651383,0.34788167,0.0065743118,0.014502767,0.5899727],"study_design_scores_gemma":[0.000047035424,0.0006235144,0.07977639,0.00009483249,0.000082368715,0.00084479357,0.00039937242,0.10829485,0.6874536,0.012814437,0.10940584,0.000162982],"about_ca_topic_score_codex":0.0072227144,"about_ca_topic_score_gemma":0.012789188,"teacher_disagreement_score":0.0072227144,"about_ca_system_score_codex":0.00073628256,"about_ca_system_score_gemma":0.0013965333,"threshold_uncertainty_score":0.015235841},"labels":[],"label_agreement":null},{"id":"W4246005524","doi":"10.32920/ryerson.14644335.v1","title":"Fuzzy Similarity Measure and its Application to High Resolution Colour Remote Sensing Image Processing","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Measure (data warehouse); Artificial intelligence; Computer science; Cluster analysis; Similarity (geometry); Fuzzy logic; Similarity measure; Multivariate statistics; Pattern recognition (psychology); Fuzzy clustering; Focus (optics); Data mining; Image processing; Computer vision; Image (mathematics); Machine learning","score_opus":0.02194577558023064,"score_gpt":0.24989570805743236,"score_spread":0.22794993247720172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246005524","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015596414,0.0013040602,0.9801631,0.00018126082,0.00007052816,0.00003545506,0.00003930162,0.000112584865,0.0024973818],"genre_scores_gemma":[0.4290951,0.0018631198,0.5659743,0.000118164295,0.0002431634,0.00010314546,0.00015087205,0.000048283127,0.0024039065],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99887115,0.00024920492,0.00009027275,0.0001879428,0.00056006876,0.000041263986],"domain_scores_gemma":[0.99890804,0.0005138145,0.00012847997,0.00009285094,0.00031466235,0.000042242078],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011854848,0.0003251837,0.0006107227,0.0027062474,0.00040366332,0.001358101,0.00060377555,0.0009432296,0.0011147939],"category_scores_gemma":[0.0041265343,0.0001708319,0.0008095245,0.0027802784,0.0009407485,0.0012194831,0.00063002843,0.0007445311,0.00033584939],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017155844,0.000114080016,0.0029052768,0.0005954539,0.0001797941,0.0005590097,0.0004989539,0.1552074,0.049497213,0.16333413,0.0027522785,0.6241849],"study_design_scores_gemma":[0.0000107006035,0.00013500881,0.003972619,0.00004292681,0.000039060564,0.00084831635,0.000112700865,0.9084419,0.01188841,0.06835005,0.0061047217,0.00005357144],"about_ca_topic_score_codex":0.0014257032,"about_ca_topic_score_gemma":0.0008023886,"teacher_disagreement_score":0.0027062474,"about_ca_system_score_codex":0.00056159485,"about_ca_system_score_gemma":0.00047424473,"threshold_uncertainty_score":0.006269574},"labels":[],"label_agreement":null},{"id":"W4248625393","doi":"10.1109/cac53003.2021.9728237","title":"Joint Groupwise Image Registration and Fusion Based on Bounded Generalized Gaussian Mixture Model","year":2021,"lang":"en","type":"article","venue":"2021 China Automation Congress (CAC)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Natural Science Foundation of China","keywords":"Bounded function; Joint (building); Mixture model; Computer science; Image fusion; Image registration; Artificial intelligence; Gaussian; Computer vision; Image (mathematics); Fusion; Maximization; Expectation–maximization algorithm; Pattern recognition (psychology); Mathematics; Mathematical optimization; Maximum likelihood; Statistics; Engineering","score_opus":0.013615342094920994,"score_gpt":0.22959879078422668,"score_spread":0.2159834486893057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248625393","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014809094,0.00013395006,0.9978934,0.00004417006,0.000013589148,0.000010508233,0.000009824911,0.00020591522,0.00020763376],"genre_scores_gemma":[0.21228306,0.0007790925,0.7837274,0.00017586639,0.00011383758,0.0001490712,0.00032321818,0.00021748018,0.0022309497],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978358,0.0007443225,0.000111622234,0.00049121026,0.0006706468,0.00014649383],"domain_scores_gemma":[0.99901617,0.0003471665,0.00013648445,0.0002365116,0.00022355001,0.000040130908],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022699425,0.0011854954,0.0018096105,0.0014025484,0.0005137429,0.00125948,0.0021358207,0.0018020313,0.0012855368],"category_scores_gemma":[0.0037652082,0.0006350583,0.0023596652,0.001632039,0.0012183969,0.002893315,0.002292988,0.001756014,0.0010561846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032740267,0.00010710347,0.0012888031,0.00034322843,0.000326552,0.0002839813,0.00036695015,0.41986102,0.0453517,0.048459206,0.003280645,0.48000342],"study_design_scores_gemma":[0.000010622865,0.000059763737,0.00029955225,0.000011206401,0.000049551643,0.00017263518,0.000024967081,0.9778972,0.0077659274,0.011898448,0.001769567,0.000040583003],"about_ca_topic_score_codex":0.0021217642,"about_ca_topic_score_gemma":0.0016565362,"teacher_disagreement_score":0.0022699425,"about_ca_system_score_codex":0.00055742374,"about_ca_system_score_gemma":0.0010430387,"threshold_uncertainty_score":0.012004733},"labels":[],"label_agreement":null},{"id":"W4249006329","doi":"10.4095/219895","title":"Defining Shaded Spectra by Model Inversion for Spectral Unmixing of Hyperspectral Datasets - Theory and Preliminary Application","year":2002,"lang":"en","type":"report","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Resources Canada","funders":"","keywords":"Hyperspectral imaging; Inversion (geology); Computer science; Spectral line; Pattern recognition (psychology); Remote sensing; Artificial intelligence; Geology; Physics; Paleontology","score_opus":0.02397832363598865,"score_gpt":0.25708477499919474,"score_spread":0.2331064513632061,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4249006329","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008956505,0.000088583954,0.99027854,0.000035985006,0.00000570545,0.000014714682,0.000020868056,0.000104057275,0.00049498666],"genre_scores_gemma":[0.2438154,0.00034902332,0.7533005,0.000050044986,0.000030847823,0.00011463149,0.0002420132,0.00014847226,0.0019490522],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998036,0.0000748347,0.0000057933394,0.00003260555,0.00006703164,0.000016102496],"domain_scores_gemma":[0.9997135,0.00014922072,0.000019727959,0.00004762477,0.000059153263,0.000010731736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080352335,0.000408517,0.00021474251,0.00025071736,0.0001974057,0.0005108042,0.00031595217,0.00030005912,0.0011162949],"category_scores_gemma":[0.0020278224,0.00025755394,0.00036265387,0.0003529517,0.00044814852,0.0010746784,0.0008119224,0.0006150183,0.0003327267],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011585941,0.00014845037,0.0027341922,0.00016095139,0.000059765993,0.0001250527,0.0002471824,0.51388144,0.06893502,0.09165935,0.0021664398,0.3197664],"study_design_scores_gemma":[0.0000035729865,0.000011445372,0.00026879573,0.0000049405403,0.000002525808,0.000027736249,0.000012578196,0.98316306,0.005291711,0.009846953,0.0013605845,0.000006037917],"about_ca_topic_score_codex":0.0019780667,"about_ca_topic_score_gemma":0.0034706064,"teacher_disagreement_score":0.0019780667,"about_ca_system_score_codex":0.00027827788,"about_ca_system_score_gemma":0.0003324179,"threshold_uncertainty_score":0.004249513},"labels":[],"label_agreement":null},{"id":"W4253047094","doi":"10.32920/ryerson.14665284","title":"Detection of waste dumping locations in landfill using multi-temporal landsat thermal images","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Leachate; Environmental science; Borehole; Municipal solid waste; Hazardous waste; Waste management; Flux (metallurgy); Groundwater; Dumping; Landfill gas; Hydrology (agriculture); Environmental engineering; Remote sensing; Geology; Geotechnical engineering; Engineering; Materials science","score_opus":0.03973313514843431,"score_gpt":0.2621654223927929,"score_spread":0.2224322872443586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253047094","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9968911,0.000036789515,0.0021654528,0.000011981831,0.0000023660525,0.000014234519,0.0003050323,0.000087391054,0.00048562186],"genre_scores_gemma":[0.9937551,0.00004898129,0.0055537177,0.0000050922354,0.0000031038956,0.000009253645,0.00037832325,0.000005106811,0.0002413465],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9999099,0.0000122440415,0.000008171659,0.000020572958,0.000025485455,0.000023512652],"domain_scores_gemma":[0.99986434,0.00001147443,0.000053393105,0.000010133085,0.000043139087,0.000017451723],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022313005,0.00030229133,0.00012313458,0.0016696046,0.00016610132,0.00033862688,0.00021055738,0.00025089597,0.00032070067],"category_scores_gemma":[0.00023255819,0.00014731161,0.00019420315,0.0011123911,0.00013163907,0.00027266782,0.00015193941,0.00010025712,0.0001363111],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00073009916,0.00029291312,0.5402771,0.00020796139,0.00012010186,0.0015156505,0.0012059379,0.018324334,0.33061966,0.00029294495,0.00084343203,0.105569884],"study_design_scores_gemma":[0.000007825903,0.0000936918,0.90846825,0.000018396775,0.000070601796,0.0004523889,0.0011640757,0.05601693,0.03282225,0.000062129286,0.0007980537,0.00002542205],"about_ca_topic_score_codex":0.0139821,"about_ca_topic_score_gemma":0.039660353,"teacher_disagreement_score":0.0139821,"about_ca_system_score_codex":0.0002874246,"about_ca_system_score_gemma":0.0002763515,"threshold_uncertainty_score":0.027801394},"labels":[],"label_agreement":null},{"id":"W4253526021","doi":"10.17760/d20003200","title":"FPGA-based hyperspectral covariance coprocessor for size, weight, and power constrained platforms","year":2013,"lang":"en","type":"dissertation","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Otsuka Canada Pharmaceutical","keywords":"Hyperspectral imaging; Coprocessor; Field-programmable gate array; Computer science; Remote sensing; Artificial intelligence; Covariance; Computer vision; Electromagnetic spectrum; Computer hardware; Geography; Mathematics; Physics","score_opus":0.009506380471565939,"score_gpt":0.22758470706265332,"score_spread":0.2180783265910874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253526021","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07275382,0.0026037009,0.80846083,0.0005550857,0.00053398724,0.00054313906,0.00063458225,0.0134169245,0.100498006],"genre_scores_gemma":[0.53765315,0.0013858725,0.38933808,0.00038234872,0.00014893305,0.0004216368,0.001209532,0.0005718881,0.06888855],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9998086,0.00001820335,0.000008968051,0.00003769552,0.00009220844,0.00003430299],"domain_scores_gemma":[0.99980205,0.00003082531,0.000015399222,0.00003388173,0.00010409667,0.000013871523],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013802647,0.00056475116,0.00023287792,0.00036373362,0.0002327383,0.00048022557,0.0008168128,0.00020495882,0.017308567],"category_scores_gemma":[0.00043195378,0.00017795424,0.00015903,0.00038949022,0.00009131541,0.0004554876,0.00024150709,0.0005204689,0.0044366266],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00062560383,0.0002657052,0.001278825,0.00053081044,0.00008349733,0.00046177025,0.00016838493,0.033858396,0.15489459,0.02571759,0.07197066,0.71014416],"study_design_scores_gemma":[0.00043471865,0.0011674942,0.004613277,0.00025371983,0.0001390433,0.0012668256,0.00012130927,0.46984065,0.25330958,0.008381267,0.2603729,0.00009920842],"about_ca_topic_score_codex":0.0011252558,"about_ca_topic_score_gemma":0.0027279102,"teacher_disagreement_score":0.017308567,"about_ca_system_score_codex":0.00038111839,"about_ca_system_score_gemma":0.0004767433,"threshold_uncertainty_score":0.057902932},"labels":[],"label_agreement":null},{"id":"W4256235392","doi":"10.23952/jano.2.2020.2.01","title":"Primal-dual algorithm for solving a convex image dejittering model with hybrid finite differences","year":2020,"lang":"en","type":"article","venue":"Journal of Applied and Numerical Optimization","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Fundamental Research Funds for the Central Universities; University of Hong Kong; National Natural Science Foundation of China; Centre National de la Recherche Scientifique; Université de Toulouse; Georgia Institute of Technology","keywords":"Dual (grammatical number); Regular polygon; Image (mathematics); Convex analysis; Mathematics; Mathematical optimization; Algorithm; Computer science; Convex optimization; Artificial intelligence; Geometry","score_opus":0.014303819283388862,"score_gpt":0.19939396366733275,"score_spread":0.1850901443839439,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4256235392","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004100292,0.0002871527,0.9929623,0.00024696154,0.00005739424,0.00004808066,0.00005266294,0.00011611981,0.0021290777],"genre_scores_gemma":[0.2783775,0.0004975139,0.71074635,0.0004979991,0.00013389667,0.000689009,0.00047052267,0.00027273502,0.008314451],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999673,0.00011620863,0.000016543572,0.000064164444,0.000084617546,0.000045404304],"domain_scores_gemma":[0.9992186,0.0005044019,0.000057053378,0.00003287517,0.00013245182,0.00005460487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015675484,0.0013141255,0.0016632352,0.0005911663,0.00049772725,0.0012352837,0.0015028429,0.0017942649,0.0041459426],"category_scores_gemma":[0.002040334,0.00073075196,0.0008980527,0.0006112436,0.0008967168,0.00087102497,0.0018217484,0.0024017936,0.000725974],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055262724,0.000058283964,0.00035554502,0.0001334445,0.000034805103,0.00007469499,0.000041690077,0.95950264,0.00089464174,0.015881332,0.0021328093,0.020834923],"study_design_scores_gemma":[0.000006476251,0.000009586626,0.00001515206,0.000004032933,0.0000021839546,0.0000066899147,0.000003888181,0.99797267,0.00009664788,0.0016070188,0.00027356378,0.0000020467285],"about_ca_topic_score_codex":0.005943596,"about_ca_topic_score_gemma":0.005639472,"teacher_disagreement_score":0.005943596,"about_ca_system_score_codex":0.00095164124,"about_ca_system_score_gemma":0.002412524,"threshold_uncertainty_score":0.013869584},"labels":[],"label_agreement":null},{"id":"W4280544949","doi":"10.5194/isprs-annals-v-3-2022-17-2022","title":"HOW FAR SHOULD I LOOK? A NEURAL ARCHITECTURE SEARCH STRATEGY FOR SEMANTIC SEGMENTATION OF REMOTE SENSING IMAGES","year":2022,"lang":"en","type":"article","venue":"ISPRS annals of the photogrammetry, remote sensing and spatial information sciences","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Pruning; Artificial intelligence; Artificial neural network; Segmentation; Pixel; Pattern recognition (psychology); Feature (linguistics); Network architecture; Set (abstract data type); Space (punctuation); Architecture; Data mining; Geography","score_opus":0.08062477983877343,"score_gpt":0.31880918376955747,"score_spread":0.23818440393078405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280544949","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30556425,0.00031262447,0.68416643,0.0009095254,0.000044961456,0.0001460879,0.00016720223,0.001121847,0.0075670173],"genre_scores_gemma":[0.8342127,0.00006976431,0.16211064,0.00013746548,0.0000152190805,0.000071185015,0.0001723684,0.00006393805,0.0031466645],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997886,0.000058637528,0.000014387132,0.00006438887,0.00003669348,0.000037225636],"domain_scores_gemma":[0.99956304,0.0001943644,0.00004203934,0.000043712414,0.0001251611,0.000031703254],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000723909,0.00044464477,0.00041703202,0.0008930499,0.0004370627,0.00070058496,0.0007485871,0.00087800727,0.0031470351],"category_scores_gemma":[0.002190833,0.00028257992,0.00042223508,0.00062502315,0.0007049788,0.0014285927,0.00074298424,0.00051752647,0.00038544726],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00057504466,0.00020146032,0.005190614,0.00015394497,0.00010957418,0.000324412,0.0005982445,0.42207667,0.023283703,0.02427454,0.005415461,0.5177963],"study_design_scores_gemma":[0.0000129884,0.000066558314,0.00047148802,0.000009175333,0.000015607307,0.00004551965,0.00006921616,0.9870645,0.0036815142,0.008073305,0.0004831429,0.0000069788807],"about_ca_topic_score_codex":0.0045405906,"about_ca_topic_score_gemma":0.00879561,"teacher_disagreement_score":0.0045405906,"about_ca_system_score_codex":0.0008769296,"about_ca_system_score_gemma":0.00083876075,"threshold_uncertainty_score":0.010527909},"labels":[],"label_agreement":null},{"id":"W4281486775","doi":"10.3390/rs14112532","title":"On Transfer Learning for Building Damage Assessment from Satellite Imagery in Emergency Contexts","year":2022,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal; Polytechnique Montréal","funders":"","keywords":"Computer science; Transfer of learning; Workflow; Context (archaeology); Deep learning; Convolutional neural network; Task (project management); Satellite imagery; Scarcity; Artificial intelligence; Machine learning; Remote sensing; Systems engineering; Engineering","score_opus":0.01706260253619489,"score_gpt":0.26901821664256653,"score_spread":0.25195561410637163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281486775","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23192273,0.001261655,0.7605541,0.000921669,0.00012743224,0.0002028196,0.00021338704,0.0016934539,0.0031027715],"genre_scores_gemma":[0.9346954,0.0003189521,0.061076738,0.00023873971,0.00007579289,0.00015959526,0.00045131307,0.000088103094,0.002895326],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999522,0.00017401772,0.000025225203,0.00013698582,0.00007131361,0.00007045591],"domain_scores_gemma":[0.9975579,0.001652808,0.0001364457,0.00023373436,0.00032309836,0.00009606803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021545812,0.0011645195,0.00067524513,0.00061583804,0.0004500139,0.00071990606,0.001715988,0.0017907524,0.0019573206],"category_scores_gemma":[0.008280274,0.00033412437,0.0005851859,0.000532418,0.0009640115,0.0018782895,0.001851967,0.0021265897,0.00059430517],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020600522,0.0002364293,0.0019411206,0.000080578386,0.0000561201,0.00010715179,0.00008623965,0.85696846,0.0027480004,0.0020405957,0.0010195416,0.13450977],"study_design_scores_gemma":[0.0000027892715,0.000025096837,0.00016938613,0.00000404637,0.000002821128,0.000005420728,0.00000782322,0.9976948,0.0004605499,0.0015531958,0.000071319904,0.0000026761609],"about_ca_topic_score_codex":0.009083788,"about_ca_topic_score_gemma":0.0062185396,"teacher_disagreement_score":0.009083788,"about_ca_system_score_codex":0.001134524,"about_ca_system_score_gemma":0.0008109308,"threshold_uncertainty_score":0.018061817},"labels":[],"label_agreement":null},{"id":"W4283008467","doi":"10.3390/rs14122907","title":"Diverse-Region Hyperspectral Image Classification via Superpixelwise Graph Convolution Technique","year":2022,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Xidian University; Government of Jiangsu Province; State Key Laboratory of Geo-Information Engineering; National Natural Science Foundation of China","keywords":"Hyperspectral imaging; Pattern recognition (psychology); Computer science; Graph; Pixel; Artificial intelligence; Dimensionality reduction; Curse of dimensionality; Benchmark (surveying); Adjacency list; Algorithm; Theoretical computer science; Cartography; Geography","score_opus":0.021461943238147194,"score_gpt":0.22522884398497237,"score_spread":0.20376690074682519,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283008467","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044883035,0.00040199023,0.9513808,0.0001707863,0.000054152122,0.00005241661,0.00012993306,0.0011546841,0.0017721499],"genre_scores_gemma":[0.5700795,0.0004884625,0.42268732,0.00025189834,0.000091290894,0.000092626164,0.00089140725,0.00018907724,0.0052283853],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995919,0.00006454033,0.000016049435,0.00014865464,0.00012378674,0.000055007098],"domain_scores_gemma":[0.99968934,0.00006681732,0.000043878124,0.00006746865,0.00010657204,0.000025962117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005191747,0.0009546316,0.0009234775,0.0014517073,0.0004418698,0.0007064706,0.0011540959,0.0008676147,0.0013721015],"category_scores_gemma":[0.00078215613,0.0002483513,0.0008576588,0.0013829824,0.00051675475,0.0015309826,0.0006908999,0.00073713035,0.00051177084],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028622663,0.00018062419,0.0034722567,0.00016269152,0.00017925701,0.0002160857,0.0001532131,0.2486332,0.048051637,0.011422629,0.005581604,0.6816606],"study_design_scores_gemma":[0.00000356968,0.000019986517,0.00060207205,0.0000035242049,0.000015124529,0.00006145957,0.000018347937,0.9904322,0.0056355405,0.0025203093,0.0006812631,0.000006641673],"about_ca_topic_score_codex":0.005126233,"about_ca_topic_score_gemma":0.008557724,"teacher_disagreement_score":0.005126233,"about_ca_system_score_codex":0.0006282919,"about_ca_system_score_gemma":0.0006758229,"threshold_uncertainty_score":0.0101928115},"labels":[],"label_agreement":null},{"id":"W4283017199","doi":"10.1142/s0219691322500254","title":"Hyperspectral imagery classification with minimum noise fraction, 2D spatial filtering and SVM","year":2022,"lang":"en","type":"article","venue":"International Journal of Wavelets Multiresolution and Information Processing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Space Agency; Concordia University","funders":"","keywords":"Hyperspectral imaging; Support vector machine; Data cube; Pattern recognition (psychology); Artificial intelligence; Cube (algebra); Noise (video); Computer science; Pixel; Spatial analysis; Curse of dimensionality; Remote sensing; Image (mathematics); Data mining; Mathematics; Geography","score_opus":0.010939943606709352,"score_gpt":0.22648730483388282,"score_spread":0.21554736122717347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283017199","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04819725,0.0007774451,0.94912773,0.00017934007,0.00007994162,0.00004443036,0.00010570747,0.0007985869,0.0006895945],"genre_scores_gemma":[0.41478923,0.00070422236,0.5811246,0.00015954602,0.00018691087,0.00012553211,0.00078064913,0.000083634775,0.0020456684],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901855,0.00015601864,0.000093219154,0.00022220532,0.00042440955,0.00008557526],"domain_scores_gemma":[0.9992872,0.00026515275,0.00011348865,0.00008518092,0.00021709454,0.000031905944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010625401,0.00085442414,0.0013220154,0.0018942928,0.0003992047,0.0007779837,0.0007980307,0.0011501082,0.00073377],"category_scores_gemma":[0.0016653666,0.0002884557,0.0012174944,0.0016608885,0.00043485494,0.0013446312,0.000637777,0.00074168434,0.00049148686],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034678218,0.00029160158,0.004848093,0.00021539445,0.0001628499,0.000110461624,0.00010077636,0.072219156,0.05119097,0.0023114933,0.0027684022,0.86543405],"study_design_scores_gemma":[0.000008642507,0.000073498806,0.0027050138,0.000010442755,0.000026031594,0.00010188575,0.0000257009,0.98477304,0.010215701,0.0011416463,0.0009011112,0.00001724039],"about_ca_topic_score_codex":0.002005487,"about_ca_topic_score_gemma":0.0015789173,"teacher_disagreement_score":0.002005487,"about_ca_system_score_codex":0.000378947,"about_ca_system_score_gemma":0.00043517543,"threshold_uncertainty_score":0.005619347},"labels":[],"label_agreement":null},{"id":"W4285181047","doi":"10.1109/lgrs.2022.3173052","title":"Remote Sensing Image Classification Using CNNs With Balanced Gradient for Distributed Heterogeneous Computing","year":2022,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"European Regional Development Fund; Junta de Extremadura; Horizon 2020 Framework Programme; CODE; Ministerio de Ciencia e Innovación","keywords":"Computer science; Symmetric multiprocessor system; Workload; Heterogeneous network; Deep learning; Contextual image classification; Feature extraction; Convolutional neural network; Distributed computing; Artificial intelligence; Feature (linguistics); Speedup; Supercomputer; Machine learning; Data mining; Image (mathematics); Parallel computing","score_opus":0.02173706144940345,"score_gpt":0.23661934093645426,"score_spread":0.2148822794870508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285181047","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1381563,0.00061791524,0.85210776,0.00039230756,0.0001173012,0.00009346583,0.00022249903,0.0025418852,0.005750635],"genre_scores_gemma":[0.8781904,0.00020665527,0.11762167,0.00011286751,0.000035699046,0.00006775955,0.00037264221,0.00008864219,0.0033036286],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998661,0.000012393665,0.000006076555,0.000037422094,0.000043682237,0.000034305584],"domain_scores_gemma":[0.9998766,0.000023077457,0.000017120328,0.000027354683,0.00004284483,0.0000130343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002506906,0.00062401366,0.0003496229,0.00039112422,0.00021942804,0.00061790756,0.0009144938,0.00038596478,0.0012172109],"category_scores_gemma":[0.0006812185,0.00020179553,0.00033066206,0.00044632173,0.00026815923,0.0008336612,0.0005660211,0.0005011239,0.00041205075],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021525296,0.00014361314,0.0028140289,0.00007558281,0.00009469058,0.00012707389,0.000055077937,0.6736813,0.024053216,0.008161368,0.003649307,0.2869295],"study_design_scores_gemma":[0.0000023068387,0.000009952584,0.0002155495,0.0000017832634,0.0000040804985,0.000007764707,0.0000039829797,0.9964386,0.0019622075,0.0010243121,0.00032759193,0.0000018478396],"about_ca_topic_score_codex":0.014506933,"about_ca_topic_score_gemma":0.017951569,"teacher_disagreement_score":0.014506933,"about_ca_system_score_codex":0.0010466874,"about_ca_system_score_gemma":0.0007152481,"threshold_uncertainty_score":0.028845012},"labels":[],"label_agreement":null},{"id":"W4285199460","doi":"10.1007/978-3-030-53125-6_7","title":"Change Detection","year":2022,"lang":"en","type":"book-chapter","venue":"Springer handbooks","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Sect; Change detection; Section (typography); Geography; Wildlife; Computer science; Ecology; Remote sensing; Political science; Biology; Law","score_opus":0.039079461959516844,"score_gpt":0.20689913899459328,"score_spread":0.16781967703507644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285199460","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004615972,0.0072007347,0.529265,0.0007469724,0.0015256855,0.000336278,0.004596058,0.020696843,0.4310165],"genre_scores_gemma":[0.044085477,0.0063925907,0.24974936,0.00093933364,0.0005888159,0.00025978882,0.012190244,0.0032117402,0.6825827],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9995493,0.000022818142,0.000012674726,0.00014630842,0.0002351053,0.000033812357],"domain_scores_gemma":[0.9997116,0.00004984141,0.000015786927,0.00008625813,0.0001196685,0.000016929602],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034889433,0.0012918937,0.00088899134,0.0026366124,0.000637814,0.0022052776,0.001364514,0.0011752622,0.08668457],"category_scores_gemma":[0.00074438856,0.00060423405,0.00061296084,0.002269053,0.00040629724,0.0019471584,0.0012186298,0.0007611735,0.080447055],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038715858,0.000038962356,0.00037812136,0.0002008737,0.000016233456,0.00006489631,0.000051356157,0.0015312732,0.008996622,0.008548143,0.1240972,0.85603774],"study_design_scores_gemma":[0.000011252672,0.00007496343,0.0025878174,0.00015703429,0.000045306642,0.0007790203,0.00012651121,0.029109797,0.024443854,0.022817582,0.9197931,0.000053769883],"about_ca_topic_score_codex":0.0017692056,"about_ca_topic_score_gemma":0.0026882768,"teacher_disagreement_score":0.08668457,"about_ca_system_score_codex":0.00041059015,"about_ca_system_score_gemma":0.00046771643,"threshold_uncertainty_score":0.28998876},"labels":[],"label_agreement":null},{"id":"W4285207472","doi":"10.1109/tgrs.2022.3177935","title":"Spectral–Spatial and Cascaded Multilayer Random Forests for Tree Species Classification in Airborne Hyperspectral Images","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Space Agency","keywords":"Hyperspectral imaging; Remote sensing; Random forest; Image resolution; Computer science; Spatial analysis; Pattern recognition (psychology); Full spectral imaging; Artificial intelligence; Data set; Ground truth; Tree (set theory); Contextual image classification; Image (mathematics); Mathematics; Geography","score_opus":0.022599696824344033,"score_gpt":0.24061908093792833,"score_spread":0.2180193841135843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285207472","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12658122,0.0010435833,0.8689719,0.00015086768,0.00007354541,0.000066206245,0.00025543227,0.0017756446,0.0010815286],"genre_scores_gemma":[0.73492366,0.00040866464,0.2623017,0.00008168118,0.000071698494,0.000065223416,0.00065031095,0.00006978857,0.0014273213],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995073,0.000111241476,0.000026930426,0.00012875999,0.00014496894,0.00008074302],"domain_scores_gemma":[0.9995783,0.00013296735,0.00006910246,0.00006389647,0.00012523704,0.000030437448],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010973645,0.000948892,0.0005991903,0.0013417164,0.00035351442,0.00033473462,0.0008272995,0.00054849155,0.00062760577],"category_scores_gemma":[0.0013662317,0.0002716991,0.001316359,0.0007645055,0.00022503818,0.00091023213,0.0004074418,0.00051716546,0.00033236592],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038164904,0.0002331258,0.0065266374,0.00016155146,0.00018441048,0.00022981466,0.00012997091,0.3459512,0.048180986,0.0018036029,0.0032898886,0.59292716],"study_design_scores_gemma":[0.000005499627,0.000036571873,0.0019135517,0.000006065749,0.000022187673,0.000062683466,0.00001590974,0.99173474,0.00499597,0.0008106932,0.0003838938,0.000012246374],"about_ca_topic_score_codex":0.00645531,"about_ca_topic_score_gemma":0.009747733,"teacher_disagreement_score":0.00645531,"about_ca_system_score_codex":0.0003709895,"about_ca_system_score_gemma":0.00042050224,"threshold_uncertainty_score":0.012835443},"labels":[],"label_agreement":null},{"id":"W4285304111","doi":"10.1109/lsp.2022.3179168","title":"Nonlinear Orthogonal NMF on the Stiefel Manifold With Graph-Based Total Variation Regularization","year":2022,"lang":"en","type":"article","venue":"IEEE Signal Processing Letters","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Regularization (linguistics); Stiefel manifold; Mathematics; Algorithm; Nonlinear system; Orthogonality; Uniqueness; Computer science; Mathematical optimization; Artificial intelligence; Applied mathematics; Pattern recognition (psychology)","score_opus":0.011461955004172316,"score_gpt":0.1860767770625264,"score_spread":0.17461482205835407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285304111","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043646363,0.00016145819,0.99462897,0.00010945926,0.000024524352,0.000014424013,0.000027872862,0.00009003881,0.00057859544],"genre_scores_gemma":[0.2806868,0.0007641978,0.7112075,0.0003297889,0.0001978757,0.00027944773,0.0005628668,0.00022141548,0.005750066],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993249,0.00025961825,0.00002586864,0.0001476271,0.00019477693,0.00004725151],"domain_scores_gemma":[0.99943775,0.00025825202,0.0000731638,0.0000689728,0.00013417772,0.00002768486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011571044,0.0012213099,0.001094996,0.0007615707,0.00043934427,0.0007148887,0.0014387257,0.0015242485,0.000913203],"category_scores_gemma":[0.0022540833,0.00044451974,0.0011397054,0.00095158495,0.001025568,0.0014956426,0.0009363269,0.0015968987,0.00042941983],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000064090425,0.00007179025,0.00046622523,0.00015017124,0.00009507344,0.00009456543,0.00009521182,0.81725705,0.008148393,0.038387388,0.003674785,0.13149527],"study_design_scores_gemma":[0.0000019385177,0.000007916536,0.000037367674,0.0000023560224,0.0000020836208,0.000009857345,0.0000022661645,0.9966017,0.00028395434,0.0026762877,0.00037064502,0.0000036837823],"about_ca_topic_score_codex":0.004218201,"about_ca_topic_score_gemma":0.004040063,"teacher_disagreement_score":0.004218201,"about_ca_system_score_codex":0.0006618718,"about_ca_system_score_gemma":0.00094548165,"threshold_uncertainty_score":0.008387268},"labels":[],"label_agreement":null},{"id":"W4285387698","doi":"10.1371/journal.pone.0269174","title":"The effects of spectral dimensionality reduction on hyperspectral pixel classification: A case study","year":2022,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto; Ontario Tech University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; University of Ontario Institute of Technology","keywords":"Hyperspectral imaging; Pixel; Artificial intelligence; Computer science; Pattern recognition (psychology); Dimensionality reduction; Compression (physics); Image resolution; Image compression; Remote sensing; Computer vision; Image processing; Image (mathematics); Geography","score_opus":0.04489474016518771,"score_gpt":0.23722160141269655,"score_spread":0.19232686124750883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285387698","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.909245,0.0014357641,0.085702896,0.0005713494,0.000046989517,0.00024264547,0.0002717529,0.00027147986,0.0022120404],"genre_scores_gemma":[0.8987735,0.00077651715,0.09903944,0.00011645919,0.00004625809,0.00008955272,0.00033092586,0.00006558857,0.00076174346],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9968454,0.0012566411,0.0002425863,0.0003388789,0.0011756999,0.00014073895],"domain_scores_gemma":[0.97983897,0.0154611785,0.0010764005,0.00175288,0.0017471071,0.00012353185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00395028,0.00082422374,0.00060007954,0.0011729723,0.00069254165,0.0008587644,0.0006555676,0.0007828108,0.00065447146],"category_scores_gemma":[0.019254517,0.00021634965,0.00064546627,0.0017503243,0.001037514,0.0014885745,0.0009258148,0.0007731325,0.00016134167],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017311907,0.0015165168,0.04066767,0.0011988846,0.0004895322,0.0013628886,0.0014350618,0.18473223,0.08463809,0.0036233955,0.0029627716,0.67564183],"study_design_scores_gemma":[0.00016748621,0.0027861816,0.082176864,0.0001950322,0.00040878027,0.0032672698,0.001213162,0.6983237,0.19872439,0.0053110057,0.0072439723,0.00018217233],"about_ca_topic_score_codex":0.0024647159,"about_ca_topic_score_gemma":0.003701375,"teacher_disagreement_score":0.00395028,"about_ca_system_score_codex":0.00053225923,"about_ca_system_score_gemma":0.00037636366,"threshold_uncertainty_score":0.020891368},"labels":[],"label_agreement":null},{"id":"W4288081641","doi":"10.18280/ts.390309","title":"Feature Extraction of Hyperspectral Images Based on Subspace Band Selection and Transform-Domain Recursive Filtering","year":2022,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Hyperspectral imaging; Pattern recognition (psychology); Artificial intelligence; Feature extraction; Subspace topology; Classifier (UML); Feature selection; Support vector machine; Computer science; Filter (signal processing); Mathematics; Computer vision","score_opus":0.008081799769599251,"score_gpt":0.2111390492245107,"score_spread":0.20305724945491146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288081641","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01361958,0.00017015703,0.9850603,0.00004839597,0.000019767711,0.000040012692,0.00005291285,0.00047158072,0.0005172055],"genre_scores_gemma":[0.20656528,0.00053709827,0.7897248,0.00008776237,0.00008375031,0.00022144108,0.00059319066,0.00012866459,0.0020580022],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99952996,0.00006969397,0.000029211542,0.0001041736,0.00021810198,0.000048925634],"domain_scores_gemma":[0.999705,0.00008251298,0.000043112268,0.000037878784,0.00011999204,0.000011387144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044223366,0.0007137049,0.0009069403,0.0013587693,0.0003652911,0.00053436495,0.0004531883,0.0004382609,0.00079636485],"category_scores_gemma":[0.00090709707,0.00022558511,0.0011027035,0.0012818224,0.000314551,0.0008011467,0.00034266908,0.0005406946,0.0005329146],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014993134,0.00014086695,0.001559008,0.00013754421,0.00010538238,0.00014241492,0.00012206198,0.04822673,0.18127415,0.0043581007,0.0025592905,0.76122445],"study_design_scores_gemma":[0.000015348376,0.00010831158,0.004447346,0.00001472354,0.000055431676,0.0003605978,0.000043954442,0.9290651,0.058484357,0.0028180114,0.0045388523,0.00004801157],"about_ca_topic_score_codex":0.0013886212,"about_ca_topic_score_gemma":0.0016176985,"teacher_disagreement_score":0.0013886212,"about_ca_system_score_codex":0.00022021001,"about_ca_system_score_gemma":0.00040632393,"threshold_uncertainty_score":0.002761066},"labels":[],"label_agreement":null},{"id":"W4289792768","doi":"10.1109/tgrs.2022.3195924","title":"Semisupervised Hyperspectral Image Classification Using a Probabilistic Pseudo-Label Generation Framework","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University; Université du Québec à Montréal","funders":"","keywords":"Discriminative model; Artificial intelligence; Computer science; Pattern recognition (psychology); Probabilistic logic; Hyperspectral imaging; Generalization; Feature (linguistics); Contextual image classification; Deep learning; Machine learning; Feature vector; Deep neural networks; Image (mathematics); Mathematics","score_opus":0.04445046404394893,"score_gpt":0.2632989039640681,"score_spread":0.21884843992011915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289792768","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015959786,0.00015547502,0.98129946,0.00017744633,0.00003260671,0.00007931721,0.00014934984,0.0009934964,0.0011530428],"genre_scores_gemma":[0.5199171,0.00025868116,0.47304294,0.00046624884,0.00013947963,0.000438074,0.0015921335,0.00019059044,0.0039547994],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990374,0.00029242833,0.000038739632,0.00030810246,0.00024697842,0.00007643604],"domain_scores_gemma":[0.9984717,0.0005831277,0.00025758447,0.0002895992,0.00033679616,0.000061100334],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014239508,0.0009087074,0.00075950444,0.0006532597,0.00041705527,0.0006732207,0.0023533213,0.0011047286,0.001386812],"category_scores_gemma":[0.0027898839,0.00041348144,0.0007551829,0.0006976966,0.0011362842,0.0019839355,0.001302429,0.0017851372,0.0004691887],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003794898,0.00035307373,0.002413966,0.00019804858,0.00007713745,0.00016515431,0.0002170597,0.52049667,0.017754968,0.02832398,0.0070401295,0.42258033],"study_design_scores_gemma":[0.000008106641,0.000018315575,0.000103586324,0.0000046959217,0.000004392951,0.000021633217,0.000004929556,0.9916437,0.002642084,0.005007474,0.00053460547,0.000006474664],"about_ca_topic_score_codex":0.0023216025,"about_ca_topic_score_gemma":0.0038842533,"teacher_disagreement_score":0.0023533213,"about_ca_system_score_codex":0.000852431,"about_ca_system_score_gemma":0.0011259823,"threshold_uncertainty_score":0.0075306892},"labels":[],"label_agreement":null},{"id":"W4292970091","doi":"10.1109/lgrs.2022.3201489","title":"SatViT: Pretraining Transformers for Earth Observation","year":2022,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Transformer; Artificial intelligence; Training set; Machine learning; Pattern recognition (psychology); Voltage; Engineering","score_opus":0.02533367531391046,"score_gpt":0.22197562040925445,"score_spread":0.196641945095344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292970091","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05817622,0.0010026623,0.7081767,0.00072115613,0.00091195374,0.00045816923,0.011273467,0.20690402,0.012375708],"genre_scores_gemma":[0.39568633,0.0005767694,0.50522125,0.0013994968,0.00017113495,0.00069424,0.06674218,0.007641296,0.02186731],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99967754,0.000039365896,0.00001607069,0.00015694185,0.0000656955,0.000044468423],"domain_scores_gemma":[0.9994017,0.00017309758,0.0000345266,0.00019329408,0.00015543055,0.000041929583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008502695,0.0018729987,0.0006361073,0.00085345266,0.00043972113,0.0010892677,0.0029662424,0.0011216849,0.015373633],"category_scores_gemma":[0.003458437,0.0010189086,0.0013607187,0.0008776272,0.00056828064,0.0023326266,0.0014990517,0.0026822125,0.010756392],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044393455,0.00037925068,0.007907958,0.00047509006,0.00033711732,0.00015763969,0.00014501385,0.2161631,0.017820619,0.0075938767,0.16596483,0.5826116],"study_design_scores_gemma":[0.00005494158,0.000094811476,0.0010772176,0.00003423887,0.000033730616,0.000062911764,0.0000490794,0.9641299,0.013570358,0.006333742,0.014535618,0.000023478318],"about_ca_topic_score_codex":0.012218994,"about_ca_topic_score_gemma":0.025649719,"teacher_disagreement_score":0.015373633,"about_ca_system_score_codex":0.0010437483,"about_ca_system_score_gemma":0.001268298,"threshold_uncertainty_score":0.051429987},"labels":[],"label_agreement":null},{"id":"W4293023455","doi":"10.1145/3487553.3524716","title":"Unsupervised Superpixel-Driven Parcel Segmentation of Remote Sensing Images Using Graph Convolutional Network","year":2022,"lang":"en","type":"article","venue":"Companion Proceedings of the Web Conference 2022","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Segmentation; Robustness (evolution); Graph; Ground truth; Pattern recognition (psychology); Image segmentation; Construct (python library)","score_opus":0.029344592515140665,"score_gpt":0.23092127261375422,"score_spread":0.20157668009861357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293023455","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.119081415,0.0006245712,0.87009287,0.00033118637,0.000064391614,0.00012446872,0.0007383314,0.0061503975,0.0027923898],"genre_scores_gemma":[0.7079933,0.00039255252,0.28190807,0.00027192043,0.000054624703,0.00012015629,0.0029464813,0.00042769182,0.005885223],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997694,0.00002393481,0.0000068067466,0.00010606679,0.00004392103,0.000049856746],"domain_scores_gemma":[0.99976236,0.00005328298,0.00004263752,0.000052455653,0.000063550506,0.000025748843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036731389,0.0011223326,0.0007884616,0.001104886,0.0003737468,0.00068068015,0.0018144897,0.0009602925,0.0011039549],"category_scores_gemma":[0.0005789726,0.00052325724,0.00088142604,0.0011591287,0.00059154624,0.0011639289,0.0007178437,0.0010121564,0.00051606],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025127674,0.00020218747,0.004217614,0.0001152601,0.00015646547,0.0001768585,0.00013615974,0.7120521,0.031986468,0.0043153306,0.005462291,0.24092802],"study_design_scores_gemma":[0.0000022146903,0.000006504869,0.0003732569,0.000002368507,0.0000055443847,0.000011276628,0.000005606376,0.9965491,0.0019033987,0.00087080925,0.00026642438,0.0000034234113],"about_ca_topic_score_codex":0.033266526,"about_ca_topic_score_gemma":0.06269734,"teacher_disagreement_score":0.033266526,"about_ca_system_score_codex":0.0014993922,"about_ca_system_score_gemma":0.0012217974,"threshold_uncertainty_score":0.06614578},"labels":[],"label_agreement":null},{"id":"W4293234904","doi":"10.1109/icgmrs55602.2022.9849283","title":"Building Instance Change Detection from High Spatial Resolution Remote Sensing Images with Improved Instance Segmentation Architecture","year":2022,"lang":"en","type":"article","venue":"2022 3rd International Conference on Geology, Mapping and Remote Sensing (ICGMRS)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Research and Development; Ministry of Natural Resources","keywords":"Change detection; Computer science; Remote sensing; Segmentation; Architecture; Artificial intelligence; Image resolution; Deep learning; Spatial analysis; Convolutional neural network; Image segmentation; Test set; Multispectral image; Data mining; Pattern recognition (psychology); Geography","score_opus":0.023761258656952226,"score_gpt":0.23579315384617328,"score_spread":0.21203189518922105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293234904","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28668883,0.0009907595,0.68357915,0.00048673147,0.0001953233,0.0002881787,0.0016149376,0.02067602,0.005480055],"genre_scores_gemma":[0.67368644,0.0004607473,0.31063434,0.00038806512,0.00007792772,0.00012378504,0.008198,0.00036051456,0.0060702357],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995321,0.000035179277,0.000022581398,0.00022390662,0.0001186617,0.00006749884],"domain_scores_gemma":[0.9996755,0.000043099855,0.000034631772,0.000105330895,0.00010028254,0.000040996005],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042909043,0.0012286742,0.0010118411,0.0011240939,0.00027550833,0.0008902408,0.0018641079,0.00094912306,0.0017253722],"category_scores_gemma":[0.0011263089,0.00038603434,0.0009957701,0.0009344095,0.00032815256,0.0015393147,0.0008791542,0.0012772809,0.0011157144],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047237973,0.0003420356,0.006825936,0.00013262521,0.00021572718,0.0003567587,0.000113789465,0.12753777,0.07488676,0.0021095397,0.011588392,0.77541834],"study_design_scores_gemma":[0.000013115827,0.00006791601,0.0025690089,0.000005653175,0.000033546046,0.0001436314,0.000023965797,0.98042244,0.0146361105,0.0008000512,0.0012695438,0.000015039305],"about_ca_topic_score_codex":0.010919849,"about_ca_topic_score_gemma":0.01676784,"teacher_disagreement_score":0.010919849,"about_ca_system_score_codex":0.0006527708,"about_ca_system_score_gemma":0.0007489905,"threshold_uncertainty_score":0.021712542},"labels":[],"label_agreement":null},{"id":"W4293868147","doi":"10.1109/crv55824.2022.00023","title":"Inter- &amp; Intra-City Image Geolocalization","year":2022,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Geolocation; Computer science; Convolutional neural network; Leverage (statistics); Pixel; Artificial intelligence; Deep learning; Image resolution; Computer vision; Pattern recognition (psychology)","score_opus":0.016889210805731046,"score_gpt":0.22664385068841433,"score_spread":0.20975463988268328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293868147","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33866704,0.0015485074,0.6250678,0.002287795,0.00036603498,0.00010113158,0.0031720346,0.0071001435,0.021689564],"genre_scores_gemma":[0.89590657,0.0005114386,0.09227087,0.00031060443,0.000088085995,0.00003129713,0.0040360796,0.00029265555,0.0065524476],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995376,0.000055679026,0.000012824556,0.00022498301,0.00007429022,0.000094649644],"domain_scores_gemma":[0.99922466,0.00013302444,0.00011261464,0.0003312142,0.00014998647,0.000048566406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006854178,0.00055705407,0.00044105318,0.0005592899,0.00034940246,0.0011986592,0.0011720374,0.0009193727,0.0036580039],"category_scores_gemma":[0.0028520012,0.00020587211,0.00039507775,0.00094005896,0.0007211263,0.0022717349,0.0013372584,0.0012275594,0.0039752047],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006646919,0.00016551251,0.038881868,0.00021132981,0.00013628794,0.00030717242,0.00043938565,0.19156642,0.022277797,0.009218192,0.03591783,0.70021355],"study_design_scores_gemma":[0.000017962386,0.00007529466,0.018654207,0.000047970552,0.000042529962,0.00027430552,0.00059300585,0.92262024,0.023055583,0.013747851,0.020830574,0.000040621944],"about_ca_topic_score_codex":0.008966274,"about_ca_topic_score_gemma":0.01901829,"teacher_disagreement_score":0.008966274,"about_ca_system_score_codex":0.0007687811,"about_ca_system_score_gemma":0.00061862497,"threshold_uncertainty_score":0.017828166},"labels":[],"label_agreement":null},{"id":"W4294142862","doi":"10.3390/rs14174298","title":"UAV-Based Multi-Sensor Data Fusion for Urban Land Cover Mapping Using a Deep Convolutional Neural Network","year":2022,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Lidar; Land cover; Computer science; Convolutional neural network; Remote sensing; Artificial intelligence; Sensor fusion; Classifier (UML); Ranging; Reference data; Pattern recognition (psychology); Land use; Data mining; Geography","score_opus":0.08205630244870482,"score_gpt":0.2697713388696633,"score_spread":0.1877150364209585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294142862","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31687203,0.0011017348,0.6736155,0.0002997181,0.00021534262,0.000082503415,0.0006822969,0.0036098766,0.0035209514],"genre_scores_gemma":[0.92323244,0.00024090994,0.073958285,0.00009359484,0.000025023437,0.000043460645,0.0008514315,0.00002846728,0.0015263646],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99983716,0.000013310743,0.0000088748275,0.000051012546,0.00005630088,0.00003336913],"domain_scores_gemma":[0.99987864,0.00002002079,0.000018852652,0.000019642974,0.00005383004,0.00000891187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025215547,0.0006598438,0.0004047488,0.0006056129,0.00021450862,0.00032727807,0.0005301307,0.00039806828,0.0005353012],"category_scores_gemma":[0.0004102032,0.00023483424,0.0004610155,0.00065491005,0.00018067614,0.0007147947,0.0006076452,0.0005878418,0.00021944435],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026691722,0.00029050853,0.008772262,0.00011883363,0.0002115025,0.0002954362,0.00013413104,0.45919874,0.052621078,0.0013277429,0.0037520009,0.47301096],"study_design_scores_gemma":[0.0000029406249,0.000031025513,0.0020300902,0.000004088728,0.000015749363,0.000023280802,0.000016817892,0.99097496,0.0060829394,0.0003490261,0.00046181882,0.0000073021934],"about_ca_topic_score_codex":0.011946805,"about_ca_topic_score_gemma":0.013721211,"teacher_disagreement_score":0.011946805,"about_ca_system_score_codex":0.00057291944,"about_ca_system_score_gemma":0.0004321239,"threshold_uncertainty_score":0.023754537},"labels":[],"label_agreement":null},{"id":"W4294310964","doi":"10.1109/jstars.2022.3203672","title":"Spatiotemporal Subpixel Mapping Based on Priori Remote Sensing Image With Variation Differences","year":2022,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Fundamental Research Funds for the Central Universities; Sichuan Normal University; Nanjing University of Aeronautics and Astronautics; Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China","keywords":"Subpixel rendering; Thematic map; Computer science; Pixel; A priori and a posteriori; Artificial intelligence; Image resolution; Computer vision; Pattern recognition (psychology); Upsampling; Variation (astronomy); Image (mathematics); Remote sensing; Geography; Cartography","score_opus":0.02408920535283145,"score_gpt":0.20892967222777747,"score_spread":0.184840466874946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294310964","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034739,0.0003136136,0.9618132,0.00009630328,0.000049737046,0.000043265118,0.0001774171,0.0007446196,0.0020228315],"genre_scores_gemma":[0.41797456,0.0007106276,0.576086,0.00012854637,0.000085306754,0.00014261172,0.0010849608,0.0002364846,0.0035509244],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996277,0.000045414803,0.000015193119,0.00012265003,0.00015490671,0.000034099732],"domain_scores_gemma":[0.99976677,0.000038414528,0.00003506112,0.00006616346,0.00007713009,0.00001651944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003356628,0.0008347693,0.0005486118,0.00083249307,0.0002114075,0.0006343657,0.0007232591,0.00031906363,0.0011916494],"category_scores_gemma":[0.0007755048,0.00032856766,0.0007834395,0.0009855598,0.00030164185,0.0014698921,0.0007477222,0.0007056153,0.00048197142],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002135241,0.000093086885,0.004385756,0.00033492572,0.00014778257,0.00023273996,0.0003633903,0.12719868,0.13008611,0.009802631,0.003813146,0.7233283],"study_design_scores_gemma":[0.000021679021,0.00010423203,0.005743041,0.00002261708,0.00006301106,0.00040596043,0.00011485988,0.942864,0.03542335,0.0073383753,0.007842978,0.000055940345],"about_ca_topic_score_codex":0.0025821982,"about_ca_topic_score_gemma":0.003332921,"teacher_disagreement_score":0.0025821982,"about_ca_system_score_codex":0.00030040892,"about_ca_system_score_gemma":0.00053248886,"threshold_uncertainty_score":0.005134344},"labels":[],"label_agreement":null},{"id":"W4294662183","doi":"10.1016/j.isprsjprs.2022.08.024","title":"A hybrid image segmentation method for building extraction from high-resolution RGB images","year":2022,"lang":"en","type":"article","venue":"ISPRS Journal of Photogrammetry and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":34,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Computer vision; Image segmentation; Segmentation; Computer science; RGB color model; Extraction (chemistry); Scale-space segmentation; Image (mathematics); Pattern recognition (psychology)","score_opus":0.012847159214715001,"score_gpt":0.2815700863358796,"score_spread":0.2687229271211646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294662183","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017078385,0.0005038193,0.97699386,0.000058854297,0.00008664686,0.000097570686,0.00028821177,0.003164296,0.0017283128],"genre_scores_gemma":[0.10948355,0.000641533,0.87974024,0.00009254807,0.00007763456,0.00016492546,0.0017052409,0.0005906577,0.007503772],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995147,0.00002861372,0.000030817922,0.00013682959,0.0002297256,0.00005926775],"domain_scores_gemma":[0.9997321,0.000046806646,0.000024306324,0.000039051243,0.00014162394,0.00001610308],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035209974,0.0010734474,0.0010418226,0.0027680986,0.00051844725,0.0010541485,0.0012416744,0.0007749223,0.0037351095],"category_scores_gemma":[0.00043652847,0.00068479433,0.0013711975,0.0022199305,0.00038161463,0.0008226705,0.0006731113,0.0006120299,0.0027635572],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014631364,0.00012017289,0.0011404643,0.00028194627,0.00014959779,0.000100563644,0.00011155259,0.014716436,0.21368557,0.0014292791,0.003322478,0.7647956],"study_design_scores_gemma":[0.000039095798,0.00016427718,0.012376618,0.00004898178,0.0002365508,0.00077703205,0.000112661255,0.7484332,0.21338393,0.002359381,0.021955587,0.000112812304],"about_ca_topic_score_codex":0.0073229247,"about_ca_topic_score_gemma":0.014629252,"teacher_disagreement_score":0.0073229247,"about_ca_system_score_codex":0.0004096366,"about_ca_system_score_gemma":0.001085843,"threshold_uncertainty_score":0.01456064},"labels":[],"label_agreement":null},{"id":"W4294811189","doi":"10.1109/tgrs.2022.3204770","title":"CLT-Det: Correlation Learning Based on Transformer for Detecting Dense Objects in Remote Sensing Images","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Six Talent Peaks Project in Jiangsu Province; Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China","keywords":"Remote sensing; Computer science; Correlation; Artificial intelligence; Computer vision; Pattern recognition (psychology); Geology; Mathematics","score_opus":0.013922604750652417,"score_gpt":0.2328524880188753,"score_spread":0.21892988326822288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294811189","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041878376,0.0006531343,0.94931,0.00020313705,0.00010368518,0.00015811037,0.000299717,0.004871994,0.0025219289],"genre_scores_gemma":[0.6076111,0.0007738976,0.38053712,0.00069470314,0.00016988785,0.00019817323,0.0028339317,0.0003982392,0.0067830114],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992736,0.00008946476,0.000031377,0.00023186477,0.00025182535,0.00012193481],"domain_scores_gemma":[0.99917334,0.00023945956,0.00009566875,0.00014245551,0.00027139473,0.000077647186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009877915,0.001278016,0.0013167703,0.0016179526,0.0004762847,0.00082160666,0.0020695315,0.0007999406,0.0020919242],"category_scores_gemma":[0.002301043,0.00035962314,0.0010795395,0.0017263638,0.0005419243,0.0015088696,0.0016922358,0.0013340076,0.0012076027],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003938091,0.00040274495,0.005954504,0.00020862135,0.00019809842,0.00027238147,0.00008675906,0.053887706,0.04171156,0.004792275,0.0149734765,0.87711805],"study_design_scores_gemma":[0.000034529075,0.00014677343,0.0020150489,0.000009553073,0.00005304407,0.00029997338,0.000035208155,0.9773826,0.014510939,0.0029480946,0.0025410685,0.000023217124],"about_ca_topic_score_codex":0.0075161955,"about_ca_topic_score_gemma":0.011590472,"teacher_disagreement_score":0.0075161955,"about_ca_system_score_codex":0.0007090951,"about_ca_system_score_gemma":0.0014546522,"threshold_uncertainty_score":0.014944911},"labels":[],"label_agreement":null},{"id":"W4294959509","doi":"10.3390/electronics11172799","title":"Multi-Class Pixel Certainty Active Learning Model for Classification of Land Cover Classes Using Hyperspectral Imagery","year":2022,"lang":"en","type":"article","venue":"Electronics","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":58,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Contextual image classification; Heuristics; Land cover; Data mining; Image segmentation; Segmentation; Machine learning; Image (mathematics)","score_opus":0.03705877885446925,"score_gpt":0.2704514693021981,"score_spread":0.23339269044772884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294959509","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0782036,0.0008640843,0.9172513,0.00045058999,0.000063624655,0.000085017,0.00010139227,0.00046273775,0.0025176352],"genre_scores_gemma":[0.9564652,0.0003111687,0.038979378,0.00014497734,0.00007521978,0.0001879054,0.00018267523,0.000020373016,0.0036330712],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994997,0.0001285671,0.000031954027,0.00016195189,0.000110734785,0.00006718723],"domain_scores_gemma":[0.99910456,0.00050393137,0.00010875812,0.000045599558,0.00020334122,0.000033830205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014243495,0.000623807,0.0011280807,0.0006482061,0.0003171288,0.0011918333,0.0020823325,0.0011292767,0.0012568645],"category_scores_gemma":[0.0020747366,0.00037571267,0.00075336284,0.0006240812,0.00081993866,0.0010621793,0.00072747655,0.0015272864,0.00027846443],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019534687,0.00016681614,0.0021647534,0.00008545948,0.00007754557,0.00007675024,0.00014955613,0.8912335,0.0020057054,0.0072767404,0.00074538053,0.095822416],"study_design_scores_gemma":[0.0000019669715,0.000009233224,0.00007049389,0.0000016971561,0.000002951037,0.0000027477008,0.0000023134521,0.9992047,0.00013503297,0.0005211128,0.00004599592,0.0000019250015],"about_ca_topic_score_codex":0.006208328,"about_ca_topic_score_gemma":0.004118508,"teacher_disagreement_score":0.006208328,"about_ca_system_score_codex":0.00087835954,"about_ca_system_score_gemma":0.00057903334,"threshold_uncertainty_score":0.01234436},"labels":[],"label_agreement":null},{"id":"W4295854875","doi":"10.1080/01431161.2022.2115863","title":"Unsupervised change detection in SAR images based on generalized likelihood ratio test and a two-stage morphological filter","year":2022,"lang":"en","type":"article","venue":"International Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Speckle noise; Synthetic aperture radar; Speckle pattern; Computer science; Likelihood-ratio test; Change detection; Artificial intelligence; Matched filter; Pixel; Pattern recognition (psychology); Noise (video); Filter (signal processing); Mathematics; Computer vision; Statistics; Image (mathematics)","score_opus":0.027585013622797857,"score_gpt":0.2603106715957832,"score_spread":0.23272565797298533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4295854875","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05004408,0.00017235691,0.94740885,0.00006914844,0.000030517096,0.00010803476,0.00007520796,0.0014058638,0.0006859263],"genre_scores_gemma":[0.37280452,0.00021384386,0.62451357,0.00008690734,0.00005455088,0.00028494382,0.0005313713,0.00015182517,0.0013584896],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99802065,0.00037666605,0.00015729212,0.0005793736,0.00073151564,0.00013443864],"domain_scores_gemma":[0.99798167,0.0008289428,0.00036081762,0.00017618755,0.0005640847,0.000088285065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021127055,0.0009703841,0.0013084643,0.0031815683,0.0003992479,0.0011660985,0.00138161,0.0010727411,0.001046606],"category_scores_gemma":[0.0043327278,0.00045224818,0.0016823226,0.0018900521,0.0008042836,0.001655219,0.00094645907,0.0009444274,0.0004811374],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00062333106,0.0003507197,0.011474553,0.0003818844,0.00037844453,0.00059686747,0.00031401723,0.058200236,0.13537288,0.0046328595,0.0018361,0.785838],"study_design_scores_gemma":[0.00006316449,0.00035319725,0.01285229,0.000017826764,0.0000855364,0.0008443094,0.000096910095,0.9309184,0.05114223,0.001984022,0.0015487496,0.00009337145],"about_ca_topic_score_codex":0.0020194827,"about_ca_topic_score_gemma":0.0020459616,"teacher_disagreement_score":0.0031815683,"about_ca_system_score_codex":0.00048267463,"about_ca_system_score_gemma":0.0009131895,"threshold_uncertainty_score":0.011173189},"labels":[],"label_agreement":null},{"id":"W4296448752","doi":"10.1080/07038992.2022.2114440","title":"Hyperspectral Image Classification Based on Novel Hybridization of Spatial-Spectral-Superpixelwise Principal Component Analysis and Dense 2D-3D Convolutional Neural Network Fusion Architecture","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Pattern recognition (psychology); Artificial intelligence; Principal component analysis; Convolutional neural network; Computer science; Hyperspectral imaging; Feature extraction; Kernel (algebra); Pixel; Dimensionality reduction; Feature (linguistics); Convolution (computer science); Block (permutation group theory); Artificial neural network; Mathematics","score_opus":0.013241864455805927,"score_gpt":0.20487536028134495,"score_spread":0.191633495825539,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296448752","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052342247,0.00043227494,0.9421188,0.00016467657,0.00007419158,0.000070540096,0.0001812946,0.0019665265,0.0026494374],"genre_scores_gemma":[0.6120541,0.00041380385,0.3815036,0.00022796108,0.00006638292,0.00014558333,0.0010615662,0.000093618495,0.0044333707],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996408,0.000032772434,0.000014484796,0.00011546177,0.00013718291,0.00005924827],"domain_scores_gemma":[0.9997893,0.000031355645,0.000022869024,0.000038587197,0.000100802456,0.000017096416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043895724,0.0009276169,0.0006917917,0.0011440531,0.0003257633,0.00067248935,0.0011276734,0.00063191005,0.0010968565],"category_scores_gemma":[0.00065217103,0.0004142774,0.00084560836,0.000941251,0.0003980713,0.001247993,0.0010487215,0.0006191986,0.00038407856],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019803751,0.00023232709,0.006218517,0.00011180832,0.00025896836,0.00015863591,0.000121904086,0.19327922,0.07504104,0.0062553613,0.004348175,0.713776],"study_design_scores_gemma":[0.0000039274414,0.000027842545,0.0011615081,0.0000044084654,0.000021675878,0.00004024458,0.000011858601,0.9887888,0.007866383,0.0011595846,0.00090366433,0.000010253763],"about_ca_topic_score_codex":0.010376487,"about_ca_topic_score_gemma":0.013109767,"teacher_disagreement_score":0.010376487,"about_ca_system_score_codex":0.0007061058,"about_ca_system_score_gemma":0.0009257628,"threshold_uncertainty_score":0.020632148},"labels":[],"label_agreement":null},{"id":"W4296701482","doi":"10.1080/07038992.2022.2116566","title":"Optimal and Fully Connected Deep Neural Networks Based Classification Model for Unmanned Aerial Vehicle Using Hyperspectral Remote Sensing Images","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Aerial image; Computer science; Artificial intelligence; Hyperspectral imaging; Artificial neural network; Hyperparameter; Remote sensing; Contextual image classification; Deep learning; Deep neural networks; Range (aeronautics); Pattern recognition (psychology); Image (mathematics); Machine learning; Geography; Engineering","score_opus":0.02763146532977546,"score_gpt":0.23039594991134277,"score_spread":0.20276448458156732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296701482","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18131693,0.0011111575,0.8081504,0.0005913154,0.000107188265,0.00008136719,0.00026774756,0.0010190303,0.0073548546],"genre_scores_gemma":[0.92714083,0.00027907602,0.064771876,0.00015634485,0.000027370363,0.00010954014,0.00039247386,0.000041232783,0.0070811566],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998933,0.000017543558,0.0000054220263,0.000037653987,0.000022687705,0.000023468196],"domain_scores_gemma":[0.9998746,0.0000456374,0.000019309078,0.000008792004,0.00004294087,0.0000086891105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028873084,0.00056975585,0.00037848542,0.00031491768,0.00023867481,0.0005351571,0.00092088507,0.00077144755,0.0013806656],"category_scores_gemma":[0.0005435497,0.00026355876,0.0004884129,0.0003045648,0.00026248247,0.0006749153,0.0004345814,0.00087393966,0.00025118105],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056299046,0.000054351687,0.00077116716,0.000035698726,0.00002425899,0.000043791082,0.000025345302,0.9442788,0.0021697923,0.001449455,0.0009290606,0.050162017],"study_design_scores_gemma":[7.7195295e-7,0.000005966035,0.000052235097,0.0000012849702,0.0000015741833,0.0000018274732,0.000001848976,0.99949527,0.00018856561,0.00020067325,0.000049082497,8.6522266e-7],"about_ca_topic_score_codex":0.014076393,"about_ca_topic_score_gemma":0.015050325,"teacher_disagreement_score":0.014076393,"about_ca_system_score_codex":0.0008130764,"about_ca_system_score_gemma":0.0007752171,"threshold_uncertainty_score":0.02798891},"labels":[],"label_agreement":null},{"id":"W4297792972","doi":"10.48550/arxiv.1304.4077","title":"A new Bayesian ensemble of trees classifier for identifying multi-class\\n labels in satellite images","year":2013,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Classifier (UML); Computer science; Artificial intelligence; Pattern recognition (psychology); Pixel; Multiclass classification; Contextual image classification; Parametric statistics; Binary classification; Bayesian probability; Satellite imagery; Remote sensing; Machine learning; Data mining; Geography; Image (mathematics); Mathematics; Support vector machine; Statistics","score_opus":0.1180687927276282,"score_gpt":0.22695778613327708,"score_spread":0.10888899340564888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297792972","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046335105,0.0013500458,0.9481623,0.00026124006,0.00022940393,0.00012503882,0.00046606618,0.0013809511,0.0016899296],"genre_scores_gemma":[0.44402748,0.0009464921,0.54605055,0.00033504286,0.00042639184,0.00029798856,0.0023939891,0.00019823854,0.0053238557],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982508,0.00034099672,0.00009723773,0.00035068186,0.000809324,0.000150932],"domain_scores_gemma":[0.9983329,0.0005487948,0.00013265324,0.00014449857,0.0007697772,0.00007132177],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022872319,0.0008900249,0.0016086433,0.0020941263,0.00065110315,0.001000484,0.0018120861,0.0015810641,0.0010626515],"category_scores_gemma":[0.0044251354,0.00034442308,0.0009923701,0.0014352936,0.00025627288,0.0017092777,0.0006233945,0.0014252444,0.0008469195],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032193394,0.00029238962,0.00719963,0.00012147244,0.00022707116,0.00014737777,0.00009376892,0.122677624,0.012879052,0.0038720928,0.011745392,0.84042233],"study_design_scores_gemma":[0.000008999896,0.00004254915,0.0011330366,0.000012085681,0.00003794084,0.0000501439,0.000012937363,0.9936773,0.0021752198,0.0013238066,0.0015121878,0.0000137466095],"about_ca_topic_score_codex":0.0082565015,"about_ca_topic_score_gemma":0.012332498,"teacher_disagreement_score":0.0082565015,"about_ca_system_score_codex":0.0006826574,"about_ca_system_score_gemma":0.0009263063,"threshold_uncertainty_score":0.016416848},"labels":[],"label_agreement":null},{"id":"W4300666872","doi":"","title":"Gas Plume Detection and Tracking in Hyperspectral Video Sequences using Binary Partition Trees","year":2014,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Hyperspectral imaging; Tracking (education); Plume; Partition (number theory); Computer science; Binary number; Artificial intelligence; Computer vision; Remote sensing; Geology; Mathematics; Meteorology; Geography; Combinatorics","score_opus":0.01744159864490559,"score_gpt":0.2216728690534101,"score_spread":0.20423127040850453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300666872","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24115354,0.00051210454,0.75511026,0.00017403303,0.000051266037,0.00006578485,0.0003324334,0.000857393,0.0017432217],"genre_scores_gemma":[0.73969036,0.00041191405,0.25665024,0.00007399901,0.000053837168,0.00005958288,0.00095254905,0.00007177738,0.0020357396],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998722,0.000020344343,0.0000055581536,0.000039547194,0.00003632403,0.000025928239],"domain_scores_gemma":[0.99969983,0.0001414083,0.00004136823,0.000021114985,0.00007211658,0.000024246458],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023410234,0.0004635356,0.00049448205,0.0012197491,0.00034062448,0.00057015347,0.0004235285,0.0005321697,0.0007599319],"category_scores_gemma":[0.0008774687,0.00018040606,0.0004049991,0.0010006726,0.0002896324,0.0006383765,0.00037263538,0.0004117733,0.0003313279],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006250165,0.00021621994,0.0045669703,0.00012681124,0.000074517906,0.00017396864,0.00018140237,0.29076728,0.111653976,0.0034906517,0.0024414884,0.5856816],"study_design_scores_gemma":[0.0000041311055,0.000029160286,0.0016425947,0.0000055356318,0.000008219814,0.00004111385,0.000025677478,0.9888404,0.0075332895,0.0014706218,0.00039361583,0.0000056379317],"about_ca_topic_score_codex":0.0062835272,"about_ca_topic_score_gemma":0.007007683,"teacher_disagreement_score":0.0062835272,"about_ca_system_score_codex":0.00039106773,"about_ca_system_score_gemma":0.00042512285,"threshold_uncertainty_score":0.012493908},"labels":[],"label_agreement":null},{"id":"W4300889849","doi":"10.1080/07038992.2021.1992594","title":"A New Endmember Extraction Method Based on Least Squares","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Canadian Space Agency; Concordia University","funders":"","keywords":"Endmember; Hyperspectral imaging; Data cube; Pixel; Pattern recognition (psychology); Cube (algebra); Artificial intelligence; Computer science; Spectral signature; Curse of dimensionality; Least-squares function approximation; Noise (video); Mathematics; Algorithm; Geography; Image (mathematics); Remote sensing; Data mining; Statistics; Combinatorics","score_opus":0.021790979310712,"score_gpt":0.2614371411031999,"score_spread":0.23964616179248788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300889849","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027011526,0.00009133085,0.99567467,0.000035277393,0.00003770521,0.000025916514,0.000058904287,0.000999268,0.0003757552],"genre_scores_gemma":[0.024791492,0.0001329388,0.97161305,0.00006607159,0.000041454172,0.00007650534,0.0003454783,0.0002682448,0.0026646513],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999038,0.00008688636,0.000052391457,0.00028920468,0.00048468067,0.00004882075],"domain_scores_gemma":[0.99933606,0.00011604223,0.00006520837,0.00008252431,0.0003696487,0.000030484824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006355603,0.0013702172,0.0011198998,0.0020775264,0.0007018132,0.00085830706,0.0014867131,0.00097304065,0.0024756286],"category_scores_gemma":[0.001163433,0.0007413745,0.00119069,0.0015819978,0.00053492456,0.0018005009,0.0011965449,0.0013668214,0.0028890357],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013595338,0.00011184297,0.001435908,0.0002661518,0.00016615455,0.0001285635,0.00013987173,0.03355528,0.13386148,0.0034310077,0.005443015,0.82132477],"study_design_scores_gemma":[0.000026529035,0.00006543071,0.0017920332,0.000020173951,0.000045460183,0.00037164416,0.000043624175,0.9019516,0.07752948,0.0032957594,0.014771892,0.00008636203],"about_ca_topic_score_codex":0.0022277092,"about_ca_topic_score_gemma":0.003533918,"teacher_disagreement_score":0.0024756286,"about_ca_system_score_codex":0.00032179468,"about_ca_system_score_gemma":0.00089939847,"threshold_uncertainty_score":0.008281767},"labels":[],"label_agreement":null},{"id":"W4307849690","doi":"10.36227/techrxiv.21430644","title":"Image Prediction Using Coordinated Hyperspectral and RGB Video of Dynamic Natural Water Scenes","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Hyperspectral imaging; RGB color model; Remote sensing; Artificial intelligence; Computer science; Computer vision; Chemical imaging; Geography","score_opus":0.011375282218481482,"score_gpt":0.23625951190165892,"score_spread":0.22488422968317745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307849690","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87164295,0.00004664393,0.12316104,0.000093114584,0.000027935095,0.000052425476,0.0010288265,0.0014831478,0.0024639778],"genre_scores_gemma":[0.96611875,0.000030261079,0.031679828,0.00001770785,0.0000066019575,0.000022062715,0.000911104,0.000056765828,0.0011570365],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.99989974,0.000006555985,0.0000024685355,0.000048125003,0.000027223707,0.000015837797],"domain_scores_gemma":[0.9998703,0.000025369456,0.000018229246,0.00001651929,0.000057277208,0.000012186268],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015593076,0.00038154973,0.00015948692,0.00034254545,0.00016760768,0.00033028086,0.0003107035,0.000217259,0.0008798988],"category_scores_gemma":[0.00044972057,0.00012990566,0.00021614697,0.0003501639,0.00019568346,0.0003455296,0.00014369794,0.00023520959,0.00030562095],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044010225,0.00035492287,0.036688633,0.00005561777,0.000049996856,0.00017018891,0.00011437848,0.70721847,0.105907075,0.0007071226,0.003299129,0.14499444],"study_design_scores_gemma":[0.000004306785,0.000019212492,0.010987996,0.0000012684792,0.000003281514,0.000009133241,0.000022248845,0.979763,0.008869037,0.000110532106,0.00020424138,0.0000057736943],"about_ca_topic_score_codex":0.028284226,"about_ca_topic_score_gemma":0.03717965,"teacher_disagreement_score":0.028284226,"about_ca_system_score_codex":0.0005904214,"about_ca_system_score_gemma":0.00045319585,"threshold_uncertainty_score":0.056239188},"labels":[],"label_agreement":null},{"id":"W4307849810","doi":"10.36227/techrxiv.21430644.v1","title":"Image Prediction Using Coordinated Hyperspectral and RGB Video of Dynamic Natural Water Scenes","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Hyperspectral imaging; RGB color model; Remote sensing; Artificial intelligence; Computer science; Computer vision; Geography","score_opus":0.011375282218481482,"score_gpt":0.23625951190165892,"score_spread":0.22488422968317745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307849810","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8726067,0.00004603583,0.12361567,0.00006454238,0.000020362979,0.000049012877,0.0008188609,0.0010824149,0.0016964531],"genre_scores_gemma":[0.9675261,0.000030646483,0.03077167,0.0000147064475,0.000005298154,0.000024009092,0.00073688116,0.00004460934,0.000846064],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9999045,0.0000066368143,0.0000024885824,0.000045928507,0.000025146403,0.0000152511775],"domain_scores_gemma":[0.9998789,0.000024421848,0.000017324555,0.000014971792,0.00005353731,0.000010940098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001571053,0.0004026449,0.00017031144,0.00034437812,0.00015257036,0.0003082111,0.00030700196,0.00020580244,0.0007076902],"category_scores_gemma":[0.00044585316,0.0001250751,0.00021711155,0.00036359095,0.00018089438,0.00034925924,0.00015768716,0.0002359823,0.0002292163],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043909936,0.00032815326,0.03962374,0.00005998346,0.000051981748,0.00015653599,0.00011006427,0.729441,0.10614265,0.00065336446,0.0021387017,0.12085472],"study_design_scores_gemma":[0.0000043205364,0.000024984214,0.011593742,0.0000013271264,0.0000037995458,0.000009974125,0.000023789527,0.9783976,0.009624749,0.00012264647,0.00018704562,0.0000060125144],"about_ca_topic_score_codex":0.02123526,"about_ca_topic_score_gemma":0.027526718,"teacher_disagreement_score":0.02123526,"about_ca_system_score_codex":0.0005338969,"about_ca_system_score_gemma":0.00043960527,"threshold_uncertainty_score":0.042223334},"labels":[],"label_agreement":null},{"id":"W4308235886","doi":"10.1109/icip46576.2022.9897527","title":"Automatic Inspection of Cultural Monuments Using Deep and Tensor-Based Learning on Hyperspectral Imagery","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Image Processing (ICIP)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Hyperspectral imaging; Robustness (evolution); Artificial intelligence; Deep learning; Computer science; Cultural heritage; Perspective (graphical); Tensor (intrinsic definition); Pattern recognition (psychology); Computer vision; Machine learning; Archaeology; Mathematics; Geography","score_opus":0.050825315607764085,"score_gpt":0.303273541000542,"score_spread":0.2524482253927779,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308235886","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28247845,0.00058744266,0.71110654,0.00032812593,0.00006531444,0.00008728326,0.00035900512,0.00285596,0.002131857],"genre_scores_gemma":[0.8233725,0.00039513203,0.17281601,0.000097399745,0.000037160607,0.000036353755,0.00066354667,0.000084405954,0.0024974148],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99969673,0.000046360303,0.000013147564,0.000081357415,0.000090879425,0.000071499],"domain_scores_gemma":[0.99961674,0.00006580355,0.000096402735,0.00006849252,0.000110372814,0.000042206993],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004538932,0.00095088535,0.0005409716,0.0014609437,0.0002793249,0.0008595405,0.000763972,0.0006630607,0.0006759263],"category_scores_gemma":[0.00076495326,0.00023713779,0.0007176402,0.0008067007,0.00060849276,0.0009113386,0.0008188449,0.0006256966,0.0004391506],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004620268,0.00026201588,0.012512835,0.00026696362,0.00013336545,0.00044815993,0.0002978081,0.16540883,0.16249757,0.0025809705,0.004178563,0.6509509],"study_design_scores_gemma":[0.0000039021124,0.000046294328,0.004133829,0.000011973866,0.00001536191,0.0000818486,0.00006827245,0.9770089,0.016995719,0.001048039,0.0005691509,0.000016714199],"about_ca_topic_score_codex":0.0049878135,"about_ca_topic_score_gemma":0.0084987655,"teacher_disagreement_score":0.0049878135,"about_ca_system_score_codex":0.0004841141,"about_ca_system_score_gemma":0.00048036085,"threshold_uncertainty_score":0.009917557},"labels":[],"label_agreement":null},{"id":"W4308236992","doi":"10.1109/icip46576.2022.9897254","title":"Predicting Soil Properties from Hyperspectral Satellite Images","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Image Processing (ICIP)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Helmholtz Association","keywords":"Hyperspectral imaging; Artificial intelligence; Computer science; Artificial neural network; Satellite; Remote sensing; Fulvic acid; Pattern recognition (psychology); Geology; Chemistry; Engineering","score_opus":0.052939804894811496,"score_gpt":0.2680628145019913,"score_spread":0.21512300960717984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308236992","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43544424,0.0019001835,0.515978,0.0020098726,0.00031278675,0.00020419506,0.015812034,0.018627161,0.0097116],"genre_scores_gemma":[0.71928316,0.000903102,0.24809007,0.0002954148,0.00017646914,0.00013594783,0.023677606,0.000520723,0.006917522],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997745,0.000036020614,0.000006892669,0.00008139673,0.00006728542,0.000033868422],"domain_scores_gemma":[0.99965155,0.00010430239,0.000036311823,0.000071502865,0.00011170544,0.000024659408],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005978044,0.001206965,0.0006273555,0.00096780766,0.00026805903,0.0009432124,0.0009784003,0.0011266716,0.0019314187],"category_scores_gemma":[0.0014109275,0.00031586905,0.0008359139,0.001178758,0.00023432187,0.0012500618,0.0005198722,0.00086270226,0.0017023837],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033223745,0.0005026973,0.017329464,0.00014690912,0.00017001377,0.00010058137,0.000037546102,0.47212005,0.026789865,0.0012737159,0.0246608,0.4565362],"study_design_scores_gemma":[0.0000114715795,0.000016832342,0.0033877862,0.000005268908,0.000009232453,0.000013990119,0.000019421654,0.98826027,0.0053613605,0.0013926544,0.001512043,0.000009675455],"about_ca_topic_score_codex":0.012665844,"about_ca_topic_score_gemma":0.023856262,"teacher_disagreement_score":0.012665844,"about_ca_system_score_codex":0.00048579765,"about_ca_system_score_gemma":0.00052171235,"threshold_uncertainty_score":0.025184214},"labels":[],"label_agreement":null},{"id":"W4311217720","doi":"10.1109/ciss57580.2022.9971318","title":"Multi-temporal PolSAR Image Classification Using F-SAE-CNN","year":2022,"lang":"en","type":"article","venue":"2022 3rd China International SAR Symposium (CISS)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Natural Science Foundation of China; Ministry of Natural Resources","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Pattern recognition (psychology); Contextual image classification; Synthetic aperture radar; Artificial neural network; Feature extraction; Image (mathematics)","score_opus":0.02293743264065474,"score_gpt":0.2636818140567001,"score_spread":0.24074438141604537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311217720","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16374804,0.00081893004,0.8241392,0.0002626512,0.0002295245,0.00009850896,0.00064082147,0.0038164102,0.0062458147],"genre_scores_gemma":[0.7565459,0.0005909908,0.2317427,0.0002269134,0.00008674138,0.0000779365,0.0019988709,0.000101367244,0.008628607],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99977916,0.000012699689,0.000012594671,0.00007866477,0.000072922856,0.000043886455],"domain_scores_gemma":[0.9997769,0.000024836452,0.000026213214,0.00004486073,0.00011211115,0.0000150038095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035939063,0.0009444939,0.00041422885,0.00091955543,0.00023299853,0.00055921555,0.00070478127,0.0005744647,0.0015978378],"category_scores_gemma":[0.00055108627,0.00030503643,0.00074619363,0.0007599305,0.00021355234,0.0011733326,0.0004892106,0.00050274964,0.000603443],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027633994,0.00022328208,0.007335678,0.00010055439,0.00022522696,0.00021344834,0.000063963824,0.17052272,0.087639496,0.0019307695,0.0046517947,0.7268167],"study_design_scores_gemma":[0.0000040957243,0.000036389738,0.0023870666,0.000005695174,0.0000351318,0.00006515532,0.000015828184,0.98156977,0.014198289,0.0005495869,0.0011229226,0.000010127333],"about_ca_topic_score_codex":0.008789372,"about_ca_topic_score_gemma":0.011287744,"teacher_disagreement_score":0.008789372,"about_ca_system_score_codex":0.00050749094,"about_ca_system_score_gemma":0.0004699433,"threshold_uncertainty_score":0.01747638},"labels":[],"label_agreement":null},{"id":"W4312755206","doi":"10.1080/07038992.2022.2123625","title":"Advances in Hyperspectral Remote Sensing for Earth Monitoring and Mapping","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Hyperspectral imaging; Remote sensing; Geography; Earth observation; Cartography; Environmental science; Engineering; Satellite; Aerospace engineering","score_opus":0.01851311901034671,"score_gpt":0.22869104883694133,"score_spread":0.2101779298265946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312755206","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04886488,0.21728976,0.5843987,0.015154872,0.0030930243,0.00025269034,0.0023649202,0.002774021,0.1258071],"genre_scores_gemma":[0.2137413,0.2236794,0.5115328,0.002731767,0.003082947,0.000123744,0.0030976404,0.00060566363,0.041404773],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991372,0.00012325287,0.000029069557,0.000107021275,0.00055895426,0.000044529406],"domain_scores_gemma":[0.99823797,0.00043578664,0.00009246331,0.00017319967,0.0009896467,0.000071031536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017914898,0.00069238065,0.0004817567,0.0016664966,0.00029599297,0.0015094897,0.0007741728,0.0005602749,0.0070716524],"category_scores_gemma":[0.0017371825,0.00025023878,0.0003981383,0.0030803955,0.0007732117,0.0020986542,0.00092677725,0.0013752012,0.0020269174],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054340697,0.00013838349,0.0022885324,0.00082575047,0.000056674304,0.000047825375,0.000096341806,0.004997335,0.04518235,0.024562992,0.02392903,0.8978205],"study_design_scores_gemma":[0.000028939347,0.00013032104,0.02200622,0.00054758793,0.000121553465,0.00050966,0.00033361933,0.11938555,0.060308367,0.04526838,0.7512026,0.00015730022],"about_ca_topic_score_codex":0.016137974,"about_ca_topic_score_gemma":0.028126938,"teacher_disagreement_score":0.016137974,"about_ca_system_score_codex":0.0009938338,"about_ca_system_score_gemma":0.0015041842,"threshold_uncertainty_score":0.0320881},"labels":[],"label_agreement":null},{"id":"W4312882064","doi":"10.1109/lgrs.2022.3227164","title":"Cross-Domain Few-Shot Contrastive Learning for Hyperspectral Images Classification","year":2022,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Natural Science Foundation of China","keywords":"Artificial intelligence; Discriminative model; Computer science; Pattern recognition (psychology); Hyperspectral imaging; Feature extraction; Deep learning; Residual; Support vector machine; Contextual image classification; Feature learning; Convolutional neural network; Similarity (geometry); Class (philosophy); Feature (linguistics); Machine learning; Image (mathematics)","score_opus":0.021903874029474062,"score_gpt":0.256930765598226,"score_spread":0.23502689156875192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312882064","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10854599,0.0014047663,0.88526237,0.00032816723,0.00010765685,0.00007930582,0.00015323538,0.0012503423,0.0028681045],"genre_scores_gemma":[0.857745,0.0005202741,0.13500331,0.00034290523,0.000111611844,0.00008536303,0.0006787278,0.00010277949,0.005409884],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997044,0.000055979257,0.000011231946,0.00011166884,0.0000744753,0.000042263502],"domain_scores_gemma":[0.99962974,0.00013600237,0.000042045915,0.00007518669,0.00008807938,0.000028955723],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008010586,0.00076115574,0.0007967835,0.00055711623,0.00028189374,0.0006075337,0.001450441,0.000771183,0.0014377641],"category_scores_gemma":[0.001427152,0.00024711151,0.0006949764,0.0005979343,0.0006700155,0.0012501094,0.0010249726,0.0014741789,0.00045341643],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035837924,0.00059373747,0.0040889136,0.00016991529,0.00020349408,0.00012937869,0.00013988411,0.34977415,0.034340743,0.008928599,0.005398468,0.5958744],"study_design_scores_gemma":[0.0000034851191,0.000036270434,0.0003494973,0.0000037808934,0.00000885706,0.000019971649,0.0000074301997,0.99468863,0.0031121538,0.0014199237,0.000344556,0.000005438228],"about_ca_topic_score_codex":0.0032976263,"about_ca_topic_score_gemma":0.004194039,"teacher_disagreement_score":0.0032976263,"about_ca_system_score_codex":0.00055148563,"about_ca_system_score_gemma":0.00041403185,"threshold_uncertainty_score":0.0065568686},"labels":[],"label_agreement":null},{"id":"W4313427125","doi":"10.1016/j.mex.2023.101998","title":"Spatial response resampling (SR2): Accounting for the spatial point spread function in hyperspectral image resampling","year":2023,"lang":"en","type":"article","venue":"MethodsX","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Space Agency; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Resampling; Hyperspectral imaging; Point (geometry); Function (biology); Artificial intelligence; Remote sensing; Computer science; Pattern recognition (psychology); Environmental science; Mathematics; Geography; Biology","score_opus":0.053630147510354366,"score_gpt":0.3238503616377083,"score_spread":0.2702202141273539,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313427125","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009781279,0.00010065227,0.98570794,0.000089329755,0.0000380648,0.0000797806,0.00017191833,0.0031134936,0.0009175981],"genre_scores_gemma":[0.11232414,0.00016278093,0.88347894,0.000115110495,0.00003804407,0.00017301814,0.0007744188,0.0012486137,0.0016849473],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990803,0.00025025487,0.00006478412,0.00016062966,0.00037284667,0.00007106517],"domain_scores_gemma":[0.9981658,0.0006897166,0.0001822609,0.00046893433,0.00042775864,0.00006549152],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027110414,0.0010139168,0.00043944104,0.00094241207,0.0005103163,0.00095300586,0.0009685876,0.0006660003,0.002906793],"category_scores_gemma":[0.005573288,0.00034876497,0.0010524627,0.0007450794,0.0005583357,0.0009385962,0.001206896,0.0010340993,0.0013376054],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043627754,0.00023030565,0.010398458,0.0004803508,0.00027744702,0.00042451048,0.00062854105,0.4031489,0.105255805,0.030411243,0.016758505,0.43154964],"study_design_scores_gemma":[0.000026703448,0.00007706308,0.0025435805,0.000025251908,0.000029869192,0.00025371576,0.00006694667,0.922497,0.05072526,0.009701858,0.014001779,0.000050999068],"about_ca_topic_score_codex":0.006653304,"about_ca_topic_score_gemma":0.010407475,"teacher_disagreement_score":0.006653304,"about_ca_system_score_codex":0.0006123042,"about_ca_system_score_gemma":0.0012157353,"threshold_uncertainty_score":0.01433754},"labels":[],"label_agreement":null},{"id":"W4315606699","doi":"10.3233/atde221242","title":"Image Classification of Land Use Land Cover of Bengaluru City Using Convolutional Neural Network","year":2023,"lang":"en","type":"book-chapter","venue":"Advances in transdisciplinary engineering","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Land cover; Support vector machine; Convolutional neural network; Cover (algebra); Random forest; Computer science; Geography; Land use; Decision tree; Artificial intelligence; Machine learning; Remote sensing; Data mining; Pattern recognition (psychology); Engineering","score_opus":0.03533813285304732,"score_gpt":0.2596181914569522,"score_spread":0.22428005860390487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4315606699","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8082489,0.0036546781,0.13844271,0.00068090647,0.000304933,0.00017276662,0.0043816715,0.004712886,0.039400518],"genre_scores_gemma":[0.89114386,0.001953359,0.0595498,0.00010183772,0.000046837424,0.000054746066,0.0052693635,0.000109491564,0.04177076],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999566,0.0000026729076,0.000002787334,0.000011734231,0.000016033073,0.000010097399],"domain_scores_gemma":[0.9999665,0.0000067804476,0.000004473544,0.0000036760873,0.00001540005,0.0000031370248],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006837323,0.000393642,0.0002215395,0.0007706089,0.00015469859,0.00051002693,0.00035925853,0.00029437448,0.002410801],"category_scores_gemma":[0.00012871614,0.00010143445,0.00033433756,0.00066252,0.00008841574,0.00025828305,0.0001659723,0.00017640437,0.0006660713],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036285116,0.00018759612,0.02152006,0.00040512206,0.00012428258,0.0010374819,0.00020127451,0.05096523,0.16674326,0.0019467262,0.015315832,0.74119025],"study_design_scores_gemma":[0.000013770761,0.00018996792,0.08235826,0.000072948686,0.00014517253,0.0006177112,0.0002918771,0.7956211,0.09814258,0.0010772715,0.021427464,0.000041886273],"about_ca_topic_score_codex":0.023536358,"about_ca_topic_score_gemma":0.029069327,"teacher_disagreement_score":0.023536358,"about_ca_system_score_codex":0.00049211876,"about_ca_system_score_gemma":0.00021909837,"threshold_uncertainty_score":0.046798706},"labels":[],"label_agreement":null},{"id":"W4315783773","doi":"10.1109/tim.2023.3236318","title":"Sub-Pixel Mapping of Spectral Imagery Based on Deviation Information Measurement","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Instrumentation and Measurement","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Society of Hong Kong Scholars; Nanjing University of Aeronautics and Astronautics; Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China","keywords":"Pixel; Artificial intelligence; Robustness (evolution); Computer science; Spatial analysis; Pattern recognition (psychology); Computer vision; Remote sensing; Mathematics; Statistics; Geography","score_opus":0.04505494885811233,"score_gpt":0.22428828570997963,"score_spread":0.17923333685186732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4315783773","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14693367,0.00097319175,0.83993816,0.00022450164,0.0001250652,0.00016795627,0.0011737371,0.0046464656,0.0058172205],"genre_scores_gemma":[0.5745563,0.0008784114,0.41596976,0.00016726687,0.00011015998,0.00018394759,0.0040969974,0.00032596738,0.0037111884],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995295,0.00004719362,0.000022208531,0.00016720682,0.00018726096,0.00004664673],"domain_scores_gemma":[0.9996582,0.00005096656,0.000047224104,0.0000901339,0.00013233356,0.000021174337],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037206706,0.0008239488,0.00074383366,0.0018123164,0.00024613496,0.00075616693,0.0008001045,0.00037040407,0.0014136214],"category_scores_gemma":[0.00092869846,0.00024230905,0.00079537026,0.0013019342,0.00032398177,0.0012841576,0.0010067145,0.0008271001,0.0010603984],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036284004,0.0001680299,0.008186094,0.0003172967,0.00017232986,0.00020059958,0.0002539904,0.040529866,0.07831522,0.003529006,0.006093686,0.861871],"study_design_scores_gemma":[0.00003407884,0.00012725609,0.015970085,0.000034754627,0.00007388733,0.00046580916,0.00029690648,0.9102472,0.056542248,0.0074922806,0.0086584,0.00005718322],"about_ca_topic_score_codex":0.0019874375,"about_ca_topic_score_gemma":0.0029389467,"teacher_disagreement_score":0.0019874375,"about_ca_system_score_codex":0.00027015212,"about_ca_system_score_gemma":0.0004428101,"threshold_uncertainty_score":0.0047290325},"labels":[],"label_agreement":null},{"id":"W4315864511","doi":"10.3390/rs15020478","title":"MS4D-Net: Multitask-Based Semi-Supervised Semantic Segmentation Framework with Perturbed Dual Mean Teachers for Building Damage Assessment from High-Resolution Remote Sensing Imagery","year":2023,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Segmentation; Deep learning; Machine learning; Pipeline (software); Consistency (knowledge bases); Benchmark (surveying); Multi-task learning; Data mining; Task (project management)","score_opus":0.02120861533477983,"score_gpt":0.27224941651536944,"score_spread":0.2510408011805896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4315864511","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026925193,0.0004370342,0.96395165,0.00022703438,0.000066892826,0.00011381458,0.000583707,0.006318403,0.0013762041],"genre_scores_gemma":[0.44696227,0.00039372683,0.53686166,0.00061055686,0.00014789646,0.00043573568,0.0047008228,0.0009017174,0.008985656],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995272,0.00007675803,0.000019608673,0.00019697374,0.0001060497,0.00007337523],"domain_scores_gemma":[0.9996524,0.000089615845,0.00004489238,0.0000671515,0.0000962066,0.000049714843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080359034,0.0015622823,0.0013310816,0.0009887241,0.00049862807,0.00090171734,0.0032241677,0.0017517895,0.0022643695],"category_scores_gemma":[0.0012784317,0.000700101,0.0014512416,0.00072250166,0.0008010646,0.00155696,0.0017606056,0.0018303267,0.0011571319],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006239252,0.000365029,0.0023494763,0.00026902027,0.00021253672,0.00032994014,0.000246664,0.5289,0.022833452,0.0067008077,0.0129877245,0.42418134],"study_design_scores_gemma":[0.000010335231,0.000032016218,0.0001876477,0.0000052317646,0.000009276377,0.00003333162,0.000010941048,0.99382025,0.0024521083,0.002694771,0.0007350721,0.000008963165],"about_ca_topic_score_codex":0.0085605765,"about_ca_topic_score_gemma":0.015909676,"teacher_disagreement_score":0.0085605765,"about_ca_system_score_codex":0.0012004268,"about_ca_system_score_gemma":0.0015200856,"threshold_uncertainty_score":0.017021477},"labels":[],"label_agreement":null},{"id":"W4316036976","doi":"10.31223/x52d39","title":"Residual U-Net with Attention for Detecting Clouds in Satellite Imagery","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Research Council Canada; Canarie","keywords":"Computer science; Residual; Cloud computing; Segmentation; Satellite imagery; Jaccard index; Artificial intelligence; Variety (cybernetics); Benchmark (surveying); Deep learning; Unavailability; Satellite; Machine learning; Remote sensing; Pattern recognition (psychology); Cartography; Geography","score_opus":0.04236751824807769,"score_gpt":0.26347353180920685,"score_spread":0.22110601356112916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4316036976","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34513718,0.0038197162,0.6151916,0.0014445287,0.00042605694,0.0002447526,0.00234731,0.016798327,0.014590607],"genre_scores_gemma":[0.8659826,0.0005974555,0.11656216,0.00063177705,0.00012440664,0.00012137419,0.0049920725,0.00028037315,0.010707732],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99979836,0.000034319524,0.000008087672,0.00007656958,0.000037043756,0.000045567733],"domain_scores_gemma":[0.9997533,0.000086039894,0.000031644882,0.00004637239,0.00005917339,0.000023397515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006389594,0.001222532,0.00056203693,0.0006458037,0.0003406126,0.0006681701,0.0013831392,0.00097451627,0.0020007123],"category_scores_gemma":[0.0012260298,0.00032311658,0.0005695859,0.00081235886,0.00053024816,0.001376585,0.00084167655,0.0012611792,0.0009632596],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009242032,0.00044928378,0.005922173,0.00021541807,0.0001697286,0.00023378707,0.000104858904,0.47709832,0.013599329,0.006609696,0.02513141,0.4695418],"study_design_scores_gemma":[0.000007525523,0.000036192094,0.00043665848,0.000009222662,0.000012457488,0.000016895505,0.000010760228,0.9930676,0.0032504108,0.002359795,0.00078717805,0.0000052805303],"about_ca_topic_score_codex":0.017752297,"about_ca_topic_score_gemma":0.02611863,"teacher_disagreement_score":0.017752297,"about_ca_system_score_codex":0.0010866134,"about_ca_system_score_gemma":0.00082459685,"threshold_uncertainty_score":0.03529793},"labels":[],"label_agreement":null},{"id":"W4316689660","doi":"10.18280/ria.360607","title":"A Case Study on Green Areas Change-Detection in Baghdad Using Artificial Intelligence","year":2022,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Economic shortage; Urban heat island; Green belt; Intervention (counseling); Artificial light; Geography; Artificial intelligence; Environmental planning; Computer science; Architectural engineering; Environmental resource management; Environmental science; Engineering; Meteorology; Psychology; Archaeology","score_opus":0.15437646175471326,"score_gpt":0.3101419387071592,"score_spread":0.15576547695244597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4316689660","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97815573,0.0005379917,0.0071082776,0.0010491195,0.00008818882,0.0001991665,0.0003389467,0.0000945952,0.012428057],"genre_scores_gemma":[0.98396295,0.00042474386,0.009030952,0.00017836287,0.000026678212,0.000052675867,0.00013711704,0.000017175766,0.006169408],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992086,0.00031031604,0.000038902926,0.00011584588,0.0001472684,0.00017902856],"domain_scores_gemma":[0.99916446,0.0003946604,0.00008787825,0.0000670722,0.00012243932,0.0001634218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074907986,0.0004281095,0.00030425686,0.0011942316,0.0030182924,0.0014310579,0.0011455609,0.0017743136,0.0025532453],"category_scores_gemma":[0.0011135578,0.00020055809,0.00046676685,0.0016300776,0.0011317418,0.00079163036,0.00095402333,0.0008611058,0.00039787198],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011617531,0.004970529,0.30334657,0.0019848961,0.0002625477,0.28529084,0.08504335,0.034918584,0.022750381,0.016301895,0.019699179,0.22426955],"study_design_scores_gemma":[0.00012445558,0.0021508262,0.36926618,0.000759362,0.000371695,0.05311607,0.28435892,0.09930374,0.030848635,0.007856493,0.15147749,0.00036615477],"about_ca_topic_score_codex":0.016503701,"about_ca_topic_score_gemma":0.040453855,"teacher_disagreement_score":0.016503701,"about_ca_system_score_codex":0.0016714704,"about_ca_system_score_gemma":0.0010861544,"threshold_uncertainty_score":0.032815278},"labels":[],"label_agreement":null},{"id":"W4318054870","doi":"10.3390/rs15030715","title":"Exploiting Superpixel-Based Contextual Information on Active Learning for High Spatial Resolution Remote Sensing Image Classification","year":2023,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Artificial intelligence; Pattern recognition (psychology); Computer science; Similarity (geometry); Benchmark (surveying); Contextual image classification; Image (mathematics); Geography","score_opus":0.030275471001311005,"score_gpt":0.25434364764440726,"score_spread":0.22406817664309625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318054870","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020694768,0.0003675021,0.9775933,0.0001045097,0.00003267539,0.00002922524,0.00003452282,0.0004180709,0.00072545325],"genre_scores_gemma":[0.6736635,0.00055901706,0.3231044,0.00028283606,0.00019791306,0.0001498904,0.00035534927,0.000115722534,0.001571435],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989498,0.00024818355,0.000053851785,0.00033217855,0.0003126704,0.00010324127],"domain_scores_gemma":[0.99866354,0.00060006924,0.00019032224,0.00018754462,0.00029805396,0.000060354952],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001528523,0.00090312096,0.0015058748,0.0015122325,0.00049588183,0.0012584206,0.0017526645,0.0011269125,0.0007858767],"category_scores_gemma":[0.00262359,0.00052074605,0.0011565324,0.0014912006,0.0009469331,0.0018582208,0.0013396925,0.0013337764,0.00027569858],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035078512,0.00026970796,0.0033610112,0.00021310583,0.00016328688,0.00018651904,0.00029263555,0.42756292,0.033676118,0.006315475,0.0020401103,0.5255684],"study_design_scores_gemma":[0.0000048254437,0.000018373674,0.0003439472,0.000005650238,0.000014165277,0.00002165815,0.000013888024,0.9945503,0.0029743135,0.0017157479,0.0003301581,0.0000070911374],"about_ca_topic_score_codex":0.0027184829,"about_ca_topic_score_gemma":0.0036639469,"teacher_disagreement_score":0.0027184829,"about_ca_system_score_codex":0.00058462704,"about_ca_system_score_gemma":0.0005647676,"threshold_uncertainty_score":0.0080836415},"labels":[],"label_agreement":null},{"id":"W4318478874","doi":"10.3390/s23031527","title":"An Adaptive Kernels Layer for Deep Neural Networks Based on Spectral Analysis for Image Applications","year":2023,"lang":"en","type":"article","venue":"Sensors","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Defence Research and Development Canada; University of Calgary","funders":"","keywords":"Computer science; Artificial intelligence; Pixel; Convolution (computer science); Convolutional neural network; Pattern recognition (psychology); Computer vision; Image (mathematics); Image resolution; Invariant (physics); Artificial neural network; Mathematics","score_opus":0.027882640690896257,"score_gpt":0.2752975462856091,"score_spread":0.24741490559471285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318478874","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0635781,0.0010074019,0.92435014,0.00027819062,0.00014345834,0.000064997635,0.00032797988,0.0061612814,0.0040885718],"genre_scores_gemma":[0.71928716,0.00059446937,0.2689043,0.00031679764,0.000035602094,0.00013688229,0.00084731594,0.0002643969,0.009613245],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99987614,0.000012105533,0.0000069436855,0.000032077343,0.000046225483,0.000026494834],"domain_scores_gemma":[0.9998374,0.00003536274,0.000018100733,0.00002969736,0.00006767159,0.000011668448],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027801294,0.0006635794,0.00031336478,0.00033422155,0.000193297,0.00045116094,0.0011356636,0.0005459493,0.0022076028],"category_scores_gemma":[0.00070285634,0.000258933,0.0004445897,0.00031706292,0.0002417345,0.0008025106,0.00059228163,0.00087634777,0.0008434714],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035972,0.0002488096,0.0020692642,0.00022999103,0.00017258535,0.00016472983,0.00008455598,0.33812502,0.086563066,0.009313167,0.010628433,0.5520407],"study_design_scores_gemma":[0.000006314547,0.000043369317,0.00030635964,0.000009903453,0.000019401821,0.000033298547,0.0000062473405,0.9821988,0.014336649,0.0011722242,0.0018583105,0.000009173919],"about_ca_topic_score_codex":0.0068606096,"about_ca_topic_score_gemma":0.010955871,"teacher_disagreement_score":0.0068606096,"about_ca_system_score_codex":0.00075874914,"about_ca_system_score_gemma":0.00070747075,"threshold_uncertainty_score":0.013641357},"labels":[],"label_agreement":null},{"id":"W4319454158","doi":"10.52939/ijg.v19i1.2497","title":"Determination of Segmentation Parameters for Object-Based Remote Sensing Image Analysis from Conventional to Recent Approaches: A Review","year":2023,"lang":"en","type":"review","venue":"International Journal of Geoinformatics","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Segmentation; Computer science; Object (grammar); Artificial intelligence; Homogeneity (statistics); Image segmentation; Segmentation-based object categorization; Scale-space segmentation; Change detection; Contrast (vision); Data mining; Pattern recognition (psychology); Computer vision; Machine learning","score_opus":0.1157308514498959,"score_gpt":0.3577703337395169,"score_spread":0.242039482289621,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319454158","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00064208667,0.9829616,0.014406103,0.00038947514,0.00026196885,0.000024127543,0.0000662637,0.000061416955,0.0011869483],"genre_scores_gemma":[0.0055456916,0.9772331,0.015599311,0.00026778723,0.000550445,0.000049632028,0.00020020944,0.000043363867,0.0005104187],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99885654,0.00018642434,0.00018451002,0.0003339169,0.00039251967,0.000046134064],"domain_scores_gemma":[0.9967013,0.0021966335,0.00030283447,0.00009727141,0.00065106165,0.000050862738],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025597885,0.0014284436,0.0018143627,0.005576979,0.0004531004,0.001963212,0.0018341673,0.0018215133,0.0020827567],"category_scores_gemma":[0.0046737012,0.00080064184,0.0014101934,0.0065267836,0.0013066112,0.0026990229,0.0008472165,0.0014145647,0.001726257],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054523975,0.00006351973,0.00085374893,0.022239005,0.00020181695,0.00013907765,0.00020746178,0.0021372442,0.0024589973,0.0070641343,0.010872553,0.95370793],"study_design_scores_gemma":[0.000028519244,0.00034596634,0.0069931597,0.015824577,0.0012137324,0.0025907184,0.0004330388,0.010650352,0.008733691,0.023686804,0.92918974,0.00030977651],"about_ca_topic_score_codex":0.0022051276,"about_ca_topic_score_gemma":0.0016361402,"teacher_disagreement_score":0.005576979,"about_ca_system_score_codex":0.0009940403,"about_ca_system_score_gemma":0.0015305439,"threshold_uncertainty_score":0.013537645},"labels":[],"label_agreement":null},{"id":"W4319601347","doi":"10.5194/isprs-archives-xlviii-4-w6-2022-179-2023","title":"HYPERSPECTRAL IMAGE CLASSIFICATION USING MULTI-LAYER PERCEPTRON MIXER (MLP-MIXER)","year":2023,"lang":"en","type":"article","venue":"˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre For Cold Ocean Resources Engineering; Memorial University of Newfoundland","funders":"","keywords":"Hyperspectral imaging; Pattern recognition (psychology); Artificial intelligence; Perceptron; Multilayer perceptron; Computer science; Curse of dimensionality; Contextual image classification; Image (mathematics); Artificial neural network","score_opus":0.0391927244795356,"score_gpt":0.28136899440026863,"score_spread":0.24217626992073304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319601347","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.111094385,0.00070085056,0.88012195,0.00035240306,0.0001663601,0.00013842166,0.00031628757,0.003262682,0.0038466163],"genre_scores_gemma":[0.73174345,0.0002582445,0.2622996,0.0002583954,0.00007165452,0.00017134949,0.000632643,0.0000676548,0.0044970145],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995035,0.00011489586,0.000036812264,0.0001467525,0.000120423836,0.0000776008],"domain_scores_gemma":[0.99941504,0.00023396884,0.000060505125,0.00006580929,0.00019195673,0.00003270032],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015411254,0.0009921961,0.0006978236,0.0009475871,0.00040727697,0.0011184542,0.0009463257,0.0011827293,0.0022117882],"category_scores_gemma":[0.0014279038,0.0003830443,0.0009900536,0.00064055563,0.00032880457,0.0011950327,0.0007926807,0.0016648552,0.00097101904],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00090985297,0.00068930845,0.008569948,0.00038839167,0.00050981354,0.00023196646,0.00011666572,0.25175667,0.104964234,0.0031861782,0.004470529,0.6242065],"study_design_scores_gemma":[0.000011738139,0.00010958812,0.0013357138,0.0000132861705,0.00003153319,0.000028755028,0.0000150008855,0.98058313,0.016663266,0.00060957274,0.0005867439,0.000011783182],"about_ca_topic_score_codex":0.0012555467,"about_ca_topic_score_gemma":0.0019060177,"teacher_disagreement_score":0.0022117882,"about_ca_system_score_codex":0.0006002897,"about_ca_system_score_gemma":0.00035831518,"threshold_uncertainty_score":0.008150339},"labels":[],"label_agreement":null},{"id":"W4321768317","doi":"10.1016/j.asoc.2023.110096","title":"Corrigendum to “A new hybrid SSA-TA: Salp Swarm Algorithm with threshold accepting for band selection in hyperspectral images” [Appl. Soft Comput. 95 (2020) 106534]","year":2023,"lang":"en","type":"erratum","venue":"Applied Soft Computing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thales (Canada)","funders":"","keywords":"Hyperspectral imaging; Swarm behaviour; Selection (genetic algorithm); Artificial intelligence; Algorithm; Pattern recognition (psychology); Computer science; Mathematics","score_opus":0.017740210834751843,"score_gpt":0.23896371811221473,"score_spread":0.22122350727746287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321768317","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002295407,0.0023665281,0.004576616,0.03617084,0.94546247,0.000054227716,0.0010967765,0.0007951927,0.009247837],"genre_scores_gemma":[0.011761334,0.008783573,0.015027944,0.061152354,0.2182189,0.00030070488,0.0048677623,0.0029237103,0.6769637],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973297,0.00040264253,0.00029981797,0.0004479922,0.0013261822,0.00019354915],"domain_scores_gemma":[0.98906577,0.0020380686,0.00032515405,0.000580547,0.007558739,0.0004317013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001773027,0.0020057382,0.0019194412,0.002959211,0.002837544,0.002360852,0.0036248702,0.0050378055,0.09931246],"category_scores_gemma":[0.022618337,0.0008261844,0.001913364,0.0024549575,0.001747493,0.0023465077,0.0021319888,0.0053388127,0.06479074],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002655645,0.000008090513,0.00003840059,0.00007640315,0.00001026908,0.00013869791,0.000014493109,0.00010694384,0.00014761205,0.0006713489,0.9913657,0.0073954803],"study_design_scores_gemma":[0.00002396753,0.000028507293,0.00062052696,0.00012661217,0.00002933859,0.0002588323,0.00004025786,0.0010280022,0.00095937756,0.0022109896,0.99461925,0.000054196073],"about_ca_topic_score_codex":0.026157508,"about_ca_topic_score_gemma":0.040172122,"teacher_disagreement_score":0.09931246,"about_ca_system_score_codex":0.0028771688,"about_ca_system_score_gemma":0.0022272673,"threshold_uncertainty_score":0.33223325},"labels":[],"label_agreement":null},{"id":"W4321783250","doi":"10.1111/mice.12981","title":"Large‐scale building damage assessment using a novel hierarchical transformer architecture on satellite images","year":2023,"lang":"en","type":"article","venue":"Computer-Aided Civil and Infrastructure Engineering","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":88,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Texas A and M University","keywords":"Computer science; Transformer; Architecture; Deep learning; Satellite imagery; Encoder; Artificial intelligence; Data mining; Real-time computing; Remote sensing; Engineering; Geography","score_opus":0.008401223590461457,"score_gpt":0.22999378966921882,"score_spread":0.22159256607875738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321783250","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26548928,0.00031268847,0.7287897,0.00023521912,0.000038391107,0.00007742831,0.0004170749,0.0012328951,0.0034073335],"genre_scores_gemma":[0.944269,0.00014043691,0.05266583,0.000057233265,0.000013448318,0.000024473216,0.00055071834,0.000030245128,0.0022487764],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998739,0.000017820383,0.0000051929164,0.00004273958,0.00003157677,0.000028729128],"domain_scores_gemma":[0.99986947,0.00002751495,0.000023133172,0.000020974196,0.000041587642,0.00001726001],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024114772,0.00062795455,0.0002869553,0.00071378413,0.00016655683,0.00042241847,0.00068070326,0.00040070218,0.00088710064],"category_scores_gemma":[0.0005691607,0.00018666184,0.0004534936,0.00046079647,0.00030737888,0.0008853421,0.00072008726,0.0005419328,0.0002685059],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023679381,0.00016962994,0.012821723,0.000060586644,0.000114107024,0.00019532892,0.000096695745,0.6621503,0.02648184,0.0032963627,0.0023162127,0.29206043],"study_design_scores_gemma":[0.0000025343438,0.000032116048,0.0012803636,0.0000027558413,0.000009555042,0.000027423432,0.000013480347,0.9945898,0.0027735939,0.001011819,0.0002523354,0.000004215273],"about_ca_topic_score_codex":0.007261083,"about_ca_topic_score_gemma":0.011063362,"teacher_disagreement_score":0.007261083,"about_ca_system_score_codex":0.0005440826,"about_ca_system_score_gemma":0.0003900898,"threshold_uncertainty_score":0.0144376755},"labels":[],"label_agreement":null},{"id":"W4322743777","doi":"10.3390/rs15051378","title":"Potential Assessment of PRISMA Hyperspectral Imagery for Remote Sensing Applications","year":2023,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Dalhousie University; Mitacs; Innovation Saskatchewan; Agriculture and Agri-Food Canada; SRM Institute of Science and Technology; University of Alberta; University of Saskatchewan; Wilfrid Laurier University; Athabasca University","keywords":"Hyperspectral imaging; Remote sensing; Environmental science; Computer science; Sensor fusion; Identification (biology); Geology; Artificial intelligence","score_opus":0.019543521976451032,"score_gpt":0.2816643772331734,"score_spread":0.26212085525672235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322743777","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7979683,0.0024384945,0.15078548,0.0011755279,0.000116358744,0.0003798161,0.0033761044,0.0013056042,0.042454284],"genre_scores_gemma":[0.9223491,0.0006665302,0.07308774,0.000114135626,0.000021392749,0.00006654691,0.002023083,0.0001779326,0.0014935257],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990557,0.00016006052,0.000027451737,0.00010074626,0.0005662661,0.00008985683],"domain_scores_gemma":[0.9987847,0.0003483048,0.00009809068,0.000085107,0.00063668174,0.000047165384],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020048525,0.00075706566,0.00026536308,0.0016445341,0.0003195053,0.0012337739,0.0006594666,0.0006045452,0.0016589535],"category_scores_gemma":[0.002674467,0.00021364276,0.0005547934,0.0017314466,0.00040264428,0.0017857882,0.000654163,0.00046804716,0.00059372315],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008171053,0.00044115563,0.08292496,0.002025195,0.00029192358,0.0022025725,0.0008329805,0.21238564,0.18798722,0.014530833,0.014789729,0.48077062],"study_design_scores_gemma":[0.000028829709,0.00036063802,0.09599608,0.00016054424,0.0001764783,0.0008262387,0.0015044207,0.80677396,0.06121754,0.0052408813,0.027623447,0.000090991845],"about_ca_topic_score_codex":0.0031867293,"about_ca_topic_score_gemma":0.0054970477,"teacher_disagreement_score":0.0031867293,"about_ca_system_score_codex":0.00053490774,"about_ca_system_score_gemma":0.000430802,"threshold_uncertainty_score":0.010602772},"labels":[],"label_agreement":null},{"id":"W4324092354","doi":"10.3390/electronics12061347","title":"Multi-Attention-Based Semantic Segmentation Network for Land Cover Remote Sensing Images","year":2023,"lang":"en","type":"article","venue":"Electronics","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Key Research and Development Program of China","keywords":"Computer science; Upsampling; Segmentation; Artificial intelligence; Benchmark (surveying); Feature (linguistics); Pattern recognition (psychology); Confusion matrix; Image segmentation; Feature extraction; Key (lock); Land cover; Semantics (computer science); Data mining; Remote sensing; Image (mathematics); Land use; Geography","score_opus":0.016181191711965956,"score_gpt":0.25592705018198003,"score_spread":0.23974585847001406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4324092354","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15120998,0.001852343,0.8312888,0.0008512322,0.00020602159,0.00021560528,0.0014092305,0.005694078,0.0072726686],"genre_scores_gemma":[0.8836944,0.0005623325,0.1042085,0.0003753554,0.00014557446,0.00014500276,0.0028823595,0.00018446754,0.007801885],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99965787,0.000040393443,0.000016172153,0.00016008555,0.00006419334,0.00006119643],"domain_scores_gemma":[0.99975497,0.000063183885,0.000033574277,0.00003434593,0.000096004835,0.000017821323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005499644,0.0011521308,0.0007606336,0.001961178,0.00053560233,0.00063995033,0.0015399262,0.0009377518,0.0015597073],"category_scores_gemma":[0.0009932143,0.00037196316,0.0010960511,0.0012501857,0.0005489795,0.0019367648,0.0008427784,0.0008954083,0.0004951809],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00051923783,0.00032037412,0.0057523055,0.00016223844,0.00018882465,0.00028701682,0.00024050276,0.42041817,0.018952133,0.00876554,0.008966766,0.53542686],"study_design_scores_gemma":[0.000004772093,0.000030953037,0.0007502986,0.00000643569,0.000029679228,0.00003719263,0.00001769549,0.99281526,0.0028286676,0.0026268887,0.00084589503,0.00000621665],"about_ca_topic_score_codex":0.023969023,"about_ca_topic_score_gemma":0.025292037,"teacher_disagreement_score":0.023969023,"about_ca_system_score_codex":0.001880089,"about_ca_system_score_gemma":0.00097365,"threshold_uncertainty_score":0.04765904},"labels":[],"label_agreement":null},{"id":"W4362701204","doi":"10.1016/j.eswa.2023.120072","title":"Spectral unmixing based random forest classifier for detecting surface water changes in multitemporal pansharpened Landsat image","year":2023,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cégep de la Gaspésie et des Îles","funders":"","keywords":"Thematic Mapper; Endmember; Multispectral image; Remote sensing; Random forest; Change detection; Pixel; Image fusion; Thematic map; Multispectral pattern recognition; Computer science; Environmental science; Cohen's kappa; Artificial intelligence; Pattern recognition (psychology); Satellite imagery; Cartography; Geography; Image (mathematics)","score_opus":0.024966662935199734,"score_gpt":0.25359962704855943,"score_spread":0.2286329641133597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362701204","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3988099,0.0008901897,0.59425765,0.00010832038,0.00014455277,0.00012614287,0.0005922052,0.0028364763,0.0022345288],"genre_scores_gemma":[0.7660181,0.000409109,0.22846092,0.00005606552,0.000057625097,0.0000951587,0.0016191372,0.000088645575,0.0031952807],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99978393,0.000022763,0.000013478415,0.000063307794,0.00008255436,0.000033980647],"domain_scores_gemma":[0.9997818,0.000057443733,0.000018062721,0.000018403947,0.00011377744,0.000010413442],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052213774,0.0005036939,0.00043426378,0.0011164045,0.0003316047,0.00030111746,0.00045100783,0.00044605593,0.0008818981],"category_scores_gemma":[0.00049528474,0.00017791588,0.00060097896,0.00058596703,0.00015082922,0.0005354961,0.00018179628,0.00040208467,0.00048742784],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000616923,0.00043930006,0.0070899967,0.00017517431,0.00012072367,0.0001311153,0.00007996838,0.03865907,0.14190187,0.0007445866,0.0027806086,0.80726063],"study_design_scores_gemma":[0.000024904852,0.00015558914,0.012890284,0.00001236873,0.000116275885,0.00014333407,0.000054284326,0.94495773,0.03977399,0.0005166563,0.0013313683,0.000023228535],"about_ca_topic_score_codex":0.0044618007,"about_ca_topic_score_gemma":0.007307789,"teacher_disagreement_score":0.0044618007,"about_ca_system_score_codex":0.0001756273,"about_ca_system_score_gemma":0.000397307,"threshold_uncertainty_score":0.008871675},"labels":[],"label_agreement":null},{"id":"W4372352998","doi":"10.18280/ijdne.180221","title":"A Comparative Study of Land Cover Mapping Based on Support Vector Machine","year":2023,"lang":"en","type":"article","venue":"International Journal of Design & Nature and Ecodynamics","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Agence Thématique de Recherche en Science et Technologie","keywords":"Multispectral image; Support vector machine; Land cover; Radial basis function; Kernel (algebra); Vegetation (pathology); Pattern recognition (psychology); Artificial intelligence; Geography; Radial basis function kernel; Contextual image classification; Remote sensing; Computer science; Polynomial; Land use; Mathematics; Kernel method; Image (mathematics); Engineering; Artificial neural network","score_opus":0.02407212366214056,"score_gpt":0.27679707100873086,"score_spread":0.2527249473465903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4372352998","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90739596,0.0024310697,0.084380075,0.00024178697,0.00007487319,0.00003732182,0.00025306238,0.0005785451,0.004607409],"genre_scores_gemma":[0.98239267,0.00042240752,0.016385792,0.000011283122,0.000019603453,0.000010580071,0.00022613253,0.000016230118,0.00051545893],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999318,0.00021695285,0.00005446893,0.00007634501,0.00028148384,0.000052746247],"domain_scores_gemma":[0.99851114,0.0008273625,0.00008550317,0.00007370496,0.00046210986,0.00004025878],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013880085,0.00037223825,0.0004502896,0.002483976,0.00016963802,0.0006923691,0.00028866285,0.00030746945,0.0007581074],"category_scores_gemma":[0.0033267792,0.00008236668,0.00036866273,0.0012526165,0.00014375975,0.000846794,0.00019680598,0.00020484005,0.00019953879],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010105642,0.0002717304,0.058856994,0.00042920574,0.00035171435,0.0002901252,0.00030048424,0.07022897,0.012775618,0.0018008158,0.0016106365,0.85207313],"study_design_scores_gemma":[0.000021557178,0.0006516273,0.086784765,0.00006073026,0.00015259915,0.00030920978,0.00052158284,0.8957421,0.011540191,0.0010648338,0.0031081887,0.000042616874],"about_ca_topic_score_codex":0.002287122,"about_ca_topic_score_gemma":0.0015986352,"teacher_disagreement_score":0.002483976,"about_ca_system_score_codex":0.0002499786,"about_ca_system_score_gemma":0.00017598402,"threshold_uncertainty_score":0.00734061},"labels":[],"label_agreement":null},{"id":"W4375928869","doi":"10.1109/tim.2023.3273689","title":"PEAMATL: A Strategy for Developing Near-Infrared Spectral Prediction Models Under Domain Shift Using Self-Supervised Transfer Learning","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Instrumentation and Measurement","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; National Key Research and Development Program of China; Higher Education Discipline Innovation Project; China Scholarship Council; National Natural Science Foundation of China","keywords":"Transfer of learning; Artificial intelligence; Computer science; Infrared; Machine learning; Pattern recognition (psychology); Physics; Optics","score_opus":0.09018907852131385,"score_gpt":0.2661405498034173,"score_spread":0.17595147128210342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4375928869","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010014227,0.00010107858,0.9868205,0.00009389779,0.000023925368,0.000050610743,0.00004970854,0.0020534743,0.0007925162],"genre_scores_gemma":[0.5934183,0.00022910765,0.39686984,0.00063617044,0.000092001865,0.00045964427,0.0008863125,0.0004511619,0.006957453],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996518,0.00006711689,0.000017169941,0.00014193883,0.00008334801,0.000038649425],"domain_scores_gemma":[0.99934715,0.00020741438,0.00008332141,0.000111902766,0.00020650844,0.000043790296],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010360567,0.0010275054,0.0006891743,0.00052990916,0.00031410687,0.0005612251,0.0023152847,0.0011119599,0.002012786],"category_scores_gemma":[0.0022609571,0.0005319491,0.0010091282,0.00040567358,0.0006541493,0.0015493657,0.0016154958,0.00179197,0.0010325129],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012571552,0.00017791364,0.00173336,0.00009831257,0.00012540394,0.0001576886,0.00014444535,0.6711853,0.015978113,0.006380657,0.0040659173,0.29982707],"study_design_scores_gemma":[0.0000022323009,0.000014733357,0.000043930675,0.0000015195296,0.0000032772953,0.0000072317584,0.0000029563062,0.9976342,0.0010253227,0.0010448612,0.00021714382,0.0000026251535],"about_ca_topic_score_codex":0.004667415,"about_ca_topic_score_gemma":0.0049076313,"teacher_disagreement_score":0.004667415,"about_ca_system_score_codex":0.00069073564,"about_ca_system_score_gemma":0.0010982775,"threshold_uncertainty_score":0.009280443},"labels":[],"label_agreement":null},{"id":"W4376137947","doi":"10.3390/su15107854","title":"A Comparison of Deep Transfer Learning Methods for Land Use and Land Cover Classification","year":2023,"lang":"en","type":"article","venue":"Sustainability","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Transfer of learning; Pace; Artificial intelligence; Deep learning; Land cover; Computer science; Machine learning; Class (philosophy); Test set; Land use; Set (abstract data type); Geography; Engineering; Civil engineering","score_opus":0.05583714975142652,"score_gpt":0.3742336261795202,"score_spread":0.3183964764280937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376137947","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6347655,0.023157056,0.2985538,0.003253475,0.0016162299,0.0007686329,0.0028394896,0.009005417,0.026040364],"genre_scores_gemma":[0.90294886,0.003328119,0.07974616,0.00048243583,0.00018243614,0.00029299708,0.004776263,0.00025700568,0.007985662],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986198,0.0003664877,0.00011698697,0.00027851693,0.00042292586,0.00019527126],"domain_scores_gemma":[0.9975254,0.0010547593,0.000102093545,0.00029085184,0.0008708693,0.0001558877],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004875297,0.0020061152,0.001052574,0.0022559157,0.00054865703,0.001297148,0.0020060502,0.0017081553,0.002031217],"category_scores_gemma":[0.00640251,0.00039416808,0.0010339642,0.0013649917,0.00046737838,0.003011892,0.0015990805,0.0021253342,0.0012182043],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00153024,0.001002867,0.012429336,0.0004091847,0.0005234508,0.00011266899,0.00014959449,0.25029927,0.0029250507,0.0024706929,0.011229457,0.7169182],"study_design_scores_gemma":[0.000044200402,0.00026573433,0.0034401387,0.00005214814,0.000052822965,0.00003479754,0.00008622154,0.99030334,0.0021761574,0.001870726,0.0016481066,0.000025655649],"about_ca_topic_score_codex":0.016025275,"about_ca_topic_score_gemma":0.011457698,"teacher_disagreement_score":0.016025275,"about_ca_system_score_codex":0.0017243212,"about_ca_system_score_gemma":0.0017694809,"threshold_uncertainty_score":0.031863987},"labels":[],"label_agreement":null},{"id":"W4376466807","doi":"10.1109/tgrs.2023.3272270","title":"Unsupervised Bayesian Subpixel Mapping Autoencoder Network for Hyperspectral Images","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Subpixel rendering; Autoencoder; Hyperspectral imaging; Artificial intelligence; Computer science; Pattern recognition (psychology); Convolutional neural network; Unsupervised learning; Leverage (statistics); Deep learning; Computer vision; Pixel","score_opus":0.022691218383158893,"score_gpt":0.2373771819795424,"score_spread":0.21468596359638353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376466807","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02356854,0.00032287076,0.97387165,0.00012925654,0.000024310219,0.000025876812,0.00009881743,0.00074327725,0.0012154247],"genre_scores_gemma":[0.5394922,0.00061495934,0.45018917,0.00027277792,0.00007942448,0.00015119798,0.0008892219,0.00016513323,0.008146002],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997588,0.00005126355,0.000010192529,0.00006995593,0.00008070205,0.000029125977],"domain_scores_gemma":[0.9997172,0.00010703296,0.00004309236,0.000031895514,0.000086490574,0.000014215232],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005406729,0.0006911686,0.00065821485,0.00048159255,0.00022968731,0.00039886712,0.0009133901,0.0006843872,0.0011568178],"category_scores_gemma":[0.0009781389,0.0004731423,0.0005364822,0.00048656442,0.0003596643,0.00083604496,0.0006873898,0.0010363716,0.0003607934],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013043347,0.000112531656,0.0011052298,0.00009004232,0.000105862404,0.000059348273,0.00007901388,0.64881974,0.012945317,0.006116184,0.0027141462,0.3277221],"study_design_scores_gemma":[0.0000014879056,0.0000056786876,0.00013932798,0.0000024491444,0.000003776755,0.000006788733,0.0000023773853,0.9980825,0.0008568098,0.0007174319,0.00017859177,0.0000026205614],"about_ca_topic_score_codex":0.008468795,"about_ca_topic_score_gemma":0.015493463,"teacher_disagreement_score":0.008468795,"about_ca_system_score_codex":0.0005899559,"about_ca_system_score_gemma":0.0008508697,"threshold_uncertainty_score":0.016839027},"labels":[],"label_agreement":null},{"id":"W4379409172","doi":"10.1109/tsmc.2023.3279023","title":"Robotic Object Perception Based on Multispectral Few-Shot Coupled Learning","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Systems Man and Cybernetics Systems","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Science Foundation of Anhui Province; National Natural Science Foundation of China","keywords":"Artificial intelligence; Computer science; Robot; Shot (pellet); Computer vision; Multispectral image; Perception; Feature (linguistics); Coupling (piping); Object (grammar); Service robot; Pattern recognition (psychology); Machine learning; Cognitive neuroscience of visual object recognition; Dimension (graph theory); Engineering; Mathematics","score_opus":0.023856349103165978,"score_gpt":0.23201935276396007,"score_spread":0.2081630036607941,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379409172","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05941568,0.0005984769,0.93740577,0.00012204544,0.000074764714,0.000062778636,0.00007717399,0.0008680617,0.0013751474],"genre_scores_gemma":[0.7730222,0.00045693523,0.2212062,0.00038324157,0.00008220125,0.00010461441,0.0006664105,0.00013692156,0.0039413013],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99919194,0.00010110914,0.00003463979,0.00030057723,0.00027916703,0.00009248965],"domain_scores_gemma":[0.9992556,0.00020036816,0.00008903646,0.00016856863,0.00022352491,0.000063010586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007161713,0.0008877799,0.0012465911,0.00083840947,0.00036460222,0.00088487443,0.0016122336,0.00090306037,0.0009200813],"category_scores_gemma":[0.0021369308,0.00045918685,0.00081939076,0.00070653285,0.00074640766,0.0017735696,0.0016714751,0.0010779873,0.00045655106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048277134,0.0003754202,0.003052306,0.00024771673,0.00023496836,0.00021826365,0.00028181053,0.22620341,0.062378876,0.003443361,0.0028655448,0.70021546],"study_design_scores_gemma":[0.000010746063,0.00010112746,0.0009392735,0.0000075620683,0.000022926399,0.00008541553,0.000032739605,0.98646104,0.009371423,0.0022451414,0.00070377055,0.000018947832],"about_ca_topic_score_codex":0.0038377407,"about_ca_topic_score_gemma":0.0037044361,"teacher_disagreement_score":0.0038377407,"about_ca_system_score_codex":0.0004909889,"about_ca_system_score_gemma":0.0005848935,"threshold_uncertainty_score":0.0076307654},"labels":[],"label_agreement":null},{"id":"W4379469137","doi":"10.1109/jstars.2023.3282975","title":"Spatial–Spectral ConvNeXt for Hyperspectral Image Classification","year":2023,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Hyperspectral imaging; Computer science; Artificial intelligence; Pattern recognition (psychology); Contextual image classification; Spatial analysis; Pointwise; Block (permutation group theory); Pixel; Projection (relational algebra); Computer vision; Remote sensing; Image (mathematics); Mathematics; Algorithm; Geography","score_opus":0.03865021743885883,"score_gpt":0.2499291183233226,"score_spread":0.21127890088446377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379469137","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048251398,0.0015146559,0.9355402,0.0003287929,0.00018716788,0.00012377343,0.00085786305,0.006768617,0.0064275307],"genre_scores_gemma":[0.53523093,0.0014029134,0.43806663,0.0005307737,0.00012659004,0.00020734181,0.0058344207,0.00071547425,0.017884826],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998331,0.000018017403,0.000008092752,0.00005931287,0.00005399849,0.000027422555],"domain_scores_gemma":[0.9998462,0.00003042996,0.000016319906,0.000043050193,0.0000522647,0.000011727522],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004174986,0.00088445126,0.0004063222,0.0004620626,0.00021086216,0.00043906833,0.0014787524,0.00057198637,0.0036689618],"category_scores_gemma":[0.0005818892,0.00025206245,0.0008267857,0.0006494945,0.00033177357,0.0009225273,0.0007081736,0.00090442045,0.0012689179],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034029316,0.00026307555,0.0015890683,0.0002577403,0.00017517492,0.0001362138,0.00006495761,0.17410548,0.05370561,0.008762306,0.02063245,0.7399676],"study_design_scores_gemma":[0.000009366012,0.0000451193,0.00065369625,0.00001209829,0.000026989954,0.000067963345,0.000014692921,0.97349125,0.017655365,0.0025656451,0.005447641,0.000010177042],"about_ca_topic_score_codex":0.0083290925,"about_ca_topic_score_gemma":0.014615174,"teacher_disagreement_score":0.0083290925,"about_ca_system_score_codex":0.00052512065,"about_ca_system_score_gemma":0.0008094596,"threshold_uncertainty_score":0.01656121},"labels":[],"label_agreement":null},{"id":"W4379930767","doi":"10.1109/jurse57346.2023.10144084","title":"Preliminary Study of Urban Land Use Classification Using Historical Aerial Photos and AI Technology","year":2023,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Fredericton; University of New Brunswick","funders":"","keywords":"Aerial photography; Multispectral image; Aerial photos; Aerial imagery; Remote sensing; Aerial image; Urban planning; Aerial survey; Computer science; Land use; Geography; Cartography; Artificial intelligence; Engineering; Civil engineering","score_opus":0.05248585663313796,"score_gpt":0.2632596487895141,"score_spread":0.21077379215637612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379930767","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95833564,0.0003216012,0.024017187,0.00020787625,0.00002933979,0.00021619831,0.0026349311,0.00020126681,0.01403595],"genre_scores_gemma":[0.95759237,0.00023633528,0.036610372,0.0000307847,0.00001960067,0.00005031778,0.0021167705,0.000021942937,0.0033213934],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997002,0.000093254646,0.000017702992,0.00006149089,0.000093017756,0.00003426831],"domain_scores_gemma":[0.9991708,0.00027177425,0.000060599697,0.000102482976,0.00035165958,0.00004272574],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058281445,0.0002654704,0.0001479908,0.0013450544,0.00036604094,0.00041992942,0.00023447942,0.00022436609,0.0017056615],"category_scores_gemma":[0.0011051064,0.00010252192,0.00018168123,0.0015752729,0.00026448484,0.0005232029,0.00020069489,0.00017872149,0.00043484746],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004140676,0.0008813154,0.2854657,0.00050050416,0.00015788463,0.001146015,0.0015046166,0.036713667,0.060995232,0.0027588017,0.007683199,0.601779],"study_design_scores_gemma":[0.00002917565,0.0005807054,0.714622,0.00009430689,0.000097830496,0.0005873766,0.0034628643,0.2104023,0.04674243,0.001123369,0.02219781,0.000059688624],"about_ca_topic_score_codex":0.015830021,"about_ca_topic_score_gemma":0.04019782,"teacher_disagreement_score":0.015830021,"about_ca_system_score_codex":0.00036080254,"about_ca_system_score_gemma":0.00019634845,"threshold_uncertainty_score":0.031475723},"labels":[],"label_agreement":null},{"id":"W4382137697","doi":"10.3390/rs15133265","title":"Small Object Detection Based on Deep Learning for Remote Sensing: A Comprehensive Review","year":2023,"lang":"en","type":"review","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":95,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Military College of Canada","funders":"","keywords":"Computer science; Object detection; Remote sensing; Artificial intelligence; Object (grammar); Remote sensing application; Computer vision; Orientation (vector space); Pattern recognition (psychology); Geography; Hyperspectral imaging","score_opus":0.10073347818407367,"score_gpt":0.3144095739837815,"score_spread":0.2136760957997078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382137697","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007031374,0.98748255,0.008445812,0.0005065972,0.00032608258,0.0000217918,0.00007197349,0.000077080906,0.0023650704],"genre_scores_gemma":[0.0059846435,0.9865754,0.005152236,0.00032477546,0.00040787092,0.000028018458,0.000192478,0.000022885364,0.0013117086],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99967504,0.000048030743,0.00004264258,0.000081544094,0.0001263782,0.00002643285],"domain_scores_gemma":[0.9990551,0.00050844665,0.00007460928,0.000034455363,0.000293317,0.00003412781],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011248989,0.0011972402,0.0012454872,0.0024205511,0.00024486447,0.0011060054,0.0014333621,0.0011963078,0.0025631739],"category_scores_gemma":[0.0019185396,0.0004671238,0.0010201343,0.002922791,0.0004241129,0.0018940044,0.0008194474,0.0011928866,0.0017354516],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003547195,0.00006801971,0.00053475425,0.0083930595,0.00013316698,0.00007885317,0.00004211434,0.0020809248,0.0010161672,0.0038884433,0.015863925,0.967865],"study_design_scores_gemma":[0.000025412082,0.00032067488,0.0036029578,0.008045295,0.00069258374,0.00153899,0.00016631873,0.014775839,0.005573884,0.012961207,0.95214534,0.00015154992],"about_ca_topic_score_codex":0.002432935,"about_ca_topic_score_gemma":0.0023120907,"teacher_disagreement_score":0.0025631739,"about_ca_system_score_codex":0.0005857649,"about_ca_system_score_gemma":0.001129066,"threshold_uncertainty_score":0.008574665},"labels":[],"label_agreement":null},{"id":"W4382395082","doi":"10.18280/ts.400336","title":"Advancements in Geological Disaster Monitoring and Early Warning Systems: A Deep Learning and Computer Vision Approach","year":2023,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Natural Science Foundation of Hunan Province; Natural Science Foundation of Hainan Province; National Natural Science Foundation of China","keywords":"Deep learning; Computer science; Hyperspectral imaging; Warning system; Artificial intelligence; Data science; Remote sensing; Machine learning; Geography","score_opus":0.017809384798778197,"score_gpt":0.24067939214995054,"score_spread":0.22287000735117235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382395082","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015839003,0.0077916025,0.96660435,0.0032984784,0.00015781734,0.000029732457,0.00008318808,0.0003354191,0.00586049],"genre_scores_gemma":[0.5806224,0.015894394,0.39334682,0.00079887704,0.00049058755,0.000065131,0.00033257128,0.00005848559,0.008390755],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99980336,0.00004242915,0.00001348894,0.000041044124,0.00007127093,0.000028470267],"domain_scores_gemma":[0.999764,0.00007572971,0.000035862155,0.000028420833,0.000072512674,0.000023479442],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046828613,0.00046473215,0.00033239028,0.00084970176,0.00018802228,0.0008204268,0.00065495,0.0008082153,0.00089685596],"category_scores_gemma":[0.0008226505,0.00021846773,0.00032031993,0.00094475946,0.0004902876,0.0014050665,0.00094957347,0.0014514419,0.00028612834],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000783248,0.00014301717,0.0026103824,0.00035454656,0.000077423436,0.000113964314,0.00012875101,0.21439847,0.014057101,0.09127263,0.0065256916,0.67023975],"study_design_scores_gemma":[0.000005813911,0.000045993336,0.00091102766,0.000051693798,0.00002007936,0.00006393994,0.000038773323,0.9465849,0.0053302906,0.03403134,0.012901082,0.000015145454],"about_ca_topic_score_codex":0.0024670311,"about_ca_topic_score_gemma":0.0025280735,"teacher_disagreement_score":0.0024670311,"about_ca_system_score_codex":0.0005760185,"about_ca_system_score_gemma":0.000709136,"threshold_uncertainty_score":0.004905343},"labels":[],"label_agreement":null},{"id":"W4383815591","doi":"10.5566/ias.2928","title":"Noise Robust Hyperspectral Image Classification With MNF-Based Edge Preserving Features","year":2023,"lang":"en","type":"article","venue":"Image Analysis & Stereology","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Space Agency; Concordia University","funders":"","keywords":"Hyperspectral imaging; Principal component analysis; Artificial intelligence; Pattern recognition (psychology); Noise (video); Cube (algebra); Data cube; Computer science; Computer vision; Mathematics; Image (mathematics); Data mining","score_opus":0.02056783721473027,"score_gpt":0.24686434051929476,"score_spread":0.2262965033045645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383815591","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.064999975,0.0005173206,0.93159246,0.00019383414,0.000075852484,0.00006407938,0.00026006385,0.0011209624,0.0011754415],"genre_scores_gemma":[0.5514027,0.00067318784,0.44218087,0.0001883849,0.00017309525,0.00014251388,0.0018682211,0.00020122742,0.0031697336],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993135,0.00006830014,0.00003531025,0.00017041256,0.0003377865,0.00007472991],"domain_scores_gemma":[0.99925774,0.00017537516,0.0000888853,0.000119617136,0.0003262561,0.000032113378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006295584,0.0009841402,0.00086811546,0.0017744969,0.0004306574,0.0007618538,0.00076421263,0.00064132287,0.0008229355],"category_scores_gemma":[0.00217713,0.00023389373,0.001092101,0.0015652812,0.0005493061,0.0015084874,0.0006200733,0.0008210017,0.00048009306],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039531957,0.00022134458,0.00513843,0.00014575852,0.00013480293,0.00016662266,0.00011303343,0.06451981,0.061787214,0.0030206232,0.0055109323,0.85884607],"study_design_scores_gemma":[0.000014487484,0.00007543651,0.006072467,0.000014987248,0.000052454307,0.000231999,0.000055968896,0.95102143,0.036397424,0.0029475498,0.0030756574,0.00004006277],"about_ca_topic_score_codex":0.0029572474,"about_ca_topic_score_gemma":0.0034770805,"teacher_disagreement_score":0.0029572474,"about_ca_system_score_codex":0.00037581567,"about_ca_system_score_gemma":0.0005858098,"threshold_uncertainty_score":0.005880058},"labels":[],"label_agreement":null},{"id":"W4384393272","doi":"10.1016/j.isprsjprs.2023.07.001","title":"An attention-based multiscale transformer network for remote sensing image change detection","year":2023,"lang":"en","type":"article","venue":"ISPRS Journal of Photogrammetry and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":160,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Science Foundation of Jiangxi Province; National Natural Science Foundation of China","keywords":"Computer science; Transformer; Change detection; Artificial intelligence; Architecture; Pattern recognition (psychology); Computer vision; Data mining","score_opus":0.025358292185722435,"score_gpt":0.2717231394693599,"score_spread":0.24636484728363744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384393272","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042479772,0.00041062952,0.95436776,0.00013818078,0.00007586622,0.000058117694,0.00015856729,0.00075706467,0.0015540195],"genre_scores_gemma":[0.82810736,0.00043312032,0.16709667,0.00015931357,0.000121778685,0.00007483402,0.00050800457,0.00010444414,0.0033945334],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997794,0.000038909486,0.000010878992,0.000072323855,0.00005896307,0.00003950877],"domain_scores_gemma":[0.99964213,0.00013536368,0.000033022712,0.000037950198,0.00012080175,0.000030751682],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004742556,0.0005483692,0.00076730666,0.00088510796,0.00029220295,0.0005128356,0.0010764503,0.000566953,0.002462344],"category_scores_gemma":[0.001234802,0.00024290747,0.00054264715,0.0008736685,0.00029260328,0.0010346308,0.0009938717,0.00058347534,0.00045595784],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046486445,0.00026255051,0.0019384793,0.00011844049,0.000113863774,0.0001797383,0.000064723376,0.1343666,0.036005232,0.0066207815,0.0044963514,0.81536835],"study_design_scores_gemma":[0.000004131111,0.00002698698,0.000382321,0.0000025071702,0.0000159304,0.000030058929,0.0000058053897,0.9958192,0.0021299187,0.0013131053,0.0002664429,0.0000035454555],"about_ca_topic_score_codex":0.0071183606,"about_ca_topic_score_gemma":0.008687206,"teacher_disagreement_score":0.0071183606,"about_ca_system_score_codex":0.0005371033,"about_ca_system_score_gemma":0.0005247786,"threshold_uncertainty_score":0.014153898},"labels":[],"label_agreement":null},{"id":"W4385399670","doi":"10.3390/rs15153782","title":"A Spatial–Temporal Bayesian Deep Image Prior Model for Moderate Resolution Imaging Spectroradiometer Temporal Mixture Analysis","year":2023,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Hyperspectral imaging; Computer science; Moderate-resolution imaging spectroradiometer; Image resolution; Temporal resolution; Remote sensing; Context (archaeology); Artificial intelligence; Time series; Pattern recognition (psychology); Spectroradiometer; Machine learning; Geography","score_opus":0.016896969699850047,"score_gpt":0.2504923610505379,"score_spread":0.23359539135068785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385399670","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0067571574,0.00033958541,0.99097764,0.00030748965,0.000029225599,0.000020896194,0.00015203387,0.0004078606,0.0010080327],"genre_scores_gemma":[0.63461107,0.0014049434,0.34212157,0.00086215395,0.00023536947,0.00039619824,0.0016840383,0.0002649071,0.018419733],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99954695,0.00008634606,0.000022427806,0.00014290863,0.00012989288,0.00007144174],"domain_scores_gemma":[0.9995233,0.00021678787,0.00006117921,0.000032079875,0.00012695113,0.00003987607],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010544066,0.0010288645,0.0011391649,0.0008196306,0.0003744615,0.0009211172,0.0027404036,0.0017126055,0.002842872],"category_scores_gemma":[0.0020352877,0.0007993307,0.0011986484,0.0009490231,0.0009828452,0.0020295496,0.0015406851,0.0025155593,0.00075314933],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019249925,0.00008327126,0.0014285038,0.000095147654,0.00009722305,0.000090836256,0.000072666015,0.8252348,0.00399646,0.029731235,0.0032962938,0.13568117],"study_design_scores_gemma":[0.0000033442107,0.000006679997,0.000071389135,0.0000031847078,0.0000062230342,0.000008726436,0.0000013660054,0.99677074,0.00027716975,0.0025996624,0.00024742525,0.0000040679543],"about_ca_topic_score_codex":0.017195322,"about_ca_topic_score_gemma":0.015169496,"teacher_disagreement_score":0.017195322,"about_ca_system_score_codex":0.001487149,"about_ca_system_score_gemma":0.0015123672,"threshold_uncertainty_score":0.034190476},"labels":[],"label_agreement":null},{"id":"W4385432686","doi":"","title":"Causal Markov mesh hierarchical modeling for the contextual classification of multiresolution satellite images","year":2019,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Artificial intelligence; Markov model; Markov chain; Satellite; Pattern recognition (psychology); Hidden Markov model; Markov process; Data mining; Machine learning; Mathematics; Engineering; Statistics","score_opus":0.01885450536417361,"score_gpt":0.22896019736209308,"score_spread":0.21010569199791948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385432686","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031401787,0.000527494,0.9663866,0.00037900003,0.000053136482,0.00003780751,0.00034331565,0.00039767698,0.00047316236],"genre_scores_gemma":[0.86577374,0.00081669225,0.12734285,0.00023050245,0.00027464834,0.00020765659,0.0015152444,0.00018944782,0.003649255],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916315,0.00034206142,0.000040863462,0.00021596559,0.00012357446,0.00011442663],"domain_scores_gemma":[0.99442416,0.0042284825,0.00049804867,0.00037548286,0.00031195578,0.00016184515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025352186,0.0006138693,0.0015392151,0.0014998885,0.00061793166,0.0011172359,0.002430804,0.0017719977,0.002339686],"category_scores_gemma":[0.008433161,0.0008783905,0.0015275468,0.0016320655,0.001112345,0.0015412098,0.001351135,0.0019350058,0.00037448938],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011882668,0.000051581977,0.0013686046,0.00008362719,0.0000870815,0.00004938184,0.000076155186,0.9318636,0.00081217126,0.030606413,0.0011548351,0.033727728],"study_design_scores_gemma":[0.0000018636407,0.0000035336018,0.000114532006,0.0000026344633,0.0000039548995,0.0000019227602,0.0000024234935,0.9948172,0.000041944815,0.00494062,0.00006696929,0.0000023372124],"about_ca_topic_score_codex":0.030060465,"about_ca_topic_score_gemma":0.03149501,"teacher_disagreement_score":0.030060465,"about_ca_system_score_codex":0.0017421882,"about_ca_system_score_gemma":0.0011208262,"threshold_uncertainty_score":0.059771},"labels":[],"label_agreement":null},{"id":"W4385446408","doi":"10.3390/s23156845","title":"Analysis of Hyperspectral Data to Develop an Approach for Document Images","year":2023,"lang":"en","type":"review","venue":"Sensors","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Hyperspectral imaging; Preprocessor; Computer science; Data pre-processing; Data science; Field (mathematics); Feature extraction; Image processing; Data mining; Artificial intelligence; Information retrieval; Pattern recognition (psychology); Image (mathematics); Mathematics","score_opus":0.19035495158476096,"score_gpt":0.37987170346447613,"score_spread":0.18951675187971517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385446408","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0077212634,0.11884141,0.8354301,0.0024101858,0.0012051153,0.00042872003,0.001204322,0.0017041388,0.03105478],"genre_scores_gemma":[0.08717895,0.18174306,0.70721275,0.0016436249,0.0010112944,0.000504244,0.0024078903,0.00043290036,0.017865334],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993311,0.00008791026,0.0000465305,0.00014313457,0.00035932384,0.000031955708],"domain_scores_gemma":[0.99938905,0.00015457712,0.00006364715,0.000055299766,0.00032224783,0.000015172307],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011002693,0.001046783,0.0007927223,0.0041917353,0.00036606466,0.0020163034,0.0011251373,0.00097043,0.003159112],"category_scores_gemma":[0.0013269293,0.00032853478,0.0009275498,0.003584011,0.00086825475,0.002050886,0.00070238725,0.001725125,0.0030098467],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003630296,0.00006690293,0.0013450853,0.0043735025,0.00016112332,0.00018129236,0.000220266,0.0042816326,0.048446003,0.024832625,0.015643878,0.9004115],"study_design_scores_gemma":[0.000018341902,0.00019890977,0.009518258,0.0024633382,0.0003053537,0.0025090177,0.0008809408,0.080835864,0.13109925,0.048487406,0.7234646,0.00021867787],"about_ca_topic_score_codex":0.0012521842,"about_ca_topic_score_gemma":0.0020672637,"teacher_disagreement_score":0.0041917353,"about_ca_system_score_codex":0.0006544233,"about_ca_system_score_gemma":0.0007088188,"threshold_uncertainty_score":0.010568261},"labels":[],"label_agreement":null},{"id":"W4385507417","doi":"10.3390/rs15153855","title":"An Unsupervised Feature Extraction Using Endmember Extraction and Clustering Algorithms for Dimension Reduction of Hyperspectral Images","year":2023,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Hyperspectral imaging; Dimensionality reduction; Endmember; Pattern recognition (psychology); Artificial intelligence; Computer science; Cluster analysis; Principal component analysis; Classifier (UML); Support vector machine; Feature extraction; Curse of dimensionality","score_opus":0.03714904626541637,"score_gpt":0.30851121036085827,"score_spread":0.2713621640954419,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385507417","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014415741,0.000182766,0.98434883,0.000045648903,0.000026983218,0.00004115972,0.000043763765,0.00045725174,0.0004378224],"genre_scores_gemma":[0.14375232,0.00032781909,0.8525282,0.000068427136,0.000046168854,0.00015428134,0.0004681063,0.00009928602,0.0025554535],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994209,0.000065552354,0.000036666697,0.0001867495,0.00024808687,0.000042075233],"domain_scores_gemma":[0.9996387,0.00006482922,0.00005106413,0.000053644642,0.00017964156,0.000012089969],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036326112,0.0007895153,0.0005871195,0.0016914811,0.00055143645,0.0005312167,0.000741514,0.0005615475,0.00061065546],"category_scores_gemma":[0.00082021265,0.00029454965,0.0011786434,0.0011518663,0.00036573762,0.0009623822,0.0005823025,0.0007632341,0.00035119362],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000086835214,0.00016349585,0.0018749334,0.00016191237,0.00014288745,0.00010198975,0.000204809,0.048926916,0.09758078,0.00461037,0.0027398386,0.84340525],"study_design_scores_gemma":[0.000015904194,0.00010177446,0.005379396,0.00002347985,0.000055456112,0.00030368162,0.00007809185,0.91193783,0.07254642,0.0030554973,0.0064281863,0.0000742341],"about_ca_topic_score_codex":0.0028485993,"about_ca_topic_score_gemma":0.003434557,"teacher_disagreement_score":0.0028485993,"about_ca_system_score_codex":0.00032697647,"about_ca_system_score_gemma":0.0007171729,"threshold_uncertainty_score":0.00566411},"labels":[],"label_agreement":null},{"id":"W4385859659","doi":"10.2139/ssrn.4542996","title":"Bd-Yolo: Detection Algorithm for High-Resolution Remote Sensing Images","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"High resolution; Remote sensing; Computer science; Computer vision; Artificial intelligence; Algorithm; Geography","score_opus":0.01629700837098123,"score_gpt":0.24520981455467283,"score_spread":0.22891280618369161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385859659","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0071749855,0.00037215772,0.98051125,0.000117787284,0.0001442962,0.00011228543,0.00089901104,0.009560189,0.0011081048],"genre_scores_gemma":[0.033733953,0.0002268002,0.9553133,0.00013668188,0.00006305052,0.00033380196,0.0027683924,0.0007579166,0.006666207],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99971324,0.00002896593,0.000019263494,0.00008157941,0.00009859124,0.000058339112],"domain_scores_gemma":[0.9997515,0.00004646146,0.00002345829,0.000042629657,0.000110024994,0.00002590032],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053441286,0.0009464208,0.0007998743,0.0013842903,0.00052569306,0.001124193,0.0013005815,0.0010322699,0.0130004315],"category_scores_gemma":[0.0015390745,0.00049970055,0.00048106676,0.0011214851,0.00030068972,0.0008382673,0.0013312477,0.0009303511,0.009020633],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000700589,0.00015108603,0.0012207483,0.000321697,0.00006148657,0.00006493261,0.00006532347,0.0063406765,0.10050025,0.0042328415,0.035838183,0.85050213],"study_design_scores_gemma":[0.00026665322,0.00027754589,0.0075090304,0.00010229026,0.00008603178,0.00041064725,0.00008232479,0.7344864,0.17996149,0.005711959,0.07101125,0.00009446391],"about_ca_topic_score_codex":0.0029512781,"about_ca_topic_score_gemma":0.0052131875,"teacher_disagreement_score":0.0130004315,"about_ca_system_score_codex":0.00040046597,"about_ca_system_score_gemma":0.0010480513,"threshold_uncertainty_score":0.043490767},"labels":[],"label_agreement":null},{"id":"W4386074499","doi":"10.11159/mvml23.102","title":"Statistical Modelling of Air-Ground Remotely Sensed Geo-Intelligence Information Using Naïve Bayesian Classification: A Decision-Making Approach","year":2023,"lang":"en","type":"article","venue":"Proceedings of the World Congress on Electrical Engineering and Computer Systems and Science","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Bayesian probability; Computer science; Remote sensing; Artificial intelligence; Environmental science; Data mining; Machine learning; Geology","score_opus":0.02386550532413943,"score_gpt":0.23539840954579044,"score_spread":0.21153290422165102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386074499","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024799807,0.0003605549,0.97113246,0.00091858365,0.000068801884,0.000128569,0.00017219206,0.00015840823,0.0022607243],"genre_scores_gemma":[0.7926708,0.0007603787,0.19970211,0.0004419446,0.00036011793,0.00041926157,0.0006479769,0.000068441135,0.00492896],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965282,0.0016159381,0.00023689093,0.00052302046,0.0007971247,0.000298828],"domain_scores_gemma":[0.9872635,0.010111712,0.0008020969,0.00033660376,0.0012699539,0.00021617347],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008684434,0.001000159,0.0022494786,0.0021900139,0.0010539211,0.0035277475,0.0033996466,0.0022269387,0.0029574274],"category_scores_gemma":[0.017441938,0.0011837358,0.0015307647,0.0016005513,0.0022987418,0.0033839326,0.0012574297,0.0024577675,0.00067563873],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010889551,0.00007681422,0.0016246093,0.00008991941,0.00007102596,0.000096307944,0.0001302619,0.9229126,0.00032872436,0.043743458,0.0009128455,0.029904556],"study_design_scores_gemma":[0.000006418663,0.000012971646,0.00015734577,0.000012193766,0.000007933099,0.000010107059,0.000010532687,0.97842944,0.0000706471,0.021121133,0.00015059467,0.000010702481],"about_ca_topic_score_codex":0.020353207,"about_ca_topic_score_gemma":0.01330261,"teacher_disagreement_score":0.020353207,"about_ca_system_score_codex":0.0026286743,"about_ca_system_score_gemma":0.0020539204,"threshold_uncertainty_score":0.04592824},"labels":[],"label_agreement":null},{"id":"W4386194718","doi":"10.1080/07038992.2023.2246158","title":"Hyperspectral Image Classification Based on the Gabor Feature with Correlation Information","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Natural Science Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Artificial intelligence; Pattern recognition (psychology); Gabor filter; Hyperspectral imaging; Principal component analysis; Filter (signal processing); Mathematics; Feature (linguistics); Feature vector; Dimensionality reduction; Computer vision; Computer science; Feature extraction","score_opus":0.012924937822112268,"score_gpt":0.1984443886033527,"score_spread":0.18551945078124044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386194718","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1778159,0.00064882357,0.81471187,0.0002144423,0.00009752701,0.000083037645,0.00030250257,0.0017427148,0.004383205],"genre_scores_gemma":[0.79717445,0.0005424457,0.1983614,0.00012788057,0.00009069076,0.00007606473,0.0006955505,0.00007205786,0.0028594572],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999613,0.00003389206,0.000019198076,0.00009351832,0.00018559888,0.00005484519],"domain_scores_gemma":[0.99973625,0.00006112226,0.00004657485,0.00003723562,0.000103083774,0.000015691101],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037325668,0.0004493656,0.0005824094,0.001671904,0.00027051166,0.00049795484,0.00030796908,0.00038966702,0.0010176692],"category_scores_gemma":[0.00076167047,0.00014138318,0.0006879761,0.0012939028,0.00033097304,0.0009601914,0.00035209843,0.0003511372,0.00052829075],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002444563,0.00018226457,0.012258466,0.00013560664,0.00009717626,0.00014315527,0.00007646941,0.021903414,0.12374831,0.0025625068,0.0041164206,0.83453184],"study_design_scores_gemma":[0.000019339423,0.00011813709,0.03493496,0.000026826301,0.000090508125,0.00041053377,0.00009259325,0.89631397,0.062091142,0.0022973288,0.0035539146,0.000050776798],"about_ca_topic_score_codex":0.0020391692,"about_ca_topic_score_gemma":0.0022568828,"teacher_disagreement_score":0.0020391692,"about_ca_system_score_codex":0.0002921996,"about_ca_system_score_gemma":0.00032172966,"threshold_uncertainty_score":0.0040546656},"labels":[],"label_agreement":null},{"id":"W4386243193","doi":"10.1109/crv60082.2023.00021","title":"Learning-to-Count by Learning-to-Rank","year":2023,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Artificial intelligence; Benchmark (surveying); Ranking (information retrieval); Feature (linguistics); Pattern recognition (psychology); Pairwise comparison; Object (grammar); Annotation; Density estimation; Constraint (computer-aided design); Representation (politics); Spurious relationship; Rank (graph theory); Feature extraction; Image (mathematics); Object detection; Feature learning; Machine learning; Estimator; Mathematics; Statistics","score_opus":0.011429447303167856,"score_gpt":0.23230072206781613,"score_spread":0.22087127476464827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386243193","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018498821,0.0005817224,0.9384721,0.0006887587,0.00028182403,0.0003810974,0.0023420912,0.031687003,0.0070665358],"genre_scores_gemma":[0.26271898,0.0004456373,0.6996443,0.0008077487,0.00055964675,0.0010325747,0.012714431,0.003795348,0.018281229],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99599224,0.0008829515,0.00021440614,0.0012822675,0.0012570407,0.00037109],"domain_scores_gemma":[0.9919191,0.0025992417,0.0007049227,0.0029213454,0.0014985122,0.00035698642],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028183856,0.0035089448,0.003091483,0.0034229383,0.0015601625,0.003327959,0.0060725957,0.0029886772,0.014338641],"category_scores_gemma":[0.019445034,0.0011221787,0.0015185609,0.0034493776,0.0016812162,0.0056749834,0.0039266394,0.0031296022,0.013581262],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039425638,0.0004819594,0.0040272735,0.00060227816,0.00019527167,0.00018414452,0.0001630901,0.14634866,0.005646837,0.03145639,0.10937753,0.7011223],"study_design_scores_gemma":[0.00006117767,0.00008582775,0.00046597968,0.000031989042,0.00002082464,0.00013558757,0.000052720097,0.9443945,0.004593067,0.04223845,0.007881606,0.000038261922],"about_ca_topic_score_codex":0.0058538276,"about_ca_topic_score_gemma":0.014558738,"teacher_disagreement_score":0.014338641,"about_ca_system_score_codex":0.0019117257,"about_ca_system_score_gemma":0.002499947,"threshold_uncertainty_score":0.047967553},"labels":[],"label_agreement":null},{"id":"W4386603268","doi":"10.1080/07038992.2023.2255068","title":"Multiscale Cascaded Network for the Semantic Segmentation of High-Resolution Remote Sensing Images","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Segmentation; Artificial intelligence; Computer science; Pooling; Pattern recognition (psychology); Feature (linguistics); Intersection (aeronautics); Pyramid (geometry); Remote sensing; Feature extraction; Data mining; Computer vision; Geography; Cartography; Mathematics","score_opus":0.022124337231576637,"score_gpt":0.24046955468740278,"score_spread":0.21834521745582613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386603268","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24827935,0.0025901282,0.7332307,0.0006033372,0.00020623567,0.00016946292,0.0011476089,0.004987689,0.008785552],"genre_scores_gemma":[0.8621995,0.000652154,0.13015606,0.00025060546,0.000075320866,0.0000845356,0.0019305397,0.00014283469,0.0045084725],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99967515,0.00003908434,0.000013641768,0.00013360682,0.00007720743,0.00006139279],"domain_scores_gemma":[0.9998093,0.00005003102,0.000028373588,0.000031100273,0.000060375467,0.000020717483],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005674609,0.0011814113,0.0006451065,0.0012292806,0.00043380185,0.0005842797,0.0011523799,0.0008480283,0.001987307],"category_scores_gemma":[0.0009329658,0.000395346,0.00093632424,0.00077638763,0.00044447038,0.0015150518,0.00080592115,0.00077542354,0.0004814996],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00072815357,0.0003106894,0.0064129513,0.0002598914,0.00035842444,0.00044779328,0.00023533548,0.436784,0.04913383,0.01028747,0.009596811,0.4854446],"study_design_scores_gemma":[0.0000063412303,0.000050016108,0.0013888503,0.000009382775,0.000041647072,0.000043720785,0.000018971848,0.9876416,0.0067011216,0.003045,0.0010444836,0.000008877199],"about_ca_topic_score_codex":0.01553752,"about_ca_topic_score_gemma":0.019251412,"teacher_disagreement_score":0.01553752,"about_ca_system_score_codex":0.0013449896,"about_ca_system_score_gemma":0.00084994786,"threshold_uncertainty_score":0.03089416},"labels":[],"label_agreement":null},{"id":"W4386858049","doi":"10.1109/jstars.2023.3316733","title":"Beyond Supervised Learning in Remote Sensing: A Systematic Review of Deep Learning Approaches","year":2023,"lang":"en","type":"review","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre For Cold Ocean Resources Engineering; Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Deep learning; Artificial intelligence; Machine learning; Remote sensing; Geology","score_opus":0.07211453422852876,"score_gpt":0.2671412366033812,"score_spread":0.19502670237485242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386858049","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017717216,0.996606,0.0017838252,0.00052484666,0.00015640011,0.000012639416,0.000039686573,0.0000129592445,0.00068651815],"genre_scores_gemma":[0.001988162,0.9954165,0.001766027,0.0003117187,0.00019593425,0.000019275541,0.00006730098,0.000007571453,0.00022753168],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990299,0.0002590075,0.00018571292,0.0001916377,0.00029118275,0.000042604494],"domain_scores_gemma":[0.9937594,0.0048611127,0.00031324624,0.00012941474,0.00084841467,0.00008848494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028717702,0.0010693168,0.0015676835,0.0044387816,0.00032594943,0.0015958257,0.0012809285,0.001319629,0.0027893507],"category_scores_gemma":[0.0069930158,0.000520239,0.0013154949,0.0057753217,0.00080429553,0.0024221775,0.0009524236,0.0015302337,0.0010042073],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052591473,0.00006820683,0.0007314137,0.05722431,0.00032808792,0.00009571916,0.00015309802,0.0014893373,0.00048103885,0.008132007,0.014869948,0.91637415],"study_design_scores_gemma":[0.000034170607,0.0002697178,0.003494013,0.06839795,0.001299199,0.0008327368,0.00037082628,0.0028753472,0.0012960322,0.016428575,0.9045935,0.00010791557],"about_ca_topic_score_codex":0.0034241485,"about_ca_topic_score_gemma":0.0061320066,"teacher_disagreement_score":0.0044387816,"about_ca_system_score_codex":0.0009668349,"about_ca_system_score_gemma":0.0036361248,"threshold_uncertainty_score":0.0151875615},"labels":[],"label_agreement":null},{"id":"W4386919833","doi":"10.1109/sas58821.2023.10254115","title":"Spectral-Spatial-Frequency Transformer Network for Hyperspectral Image Classification","year":2023,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Hyperspectral imaging; Computer science; Transformer; Artificial intelligence; Pattern recognition (psychology); Remote sensing; Geology; Engineering; Electrical engineering; Voltage","score_opus":0.027039426782337908,"score_gpt":0.2530126333482953,"score_spread":0.22597320656595743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386919833","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.093767084,0.0012748955,0.89395535,0.0005654935,0.00015032895,0.000083018975,0.00040004728,0.00230267,0.007501099],"genre_scores_gemma":[0.8773574,0.00072306156,0.112634555,0.00022870988,0.000063710075,0.00008811263,0.00096642616,0.00006340084,0.00787458],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999877,0.000019732388,0.0000054571456,0.000026238326,0.000050099006,0.000021507609],"domain_scores_gemma":[0.99987996,0.000036282938,0.000017469381,0.000012043455,0.000044927525,0.000009293167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032416594,0.00051769987,0.0003018021,0.00038190561,0.00018370591,0.0003398865,0.0006521036,0.0004291283,0.00167826],"category_scores_gemma":[0.00059627875,0.00012989166,0.00033522546,0.00048397036,0.00024080837,0.00069263147,0.00044409494,0.0007094017,0.00049058255],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028090875,0.00029400495,0.0036677036,0.00013153919,0.00009228294,0.00016583974,0.000060298767,0.38738158,0.035541873,0.009105343,0.010275142,0.55300355],"study_design_scores_gemma":[0.0000025976126,0.00002336514,0.00030173524,0.0000039993515,0.0000070042292,0.000022586353,0.00000944118,0.9937012,0.0038507031,0.001422322,0.00065095926,0.0000040494365],"about_ca_topic_score_codex":0.005055485,"about_ca_topic_score_gemma":0.0066746958,"teacher_disagreement_score":0.005055485,"about_ca_system_score_codex":0.00048660638,"about_ca_system_score_gemma":0.00058023963,"threshold_uncertainty_score":0.0100521445},"labels":[],"label_agreement":null},{"id":"W4387101011","doi":"10.3390/app131910729","title":"Detection and Classification of Buildings by Height from Single Urban High-Resolution Remote Sensing Images","year":2023,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Shadow (psychology); Remote sensing; Beijing; Computer science; Geography; Artificial intelligence; Change detection; Computer vision","score_opus":0.019792637584718675,"score_gpt":0.21978770631476793,"score_spread":0.19999506873004927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387101011","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7098082,0.00026537236,0.2824775,0.00007196875,0.00003866029,0.00013341178,0.0007742673,0.0022701698,0.0041604443],"genre_scores_gemma":[0.88376385,0.00011262513,0.11406798,0.000026536967,0.000013917331,0.000025566002,0.00088916067,0.000046209578,0.0010541095],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997981,0.000024957504,0.000009847439,0.000046334637,0.000080620455,0.000040111143],"domain_scores_gemma":[0.99973804,0.00004590484,0.00004300085,0.000056268622,0.00009070749,0.000026109981],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026068802,0.0004302881,0.0002507293,0.0016866825,0.00018044887,0.00036501177,0.00028993355,0.0002686575,0.0008821145],"category_scores_gemma":[0.0003738389,0.00016877228,0.00030602212,0.0008034494,0.00022289189,0.00027129528,0.00028577095,0.00022085344,0.0004731682],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036085068,0.00016271284,0.05445788,0.00025355263,0.00013353769,0.00025045555,0.00030471585,0.028622119,0.3823441,0.0010828944,0.002154172,0.529873],"study_design_scores_gemma":[0.00003545214,0.00018941097,0.29882005,0.000025538238,0.00012671355,0.00053660583,0.00039220075,0.50297546,0.19220713,0.0009875924,0.0036250353,0.00007873672],"about_ca_topic_score_codex":0.004402056,"about_ca_topic_score_gemma":0.010930521,"teacher_disagreement_score":0.004402056,"about_ca_system_score_codex":0.00021774945,"about_ca_system_score_gemma":0.00023799353,"threshold_uncertainty_score":0.008752823},"labels":[],"label_agreement":null},{"id":"W4387227650","doi":"10.1145/3570361.3613296","title":"MobiSpectral: Hyperspectral Imaging on Mobile Devices","year":2023,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Hyperspectral imaging; Computer science; Artificial intelligence; RGB color model; Electromagnetic spectrum; Computer vision; Remote sensing; Mobile phone; Near-infrared spectroscopy; Mobile device; Identification (biology); Telecommunications; Geography; Optics","score_opus":0.013373097658204913,"score_gpt":0.24392748623274288,"score_spread":0.23055438857453797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387227650","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1127232,0.0021175796,0.8101404,0.000988616,0.00037000497,0.0004612473,0.005747955,0.045807373,0.02164371],"genre_scores_gemma":[0.5322146,0.0012524104,0.4397401,0.0010217773,0.00014690205,0.0005008901,0.009547679,0.0014913069,0.014084431],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999686,0.00003829847,0.000009023001,0.000076421864,0.00015853473,0.0000317659],"domain_scores_gemma":[0.9997652,0.000050043127,0.00003340834,0.000059447015,0.00006830001,0.000023610784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028671708,0.0009269702,0.00030081504,0.00055852544,0.00020280645,0.0005348511,0.000953374,0.00056232413,0.0033810185],"category_scores_gemma":[0.00073258823,0.00024127442,0.00031698888,0.00036021488,0.00023728299,0.0010817746,0.0011397961,0.00055513275,0.0014520336],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008165491,0.0004108658,0.0054108663,0.00053319725,0.00021972794,0.0004961809,0.00017606991,0.035042066,0.18893708,0.0057338867,0.11255146,0.64967203],"study_design_scores_gemma":[0.00010853092,0.00037061845,0.008958667,0.00007524251,0.000037939346,0.00075534015,0.00012087861,0.7669722,0.14306836,0.0067867194,0.072636776,0.00010871117],"about_ca_topic_score_codex":0.002001939,"about_ca_topic_score_gemma":0.003646266,"teacher_disagreement_score":0.0033810185,"about_ca_system_score_codex":0.0003373887,"about_ca_system_score_gemma":0.00027695895,"threshold_uncertainty_score":0.011310637},"labels":[],"label_agreement":null},{"id":"W4387331747","doi":"10.1007/978-3-031-26588-4_11","title":"Object-Based Image Analysis","year":2023,"lang":"en","type":"book-chapter","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Resources Canada; McGill University; Canadian Forest Service","funders":"","keywords":"Computer science; Artificial intelligence; Computer vision; Image (mathematics); Object (grammar)","score_opus":0.020721201135358996,"score_gpt":0.22011994922575379,"score_spread":0.1993987480903948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387331747","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020703748,0.029680181,0.7064195,0.0013372784,0.0062902127,0.00023469563,0.0024963391,0.01185054,0.23962086],"genre_scores_gemma":[0.025224898,0.026798178,0.35339174,0.0016696337,0.0014252126,0.00016818872,0.006480915,0.0046917317,0.5801494],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991992,0.000031803378,0.000023803505,0.00011580967,0.00058627414,0.0000430792],"domain_scores_gemma":[0.9995334,0.00007251516,0.000014148559,0.00006747615,0.00029803775,0.000014483681],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051827607,0.0011728855,0.0008744036,0.0030457147,0.00058826467,0.0027837497,0.0014536317,0.0011073764,0.03671831],"category_scores_gemma":[0.00076644943,0.0006253056,0.0008463084,0.0034830153,0.00064994965,0.0017656082,0.001171303,0.0011188878,0.03739792],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021645714,0.000029322002,0.0001229176,0.00048353907,0.00004415119,0.00007481069,0.00007032319,0.0017591818,0.01455722,0.02122324,0.24233766,0.719276],"study_design_scores_gemma":[0.000005069149,0.000018000923,0.0010398363,0.00014696893,0.000030597013,0.00041993137,0.000035634657,0.014399402,0.017761834,0.014119517,0.9519812,0.00004196063],"about_ca_topic_score_codex":0.0035427576,"about_ca_topic_score_gemma":0.0053887013,"teacher_disagreement_score":0.03671831,"about_ca_system_score_codex":0.0008174372,"about_ca_system_score_gemma":0.00071707246,"threshold_uncertainty_score":0.12283498},"labels":[],"label_agreement":null},{"id":"W4387338201","doi":"10.1049/cvi2.12242","title":"Guest Editorial: Spectral imaging powered computer vision","year":2023,"lang":"en","type":"editorial","venue":"IET Computer Vision","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Computer vision; Computer science; Artificial intelligence; Imaging science; Spectral imaging; Computer graphics (images); Remote sensing; Geography","score_opus":0.005511212499722027,"score_gpt":0.2526673970356766,"score_spread":0.24715618453595456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387338201","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013255753,0.008515611,0.0004774832,0.01574882,0.9714855,0.000022611988,0.000063383995,0.00014360511,0.0034104816],"genre_scores_gemma":[0.0012220617,0.0072988784,0.00025770356,0.0067648985,0.97021717,0.000021504184,0.00006188933,0.00010288171,0.01405316],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957196,0.00049740454,0.00043866967,0.00079941604,0.0021328672,0.00041194074],"domain_scores_gemma":[0.97988224,0.0048919097,0.0010924417,0.0006044563,0.009697438,0.0038316124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046122465,0.002884856,0.0025539023,0.00452389,0.0023636401,0.009949754,0.0030721405,0.009230592,0.03583715],"category_scores_gemma":[0.014225629,0.0009833585,0.002415521,0.0012883922,0.002017868,0.0041803936,0.0015462332,0.010421726,0.028890043],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000081775295,0.000021171316,0.000058207603,0.00033529595,0.000025694831,0.00019195993,0.000016373584,0.000050129114,0.00022900768,0.0007414279,0.985307,0.0129419705],"study_design_scores_gemma":[0.000043563414,0.00007013063,0.00029219143,0.0002887683,0.00003560503,0.0006780033,0.00004263722,0.000258306,0.00045802165,0.0013459162,0.9964599,0.0000269313],"about_ca_topic_score_codex":0.0004582146,"about_ca_topic_score_gemma":0.0008106503,"teacher_disagreement_score":0.03583715,"about_ca_system_score_codex":0.0020785746,"about_ca_system_score_gemma":0.001987814,"threshold_uncertainty_score":0.11988717},"labels":[],"label_agreement":null},{"id":"W4387717108","doi":"10.1364/hmise.2023.hw5c.2","title":"Denoising and Dimensionality Reduction for Improving Constrained Energy Minimization in Hyperspectral Imagery Analysis","year":2023,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Canadian Space Agency","funders":"","keywords":"Hyperspectral imaging; Dimensionality reduction; Artificial intelligence; Noise reduction; Energy minimization; Computer science; Minification; Pattern recognition (psychology); Energy (signal processing); Image denoising; Reduction (mathematics); Computer vision; Curse of dimensionality; Image (mathematics); Mathematics; Statistics; Chemistry","score_opus":0.014997563481556623,"score_gpt":0.23338285466827802,"score_spread":0.2183852911867214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387717108","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013868601,0.00020422756,0.98512506,0.00006975256,0.000020833812,0.00001532484,0.000028837241,0.00016583723,0.00050135894],"genre_scores_gemma":[0.21810117,0.00054171507,0.77780974,0.00012529045,0.000066888126,0.00010947262,0.0003846662,0.00022885832,0.0026321907],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995896,0.00009675915,0.000023709927,0.00008885006,0.00017381851,0.000027264881],"domain_scores_gemma":[0.99965405,0.00013558584,0.00003961409,0.000050491755,0.00010768996,0.000012584392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005011609,0.0008469405,0.0006796722,0.0007453387,0.00030406463,0.00049536594,0.0006275824,0.0006054308,0.0008829668],"category_scores_gemma":[0.0014825714,0.00027305388,0.000727987,0.00072752434,0.00046204033,0.00089982315,0.00075688533,0.00071234215,0.0003927744],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022442942,0.00016740404,0.001502565,0.00030089484,0.00017650206,0.00022449729,0.00025372923,0.21635184,0.23480429,0.01656336,0.0035023934,0.5259281],"study_design_scores_gemma":[0.000007270082,0.000042533535,0.0009503393,0.000009178717,0.000020330479,0.00013050348,0.000021577405,0.9562311,0.036571126,0.0038667328,0.0021242576,0.00002512709],"about_ca_topic_score_codex":0.0010275362,"about_ca_topic_score_gemma":0.0013855874,"teacher_disagreement_score":0.0010275362,"about_ca_system_score_codex":0.00019340854,"about_ca_system_score_gemma":0.00036007442,"threshold_uncertainty_score":0.0029537678},"labels":[],"label_agreement":null},{"id":"W4387801726","doi":"10.1109/igarss52108.2023.10282538","title":"Natural Language Aided Remote Sensing Image Few-Shot Classification","year":2023,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Contextual image classification; Generalization; Embedding; Artificial intelligence; Feature (linguistics); Image (mathematics); Remote sensing; Domain (mathematical analysis); Deep learning; Feature extraction; Modal; Machine learning; Pattern recognition (psychology)","score_opus":0.02914390381003166,"score_gpt":0.27602158091158735,"score_spread":0.2468776771015557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387801726","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13006249,0.00094431493,0.8468423,0.0004396438,0.0002515541,0.0003687605,0.0020803686,0.009441119,0.00956944],"genre_scores_gemma":[0.53072476,0.00032935457,0.44811183,0.00040805916,0.00014532283,0.00033082056,0.0066441386,0.00028655125,0.013019094],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994653,0.00007488211,0.00002425943,0.00024122959,0.000111231275,0.000083032435],"domain_scores_gemma":[0.99941456,0.00015393834,0.000054191176,0.00015875262,0.00018077168,0.000037795042],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007336232,0.0009036284,0.00078132923,0.0013930391,0.00038157424,0.0007523607,0.0015348084,0.0010028381,0.0049152775],"category_scores_gemma":[0.0013889188,0.00017998286,0.0007956162,0.0007588591,0.00047034756,0.0013081036,0.0010114778,0.00094445655,0.002412742],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034909864,0.0005843222,0.0022032626,0.0003880335,0.00008884801,0.00040419176,0.00016949287,0.033040304,0.1256979,0.004427034,0.012456355,0.82019114],"study_design_scores_gemma":[0.000016612123,0.00018337816,0.0035704924,0.000037550413,0.000039392376,0.00032870888,0.00014375531,0.91438,0.06643358,0.0054735877,0.009350131,0.000042801552],"about_ca_topic_score_codex":0.0040961015,"about_ca_topic_score_gemma":0.009054614,"teacher_disagreement_score":0.0049152775,"about_ca_system_score_codex":0.00057968055,"about_ca_system_score_gemma":0.0007420446,"threshold_uncertainty_score":0.016443193},"labels":[],"label_agreement":null},{"id":"W4387802020","doi":"10.1109/igarss52108.2023.10282175","title":"An Iterative Method for Hyperspectral Pixel Unmixing Leveraging Latent Dirichlet Variational Autoencoder","year":2023,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Endmember; Hyperspectral imaging; Pixel; Pattern recognition (psychology); Autoencoder; Artificial intelligence; Computer science; Benchmark (surveying); Abundance estimation; Ground truth; Mathematics; Abundance (ecology); Deep learning; Geography; Biology","score_opus":0.039163829822087694,"score_gpt":0.3059089571069433,"score_spread":0.2667451272848556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387802020","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021488208,0.0000456166,0.997079,0.000034517387,0.00001094714,0.000016293638,0.000020866966,0.00029773408,0.00034619868],"genre_scores_gemma":[0.07169897,0.00009863321,0.9242691,0.00010336405,0.000033953023,0.00014649317,0.0002700176,0.0002649397,0.003114573],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993923,0.00014095232,0.000028204206,0.00016368495,0.00022259305,0.000052326337],"domain_scores_gemma":[0.99951506,0.00021987155,0.000047266625,0.00005531375,0.00013733831,0.00002502245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001242818,0.0008537588,0.00073291356,0.00058348366,0.00033264648,0.00060624327,0.0015528641,0.0011414248,0.0017805642],"category_scores_gemma":[0.0017614219,0.0007245941,0.0011426036,0.0005407641,0.0006439344,0.0010520883,0.0013598573,0.00175955,0.0008018288],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009633467,0.000078023855,0.00065752986,0.0001297929,0.00015019052,0.000071747316,0.00017655807,0.66108716,0.03153017,0.013417321,0.002407091,0.29019803],"study_design_scores_gemma":[0.000002970395,0.0000064068695,0.00004771092,0.0000025840116,0.0000033494875,0.000008854583,0.0000034249506,0.9961029,0.0022016047,0.0011210652,0.0004944569,0.0000047052176],"about_ca_topic_score_codex":0.006758574,"about_ca_topic_score_gemma":0.010396082,"teacher_disagreement_score":0.006758574,"about_ca_system_score_codex":0.00080178137,"about_ca_system_score_gemma":0.0012988863,"threshold_uncertainty_score":0.013438463},"labels":[],"label_agreement":null},{"id":"W4387828759","doi":"10.1109/igarss52108.2023.10283306","title":"Light-Weighted Explainable Dual Transformer Network for Hyperspectral Image Classification","year":2023,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Artificial intelligence; Transformer; Hyperspectral imaging; Feature extraction; Pattern recognition (psychology); Visualization; Computer vision; Engineering","score_opus":0.024552459124265746,"score_gpt":0.24518946790268825,"score_spread":0.22063700877842252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387828759","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07123289,0.0006891128,0.92244154,0.0005263954,0.000079861406,0.000048704555,0.00022576711,0.0012160009,0.0035396589],"genre_scores_gemma":[0.916803,0.0004041684,0.076250024,0.00024530917,0.00006711683,0.000066658315,0.0005394329,0.00007542752,0.0055488325],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999889,0.000022741502,0.000004519478,0.000031499523,0.00003087336,0.000021280375],"domain_scores_gemma":[0.99981683,0.00007198443,0.000027094695,0.000020901307,0.00004919972,0.000014014513],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003418102,0.0006806403,0.00040025666,0.0004114706,0.00019295745,0.0005147836,0.0011513666,0.0006841058,0.002147922],"category_scores_gemma":[0.00086213445,0.00020858078,0.00050355995,0.00046486888,0.00037797846,0.001107445,0.0007232384,0.0010160079,0.00032210653],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025551536,0.00019919104,0.0023122965,0.00012202413,0.0001265563,0.00018647547,0.00008043572,0.6097354,0.018924182,0.020215625,0.0054980763,0.34234416],"study_design_scores_gemma":[0.0000022511579,0.000011084276,0.00009701881,0.0000018652489,0.000006407236,0.000009854029,0.00000391426,0.99549145,0.0010640479,0.00308744,0.00022225794,0.0000023823927],"about_ca_topic_score_codex":0.0035316532,"about_ca_topic_score_gemma":0.005035304,"teacher_disagreement_score":0.0035316532,"about_ca_system_score_codex":0.00065976585,"about_ca_system_score_gemma":0.0004723746,"threshold_uncertainty_score":0.007185459},"labels":[],"label_agreement":null},{"id":"W4387986940","doi":"10.1109/jstars.2023.3328115","title":"A Dual Frequency Transformer Network for Hyperspectral Image Classification","year":2023,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Hyperspectral imaging; Computer science; Artificial intelligence; Pattern recognition (psychology); Frequency domain; Feature extraction; Block (permutation group theory); Convolutional neural network; Transformer; Pixel; Computer vision; Mathematics; Engineering","score_opus":0.03651208899921505,"score_gpt":0.24646342376746563,"score_spread":0.2099513347682506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387986940","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06012058,0.0008014758,0.9305804,0.0002716328,0.00013949028,0.000096153286,0.00037550266,0.0024577207,0.0051571066],"genre_scores_gemma":[0.7503019,0.00065584085,0.2334794,0.0004040935,0.000104996696,0.00015426172,0.0019634822,0.00012294712,0.012813046],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998098,0.00002585726,0.000008579545,0.000057753947,0.000059200498,0.00003879299],"domain_scores_gemma":[0.99984896,0.0000375753,0.000018266794,0.00002012504,0.00005980536,0.000015267224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030771433,0.0007097093,0.00048914744,0.0005655616,0.00023235471,0.00044180808,0.0010250576,0.000553257,0.001949674],"category_scores_gemma":[0.00066094525,0.00022006224,0.00046294634,0.00051482534,0.00026017107,0.0009094415,0.0007140519,0.0007351695,0.00075160677],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037339432,0.00028717596,0.0025483018,0.00010861733,0.000100655794,0.00018657034,0.00006286689,0.16498306,0.035657827,0.006448043,0.010755243,0.77848834],"study_design_scores_gemma":[0.000007552391,0.00003455971,0.00031737058,0.0000045220168,0.000014611247,0.00004564911,0.000012596811,0.9920586,0.004937085,0.0016423598,0.0009186081,0.000006443929],"about_ca_topic_score_codex":0.005438762,"about_ca_topic_score_gemma":0.0075944215,"teacher_disagreement_score":0.005438762,"about_ca_system_score_codex":0.000574987,"about_ca_system_score_gemma":0.0006152035,"threshold_uncertainty_score":0.0108142495},"labels":[],"label_agreement":null},{"id":"W4388023413","doi":"10.1080/2150704x.2023.2273244","title":"Change Detection in Synthetic Aperture Radar Images based on a Spatial Pyramid Pooling Attention Network (SPPANet)","year":2023,"lang":"en","type":"article","venue":"Remote Sensing Letters","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Pooling; Computer science; Pyramid (geometry); Synthetic aperture radar; Artificial intelligence; Change detection; Cluster analysis; Radar imaging; Pattern recognition (psychology); Remote sensing; Computer vision; Data mining; Radar; Geography; Mathematics; Telecommunications","score_opus":0.01600741610846116,"score_gpt":0.21389810505464193,"score_spread":0.19789068894618078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388023413","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30434945,0.0006394118,0.6853987,0.0004623201,0.00022374361,0.00019838795,0.0003954769,0.0035429315,0.004789549],"genre_scores_gemma":[0.8568586,0.00028589688,0.13627854,0.00031518695,0.00009797125,0.0000990249,0.0012648086,0.00008191357,0.004718129],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996556,0.00004149536,0.00001399321,0.00013099283,0.00009017458,0.00006773884],"domain_scores_gemma":[0.9997261,0.00006585539,0.000034300847,0.000033036766,0.000113395545,0.000027269956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007279519,0.0007895356,0.0006131963,0.0010602014,0.00034952356,0.0005114458,0.00093569956,0.000529793,0.001129523],"category_scores_gemma":[0.0010659249,0.0002847527,0.0006545447,0.00060857425,0.00039135414,0.00091387244,0.0008903866,0.0007214483,0.0003175321],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055489753,0.00038814492,0.008090314,0.000113721435,0.00022624277,0.0004101078,0.00013405079,0.13807103,0.072374165,0.0020625922,0.0061761974,0.77139854],"study_design_scores_gemma":[0.000009453626,0.00009446917,0.0022865431,0.0000045556117,0.000031051775,0.000083089995,0.00001637105,0.9861021,0.0100527685,0.0006598959,0.0006500962,0.000009606585],"about_ca_topic_score_codex":0.008646087,"about_ca_topic_score_gemma":0.010415679,"teacher_disagreement_score":0.008646087,"about_ca_system_score_codex":0.0007253848,"about_ca_system_score_gemma":0.0006099386,"threshold_uncertainty_score":0.01719153},"labels":[],"label_agreement":null},{"id":"W4388024024","doi":"10.18280/ts.400512","title":"Multiscale Feature Fusion for Hyperspectral Image Classification Using Hybrid 3D-2D Depthwise Separable Convolution Networks","year":2023,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Hyperspectral imaging; Artificial intelligence; Pattern recognition (psychology); Convolution (computer science); Separable space; Feature (linguistics); Fusion; Image (mathematics); Computer science; Image fusion; Mathematics; Artificial neural network","score_opus":0.030821730835498943,"score_gpt":0.25894170041814135,"score_spread":0.2281199695826424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388024024","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15717284,0.0007201162,0.8359636,0.00023822195,0.000078166115,0.00007482252,0.00041348278,0.002398104,0.0029405884],"genre_scores_gemma":[0.7601166,0.00036196786,0.23329987,0.00016779553,0.000047995338,0.00011031924,0.0016829353,0.00009283674,0.0041197427],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9997328,0.000028619008,0.000012539306,0.000070731745,0.000107527056,0.00004780785],"domain_scores_gemma":[0.9997873,0.00004763769,0.000029403414,0.000033415363,0.000085236716,0.000017082464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005368507,0.0009094281,0.0007028275,0.00086025003,0.00024097809,0.0005315079,0.0007420506,0.0005138901,0.0013355929],"category_scores_gemma":[0.00086792314,0.00024690497,0.0008613729,0.0006623451,0.0002715243,0.0009607624,0.0010703987,0.00069891143,0.00053207634],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003637899,0.0002391323,0.004423533,0.000094824005,0.00016786547,0.0001758279,0.00010949445,0.24411175,0.06290251,0.0032827405,0.0039597163,0.68016887],"study_design_scores_gemma":[0.0000037289728,0.000031087806,0.00088379346,0.0000038351923,0.000013410465,0.000027840126,0.000012622439,0.9917162,0.005888454,0.0007779708,0.00063407904,0.0000070171686],"about_ca_topic_score_codex":0.005536236,"about_ca_topic_score_gemma":0.0069710207,"teacher_disagreement_score":0.005536236,"about_ca_system_score_codex":0.00056764967,"about_ca_system_score_gemma":0.000580716,"threshold_uncertainty_score":0.011008024},"labels":[],"label_agreement":null},{"id":"W4388486813","doi":"10.26434/chemrxiv-2023-cljn3","title":"Keeping an “eye” on the experiment: computer vision for real-time monitoring and control","year":2023,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Pfizer","keywords":"Computer science; Automation; Software; Visualization; Data acquisition; Workflow; Instrument control; Data collection; Real-time computing; Artificial intelligence; Computer hardware; Engineering","score_opus":0.03987122275068952,"score_gpt":0.2916138203284568,"score_spread":0.2517425975777673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388486813","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031528198,0.00053736306,0.99468565,0.00021523864,0.00005022715,0.000016660571,0.000015217132,0.00048083288,0.0008459617],"genre_scores_gemma":[0.3899237,0.0018148137,0.60349256,0.0005217274,0.00014530976,0.00021154043,0.00014801514,0.0002840158,0.0034584291],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989768,0.00023509638,0.0000375252,0.00033039457,0.0003493408,0.000070852504],"domain_scores_gemma":[0.9991086,0.00041890392,0.000111157446,0.00014971856,0.00017020159,0.000041455336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015271752,0.0006437595,0.0006211024,0.0005717722,0.0002782126,0.0013299254,0.0012089412,0.0011865688,0.00079735543],"category_scores_gemma":[0.0025895084,0.00032852884,0.00072534854,0.0004912721,0.0016373207,0.0012758055,0.00077618426,0.0017784619,0.00036784372],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020599154,0.00017157468,0.0010849021,0.0003432541,0.000121454075,0.00013755792,0.0002108785,0.4474806,0.07773959,0.04781303,0.0058728564,0.41881838],"study_design_scores_gemma":[0.000008665241,0.000055856184,0.0003773019,0.0000191729,0.000011233832,0.000041413656,0.000011727638,0.97094023,0.009601523,0.014504735,0.004402869,0.000025324329],"about_ca_topic_score_codex":0.0041162637,"about_ca_topic_score_gemma":0.0022820972,"teacher_disagreement_score":0.0041162637,"about_ca_system_score_codex":0.0010489518,"about_ca_system_score_gemma":0.0008015404,"threshold_uncertainty_score":0.008184612},"labels":[],"label_agreement":null},{"id":"W4388756939","doi":"10.1109/jstars.2023.3333959","title":"Concatenated Deep-Learning Framework for Multitask Change Detection of Optical and SAR Images","year":2023,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":82,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Hubei Key Laboratory of Intelligent Geo-Information Processing; Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China; Ministry of Natural Resources","keywords":"Computer science; Artificial intelligence; Deep learning; Synthetic aperture radar; Change detection; Computer vision; Remote sensing; Pattern recognition (psychology); Geology","score_opus":0.038211917375120155,"score_gpt":0.25366016435414396,"score_spread":0.21544824697902382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388756939","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029744444,0.00090338493,0.9610539,0.00038833654,0.00013839014,0.0000871204,0.0005473008,0.004731625,0.0024054623],"genre_scores_gemma":[0.66623026,0.00057920406,0.31642807,0.0005298761,0.00017877274,0.00022253167,0.004272604,0.000407057,0.011151548],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99961346,0.000053408374,0.000015002702,0.00015345223,0.00008902147,0.00007572329],"domain_scores_gemma":[0.9997309,0.00006356032,0.000037848058,0.00006058748,0.00007180143,0.000035269186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069663784,0.0012681325,0.00085580896,0.000736829,0.00031494888,0.00061924197,0.0020750368,0.0010090495,0.0022061153],"category_scores_gemma":[0.0010464047,0.0005745553,0.0009742113,0.0008003951,0.00053753273,0.0013145643,0.0014153792,0.0021251491,0.0008668825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026180205,0.00023445416,0.002405246,0.00011343097,0.00019979879,0.00021847506,0.00008534997,0.62171537,0.013380035,0.0071421103,0.008529656,0.34571427],"study_design_scores_gemma":[0.0000046077926,0.00002017694,0.00021466742,0.0000027537278,0.000009296244,0.000021131624,0.000004207536,0.99569315,0.0014153561,0.0018949494,0.000715219,0.0000044903177],"about_ca_topic_score_codex":0.009830079,"about_ca_topic_score_gemma":0.014869522,"teacher_disagreement_score":0.009830079,"about_ca_system_score_codex":0.0010251747,"about_ca_system_score_gemma":0.0011657864,"threshold_uncertainty_score":0.019545734},"labels":[],"label_agreement":null},{"id":"W4389004940","doi":"10.23977/jeis.2023.080602","title":"A Deep Neural Network for Image Segmentation","year":2023,"lang":"en","type":"article","venue":"Journal of Electronics and Information Science","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Key Research and Development Program of China","keywords":"Computer science; Annotation; Artificial intelligence; Metric (unit); Convolutional neural network; Segmentation; Quality (philosophy); Convolution (computer science); Artificial neural network; Automatic image annotation; Data mining; Image (mathematics); Architecture; Pattern recognition (psychology); Machine learning; Image retrieval","score_opus":0.010490565257116016,"score_gpt":0.2539490747978226,"score_spread":0.24345850954070658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389004940","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027449599,0.001394418,0.9571252,0.00044541384,0.00019499502,0.000082344726,0.00073158223,0.0067504128,0.0058259885],"genre_scores_gemma":[0.39949954,0.0010376864,0.57358736,0.0004778148,0.000113791444,0.00020609723,0.0028335848,0.0003756581,0.021868527],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99975723,0.000028650895,0.0000116118545,0.00009311493,0.00006771833,0.000041710704],"domain_scores_gemma":[0.99982196,0.000039831764,0.000018384897,0.000030298392,0.00007638103,0.0000132385585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039692412,0.00085347984,0.0004806185,0.0006409544,0.0003647015,0.0006316476,0.0011745151,0.00105749,0.0034932469],"category_scores_gemma":[0.0008147621,0.0004222508,0.000546018,0.0008808496,0.0003198436,0.00087987864,0.00065610115,0.0012814282,0.0015870285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023753066,0.00012282391,0.0009857012,0.00012260026,0.00009837389,0.000111868394,0.000057237787,0.27062398,0.036857635,0.0063405326,0.011540864,0.6729009],"study_design_scores_gemma":[0.0000044810668,0.000020393403,0.0002579056,0.000009094871,0.000010598489,0.000022025326,0.000005709746,0.9892669,0.00628588,0.0020044749,0.0021050214,0.000007532101],"about_ca_topic_score_codex":0.013712669,"about_ca_topic_score_gemma":0.017129986,"teacher_disagreement_score":0.013712669,"about_ca_system_score_codex":0.0011473376,"about_ca_system_score_gemma":0.0009837253,"threshold_uncertainty_score":0.027265728},"labels":[],"label_agreement":null},{"id":"W4389206062","doi":"10.22215/etd/2023-15793","title":"Self-supervised Pretraining of Vision Transformers for Earth Observation","year":2023,"lang":"en","type":"dissertation","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Artificial intelligence; Transformer; Modal; Machine learning; Flexibility (engineering); Engineering; Mathematics","score_opus":0.028926438100434597,"score_gpt":0.26931680844697026,"score_spread":0.24039037034653565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389206062","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10863198,0.00039431002,0.88130444,0.00038482336,0.00010756104,0.000090596644,0.00046728534,0.0037274319,0.0048915613],"genre_scores_gemma":[0.81941247,0.00024046596,0.17033459,0.00031822312,0.00006284516,0.00012436604,0.002171939,0.0002985509,0.0070366124],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99971205,0.00005979911,0.000010671771,0.0001360926,0.000043891047,0.000037506754],"domain_scores_gemma":[0.9992913,0.0002932551,0.00006853848,0.00015030666,0.00015179093,0.000044824064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007481485,0.0008601279,0.00048704282,0.0004767985,0.00027161077,0.00069187046,0.0011870561,0.0007386193,0.002510083],"category_scores_gemma":[0.002562479,0.0003912564,0.00083018106,0.0004488223,0.0006395183,0.0015719623,0.0010514415,0.0021856949,0.0010916766],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024197143,0.00025192957,0.006537448,0.0001612084,0.00015397598,0.00008625046,0.00018571224,0.372607,0.021947542,0.0177921,0.010801436,0.56923336],"study_design_scores_gemma":[0.000005587718,0.000053501877,0.000722675,0.000011304887,0.00001056422,0.000019072824,0.000021478661,0.9882712,0.004544315,0.0052962243,0.0010379234,0.000006125214],"about_ca_topic_score_codex":0.004352031,"about_ca_topic_score_gemma":0.009892537,"teacher_disagreement_score":0.004352031,"about_ca_system_score_codex":0.0007694583,"about_ca_system_score_gemma":0.00089241285,"threshold_uncertainty_score":0.008653402},"labels":[],"label_agreement":null},{"id":"W4389657266","doi":"10.5194/isprs-archives-xlviii-1-w2-2023-187-2023","title":"LAND COVERAGE ANALYSIS OF PAKISTAN USING SATELLITE IMAGERY","year":2023,"lang":"en","type":"article","venue":"˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Satellite imagery; Geography; Environmental resource management; Remote sensing; Vegetation (pathology); Segmentation; Land use; Satellite; Climate change; Computer science; Environmental planning; Environmental science; Artificial intelligence; Civil engineering","score_opus":0.021849634708544577,"score_gpt":0.27096842487386696,"score_spread":0.2491187901653224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389657266","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4567978,0.000680689,0.0019908485,0.0006241428,0.00016303307,0.00016342751,0.52826625,0.0017070791,0.009606635],"genre_scores_gemma":[0.33761734,0.00039333597,0.003229729,0.000093974864,0.000028976774,0.000079362864,0.6565186,0.000046560213,0.0019921325],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99973327,0.0000203426,0.000020188374,0.00007350327,0.00007949562,0.00007321964],"domain_scores_gemma":[0.99966455,0.000045214223,0.000031386644,0.000064399304,0.00014825471,0.00004625812],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019178099,0.00074127555,0.00033766075,0.0021390996,0.0004805942,0.0005929772,0.00067343115,0.0005334897,0.003015957],"category_scores_gemma":[0.0005713048,0.00013009085,0.0004735782,0.002596996,0.00034592004,0.0005036125,0.00059330853,0.0005402116,0.001972592],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012721745,0.0010862739,0.2537657,0.0015943402,0.00047244664,0.002541131,0.0007399399,0.03242823,0.009452137,0.0021417968,0.4548329,0.23967296],"study_design_scores_gemma":[0.00022129065,0.00030237102,0.6864216,0.0003613761,0.0001747039,0.0019283276,0.0045349873,0.10008653,0.016350608,0.00193543,0.18751524,0.0001674982],"about_ca_topic_score_codex":0.08344794,"about_ca_topic_score_gemma":0.107324794,"teacher_disagreement_score":0.08344794,"about_ca_system_score_codex":0.0009828897,"about_ca_system_score_gemma":0.0008156597,"threshold_uncertainty_score":0.16592443},"labels":[],"label_agreement":null},{"id":"W4389672043","doi":"10.1080/22797254.2023.2293163","title":"A review of research on remote sensing images shadow detection and application to building extraction","year":2023,"lang":"en","type":"review","venue":"European Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Key Laboratory of Degraded and Unused Land Consolidation Engineering; National Natural Science Foundation of China; Ministry of Natural Resources","keywords":"Shadow (psychology); Computer science; Remote sensing; Identification (biology); Building model; Feature extraction; Field (mathematics); Artificial intelligence; Computer vision; Geography; Simulation","score_opus":0.10200786687488067,"score_gpt":0.3916216849140937,"score_spread":0.28961381803921304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389672043","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00041938652,0.99345183,0.0027104977,0.0003841692,0.0003817824,0.000018257138,0.0000910975,0.000046201905,0.0024967464],"genre_scores_gemma":[0.0022142427,0.9931564,0.0028870427,0.000220976,0.00035780517,0.000020067002,0.00017053244,0.000014269045,0.00095869583],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994524,0.00007596082,0.00008265838,0.00013200345,0.00022084209,0.000036066886],"domain_scores_gemma":[0.9977208,0.001254146,0.00018227122,0.00007017719,0.00071907334,0.000053619748],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012647555,0.0012168671,0.0013248854,0.004592974,0.00033820956,0.0014728304,0.0010303367,0.0012478353,0.004208692],"category_scores_gemma":[0.0028479616,0.0005989156,0.0011106905,0.006435138,0.00056239864,0.0022664724,0.00049371907,0.0011759424,0.0027459385],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050120023,0.00006155234,0.000488998,0.018989155,0.00011965233,0.00009532331,0.00008358816,0.00090989715,0.0019804235,0.0034266994,0.02229782,0.9514967],"study_design_scores_gemma":[0.00001220285,0.00013600968,0.0037086261,0.009686961,0.00035747694,0.0012739007,0.00018085321,0.0011901997,0.002331547,0.0033233052,0.97772217,0.000076697936],"about_ca_topic_score_codex":0.0027599984,"about_ca_topic_score_gemma":0.0026768986,"teacher_disagreement_score":0.004592974,"about_ca_system_score_codex":0.0006624809,"about_ca_system_score_gemma":0.0014454776,"threshold_uncertainty_score":0.014079452},"labels":[],"label_agreement":null},{"id":"W4389686059","doi":"10.3390/rs15245717","title":"MSSFF: Advancing Hyperspectral Classification through Higher-Accuracy Multistage Spectral–Spatial Feature Fusion","year":2023,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"National Natural Science Foundation of China","keywords":"Hyperspectral imaging; Computer science; Segmentation; Artificial intelligence; Feature (linguistics); Encoder; Spatial contextual awareness; Pattern recognition (psychology); Fusion; Remote sensing; Spatial analysis; Geography","score_opus":0.025445097538295044,"score_gpt":0.2692713332501216,"score_spread":0.24382623571182654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389686059","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0136523815,0.00014084498,0.98363924,0.00008322313,0.000025232515,0.000030331736,0.00010662892,0.0012911713,0.0010310464],"genre_scores_gemma":[0.37931672,0.0002148565,0.616072,0.0002022846,0.0000630832,0.000087881206,0.001108406,0.0002743339,0.0026604892],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99961865,0.00004993659,0.000017772696,0.000095587326,0.000156699,0.00006130601],"domain_scores_gemma":[0.9996039,0.00011366849,0.00004271704,0.00007945017,0.00013391774,0.000026348698],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008177438,0.0009622249,0.00066584477,0.0011205807,0.00041151297,0.0009017882,0.0012427428,0.0008715475,0.002194922],"category_scores_gemma":[0.0014607148,0.0002905135,0.0010610421,0.0008303695,0.00052311807,0.002214072,0.0015602049,0.001128167,0.0008762363],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023261468,0.00021347051,0.0026148644,0.00014188098,0.00011864146,0.00015420963,0.0002202133,0.2708959,0.06474195,0.015155495,0.005238919,0.64027184],"study_design_scores_gemma":[0.0000035566773,0.000025754192,0.00049035274,0.000006258645,0.000011001846,0.000034974863,0.000020769046,0.9841009,0.0076672398,0.006044245,0.0015845974,0.000010247398],"about_ca_topic_score_codex":0.006319533,"about_ca_topic_score_gemma":0.008628015,"teacher_disagreement_score":0.006319533,"about_ca_system_score_codex":0.0007071597,"about_ca_system_score_gemma":0.0008178817,"threshold_uncertainty_score":0.012565494},"labels":[],"label_agreement":null},{"id":"W4389794452","doi":"10.1007/s11760-023-02882-8","title":"Residential building type classification from street-view imagery with convolutional neural networks","year":2023,"lang":"en","type":"article","venue":"Signal Image and Video Processing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Statistics Canada","funders":"","keywords":"Convolutional neural network; Computer science; Apartment; Task (project management); Artificial intelligence; Contextual image classification; Machine learning; Image (mathematics)","score_opus":0.023313100239074756,"score_gpt":0.25716716957141456,"score_spread":0.2338540693323398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389794452","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7479969,0.0018073778,0.22769147,0.0003175632,0.00026083164,0.00016530494,0.006937144,0.0048648417,0.009958597],"genre_scores_gemma":[0.9369203,0.0005039925,0.04689464,0.00008018727,0.00008168347,0.00005423108,0.009010569,0.00008431963,0.0063701333],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99984837,0.000011633819,0.0000061394385,0.00005057671,0.00003077569,0.00005240471],"domain_scores_gemma":[0.99986696,0.00002575807,0.000017651155,0.000024523173,0.00005200808,0.00001317203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019482651,0.0007682329,0.00049831095,0.00153579,0.00019914212,0.00044988864,0.0006552578,0.00049520045,0.0018072409],"category_scores_gemma":[0.00037048722,0.00025700056,0.0008893306,0.0010747269,0.0001782946,0.00044705346,0.0004927976,0.00052241475,0.001559821],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005519858,0.0006452931,0.031162398,0.0001784443,0.0002983678,0.00028674497,0.00008153501,0.090958185,0.04480477,0.00094194885,0.013352505,0.81673783],"study_design_scores_gemma":[0.000009039485,0.000048462203,0.019966694,0.000023602517,0.00006876645,0.000078676705,0.000064916916,0.9684354,0.008955024,0.0006852557,0.0016481377,0.00001599532],"about_ca_topic_score_codex":0.016209813,"about_ca_topic_score_gemma":0.028942592,"teacher_disagreement_score":0.016209813,"about_ca_system_score_codex":0.000426856,"about_ca_system_score_gemma":0.00038799192,"threshold_uncertainty_score":0.032230914},"labels":[],"label_agreement":null},{"id":"W4390048238","doi":"10.1007/s00107-023-02027-1","title":"Information fusion technology for terahertz spectra and hyperspectral imaging in wood species identification","year":2023,"lang":"en","type":"article","venue":"European Journal of Wood and Wood Products","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Hyperspectral imaging; Artificial intelligence; Pattern recognition (psychology); Full spectral imaging; Remote sensing; Computer science; Random forest; Spatial analysis; Computer vision; Geography","score_opus":0.011978807533725164,"score_gpt":0.20714499003009457,"score_spread":0.1951661824963694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390048238","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11301059,0.004430658,0.87291914,0.0007061675,0.00025376282,0.00007090002,0.00044087574,0.0010321556,0.0071357153],"genre_scores_gemma":[0.6633613,0.0029013318,0.32665327,0.00031045734,0.00013667115,0.000108807464,0.0008021911,0.00008667569,0.005639301],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99956673,0.00006391969,0.000028149308,0.00008766381,0.00020146808,0.000052064657],"domain_scores_gemma":[0.9997346,0.00007102713,0.000045126322,0.000040901265,0.00009742602,0.000010957553],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053423207,0.00036610392,0.00050960685,0.0013328221,0.0003810659,0.0007763355,0.00048168577,0.0007074353,0.002111811],"category_scores_gemma":[0.0006286914,0.00025096536,0.00064462,0.0016981266,0.00033307486,0.0019459354,0.00090169796,0.00069396413,0.00090828113],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003487533,0.00017066828,0.0023401957,0.0003455527,0.00012063072,0.00011989761,0.00020185004,0.019977096,0.41864103,0.01028473,0.0025698135,0.54487985],"study_design_scores_gemma":[0.000025333587,0.00029352534,0.010891008,0.00006221756,0.00022721957,0.0006589505,0.00023062283,0.5381433,0.41944167,0.01692315,0.012977623,0.00012543422],"about_ca_topic_score_codex":0.0006012838,"about_ca_topic_score_gemma":0.00086792145,"teacher_disagreement_score":0.002111811,"about_ca_system_score_codex":0.00034802564,"about_ca_system_score_gemma":0.00034667342,"threshold_uncertainty_score":0.0070647597},"labels":[],"label_agreement":null},{"id":"W4390061979","doi":"10.3390/rs16010051","title":"Enhancing Object Detection in Remote Sensing: A Hybrid YOLOv7 and Transformer Approach with Automatic Model Selection","year":2023,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Object detection; Artificial intelligence; Field (mathematics); Bridging (networking); Data mining; Process (computing); Remote sensing; Computer vision; Real-time computing; Pattern recognition (psychology); Computer security","score_opus":0.014847908829542756,"score_gpt":0.21931308590368945,"score_spread":0.2044651770741467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390061979","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015345164,0.000093653114,0.98299015,0.000050031136,0.000012668479,0.000027464703,0.00001838783,0.0007581613,0.00070419116],"genre_scores_gemma":[0.4812619,0.00025879938,0.513424,0.0002492121,0.000056492467,0.00009238291,0.0003102631,0.0003549808,0.0039919917],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99941707,0.000108150154,0.000023748013,0.00012531239,0.0002457802,0.000079936035],"domain_scores_gemma":[0.99956256,0.00015916895,0.000046330482,0.000070939364,0.00012801825,0.000032957727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000847223,0.0007512029,0.0009725258,0.0011352911,0.0002795143,0.0010633466,0.0015211276,0.0007834425,0.0017906807],"category_scores_gemma":[0.0010948475,0.00045429147,0.0011221162,0.00064471125,0.0004222166,0.0009932237,0.0013435365,0.00068902556,0.0009855129],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036333987,0.00028787702,0.0027225916,0.0001424744,0.00019749663,0.0002086135,0.00012543154,0.19672315,0.10761353,0.008843241,0.0020291288,0.68074316],"study_design_scores_gemma":[0.0000085337715,0.000054263022,0.00033040642,0.0000031429463,0.000019198316,0.000069794216,0.000013850992,0.9878533,0.009404915,0.0015003405,0.0007329306,0.000009322203],"about_ca_topic_score_codex":0.0026934145,"about_ca_topic_score_gemma":0.0035190582,"teacher_disagreement_score":0.0026934145,"about_ca_system_score_codex":0.00044361516,"about_ca_system_score_gemma":0.0006572865,"threshold_uncertainty_score":0.005990386},"labels":[],"label_agreement":null},{"id":"W4390116550","doi":"10.1016/j.patrec.2023.12.011","title":"Special section: Best papers of the international conference on pattern recognition and artificial intelligence (ICPRAI) 2022","year":2023,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Section (typography); Artificial intelligence; Special section; Computer science; Pattern recognition (psychology); Engineering; Engineering physics","score_opus":0.09773453538610027,"score_gpt":0.2559290235569067,"score_spread":0.15819448817080645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390116550","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00079070334,0.023512498,0.0010615072,0.020173745,0.90933716,0.00023466842,0.0012244317,0.00030878308,0.04335643],"genre_scores_gemma":[0.004593738,0.023176393,0.0010222525,0.0083858,0.647724,0.00019650151,0.0023002687,0.00051195995,0.31208906],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99849045,0.00018295,0.0002207695,0.00026637327,0.0006459233,0.00019347933],"domain_scores_gemma":[0.9902576,0.0012907098,0.0007193817,0.00046513727,0.0047781006,0.002489088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021668659,0.0024069336,0.0030599367,0.005505824,0.001671841,0.00669954,0.0021091276,0.0046204566,0.13735285],"category_scores_gemma":[0.0049303668,0.00062952907,0.0016129791,0.0031232433,0.0006930379,0.0028308239,0.0020123818,0.0027832878,0.10606054],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012484053,0.00003904103,0.00013777927,0.00026055504,0.000017334054,0.00008492012,0.000005497889,0.000043249896,0.00026288125,0.00019467663,0.97675747,0.022071768],"study_design_scores_gemma":[0.00002931392,0.000082575716,0.0012825273,0.00021917802,0.000030084759,0.00021033366,0.000020076484,0.00019918302,0.00034100318,0.0005404121,0.9970305,0.000014704234],"about_ca_topic_score_codex":0.0010566743,"about_ca_topic_score_gemma":0.0020680232,"teacher_disagreement_score":0.13735285,"about_ca_system_score_codex":0.0012386782,"about_ca_system_score_gemma":0.0015966963,"threshold_uncertainty_score":0.45949107},"labels":[],"label_agreement":null},{"id":"W4390446410","doi":"10.1016/j.infrared.2023.105039","title":"Multimanifold Bistructured Low Rank Representation of hyperspectral images","year":2023,"lang":"en","type":"article","venue":"Infrared Physics & Technology","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Hyperspectral imaging; Computer science; Noise (video); Noise reduction; Pattern recognition (psychology); Algorithm; Artificial intelligence; Representation (politics); Gaussian noise; Rank (graph theory); Gaussian; Graph; Manifold (fluid mechanics); Image (mathematics); Mathematics; Theoretical computer science","score_opus":0.013187699378367914,"score_gpt":0.24789923840010689,"score_spread":0.23471153902173897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390446410","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29308274,0.00028080522,0.6979998,0.00060520804,0.00013360966,0.000041865063,0.0008298898,0.0008897734,0.0061363433],"genre_scores_gemma":[0.83785677,0.0003248774,0.1508561,0.00019912049,0.00009312292,0.000045123947,0.0012113863,0.0001296159,0.009283886],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999032,0.000018696714,0.000004608585,0.000017640315,0.00003667145,0.000019145571],"domain_scores_gemma":[0.9998472,0.000025033603,0.00003307153,0.000044144166,0.0000359234,0.000014721044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001284153,0.00044219213,0.00021809978,0.00053416943,0.00013062885,0.0005179395,0.00023589864,0.0003709854,0.0039843796],"category_scores_gemma":[0.00045283162,0.00009793994,0.00026344572,0.0004775656,0.00022989785,0.0005273226,0.00036816963,0.00047612816,0.00085768005],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00051092333,0.00021699398,0.0018231942,0.0001904593,0.000056832258,0.00028834125,0.0001442781,0.109665275,0.4646382,0.026184408,0.008954854,0.38732624],"study_design_scores_gemma":[0.0000071649856,0.00010288324,0.0031262366,0.000010920392,0.0000132816085,0.00022944457,0.000058113455,0.94834024,0.040524982,0.0053338995,0.0022308822,0.000022028327],"about_ca_topic_score_codex":0.0006718087,"about_ca_topic_score_gemma":0.00081856747,"teacher_disagreement_score":0.0039843796,"about_ca_system_score_codex":0.00015740324,"about_ca_system_score_gemma":0.00023028352,"threshold_uncertainty_score":0.013329089},"labels":[],"label_agreement":null},{"id":"W4390871472","doi":"10.1109/lgrs.2024.3354175","title":"Spatial-Gated Multilayer Perceptron for Land Use and Land Cover Mapping","year":2024,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Hyperspectral imaging; Convolutional neural network; Artificial intelligence; Land cover; Pattern recognition (psychology); Perceptron; Benchmark (surveying); Deep learning; Feature extraction; Remote sensing; Artificial neural network; Machine learning; Land use; Cartography","score_opus":0.02435751242022765,"score_gpt":0.23147013312488177,"score_spread":0.2071126207046541,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390871472","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048949532,0.0036792648,0.9262825,0.00068013323,0.00028718033,0.000086046864,0.0015064203,0.012284912,0.006244016],"genre_scores_gemma":[0.6758461,0.0018140195,0.304834,0.0003974905,0.00013601936,0.00015593805,0.0042730793,0.00036095185,0.012182434],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99981135,0.00003178034,0.00001136312,0.000057652727,0.0000572835,0.0000306278],"domain_scores_gemma":[0.99982506,0.000055572422,0.00002378668,0.000030499157,0.000052739848,0.000012390698],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000478401,0.00066044874,0.00044859305,0.00049521483,0.00016908557,0.00044502772,0.0008439585,0.0005163914,0.0030431426],"category_scores_gemma":[0.0010615652,0.00027862217,0.0005446593,0.0009112279,0.00025051425,0.0009014029,0.0006067993,0.0010039456,0.0010557666],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000149005,0.0001246811,0.0024094484,0.0001798115,0.00011842478,0.00010312332,0.00003970673,0.43670118,0.009794534,0.0064834985,0.0129435705,0.530953],"study_design_scores_gemma":[0.0000037456039,0.000014513592,0.00045377456,0.000007705626,0.000009489134,0.000012696315,0.000004866695,0.99291444,0.002034656,0.002755063,0.0017834327,0.0000055412156],"about_ca_topic_score_codex":0.012320655,"about_ca_topic_score_gemma":0.013996038,"teacher_disagreement_score":0.012320655,"about_ca_system_score_codex":0.0007050151,"about_ca_system_score_gemma":0.0009227818,"threshold_uncertainty_score":0.024497926},"labels":[],"label_agreement":null},{"id":"W4390873228","doi":"10.1109/tgrs.2024.3354737","title":"A Novel Weighted Ensemble Transferred U-Net Based Model (WETUM) for Postearthquake Building Damage Assessment From UAV Data: A Comparison of Deep Learning- and Machine Learning-Based Approaches","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Science Foundation of Zhejiang Province","keywords":"Computer science; Random forest; Generalizability theory; Deep learning; Artificial intelligence; Classifier (UML); Machine learning; Pattern recognition (psychology); Remote sensing; Data mining; Mathematics; Geology; Statistics","score_opus":0.06766531579218184,"score_gpt":0.2939087224727517,"score_spread":0.22624340668056986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390873228","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15757735,0.0014722405,0.83258635,0.0007022923,0.00018740515,0.00008812332,0.00031072748,0.0010141806,0.0060612876],"genre_scores_gemma":[0.9475251,0.0004548124,0.045950264,0.00022385741,0.000049076843,0.00012415786,0.00035914104,0.000044108736,0.005269643],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9998796,0.000022342307,0.000007116419,0.000036664882,0.000026977505,0.000027272115],"domain_scores_gemma":[0.99978215,0.00008185157,0.00003224777,0.000012445305,0.000073452065,0.00001781314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004581268,0.00092060695,0.00061621936,0.0005028762,0.00029640694,0.0007566646,0.0016437075,0.001014011,0.0012816907],"category_scores_gemma":[0.000908552,0.0003152926,0.000669353,0.00037697374,0.00036288486,0.001046611,0.00076765404,0.0008461939,0.00023867436],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005339305,0.00003700799,0.001556398,0.00002438928,0.00003646149,0.000052971278,0.00002048111,0.9638186,0.0007423135,0.0009145719,0.00045571476,0.032287702],"study_design_scores_gemma":[0.0000010787132,0.000008755191,0.00008358673,0.000002170706,0.000003073446,0.000003592095,0.0000022282609,0.99953926,0.000123062,0.00017103857,0.00006076368,0.000001370628],"about_ca_topic_score_codex":0.011569552,"about_ca_topic_score_gemma":0.012422411,"teacher_disagreement_score":0.011569552,"about_ca_system_score_codex":0.00067549257,"about_ca_system_score_gemma":0.0006785835,"threshold_uncertainty_score":0.023004413},"labels":[],"label_agreement":null},{"id":"W4390910924","doi":"10.1080/07038992.2023.2298806","title":"Dense Connected Edge Feature Enhancement Network for Building Edge Detection from High Resolution Remote Sensing Imagery","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Enhanced Data Rates for GSM Evolution; Computer science; Edge detection; Convolutional neural network; Feature (linguistics); Artificial intelligence; Representation (politics); Edge enhancement; Aerial image; Deep learning; Feature extraction; Remote sensing; Computer vision; Pattern recognition (psychology); Image (mathematics); Image processing; Geography","score_opus":0.01367416442448294,"score_gpt":0.22244376763926774,"score_spread":0.2087696032147848,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390910924","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.110871635,0.0006271671,0.88122755,0.00023502557,0.00007412205,0.000114030045,0.00056012085,0.0035035592,0.0027867926],"genre_scores_gemma":[0.61279845,0.0005505912,0.37627807,0.00032275592,0.00006808997,0.00015030858,0.0028423697,0.00020502099,0.006784376],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99981815,0.00002147773,0.00000759909,0.00006318125,0.000057140987,0.000032540884],"domain_scores_gemma":[0.99978966,0.000063675034,0.00003240478,0.000034550943,0.000066382454,0.000013381002],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033086105,0.000821636,0.0004785214,0.0009993094,0.00020065412,0.00040084374,0.0009403814,0.0006393791,0.001370719],"category_scores_gemma":[0.00088916364,0.00035196298,0.00061176927,0.00068334833,0.00028275614,0.00085466314,0.0006851932,0.0007704624,0.00052357203],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054574246,0.00028268015,0.003417207,0.00020975075,0.00018298188,0.00039805748,0.00013173546,0.2836681,0.05786775,0.003852346,0.0074626,0.64198095],"study_design_scores_gemma":[0.00000771336,0.00004123547,0.0013714366,0.000010556213,0.00002696616,0.00007125855,0.000013605602,0.981296,0.014208353,0.0016532086,0.0012896984,0.000009934885],"about_ca_topic_score_codex":0.0037908126,"about_ca_topic_score_gemma":0.007931891,"teacher_disagreement_score":0.0037908126,"about_ca_system_score_codex":0.00043294506,"about_ca_system_score_gemma":0.00039479256,"threshold_uncertainty_score":0.007537544},"labels":[],"label_agreement":null},{"id":"W4390970718","doi":"10.1109/apsar58496.2023.10389118","title":"Change Detection Analysis using Information Theoretic Measures on SAR Images","year":2023,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Randomness; Change detection; Hellinger distance; Entropy (arrow of time); Thresholding; Statistics; Cluster analysis; Statistical hypothesis testing; Kurtosis; Synthetic aperture radar; Computer science; Mathematics; Context (archaeology); Measure (data warehouse); Kullback–Leibler divergence; Artificial intelligence; Pattern recognition (psychology); Image (mathematics); Data mining; Geography","score_opus":0.04241153151307248,"score_gpt":0.2501774843968364,"score_spread":0.20776595288376393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390970718","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12212801,0.0008717451,0.8734853,0.00040283217,0.000043432414,0.000078873985,0.00015958484,0.00020162472,0.0026285423],"genre_scores_gemma":[0.7951381,0.00051738665,0.2033019,0.000113640024,0.00013338806,0.00010932177,0.00022920477,0.00005142489,0.00040563272],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99785596,0.0007441395,0.00016568691,0.00030677844,0.0007889847,0.00013844029],"domain_scores_gemma":[0.986736,0.010319957,0.0014224743,0.0005866873,0.000785481,0.0001493637],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037819634,0.00074444426,0.00085038535,0.0064806757,0.0005347148,0.002479743,0.0008077191,0.0010046216,0.000575195],"category_scores_gemma":[0.017781913,0.00027731116,0.00094363495,0.0036943464,0.002803104,0.0030891248,0.0010307261,0.00088508485,0.00013011541],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031441663,0.0002409308,0.029464588,0.00050692324,0.00040858306,0.00108623,0.0009885447,0.5022654,0.031254727,0.21295758,0.0009975568,0.21951449],"study_design_scores_gemma":[0.00001522174,0.00030878838,0.02147839,0.000059222202,0.00009177354,0.0007006442,0.00029634256,0.856966,0.013768565,0.10447239,0.0017143176,0.00012836394],"about_ca_topic_score_codex":0.0009911121,"about_ca_topic_score_gemma":0.0007249035,"teacher_disagreement_score":0.0064806757,"about_ca_system_score_codex":0.0010748155,"about_ca_system_score_gemma":0.00049609103,"threshold_uncertainty_score":0.020001173},"labels":[],"label_agreement":null},{"id":"W4391019542","doi":"10.1109/lgrs.2024.3356422","title":"Attention Graph Convolutional Network for Disjoint Hyperspectral Image Classification","year":2024,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Natural Science Foundation of China","keywords":"Convolutional neural network; Computer science; Hyperspectral imaging; Pattern recognition (psychology); Artificial intelligence; Graph; Pixel; Kernel (algebra); Disjoint sets; Contextual image classification; Benchmark (surveying); Image (mathematics); Mathematics; Theoretical computer science; Cartography","score_opus":0.01790677766745367,"score_gpt":0.2375886342189074,"score_spread":0.21968185655145375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391019542","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.069747336,0.0026083523,0.90879285,0.0009653362,0.00023151217,0.00011731973,0.0009959105,0.0061974516,0.010343907],"genre_scores_gemma":[0.8491707,0.00087669067,0.13096835,0.0005586939,0.00012200542,0.00012051974,0.0027662579,0.00024313615,0.015173737],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99977833,0.000026576456,0.000008417534,0.00008130991,0.00005258,0.000052714408],"domain_scores_gemma":[0.9997881,0.00006388118,0.000028126102,0.000037510144,0.00006706934,0.000015290832],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029982664,0.00074456556,0.00053285673,0.0008189552,0.000291367,0.00049142714,0.0012367017,0.0007593449,0.003274338],"category_scores_gemma":[0.0009478642,0.00022660285,0.0005632559,0.000912535,0.0003519261,0.00091499893,0.00074673566,0.0009422043,0.00076416385],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021986141,0.00014162899,0.0022596987,0.00012811793,0.00011091236,0.00016809271,0.000052195544,0.5237681,0.009837386,0.017025366,0.017126467,0.4291621],"study_design_scores_gemma":[0.0000032081193,0.000010822448,0.00028465278,0.0000042600213,0.000010009481,0.00001878237,0.0000038561807,0.99314237,0.0014475043,0.0039428268,0.0011277567,0.000003864892],"about_ca_topic_score_codex":0.028128231,"about_ca_topic_score_gemma":0.031442616,"teacher_disagreement_score":0.028128231,"about_ca_system_score_codex":0.0015969557,"about_ca_system_score_gemma":0.0011047665,"threshold_uncertainty_score":0.055929005},"labels":[],"label_agreement":null},{"id":"W4391033652","doi":"10.3389/fenvs.2023.1353447","title":"Editorial: Hyperspectral imaging in environmental monitoring and analysis","year":2024,"lang":"en","type":"editorial","venue":"Frontiers in Environmental Science","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":63,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Agriculture and Agri-Food Canada","funders":"","keywords":"Hyperspectral imaging; Remote sensing; Environmental science; Environmental monitoring; Geology; Environmental engineering","score_opus":0.0029721729720859637,"score_gpt":0.2017696045931117,"score_spread":0.19879743162102573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391033652","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000023635943,0.006119307,0.00017322473,0.023739304,0.9674587,0.000018358163,0.00004303803,0.00006235954,0.0023620394],"genre_scores_gemma":[0.00026521154,0.0044878093,0.000108019056,0.014540379,0.9706113,0.000018057874,0.00003314337,0.000041726915,0.009894348],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99596053,0.0006110034,0.00037609666,0.0005202121,0.0023058737,0.00022614823],"domain_scores_gemma":[0.9839244,0.0059449635,0.0007912114,0.00043415438,0.006575682,0.0023295516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046734083,0.0036891266,0.0037316207,0.0036568257,0.0031074095,0.008181206,0.0035816093,0.014765693,0.020765554],"category_scores_gemma":[0.018439362,0.001105545,0.0026326342,0.0017848272,0.0025782567,0.0056783743,0.0017092387,0.018778894,0.024575625],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018078352,0.000009305229,0.000012416896,0.000109214256,0.000008173395,0.00006744602,0.0000046518403,0.00002231476,0.000041128973,0.00018623329,0.99552226,0.0039987094],"study_design_scores_gemma":[0.000027983637,0.000016115184,0.00016855815,0.00029975016,0.00001964935,0.00026514786,0.000017726332,0.00014742734,0.000088079825,0.0008888035,0.9980459,0.000014705865],"about_ca_topic_score_codex":0.0013753414,"about_ca_topic_score_gemma":0.0036263308,"teacher_disagreement_score":0.020765554,"about_ca_system_score_codex":0.0025214122,"about_ca_system_score_gemma":0.0021482,"threshold_uncertainty_score":0.069467664},"labels":[],"label_agreement":null},{"id":"W4391383156","doi":"10.1016/j.engappai.2024.107926","title":"A manifold intelligent decision system for fusion and benchmarking of deep waste-sorting models","year":2024,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Ostravská Univerzita v Ostravě; Ministerstvo Školství, Mládeže a Tělovýchovy; European Commission","keywords":"Computer science; Benchmarking; Sorting; Artificial intelligence; Manifold (fluid mechanics); Decision support system; Fusion; Deep learning; Machine learning; Operations research; Algorithm","score_opus":0.023559252718012853,"score_gpt":0.256387405038613,"score_spread":0.23282815232060017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391383156","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.063320525,0.0002753946,0.92918974,0.0002401086,0.00007842834,0.00019194387,0.0002955071,0.0040393886,0.002368926],"genre_scores_gemma":[0.75441843,0.00009648126,0.24287198,0.00011717979,0.000027755721,0.00029470827,0.00079219835,0.000109728375,0.0012714865],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99863154,0.00038940183,0.00017831482,0.00037762462,0.0002716996,0.00015145798],"domain_scores_gemma":[0.9982236,0.0005724994,0.00017467282,0.00016862016,0.00077244826,0.00008822288],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004213669,0.0014916415,0.0013047806,0.001936855,0.00083747215,0.0020136253,0.0015461427,0.0015577734,0.002766659],"category_scores_gemma":[0.0069168815,0.00046583833,0.0014248407,0.0010550356,0.0005429894,0.0014286885,0.001774339,0.0015190026,0.00063229474],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003865697,0.0002292911,0.0041444805,0.00012556664,0.00020114043,0.00014314038,0.00019528544,0.72489405,0.004864768,0.0069115134,0.0023104143,0.25559387],"study_design_scores_gemma":[0.0000047896738,0.000026996506,0.00017193958,0.0000050378017,0.000007964946,0.0000055686482,0.0000111048475,0.99710983,0.001099141,0.0013462007,0.00020637826,0.000005173891],"about_ca_topic_score_codex":0.010009601,"about_ca_topic_score_gemma":0.0062850425,"teacher_disagreement_score":0.010009601,"about_ca_system_score_codex":0.0019445876,"about_ca_system_score_gemma":0.0015479022,"threshold_uncertainty_score":0.022284329},"labels":[],"label_agreement":null},{"id":"W4391483017","doi":"10.21203/rs.3.rs-3913857/v1","title":"WITHDRAWN: Surface multi-spectral reflectivity and texture material recognition in non-constrained environments","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"RGB color model; Artificial intelligence; Computer science; Computer vision; Projector; Bidirectional reflectance distribution function; Reflection (computer programming); Complementarity (molecular biology); Texture (cosmology); Facial recognition system; Pattern recognition (psychology); Reflectivity; Optics; Image (mathematics)","score_opus":0.05693312172644717,"score_gpt":0.3456642270086278,"score_spread":0.28873110528218066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391483017","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01467926,0.027640687,0.029634468,0.14923736,0.5192475,0.0007428985,0.063060924,0.0054679806,0.19028887],"genre_scores_gemma":[0.054612007,0.011987824,0.016779661,0.010097686,0.081238426,0.00035265836,0.03282535,0.0015039046,0.7906025],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986657,0.00014862743,0.00015194698,0.0002032709,0.0007323579,0.000098103024],"domain_scores_gemma":[0.99199647,0.001372807,0.0002539256,0.0008082663,0.004913921,0.00065453775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001714604,0.00130207,0.0015473252,0.0019202068,0.0013317239,0.0023649514,0.0019005699,0.002243678,0.16728708],"category_scores_gemma":[0.011739477,0.000373124,0.0008952752,0.0020476175,0.0007555777,0.0022769112,0.001038412,0.001531636,0.07509956],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004408763,0.00006521277,0.00036766153,0.00065922574,0.000047117122,0.00014331829,0.00005539785,0.00029306381,0.004343838,0.0047773635,0.9296349,0.059171952],"study_design_scores_gemma":[0.00020506083,0.0002178714,0.0065324535,0.0002275126,0.00009684134,0.0005277919,0.00011969124,0.0031170077,0.011634046,0.010380082,0.9668725,0.000069069334],"about_ca_topic_score_codex":0.00751615,"about_ca_topic_score_gemma":0.005167067,"teacher_disagreement_score":0.16728708,"about_ca_system_score_codex":0.0010830744,"about_ca_system_score_gemma":0.0019374535,"threshold_uncertainty_score":0.55963105},"labels":[],"label_agreement":null},{"id":"W4392167461","doi":"10.18280/isi.290137","title":"Supervised Machine Learning Algorithms for Land Cover Classification in Casablanca, Morocco","year":2024,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Land cover; Cover (algebra); Machine learning; Computer science; Artificial intelligence; Algorithm; Geography; Forestry; Land use; Engineering; Civil engineering","score_opus":0.024310694216102935,"score_gpt":0.2434505348293784,"score_spread":0.21913984061327546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392167461","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8540429,0.0104411775,0.11622454,0.001934756,0.00017819548,0.00029334475,0.0031721324,0.0014197943,0.012293255],"genre_scores_gemma":[0.95195234,0.00077650737,0.044252615,0.000065421285,0.000045933237,0.00009088539,0.0014432461,0.000026674985,0.0013463828],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991372,0.0003811829,0.000060712195,0.00011435875,0.0002047423,0.00010176536],"domain_scores_gemma":[0.9987275,0.00062015053,0.00017928143,0.00009449738,0.00034090524,0.00003773518],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013557295,0.0006271364,0.0004487346,0.0020310055,0.0005371151,0.001068059,0.000550113,0.00043564115,0.0006181762],"category_scores_gemma":[0.0035482699,0.00010691682,0.00033261537,0.0016171341,0.00028672392,0.00041968309,0.00043319602,0.0003053361,0.00024503915],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040845835,0.00026323381,0.10897228,0.000602304,0.00031501806,0.00080143503,0.0005543567,0.30939794,0.009117233,0.008320817,0.009097065,0.5521498],"study_design_scores_gemma":[0.00003378875,0.0001447193,0.122744665,0.00012823143,0.00008194861,0.00024414013,0.00086381903,0.8510686,0.0061685806,0.005225472,0.013241201,0.00005481292],"about_ca_topic_score_codex":0.08587187,"about_ca_topic_score_gemma":0.088110745,"teacher_disagreement_score":0.08587187,"about_ca_system_score_codex":0.0024074512,"about_ca_system_score_gemma":0.00158843,"threshold_uncertainty_score":0.17074406},"labels":[],"label_agreement":null},{"id":"W4392386471","doi":"10.3390/rs16050878","title":"Performance Comparison of Deep Learning (DL)-Based Tabular Models for Building Mapping Using High-Resolution Red, Green, and Blue Imagery and the Geographic Object-Based Image Analysis Framework","year":2024,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Artificial intelligence; Convolutional neural network; Object based; Deep learning; Remote sensing; High resolution; Cartography; Object (grammar); Pattern recognition (psychology); Geography","score_opus":0.017938323336639247,"score_gpt":0.24982729451316643,"score_spread":0.23188897117652718,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392386471","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63970417,0.00732524,0.31564692,0.0013222144,0.0007555523,0.00024850093,0.005243262,0.0142309945,0.0155230835],"genre_scores_gemma":[0.8908808,0.0014009547,0.09171745,0.0004219706,0.00006587794,0.00011121723,0.009635873,0.0002088145,0.0055571133],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995053,0.00010124459,0.000054131215,0.00014189733,0.00009547117,0.00010199799],"domain_scores_gemma":[0.9987903,0.0005214735,0.00009841553,0.00014838224,0.00035612774,0.00008525183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014700147,0.0012960538,0.00087762426,0.001474265,0.00034295945,0.0014616603,0.0016709579,0.0009941108,0.0031314685],"category_scores_gemma":[0.0025156264,0.0002820233,0.0010288713,0.0012572291,0.00032773457,0.0017315266,0.0010700306,0.0009467703,0.0017117464],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015923129,0.00050320604,0.012366745,0.00034743824,0.00034945566,0.000105854604,0.00008855379,0.47246748,0.004094022,0.002011151,0.009189752,0.496884],"study_design_scores_gemma":[0.000013509325,0.00008522236,0.0011354355,0.000019644203,0.000021264324,0.000019120112,0.000038469294,0.99607605,0.0014971583,0.00054687576,0.00053668604,0.000010642433],"about_ca_topic_score_codex":0.02397695,"about_ca_topic_score_gemma":0.019889096,"teacher_disagreement_score":0.02397695,"about_ca_system_score_codex":0.0015293594,"about_ca_system_score_gemma":0.0013482255,"threshold_uncertainty_score":0.047674775},"labels":[],"label_agreement":null},{"id":"W4392719398","doi":"10.1109/tgrs.2024.3374324","title":"Cross Hyperspectral and LiDAR Attention Transformer: An Extended Self-Attention for Land Use and Land Cover Classification","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":76,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"European Regional Development Fund; Science and Engineering Research Board; Helmholtz-Zentrum Dresden-Rossendorf","keywords":"Lidar; Hyperspectral imaging; Computer science; Land cover; Deep learning; Ranging; Remote sensing; Artificial intelligence; Transformer; Machine learning; Land use; Geography","score_opus":0.023823349152431297,"score_gpt":0.2685786684794086,"score_spread":0.2447553193269773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392719398","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.091842726,0.0008852349,0.89249414,0.00048424315,0.00016497179,0.00015314453,0.0004516502,0.008116701,0.005407123],"genre_scores_gemma":[0.79974025,0.0003570853,0.18537892,0.00095437025,0.00014780935,0.00015662974,0.0016474996,0.00035403826,0.011263408],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99968624,0.000048072667,0.000012050394,0.00011298515,0.00006877776,0.00007194716],"domain_scores_gemma":[0.9997261,0.00008020561,0.000019926274,0.000054130527,0.000079688456,0.000039860053],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007614945,0.00097106484,0.000658538,0.0008339874,0.00031480181,0.0005801069,0.0020538568,0.0009339196,0.004428897],"category_scores_gemma":[0.00096062245,0.00032886822,0.00082933356,0.00068656687,0.00040926773,0.0017272448,0.0022030168,0.0010946231,0.0009760723],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044105764,0.00066380826,0.0030389067,0.00011479613,0.00017275855,0.00022112681,0.00020088753,0.07956896,0.03787434,0.008154255,0.013821457,0.85572773],"study_design_scores_gemma":[0.00001587492,0.0000738743,0.00077751226,0.0000070962315,0.000029597622,0.000055246248,0.000021868607,0.98386,0.009140825,0.004416544,0.0015914334,0.000010136122],"about_ca_topic_score_codex":0.009755036,"about_ca_topic_score_gemma":0.01064914,"teacher_disagreement_score":0.009755036,"about_ca_system_score_codex":0.000886722,"about_ca_system_score_gemma":0.0008123964,"threshold_uncertainty_score":0.019396544},"labels":[],"label_agreement":null},{"id":"W4392858711","doi":"10.3390/rs16061049","title":"Comparing Pixel- and Object-Based Approaches for Classifying Multispectral Drone Imagery of a Salt Marsh Restoration and Reference Site","year":2024,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Environment and Climate Change Canada; Lakehead University; University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada; Mount Allison University; Mitacs; Lakehead University; University of New Brunswick","keywords":"Multispectral image; Remote sensing; Salt marsh; Object based; Computer science; Pixel; Environmental science; Geology; Artificial intelligence; Oceanography","score_opus":0.07258483753009941,"score_gpt":0.26085374564393393,"score_spread":0.1882689081138345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392858711","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9469911,0.0003551741,0.048467357,0.0001292364,0.000033881028,0.00016100872,0.00040361518,0.00027177465,0.0031869013],"genre_scores_gemma":[0.94898224,0.0001821956,0.04906666,0.000071346236,0.000012452376,0.000063870306,0.00078595156,0.000028219825,0.0008071218],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984421,0.00050416955,0.000107975124,0.0003352316,0.00045913394,0.0001513181],"domain_scores_gemma":[0.9970229,0.0012308575,0.00023702887,0.00032376815,0.0010716578,0.00011377727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004584273,0.000528184,0.00037429415,0.0025214842,0.0004657404,0.0015174766,0.00051765126,0.00064887025,0.00056660804],"category_scores_gemma":[0.0050799693,0.00017921327,0.00048617914,0.0010321017,0.0003298375,0.0014212364,0.00047958878,0.00036281568,0.0003984958],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009836904,0.0008392881,0.5047687,0.00024064886,0.00088745373,0.00011412526,0.00075327273,0.0504376,0.03436477,0.0008655192,0.0013330989,0.40441182],"study_design_scores_gemma":[0.000049870076,0.0006773022,0.5072044,0.000076494754,0.00024052132,0.00017696738,0.0014573296,0.4703885,0.016721351,0.00074788387,0.0021678363,0.00009141466],"about_ca_topic_score_codex":0.022081167,"about_ca_topic_score_gemma":0.06395346,"teacher_disagreement_score":0.022081167,"about_ca_system_score_codex":0.0009826556,"about_ca_system_score_gemma":0.00053116906,"threshold_uncertainty_score":0.04390526},"labels":[],"label_agreement":null},{"id":"W4392876402","doi":"10.32920/25418056","title":"Geographic Object-based Image Analysis Change Detection in a Shrinking City: Detroit, Michigan, 2014-2018","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; University of Toronto","funders":"","keywords":"Impervious surface; Geography; Cartography; Change analysis; Change detection; Aerial imagery; Object based; Land cover; Population; Geographic information system; Cover (algebra); Remote sensing; Object (grammar); Land use; Physical geography; Computer science; Civil engineering; Engineering; Artificial intelligence","score_opus":0.022109057118293047,"score_gpt":0.24416256402595524,"score_spread":0.22205350690766218,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392876402","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9195595,0.00068232534,0.0091637885,0.0031028278,0.0002271018,0.00023004277,0.03329715,0.0020927717,0.031644437],"genre_scores_gemma":[0.8872899,0.00062919914,0.025516277,0.00024551878,0.00016099702,0.00016614991,0.05254477,0.00024039604,0.03320691],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9998023,0.000017806162,0.000009615859,0.00006582499,0.00007482789,0.000029598885],"domain_scores_gemma":[0.9996774,0.000017880953,0.000028701934,0.000033879962,0.00020390304,0.000038216047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029327915,0.00033985297,0.00016856722,0.0013332912,0.000522826,0.0008879932,0.00036508136,0.0003142048,0.0028989094],"category_scores_gemma":[0.00051745,0.00014520397,0.00020061414,0.0016202743,0.00027109077,0.0005123292,0.00047705695,0.0003188599,0.0013722504],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030026893,0.000383499,0.49585107,0.00018750699,0.00012505164,0.0011070432,0.0011460449,0.0068538007,0.020666726,0.0010290063,0.1474204,0.3249296],"study_design_scores_gemma":[0.000011183428,0.00004308096,0.9104095,0.000040590872,0.000037611735,0.00024078846,0.0016921884,0.034565296,0.006872301,0.00020421384,0.045859862,0.000023234828],"about_ca_topic_score_codex":0.2165368,"about_ca_topic_score_gemma":0.4952775,"teacher_disagreement_score":0.2165368,"about_ca_system_score_codex":0.0010872186,"about_ca_system_score_gemma":0.0005831609,"threshold_uncertainty_score":0.4305529},"labels":[],"label_agreement":null},{"id":"W4392876507","doi":"10.32920/25418056.v1","title":"Geographic Object-based Image Analysis Change Detection in a Shrinking City: Detroit, Michigan, 2014-2018","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; University of Toronto","funders":"","keywords":"Impervious surface; Geography; Change analysis; Change detection; Cartography; Aerial imagery; Land cover; Object based; Geographic information system; Population; Remote sensing; Object (grammar); Land use; Physical geography; Computer science; Civil engineering; Engineering; Artificial intelligence","score_opus":0.022109057118293047,"score_gpt":0.24416256402595524,"score_spread":0.22205350690766218,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392876507","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9195595,0.00068232534,0.0091637885,0.0031028278,0.0002271018,0.00023004277,0.03329715,0.0020927717,0.031644437],"genre_scores_gemma":[0.8872899,0.00062919914,0.025516277,0.00024551878,0.00016099702,0.00016614991,0.05254477,0.00024039604,0.03320691],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9998023,0.000017806162,0.000009615859,0.00006582499,0.00007482789,0.000029598885],"domain_scores_gemma":[0.9996774,0.000017880953,0.000028701934,0.000033879962,0.00020390304,0.000038216047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029327915,0.00033985297,0.00016856722,0.0013332912,0.000522826,0.0008879932,0.00036508136,0.0003142048,0.0028989094],"category_scores_gemma":[0.00051745,0.00014520397,0.00020061414,0.0016202743,0.00027109077,0.0005123292,0.00047705695,0.0003188599,0.0013722504],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030026893,0.000383499,0.49585107,0.00018750699,0.00012505164,0.0011070432,0.0011460449,0.0068538007,0.020666726,0.0010290063,0.1474204,0.3249296],"study_design_scores_gemma":[0.000011183428,0.00004308096,0.9104095,0.000040590872,0.000037611735,0.00024078846,0.0016921884,0.034565296,0.006872301,0.00020421384,0.045859862,0.000023234828],"about_ca_topic_score_codex":0.2165368,"about_ca_topic_score_gemma":0.4952775,"teacher_disagreement_score":0.2165368,"about_ca_system_score_codex":0.0010872186,"about_ca_system_score_gemma":0.0005831609,"threshold_uncertainty_score":0.4305529},"labels":[],"label_agreement":null},{"id":"W4392910300","doi":"10.1109/icassp48485.2024.10446925","title":"AQF: Assessing the Quality of Hyperspectral Reconstruction with a Learnable Metric","year":2024,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Hyperspectral imaging; Metric (unit); Quality (philosophy); Computer science; Artificial intelligence; Remote sensing; Environmental science; Geology; Business; Marketing","score_opus":0.034075745386048226,"score_gpt":0.29839199240875497,"score_spread":0.26431624702270673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392910300","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053036835,0.00082417304,0.9439739,0.00019646875,0.000063100146,0.00006808687,0.00016843564,0.0004855209,0.001183374],"genre_scores_gemma":[0.80640167,0.0006355033,0.19076401,0.00016690936,0.000116118266,0.00015489443,0.00060515886,0.00012669091,0.0010290545],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977544,0.0005724418,0.00017115766,0.00043213906,0.0009537454,0.00011612007],"domain_scores_gemma":[0.99536407,0.0019763287,0.0008463328,0.00045322062,0.0012013705,0.0001585716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036267566,0.0013281526,0.001003512,0.0027784822,0.0003374778,0.0012685396,0.0013218328,0.0016150352,0.00076892687],"category_scores_gemma":[0.010803421,0.00019746498,0.0006777682,0.0014292003,0.0013171686,0.0032982565,0.0015197832,0.0010770259,0.00021169837],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047499966,0.00028484067,0.022405012,0.0005274611,0.000500013,0.00022861511,0.00022506509,0.47617194,0.02768034,0.011237037,0.0030725235,0.45719206],"study_design_scores_gemma":[0.000010572647,0.00022341273,0.0040502613,0.000034967066,0.00004745739,0.00017660882,0.0000498102,0.9811885,0.0077902963,0.0055280053,0.0008548349,0.00004533294],"about_ca_topic_score_codex":0.0017389777,"about_ca_topic_score_gemma":0.0013715756,"teacher_disagreement_score":0.0036267566,"about_ca_system_score_codex":0.0009981984,"about_ca_system_score_gemma":0.0006153232,"threshold_uncertainty_score":0.019180417},"labels":[],"label_agreement":null},{"id":"W4393542943","doi":"10.5281/zenodo.10048770","title":"Evergreen needleleaf forest pigment, MONI-PAM, eddy-covariance, and tower-scale remote sensing data across four different sites","year":2023,"lang":"en","type":"dataset","venue":"Open MIND","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Eddy covariance; Evergreen; Environmental science; Scale (ratio); Tower; Evergreen forest; Remote sensing; Geography; Biology; Ecology; Cartography; Ecosystem","score_opus":0.11617911877061161,"score_gpt":0.33734048028377667,"score_spread":0.22116136151316507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393542943","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027925659,0.0000454384,0.00013574382,0.000057631347,0.000020447298,0.000031394487,0.99555075,0.0003360887,0.0010298736],"genre_scores_gemma":[0.0013060609,0.000016369102,0.00029914154,0.000018612376,0.0000032652176,0.000051543215,0.9978422,0.000020382247,0.00044238789],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99938023,0.00006052691,0.000059259943,0.0001847614,0.00019338231,0.000121909565],"domain_scores_gemma":[0.9992914,0.00010857346,0.00007697682,0.00016194007,0.00025632625,0.000104784354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073768577,0.0019249851,0.0009883045,0.0020254566,0.0008534417,0.0010580703,0.0022077395,0.0013061782,0.012725894],"category_scores_gemma":[0.0015074434,0.00039771988,0.00092311244,0.004072249,0.00043496705,0.000645135,0.0011770149,0.0012375078,0.028231347],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021014891,0.00017968065,0.0076449527,0.0005350145,0.00007666271,0.000088991306,0.00007036623,0.0014486121,0.00083336513,0.0005271291,0.9785387,0.00984642],"study_design_scores_gemma":[0.0006624887,0.00007694937,0.059350394,0.0002424486,0.000086658205,0.00018954139,0.00045089913,0.004289453,0.002294314,0.0011274526,0.9311338,0.00009550729],"about_ca_topic_score_codex":0.04749796,"about_ca_topic_score_gemma":0.08084576,"teacher_disagreement_score":0.04749796,"about_ca_system_score_codex":0.001197992,"about_ca_system_score_gemma":0.00156767,"threshold_uncertainty_score":0.09444296},"labels":[],"label_agreement":null},{"id":"W4393612657","doi":"10.5281/zenodo.10048769","title":"Evergreen needleleaf forest pigment, MONI-PAM, eddy-covariance, and tower-scale remote sensing data across four different sites","year":2024,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Eddy covariance; Evergreen; Scale (ratio); Environmental science; Tower; Evergreen forest; Covariance; Remote sensing; Atmospheric sciences; Geography; Mathematics; Ecology; Statistics; Geology; Biology; Ecosystem; Cartography","score_opus":0.06548981450580608,"score_gpt":0.2760592982555048,"score_spread":0.2105694837496987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393612657","genre_codex":"empirical","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9704663,0.000098786615,0.0003719141,0.000027758855,0.000005448597,0.00004068444,0.025070649,0.00005752959,0.0038609065],"genre_scores_gemma":[0.9145431,0.00019504127,0.0041207056,0.000060786464,0.000008894245,0.00017477153,0.07695432,0.000030643434,0.0039116805],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.999821,0.000016180624,0.0000112456555,0.000056670746,0.00005823205,0.00003665452],"domain_scores_gemma":[0.9995485,0.000040885072,0.000065564986,0.000047427515,0.00019686768,0.00010078029],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031340783,0.00027292245,0.0001989893,0.00096212776,0.000493272,0.00036328554,0.00043253475,0.00016900434,0.0012272017],"category_scores_gemma":[0.00030948693,0.00015086662,0.00015444407,0.0015697822,0.00013004088,0.0002162816,0.00032951563,0.00019164772,0.00039741478],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040550786,0.00020374607,0.9339116,0.00010310696,0.00016885778,0.00013829826,0.00065724575,0.0021163055,0.015939621,0.00015191411,0.0067865634,0.039417263],"study_design_scores_gemma":[0.000019520849,0.000015897242,0.99344903,0.0000056788817,0.000028052018,0.000040667295,0.00022361022,0.00048424632,0.0012364609,0.00001679008,0.004471424,0.000008754835],"about_ca_topic_score_codex":0.20463254,"about_ca_topic_score_gemma":0.4298142,"teacher_disagreement_score":0.20463254,"about_ca_system_score_codex":0.0007140196,"about_ca_system_score_gemma":0.0005225223,"threshold_uncertainty_score":0.40688288},"labels":[],"label_agreement":null},{"id":"W4395056482","doi":"10.1109/tevc.2024.3392749","title":"Superpixel Segmentation-Based Evolutionary Multitasking Algorithm for Feature Selection of Hyperspectral Images","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Evolutionary Computation","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Natural Science Foundation of China","keywords":"Hyperspectral imaging; Human multitasking; Computer science; Feature selection; Artificial intelligence; Pattern recognition (psychology); Segmentation; Image segmentation; Evolutionary algorithm; Feature (linguistics); Selection (genetic algorithm); Genetic algorithm; Algorithm; Computer vision; Machine learning; Biology","score_opus":0.011714680546136218,"score_gpt":0.24899503956920108,"score_spread":0.23728035902306485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395056482","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027380442,0.00017516955,0.97073495,0.00007477002,0.000024916031,0.00004151355,0.00001877288,0.0003118078,0.0012377311],"genre_scores_gemma":[0.5338388,0.00016503842,0.46232677,0.00013966241,0.000035841327,0.00027724452,0.00017259925,0.000102478014,0.0029414843],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996847,0.000058895443,0.000016386648,0.000083688305,0.00010878122,0.00004748802],"domain_scores_gemma":[0.9996897,0.0001381611,0.000040197276,0.000025656427,0.00008077015,0.00002557098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006491449,0.00078528235,0.00089736417,0.000666438,0.0004585257,0.00043016163,0.000958643,0.00073308893,0.0013024297],"category_scores_gemma":[0.00109219,0.00035515492,0.0006771901,0.00068393827,0.00040897695,0.0005971455,0.00065669295,0.0005677947,0.00019374891],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009135849,0.00007701914,0.0013266994,0.00006421892,0.00006170363,0.00012196946,0.00015448454,0.78259265,0.016221073,0.004612719,0.0015740602,0.19310208],"study_design_scores_gemma":[0.0000051828233,0.000014724204,0.00014044983,0.000001820064,0.000004322889,0.000012048643,0.0000053124995,0.99817324,0.0007406771,0.0006522744,0.00024722106,0.0000026840657],"about_ca_topic_score_codex":0.0041136728,"about_ca_topic_score_gemma":0.004201691,"teacher_disagreement_score":0.0041136728,"about_ca_system_score_codex":0.0006127158,"about_ca_system_score_gemma":0.0008241679,"threshold_uncertainty_score":0.008179486},"labels":[],"label_agreement":null},{"id":"W4396508863","doi":"10.18280/ts.410226","title":"Automatic Cloud Detection and Removal in Satellite Imagery Using Deep Learning Techniques","year":2024,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Deep learning; Satellite imagery; Cloud computing; Remote sensing; Computer science; Satellite; Artificial intelligence; Geology; Engineering; Aerospace engineering","score_opus":0.013814884911691343,"score_gpt":0.2334151932461515,"score_spread":0.21960030833446018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396508863","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.091271184,0.00070243055,0.90473306,0.00026290928,0.000041655094,0.000041812986,0.00012134104,0.001032894,0.0017927128],"genre_scores_gemma":[0.64678794,0.000771721,0.34949246,0.00017002846,0.00006552513,0.000034911056,0.0005172494,0.00014888488,0.0020112728],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99985456,0.00002401972,0.0000066064376,0.000035850393,0.000052290063,0.000026643907],"domain_scores_gemma":[0.9998086,0.00006810211,0.000042551466,0.000029661547,0.000039200884,0.000011864263],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034093848,0.00047027093,0.00037486976,0.0006723865,0.0001903008,0.00043074656,0.0005013336,0.00036450283,0.00048873684],"category_scores_gemma":[0.000649385,0.00023293387,0.00050613564,0.0006160065,0.00038868663,0.0005769982,0.00043357463,0.0007495272,0.00023277313],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001832257,0.00010059588,0.0035601112,0.00019299006,0.000079602854,0.00022830223,0.00013217556,0.42673928,0.08123141,0.006651582,0.0034149308,0.47748587],"study_design_scores_gemma":[0.000002613576,0.000009761821,0.0006820611,0.0000068586705,0.0000049448568,0.000031693915,0.000009344539,0.9898935,0.0076006046,0.0013141437,0.00044092978,0.000003482308],"about_ca_topic_score_codex":0.004295978,"about_ca_topic_score_gemma":0.007222738,"teacher_disagreement_score":0.004295978,"about_ca_system_score_codex":0.00043270076,"about_ca_system_score_gemma":0.00036021124,"threshold_uncertainty_score":0.008541942},"labels":[],"label_agreement":null},{"id":"W4396534783","doi":"10.1109/jstars.2024.3394771","title":"Active Learning-Based Spectral–Spatial Classification for Discriminating Tree Species in Hyperspectral Images","year":2024,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Space Agency","keywords":"Hyperspectral imaging; Artificial intelligence; Computer science; Pattern recognition (psychology); Contextual image classification; Tree (set theory); Remote sensing; Mathematics; Geography; Image (mathematics)","score_opus":0.03240493958427956,"score_gpt":0.24731918934093472,"score_spread":0.21491424975665516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396534783","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04914836,0.0008684975,0.9472093,0.0002343663,0.000053469208,0.000058425245,0.000092367125,0.0006157597,0.0017194396],"genre_scores_gemma":[0.7663656,0.00075284066,0.22789976,0.00039614676,0.00015134277,0.00019480746,0.0005435897,0.00007711271,0.0036187854],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994912,0.00012948088,0.00003218865,0.00015022205,0.00014455423,0.000052383493],"domain_scores_gemma":[0.99887854,0.00060920557,0.00013384328,0.00009045862,0.00025438357,0.000033568816],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012355178,0.00076036045,0.00080358767,0.0011523057,0.00033013604,0.0008108256,0.0015054854,0.0008623847,0.00075208326],"category_scores_gemma":[0.0017627295,0.00030782522,0.0008686256,0.0009807434,0.0007083835,0.0014455362,0.000643615,0.0011246353,0.00033601193],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029929605,0.00045386737,0.004796225,0.0002016294,0.00017294072,0.00009270694,0.00019425048,0.3885087,0.030214438,0.005076386,0.0027154684,0.56727403],"study_design_scores_gemma":[0.000003702148,0.000023701848,0.0004082921,0.0000058895744,0.000012270491,0.000015166058,0.000013057212,0.9950458,0.0029988617,0.0011132181,0.00035401032,0.0000059398158],"about_ca_topic_score_codex":0.0023877455,"about_ca_topic_score_gemma":0.00401439,"teacher_disagreement_score":0.0023877455,"about_ca_system_score_codex":0.00043425657,"about_ca_system_score_gemma":0.0004553756,"threshold_uncertainty_score":0.0065340996},"labels":[],"label_agreement":null},{"id":"W4396781103","doi":"10.1080/07038992.2024.2333424","title":"Multi-Scale Dense Graph Attention Network for Hyperspectral Classification","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Hyperspectral imaging; Scale (ratio); Graph; Geography; Computer science; Cartography; Artificial intelligence; Pattern recognition (psychology); Remote sensing; Theoretical computer science","score_opus":0.028570731261071836,"score_gpt":0.24434623151298876,"score_spread":0.2157755002519169,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396781103","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08202314,0.0015028471,0.90487593,0.0008872617,0.00018211099,0.00010473264,0.00063970784,0.0038284555,0.0059558083],"genre_scores_gemma":[0.82489735,0.00087245036,0.1587628,0.0006829895,0.00014913686,0.00016568304,0.0026403219,0.0002543277,0.011574862],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99975616,0.000037710626,0.000008899729,0.00009569726,0.000054171556,0.00004723891],"domain_scores_gemma":[0.9997147,0.00009206937,0.000035860183,0.000038975853,0.00009303711,0.00002534713],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036631094,0.0010956408,0.00069760816,0.0009784106,0.00042621396,0.0005976406,0.0013355903,0.0008480081,0.0030912082],"category_scores_gemma":[0.0010880812,0.0003807596,0.0007392446,0.0010825832,0.00050099613,0.0014389867,0.0010313606,0.0010701392,0.0006137795],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002455437,0.00025056052,0.0035105008,0.00019713235,0.00016291554,0.00020155293,0.00014268997,0.478061,0.015499668,0.013825014,0.015026669,0.47287682],"study_design_scores_gemma":[0.000004027293,0.000013973979,0.00032646375,0.0000045356915,0.000012525798,0.000018429317,0.000010440136,0.99298817,0.0012626557,0.0046705413,0.0006835535,0.0000047380436],"about_ca_topic_score_codex":0.012966285,"about_ca_topic_score_gemma":0.019563094,"teacher_disagreement_score":0.012966285,"about_ca_system_score_codex":0.0012899645,"about_ca_system_score_gemma":0.000675358,"threshold_uncertainty_score":0.025781631},"labels":[],"label_agreement":null},{"id":"W4396897807","doi":"10.7717/peerj-cs.2003","title":"Applying a deep learning pipeline to classify land cover from low-quality historical RGB imagery","year":2024,"lang":"en","type":"article","venue":"PeerJ Computer Science","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Environment and Climate Change Canada","keywords":"Land cover; Satellite imagery; Cover (algebra); Remote sensing; Land use; Convolutional neural network; Computer science; Deep learning; Artificial intelligence; Physical geography; Geography; Ecology; Engineering","score_opus":0.022467717988204416,"score_gpt":0.26466896743543333,"score_spread":0.24220124944722893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396897807","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20556405,0.00033254648,0.7339078,0.0008285047,0.0002485853,0.00048202067,0.0064402497,0.039194804,0.013001515],"genre_scores_gemma":[0.5603213,0.00025697876,0.40432748,0.00040735514,0.000046214533,0.00033812676,0.015883345,0.00084135064,0.017577866],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999798,0.000013487273,0.000010179116,0.00007554135,0.00005514803,0.0000476402],"domain_scores_gemma":[0.99964726,0.00005222829,0.00002369737,0.00007213438,0.00017569619,0.000029016132],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004560639,0.0011355203,0.0002927827,0.0011052102,0.0005239617,0.0007327638,0.0011093372,0.00060335675,0.0041805306],"category_scores_gemma":[0.0011371224,0.00045322563,0.0007122752,0.00085902214,0.000448384,0.0009048216,0.00090875325,0.0010749487,0.0026429787],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020563389,0.0004229998,0.019436197,0.00022034421,0.0001810291,0.00032650906,0.0003847411,0.20246452,0.06419508,0.0028253566,0.03180153,0.67753595],"study_design_scores_gemma":[0.000013380433,0.000058760994,0.0063555725,0.000021623722,0.000024957684,0.000047948393,0.000059333,0.96287704,0.019557862,0.0026075195,0.008356649,0.000019364239],"about_ca_topic_score_codex":0.060483944,"about_ca_topic_score_gemma":0.088771366,"teacher_disagreement_score":0.060483944,"about_ca_system_score_codex":0.0013248723,"about_ca_system_score_gemma":0.0016608372,"threshold_uncertainty_score":0.120263755},"labels":[],"label_agreement":null},{"id":"W4398756748","doi":"10.2478/ijssis-2024-0014","title":"Analyzing recent trends in deep-learning approaches: a review on urban environmental hazards and disaster studies for monitoring, management, and mitigation toward sustainability","year":2024,"lang":"en","type":"review","venue":"International Journal on Smart Sensing and Intelligent Systems","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Fundamental Research Funds for the Central Universities; Natural Science Foundation of Shandong Province; China Scholarship Council; Ministry of Science and Technology of the People's Republic of China; China Postdoctoral Science Foundation; Chinese Academy of Sciences; National Natural Science Foundation of China; European Commission; National Aeronautics and Space Administration; Ministry of Education of the People's Republic of China; National Science Foundation","keywords":"Sustainability; Environmental planning; Environmental resource management; Emergency management; Environmental science; Risk analysis (engineering); Business; Political science; Ecology","score_opus":0.09064929126052221,"score_gpt":0.34994781115295764,"score_spread":0.25929851989243546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398756748","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00027668645,0.9959384,0.0016389996,0.0008434719,0.00022565354,0.000007203037,0.00002869407,0.000013892469,0.0010269653],"genre_scores_gemma":[0.0019101988,0.9960299,0.0010220298,0.00031327287,0.00026244088,0.000009674195,0.000045112734,0.0000064159617,0.00040097738],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99953735,0.00009933253,0.000067183166,0.000094800474,0.00016716094,0.000034127945],"domain_scores_gemma":[0.99741334,0.001578203,0.00017095057,0.000049125094,0.00070497586,0.00008340934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001667923,0.0010116136,0.0010182555,0.003364653,0.00024313362,0.0012888991,0.0009939389,0.0011983572,0.002819431],"category_scores_gemma":[0.0036410915,0.0004254569,0.00072033843,0.0047735525,0.0005765213,0.0023357081,0.00091761636,0.0015825137,0.0013403115],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004594366,0.00005771288,0.00048599977,0.015722826,0.00011897256,0.00008716289,0.000077996505,0.0015437119,0.00061905757,0.009070649,0.020460047,0.95170987],"study_design_scores_gemma":[0.000014640899,0.00014895173,0.0016147069,0.012223281,0.00029159078,0.00057425705,0.00015967588,0.0019687326,0.0011309414,0.010029726,0.9717891,0.00005445817],"about_ca_topic_score_codex":0.0018660129,"about_ca_topic_score_gemma":0.002661477,"teacher_disagreement_score":0.003364653,"about_ca_system_score_codex":0.00078091084,"about_ca_system_score_gemma":0.00161052,"threshold_uncertainty_score":0.009431899},"labels":[],"label_agreement":null},{"id":"W4399555383","doi":"10.1016/j.swevo.2024.101614","title":"Multiobjective band selection approach via an adaptive particle swarm optimizer for remote sensing hyperspectral images","year":2024,"lang":"en","type":"article","venue":"Swarm and Evolutionary Computation","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Science, Technology and Innovation Commission of Shenzhen Municipality; Natural Science Foundation of Guangdong Province; National Natural Science Foundation of China; Science and Technology Foundation of Shenzhen City","keywords":"Hyperspectral imaging; Computer science; Particle swarm optimization; Selection (genetic algorithm); Swarm behaviour; Remote sensing; Artificial intelligence; Mathematical optimization; Algorithm; Geology; Mathematics","score_opus":0.019255237625432547,"score_gpt":0.24838162116408438,"score_spread":0.22912638353865183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399555383","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02727437,0.00020758944,0.9702967,0.00010538005,0.000038785973,0.000035624133,0.000016071825,0.00015542956,0.0018701252],"genre_scores_gemma":[0.5344316,0.00025184182,0.45989397,0.0001499625,0.00009174589,0.00022737058,0.00009654333,0.00010549067,0.004751424],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99977833,0.00008749659,0.000010529045,0.000036531237,0.000066324814,0.000020940266],"domain_scores_gemma":[0.999741,0.00013320491,0.000032978773,0.000018750496,0.000059860526,0.000014126807],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00086772296,0.0007628174,0.00082734245,0.0005721162,0.0003744815,0.0007660522,0.00074610155,0.001042103,0.0012675402],"category_scores_gemma":[0.0010309828,0.00040099947,0.00071414816,0.0004869393,0.0004222766,0.00048524459,0.0005526272,0.0006887209,0.00024423675],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000075210526,0.00008411155,0.00042673716,0.00004932455,0.00009139186,0.00005676349,0.00005090387,0.917936,0.0049605565,0.0033300966,0.0008228587,0.07211607],"study_design_scores_gemma":[0.0000030064832,0.000009100222,0.000051916002,0.000001061343,0.0000042778365,0.0000030613282,0.0000018319975,0.9994655,0.00017929588,0.0002109956,0.00006877831,0.0000011744916],"about_ca_topic_score_codex":0.0029368277,"about_ca_topic_score_gemma":0.0028508895,"teacher_disagreement_score":0.0029368277,"about_ca_system_score_codex":0.00035403145,"about_ca_system_score_gemma":0.00049406535,"threshold_uncertainty_score":0.005839467},"labels":[],"label_agreement":null},{"id":"W4399619735","doi":"10.1109/jstars.2024.3413987","title":"CSA-Net: Complex Scenarios Adaptive Network for Building Extraction for Remote Sensing Images","year":2024,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Tianjin Science and Technology Program; Hunan University of Science and Technology; National Natural Science Foundation of China; Ministry of Natural Resources","keywords":"Computer science; Extraction (chemistry); Remote sensing; Net (polyhedron); Real-time computing; Artificial intelligence; Computer vision; Geology","score_opus":0.04630487908869425,"score_gpt":0.2737569899614845,"score_spread":0.22745211087279027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399619735","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04495634,0.0007015361,0.94032854,0.00027266968,0.0001384758,0.00019301461,0.0018108675,0.0077992138,0.0037992615],"genre_scores_gemma":[0.36352322,0.00076774356,0.6167338,0.0003539542,0.00012417985,0.00033246182,0.010751894,0.0004385262,0.0069742305],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999681,0.00004075715,0.000017236329,0.000105338404,0.00010631504,0.000049383125],"domain_scores_gemma":[0.9998355,0.00003475909,0.000023317729,0.000032451786,0.000060325365,0.000013651897],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004822366,0.001445775,0.00066220056,0.0017856193,0.00047532958,0.0006598677,0.0013186284,0.0007129557,0.0024915885],"category_scores_gemma":[0.0008410267,0.00047440638,0.0010287013,0.0012896347,0.00035321663,0.0015444785,0.0012392681,0.00079241,0.0009864973],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046392094,0.00023674061,0.005125393,0.00024338152,0.00031167886,0.00034099002,0.00014812885,0.19395128,0.02761529,0.00606387,0.023600385,0.7418989],"study_design_scores_gemma":[0.00002080352,0.000047715832,0.0019545746,0.000014592142,0.000046431967,0.00015654687,0.000054489552,0.9778114,0.009525223,0.004513706,0.005829425,0.000025108508],"about_ca_topic_score_codex":0.008312122,"about_ca_topic_score_gemma":0.016205061,"teacher_disagreement_score":0.008312122,"about_ca_system_score_codex":0.00072108436,"about_ca_system_score_gemma":0.00066177215,"threshold_uncertainty_score":0.016527534},"labels":[],"label_agreement":null},{"id":"W4399666848","doi":"10.5566/ias.3078","title":"An Experimental Study for the Effects of Noise on Hyperspectral Imagery Classification","year":2024,"lang":"en","type":"article","venue":"Image Analysis & Stereology","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Space Agency; Concordia University","funders":"","keywords":"Hyperspectral imaging; Noise (video); Computer science; Artificial intelligence; Pattern recognition (psychology); Gaussian noise; Data cube; Contextual image classification; Computer vision; Image (mathematics); Data mining","score_opus":0.01593998674057442,"score_gpt":0.30168004332277754,"score_spread":0.28574005658220314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399666848","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8603924,0.00092431216,0.13331084,0.0002835859,0.0003513029,0.00021822286,0.0006162469,0.0009552195,0.0029479705],"genre_scores_gemma":[0.862333,0.00044034768,0.13289331,0.00023351476,0.000058659683,0.00028985983,0.0014586506,0.00032111251,0.0019714762],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9978661,0.00038370411,0.00019863337,0.00043089516,0.0009499867,0.00017064564],"domain_scores_gemma":[0.98873025,0.0055277436,0.0007254052,0.0013749686,0.0033972368,0.00024441845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019916669,0.0008571685,0.00058776536,0.00084189273,0.00074762246,0.00076544436,0.0010340312,0.00085102004,0.002047516],"category_scores_gemma":[0.0107738795,0.00028191792,0.00048913923,0.0009364456,0.0008754143,0.0011863597,0.000756328,0.000752318,0.00044669906],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0053771036,0.0023484644,0.016705176,0.0017104263,0.00035193906,0.00067877636,0.0009637233,0.15511164,0.6018684,0.0030519518,0.0048874817,0.20694494],"study_design_scores_gemma":[0.00012968977,0.0034307262,0.025346896,0.00015654541,0.00017989859,0.0005386897,0.00075438665,0.47201368,0.48938838,0.0019522861,0.0059673768,0.00014139517],"about_ca_topic_score_codex":0.002000899,"about_ca_topic_score_gemma":0.0018315825,"teacher_disagreement_score":0.002047516,"about_ca_system_score_codex":0.0005139354,"about_ca_system_score_gemma":0.00042356222,"threshold_uncertainty_score":0.010533094},"labels":[],"label_agreement":null},{"id":"W4400041392","doi":"10.18280/ts.410348","title":"Improving Built-up Extraction Using Spectral Indices and Machine Learning on Sentinel-2 Satellite Data in Mumbai Suburban District, India","year":2024,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Extraction (chemistry); Satellite; Remote sensing; Computer science; Geography; Engineering; Aerospace engineering","score_opus":0.03998812407133401,"score_gpt":0.26837457645724944,"score_spread":0.22838645238591543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400041392","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9905708,0.00021210936,0.0047158413,0.000145856,0.00003069233,0.000025247591,0.0016349817,0.00045321297,0.0022112243],"genre_scores_gemma":[0.98494107,0.00014691596,0.009663014,0.00004185655,0.000018422248,0.00002048341,0.0041341223,0.000030390713,0.0010037753],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99974495,0.00003553583,0.000015849577,0.00006247019,0.000065546985,0.00007567636],"domain_scores_gemma":[0.99972194,0.00004838536,0.000031348984,0.000039557126,0.00013424928,0.000024558041],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031733027,0.0005256041,0.00037205077,0.0015107731,0.00032311626,0.0007416691,0.00069303456,0.00034829366,0.00048328371],"category_scores_gemma":[0.00054773584,0.00019883833,0.00056041236,0.0014765573,0.00025838971,0.0005370142,0.00044467,0.00034033964,0.0004737836],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055663777,0.00045906747,0.5227431,0.00062920613,0.00034217667,0.0021769693,0.0013963184,0.116287515,0.045885485,0.0010335403,0.013524234,0.29496583],"study_design_scores_gemma":[0.000036644415,0.000105184685,0.714734,0.00007343102,0.00019625729,0.00033156833,0.0027854338,0.2584911,0.016301729,0.0004639933,0.006386047,0.00009455781],"about_ca_topic_score_codex":0.050994303,"about_ca_topic_score_gemma":0.09323404,"teacher_disagreement_score":0.050994303,"about_ca_system_score_codex":0.00045608237,"about_ca_system_score_gemma":0.00059160375,"threshold_uncertainty_score":0.10139495},"labels":[],"label_agreement":null},{"id":"W4400486093","doi":"10.61091/jcmcc120-10","title":"RICE: A Dataset and Baseline for Cloud Removal in Remote Sensing Images","year":2024,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Baseline (sea); Cloud computing; Remote sensing; Environmental science; Computer science; Geography; Geology; Operating system; Oceanography","score_opus":0.01613653581832174,"score_gpt":0.2685562967376969,"score_spread":0.2524197609193751,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400486093","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3580425,0.0045492435,0.06411637,0.0026866428,0.0011888501,0.0030126846,0.50928664,0.03262608,0.024491],"genre_scores_gemma":[0.16848244,0.0009982295,0.068288594,0.0006502625,0.00016329251,0.0009215804,0.753092,0.000801037,0.0066026594],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992028,0.00008438269,0.00006633242,0.0002670671,0.00025392676,0.00012552425],"domain_scores_gemma":[0.9992674,0.00007535178,0.000062285006,0.0002938189,0.00022053394,0.00008059741],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007744993,0.0019432987,0.0009346157,0.001999259,0.00080842525,0.00095295685,0.0023237064,0.0019083723,0.0028181926],"category_scores_gemma":[0.0015015103,0.00034590307,0.0016147892,0.0020403506,0.0008010681,0.00094166625,0.0013008286,0.0017003372,0.0043105907],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018392078,0.0030289176,0.022364903,0.0027031743,0.00072709064,0.0014377392,0.0002887705,0.07835542,0.05733119,0.003547303,0.56361836,0.26475793],"study_design_scores_gemma":[0.0013000931,0.0013305445,0.10993155,0.00061689666,0.000497145,0.0038817017,0.0012454457,0.361994,0.07835342,0.0076599214,0.4326802,0.0005090978],"about_ca_topic_score_codex":0.023229485,"about_ca_topic_score_gemma":0.03721202,"teacher_disagreement_score":0.023229485,"about_ca_system_score_codex":0.0010371987,"about_ca_system_score_gemma":0.0013042663,"threshold_uncertainty_score":0.046188533},"labels":[],"label_agreement":null},{"id":"W4400613682","doi":"10.1016/j.rse.2024.114290","title":"Deep learning for urban land use category classification: A review and experimental assessment","year":2024,"lang":"en","type":"review","venue":"Remote Sensing of Environment","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":166,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Remote sensing; Land use; Computer science; Environmental science; Artificial intelligence; Geography","score_opus":0.05394558127974756,"score_gpt":0.31015421843692675,"score_spread":0.2562086371571792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400613682","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016125971,0.9866992,0.0067913337,0.00072523736,0.0002672872,0.0000341077,0.00014648074,0.000055018405,0.0036688158],"genre_scores_gemma":[0.009522565,0.9844259,0.0042442633,0.00033064964,0.00017685088,0.000033708413,0.0002452046,0.000013586661,0.0010073334],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9996692,0.00007049479,0.000045416517,0.00009011521,0.000100687364,0.000024060222],"domain_scores_gemma":[0.9987853,0.000732367,0.000076780685,0.000043946653,0.00032791437,0.000033653123],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015104343,0.0010390719,0.0009824754,0.0026389293,0.00026958555,0.001181184,0.0012307088,0.0008162101,0.0024655529],"category_scores_gemma":[0.0029916512,0.00039542228,0.0009719742,0.004185593,0.000467537,0.001839411,0.0006941384,0.0011129879,0.0011294123],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043101696,0.000077997385,0.0010062084,0.011353917,0.00016687067,0.000041971114,0.00006468054,0.0023325735,0.0005714928,0.0048555913,0.012554577,0.9669311],"study_design_scores_gemma":[0.000034462213,0.0004584435,0.0060695335,0.016145077,0.0012153059,0.0007638481,0.00036461142,0.01341447,0.0040253503,0.012622451,0.9447652,0.00012126349],"about_ca_topic_score_codex":0.0044535017,"about_ca_topic_score_gemma":0.0046818955,"teacher_disagreement_score":0.0044535017,"about_ca_system_score_codex":0.00071401644,"about_ca_system_score_gemma":0.0017398197,"threshold_uncertainty_score":0.008855164},"labels":[],"label_agreement":null},{"id":"W4400942153","doi":"10.2139/ssrn.4904751","title":"Building Detection in Vhr Remote Sensing Images Using a Novel Dual Attention Residual-Based U-Net (Dattresu-Net): An Application to Generating Building Change Maps","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Net (polyhedron); Change detection; Residual; Remote sensing; Computer science; Dual (grammatical number); Artificial intelligence; Computer vision; Geography; Mathematics; Algorithm","score_opus":0.026204615756845503,"score_gpt":0.2849646454146078,"score_spread":0.2587600296577623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400942153","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1763107,0.00044926928,0.80366945,0.0002012227,0.00015160996,0.00015125354,0.0016434606,0.012178492,0.0052445643],"genre_scores_gemma":[0.49313644,0.0002197677,0.49718574,0.00011987929,0.00008426096,0.00010224973,0.002816754,0.0003512963,0.005983724],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99986637,0.000013742988,0.0000056121407,0.000048163154,0.000040790797,0.000025326715],"domain_scores_gemma":[0.99982613,0.000044458917,0.000018203391,0.000026505713,0.00006854679,0.000016193673],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003446256,0.0006812389,0.0005312944,0.0014430975,0.00027807074,0.0004979111,0.00093129074,0.00060068804,0.0029845722],"category_scores_gemma":[0.00046233748,0.0002492342,0.0005574782,0.0009232456,0.00021754773,0.00041097548,0.00072033366,0.00034662103,0.0010775964],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004045053,0.00020913075,0.0031857947,0.00014102117,0.00008058742,0.00012640585,0.000058404592,0.053301595,0.052820545,0.0010019711,0.004636179,0.8840338],"study_design_scores_gemma":[0.000014650011,0.00007569067,0.004088682,0.000008791728,0.000039258663,0.00008026031,0.000030853527,0.9646186,0.02871679,0.0007038362,0.0016101733,0.000012412972],"about_ca_topic_score_codex":0.007785283,"about_ca_topic_score_gemma":0.015966762,"teacher_disagreement_score":0.007785283,"about_ca_system_score_codex":0.00034674845,"about_ca_system_score_gemma":0.00042099095,"threshold_uncertainty_score":0.015479922},"labels":[],"label_agreement":null},{"id":"W4400959887","doi":"10.23952/jano.6.2024.3.02","title":"A stochastic proximal gradient method for linear hyperspectral unmixing","year":2024,"lang":"en","type":"article","venue":"Journal of Applied and Numerical Optimization","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Chinese Academy of Sciences; National Natural Science Foundation of China","keywords":"Hyperspectral imaging; Computer science; Artificial intelligence; Pattern recognition (psychology); Mathematics","score_opus":0.011852992522159518,"score_gpt":0.2555297992872905,"score_spread":0.243676806765131,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400959887","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00074331166,0.00008875581,0.9985922,0.000059250553,0.000016253318,0.000013040059,0.000010343759,0.000058822552,0.00041804864],"genre_scores_gemma":[0.13563044,0.00066729396,0.8550818,0.00021473554,0.00014752944,0.00033747914,0.00020552678,0.00020841644,0.0075068353],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993286,0.00027540448,0.000020679183,0.00010463367,0.00022096894,0.00004965449],"domain_scores_gemma":[0.9995278,0.0002627998,0.000049399863,0.00002600614,0.0001013054,0.000032616088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001529436,0.0011359833,0.00138751,0.0006396113,0.0004751993,0.00072008313,0.0011825698,0.0014311179,0.0020605156],"category_scores_gemma":[0.0019459188,0.00059753633,0.0009494247,0.0009465011,0.001092663,0.0011094116,0.0019693081,0.0018361983,0.00076602877],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006280957,0.00006664482,0.00020183926,0.00020100403,0.00007319,0.000077397424,0.00007174782,0.8806873,0.0043039867,0.049725883,0.0025154627,0.062012736],"study_design_scores_gemma":[0.0000041386616,0.000012902083,0.000021023392,0.0000040851037,0.0000025684599,0.000008669254,0.000002469442,0.9950283,0.00033325245,0.0038626215,0.00071507454,0.0000048209263],"about_ca_topic_score_codex":0.0028672486,"about_ca_topic_score_gemma":0.0023025419,"teacher_disagreement_score":0.0028672486,"about_ca_system_score_codex":0.0006676007,"about_ca_system_score_gemma":0.0017427903,"threshold_uncertainty_score":0.008088529},"labels":[],"label_agreement":null},{"id":"W4401240285","doi":"10.36227/techrxiv.172263334.44229028/v1","title":"Segmentation of Overlapping Pixels in Multi-spectral Document Images by Statistical Techniques","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Pixel; Segmentation; Artificial intelligence; Computer science; Pattern recognition (psychology); Computer vision","score_opus":0.018509264191445288,"score_gpt":0.2970333100306403,"score_spread":0.27852404583919504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401240285","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061022244,0.00031291126,0.9360958,0.000094513765,0.00003411873,0.000050284907,0.00009719875,0.0011629196,0.0011299899],"genre_scores_gemma":[0.31780213,0.00048759347,0.67883176,0.000088802364,0.0000753653,0.00008807509,0.0005603035,0.0003785695,0.0016874525],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993375,0.00008682293,0.000049805843,0.00018719285,0.00027148487,0.00006712581],"domain_scores_gemma":[0.99873036,0.00039195633,0.00027431847,0.00025478596,0.00029918464,0.00004942621],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074045797,0.0006225244,0.0005668557,0.0028236748,0.00042568223,0.0012549835,0.0006820357,0.00074268127,0.00095220713],"category_scores_gemma":[0.0017786454,0.00033460476,0.00079092797,0.002028194,0.00090826594,0.0011015177,0.0005959438,0.0008052315,0.0011036621],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025600588,0.00020255383,0.004355428,0.00026674633,0.00010443874,0.00023532401,0.0003634509,0.055200614,0.35941058,0.0045835506,0.0014125179,0.57360876],"study_design_scores_gemma":[0.000013776814,0.00010406394,0.011218906,0.000032045587,0.0000689784,0.00053432444,0.00024557146,0.7832143,0.19229835,0.006460134,0.0057571437,0.000052396692],"about_ca_topic_score_codex":0.0016390209,"about_ca_topic_score_gemma":0.0033947485,"teacher_disagreement_score":0.0028236748,"about_ca_system_score_codex":0.0005129092,"about_ca_system_score_gemma":0.0008756696,"threshold_uncertainty_score":0.0039159656},"labels":[],"label_agreement":null},{"id":"W4401626802","doi":"10.20944/preprints202408.1033.v1","title":"Enhanced Mapping for Ecosystem Management: Evaluating the Accuracy of Sentinel-1 and Sentinel-2 Data Fusion Compared to Sole Sentinel-2 Using Random Forest Classification","year":2024,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"European Space Agency","keywords":"Wetland; Remote sensing; Environmental science; Random forest; Ecosystem; Synthetic aperture radar; Satellite imagery; Mangrove ecosystem; Geography; Computer science; Ecology; Artificial intelligence","score_opus":0.2899762216349035,"score_gpt":0.39925913642558525,"score_spread":0.10928291479068175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401626802","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9633518,0.0006351854,0.03273168,0.00015150705,0.00010000186,0.0001097604,0.0004894646,0.0003951139,0.0020354416],"genre_scores_gemma":[0.9740951,0.00014168536,0.02490915,0.00003603474,0.000027384625,0.000032153872,0.0004796927,0.00002125407,0.00025759242],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9982716,0.00059703295,0.00013175223,0.00027570466,0.0005473455,0.0001766621],"domain_scores_gemma":[0.9972766,0.001298209,0.00037404874,0.00023492938,0.0007155699,0.000100676545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052433116,0.00086740765,0.0005677306,0.0015538306,0.00029728966,0.0007621762,0.0005005026,0.00088740274,0.0004923766],"category_scores_gemma":[0.006455035,0.00016870438,0.0006968121,0.00077511586,0.00026887684,0.0015715087,0.0007658026,0.00034680564,0.00021400953],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0064185364,0.001627187,0.26757804,0.00067266426,0.0015583672,0.0004627066,0.0005492697,0.2795667,0.04259507,0.0013601143,0.001915325,0.39569607],"study_design_scores_gemma":[0.0001011342,0.0019879364,0.1293056,0.000060387858,0.0003887611,0.00022378346,0.0003872318,0.8494431,0.01637063,0.00072807324,0.00092261436,0.000080795406],"about_ca_topic_score_codex":0.003109925,"about_ca_topic_score_gemma":0.00300208,"teacher_disagreement_score":0.0052433116,"about_ca_system_score_codex":0.00035736698,"about_ca_system_score_gemma":0.0003827251,"threshold_uncertainty_score":0.02772963},"labels":[],"label_agreement":null},{"id":"W4401867942","doi":"10.1080/07038992.2024.2393479","title":"Correction","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Geography; Library science; Computer science; Information retrieval","score_opus":0.013513130779652886,"score_gpt":0.21418058611197058,"score_spread":0.2006674553323177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401867942","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00075208605,0.0021633706,0.0030651928,0.04935223,0.8639457,0.000114482355,0.016844118,0.0040620975,0.059700824],"genre_scores_gemma":[0.022949079,0.0063150832,0.0073008444,0.023654297,0.12731022,0.00025987203,0.024932962,0.006050835,0.7812268],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955035,0.00046164988,0.00050329225,0.00076667225,0.0023223609,0.00044261367],"domain_scores_gemma":[0.96630424,0.004383698,0.001436087,0.003680936,0.023029182,0.0011658603],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002545099,0.0020467648,0.0012152328,0.006931706,0.0032697187,0.0061683455,0.002630239,0.004033365,0.34307843],"category_scores_gemma":[0.044411425,0.0009199695,0.0014976506,0.005303764,0.0016326249,0.0046884976,0.0031445993,0.0058392105,0.17967698],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002810594,0.000004826842,0.00013543859,0.00012145963,0.0000073401557,0.00009536286,0.00003233731,0.000046031073,0.00006315959,0.0015082828,0.98504096,0.012916742],"study_design_scores_gemma":[0.000015886537,0.00000774192,0.00041773784,0.00015563946,0.000009438691,0.00020117364,0.00005142567,0.00009762797,0.00025913367,0.0009178015,0.9978498,0.000016634158],"about_ca_topic_score_codex":0.016141979,"about_ca_topic_score_gemma":0.01651399,"teacher_disagreement_score":0.65692157,"about_ca_system_score_codex":0.0038594955,"about_ca_system_score_gemma":0.005949918,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W4401981122","doi":"10.1109/jstars.2024.3450856","title":"DSFC-AE: A New Hyperspectral Unmixing Method Based on Deep Shared Fully Connected Autoencoder","year":2024,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Natural Science Foundation of China; Ministry of Natural Resources","keywords":"Autoencoder; Hyperspectral imaging; Computer science; Artificial intelligence; Remote sensing; Pattern recognition (psychology); Deep learning; Geology","score_opus":0.025817094278112813,"score_gpt":0.25227258357287013,"score_spread":0.2264554892947573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401981122","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019771542,0.0005086481,0.97571087,0.00019455764,0.00007966891,0.000048929345,0.00013026154,0.0017091878,0.0018463074],"genre_scores_gemma":[0.4088429,0.000646953,0.57471853,0.0006702471,0.00010683937,0.00019619515,0.0015399394,0.0002875015,0.012990936],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999723,0.000038363567,0.000013365915,0.000088858185,0.00010040741,0.000035913596],"domain_scores_gemma":[0.9997292,0.000079745034,0.00003118973,0.000044728047,0.00009455924,0.00002055175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005685629,0.0012245015,0.00074622204,0.0005447078,0.00032478187,0.00051442115,0.0016974112,0.0012341869,0.0014966562],"category_scores_gemma":[0.0011190701,0.00046737972,0.00081358326,0.00048065284,0.00050073786,0.0015940502,0.001070436,0.0017278075,0.0005148106],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001599426,0.00015791482,0.0013579978,0.00013092198,0.00021113097,0.00017514652,0.00012474255,0.50760704,0.025305625,0.006387133,0.0053476975,0.45303473],"study_design_scores_gemma":[0.00000453916,0.00001662165,0.00013239663,0.0000055582977,0.000008929398,0.000025337498,0.0000044027697,0.9949509,0.0029218402,0.0011790085,0.0007437885,0.0000066279613],"about_ca_topic_score_codex":0.006466329,"about_ca_topic_score_gemma":0.010379529,"teacher_disagreement_score":0.006466329,"about_ca_system_score_codex":0.0005685808,"about_ca_system_score_gemma":0.0009173371,"threshold_uncertainty_score":0.0128573775},"labels":[],"label_agreement":null},{"id":"W4402122272","doi":"10.1016/j.rsase.2024.101336","title":"Building detection in VHR remote sensing images using a novel dual attention residual-based U-Net (DAttResU-Net): An application to generating building change maps","year":2024,"lang":"en","type":"article","venue":"Remote Sensing Applications Society and Environment","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Change detection; Block (permutation group theory); Sensitivity (control systems); Residual; Remote sensing; Process (computing); Net (polyhedron); Artificial intelligence; Data mining; Real-time computing; Geography; Engineering; Algorithm","score_opus":0.02455593584750891,"score_gpt":0.2560075147596258,"score_spread":0.23145157891211687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402122272","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2333406,0.00042814563,0.7463559,0.00021193615,0.00016134142,0.00015296345,0.0015206928,0.011262814,0.006565645],"genre_scores_gemma":[0.5502883,0.00020634402,0.44007248,0.0001360952,0.000069026675,0.000084908876,0.002516879,0.00028463008,0.0063414034],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998896,0.000010196138,0.0000048983743,0.00003552881,0.000038324397,0.000021395688],"domain_scores_gemma":[0.9998723,0.000026783533,0.00001458906,0.000017288807,0.00005641896,0.000012687991],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002560909,0.0005752767,0.00041611528,0.0013534481,0.0002689458,0.000408298,0.00077475584,0.0004289336,0.0026569702],"category_scores_gemma":[0.00032935233,0.00020105169,0.00044799777,0.0007691002,0.00017346191,0.00038139606,0.00059513724,0.0002811824,0.00081773684],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038506935,0.00023294931,0.004392902,0.000121696794,0.00008019609,0.00013211033,0.000056069246,0.039112795,0.06926928,0.0009493303,0.0048736557,0.8803939],"study_design_scores_gemma":[0.000015061989,0.000085356805,0.0062539834,0.00000891831,0.000045103418,0.00010387086,0.000042252752,0.9494368,0.041277207,0.000538852,0.0021769786,0.000015689544],"about_ca_topic_score_codex":0.008061614,"about_ca_topic_score_gemma":0.019980563,"teacher_disagreement_score":0.008061614,"about_ca_system_score_codex":0.00031427763,"about_ca_system_score_gemma":0.00041358275,"threshold_uncertainty_score":0.016029358},"labels":[],"label_agreement":null},{"id":"W4402187667","doi":"10.1016/j.geomat.2024.100023","title":"A comparative analysis of PlanetScope 4-band and 8-band imageries for land use land cover classification","year":2024,"lang":"en","type":"article","venue":"GEOMATICA","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Prince Edward Island","funders":"Department of Energy, Environment and Climate Action; Natural Resources Canada; Natural Sciences and Engineering Research Council of Canada; Princeton Environmental Institute, Princeton University","keywords":"Land cover; Remote sensing; Support vector machine; Cohen's kappa; Environmental science; Satellite imagery; Agricultural land; Random forest; Land use; Cartography; Computer science; Geography; Artificial intelligence; Machine learning; Ecology","score_opus":0.03778723101058647,"score_gpt":0.2737110143003825,"score_spread":0.23592378328979607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402187667","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9675531,0.0006816813,0.021311058,0.00009289916,0.000042750056,0.00012661413,0.0021918328,0.00033859987,0.007661463],"genre_scores_gemma":[0.9629436,0.00039807483,0.030057438,0.0000252755,0.000016312275,0.000052503925,0.0038803085,0.000063054,0.0025633825],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9993581,0.000109451415,0.00004646781,0.0001046681,0.00032465742,0.00005671435],"domain_scores_gemma":[0.9985177,0.00037818844,0.000091089714,0.0001098606,0.0008526815,0.00005054482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014238667,0.0003457583,0.00021858652,0.0026343588,0.0002081187,0.0005374608,0.00021871869,0.00021984121,0.0010080193],"category_scores_gemma":[0.0021136054,0.00009342187,0.00037069005,0.0015472965,0.00017477665,0.0007178779,0.00019294089,0.00017668196,0.00049950485],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00096102786,0.00024938266,0.39156827,0.0003708631,0.00033682623,0.00032132046,0.0006368978,0.012640071,0.040543985,0.0011860422,0.00583415,0.54535115],"study_design_scores_gemma":[0.000020078158,0.00032090786,0.8845714,0.00004683482,0.00015988457,0.00027730578,0.0009893057,0.093411244,0.014811513,0.00033974205,0.0050119506,0.000039796552],"about_ca_topic_score_codex":0.010816377,"about_ca_topic_score_gemma":0.022305036,"teacher_disagreement_score":0.010816377,"about_ca_system_score_codex":0.00032582576,"about_ca_system_score_gemma":0.0002845497,"threshold_uncertainty_score":0.021506786},"labels":[],"label_agreement":null},{"id":"W4402260472","doi":"10.1109/igarss53475.2024.10640940","title":"SpACNN-LDVAE: Spatial Attention Convolutional Latent Dirichlet Variational Autoencoder for Hyperspectral Pixel Unmixing","year":2024,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Autoencoder; Hyperspectral imaging; Computer science; Pixel; Latent Dirichlet allocation; Artificial intelligence; Pattern recognition (psychology); Remote sensing; Deep learning; Geography; Topic model","score_opus":0.016874692342922954,"score_gpt":0.23856804186765967,"score_spread":0.2216933495247367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402260472","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026216794,0.0006109989,0.9695948,0.0002638405,0.000080119935,0.000041303178,0.0003594116,0.0015715861,0.0012611013],"genre_scores_gemma":[0.5591125,0.0005963706,0.4259978,0.000510103,0.000114188864,0.00016074826,0.0030308764,0.0004574547,0.010019961],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996507,0.00009858348,0.00001565952,0.0001221155,0.00007275269,0.00004012746],"domain_scores_gemma":[0.9996222,0.00016948837,0.000031052605,0.00006376688,0.00009233036,0.00002108061],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010079502,0.0008819826,0.0008388614,0.00040478044,0.00031768804,0.0005655964,0.0014427053,0.00091988884,0.001229632],"category_scores_gemma":[0.0017499895,0.0005088712,0.0009345631,0.00048182395,0.0005675304,0.0011682393,0.0011474934,0.0019278894,0.00050463865],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017153127,0.00016852666,0.0020470603,0.00012429104,0.00022904875,0.000102893595,0.00012595538,0.7479611,0.0152348075,0.010262748,0.006321703,0.2172504],"study_design_scores_gemma":[0.0000027260141,0.000005189629,0.00011981219,0.0000032798448,0.00000434707,0.000008994273,0.000003769513,0.9964014,0.0013669144,0.001672299,0.00040729655,0.000003940997],"about_ca_topic_score_codex":0.012347672,"about_ca_topic_score_gemma":0.025759315,"teacher_disagreement_score":0.012347672,"about_ca_system_score_codex":0.00092624134,"about_ca_system_score_gemma":0.0010054547,"threshold_uncertainty_score":0.02455157},"labels":[],"label_agreement":null},{"id":"W4402262640","doi":"10.1109/igarss53475.2024.10640380","title":"Historical Cumulative Change Detection in Land Cover Using Time Series PolSAR Data Based on a Difference Matrix","year":2024,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Ministry of Natural Resources","keywords":"Change detection; Land cover; Series (stratigraphy); Cover (algebra); Time series; Matrix (chemical analysis); Computer science; Remote sensing; Artificial intelligence; Land use; Geology; Machine learning; Engineering","score_opus":0.08236473626783992,"score_gpt":0.2915340616408649,"score_spread":0.20916932537302502,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402262640","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55764,0.000622973,0.43187216,0.00014144658,0.000111447225,0.00016613207,0.0017376695,0.0034378339,0.0042703473],"genre_scores_gemma":[0.8629984,0.00023519968,0.13294885,0.000037880433,0.00005165272,0.00006488633,0.0022323616,0.0000637666,0.0013669456],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9996437,0.000034354816,0.000027323154,0.00014588403,0.0001181602,0.000030622847],"domain_scores_gemma":[0.99943155,0.00011916459,0.00012349972,0.000108168635,0.00018825138,0.000029250285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000494906,0.00047533613,0.0003692841,0.0032453942,0.00018423796,0.00054282823,0.0003872466,0.00025800394,0.0009870554],"category_scores_gemma":[0.0010602818,0.00014122136,0.00040534863,0.001670022,0.00023069493,0.0007352238,0.00033149158,0.0003384389,0.0006345486],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026983087,0.00029189757,0.07670665,0.00018934472,0.00024219105,0.00019569209,0.00021167356,0.028387073,0.088861,0.0013619357,0.0033611692,0.7999215],"study_design_scores_gemma":[0.000020846113,0.0002310664,0.19580112,0.000027024305,0.00011659096,0.0007520255,0.0002966862,0.73505527,0.05857225,0.0020386747,0.007016244,0.00007222058],"about_ca_topic_score_codex":0.0024628758,"about_ca_topic_score_gemma":0.0060697617,"teacher_disagreement_score":0.0032453942,"about_ca_system_score_codex":0.0002668104,"about_ca_system_score_gemma":0.00026250372,"threshold_uncertainty_score":0.004897058},"labels":[],"label_agreement":null},{"id":"W4402308593","doi":"10.18280/ts.410410","title":"Spectral Similarity Based Multiscale Spatial-Spectral Preprocessing Framework for Hyperspectral Image Classification","year":2024,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Hyperspectral imaging; Preprocessor; Pattern recognition (psychology); Similarity (geometry); Artificial intelligence; Full spectral imaging; Computer science; Image (mathematics); Mathematics; Remote sensing; Geology","score_opus":0.02909131623380311,"score_gpt":0.2748347191545745,"score_spread":0.2457434029207714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402308593","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008312271,0.00026799104,0.9901299,0.00007290447,0.000028525634,0.000024996945,0.00006492055,0.00031994865,0.0007785467],"genre_scores_gemma":[0.35805327,0.0010686092,0.63101584,0.00020293391,0.00024523,0.00016359297,0.0009325705,0.00017198846,0.008146026],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996413,0.0000517114,0.0000183536,0.00007404554,0.00017121858,0.00004336191],"domain_scores_gemma":[0.9997749,0.000030543673,0.000033647553,0.000035144894,0.00010870745,0.000017108956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037675767,0.00044525383,0.00077397807,0.0009983715,0.0002937994,0.0007072624,0.0009032927,0.0005869413,0.0021448806],"category_scores_gemma":[0.0005772821,0.00018055299,0.0008802783,0.0012104085,0.00030132508,0.0007170007,0.0008690779,0.00068677886,0.000946479],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022137813,0.00028795016,0.0012668327,0.00028095997,0.00015379333,0.00017538959,0.00011093229,0.09393912,0.1337925,0.029929278,0.00613164,0.7337102],"study_design_scores_gemma":[0.000006346192,0.00009682691,0.0013102392,0.000009486508,0.000044487166,0.00013503335,0.000029469855,0.9740737,0.01347799,0.0065540057,0.004243813,0.000018615532],"about_ca_topic_score_codex":0.0028539696,"about_ca_topic_score_gemma":0.004500821,"teacher_disagreement_score":0.0028539696,"about_ca_system_score_codex":0.00030084487,"about_ca_system_score_gemma":0.0007427662,"threshold_uncertainty_score":0.0071753263},"labels":[],"label_agreement":null},{"id":"W4402351422","doi":"10.1109/ijcnn60899.2024.10650176","title":"Hierarchical Multi-Label Classification with Missing Information for Benthic Habitat Imagery","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland; Dalhousie University","funders":"Alliance de recherche numérique du Canada; Canada First Research Excellence Fund; Ocean Frontier Institute","keywords":"Benthic habitat; Benthic zone; Computer science; Habitat; Multi-label classification; Environmental science; Artificial intelligence; Remote sensing; Data mining; Geography; Geology; Ecology; Oceanography","score_opus":0.043725425855644595,"score_gpt":0.27863551141666504,"score_spread":0.23491008556102044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402351422","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18629812,0.001014429,0.79358625,0.0009197406,0.0002584869,0.00028546792,0.0017111049,0.0122507475,0.0036757672],"genre_scores_gemma":[0.68861204,0.00015423623,0.29614085,0.000600989,0.00021154924,0.00024169622,0.007328967,0.00047728673,0.0062323646],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998164,0.0006488808,0.00006922629,0.00063290115,0.00029998782,0.00018499787],"domain_scores_gemma":[0.9939833,0.0027913898,0.00043048707,0.0016927721,0.0008913496,0.0002106929],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039009082,0.0014150154,0.0011727515,0.0014288424,0.0009879755,0.0010229201,0.0032271685,0.0018169156,0.001867007],"category_scores_gemma":[0.0077023646,0.00051093294,0.0011770659,0.0012809016,0.0010212731,0.0026319367,0.0016367558,0.0025053644,0.0016827568],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00063554937,0.0010630261,0.017581869,0.00029630229,0.00024933837,0.00026097524,0.0005105597,0.30082715,0.010688317,0.0026670601,0.021352476,0.64386743],"study_design_scores_gemma":[0.000015846148,0.000054756583,0.001258255,0.000012589499,0.000013629654,0.000029082861,0.00006115073,0.9916094,0.0033410254,0.0025841747,0.001007844,0.000012248844],"about_ca_topic_score_codex":0.010244434,"about_ca_topic_score_gemma":0.0182954,"teacher_disagreement_score":0.010244434,"about_ca_system_score_codex":0.0012792539,"about_ca_system_score_gemma":0.0012221221,"threshold_uncertainty_score":0.02063024},"labels":[],"label_agreement":null},{"id":"W4402461578","doi":"10.1016/j.rse.2024.114402","title":"DRMAT: A multivariate algorithm for detecting breakpoints in multispectral time series","year":2024,"lang":"en","type":"article","venue":"Remote Sensing of Environment","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Resources Canada; Canadian Forest Service","funders":"Ohio Agricultural Research and Development Center, Ohio State University; National Institute of Food and Agriculture; Lowe Syndrome Trust; Ohio Department of Higher Education; U.S. Geological Survey; U.S. Department of Agriculture; National Aeronautics and Space Administration","keywords":"Multispectral image; Remote sensing; Series (stratigraphy); Multivariate statistics; Algorithm; Computer science; Multispectral pattern recognition; Time series; Data mining; Geology; Machine learning","score_opus":0.009213438682920523,"score_gpt":0.21802927998188393,"score_spread":0.2088158412989634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402461578","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008171114,0.00013940866,0.9860124,0.00006433223,0.000052378196,0.000042913227,0.00036018944,0.0048260996,0.00033115598],"genre_scores_gemma":[0.07580027,0.00015318076,0.9188705,0.00009597132,0.0000927439,0.00017533811,0.0014655994,0.00058623275,0.0027601372],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994311,0.00009249767,0.000040939653,0.00016649565,0.00020959131,0.000059385675],"domain_scores_gemma":[0.9993943,0.00017798056,0.0001105624,0.00011858007,0.00015829541,0.00004023817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010008157,0.0011430782,0.0008818196,0.0024056288,0.00057986676,0.00093658664,0.0014910664,0.0010811914,0.0057497313],"category_scores_gemma":[0.0024400486,0.000443855,0.0011417413,0.0015124766,0.00038293787,0.001364106,0.0013334468,0.0015138584,0.0027734493],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037562303,0.00014896676,0.0021035976,0.000096627904,0.0001331027,0.00006339951,0.000051854935,0.030052237,0.025354428,0.0027827576,0.007659575,0.93117785],"study_design_scores_gemma":[0.00006678573,0.0001682797,0.0054690107,0.000018135876,0.00006537336,0.00020418063,0.000043348824,0.95786214,0.01935189,0.0041376697,0.012558672,0.000054510958],"about_ca_topic_score_codex":0.0031090956,"about_ca_topic_score_gemma":0.0049850666,"teacher_disagreement_score":0.0057497313,"about_ca_system_score_codex":0.0003761741,"about_ca_system_score_gemma":0.00070385705,"threshold_uncertainty_score":0.019234776},"labels":[],"label_agreement":null},{"id":"W4402469225","doi":"10.14796/jwmm.h524","title":"Statistical comparison of simple and machine learning based land use and land cover classification algorithms: A case study","year":2024,"lang":"en","type":"article","venue":"Journal of Water Management Modeling","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Support vector machine; Land cover; Artificial intelligence; Random forest; Cohen's kappa; Algorithm; Mathematics; Machine learning; Computer science; Classifier (UML); Boundary (topology); Pattern recognition (psychology); Statistics; Land use; Engineering","score_opus":0.06950683480333616,"score_gpt":0.29733879975112354,"score_spread":0.22783196494778737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402469225","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95266956,0.0008369546,0.043413974,0.00022295592,0.00006618675,0.00020640729,0.0006203044,0.00022425565,0.0017393533],"genre_scores_gemma":[0.9697207,0.00020331614,0.028615149,0.000033139237,0.000041270978,0.00013100375,0.0006661068,0.000045874465,0.00054326165],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9933561,0.003264907,0.00056982,0.0010194262,0.0015111987,0.00027851597],"domain_scores_gemma":[0.97782063,0.015269517,0.0014315206,0.0013193742,0.003913573,0.00024530085],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012471294,0.0008143201,0.0007872866,0.0024237519,0.00044366717,0.0016684661,0.0009373208,0.0009886011,0.0007590287],"category_scores_gemma":[0.019339332,0.00023742986,0.0013958007,0.0020950125,0.0008793113,0.0015646196,0.0007509953,0.00069189654,0.0002907166],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018559704,0.0014806248,0.46684334,0.00080143625,0.0015093378,0.0011980715,0.0012204761,0.20994246,0.0060395114,0.0054171346,0.0045272084,0.29916447],"study_design_scores_gemma":[0.000072876464,0.0020859076,0.16129762,0.0001003996,0.00033133908,0.00080640154,0.0018229986,0.8181073,0.006772697,0.0040952414,0.004396929,0.000110269815],"about_ca_topic_score_codex":0.004429028,"about_ca_topic_score_gemma":0.0040226937,"teacher_disagreement_score":0.012471294,"about_ca_system_score_codex":0.001059477,"about_ca_system_score_gemma":0.0006990913,"threshold_uncertainty_score":0.06595528},"labels":[],"label_agreement":null},{"id":"W4402679099","doi":"10.1080/2150704x.2024.2399864","title":"Classification of hyperspectral and LiDAR data by transformer-based enhancement","year":2024,"lang":"en","type":"article","venue":"Remote Sensing Letters","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Natural Science Foundation of China; Ministry of Natural Resources","keywords":"Hyperspectral imaging; Lidar; Remote sensing; Transformer; Computer science; Artificial intelligence; Environmental science; Geology; Engineering; Voltage","score_opus":0.02604050940488013,"score_gpt":0.25089042839100606,"score_spread":0.22484991898612594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402679099","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15632975,0.000494235,0.8369204,0.00019003788,0.00008606473,0.00012637083,0.0002640791,0.0019275645,0.0036614311],"genre_scores_gemma":[0.82009524,0.00031947572,0.17417464,0.00024139773,0.000048025144,0.000079222,0.0010427582,0.000099190824,0.0039001855],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999728,0.000033298482,0.000011679349,0.00007775233,0.00009444332,0.00005481966],"domain_scores_gemma":[0.9997545,0.00005071835,0.000027645896,0.00003307705,0.00011595306,0.000018139493],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066813314,0.00068904035,0.00047409942,0.00096794224,0.00020976046,0.00045773285,0.0008084664,0.0004404026,0.0013249619],"category_scores_gemma":[0.0008596375,0.00018138904,0.0008021019,0.00077702495,0.0004217976,0.0012632494,0.0013487532,0.00062084204,0.0005473979],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004631175,0.0003657145,0.005020273,0.00014190443,0.0001039591,0.0001451098,0.00018617033,0.044735778,0.13359506,0.0034170689,0.00408547,0.80774033],"study_design_scores_gemma":[0.000014141843,0.00013680226,0.0032058987,0.000011212122,0.000056781733,0.00019477766,0.000104169805,0.934248,0.05657562,0.0033459747,0.002086136,0.000020388039],"about_ca_topic_score_codex":0.0021189929,"about_ca_topic_score_gemma":0.003417013,"teacher_disagreement_score":0.0021189929,"about_ca_system_score_codex":0.00036107923,"about_ca_system_score_gemma":0.0004454481,"threshold_uncertainty_score":0.00443238},"labels":[],"label_agreement":null},{"id":"W4403147695","doi":"10.54021/seesv5n2-293","title":"Change detection in remote sensing image using a modified logarithmic mean-based thresholding","year":2024,"lang":"en","type":"article","venue":"STUDIES IN ENGINEERING AND EXACT SCIENCES","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Thresholding; Change detection; Logarithm; Logarithmic mean; Artificial intelligence; Remote sensing; Image (mathematics); Pattern recognition (psychology); Mathematics; Computer science; Computer vision; Statistics; Geography; Mathematical analysis","score_opus":0.08847914473464193,"score_gpt":0.3144764764397421,"score_spread":0.22599733170510017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403147695","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05455751,0.00080017524,0.9401035,0.00016493333,0.00013258857,0.00010357758,0.00023700958,0.0019436184,0.0019571763],"genre_scores_gemma":[0.38646284,0.00050624396,0.6098205,0.0001923437,0.00014114892,0.00012430538,0.00076577475,0.00026861398,0.0017182231],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99916506,0.00007406972,0.00006496297,0.000278529,0.00034133537,0.00007607482],"domain_scores_gemma":[0.9991252,0.00027950053,0.00013771406,0.00013999084,0.0002819827,0.00003566603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084501144,0.00058722106,0.00089340855,0.0027775827,0.00034810643,0.0012194187,0.0011781355,0.00065217254,0.0011675557],"category_scores_gemma":[0.0024311,0.00029144174,0.0010021223,0.0022392718,0.00061770703,0.0012875937,0.00074935466,0.0008451581,0.0006263876],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038291252,0.0001778956,0.010308783,0.00042840003,0.0001811068,0.00024407939,0.00021496939,0.03011819,0.14603454,0.0031606033,0.0029337162,0.8058148],"study_design_scores_gemma":[0.00004543917,0.00027340103,0.024407113,0.000054305983,0.00016834981,0.0010249153,0.00015319978,0.8503223,0.10751025,0.0050646514,0.010868301,0.00010780965],"about_ca_topic_score_codex":0.0019694283,"about_ca_topic_score_gemma":0.0031121387,"teacher_disagreement_score":0.0027775827,"about_ca_system_score_codex":0.00047553552,"about_ca_system_score_gemma":0.00050736615,"threshold_uncertainty_score":0.004468918},"labels":[],"label_agreement":null},{"id":"W4403331717","doi":"10.23919/fusion59988.2024.10706502","title":"Leveraging Generative Deep Learning Models for Enhanced Change Detection in Heterogeneous Remote Sensing Data","year":2024,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Space Agency","keywords":"Computer science; Generative grammar; Change detection; Generative model; Deep learning; Data modeling; Artificial intelligence; Remote sensing; Machine learning; Data science; Geography; Database","score_opus":0.10778591497127073,"score_gpt":0.2840511133610563,"score_spread":0.1762651983897856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403331717","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034315616,0.00033857606,0.96321064,0.00018793608,0.000036502555,0.000029634766,0.00009654544,0.000901529,0.00088307227],"genre_scores_gemma":[0.79543,0.00032126365,0.2003181,0.00038413535,0.00010694719,0.000057174762,0.00064539374,0.0001818775,0.00255506],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996244,0.00008334692,0.000015151786,0.00012697195,0.00009659075,0.00005348368],"domain_scores_gemma":[0.9992957,0.00034101788,0.000109102664,0.00014020578,0.00007906608,0.00003477473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00086932845,0.00082030677,0.000698628,0.0009845579,0.00018133732,0.0006693623,0.0011106541,0.00075515447,0.000771573],"category_scores_gemma":[0.001896013,0.00035835206,0.000770389,0.00076855544,0.00061900716,0.0011394416,0.0011650354,0.0012528569,0.0003739785],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019025024,0.00014593852,0.0052599115,0.00012739016,0.00019586571,0.00029880085,0.00017871762,0.63502973,0.025554437,0.007967312,0.0026780083,0.3223737],"study_design_scores_gemma":[0.000001807231,0.000010739689,0.00037716777,0.0000032341065,0.0000078145495,0.000037206613,0.000009177176,0.9950363,0.0021980435,0.0019632056,0.0003508789,0.0000043866803],"about_ca_topic_score_codex":0.0020799935,"about_ca_topic_score_gemma":0.003391132,"teacher_disagreement_score":0.0020799935,"about_ca_system_score_codex":0.0004596679,"about_ca_system_score_gemma":0.00033481375,"threshold_uncertainty_score":0.0045975447},"labels":[],"label_agreement":null},{"id":"W4403775011","doi":"10.3390/rs16213961","title":"Multi-Scale and Multi-Network Deep Feature Fusion for Discriminative Scene Classification of High-Resolution Remote Sensing Images","year":2024,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"City University of Hong Kong","keywords":"Discriminative model; Remote sensing; Artificial intelligence; Computer science; High resolution; Pattern recognition (psychology); Scale (ratio); Feature (linguistics); Image fusion; Fusion; Computer vision; Geology; Cartography; Image (mathematics); Geography","score_opus":0.02637440067172655,"score_gpt":0.2697393227894569,"score_spread":0.24336492211773034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403775011","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11145298,0.0016090767,0.87892014,0.00034417736,0.0002025614,0.00010852985,0.0006400871,0.0034607488,0.0032617555],"genre_scores_gemma":[0.81247795,0.0006497929,0.17864016,0.0002690553,0.00011195439,0.0000856835,0.002225113,0.00013134886,0.0054089767],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99959034,0.00005305129,0.000018801133,0.00012866572,0.0001316204,0.00007740324],"domain_scores_gemma":[0.99972767,0.00004386027,0.000037019527,0.000059501384,0.00011069194,0.000021219757],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080098526,0.0011975231,0.0008465395,0.0011475125,0.00029962033,0.00056409376,0.0010510655,0.0006135859,0.0012515588],"category_scores_gemma":[0.0008304382,0.000315963,0.0011143979,0.0010100285,0.00035524112,0.001211944,0.0009988182,0.001108783,0.0004941146],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033411023,0.000341375,0.004156741,0.000115601644,0.00029053062,0.00020125764,0.00008397311,0.20793968,0.040695313,0.0034653004,0.009421976,0.7329542],"study_design_scores_gemma":[0.00000560262,0.000042013042,0.0013700208,0.000005962707,0.000030460498,0.00004161293,0.000016576367,0.9887989,0.0072413534,0.001191031,0.0012446292,0.000011867524],"about_ca_topic_score_codex":0.010356347,"about_ca_topic_score_gemma":0.013599781,"teacher_disagreement_score":0.010356347,"about_ca_system_score_codex":0.00074347894,"about_ca_system_score_gemma":0.00077761087,"threshold_uncertainty_score":0.020592093},"labels":[],"label_agreement":null},{"id":"W4403827183","doi":"10.1109/tgrs.2024.3486787","title":"A Multitask CNN-Transformer Network for Semantic Change Detection From Bitemporal Remote Sensing Images","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Science Foundation of Jiangxi Province; National Natural Science Foundation of China","keywords":"Computer science; Change detection; Remote sensing; Transformer; Artificial intelligence; Geology","score_opus":0.026887943481739958,"score_gpt":0.25162542971169244,"score_spread":0.2247374862299525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403827183","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13037254,0.001369667,0.84228784,0.0008557338,0.0003495113,0.0002606377,0.0027862163,0.01239553,0.009322385],"genre_scores_gemma":[0.7038868,0.00064626534,0.26961973,0.0005450485,0.00013922343,0.00022472341,0.00808246,0.00034365125,0.016512182],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99981385,0.000018737239,0.000008041758,0.000080072095,0.000041472576,0.000037854163],"domain_scores_gemma":[0.99985707,0.000031593892,0.000014855594,0.000029980461,0.000047882513,0.000018558305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036278352,0.0010953153,0.0004990349,0.0006503065,0.00030623435,0.0005310947,0.0015630412,0.0007990417,0.0033043944],"category_scores_gemma":[0.0008182937,0.00033180648,0.00069668936,0.00056061056,0.00030542753,0.0011964138,0.0008727201,0.0008123523,0.0011148523],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041950934,0.00031753912,0.003914628,0.00021949872,0.00026574256,0.000342767,0.00009633699,0.20272446,0.041307464,0.005154031,0.02220136,0.7230367],"study_design_scores_gemma":[0.00001132777,0.00006116316,0.00076281605,0.0000074355535,0.000026192174,0.000053303676,0.000017919385,0.98780406,0.00698543,0.0021743919,0.0020849917,0.000011019133],"about_ca_topic_score_codex":0.01634025,"about_ca_topic_score_gemma":0.029117286,"teacher_disagreement_score":0.01634025,"about_ca_system_score_codex":0.0010411246,"about_ca_system_score_gemma":0.0009474642,"threshold_uncertainty_score":0.032490313},"labels":[],"label_agreement":null},{"id":"W4403867810","doi":"10.3390/rs16214015","title":"How to Learn More? Exploring Kolmogorov–Arnold Networks for Hyperspectral Image Classification","year":2024,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":74,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Hyperspectral imaging; Computer science; Artificial intelligence; Remote sensing; Pattern recognition (psychology); Geology","score_opus":0.05126473338752103,"score_gpt":0.2620400992997386,"score_spread":0.21077536591221757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403867810","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11481795,0.0022961006,0.8752852,0.0011337628,0.00009423892,0.000036099,0.000117282005,0.000800681,0.0054187044],"genre_scores_gemma":[0.81315744,0.0013451438,0.17903337,0.00034096232,0.000101241334,0.00006243475,0.00029193997,0.00008599488,0.0055814963],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99982953,0.000040407005,0.000011816216,0.0000459227,0.00004899143,0.000023354578],"domain_scores_gemma":[0.99960953,0.00019523826,0.000055087447,0.00004114613,0.00007275288,0.000026281989],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047019584,0.0005410623,0.00040005427,0.0005447348,0.00021041246,0.00070052355,0.0006230521,0.00065555476,0.0009416838],"category_scores_gemma":[0.001536313,0.0003077243,0.00050040573,0.0005064809,0.0006635067,0.0016895867,0.0008339527,0.0009790019,0.00029883327],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009735652,0.000062710744,0.00402566,0.00014034321,0.00008268452,0.00012210195,0.00014437459,0.7235158,0.0104052005,0.030396799,0.0026201939,0.22838683],"study_design_scores_gemma":[0.0000017819273,0.000010061175,0.00013406204,0.000004215511,0.0000036991928,0.000009207172,0.000008689752,0.9934582,0.0007440497,0.0052585136,0.00036339724,0.000004057963],"about_ca_topic_score_codex":0.0045966795,"about_ca_topic_score_gemma":0.005662571,"teacher_disagreement_score":0.0045966795,"about_ca_system_score_codex":0.0005486432,"about_ca_system_score_gemma":0.0005680277,"threshold_uncertainty_score":0.009139836},"labels":[],"label_agreement":null},{"id":"W4404366829","doi":"10.18280/ts.410526","title":"Classification of Satellite Images Using a Deep Learning-Inspired Hybrid Novel Approach","year":2024,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Deep learning; Artificial intelligence; Computer science; Satellite; Remote sensing; Pattern recognition (psychology); Computer vision; Geology; Engineering","score_opus":0.03276949814706344,"score_gpt":0.24224183270654237,"score_spread":0.20947233455947895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404366829","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2499746,0.0010759375,0.7400142,0.00059601944,0.00014193785,0.00014101606,0.0003733752,0.002577638,0.0051052864],"genre_scores_gemma":[0.84351075,0.000310137,0.14877173,0.00030652175,0.000066582754,0.00010463755,0.0008707967,0.000042986147,0.0060158134],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997092,0.000037563455,0.000017320559,0.000089700545,0.00008100245,0.000065146545],"domain_scores_gemma":[0.9997819,0.000048912163,0.00002601682,0.000032222157,0.00009195474,0.00001902981],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004500774,0.0007716755,0.00055011513,0.0010113448,0.00027635598,0.0006697343,0.0011455449,0.0008380441,0.0008669535],"category_scores_gemma":[0.000542148,0.00027926336,0.0007449765,0.0008261383,0.00034133394,0.0007850328,0.00072153046,0.0007313005,0.0003971957],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029447145,0.00058678695,0.005704457,0.000103892606,0.00025262148,0.00015003055,0.00009699383,0.35470915,0.039396856,0.003416393,0.0043739984,0.59091437],"study_design_scores_gemma":[0.0000028039647,0.00003081661,0.00040407004,0.0000025987667,0.000008743563,0.000015023557,0.00000742225,0.9964474,0.0023393854,0.00046237302,0.0002754398,0.000004012585],"about_ca_topic_score_codex":0.007666992,"about_ca_topic_score_gemma":0.011724843,"teacher_disagreement_score":0.007666992,"about_ca_system_score_codex":0.0007850848,"about_ca_system_score_gemma":0.0005762461,"threshold_uncertainty_score":0.015244782},"labels":[],"label_agreement":null},{"id":"W4404484255","doi":"10.1080/07038992.2024.2418091","title":"FMCNet: A Fuzzy Multiscale Convolution Network for Remote Sensing Image Segmentation","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Segmentation; Fuzzy logic; Convolution (computer science); Geography; Artificial intelligence; Remote sensing; Image (mathematics); Computer science; Image segmentation; Computer vision; Cartography; Pattern recognition (psychology); Artificial neural network","score_opus":0.01674080210555011,"score_gpt":0.2411900327288159,"score_spread":0.22444923062326577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404484255","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041710433,0.000907441,0.9519797,0.00023467664,0.000131659,0.000078266785,0.00025046588,0.0022078159,0.0024995834],"genre_scores_gemma":[0.5367729,0.00068865897,0.45441106,0.00034923592,0.000112352376,0.00014343306,0.0009779276,0.00014829553,0.006396138],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997002,0.00003775396,0.000018444296,0.00008957715,0.00010844523,0.00004554657],"domain_scores_gemma":[0.9997749,0.000061619125,0.000029269655,0.000024173836,0.00009538242,0.000014697312],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071135606,0.0006794844,0.00075301586,0.00090935663,0.00036435935,0.0005202886,0.0011358941,0.001101978,0.0016968538],"category_scores_gemma":[0.0011523317,0.00029062876,0.0007586667,0.0009616159,0.00031003833,0.00085883273,0.00058757013,0.0007505539,0.000352179],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030947654,0.00015737911,0.0018238937,0.00012624812,0.00015583885,0.00014126583,0.000049084592,0.30401546,0.02621315,0.0034927358,0.0059802434,0.65753525],"study_design_scores_gemma":[0.0000037764642,0.000015869591,0.00026745582,0.0000041143135,0.000008045139,0.00002520599,0.0000031865225,0.9963025,0.0024379839,0.0004956181,0.0004311622,0.0000050767453],"about_ca_topic_score_codex":0.0148379905,"about_ca_topic_score_gemma":0.013808307,"teacher_disagreement_score":0.0148379905,"about_ca_system_score_codex":0.0009406373,"about_ca_system_score_gemma":0.0009407552,"threshold_uncertainty_score":0.029503226},"labels":[],"label_agreement":null},{"id":"W4404763830","doi":"10.1016/j.eswa.2024.125962","title":"Graph-Transformer with spatial-spectral features fusion for hyperspectral image classification","year":2024,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Canadian Stroke Consortium; China Scholarship Council; National Natural Science Foundation of China; McGill University","keywords":"Hyperspectral imaging; Computer science; Pattern recognition (psychology); Artificial intelligence; Graph; Fusion; Transformer; Theoretical computer science; Physics","score_opus":0.011569077002822914,"score_gpt":0.24327598641237574,"score_spread":0.23170690940955282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404763830","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05634556,0.00044629065,0.9356364,0.00023518527,0.0000916392,0.00010188714,0.00036511468,0.0035693652,0.0032086808],"genre_scores_gemma":[0.77680755,0.00037477625,0.21623282,0.00023244548,0.000059546826,0.00008897736,0.0015565497,0.00016896341,0.004478338],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996747,0.000052832896,0.000015466665,0.00009345633,0.00011700594,0.000046581088],"domain_scores_gemma":[0.99972147,0.00006628001,0.00003403931,0.000053758427,0.00009856742,0.000025886606],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005022762,0.0009815258,0.0006185734,0.0015356635,0.0003512544,0.0006013789,0.0012391413,0.0006445515,0.0021059748],"category_scores_gemma":[0.0011628418,0.00023047991,0.0009429869,0.001638427,0.0004488888,0.0018573331,0.0010280331,0.00080066704,0.00077208335],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030424117,0.00026577315,0.0030411894,0.00013364665,0.00014649797,0.0001610092,0.000099565186,0.20870984,0.027630359,0.0092901215,0.007824787,0.7423931],"study_design_scores_gemma":[0.000008369072,0.00005268699,0.00065627764,0.0000047496633,0.000030764568,0.000065994915,0.000032800726,0.9807668,0.009271071,0.007599143,0.0014996572,0.0000116931715],"about_ca_topic_score_codex":0.006886373,"about_ca_topic_score_gemma":0.009463879,"teacher_disagreement_score":0.006886373,"about_ca_system_score_codex":0.0008459206,"about_ca_system_score_gemma":0.0007572215,"threshold_uncertainty_score":0.013692558},"labels":[],"label_agreement":null},{"id":"W4404914900","doi":"10.1109/tgrs.2024.3509735","title":"SECBNet: Semantic Segmentation-Enhanced Color Balance Network for Optical Satellite Images","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Fundamental Research Funds for Central Universities of the Central South University; Natural Science Foundation of Fujian Province; National Natural Science Foundation of China","keywords":"Computer science; Segmentation; Artificial intelligence; Satellite; Image segmentation; Remote sensing; Balance (ability); Computer vision; Pattern recognition (psychology); Geology; Astronomy","score_opus":0.012599642878496351,"score_gpt":0.24776458730658016,"score_spread":0.2351649444280838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404914900","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16430266,0.0013065138,0.76827645,0.00061764504,0.00035227378,0.0008924225,0.013909671,0.03598772,0.014354551],"genre_scores_gemma":[0.5236655,0.00075348443,0.40915814,0.00055471284,0.00015004961,0.000888711,0.050901897,0.0011482994,0.012779297],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99967384,0.00003754723,0.00001435878,0.00010938726,0.0001132095,0.000051664432],"domain_scores_gemma":[0.9997482,0.000034409622,0.000037537025,0.000059579546,0.000095780764,0.000024444658],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056168507,0.0013928402,0.000578154,0.001978354,0.0005487109,0.0008853007,0.0013794735,0.0006546083,0.0027702134],"category_scores_gemma":[0.0012711793,0.00032745567,0.0005446982,0.0014217569,0.00039121913,0.0016721835,0.0013445978,0.0007418741,0.0012837889],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014715233,0.00056295615,0.0074315495,0.00039037922,0.00018848364,0.00019917353,0.00018544169,0.113582246,0.04996755,0.008844866,0.052954867,0.76422095],"study_design_scores_gemma":[0.00007628413,0.00019457036,0.00388492,0.00003691277,0.00005033017,0.00015683626,0.00011913508,0.9310374,0.03523383,0.008184917,0.020983504,0.000041307594],"about_ca_topic_score_codex":0.008656884,"about_ca_topic_score_gemma":0.012970527,"teacher_disagreement_score":0.008656884,"about_ca_system_score_codex":0.0012471926,"about_ca_system_score_gemma":0.0007756116,"threshold_uncertainty_score":0.017212987},"labels":[],"label_agreement":null},{"id":"W4405318641","doi":"10.1080/07038992.2024.2430490","title":"Building Detection and Outlining in Multi-Modal Remote Sensor Data: A Stratified Approach","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Remote sensing; Geography; Modal; Environmental science; Computer science; Cartography","score_opus":0.05519897207380312,"score_gpt":0.2733519527800273,"score_spread":0.21815298070622416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405318641","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060574193,0.00012648787,0.9373222,0.000047397632,0.000009092753,0.0001379957,0.00026537417,0.0010349462,0.00048242556],"genre_scores_gemma":[0.38461378,0.00012079791,0.6117621,0.00007497924,0.000022154267,0.00019591139,0.0019174687,0.00018736116,0.0011054393],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880576,0.00023890303,0.000100314704,0.00032234273,0.0003393658,0.00019331925],"domain_scores_gemma":[0.9985469,0.0003821454,0.0001618154,0.0004310586,0.00041386104,0.00006417118],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016486659,0.0009131143,0.0009345872,0.00297647,0.00043148937,0.0015555514,0.0013089123,0.001028087,0.00072408153],"category_scores_gemma":[0.0025425896,0.0005966213,0.0013259054,0.0015906352,0.0006446873,0.0014018593,0.0017813033,0.00071396783,0.00086014054],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005242628,0.000492272,0.020101925,0.0002263865,0.00028503238,0.00042409397,0.0009133353,0.25948006,0.12749805,0.0060061645,0.0019983312,0.5820501],"study_design_scores_gemma":[0.000011872648,0.0001364953,0.010643763,0.000018860392,0.000052302617,0.00017464343,0.0002255515,0.96127725,0.021368459,0.0039181393,0.0021244579,0.000048138692],"about_ca_topic_score_codex":0.0059616566,"about_ca_topic_score_gemma":0.011688244,"teacher_disagreement_score":0.0059616566,"about_ca_system_score_codex":0.0005192868,"about_ca_system_score_gemma":0.0009123624,"threshold_uncertainty_score":0.011853933},"labels":[],"label_agreement":null},{"id":"W4405452871","doi":"10.1017/pasa.2024.118","title":"Selecting variable sources with median colours using a self-organising map","year":2024,"lang":"en","type":"article","venue":"Publications of the Astronomical Society of Australia","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"U.S. Department of Energy; U.S. Naval Observatory; Case Western Reserve University; National Science Foundation; Fermilab; Max-Planck-Institut für Astronomie; Max-Planck-Gesellschaft; Chinese Academy of Sciences; National Research Foundation of Korea; New Mexico State University; University of Portsmouth; Universität Basel; University of Pittsburgh; Los Alamos National Laboratory; Alfred P. Sloan Foundation; University of Washington; Princeton University; Johns Hopkins University; National Research Foundation; Ohio State University; California Institute of Technology; Ministry of Science and ICT, South Korea; Drexel University; National Aeronautics and Space Administration","keywords":"Physics; Variable (mathematics); Astronomy; Astrophysics; Mathematics","score_opus":0.021301101815512608,"score_gpt":0.24099622651728786,"score_spread":0.21969512470177524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405452871","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48030356,0.0005669198,0.49760583,0.00036579778,0.00015151888,0.0004643739,0.00425667,0.009416562,0.0068688616],"genre_scores_gemma":[0.66038686,0.00016585394,0.32796603,0.00011537379,0.00008180321,0.00027734175,0.007596073,0.0006416159,0.0027690104],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99943036,0.00010231553,0.00003438737,0.00016370321,0.00016796724,0.00010118931],"domain_scores_gemma":[0.9978383,0.0008929712,0.00020445275,0.00028556646,0.0006341396,0.00014461883],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014696298,0.0006681147,0.00073771254,0.0045193783,0.00055220805,0.0019511572,0.0011101558,0.00086735474,0.0027563744],"category_scores_gemma":[0.005474407,0.00027727228,0.0010672809,0.002704315,0.00048681887,0.00090052816,0.0015814903,0.00061175704,0.0018110701],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015708755,0.00061936234,0.13985364,0.00094207376,0.0005639103,0.00068241055,0.0017784477,0.08357356,0.041217342,0.0053911014,0.023641603,0.7001656],"study_design_scores_gemma":[0.00016343087,0.00017934416,0.053142764,0.00018511552,0.00015835385,0.00035185434,0.0008515001,0.8967702,0.016561523,0.019982295,0.0115569895,0.00009662849],"about_ca_topic_score_codex":0.0040634284,"about_ca_topic_score_gemma":0.004680247,"teacher_disagreement_score":0.0045193783,"about_ca_system_score_codex":0.00041126017,"about_ca_system_score_gemma":0.0006772014,"threshold_uncertainty_score":0.009221017},"labels":[],"label_agreement":null},{"id":"W4405751093","doi":"10.18280/isi.290624","title":"Hyperspectral Image Classification Using Hybrid Swarm Feature Selection and Ensemble Classifier","year":2024,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Hyperspectral imaging; Pattern recognition (psychology); Feature selection; Artificial intelligence; Classifier (UML); Computer science; Contextual image classification; Ensemble learning; Machine learning; Image (mathematics)","score_opus":0.018067749558016936,"score_gpt":0.23674413687668475,"score_spread":0.21867638731866781,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405751093","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14396195,0.00046317,0.8520379,0.00016789342,0.00022109538,0.000081029,0.00014994912,0.00086096517,0.0020560545],"genre_scores_gemma":[0.8089378,0.00029789662,0.18548298,0.00009789294,0.00017143445,0.0001522841,0.0006089007,0.000071063674,0.0041797855],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994578,0.0000841074,0.000042585525,0.00012112274,0.00023026655,0.00006413301],"domain_scores_gemma":[0.99933004,0.00018565307,0.000054009994,0.0000807538,0.0003191585,0.000030449482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084471685,0.0008516439,0.0014713025,0.0011322643,0.00057502615,0.0006390806,0.0005828472,0.00064417504,0.0007683226],"category_scores_gemma":[0.0012060433,0.00027132788,0.0010023925,0.00111347,0.00021097275,0.001030408,0.0006281102,0.0005580359,0.00027267847],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034149777,0.00037363375,0.00838894,0.000075918106,0.00032589925,0.00013847945,0.00011599159,0.18672863,0.042461663,0.0013447788,0.0048592943,0.75484526],"study_design_scores_gemma":[0.000007423163,0.00004224284,0.0016315089,0.0000025707425,0.000034583503,0.000029993991,0.000013790718,0.9946331,0.0029854001,0.00028524426,0.00032630673,0.000007858876],"about_ca_topic_score_codex":0.003949539,"about_ca_topic_score_gemma":0.0035266664,"teacher_disagreement_score":0.003949539,"about_ca_system_score_codex":0.00028957054,"about_ca_system_score_gemma":0.00050834083,"threshold_uncertainty_score":0.00785315},"labels":[],"label_agreement":null},{"id":"W4405882677","doi":"10.1007/978-981-96-2061-6_30","title":"MLP-AMDC: A MLP Architecture for Adaptive-Mask-Based Dual-Camera Snapshot Hyperspectral Imaging","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ministry of Education and Child Care","funders":"","keywords":"Computer science; Hyperspectral imaging; Snapshot (computer storage); Computer vision; Artificial intelligence; Architecture; Dual (grammatical number); Computer graphics (images)","score_opus":0.018012777113394187,"score_gpt":0.23717348832073015,"score_spread":0.21916071120733596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405882677","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007933604,0.0008496162,0.98235774,0.0001779848,0.000202833,0.00004647654,0.0003997109,0.0042355284,0.00379658],"genre_scores_gemma":[0.15442258,0.0009086258,0.82277846,0.00033590297,0.0001711974,0.00015345713,0.0012200002,0.00045708666,0.019552795],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9997342,0.0000318939,0.000012845074,0.00007687878,0.00011225367,0.000031878662],"domain_scores_gemma":[0.99969065,0.00006283485,0.000015512616,0.000057664514,0.00014643854,0.000026881424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044135682,0.0008457848,0.0005685531,0.00046665405,0.00039669825,0.0008422177,0.0023201052,0.0012552405,0.007280815],"category_scores_gemma":[0.00095051486,0.0005084329,0.0005068482,0.0006597863,0.00035052045,0.0010153634,0.0010776628,0.0015986062,0.003726232],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028586076,0.00011269868,0.00044006514,0.00020108424,0.00013314924,0.00011545237,0.000047503992,0.07347959,0.066076934,0.004838566,0.020468347,0.83380073],"study_design_scores_gemma":[0.000009109683,0.000044126326,0.00039588285,0.0000205956,0.000027980059,0.0000798135,0.000006880318,0.96954197,0.020393236,0.0017767104,0.0076819314,0.000021685082],"about_ca_topic_score_codex":0.006258388,"about_ca_topic_score_gemma":0.011272528,"teacher_disagreement_score":0.007280815,"about_ca_system_score_codex":0.00072286744,"about_ca_system_score_gemma":0.00071669085,"threshold_uncertainty_score":0.024356782},"labels":[],"label_agreement":null},{"id":"W4405909274","doi":"10.1109/wf-iot62078.2024.10811453","title":"Optimizing Satellite Imagery Object Detection in Challenging Weather Conditions using IoT-Driven Fusion Strategies","year":2024,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Satellite; Internet of Things; Fusion; Object detection; Sensor fusion; Remote sensing; Object (grammar); Artificial intelligence; Satellite imagery; Computer vision; Geology; Aerospace engineering; Pattern recognition (psychology); Engineering; Embedded system","score_opus":0.024035842366493487,"score_gpt":0.2642413351137389,"score_spread":0.2402054927472454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405909274","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3169245,0.00024098286,0.6777467,0.0002688931,0.00006885889,0.00007655167,0.00012016846,0.0010457352,0.0035076144],"genre_scores_gemma":[0.9198019,0.00006136703,0.07932499,0.00007534228,0.000013712541,0.00003387552,0.00014995322,0.00006058126,0.00047832343],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996191,0.00005949186,0.000019789408,0.000112823174,0.00010343416,0.000085284984],"domain_scores_gemma":[0.99948823,0.00019337905,0.00007000192,0.000060345832,0.0001491228,0.000038766648],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010339012,0.00080917234,0.00050348387,0.00058569515,0.00039901675,0.00081897085,0.0008122764,0.0006618312,0.00071453076],"category_scores_gemma":[0.0026482039,0.00029782072,0.00060222007,0.00048923603,0.00051416253,0.0014273823,0.0008535149,0.00064439885,0.00022073892],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017624833,0.00013978337,0.007913971,0.00006765234,0.00007690986,0.00012867173,0.00014324105,0.88046855,0.022708911,0.0028594877,0.00091151113,0.08440497],"study_design_scores_gemma":[0.0000049004807,0.000023173734,0.000922305,0.0000026738142,0.00000764083,0.000016789021,0.000023702341,0.9938962,0.0038316755,0.0011108737,0.00015488375,0.000005322375],"about_ca_topic_score_codex":0.0071736816,"about_ca_topic_score_gemma":0.0061270306,"teacher_disagreement_score":0.0071736816,"about_ca_system_score_codex":0.0006203262,"about_ca_system_score_gemma":0.00071396306,"threshold_uncertainty_score":0.014263868},"labels":[],"label_agreement":null},{"id":"W4406244347","doi":"10.1080/07038992.2024.2448169","title":"Machine learning approaches to Landsat change detection analysis","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Natural Resources Canada; Canadian Forest Service; University of Ottawa","funders":"University of Ottawa","keywords":"Change detection; Machine learning; Artificial intelligence; Computer science; Generative model; Geography; Remote sensing; Generative grammar; Data science","score_opus":0.05845538086283097,"score_gpt":0.21829644606174353,"score_spread":0.15984106519891256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406244347","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003534785,0.050072696,0.9241217,0.004781581,0.0004144893,0.00020586565,0.0003315184,0.0004936607,0.016043823],"genre_scores_gemma":[0.1577874,0.079063006,0.7503698,0.0017269895,0.0018351144,0.00064409577,0.00094358437,0.00022287891,0.007407129],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99681693,0.0012235234,0.00024095479,0.00044210258,0.0011708316,0.000105671104],"domain_scores_gemma":[0.9942889,0.0040020496,0.00034476272,0.0003436078,0.0009738852,0.000046756733],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056747594,0.0010406371,0.0010700302,0.004916544,0.00045320188,0.00314329,0.0022586884,0.0013391051,0.0022670946],"category_scores_gemma":[0.010089234,0.00045483417,0.0013311539,0.005089718,0.0021921322,0.0023232554,0.0010913751,0.0028345184,0.0008344567],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002568489,0.00012328666,0.0037095754,0.0022219499,0.0004358005,0.00021654369,0.0004921229,0.061618283,0.001153905,0.4376394,0.012619886,0.47974357],"study_design_scores_gemma":[0.000017801043,0.00007790823,0.0041631097,0.0011213272,0.00010877924,0.00036052358,0.0003162052,0.21227655,0.0024297105,0.65203506,0.12698364,0.00010950148],"about_ca_topic_score_codex":0.0033756387,"about_ca_topic_score_gemma":0.003933516,"teacher_disagreement_score":0.0056747594,"about_ca_system_score_codex":0.0024236436,"about_ca_system_score_gemma":0.0014738531,"threshold_uncertainty_score":0.030011356},"labels":[],"label_agreement":null},{"id":"W4406410734","doi":"10.1016/j.patcog.2025.111355","title":"Hierarchical Feature Alignment-based Progressive Addition Network for Multimodal Change Detection","year":2025,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Key Research and Development Projects of Shaanxi Province; Education Department of Shaanxi Province; Natural Science Foundation of Shaanxi Province; National Natural Science Foundation of China","keywords":"Feature (linguistics); Computer science; Artificial intelligence; Pattern recognition (psychology); Change detection; Computer vision","score_opus":0.02690880757416886,"score_gpt":0.2552595268835465,"score_spread":0.22835071930937761,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406410734","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042499203,0.00030082362,0.95263505,0.000086451,0.000070473914,0.00011623362,0.00025757594,0.0016139948,0.0024201847],"genre_scores_gemma":[0.5382965,0.000292769,0.45232984,0.00014356295,0.000095550764,0.00023870544,0.0011480169,0.00013090917,0.00732412],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996088,0.00005871903,0.00001837586,0.00013915193,0.00011299752,0.00006200558],"domain_scores_gemma":[0.9996325,0.00011530741,0.0000386255,0.000058355206,0.00012878078,0.00002642618],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048053195,0.00080253236,0.00083358644,0.0012936741,0.0006370203,0.000508692,0.0015888104,0.00059399934,0.0037929926],"category_scores_gemma":[0.00095071143,0.00031545045,0.0005787541,0.0015002255,0.00038356904,0.0010713745,0.001160114,0.00078311184,0.0009970926],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042774528,0.0002920649,0.0016836622,0.00009552774,0.00010119595,0.00016358815,0.00010096209,0.10372792,0.038217276,0.0041530025,0.0046658893,0.84637105],"study_design_scores_gemma":[0.000008508472,0.00008383933,0.00095676095,0.0000048121674,0.000031980904,0.000057212947,0.000019487457,0.9882591,0.007571819,0.001959135,0.0010358065,0.0000116017645],"about_ca_topic_score_codex":0.006684212,"about_ca_topic_score_gemma":0.011865716,"teacher_disagreement_score":0.006684212,"about_ca_system_score_codex":0.00048440765,"about_ca_system_score_gemma":0.00069721305,"threshold_uncertainty_score":0.013290644},"labels":[],"label_agreement":null},{"id":"W4406492565","doi":"10.23900/2359-1552v14n1-26-2025","title":"PERSPECTIVAS BIBLIOMÉTRICAS SOBRE O SENSORIAMENTO REMOTO NA CLASSIFICAÇÃO DO SOLO URBANO","year":2025,"lang":"pt","type":"article","venue":"Revista Políticas Públicas & Cidades","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact","funders":"","keywords":"Political science; Physics","score_opus":0.024292360565634805,"score_gpt":0.3060592033837439,"score_spread":0.2817668428181091,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406492565","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34382662,0.039295293,0.10701093,0.029187124,0.0015322493,0.00083736144,0.0592309,0.0033428692,0.4157367],"genre_scores_gemma":[0.8827383,0.019832376,0.049769938,0.00087225967,0.000794747,0.00069771125,0.014376311,0.00043657736,0.030481838],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98365915,0.003762038,0.0018513356,0.0016210381,0.008465365,0.0006410892],"domain_scores_gemma":[0.9473467,0.022675354,0.0074266978,0.003908606,0.017916415,0.0007262411],"candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.011602031,0.00093967037,0.0015714742,0.045420967,0.0026069619,0.014275753,0.0012851659,0.0012026477,0.0095104575],"category_scores_gemma":[0.04487428,0.00055434543,0.001259906,0.11971751,0.0018469371,0.008394056,0.0031799132,0.0009042805,0.0028723204],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024821152,0.00014260212,0.23208079,0.009565739,0.0010298017,0.0004483434,0.022431249,0.008114275,0.005626377,0.13528821,0.047353093,0.5376713],"study_design_scores_gemma":[0.000041066727,0.00015901795,0.33779913,0.0026983134,0.00080148014,0.0006779369,0.03803052,0.010501512,0.009855341,0.07214479,0.5269901,0.0003006921],"about_ca_topic_score_codex":0.02524151,"about_ca_topic_score_gemma":0.028790614,"teacher_disagreement_score":0.95457906,"about_ca_system_score_codex":0.004787375,"about_ca_system_score_gemma":0.0060500447,"threshold_uncertainty_score":0.061358154},"labels":[],"label_agreement":null},{"id":"W4406584002","doi":"10.1142/s021812662550210x","title":"Enhanced Segmentation Accuracy in High-Resolution Remote Sensing Images Using a Multi-Scale Convolutional Network","year":2025,"lang":"en","type":"article","venue":"Journal of Circuits Systems and Computers","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Remote sensing; Segmentation; Scale (ratio); Artificial intelligence; Computer vision; Convolutional neural network; High resolution; Pattern recognition (psychology); Geography; Cartography","score_opus":0.019064230883988644,"score_gpt":0.2536979859496315,"score_spread":0.23463375506564285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406584002","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.099212594,0.00077036524,0.8930853,0.00034767616,0.00011237244,0.000042561565,0.00011688865,0.0027651822,0.0035470645],"genre_scores_gemma":[0.8043781,0.0005377194,0.18966085,0.00020573132,0.00006553419,0.0000371453,0.00036377288,0.00021289526,0.004538321],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999571,0.00005330734,0.000022945378,0.00013850798,0.00015339599,0.000060843548],"domain_scores_gemma":[0.9995944,0.000108345586,0.000055425127,0.00007853615,0.00014342305,0.00001980791],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082311546,0.0008027794,0.0005502887,0.0010074582,0.00040916863,0.00091724796,0.001004803,0.0011231728,0.0010881678],"category_scores_gemma":[0.0015443101,0.0003842104,0.0007151626,0.0008020572,0.00048336457,0.0019366366,0.0007410594,0.0006117457,0.00045069196],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035644695,0.00014036155,0.0054910625,0.0001516027,0.00016666169,0.00024128324,0.00014890682,0.4516087,0.07822171,0.004036251,0.0030956278,0.4563414],"study_design_scores_gemma":[0.000003096499,0.000015640964,0.00092419045,0.0000041941607,0.000018679535,0.000038356837,0.000006311751,0.98940545,0.008545107,0.0005540602,0.00047558962,0.00000939627],"about_ca_topic_score_codex":0.009893214,"about_ca_topic_score_gemma":0.011788238,"teacher_disagreement_score":0.009893214,"about_ca_system_score_codex":0.0009737293,"about_ca_system_score_gemma":0.0007355006,"threshold_uncertainty_score":0.019671261},"labels":[],"label_agreement":null},{"id":"W4406611022","doi":"10.1109/tgrs.2025.3530515","title":"GLFRNet: Global-Local Feature Refusion Network for Remote Sensing Image Instance Segmentation","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Six Talent Peaks Project in Jiangsu Province; National Natural Science Foundation of China","keywords":"Image segmentation; Computer science; Artificial intelligence; Feature (linguistics); Computer vision; Remote sensing; Segmentation; Feature extraction; Pattern recognition (psychology); Image (mathematics); Geology","score_opus":0.009661560108592393,"score_gpt":0.25245549914904514,"score_spread":0.24279393904045274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406611022","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07353877,0.0023909798,0.8897207,0.000687232,0.00031641248,0.00029276882,0.00300162,0.02326113,0.006790484],"genre_scores_gemma":[0.61977726,0.0010650323,0.35278067,0.0009770141,0.00015096944,0.00040813859,0.011965065,0.00084959815,0.012026317],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99971944,0.00002047287,0.000012727324,0.00013590437,0.000058265632,0.000053083346],"domain_scores_gemma":[0.9998337,0.000029695777,0.00002427122,0.000044191926,0.00005135435,0.000016742135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040778707,0.0013881538,0.0009648592,0.00089479,0.0003921399,0.000868779,0.0025962552,0.0013718336,0.0029161451],"category_scores_gemma":[0.0011214991,0.00045907305,0.0009720923,0.0008534811,0.00049130793,0.0020244024,0.0010490258,0.001196685,0.0012449778],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004622743,0.00021274912,0.0032984605,0.00026252776,0.00020741372,0.0003980082,0.00019766352,0.17278214,0.034583412,0.008211507,0.037910722,0.74147314],"study_design_scores_gemma":[0.000022196757,0.00006890693,0.0008621597,0.000019632276,0.0000402194,0.00011269584,0.000031537424,0.97560096,0.012391922,0.0044456325,0.006377726,0.000026431093],"about_ca_topic_score_codex":0.014887308,"about_ca_topic_score_gemma":0.016446564,"teacher_disagreement_score":0.014887308,"about_ca_system_score_codex":0.0013058006,"about_ca_system_score_gemma":0.0009284264,"threshold_uncertainty_score":0.029601276},"labels":[],"label_agreement":null},{"id":"W4406998231","doi":"10.1016/j.rsase.2025.101464","title":"Analysis of asbestos-cement roof classification in urban areas: Supervised and unsupervised methods with multispectral and hyperspectral remote sensing","year":2025,"lang":"en","type":"article","venue":"Remote Sensing Applications Society and Environment","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Public Health","funders":"European Space Agency; Universidad de Granada; Ryerson University; Universidad de Cartagena; Sistema General de Regalías de Colombia; Toronto Metropolitan University","keywords":"Multispectral image; Hyperspectral imaging; Asbestos cement; Asbestos; Remote sensing; Multispectral pattern recognition; Environmental science; Artificial intelligence; Cartography; Computer science; Geography","score_opus":0.014784537258135269,"score_gpt":0.25301378823836085,"score_spread":0.23822925098022557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406998231","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7446049,0.00048270315,0.2510735,0.00007153811,0.000029236662,0.00012380295,0.00038733834,0.0005226301,0.0027043722],"genre_scores_gemma":[0.88293105,0.00024234252,0.114445575,0.000023737894,0.000019302252,0.000085068845,0.000823697,0.000053544034,0.0013756998],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925154,0.00015804353,0.000048811256,0.00015579867,0.00032901208,0.000056713434],"domain_scores_gemma":[0.9991756,0.00026315305,0.00016867045,0.00007394572,0.0002880622,0.000030548723],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000991111,0.000565822,0.00032823643,0.0021514846,0.00024306918,0.0006198939,0.0003801075,0.00037247982,0.00036586652],"category_scores_gemma":[0.0011562983,0.000116394294,0.0006796858,0.0011557319,0.0003395974,0.0004617434,0.0003853293,0.0002363613,0.00026341356],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003864376,0.0007169866,0.10485526,0.00053774077,0.00042130225,0.0002901414,0.0007499702,0.0824613,0.09944412,0.0010694049,0.0016939526,0.7073734],"study_design_scores_gemma":[0.000019206705,0.00023978844,0.22912659,0.00005924947,0.00014912043,0.00036451122,0.00091641914,0.7126583,0.052503902,0.0010347314,0.0028625473,0.00006569573],"about_ca_topic_score_codex":0.002727721,"about_ca_topic_score_gemma":0.005576754,"teacher_disagreement_score":0.002727721,"about_ca_system_score_codex":0.00023454381,"about_ca_system_score_gemma":0.00037100026,"threshold_uncertainty_score":0.0054237247},"labels":[],"label_agreement":null},{"id":"W4407027175","doi":"10.1016/j.rsase.2025.101478","title":"SimPoolFormer: A two-stream vision transformer for hyperspectral image classification","year":2025,"lang":"en","type":"article","venue":"Remote Sensing Applications Society and Environment","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Hyperspectral imaging; Artificial intelligence; Computer vision; Computer science; Transformer; Pattern recognition (psychology); Engineering","score_opus":0.009441330346232122,"score_gpt":0.2442120558041671,"score_spread":0.23477072545793498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407027175","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015064487,0.00014516176,0.9944593,0.00009046634,0.00006876877,0.000042792693,0.00020078664,0.0022273255,0.0012588933],"genre_scores_gemma":[0.056976393,0.00055915565,0.9245466,0.0005543719,0.000145938,0.00020382868,0.0014706068,0.0008939791,0.014649161],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995309,0.000090611145,0.000024219158,0.00007280935,0.00023076774,0.000050732793],"domain_scores_gemma":[0.9995017,0.000124833,0.00003256466,0.00007865778,0.00021283365,0.00004947835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094418443,0.0012296488,0.00071553956,0.00075278414,0.00033071378,0.0011298874,0.001369212,0.0008834823,0.020113187],"category_scores_gemma":[0.0014958825,0.00041945514,0.0005542303,0.0012236095,0.00043674427,0.001410955,0.001411898,0.0012366741,0.008535137],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00059337885,0.00015101167,0.00040222873,0.00020213106,0.00008187795,0.00010863465,0.00006289336,0.01182635,0.092158474,0.008504916,0.033120777,0.85278744],"study_design_scores_gemma":[0.00014613807,0.00024381506,0.00082235294,0.000040563744,0.000067311244,0.00052403926,0.000072618845,0.7674031,0.17131476,0.010038915,0.049256515,0.00006972],"about_ca_topic_score_codex":0.0023668804,"about_ca_topic_score_gemma":0.004822869,"teacher_disagreement_score":0.020113187,"about_ca_system_score_codex":0.00041661048,"about_ca_system_score_gemma":0.0012126034,"threshold_uncertainty_score":0.06728536},"labels":[],"label_agreement":null},{"id":"W4407737361","doi":"10.1109/whispers65427.2024.10876533","title":"HSIFormer: An Efficient Vision Transformer Framework for Enhanced Hyperspectral Image Classification Using Local Window Attention","year":2024,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Hyperspectral imaging; Computer science; Artificial intelligence; Computer vision; Window (computing); Transformer; Pattern recognition (psychology); Engineering; Voltage","score_opus":0.02387872059069562,"score_gpt":0.3080661416737927,"score_spread":0.2841874210830971,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407737361","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024859454,0.00088496157,0.9581607,0.00025088643,0.0001290928,0.00013632004,0.0006250068,0.011697436,0.0032560902],"genre_scores_gemma":[0.44722927,0.0013547167,0.5221064,0.0009167888,0.00016707958,0.00031436273,0.0060696504,0.0010574156,0.0207843],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99982506,0.000018437086,0.000006231849,0.000057758076,0.000060635506,0.00003192525],"domain_scores_gemma":[0.99987316,0.000025363433,0.000014309487,0.000027783242,0.000044738026,0.000014666075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040594063,0.0013073755,0.0007305166,0.0008278784,0.0002262298,0.000661098,0.0020600853,0.0006168463,0.0040381886],"category_scores_gemma":[0.00055640057,0.00039138808,0.00089188275,0.0007116334,0.00028742568,0.0013787762,0.001084264,0.0011849354,0.0016014408],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022474423,0.0002451243,0.0014843761,0.00014040696,0.00017216479,0.00013439008,0.00005849417,0.10675825,0.04165846,0.0051903315,0.019940473,0.82399285],"study_design_scores_gemma":[0.000016539612,0.00006440071,0.00048847054,0.000006630028,0.000029407736,0.00006887635,0.000015231889,0.9827339,0.010572903,0.0025146743,0.0034774726,0.000011362264],"about_ca_topic_score_codex":0.011271673,"about_ca_topic_score_gemma":0.021515729,"teacher_disagreement_score":0.011271673,"about_ca_system_score_codex":0.0007317244,"about_ca_system_score_gemma":0.0010043173,"threshold_uncertainty_score":0.02241218},"labels":[],"label_agreement":null},{"id":"W4407867799","doi":"10.23977/acss.2025.090102","title":"A Comparative Study of Deep Learning-Based Semantic Segmentation Methods for High-Resolution Remote Sensing Imagery","year":2025,"lang":"en","type":"article","venue":"Advances in Computer Signals and Systems","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"High resolution; Segmentation; Computer science; Deep learning; Remote sensing; Artificial intelligence; Geology","score_opus":0.02707748939167514,"score_gpt":0.34170059666708924,"score_spread":0.3146231072754141,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407867799","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36881804,0.015762148,0.5796188,0.0013781463,0.0006319156,0.00025908742,0.0018245975,0.005977535,0.02572973],"genre_scores_gemma":[0.7473887,0.004170764,0.23359111,0.00036156466,0.00012612947,0.00009480333,0.0052158446,0.00045953438,0.008591511],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999263,0.00011059143,0.000054202494,0.00018066032,0.00028748854,0.00010412632],"domain_scores_gemma":[0.99887556,0.00041503436,0.0000819842,0.00015098484,0.00041030784,0.00006606358],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018591647,0.0011038065,0.00069915823,0.002604171,0.00044233844,0.001330159,0.0011475453,0.001248261,0.0022264165],"category_scores_gemma":[0.0034233287,0.00032302202,0.00092899054,0.0015988348,0.00049751665,0.0024577826,0.0007324489,0.00078434264,0.0008342699],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00089722686,0.00029910513,0.0063474313,0.00052586256,0.0003078941,0.0001107265,0.00014240837,0.14966545,0.015765022,0.0046254555,0.0073107756,0.81400263],"study_design_scores_gemma":[0.000017736726,0.00016763344,0.004785862,0.00005790064,0.00006160236,0.00009605818,0.000096937314,0.97790843,0.010632333,0.002265105,0.0038819958,0.000028487098],"about_ca_topic_score_codex":0.009571208,"about_ca_topic_score_gemma":0.013596059,"teacher_disagreement_score":0.009571208,"about_ca_system_score_codex":0.0011029863,"about_ca_system_score_gemma":0.0011506003,"threshold_uncertainty_score":0.019030988},"labels":[],"label_agreement":null},{"id":"W4407869962","doi":"10.1007/s41651-025-00215-6","title":"SACNet: A Novel Self-Supervised Learning Method for Shadow Detection from High-Resolution Remote Sensing Images","year":2025,"lang":"en","type":"article","venue":"Journal of Geovisualization and Spatial Analysis","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Shadow (psychology); High resolution; Computer science; Remote sensing; Artificial intelligence; Computer vision; Pattern recognition (psychology); Geography; Psychology","score_opus":0.009762986310687127,"score_gpt":0.26861587957197214,"score_spread":0.258852893261285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407869962","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035401493,0.0006090899,0.9495424,0.00015099991,0.00028353313,0.00017100693,0.0008075027,0.011070429,0.0019634953],"genre_scores_gemma":[0.25570253,0.00052921916,0.7212336,0.0003989833,0.0004100994,0.00038608877,0.0068701827,0.0007966393,0.0136726415],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99938273,0.00009077137,0.000032089167,0.00017991649,0.00024372827,0.00007077552],"domain_scores_gemma":[0.9993467,0.00013633573,0.000052945874,0.00009287559,0.00032277394,0.00004845926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010243845,0.0014044725,0.0014411219,0.0019861874,0.0006773262,0.00070599135,0.0021963802,0.0014039631,0.0024003705],"category_scores_gemma":[0.0011827715,0.0005001268,0.00090897846,0.0014160196,0.00051731535,0.0013765771,0.0011643609,0.001174212,0.0019016648],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000342563,0.00045358986,0.0027070616,0.00016903879,0.00021063875,0.00013263895,0.00006122833,0.050142676,0.025945049,0.0021506064,0.025570648,0.89211434],"study_design_scores_gemma":[0.000015807562,0.000054532786,0.0009000721,0.000008304466,0.000022935315,0.000075580196,0.000018138207,0.9855149,0.008539384,0.0011406029,0.003695185,0.000014657227],"about_ca_topic_score_codex":0.007781287,"about_ca_topic_score_gemma":0.016249577,"teacher_disagreement_score":0.007781287,"about_ca_system_score_codex":0.00055577833,"about_ca_system_score_gemma":0.0013629535,"threshold_uncertainty_score":0.015471995},"labels":[],"label_agreement":null},{"id":"W4408111569","doi":"10.5220/0013151200003912","title":"Garbage Classification from Visual Footprints: Using Transfer Learning Strategy","year":2025,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University of Edmonton","funders":"","keywords":"Computer science; Transfer of learning; Artificial intelligence; Garbage; Programming language","score_opus":0.030852888152362683,"score_gpt":0.2803633057753888,"score_spread":0.24951041762302614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408111569","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15277173,0.0007738647,0.83971596,0.00028413572,0.00012837492,0.00012381232,0.00031355707,0.0035134398,0.0023751017],"genre_scores_gemma":[0.8483517,0.00039855152,0.14507797,0.00015141873,0.000118259275,0.000102834754,0.0010292192,0.00019536263,0.004574707],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996427,0.000053792195,0.000019883857,0.000126321,0.00007788342,0.00007931115],"domain_scores_gemma":[0.99928856,0.00021386631,0.00005643293,0.0001289488,0.00026776514,0.000044356682],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078140775,0.0010045652,0.0012686,0.0018907774,0.0004653226,0.0007829081,0.0013317569,0.0010704114,0.0021245335],"category_scores_gemma":[0.0014417926,0.0002759163,0.0009091941,0.0018721003,0.0005115321,0.0015035355,0.0011808684,0.00079161185,0.0013533713],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041594592,0.0003707609,0.0038105971,0.000119191645,0.000101376434,0.00014269086,0.000099169534,0.072500415,0.027039494,0.0012961478,0.0031815614,0.89092255],"study_design_scores_gemma":[0.000007998102,0.00004818829,0.00097180053,0.000008409306,0.000023073593,0.00003948426,0.000051918505,0.9900732,0.0063342405,0.001934301,0.00049704674,0.0000103307375],"about_ca_topic_score_codex":0.0069013415,"about_ca_topic_score_gemma":0.0051423865,"teacher_disagreement_score":0.0069013415,"about_ca_system_score_codex":0.0004071663,"about_ca_system_score_gemma":0.0008468824,"threshold_uncertainty_score":0.01372236},"labels":[],"label_agreement":null},{"id":"W4408122255","doi":"10.18280/mmep.120229","title":"Utilizing a Novel Deep Learning Method for Scene Categorization in Remote Sensing Data","year":2025,"lang":"en","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Categorization; Computer science; Remote sensing; Deep learning; Artificial intelligence; Pattern recognition (psychology); Geology","score_opus":0.05730697859289708,"score_gpt":0.2785200431018995,"score_spread":0.2212130645090024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408122255","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037978493,0.00048429827,0.9555942,0.00033028712,0.00012100121,0.00010615579,0.00044566678,0.0025206325,0.0024192466],"genre_scores_gemma":[0.5598356,0.0006043799,0.42617744,0.00042774616,0.0001317353,0.00017715008,0.0028894725,0.00017756278,0.009578872],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996731,0.000036381167,0.000022149447,0.00012303787,0.000088798435,0.00005654776],"domain_scores_gemma":[0.9997459,0.00004747517,0.000032459466,0.00005361408,0.00010242145,0.00001819058],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050084235,0.0007641893,0.0005079456,0.0011307445,0.00030944624,0.00064083806,0.0012423694,0.0007928488,0.0017425524],"category_scores_gemma":[0.00087716314,0.0002500532,0.00087011285,0.001040488,0.00031596873,0.0013236147,0.0007581031,0.00096672936,0.0008491348],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000115210874,0.0002121426,0.0030402779,0.00017035751,0.000108773216,0.00011360017,0.00010599257,0.12307795,0.026373496,0.0056612487,0.00711496,0.8339059],"study_design_scores_gemma":[0.000003946687,0.000032442113,0.00068322575,0.000009278577,0.000014109981,0.00003964918,0.000024579982,0.99037886,0.0049287467,0.0023483413,0.0015290387,0.00000788644],"about_ca_topic_score_codex":0.008332622,"about_ca_topic_score_gemma":0.012122185,"teacher_disagreement_score":0.008332622,"about_ca_system_score_codex":0.000701416,"about_ca_system_score_gemma":0.00095375074,"threshold_uncertainty_score":0.016568244},"labels":[],"label_agreement":null},{"id":"W4408733098","doi":"10.1016/j.compbiomed.2025.110053","title":"Enhancing interdisciplinary image segmentation through a Gaussian-based modified local consensus spatial fuzzy approach","year":2025,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Federation of Canadian Municipalities","keywords":"Artificial intelligence; Computer science; Segmentation; Image segmentation; Fuzzy logic; Gaussian; Pattern recognition (psychology); Image (mathematics); Computer vision","score_opus":0.01638086184043921,"score_gpt":0.30876468357964243,"score_spread":0.29238382173920324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408733098","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023830842,0.00011582164,0.9748429,0.000078570745,0.000029876861,0.0000209612,0.000013014064,0.00012678721,0.0009412911],"genre_scores_gemma":[0.7447964,0.0001584521,0.25210086,0.00012071862,0.00004797736,0.00008231118,0.00008186526,0.000053936215,0.002557615],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994067,0.00010046959,0.000033665518,0.00016081275,0.00023501749,0.00006327238],"domain_scores_gemma":[0.9993887,0.00015700024,0.00006385567,0.000045447396,0.00030647067,0.000038591857],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010017997,0.00053416204,0.001004103,0.0010289076,0.00072439865,0.0006948549,0.0012653135,0.0011539002,0.00084252714],"category_scores_gemma":[0.0014462989,0.00031949222,0.0009191757,0.0008815032,0.00073975767,0.0009820589,0.0011039344,0.00046969007,0.00020837583],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038763275,0.00015820636,0.0015160602,0.00020760066,0.00017121511,0.00019105236,0.0003227748,0.72110224,0.04509558,0.01679421,0.0018302752,0.21222317],"study_design_scores_gemma":[0.0000053627423,0.000023785351,0.00014094567,0.0000026112825,0.000014101483,0.000016008558,0.000011209803,0.99668956,0.0015594993,0.0013370626,0.00019258872,0.0000073066753],"about_ca_topic_score_codex":0.007321084,"about_ca_topic_score_gemma":0.007856814,"teacher_disagreement_score":0.007321084,"about_ca_system_score_codex":0.000765584,"about_ca_system_score_gemma":0.0011584212,"threshold_uncertainty_score":0.014556944},"labels":[],"label_agreement":null},{"id":"W4409356476","doi":"10.1109/taes.2025.3560256","title":"Multiview Visual and Topological Features Coordination Aggregation Framework for SAR Target Recognition","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Aerospace and Electronic Systems","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Shanghai Aerospace Science and Technology Innovation Foundation; National Natural Science Foundation of China","keywords":"Computer science; Automatic target recognition; Artificial intelligence; Computer vision; Topology (electrical circuits); Synthetic aperture radar; Pattern recognition (psychology); Engineering; Electrical engineering","score_opus":0.01290505558964719,"score_gpt":0.26533917861043327,"score_spread":0.25243412302078605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409356476","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007136632,0.00024240548,0.9912487,0.000052512332,0.000018448285,0.000020242334,0.000083166924,0.000528776,0.00066899],"genre_scores_gemma":[0.6237191,0.0006157459,0.37083888,0.00015964509,0.00015323181,0.00014264765,0.0009805971,0.00015545232,0.0032345715],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99957854,0.000053969405,0.000019760391,0.00015486572,0.00014077076,0.000052076688],"domain_scores_gemma":[0.999775,0.000032103904,0.000047741752,0.000052619806,0.00007330668,0.000019253224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045373102,0.000750521,0.0007616233,0.0012296167,0.0002576743,0.00083265133,0.0013515753,0.00046226147,0.0011293881],"category_scores_gemma":[0.0006736231,0.00028753342,0.0010520918,0.0015178134,0.00037297784,0.0013332264,0.0009765262,0.0007441672,0.0003709831],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001278636,0.000091605034,0.0017052271,0.000089366426,0.00014514929,0.00014416169,0.000113219,0.50961244,0.021585457,0.016845712,0.0036446187,0.44589517],"study_design_scores_gemma":[0.0000029582384,0.000024511763,0.00044093016,0.000002653144,0.000018046818,0.000030199422,0.000013432786,0.9930534,0.0016586898,0.0037824095,0.00096512254,0.000007653004],"about_ca_topic_score_codex":0.009125602,"about_ca_topic_score_gemma":0.007447875,"teacher_disagreement_score":0.009125602,"about_ca_system_score_codex":0.0007374778,"about_ca_system_score_gemma":0.0007082367,"threshold_uncertainty_score":0.018144965},"labels":[],"label_agreement":null},{"id":"W4409981863","doi":"10.18280/ts.420249","title":"Unsupervised Classification of Remote Sensing Images via Generative Adversarial Networks and Transfer Learning","year":2025,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Generative grammar; Adversarial system; Transfer of learning; Computer science; Artificial intelligence; Generative adversarial network; Pattern recognition (psychology); Unsupervised learning; Transfer (computing); Machine learning; Deep learning","score_opus":0.012592375896158133,"score_gpt":0.22013853719407195,"score_spread":0.2075461612979138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409981863","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018550523,0.00020740648,0.97906244,0.00021171212,0.00004321125,0.000038229922,0.000051564224,0.0005001002,0.0013348309],"genre_scores_gemma":[0.7847956,0.0004165178,0.20769429,0.0004271565,0.00015432147,0.00021430974,0.00045226593,0.00016013886,0.00568546],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994216,0.0001791364,0.000021880402,0.00018328957,0.00012447979,0.0000695698],"domain_scores_gemma":[0.9990031,0.00053284114,0.00016063517,0.00013286386,0.00012540322,0.000045132976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009530403,0.00087396585,0.0007563946,0.0005989798,0.00026551748,0.0006970529,0.0013477312,0.00089640747,0.0009513453],"category_scores_gemma":[0.0021090154,0.00044341432,0.0010973739,0.0005068463,0.0010552247,0.0008853252,0.0011501954,0.0019503355,0.00035163516],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000091069276,0.000061089966,0.0011189023,0.000059476068,0.000070698385,0.0001297789,0.00009694458,0.893162,0.006878572,0.012789835,0.001692779,0.083848886],"study_design_scores_gemma":[0.0000014127309,0.0000066955445,0.000068271765,0.0000018070498,0.0000022805418,0.000010220922,0.0000021502738,0.9974884,0.0005338192,0.001754585,0.00012750733,0.000002783136],"about_ca_topic_score_codex":0.0024737194,"about_ca_topic_score_gemma":0.0025782161,"teacher_disagreement_score":0.0024737194,"about_ca_system_score_codex":0.0006669209,"about_ca_system_score_gemma":0.00046621633,"threshold_uncertainty_score":0.0050401688},"labels":[],"label_agreement":null},{"id":"W4410485256","doi":"10.1117/1.jrs.19.024507","title":"Coordinating high-resolution hyperspectral and RGB video acquisition of dynamic natural water scenes","year":2025,"lang":"en","type":"article","venue":"Journal of Applied Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Hyperspectral imaging; Remote sensing; Computer science; RGB color model; Computer vision; Image resolution; Artificial intelligence; Geology","score_opus":0.004171821021563098,"score_gpt":0.21043660549573076,"score_spread":0.20626478447416766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410485256","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.51222897,0.00008865845,0.47665676,0.000114862734,0.00005469105,0.0005076643,0.0016151264,0.0041720155,0.004561229],"genre_scores_gemma":[0.73399794,0.00006906795,0.26077902,0.00006043704,0.000021474896,0.00031917912,0.0020671112,0.00025993068,0.002425863],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99962485,0.00002869194,0.000012669774,0.00015269066,0.00012395764,0.000057188434],"domain_scores_gemma":[0.99967015,0.0000501197,0.000035647867,0.000041024257,0.00016773347,0.000035319958],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047203613,0.00048213455,0.0003255637,0.0004866314,0.00038096381,0.0005323952,0.00052535144,0.00025266132,0.0012941579],"category_scores_gemma":[0.000788252,0.0002728124,0.00019624794,0.00066146353,0.00028277098,0.0005254872,0.0005664787,0.00034025576,0.0005807185],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00060352293,0.00043812196,0.035516508,0.00015832898,0.000058918235,0.00024350556,0.00037185478,0.07485291,0.69410545,0.001214266,0.0057020728,0.18673453],"study_design_scores_gemma":[0.000047592766,0.00026257857,0.05396429,0.000013880196,0.000029867042,0.00011196868,0.00038065956,0.6784196,0.25914496,0.00090815977,0.006661271,0.00005511998],"about_ca_topic_score_codex":0.015720168,"about_ca_topic_score_gemma":0.03521995,"teacher_disagreement_score":0.015720168,"about_ca_system_score_codex":0.0006232374,"about_ca_system_score_gemma":0.0012678632,"threshold_uncertainty_score":0.03125733},"labels":[],"label_agreement":null},{"id":"W4411002559","doi":"10.1007/s10708-025-11394-6","title":"Spatio-temporal analysis of land use and land cover (LULC) changes using an object-based image analysis (OBIA) approach: a case study of Telangana state agglomeration, India","year":2025,"lang":"en","type":"article","venue":"GeoJournal","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Land cover; Geography; Human geography; Object based; Land use; State (computer science); Cover (algebra); Object (grammar); Economic geography; Computer science; Civil engineering; Artificial intelligence; Engineering","score_opus":0.03522855955563703,"score_gpt":0.26985105267369724,"score_spread":0.23462249311806022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411002559","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9976927,0.00004395999,0.0006046373,0.000050183207,0.0000026771,0.000013724691,0.0003300888,0.0000376376,0.0012244525],"genre_scores_gemma":[0.9984518,0.00004187675,0.00086452015,0.0000059737195,0.0000023228006,0.000006066635,0.00023304844,0.000004124165,0.00039011898],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99986494,0.000022987875,0.000007726971,0.00002761256,0.00003460984,0.000042132287],"domain_scores_gemma":[0.99971896,0.00008457803,0.000060536397,0.000017639353,0.00009076884,0.00002744781],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018530754,0.00020509507,0.00015220317,0.001771505,0.00038750327,0.00079233554,0.0003495062,0.00030220978,0.0006139691],"category_scores_gemma":[0.00031019413,0.00013594714,0.00032586025,0.0023705359,0.00040084546,0.00033753458,0.00027742644,0.00020546364,0.00018028446],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034514733,0.0004768005,0.8906283,0.00021152022,0.0002145766,0.0059090336,0.0036083395,0.01871307,0.019576114,0.0013889581,0.0015177679,0.057410456],"study_design_scores_gemma":[0.000006480283,0.00007726947,0.93301725,0.000013858634,0.0001068974,0.00049741147,0.0064798854,0.055612233,0.0027725082,0.00016968873,0.0012209726,0.000025431435],"about_ca_topic_score_codex":0.10095747,"about_ca_topic_score_gemma":0.18798396,"teacher_disagreement_score":0.10095747,"about_ca_system_score_codex":0.0011497292,"about_ca_system_score_gemma":0.00045603432,"threshold_uncertainty_score":0.20073962},"labels":[],"label_agreement":null},{"id":"W4411799273","doi":"10.1109/tgrs.2025.3584126","title":"Scale- and Shape-Aware Network With Prediction Decoupling for Building Fine-Grained Change Detection","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Computer science; Scale (ratio); Change detection; Remote sensing; Artificial intelligence; Data mining; Geology; Cartography","score_opus":0.01570392031664417,"score_gpt":0.23310043224140645,"score_spread":0.21739651192476228,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411799273","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20611255,0.0029597918,0.7526621,0.0010967937,0.00065183913,0.0002982701,0.0063018324,0.0180107,0.011906044],"genre_scores_gemma":[0.7527078,0.0009805298,0.21920267,0.00051142543,0.00023603313,0.00025130797,0.01539118,0.000446057,0.010273102],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996686,0.000029885297,0.000013707014,0.00015357754,0.00007114066,0.000063078005],"domain_scores_gemma":[0.9996706,0.0000788194,0.000036334997,0.000094296425,0.00008979577,0.00003011734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003768735,0.001827221,0.000925701,0.0011731901,0.00057026895,0.00073586835,0.0018738483,0.00090093975,0.0017939849],"category_scores_gemma":[0.0015444711,0.00049687305,0.0006362789,0.0012642901,0.00042089968,0.0017957456,0.0012005504,0.0011321445,0.0010016131],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007188766,0.00040927264,0.010640197,0.00036284348,0.0002326423,0.00044943846,0.0002356665,0.24443717,0.033079505,0.0050782044,0.036535535,0.6678206],"study_design_scores_gemma":[0.000014267052,0.00005089644,0.0017790628,0.000013249946,0.00004214191,0.00010813678,0.00004184268,0.9841687,0.0071168826,0.00361356,0.0030332583,0.000017977305],"about_ca_topic_score_codex":0.017091148,"about_ca_topic_score_gemma":0.033049285,"teacher_disagreement_score":0.017091148,"about_ca_system_score_codex":0.00090142054,"about_ca_system_score_gemma":0.00082239346,"threshold_uncertainty_score":0.03398335},"labels":[],"label_agreement":null},{"id":"W4411867217","doi":"10.1109/tevc.2025.3584435","title":"Unsupervised Band Selection for Hyperspectral Image Classification: Particle Swarm Optimization via Cross-Domain Knowledge Transfer","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Evolutionary Computation","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Science Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Hyperspectral imaging; Particle swarm optimization; Artificial intelligence; Computer science; Pattern recognition (psychology); Selection (genetic algorithm); Domain (mathematical analysis); Transfer of learning; Remote sensing; Machine learning; Mathematics; Geology","score_opus":0.017481479696025537,"score_gpt":0.2731725345674727,"score_spread":0.25569105487144717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411867217","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017385134,0.00022128575,0.9811803,0.000101595586,0.00002432309,0.00002897377,0.000021326545,0.00025659462,0.00078043825],"genre_scores_gemma":[0.6109292,0.00045646224,0.38446796,0.0002994378,0.00010499543,0.0002675405,0.00039110405,0.000118823016,0.0029645078],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996588,0.00009426636,0.000016417634,0.000101074605,0.00009151922,0.000037888487],"domain_scores_gemma":[0.999368,0.00032642405,0.00010140103,0.000057229823,0.000116544135,0.000030436066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010160765,0.0010770562,0.0010232774,0.0007973052,0.00040907503,0.00075063185,0.0009820337,0.0011077784,0.00091476185],"category_scores_gemma":[0.0019043937,0.00044142964,0.0008277371,0.0008624155,0.0006829961,0.0010069156,0.000935679,0.0010742863,0.00028589848],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000118879085,0.00012695313,0.0009690671,0.00008226202,0.0000914764,0.00007727153,0.00010487172,0.8471433,0.0058806445,0.0031862825,0.0017655264,0.14045341],"study_design_scores_gemma":[0.000004034495,0.000008667348,0.0000848948,0.0000019805098,0.0000035066207,0.000005144695,0.0000051103134,0.99891543,0.0003729034,0.00049106195,0.00010515018,0.0000021030046],"about_ca_topic_score_codex":0.0036535333,"about_ca_topic_score_gemma":0.0022089467,"teacher_disagreement_score":0.0036535333,"about_ca_system_score_codex":0.00044379936,"about_ca_system_score_gemma":0.00073253614,"threshold_uncertainty_score":0.007264495},"labels":[],"label_agreement":null},{"id":"W4412081829","doi":"10.1109/tgrs.2025.3586287","title":"Spatial–Spectral Diffusion Contrastive Representation Network for Hyperspectral Image Classification","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hyperspectral imaging; Artificial intelligence; Pattern recognition (psychology); Computer science; Remote sensing; Contextual image classification; Image (mathematics); Geology","score_opus":0.016280092070142457,"score_gpt":0.26081941523364305,"score_spread":0.24453932316350058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412081829","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033557575,0.00076892035,0.96167785,0.00035643106,0.000084874555,0.000051161285,0.00011876312,0.0008469598,0.0025374796],"genre_scores_gemma":[0.7842494,0.0006958166,0.20570691,0.00037862637,0.00010195125,0.00018397941,0.00064295495,0.00009051722,0.007949723],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99977034,0.00003723369,0.000011369223,0.00008267497,0.00006731467,0.000031083164],"domain_scores_gemma":[0.999676,0.00010454076,0.000046449888,0.000038087564,0.000116727904,0.000018093098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005179166,0.0006970998,0.0004957734,0.0004598726,0.000258817,0.0005523223,0.0012917374,0.0007289512,0.0010475168],"category_scores_gemma":[0.0015063444,0.00024759144,0.00056702376,0.0005949507,0.0004344878,0.0011990262,0.00082968525,0.0011291148,0.0002912034],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015890005,0.00015589429,0.0018273307,0.00011145195,0.000097667675,0.00007932485,0.00009623403,0.53288555,0.020025115,0.013536292,0.00481975,0.42620638],"study_design_scores_gemma":[0.0000021232167,0.000015447325,0.000116492,0.0000027768576,0.00000723524,0.000010741907,0.000003771232,0.9961212,0.0016754791,0.0016433708,0.00039722162,0.0000041528756],"about_ca_topic_score_codex":0.0050624786,"about_ca_topic_score_gemma":0.005224119,"teacher_disagreement_score":0.0050624786,"about_ca_system_score_codex":0.00094038906,"about_ca_system_score_gemma":0.00065262744,"threshold_uncertainty_score":0.010066032},"labels":[],"label_agreement":null},{"id":"W4412153734","doi":"10.1007/s00138-025-01714-8","title":"Surface multi-spectral reflectivity and texture material recognition in non-constrained environments","year":2025,"lang":"en","type":"article","venue":"Machine Vision and Applications","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Reflectivity; Texture (cosmology); Materials science; Surface (topology); Surface finish; Computer science; Artificial intelligence; Optics; Composite material; Mathematics; Geometry; Image (mathematics); Physics","score_opus":0.009912751609323757,"score_gpt":0.2671148894748426,"score_spread":0.2572021378655188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412153734","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5608894,0.0006620325,0.43373623,0.00020465865,0.000039074203,0.000036192952,0.00027537768,0.00052054366,0.003636468],"genre_scores_gemma":[0.9510036,0.00029394604,0.04657043,0.000036604073,0.000029382485,0.00001728952,0.0002492683,0.00005625837,0.0017432619],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997476,0.00004962001,0.00000688567,0.00006361827,0.00008563207,0.000046606925],"domain_scores_gemma":[0.99972254,0.00011187639,0.000049930775,0.000047725636,0.000045095625,0.000022868611],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023569899,0.00041838907,0.00046042833,0.00049807446,0.0002551706,0.0007493704,0.000493343,0.0005485558,0.00086506887],"category_scores_gemma":[0.0008774808,0.00030806835,0.00035828273,0.00055973174,0.0005833727,0.000985449,0.000604169,0.00036171987,0.00042889683],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008277002,0.00041122458,0.012276606,0.00035013424,0.00018517463,0.0006827352,0.000253929,0.34011614,0.3753587,0.0060632993,0.0018683133,0.26160613],"study_design_scores_gemma":[0.000010985779,0.00005306849,0.009897541,0.0000071183504,0.00001670339,0.00021673604,0.000120681936,0.9601,0.026375547,0.00262027,0.0005613324,0.000020005187],"about_ca_topic_score_codex":0.0026598766,"about_ca_topic_score_gemma":0.004358031,"teacher_disagreement_score":0.0026598766,"about_ca_system_score_codex":0.00014960341,"about_ca_system_score_gemma":0.0003011499,"threshold_uncertainty_score":0.0052887797},"labels":[],"label_agreement":null},{"id":"W4412369264","doi":"10.3390/rs17142337","title":"CSDNet: Context-Aware Segmentation of Disaster Aerial Imagery Using Detection-Guided Features and Lightweight Transformers","year":2025,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec en Outaouais","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Segmentation; Computer science; Artificial intelligence; Transformer; Image segmentation; Context (archaeology); Computer vision; Machine learning; Geography; Engineering","score_opus":0.014048152809052656,"score_gpt":0.2507789296657732,"score_spread":0.23673077685672053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412369264","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03543857,0.00032662047,0.9564652,0.0001127804,0.00006689503,0.00011706434,0.00055332703,0.0054299044,0.0014896848],"genre_scores_gemma":[0.5340226,0.00035972567,0.45937565,0.00018653728,0.00005938925,0.00016895318,0.002281437,0.0004720264,0.0030735694],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99982494,0.000014409433,0.000009140771,0.000074459196,0.000049640414,0.000027498669],"domain_scores_gemma":[0.9998766,0.000027515043,0.000015301639,0.000027691522,0.000035951947,0.000016896038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027017712,0.00065062306,0.0005037049,0.00090933836,0.0002908971,0.0007935234,0.0011739095,0.000592193,0.001397804],"category_scores_gemma":[0.00077461335,0.00031798347,0.00062605785,0.00064847176,0.00036925136,0.0011506836,0.0012794896,0.0006378998,0.0005779567],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00062435557,0.00023961127,0.0042099156,0.0002517293,0.00012706534,0.0002370598,0.00023263044,0.24059722,0.09586707,0.007883217,0.011517871,0.63821226],"study_design_scores_gemma":[0.000015083156,0.000047467165,0.001023605,0.000010471407,0.000019148167,0.00010065795,0.00003534916,0.9742735,0.017054904,0.0035656218,0.0038411445,0.000012991314],"about_ca_topic_score_codex":0.006401464,"about_ca_topic_score_gemma":0.014351854,"teacher_disagreement_score":0.006401464,"about_ca_system_score_codex":0.0007645896,"about_ca_system_score_gemma":0.0008116288,"threshold_uncertainty_score":0.012728393},"labels":[],"label_agreement":null},{"id":"W4412538447","doi":"10.1016/j.rsase.2025.101668","title":"Enhancing U-Net performance for high-resolution land cover classification using a dynamic epoch-centric optimizer (DECO)","year":2025,"lang":"en","type":"article","venue":"Remote Sensing Applications Society and Environment","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Institut National de la Recherche Scientifique","funders":"","keywords":"Epoch (astronomy); Land cover; Cover (algebra); Net (polyhedron); Computer science; Geography; Environmental resource management; Environmental science; Land use; Engineering; Mathematics; Civil engineering; Computer vision","score_opus":0.010578383875636197,"score_gpt":0.21886827135859943,"score_spread":0.20828988748296323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412538447","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42271033,0.0017197777,0.54796886,0.00078586227,0.0004926997,0.00012496469,0.00095570047,0.014334807,0.010906961],"genre_scores_gemma":[0.8271457,0.00019867903,0.16523483,0.00029743166,0.00010551714,0.00007974139,0.0010849023,0.0006248397,0.0052283118],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9997793,0.00004648806,0.000012260365,0.00006160512,0.00004590743,0.000054478536],"domain_scores_gemma":[0.99974674,0.000080111175,0.000022802784,0.00004805123,0.000077572695,0.000024689643],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009231239,0.0009257041,0.0007027803,0.0004075937,0.00042999804,0.00084489153,0.0010040853,0.00075003086,0.0024479772],"category_scores_gemma":[0.0014909017,0.00023066676,0.00039708626,0.00052989146,0.00031623634,0.0009101753,0.0006957286,0.00064801035,0.0007915617],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00096011144,0.00035038107,0.005220787,0.000097378535,0.00020507778,0.00014192308,0.000055208937,0.6405486,0.014456696,0.0029007792,0.011899501,0.3231635],"study_design_scores_gemma":[0.00001404968,0.00003325929,0.0004908148,0.000002288559,0.000011067304,0.000013078032,0.0000070595247,0.9960395,0.0025686377,0.0003693123,0.00044644854,0.0000043133728],"about_ca_topic_score_codex":0.010951032,"about_ca_topic_score_gemma":0.018400269,"teacher_disagreement_score":0.010951032,"about_ca_system_score_codex":0.0006154942,"about_ca_system_score_gemma":0.0011874501,"threshold_uncertainty_score":0.02177459},"labels":[],"label_agreement":null},{"id":"W4413125769","doi":"10.1109/jstars.2025.3596770","title":"Dual-Branch Soft Attention Network With Multiscale Feature Interaction for Hyperspectral and LiDAR Data Classification","year":2025,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Changsha University of Science and Technology","keywords":"Hyperspectral imaging; Computer science; Lidar; Feature (linguistics); Artificial intelligence; Dual (grammatical number); Pattern recognition (psychology); Feature extraction; Remote sensing; Geology","score_opus":0.0328717889898559,"score_gpt":0.25774413746201846,"score_spread":0.22487234847216256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413125769","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.066879764,0.0010087237,0.9263331,0.00046016995,0.000111237045,0.00008490624,0.00011971804,0.0012689454,0.0037334387],"genre_scores_gemma":[0.91990125,0.0003683521,0.07313316,0.00050848856,0.00018044037,0.00014005616,0.00040286698,0.00007822228,0.0052872496],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995209,0.00008360536,0.00002168652,0.00014913424,0.0001285805,0.000096141936],"domain_scores_gemma":[0.9995695,0.00017113544,0.000046612757,0.00004385207,0.00012939249,0.000039571583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007690694,0.0011083996,0.00085475104,0.0008921514,0.00050641404,0.0007202633,0.001644851,0.0010715342,0.0022125768],"category_scores_gemma":[0.0014875677,0.00029653555,0.0007870455,0.00082329,0.0005291064,0.0017992912,0.001567417,0.001199043,0.00043121798],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003883317,0.00038321683,0.0032612812,0.00014836749,0.00015417246,0.00021195562,0.00021180567,0.3147022,0.017166944,0.0091466205,0.006065965,0.64815915],"study_design_scores_gemma":[0.0000039101274,0.000028911389,0.000299773,0.0000036492825,0.000017449765,0.00001534742,0.000010116017,0.99572337,0.0013283807,0.002258334,0.00030600317,0.0000046890214],"about_ca_topic_score_codex":0.0076311054,"about_ca_topic_score_gemma":0.007670428,"teacher_disagreement_score":0.0076311054,"about_ca_system_score_codex":0.0010293007,"about_ca_system_score_gemma":0.00069052866,"threshold_uncertainty_score":0.015173376},"labels":[],"label_agreement":null},{"id":"W4413306939","doi":"10.1080/07038992.2025.2532528","title":"Self-Supervised Deep Learning for Urban Land Cover Classification from Very High Resolution Imagery","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Natural Sciences and Engineering Research Council of Canada; Institut National de la Recherche Scientifique","funders":"","keywords":"Land cover; Geography; Satellite imagery; Remote sensing; Aerial imagery; Cartography; Cover (algebra); High resolution; Deep learning; Land use; Artificial intelligence; Physical geography; Computer science; Ecology; Engineering; Biology","score_opus":0.0125221850229363,"score_gpt":0.2083055235858787,"score_spread":0.1957833385629424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413306939","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35358557,0.00071429706,0.63111,0.0005479344,0.00009294274,0.00013784917,0.001266911,0.007573066,0.0049714358],"genre_scores_gemma":[0.82329196,0.00020719337,0.16804513,0.00021241207,0.000032235926,0.00009373717,0.0036068219,0.0001501619,0.0043603443],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997315,0.000046849043,0.000011953463,0.00008484399,0.000060986935,0.00006389761],"domain_scores_gemma":[0.9996489,0.00010489755,0.000039827148,0.000076524775,0.00010856849,0.000021246798],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006177491,0.0005841901,0.00041566274,0.0006239586,0.00025179726,0.0005275581,0.0010499606,0.0006320631,0.0014231143],"category_scores_gemma":[0.0010601727,0.0003056868,0.0006291176,0.0006679763,0.00042253084,0.0009674412,0.0006823689,0.0011593064,0.00056021527],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030038002,0.000434657,0.0058180457,0.00014240612,0.00014976459,0.00019381642,0.00017926849,0.4803685,0.02947882,0.0024425557,0.008281371,0.47221044],"study_design_scores_gemma":[0.000004042347,0.000016913516,0.0008810994,0.0000038407748,0.000005431288,0.000011682491,0.000019549534,0.9936372,0.0042260294,0.00083933526,0.00035031902,0.0000045204315],"about_ca_topic_score_codex":0.009934988,"about_ca_topic_score_gemma":0.020245472,"teacher_disagreement_score":0.009934988,"about_ca_system_score_codex":0.0007339214,"about_ca_system_score_gemma":0.00082137604,"threshold_uncertainty_score":0.01975435},"labels":[],"label_agreement":null},{"id":"W4413743190","doi":"10.18280/ijsdp.200712","title":"Integrating NTL Imagery and Environmental Indicators for Poverty Mapping in India: An Approach Toward SDG-1","year":2025,"lang":"en","type":"article","venue":"International Journal of Sustainable Development and Planning","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Poverty; Environmental resource management; Environmental planning; Geography; Environmental science; Natural resource economics; Economics; Economic growth","score_opus":0.010919495667350678,"score_gpt":0.2313798290433709,"score_spread":0.22046033337602022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413743190","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6834172,0.00096807483,0.29503158,0.0032788897,0.00009125484,0.00021972116,0.0023138702,0.0012833093,0.0133961085],"genre_scores_gemma":[0.9423184,0.0003471675,0.054594073,0.00012163027,0.00002235501,0.00006165057,0.00084056094,0.000025117068,0.0016690681],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99979466,0.00006321424,0.000010118735,0.000044354525,0.000039239276,0.00004841902],"domain_scores_gemma":[0.9998031,0.000039511287,0.000031258205,0.000027190046,0.000079382306,0.000019543544],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041971356,0.00045329912,0.00022044593,0.001226469,0.00027709708,0.00092808856,0.0009549691,0.00032710558,0.0006828578],"category_scores_gemma":[0.0008225913,0.00021651266,0.00051419315,0.0013310157,0.0003680942,0.0006598428,0.0014473674,0.00052623777,0.0001887296],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001980348,0.00035425945,0.10884594,0.0003497007,0.00021118515,0.0006155129,0.0006741333,0.47063646,0.00877842,0.011195435,0.006016971,0.392124],"study_design_scores_gemma":[0.000007936359,0.000063639774,0.028981118,0.000046706842,0.000049389077,0.000083900995,0.0008388495,0.9594451,0.0031365582,0.003910757,0.0034057766,0.000030305227],"about_ca_topic_score_codex":0.032517325,"about_ca_topic_score_gemma":0.033608295,"teacher_disagreement_score":0.032517325,"about_ca_system_score_codex":0.0007911936,"about_ca_system_score_gemma":0.0013282804,"threshold_uncertainty_score":0.06465608},"labels":[],"label_agreement":null},{"id":"W4414051071","doi":"10.1016/j.engappai.2025.112187","title":"Land use and land cover change detection from multisource satellite imagery – A hybrid convolutional neural network approach","year":2025,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Land cover; Convolutional neural network; Change detection; Satellite imagery; Land use; Normalized Difference Vegetation Index; Satellite; Vegetation (pathology); Preprocessor","score_opus":0.030587821622014014,"score_gpt":0.23436069982789098,"score_spread":0.20377287820587697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414051071","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48013416,0.001528806,0.5113859,0.00041257357,0.00013719682,0.00007397439,0.0003963064,0.0007601383,0.005170999],"genre_scores_gemma":[0.9398275,0.00033552834,0.05379548,0.00006378918,0.000060442548,0.000029789237,0.0004485145,0.00003137498,0.00540767],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99985206,0.000016491334,0.000007839381,0.000046381927,0.000041965042,0.00003524448],"domain_scores_gemma":[0.9998387,0.000054761345,0.000022543778,0.000018624787,0.000052654836,0.000012725712],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003547034,0.00047006115,0.00036539906,0.001061668,0.00022584316,0.00056215376,0.0006004225,0.0005892256,0.00067174213],"category_scores_gemma":[0.0005372892,0.00029213165,0.0005893267,0.00068574195,0.0002495666,0.00073782116,0.00045728913,0.0003679007,0.00019783399],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002924445,0.00039958325,0.014935206,0.00012315456,0.0003405638,0.0002601328,0.00009948652,0.40309614,0.055967942,0.0032326526,0.0017059676,0.5195468],"study_design_scores_gemma":[0.0000021962737,0.000014178512,0.0039913687,0.00000319209,0.00002239082,0.000021928863,0.000011401939,0.99282104,0.0024040018,0.0004685612,0.00023414512,0.000005529261],"about_ca_topic_score_codex":0.015883664,"about_ca_topic_score_gemma":0.022181338,"teacher_disagreement_score":0.015883664,"about_ca_system_score_codex":0.0004140652,"about_ca_system_score_gemma":0.0004421778,"threshold_uncertainty_score":0.031582415},"labels":[],"label_agreement":null},{"id":"W4414119930","doi":"10.1016/j.jag.2025.104831","title":"Early Deforestation Detection in the Tropics using L-band SAR and Optical multi-sensor data and Bayesian Statistics","year":2025,"lang":"en","type":"article","venue":"International Journal of Applied Earth Observation and Geoinformation","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ste. Anne's Hospital; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Japan Aerospace Exploration Agency; National Aeronautics and Space Administration","keywords":"Synthetic aperture radar; Change detection; Deforestation (computer science); Bayesian probability; Lag; Satellite; Radar; Climate change","score_opus":0.031327671680705646,"score_gpt":0.2693736626989809,"score_spread":0.23804599101827523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414119930","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68604404,0.0009244033,0.30794388,0.0003085327,0.00003444635,0.000062389634,0.00046377728,0.0007256278,0.0034929225],"genre_scores_gemma":[0.941421,0.00022434129,0.057397064,0.000068297464,0.000023605764,0.000024367266,0.00042553496,0.000024916399,0.00039093386],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991873,0.00027094543,0.000044581444,0.0001758508,0.00024836857,0.00007302684],"domain_scores_gemma":[0.9981822,0.00086653035,0.00043356855,0.0001520257,0.00029777284,0.00006794259],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023475806,0.00067843805,0.00038410493,0.0013429117,0.000199872,0.00073140755,0.0005315778,0.00052659475,0.0003371649],"category_scores_gemma":[0.0048527587,0.00037542733,0.00059801724,0.0006978947,0.00029610642,0.0011484727,0.000703134,0.0004542438,0.0001554714],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044719214,0.00030657896,0.22294493,0.00022116008,0.0004258133,0.00023037466,0.00028309936,0.53698367,0.027831981,0.0030840638,0.001149651,0.20609146],"study_design_scores_gemma":[0.000009249277,0.00007110531,0.0324227,0.000016873055,0.000034514876,0.000074889474,0.00004350188,0.96364635,0.0022777312,0.0009788582,0.00039646804,0.000027688713],"about_ca_topic_score_codex":0.009593953,"about_ca_topic_score_gemma":0.016051915,"teacher_disagreement_score":0.009593953,"about_ca_system_score_codex":0.00055750663,"about_ca_system_score_gemma":0.0005793019,"threshold_uncertainty_score":0.019076228},"labels":[],"label_agreement":null},{"id":"W4414125552","doi":"10.1080/07038992.2025.2551533","title":"MSDANet: A Multiscale Dual-Channel Spatial Attention Network with Depthwise Separable Convolution for Hyperspectral Image Classification","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Natural Science Foundation of Guangdong Province","keywords":"Hyperspectral imaging; Pattern recognition (psychology); Feature extraction; Benchmark (surveying); Contextual image classification; Convolution (computer science); Identification (biology); Feature (linguistics); Spatial analysis; Convolutional neural network","score_opus":0.013359398701488393,"score_gpt":0.22476560112399718,"score_spread":0.2114062024225088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414125552","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043234754,0.0010679256,0.9496647,0.00034569402,0.00014878185,0.00006122619,0.00026454675,0.0017875604,0.0034246987],"genre_scores_gemma":[0.7323251,0.00088055717,0.25365114,0.00067567604,0.0001540193,0.00017281897,0.0012884826,0.00017516104,0.0106771],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997801,0.000035811194,0.00001004241,0.00006232564,0.00006579278,0.000045938916],"domain_scores_gemma":[0.9997509,0.000078738725,0.000027761596,0.00002688179,0.00009175514,0.00002394697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042350937,0.0008506545,0.00066768215,0.00062850956,0.00030781995,0.0005956023,0.0014402432,0.000684502,0.0016387977],"category_scores_gemma":[0.0010404716,0.00028801628,0.00070241274,0.0006824281,0.00037626896,0.001048682,0.0011399824,0.00093079044,0.00048349728],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030448206,0.00021942693,0.0033555806,0.0001579462,0.00019519268,0.00019095895,0.000107215346,0.3450745,0.034668393,0.007817133,0.010771811,0.5971374],"study_design_scores_gemma":[0.000005313937,0.00003007764,0.000304921,0.0000052178693,0.00001653055,0.00003090641,0.000010085648,0.99312615,0.0032507172,0.0020890937,0.0011242243,0.0000066916973],"about_ca_topic_score_codex":0.007277193,"about_ca_topic_score_gemma":0.011364393,"teacher_disagreement_score":0.007277193,"about_ca_system_score_codex":0.0008140404,"about_ca_system_score_gemma":0.0007890896,"threshold_uncertainty_score":0.014469683},"labels":[],"label_agreement":null},{"id":"W4414440865","doi":"10.23977/acss.2025.090311","title":"Multi-Scale Graph Wavelet Convolution for Hyperspectral-LiDAR Urban Scene Classification","year":2025,"lang":"en","type":"article","venue":"Advances in Computer Signals and Systems","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Wavelet; Graph; Pattern recognition (psychology); Weight function; Cut; Perceptron; Pixel; Robustness (evolution); Preprocessor","score_opus":0.022206419946986748,"score_gpt":0.2665525997182345,"score_spread":0.24434617977124773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414440865","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31168416,0.00096662453,0.6641693,0.0005901001,0.0002183658,0.00020166436,0.0023064765,0.012543545,0.0073196907],"genre_scores_gemma":[0.6933166,0.0002063331,0.29596043,0.00016814661,0.000036906204,0.000108843305,0.0054249177,0.0005745847,0.0042032246],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992387,0.00020068586,0.000029073952,0.00020022456,0.00022909015,0.00010227963],"domain_scores_gemma":[0.99933976,0.00020900193,0.000050895545,0.0001997371,0.00015656553,0.00004404491],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017997228,0.0010619856,0.0005442088,0.0010518337,0.00036798118,0.0006946166,0.0010569688,0.0009182132,0.0026845245],"category_scores_gemma":[0.0031716817,0.00024461755,0.0007184942,0.0012879187,0.0004084716,0.0010727942,0.00081102434,0.0009857964,0.001301157],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005632205,0.00036707052,0.004811622,0.0002505139,0.00024717115,0.00013556074,0.00010010226,0.4925241,0.023208976,0.006482252,0.019813243,0.45149612],"study_design_scores_gemma":[0.0000117448735,0.00005187159,0.0014952744,0.0000079004,0.000009925655,0.000031637333,0.000026456553,0.9870508,0.007380766,0.0022236104,0.0017028449,0.0000073043484],"about_ca_topic_score_codex":0.008365982,"about_ca_topic_score_gemma":0.012525425,"teacher_disagreement_score":0.008365982,"about_ca_system_score_codex":0.0007128427,"about_ca_system_score_gemma":0.00077145785,"threshold_uncertainty_score":0.016634583},"labels":[],"label_agreement":null},{"id":"W4414706405","doi":"10.21203/rs.3.rs-7626645/v1","title":"RMAU-NET: A Residual-Multihead-Attention U-Net Architecture forLandslide Segmentation and Detection from Remote Sensing Images","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Landslide; Segmentation; Task (project management); Image segmentation; Architecture; Artificial neural network","score_opus":0.031015086404379107,"score_gpt":0.3335019726388494,"score_spread":0.3024868862344703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414706405","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027838342,0.0011081939,0.92285377,0.00028665946,0.00024737907,0.00015189461,0.0015412683,0.040948268,0.0050240997],"genre_scores_gemma":[0.31895232,0.00067574345,0.6450238,0.00082429865,0.00012770873,0.00029461292,0.006103779,0.0013897008,0.02660799],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99974245,0.00002610646,0.00001423358,0.0001188534,0.000047383368,0.00005092606],"domain_scores_gemma":[0.99974006,0.00006138425,0.000019547382,0.00007043312,0.00007467382,0.000033888937],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005694067,0.0014212818,0.001099782,0.0010704125,0.0006567041,0.0012914612,0.0036789947,0.0017085702,0.011783983],"category_scores_gemma":[0.0009049739,0.00073817663,0.0009799233,0.0009856087,0.00055219437,0.0018383013,0.0018629647,0.0010822667,0.0044687726],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00092239684,0.0003386975,0.0017902022,0.00034045498,0.00027120937,0.00019756019,0.00009616991,0.07689075,0.030887315,0.00844567,0.030271765,0.84954774],"study_design_scores_gemma":[0.000021725527,0.00011622667,0.0004772802,0.00003054117,0.00006492716,0.000049480255,0.000026026564,0.9684958,0.017870946,0.0068635703,0.005960549,0.000022969938],"about_ca_topic_score_codex":0.0224171,"about_ca_topic_score_gemma":0.042182278,"teacher_disagreement_score":0.0224171,"about_ca_system_score_codex":0.0011934686,"about_ca_system_score_gemma":0.0012818084,"threshold_uncertainty_score":0.044573247},"labels":[],"label_agreement":null},{"id":"W4414871360","doi":"10.1109/lgrs.2025.3616338","title":"MixerSENet: A Lightweight Framework for Efficient Hyperspectral Image Classification","year":2025,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Hyperspectral imaging; Block (permutation group theory); Pattern recognition (psychology); Benchmark (surveying); Feature extraction; Contextual image classification; Image (mathematics); Image resolution; Inference","score_opus":0.01331276527486414,"score_gpt":0.24943040196504992,"score_spread":0.2361176366901858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414871360","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043255193,0.00036274546,0.98229915,0.00016341395,0.00010078804,0.00009347917,0.00070519635,0.010277914,0.0016717191],"genre_scores_gemma":[0.14554746,0.0009767878,0.82444197,0.0007474992,0.00021641294,0.0006174513,0.009233209,0.0020564925,0.016162656],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9997211,0.000038256447,0.000010855733,0.00009173657,0.00009336249,0.00004474108],"domain_scores_gemma":[0.9997377,0.000070690076,0.000027015793,0.00006474957,0.00007308678,0.000026744756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063343265,0.0016966107,0.00096304534,0.0011340075,0.0005010661,0.0013389189,0.0030222666,0.0010820167,0.0064389473],"category_scores_gemma":[0.0015888179,0.0006303122,0.0011022404,0.0010989221,0.00044483342,0.0022860158,0.0017060798,0.0019112871,0.003322875],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004092697,0.00026150182,0.0020785283,0.0003328169,0.00027266037,0.0002391518,0.00009330966,0.21820644,0.023104139,0.017280646,0.052193142,0.68552834],"study_design_scores_gemma":[0.000017297272,0.000029350416,0.00018401377,0.000012906839,0.00001604159,0.0000557252,0.000016231812,0.9829863,0.004799001,0.006193824,0.0056749983,0.000014396725],"about_ca_topic_score_codex":0.008305388,"about_ca_topic_score_gemma":0.022756912,"teacher_disagreement_score":0.008305388,"about_ca_system_score_codex":0.00090105686,"about_ca_system_score_gemma":0.0013376169,"threshold_uncertainty_score":0.021540403},"labels":[],"label_agreement":null},{"id":"W4415269351","doi":"10.2139/ssrn.5616763","title":"Knowledge-Aware Mamba for Joint Change Detection and Classification from MODIS Times Series","year":2025,"lang":"","type":"preprint","venue":"SSRN Electronic Journal","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Change detection; Leverage (statistics); Series (stratigraphy); Joint (building); Time series","score_opus":0.041139759383553576,"score_gpt":0.2662303830868895,"score_spread":0.22509062370333593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415269351","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05899181,0.0010824064,0.92607075,0.00044417527,0.00020254188,0.000103115344,0.0019367273,0.009520554,0.0016480498],"genre_scores_gemma":[0.6191616,0.00041571274,0.37166736,0.00028799067,0.00021055556,0.00024748044,0.0050144983,0.00031747477,0.0026772877],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996942,0.00005592837,0.000020649673,0.000118845506,0.00005945232,0.000050984243],"domain_scores_gemma":[0.99949956,0.00023731533,0.000038804592,0.00009726704,0.00009953568,0.000027486993],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00090720516,0.00084806216,0.0013412614,0.00082807126,0.00047532594,0.0010895521,0.0014466537,0.0010208461,0.002122945],"category_scores_gemma":[0.0028452775,0.0004617051,0.0009929835,0.00093377545,0.0002930712,0.0012986356,0.0012160654,0.0013929133,0.0014216811],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010066326,0.00041021247,0.004440978,0.0002916072,0.00035950314,0.00016770924,0.00014400485,0.22939357,0.030312905,0.0050345026,0.011885847,0.71655244],"study_design_scores_gemma":[0.0000118697735,0.000023539544,0.0007943052,0.000006541385,0.000021520538,0.000019087556,0.000022439666,0.9913886,0.0026102562,0.0040826895,0.001010256,0.00000899915],"about_ca_topic_score_codex":0.0105024325,"about_ca_topic_score_gemma":0.015102799,"teacher_disagreement_score":0.0105024325,"about_ca_system_score_codex":0.00050856936,"about_ca_system_score_gemma":0.00094170746,"threshold_uncertainty_score":0.020882607},"labels":[],"label_agreement":null},{"id":"W4415338782","doi":"10.2139/ssrn.5626331","title":"Segmentation of Overlapping Pixels in Hyperspectral Document Images by Statistical Techniques","year":2025,"lang":"","type":"preprint","venue":"SSRN Electronic Journal","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Hyperspectral imaging; Segmentation; Pattern recognition (psychology); Pixel; RGB color model; Image segmentation; Class (philosophy); Ground truth","score_opus":0.006505125476459373,"score_gpt":0.2666543707289642,"score_spread":0.2601492452525048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415338782","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07576299,0.00060435064,0.920394,0.00015251391,0.000044454013,0.0000704931,0.00030336913,0.0012084447,0.0014593867],"genre_scores_gemma":[0.39397025,0.0008842275,0.599244,0.000099328616,0.00017005403,0.00016658145,0.0018380458,0.00058329524,0.0030442623],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.999483,0.00007924677,0.000041422056,0.00013707731,0.00018378113,0.000075512005],"domain_scores_gemma":[0.9990865,0.00042808746,0.00012991828,0.00011174157,0.00020829022,0.00003543742],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058808166,0.00072465034,0.0007777513,0.0036477179,0.00046547322,0.0012459565,0.0005654427,0.0007106135,0.0013256397],"category_scores_gemma":[0.0014635385,0.0004410847,0.0010193931,0.0032393315,0.00075814425,0.0009104675,0.0005778444,0.000676662,0.0010530931],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042934,0.00023969337,0.0039740945,0.00036191999,0.00012433765,0.00018463041,0.00025987744,0.063329905,0.25038144,0.0054756044,0.0026595057,0.6725796],"study_design_scores_gemma":[0.000018997467,0.0001244472,0.01790408,0.000036929196,0.00012762383,0.00033358534,0.00017933149,0.86857617,0.09825186,0.008865176,0.0055382894,0.000043537926],"about_ca_topic_score_codex":0.0025790979,"about_ca_topic_score_gemma":0.0034228717,"teacher_disagreement_score":0.0036477179,"about_ca_system_score_codex":0.000416274,"about_ca_system_score_gemma":0.0009912523,"threshold_uncertainty_score":0.005128145},"labels":[],"label_agreement":null},{"id":"W4415428460","doi":"10.1016/j.engappai.2025.112878","title":"GMFIMamba: Remote sensing change detection based on group Mamba feature interaction","year":2025,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"National Natural Science Foundation of China","keywords":"Change detection; Convolution (computer science); Feature (linguistics); Feature extraction; Convolutional neural network; Field (mathematics); Satellite","score_opus":0.024581767964227733,"score_gpt":0.26803579084048196,"score_spread":0.24345402287625423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415428460","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19977783,0.0005474356,0.7239105,0.0002993053,0.00027564578,0.0004500307,0.0033877152,0.061519153,0.009832293],"genre_scores_gemma":[0.52466303,0.000105526226,0.4593636,0.00015307395,0.00006777261,0.00040098702,0.0048312717,0.0007378692,0.009676819],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999871,0.000015580865,0.0000033305894,0.000032630272,0.000050375675,0.000027058515],"domain_scores_gemma":[0.9999075,0.000015291273,0.000009807941,0.000024553981,0.000028707362,0.000014188899],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022776451,0.0004801015,0.00057486806,0.00083387207,0.00038939185,0.00042495204,0.0008610689,0.00047520472,0.0051813466],"category_scores_gemma":[0.0004480251,0.00020169087,0.00036166798,0.0005212039,0.00014348366,0.0005970089,0.0007086614,0.0003920739,0.0015784642],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013769511,0.0003264838,0.011690174,0.0002420489,0.00024247574,0.0003453607,0.00019851944,0.008834391,0.25215483,0.002472221,0.02759618,0.6945203],"study_design_scores_gemma":[0.00015132429,0.00033901416,0.035792436,0.000018795477,0.00009660456,0.00041834585,0.00012829198,0.8398724,0.08816318,0.0018419335,0.033088144,0.0000894447],"about_ca_topic_score_codex":0.004080321,"about_ca_topic_score_gemma":0.008199314,"teacher_disagreement_score":0.0051813466,"about_ca_system_score_codex":0.00021899455,"about_ca_system_score_gemma":0.00028723283,"threshold_uncertainty_score":0.017333329},"labels":[],"label_agreement":null},{"id":"W4416240237","doi":"10.48550/arxiv.2511.10604","title":"Multitask GLocal OBIA-Mamba for Sentinel-2 Landcover Mapping","year":2025,"lang":"","type":"preprint","venue":"ArXiv.org","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Convolutional neural network; Land cover; Context (archaeology); Task (project management); Key (lock); Spatial contextual awareness; Feature extraction; Contextual image classification; Deep learning","score_opus":0.06168917082302354,"score_gpt":0.28083975571828046,"score_spread":0.2191505848952569,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416240237","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1075367,0.00072525186,0.8831629,0.0004917686,0.00017007731,0.00009263696,0.0004981846,0.0037485766,0.0035739057],"genre_scores_gemma":[0.70336324,0.00024770355,0.28804833,0.00036438825,0.00009682206,0.00012772727,0.0014744304,0.00020973505,0.006067641],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998568,0.000026911033,0.000005159261,0.000041611675,0.00003578615,0.000033706743],"domain_scores_gemma":[0.99984694,0.000029238896,0.000018997376,0.000036070633,0.000053232376,0.0000154729],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050152885,0.00070397113,0.0003820578,0.0003664526,0.00022029024,0.00041039838,0.00096354546,0.00047817413,0.0013353945],"category_scores_gemma":[0.0007161553,0.0002296433,0.0004815595,0.00032668735,0.00022055062,0.00076124026,0.0009055324,0.00077422033,0.0005440916],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048146414,0.00029691012,0.006780386,0.00015766357,0.00019497634,0.00012216631,0.00012631768,0.3305952,0.08523718,0.0061793723,0.0116494335,0.55817896],"study_design_scores_gemma":[0.0000055944383,0.000025527428,0.00094842014,0.0000035902672,0.000008874657,0.000016041156,0.000014327116,0.99140644,0.0047531053,0.0013769387,0.001435918,0.000005319888],"about_ca_topic_score_codex":0.0060062087,"about_ca_topic_score_gemma":0.014671262,"teacher_disagreement_score":0.0060062087,"about_ca_system_score_codex":0.00046559528,"about_ca_system_score_gemma":0.0007643758,"threshold_uncertainty_score":0.011942506},"labels":[],"label_agreement":null},{"id":"W4416295184","doi":"10.1049/cit2.70080","title":"A Temporal Correlation Networks Based on Interactive Modelling for Remote Sensing Images Change Detection","year":2025,"lang":"en","type":"article","venue":"CAAI Transactions on Intelligence Technology","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Francis Xavier University","funders":"","keywords":"Change detection; Feature (linguistics); Upsampling; Noise (video); Correlation; Object detection; Pattern recognition (psychology)","score_opus":0.028351568410004538,"score_gpt":0.26871466113049963,"score_spread":0.2403630927204951,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416295184","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13401636,0.00043536426,0.8579466,0.00037852422,0.000083838626,0.00010475222,0.0008389257,0.0034112467,0.0027843032],"genre_scores_gemma":[0.81749964,0.00028033974,0.17679623,0.0001780222,0.000063830885,0.000161601,0.002083608,0.0001905184,0.0027462174],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996804,0.000074501986,0.000016678443,0.000113647584,0.00006185091,0.00005287463],"domain_scores_gemma":[0.9992219,0.0003862664,0.000085497064,0.00009439064,0.00017824149,0.000033641325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007508114,0.0008252968,0.0005436438,0.001162617,0.0003670382,0.00075618457,0.0011467957,0.0006332117,0.0013045477],"category_scores_gemma":[0.002266471,0.0003973684,0.0008086039,0.0012496469,0.0003820449,0.0013520425,0.0007475883,0.0009512147,0.00039112516],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021766884,0.00009843381,0.002725438,0.00004329083,0.00007825877,0.00009838181,0.000060679755,0.8944588,0.0036391504,0.0033831864,0.001906022,0.0932907],"study_design_scores_gemma":[9.520469e-7,0.000005484517,0.00014311231,0.0000010697038,0.0000030178212,0.000004988612,0.0000022797421,0.9988984,0.00037234285,0.00042853496,0.00013821323,0.0000015423461],"about_ca_topic_score_codex":0.031921472,"about_ca_topic_score_gemma":0.03373636,"teacher_disagreement_score":0.031921472,"about_ca_system_score_codex":0.0014731137,"about_ca_system_score_gemma":0.00074913335,"threshold_uncertainty_score":0.06347132},"labels":[],"label_agreement":null},{"id":"W4416683364","doi":"10.18280/mmep.121015","title":"Deep Learning Based Remote Sensing Image Annotation Based on Semantic and Contextual Information","year":2025,"lang":"","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Deep learning; Annotation; Image (mathematics); Image retrieval; Remote sensing application","score_opus":0.012837634429276528,"score_gpt":0.20943264269285522,"score_spread":0.1965950082635787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416683364","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07785051,0.000580549,0.9121116,0.00036908116,0.0001150429,0.00008320938,0.0009721907,0.0033810043,0.0045367945],"genre_scores_gemma":[0.6817327,0.00078192074,0.30414966,0.00030678802,0.00013463067,0.00013546458,0.004026513,0.0004832592,0.00824893],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995734,0.000058935067,0.000021933494,0.00015462952,0.00010886126,0.000082241626],"domain_scores_gemma":[0.99950075,0.00010345862,0.00006874572,0.00013714419,0.00015950008,0.000030290044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051510805,0.000940286,0.00093903666,0.0018862125,0.00047900333,0.0012626752,0.0011555881,0.001143546,0.0023177024],"category_scores_gemma":[0.0011648434,0.00039441764,0.0009972559,0.0018343009,0.00067195925,0.0019556615,0.0012470358,0.0011587704,0.0018354903],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00060022605,0.00046668458,0.0066619567,0.00042652647,0.00014139588,0.0003980535,0.00023720016,0.14628756,0.1219301,0.015576772,0.01156157,0.695712],"study_design_scores_gemma":[0.0000072168828,0.00003065098,0.0020228208,0.00003385472,0.00004098993,0.00007444037,0.00006267969,0.96655285,0.019853445,0.008251735,0.0030494204,0.00001978306],"about_ca_topic_score_codex":0.0076575875,"about_ca_topic_score_gemma":0.011840918,"teacher_disagreement_score":0.0076575875,"about_ca_system_score_codex":0.0006341614,"about_ca_system_score_gemma":0.00080815057,"threshold_uncertainty_score":0.0152260065},"labels":[],"label_agreement":null},{"id":"W4416706988","doi":"10.1109/lgrs.2025.3637209","title":"Exploiting Self-Adjusted Logical Individual Feature Subspace for Hyperspectral Analysis","year":2025,"lang":"","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Natural Science Foundation of China","keywords":"Hyperspectral imaging; Linear subspace; Subspace topology; Pattern recognition (psychology); Pixel; Feature (linguistics); Fidelity; Feature extraction","score_opus":0.02288103364858025,"score_gpt":0.25235569033135324,"score_spread":0.229474656682773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416706988","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0069275876,0.00006677073,0.992124,0.000030799052,0.000005862427,0.00001700759,0.000037780548,0.00046206912,0.00032809586],"genre_scores_gemma":[0.18772888,0.00025357207,0.8090512,0.00010357359,0.000037470323,0.00014683059,0.00060879154,0.00022593574,0.0018437683],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994875,0.000116400115,0.00002214297,0.00009548988,0.00023600366,0.000042394397],"domain_scores_gemma":[0.9994773,0.00017054814,0.000079917154,0.00011133099,0.0001364795,0.000024406825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008776301,0.00085972267,0.0006233821,0.0010572387,0.00040642952,0.00065768877,0.0009691456,0.0006601089,0.0011436783],"category_scores_gemma":[0.0014745396,0.00030425919,0.0009756446,0.0010918617,0.0006143487,0.0014088692,0.0013250457,0.0007983993,0.00065833627],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001685426,0.00017130848,0.0019641176,0.00018184097,0.00016922259,0.00014918695,0.00025492653,0.3294679,0.08803596,0.0159413,0.0036015862,0.5598942],"study_design_scores_gemma":[0.0000053137264,0.000021566864,0.00027986823,0.0000039757156,0.000010382106,0.00005711907,0.00001813483,0.98623013,0.008472618,0.0036833994,0.0011991691,0.000018374498],"about_ca_topic_score_codex":0.002849232,"about_ca_topic_score_gemma":0.004186202,"teacher_disagreement_score":0.002849232,"about_ca_system_score_codex":0.0004118987,"about_ca_system_score_gemma":0.001069131,"threshold_uncertainty_score":0.0056653023},"labels":[],"label_agreement":null},{"id":"W4417131117","doi":"10.1109/tnnls.2025.3634765","title":"Hyperspectral Anomaly Detection via Hybrid Convolutional and Transformer-Based U-Net With Error Attention Mechanism","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; Natural Science Foundation of Jiangxi Province; Nanjing University of Aeronautics and Astronautics; National Natural Science Foundation of China","keywords":"Hyperspectral imaging; Anomaly detection; Pattern recognition (psychology); Pixel; Anomaly (physics); Feature (linguistics); Feature extraction; Convolution (computer science)","score_opus":0.0071032259688092346,"score_gpt":0.19378248935984768,"score_spread":0.18667926339103844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417131117","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054882083,0.00029167422,0.9410671,0.00011298717,0.00004439862,0.000038556907,0.000059212984,0.0016412098,0.0018627716],"genre_scores_gemma":[0.8338865,0.00021680353,0.16162984,0.00017380579,0.00003154035,0.000052041927,0.00022326938,0.00008170824,0.0037044939],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99972874,0.00003311312,0.00001402301,0.0000775923,0.00009332502,0.000053222175],"domain_scores_gemma":[0.9996892,0.0000906964,0.00004810161,0.000038301045,0.00010725057,0.000026452364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006107905,0.000752265,0.00063527207,0.0006224699,0.00027514558,0.00063686917,0.0013816535,0.0006052191,0.0010849646],"category_scores_gemma":[0.0012559037,0.00024048827,0.00046163113,0.0005352535,0.0005390499,0.0014564237,0.0010576552,0.0006073722,0.00026039066],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00053923874,0.00021800425,0.004069383,0.00011425362,0.00012272713,0.00023341147,0.00009317712,0.3438878,0.048299704,0.011364519,0.0030077298,0.58804995],"study_design_scores_gemma":[0.0000031105308,0.000029309667,0.0002203569,0.000002461961,0.000009913966,0.000035201567,0.0000047057865,0.9903673,0.007881669,0.0011816642,0.00025973874,0.0000046259074],"about_ca_topic_score_codex":0.005310663,"about_ca_topic_score_gemma":0.006031558,"teacher_disagreement_score":0.005310663,"about_ca_system_score_codex":0.0007644053,"about_ca_system_score_gemma":0.000687591,"threshold_uncertainty_score":0.010559499},"labels":[],"label_agreement":null},{"id":"W4417208010","doi":"10.1162/neco.a.1482","title":"Sum-of-Norms Regularized Nonnegative Matrix Factorization","year":2025,"lang":"en","type":"article","venue":"Neural Computation","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Division of Mathematical Sciences; University of Waterloo","keywords":"Non-negative matrix factorization; Rank (graph theory); Low-rank approximation; Matrix decomposition; Hyperspectral imaging; Matrix (chemical analysis); Pairwise comparison; Computational complexity theory; Factorization","score_opus":0.011814079670758825,"score_gpt":0.2665849937158407,"score_spread":0.2547709140450819,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417208010","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025471526,0.0001561747,0.9962142,0.000097580945,0.00004735648,0.000026507081,0.00007565394,0.00019307103,0.00064222986],"genre_scores_gemma":[0.14582378,0.00064133445,0.8482478,0.0002944375,0.00023045277,0.0003267351,0.0010406764,0.00029056513,0.0031041151],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99828327,0.00054319674,0.000094569274,0.00044165502,0.0004952416,0.00014197097],"domain_scores_gemma":[0.99757,0.0012450153,0.00025158576,0.0002900928,0.000549766,0.00009346186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018896024,0.0021280705,0.0016669879,0.00082204863,0.0006580935,0.0012397529,0.0013915309,0.0014554871,0.0024990733],"category_scores_gemma":[0.007250947,0.00063802465,0.0013047024,0.0009890567,0.0013796818,0.0018561506,0.0013804573,0.0026005965,0.0011858693],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022615147,0.00014816588,0.001231311,0.00061561115,0.00019540371,0.00030593682,0.00023764138,0.6350072,0.017743908,0.065403774,0.016417464,0.26246747],"study_design_scores_gemma":[0.000010919936,0.000029365969,0.00011466833,0.00001628326,0.000009667296,0.00004715098,0.000019374746,0.9787174,0.0015013545,0.017512051,0.0020071538,0.000014630784],"about_ca_topic_score_codex":0.0032690817,"about_ca_topic_score_gemma":0.0054393653,"teacher_disagreement_score":0.0032690817,"about_ca_system_score_codex":0.0006425563,"about_ca_system_score_gemma":0.0015144886,"threshold_uncertainty_score":0.009993315},"labels":[],"label_agreement":null},{"id":"W4417279416","doi":"10.1016/j.rsase.2025.101823","title":"MixerCA: An efficient and accurate model for high-performance hyperspectral image classification","year":2025,"lang":"en","type":"article","venue":"Remote Sensing Applications Society and Environment","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Benchmark (surveying); Hyperspectral imaging; Pattern recognition (psychology); Process (computing); Channel (broadcasting); Segmentation; Feature (linguistics); Convolutional neural network; Contextual image classification; Convolution (computer science)","score_opus":0.015282786613061662,"score_gpt":0.2290380914331533,"score_spread":0.21375530482009164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417279416","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007507804,0.00040542296,0.9841591,0.00019341084,0.0001452732,0.00007133192,0.0004780712,0.006381764,0.00065782235],"genre_scores_gemma":[0.17753933,0.0006660547,0.7999372,0.00052574044,0.0002176334,0.00055401196,0.0038389415,0.001390059,0.015331051],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995388,0.00008022553,0.000020036463,0.00012230543,0.0001803784,0.00005831035],"domain_scores_gemma":[0.9995415,0.0001151578,0.000033946668,0.00009479174,0.00018723536,0.000027456968],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010547186,0.0012712756,0.0010479749,0.0008859332,0.0006238623,0.0012967415,0.0023985214,0.0012931131,0.0038462875],"category_scores_gemma":[0.0019285089,0.0005894121,0.0011283874,0.00088334584,0.00037511895,0.001830853,0.0011965449,0.0023825204,0.0024562203],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042816967,0.0003645958,0.001643358,0.00013806371,0.00033548378,0.00006624722,0.00004808281,0.23805244,0.030106425,0.007093893,0.038500004,0.68322325],"study_design_scores_gemma":[0.000008343253,0.0000127303165,0.0002047621,0.00000292321,0.000008978842,0.000010878738,0.0000027858719,0.9928069,0.0033966862,0.0011874485,0.0023466498,0.0000107498745],"about_ca_topic_score_codex":0.013435421,"about_ca_topic_score_gemma":0.021367216,"teacher_disagreement_score":0.013435421,"about_ca_system_score_codex":0.00084744545,"about_ca_system_score_gemma":0.0016582318,"threshold_uncertainty_score":0.026714444},"labels":[],"label_agreement":null},{"id":"W4417338471","doi":"10.1109/iceccme64568.2025.11277836","title":"Design and Conceptual Framework of ARGOS: An AI-Assisted System for Managing Georeferenced Environmental Surveys using UAS","year":2025,"lang":"","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute on Governance","funders":"","keywords":"Metadata; Georeference; Modular design; Consistency (knowledge bases); Drone; Conceptual framework; Systems architecture; Data integration; Environmental data; Architecture","score_opus":0.04570976033986428,"score_gpt":0.27417453793426444,"score_spread":0.22846477759440015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417338471","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024405667,0.0002093627,0.9872558,0.0005582078,0.00008077287,0.00058714056,0.00015396578,0.0017640475,0.006950108],"genre_scores_gemma":[0.07060076,0.00073733553,0.91716623,0.00043040796,0.00010227219,0.0018355161,0.00092396326,0.00048447528,0.007718888],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99807906,0.00042909707,0.00023066318,0.0004242715,0.0006645732,0.00017221145],"domain_scores_gemma":[0.99894124,0.00017516485,0.00013637834,0.00022649195,0.00031964164,0.0002011994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028991492,0.001190926,0.00061641145,0.0013894757,0.0010515403,0.0053178393,0.003992688,0.00255233,0.0038756784],"category_scores_gemma":[0.0023435995,0.000956822,0.0013655657,0.00077048806,0.0037307064,0.0035920115,0.003345496,0.0026312848,0.0023697545],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010251646,0.00019365893,0.001646564,0.00074569916,0.00011276672,0.00089442683,0.0020928695,0.06372489,0.020683639,0.8329804,0.007433472,0.06938921],"study_design_scores_gemma":[0.00011395522,0.00045090626,0.0010626562,0.0006589102,0.00014312378,0.0010192834,0.0009291866,0.34732282,0.02045902,0.15016703,0.477502,0.0001711173],"about_ca_topic_score_codex":0.0068200002,"about_ca_topic_score_gemma":0.004096679,"teacher_disagreement_score":0.0068200002,"about_ca_system_score_codex":0.0018697057,"about_ca_system_score_gemma":0.0046847207,"threshold_uncertainty_score":0.015332401},"labels":[],"label_agreement":null},{"id":"W4417465349","doi":"10.1038/s41598-025-27919-5","title":"Storage tank detection in remote sensing images based on circular bounding boxes and large selective kernel","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Bounding overwatch; Leverage (statistics); Kernel (algebra); Minimum bounding box; Support vector machine; Precision and recall; Intersection (aeronautics)","score_opus":0.007195866969045354,"score_gpt":0.2301725145940873,"score_spread":0.22297664762504193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417465349","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21131195,0.0038730584,0.7341781,0.00043434167,0.00019576547,0.0003039133,0.0040118108,0.039458327,0.0062326975],"genre_scores_gemma":[0.47283882,0.0012802971,0.5068936,0.00033474786,0.00006994937,0.00016938511,0.011934211,0.0010805455,0.005398501],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99910694,0.00009047239,0.00005552938,0.0003304272,0.00025881664,0.00015786206],"domain_scores_gemma":[0.9992379,0.00015765315,0.00011310026,0.00021100711,0.00022784865,0.000052500385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096903293,0.0014936805,0.0012270726,0.002332853,0.0004143633,0.001434275,0.001885087,0.0009395119,0.0017588056],"category_scores_gemma":[0.0019155771,0.00054709066,0.0012544213,0.0015343035,0.00061650516,0.0019564321,0.002106051,0.00091993314,0.002442751],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014477283,0.00032706052,0.011328379,0.0006115385,0.0003233232,0.00041771683,0.00029003134,0.08011154,0.10814741,0.0035998744,0.02160342,0.771792],"study_design_scores_gemma":[0.00005520029,0.00013492313,0.00645604,0.00009475001,0.000106927866,0.00048416396,0.0002465469,0.89387107,0.08635625,0.0023176812,0.009803083,0.00007335733],"about_ca_topic_score_codex":0.013301159,"about_ca_topic_score_gemma":0.018642452,"teacher_disagreement_score":0.013301159,"about_ca_system_score_codex":0.00086789584,"about_ca_system_score_gemma":0.0015462744,"threshold_uncertainty_score":0.026447475},"labels":[],"label_agreement":null},{"id":"W4417508493","doi":"10.36227/techrxiv.176617104.42612822/v1","title":"PatchGraph-MTFormer: A Multitask Patch-Graph Transformer for Hyperspectral Image Analysis","year":2025,"lang":"","type":"preprint","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Hyperspectral imaging; Pattern recognition (psychology); Principal component analysis; Grid; Multi-task learning; Graph; Transformer; Pixel","score_opus":0.016187636558771645,"score_gpt":0.271160769203132,"score_spread":0.25497313264436033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417508493","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032771092,0.0005614619,0.9500133,0.00027534986,0.00011221509,0.00014687817,0.0006273424,0.011939524,0.003552849],"genre_scores_gemma":[0.4604262,0.00063853967,0.51743287,0.00087610766,0.00010112945,0.0002673211,0.00408089,0.0012555631,0.014921483],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998,0.00003162675,0.0000064661813,0.00008291715,0.000048937636,0.000029999457],"domain_scores_gemma":[0.9996749,0.000090407535,0.000026528203,0.00009190413,0.00007730024,0.00003885247],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038940003,0.0013355616,0.00068690587,0.00064371596,0.00029012878,0.00054892665,0.0021954544,0.00082248467,0.0051694084],"category_scores_gemma":[0.0010977105,0.00039257845,0.00094292365,0.00080073794,0.00044681598,0.0016402815,0.0013516376,0.0011613894,0.0022289972],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038188105,0.0003460036,0.0024737976,0.00024631547,0.00023799151,0.0002762678,0.00014462088,0.17581324,0.05741535,0.007300777,0.026134979,0.72922885],"study_design_scores_gemma":[0.000026852837,0.000117647076,0.0005967331,0.0000075095368,0.000036395417,0.00011489701,0.000038785973,0.97789556,0.010441449,0.0069493847,0.003760691,0.00001415539],"about_ca_topic_score_codex":0.008086318,"about_ca_topic_score_gemma":0.022617288,"teacher_disagreement_score":0.008086318,"about_ca_system_score_codex":0.0007493125,"about_ca_system_score_gemma":0.0008937169,"threshold_uncertainty_score":0.017293453},"labels":[],"label_agreement":null},{"id":"W569391","doi":"10.22260/isarc2013/0039","title":"Image-Based Change Detection for Bridge Inspection","year":2013,"lang":"en","type":"article","venue":"Proceedings of the ... ISARC","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Concordia University","keywords":"Change detection; Computer science; Artificial intelligence; Computer vision; Process (computing); Background subtraction; Visual inspection; Bridge (graph theory); Digital image; Image processing; Image (mathematics); Pattern recognition (psychology); Pixel","score_opus":0.02878606335900784,"score_gpt":0.22146262328902752,"score_spread":0.19267655993001967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W569391","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02773991,0.00092043565,0.96702677,0.00012031489,0.00007352822,0.000093337265,0.00015045775,0.0013958802,0.0024793507],"genre_scores_gemma":[0.34480765,0.0012102983,0.6507283,0.00012608837,0.0000962492,0.00012824948,0.00041784986,0.000110760586,0.002374412],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99961275,0.000054369244,0.000016508076,0.0000769014,0.00020730752,0.000032047887],"domain_scores_gemma":[0.99963725,0.00008790097,0.000058310874,0.000055868724,0.00014134863,0.000019363551],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037134028,0.00037138385,0.0005092441,0.002070946,0.00016271933,0.00059841323,0.0006297211,0.000772094,0.0015365741],"category_scores_gemma":[0.0010679979,0.00022872553,0.00042996608,0.0013747364,0.0003927744,0.00076816184,0.00046205622,0.0004851729,0.0009263372],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021874472,0.00012887934,0.0021978945,0.00029784514,0.000048194943,0.0001654217,0.00008793359,0.021845384,0.17501578,0.0036249394,0.0031904504,0.79317856],"study_design_scores_gemma":[0.000022991735,0.00019604705,0.010536598,0.00004254839,0.00006913389,0.0005929952,0.0000889965,0.8701305,0.10294475,0.0035782948,0.011739833,0.000057284],"about_ca_topic_score_codex":0.001157949,"about_ca_topic_score_gemma":0.0012023797,"teacher_disagreement_score":0.002070946,"about_ca_system_score_codex":0.0003513426,"about_ca_system_score_gemma":0.00025578198,"threshold_uncertainty_score":0.005140364},"labels":[],"label_agreement":null},{"id":"W597090566","doi":"10.1016/j.procs.2015.05.157","title":"A Fuzzy Decision Tree for Processing Satellite Images and Landsat Data","year":2015,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; Western University","funders":"","keywords":"Computer science; Decision tree; Satellite; Fuzzy logic; Remote sensing; Tree (set theory); Data mining; Artificial intelligence; Geology","score_opus":0.0646452796961345,"score_gpt":0.28928343866312173,"score_spread":0.22463815896698724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W597090566","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006380232,0.00027457307,0.99160635,0.00006779019,0.000050364615,0.000079862504,0.00012811647,0.0002905778,0.0011221276],"genre_scores_gemma":[0.10867097,0.00041014905,0.88870996,0.00007429939,0.000048557686,0.00020685518,0.00045011297,0.000027265893,0.0014017341],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992061,0.00019738803,0.000064899075,0.000113812275,0.0003707144,0.000047116755],"domain_scores_gemma":[0.9993888,0.00027889124,0.000043428336,0.00002945264,0.0002314832,0.000027807813],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011971662,0.00055283925,0.000548051,0.0012122523,0.0005853786,0.0007773719,0.0008536003,0.0006391086,0.0018548277],"category_scores_gemma":[0.0023978117,0.00017104982,0.00090660155,0.0016431115,0.00023643071,0.00092811696,0.00035297323,0.000690274,0.0005696624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019916006,0.0001843562,0.0023652953,0.0003867826,0.00012176581,0.00021798527,0.00014687635,0.1985662,0.01450596,0.0223465,0.0053915433,0.75556755],"study_design_scores_gemma":[0.000015822012,0.000099299985,0.0007391798,0.000033359203,0.000027552056,0.000100349076,0.000030087216,0.98056215,0.0041158916,0.00848725,0.005772794,0.000016230293],"about_ca_topic_score_codex":0.0047442857,"about_ca_topic_score_gemma":0.003855448,"teacher_disagreement_score":0.0047442857,"about_ca_system_score_codex":0.0005861882,"about_ca_system_score_gemma":0.000982745,"threshold_uncertainty_score":0.009433329},"labels":[],"label_agreement":null},{"id":"W619223265","doi":"","title":"Urban land-cover mapping and change detection with RADARSAT SAR data using neural network and rule-based classifiers","year":2008,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Land cover; Remote sensing; Support vector machine; Synthetic aperture radar; Artificial neural network; Image resolution; Segmentation; Computer science; Artificial intelligence; Geography; Pattern recognition (psychology); Land use; Engineering","score_opus":0.08841608917372523,"score_gpt":0.2276113524894338,"score_spread":0.13919526331570856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W619223265","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.271895,0.00075755815,0.71994287,0.00019290991,0.00005916848,0.00013120731,0.00030848707,0.0016720112,0.0050408817],"genre_scores_gemma":[0.65682614,0.00033510203,0.3391001,0.00007913606,0.000052156804,0.00009264207,0.0005263982,0.0000382434,0.002949995],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9997018,0.000057169604,0.000023384755,0.00007196476,0.000120645,0.000025040996],"domain_scores_gemma":[0.9995339,0.00017869582,0.00006200507,0.00004944541,0.00015965544,0.000016321454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060928205,0.00037107576,0.0004070924,0.0013717088,0.00017958842,0.0007003149,0.00041453398,0.00047297953,0.0006912351],"category_scores_gemma":[0.0012179809,0.00021133575,0.00033259223,0.0006786864,0.00021084303,0.0007822287,0.00020700016,0.00030765828,0.00041725134],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017975052,0.00031102507,0.022826694,0.00013515177,0.00014745994,0.0002404752,0.00011683434,0.098995686,0.020851694,0.0012175381,0.0014324833,0.8535452],"study_design_scores_gemma":[0.000015737462,0.00007683395,0.014763035,0.000023612654,0.000049039325,0.00013309691,0.000050971335,0.96922845,0.012736178,0.0010852682,0.0018151129,0.000022678807],"about_ca_topic_score_codex":0.0035041797,"about_ca_topic_score_gemma":0.005563933,"teacher_disagreement_score":0.0035041797,"about_ca_system_score_codex":0.0003458953,"about_ca_system_score_gemma":0.00022258586,"threshold_uncertainty_score":0.006967604},"labels":[],"label_agreement":null},{"id":"W6887115841","doi":"10.15468/dl.p4hcgc","title":"Occurrence Download","year":2022,"lang":"en","type":"dataset","venue":"Global Biodiversity Information Facility","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Download; Matching (statistics); Range (aeronautics); Set (abstract data type); Data set","score_opus":0.014856555061625993,"score_gpt":0.20250831815859585,"score_spread":0.18765176309696985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6887115841","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000072216884,0.000030730487,0.00006183444,0.00004021285,0.000014678791,0.0000075884327,0.9984388,0.00061121344,0.00072268385],"genre_scores_gemma":[0.00015209282,0.000023316674,0.00020094853,0.000032999113,0.000002873745,0.000034540582,0.9990687,0.00010684832,0.00037778972],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990023,0.00012751915,0.00012120895,0.00033929225,0.00024793588,0.00016171699],"domain_scores_gemma":[0.99810106,0.0004553801,0.00016133414,0.0005441031,0.0004992718,0.00023894288],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00089407415,0.002330802,0.0015895942,0.004440788,0.0010523219,0.0023845956,0.0031851304,0.0022343083,0.10985602],"category_scores_gemma":[0.004508671,0.00083059096,0.0012509545,0.007913684,0.00046998117,0.0021640584,0.0023381237,0.0021519104,0.19388507],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029388331,0.000016496211,0.00036881302,0.0003609279,0.0000132318255,0.000016965892,0.000019121728,0.00013811028,0.00010931426,0.0003037547,0.997162,0.0014618577],"study_design_scores_gemma":[0.00009205601,0.000011524368,0.0022612917,0.00015272704,0.000014474095,0.00005498462,0.000078745004,0.00031760277,0.00025871253,0.00081313046,0.9959241,0.000020745389],"about_ca_topic_score_codex":0.023950266,"about_ca_topic_score_gemma":0.044879727,"teacher_disagreement_score":0.890144,"about_ca_system_score_codex":0.0016093097,"about_ca_system_score_gemma":0.0021644186,"threshold_uncertainty_score":0.36750495},"labels":[],"label_agreement":null},{"id":"W6891802063","doi":"10.48448/am9m-es87","title":"Evaluating Embedding APIs for Information Retrieval","year":2022,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Embedding; Domain (mathematical analysis); Generalization; Order (exchange); Language model; Key (lock)","score_opus":0.04511703273861628,"score_gpt":0.3456165370082905,"score_spread":0.3004995042696742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6891802063","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5386047,0.023896366,0.3215575,0.0030649016,0.0013456983,0.0019956767,0.009376269,0.061974715,0.03818417],"genre_scores_gemma":[0.77962065,0.0024457423,0.19455759,0.00046920334,0.00034636038,0.0006934429,0.017298225,0.0013666367,0.0032021508],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97934055,0.010925999,0.0023556298,0.0013876165,0.005251574,0.0007386167],"domain_scores_gemma":[0.9688204,0.019770356,0.0016797114,0.005205176,0.0039169495,0.000607379],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014922469,0.0024517763,0.0018754471,0.006675685,0.0009270533,0.0048867944,0.0018550712,0.0023926082,0.0033757847],"category_scores_gemma":[0.06971598,0.00047093662,0.0015482281,0.0056888675,0.0011148227,0.008237348,0.0029980638,0.0017292539,0.0024096693],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003619466,0.0019286409,0.017935496,0.0033322305,0.0010776039,0.00024861508,0.00046954962,0.14811844,0.00901954,0.01400134,0.045639224,0.7546098],"study_design_scores_gemma":[0.0002268268,0.0015461962,0.005241963,0.00015360008,0.00025984948,0.00021050918,0.00030987998,0.96144605,0.010781175,0.010173106,0.009545554,0.000105296305],"about_ca_topic_score_codex":0.008265263,"about_ca_topic_score_gemma":0.008181256,"teacher_disagreement_score":0.014922469,"about_ca_system_score_codex":0.0019931602,"about_ca_system_score_gemma":0.00171815,"threshold_uncertainty_score":0.07891852},"labels":[],"label_agreement":null},{"id":"W6901846267","doi":"10.60692/q4ge6-2jq60","title":"IMPROVING DATA QUALITY AND MANAGEMENT FOR REMOTE SENSING ANALYSIS: USE-CASES AND EMERGING RESEARCH QUESTIONS","year":2023,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Data quality; Data management; Geospatial analysis; Data modeling; Data integration; Big data; Data virtualization; Quality (philosophy)","score_opus":0.2647868819306809,"score_gpt":0.35421004143405216,"score_spread":0.08942315950337126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6901846267","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27746788,0.095700465,0.44707498,0.14129937,0.00073051144,0.00085428375,0.00084732164,0.0010697271,0.03495558],"genre_scores_gemma":[0.7512533,0.027685866,0.21662928,0.0015568123,0.0006422647,0.00019217888,0.0004925841,0.00015424301,0.0013935021],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97758305,0.012471428,0.0014961133,0.0016346057,0.0060590277,0.0007558254],"domain_scores_gemma":[0.92142844,0.04812989,0.006857106,0.008847635,0.013549106,0.0011877895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.039067585,0.00082324294,0.00084176596,0.003658148,0.0013378654,0.00951097,0.002988936,0.0033412217,0.0020310015],"category_scores_gemma":[0.04929772,0.0004894744,0.0009318299,0.009162092,0.0048847264,0.012801156,0.0027615028,0.0020533127,0.00042403996],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031836258,0.0007691557,0.09709398,0.005052352,0.00021803033,0.00071989716,0.004527867,0.0197387,0.006071304,0.17108808,0.013887201,0.68051505],"study_design_scores_gemma":[0.00016077806,0.0011873038,0.08296298,0.009099269,0.00039119253,0.0022020682,0.031295314,0.30377898,0.049987897,0.36874792,0.14977996,0.00040633776],"about_ca_topic_score_codex":0.006251832,"about_ca_topic_score_gemma":0.004341003,"teacher_disagreement_score":0.039067585,"about_ca_system_score_codex":0.0037894808,"about_ca_system_score_gemma":0.0047294507,"threshold_uncertainty_score":0.20661157},"labels":[],"label_agreement":null},{"id":"W6901855280","doi":"10.60692/yykzm-40434","title":"Phenotyping urban built and natural environments with high-resolution satellite images and unsupervised deep learning","year":2023,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Deep learning; Satellite; Cluster analysis; Scale (ratio); Unsupervised learning; Natural (archaeology); Satellite imagery; Scalability; Spatial ecology","score_opus":0.012717553583667085,"score_gpt":0.17216940028902056,"score_spread":0.15945184670535348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6901855280","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73493266,0.00057022675,0.2563211,0.0005831172,0.000070313654,0.00009096191,0.0022967078,0.0018385346,0.003296374],"genre_scores_gemma":[0.88421315,0.00020798366,0.111137986,0.000114465496,0.00003373811,0.00005351517,0.0029910386,0.00009031861,0.0011577358],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998197,0.000039933642,0.000007296995,0.000064937696,0.00003266147,0.000035587193],"domain_scores_gemma":[0.99967,0.000091879854,0.000069910035,0.00006166057,0.00008148585,0.000024927358],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003695685,0.00065103336,0.00025807973,0.0010228904,0.00023873738,0.0006356185,0.0005936354,0.0005043581,0.00044849212],"category_scores_gemma":[0.0011067579,0.00027607314,0.0005527183,0.0011325517,0.00046226857,0.0006605331,0.0006903411,0.0006313578,0.0002705929],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031360873,0.00032123044,0.10115998,0.00019532855,0.0004435989,0.0003552819,0.00058364996,0.5472878,0.05042238,0.003137,0.0060402877,0.28973985],"study_design_scores_gemma":[0.00000842484,0.000029596215,0.028631069,0.000017157638,0.000025651478,0.000045261208,0.00021524593,0.96068704,0.006338312,0.0028972987,0.0010856434,0.000019315406],"about_ca_topic_score_codex":0.021946995,"about_ca_topic_score_gemma":0.045498837,"teacher_disagreement_score":0.021946995,"about_ca_system_score_codex":0.00070710306,"about_ca_system_score_gemma":0.00042930426,"threshold_uncertainty_score":0.043638527},"labels":[],"label_agreement":null},{"id":"W6920393657","doi":"10.60692/1139v-3h974","title":"The Segment Anything Model (SAM) for remote sensing applications: From zero to one shot","year":2023,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Segmentation; Remote sensing application; Field (mathematics); Bounding overwatch; Image segmentation; Minimum bounding box; Software deployment; Adaptability","score_opus":0.08395335360252199,"score_gpt":0.24426665264353759,"score_spread":0.1603132990410156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920393657","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042633273,0.000423809,0.9439106,0.00078036654,0.00013208084,0.00018402639,0.0007346833,0.007795852,0.0034054143],"genre_scores_gemma":[0.4310895,0.0003714273,0.5568361,0.00078769744,0.00012255914,0.0003400271,0.0032083376,0.0010327273,0.0062116324],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991934,0.00017809044,0.000036235895,0.00038971828,0.00013056205,0.00007207668],"domain_scores_gemma":[0.9983656,0.00092910463,0.000095827076,0.00030868204,0.0002135989,0.000087220265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015706762,0.001316527,0.000986713,0.000931017,0.00057393295,0.0016694401,0.0029524937,0.0019530144,0.0034134716],"category_scores_gemma":[0.0043714484,0.00063605385,0.0014444834,0.0007507442,0.0010271168,0.0031152708,0.0016140222,0.002384254,0.0014530392],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010632282,0.00034959093,0.005951787,0.00048278828,0.00020851521,0.00040241395,0.00062145793,0.3650127,0.021997463,0.02099509,0.015729789,0.5671852],"study_design_scores_gemma":[0.000012308148,0.00009038539,0.00046365647,0.000029059975,0.000021807507,0.000069332076,0.000068684174,0.9782177,0.0042751245,0.013511109,0.003223651,0.000017126282],"about_ca_topic_score_codex":0.007546234,"about_ca_topic_score_gemma":0.012745596,"teacher_disagreement_score":0.007546234,"about_ca_system_score_codex":0.0011036857,"about_ca_system_score_gemma":0.0010426755,"threshold_uncertainty_score":0.015004635},"labels":[],"label_agreement":null},{"id":"W6929994638","doi":"10.5281/zenodo.11889255","title":"t1 2021 pdf","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Worksheet; Download; Order (exchange); Income tax; Gross income; State income tax; Tax revenue; Tourism","score_opus":0.02289914658924273,"score_gpt":0.22324552686299678,"score_spread":0.20034638027375407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6929994638","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00024040566,0.00010285862,0.0005127177,0.0010024477,0.0024839665,0.00033958725,0.0050381967,0.0025553117,0.98772454],"genre_scores_gemma":[0.00064947555,0.000103358056,0.00024075762,0.0005114531,0.00033242776,0.00008803941,0.0028726223,0.00082340837,0.9943784],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99904543,0.00006609649,0.00004638678,0.000094765215,0.00055782776,0.00018947321],"domain_scores_gemma":[0.9948354,0.0003950085,0.00011892205,0.00042170097,0.0029917497,0.0012372726],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0009036142,0.0011102632,0.0008427398,0.002332864,0.0026243425,0.009230134,0.0019495367,0.0031983957,0.9580151],"category_scores_gemma":[0.005693285,0.0006982656,0.0009414989,0.0023585057,0.00055754196,0.0047716885,0.0028707883,0.0025493843,0.9335817],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012550187,0.000019194838,0.000025752297,0.000047044876,6.18241e-7,0.000012312551,0.000009471229,0.000017295588,0.00007642497,0.00054467097,0.98268074,0.01655381],"study_design_scores_gemma":[0.000010388382,0.00001456192,0.00025853526,0.000050327126,9.265035e-7,0.000026147593,0.000050507624,0.000043125674,0.00009068459,0.00027673028,0.99917126,0.0000067949845],"about_ca_topic_score_codex":0.008637144,"about_ca_topic_score_gemma":0.010451786,"teacher_disagreement_score":0.041984916,"about_ca_system_score_codex":0.0017199151,"about_ca_system_score_gemma":0.0019379708,"threshold_uncertainty_score":0.059886277},"labels":[],"label_agreement":null},{"id":"W6930376566","doi":"10.5281/zenodo.12109403","title":"Sony drive s autoradio bedienungsanleitung pdf","year":2024,"lang":"de","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Warranty; Download; Notice; Electronics; Electronic equipment","score_opus":0.023862701542268504,"score_gpt":0.23025168355960549,"score_spread":0.206388982017337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930376566","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025164182,0.0066786986,0.032446098,0.002325121,0.004226314,0.000851794,0.04656453,0.04320812,0.8611828],"genre_scores_gemma":[0.0069383755,0.004379717,0.014884428,0.0012609767,0.00054866105,0.00066834094,0.030344512,0.018106468,0.9228685],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992323,0.0000552699,0.000043128846,0.00020577661,0.00036460918,0.00009894384],"domain_scores_gemma":[0.9984059,0.0004117438,0.000053945692,0.0003295705,0.00054068764,0.00025815816],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0010987472,0.0019920573,0.0016311427,0.0028039508,0.0015044436,0.0039842604,0.0019518492,0.0024254415,0.82730645],"category_scores_gemma":[0.0027937975,0.0019657698,0.0012387702,0.0020114752,0.00066800194,0.003888224,0.0020117373,0.0030585318,0.73126835],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038273633,0.00006945171,0.00017821942,0.0010462356,0.000028843198,0.00028105878,0.0000983825,0.00018961896,0.027962988,0.0029503242,0.867123,0.099689014],"study_design_scores_gemma":[0.00005116748,0.00005673633,0.00037088426,0.00010557824,0.000016938122,0.00045298104,0.000046543624,0.00015810569,0.011559442,0.0005902597,0.9865643,0.000026995916],"about_ca_topic_score_codex":0.0019646203,"about_ca_topic_score_gemma":0.0037284847,"teacher_disagreement_score":0.17269355,"about_ca_system_score_codex":0.0010404433,"about_ca_system_score_gemma":0.0013193224,"threshold_uncertainty_score":0.24632639},"labels":[],"label_agreement":null},{"id":"W6930778647","doi":"10.5281/zenodo.12525822","title":"Fitspresso Reviews: March 2024 Updated, What Customers Say About!","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Weight loss; Natural (archaeology); Work (physics); Simple (philosophy); Carry (investment)","score_opus":0.030190761172586737,"score_gpt":0.2541123502435059,"score_spread":0.2239215890709192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930778647","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005125024,0.018793562,0.0009822896,0.015582737,0.03411008,0.0006922607,0.026658148,0.009883874,0.89278466],"genre_scores_gemma":[0.0011537847,0.009913604,0.0009873918,0.009920125,0.0053279283,0.00031784232,0.014527872,0.0025192408,0.9553321],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977113,0.00019190491,0.00019937054,0.0002267589,0.0014462381,0.0002243919],"domain_scores_gemma":[0.9922633,0.000783012,0.0005088045,0.0004518902,0.0045545115,0.0014384768],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0017706975,0.0016806425,0.0017506576,0.0039234255,0.0015910774,0.010783565,0.0019008423,0.0046467925,0.76137966],"category_scores_gemma":[0.012810862,0.0011618957,0.0016493512,0.004167115,0.0006016051,0.006192151,0.0024344064,0.003966776,0.83534884],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001311552,0.00001221197,0.000019080531,0.00018202107,0.0000018279989,0.000016647413,0.0000073080423,0.0000058158153,0.00009007381,0.00016348116,0.98193216,0.017556384],"study_design_scores_gemma":[0.000012645588,0.00000905755,0.00012038775,0.00012010805,0.000002327152,0.000028347162,0.000011098083,0.0000073461933,0.000036030146,0.0000776386,0.99956995,0.000005054486],"about_ca_topic_score_codex":0.00479294,"about_ca_topic_score_gemma":0.009957932,"teacher_disagreement_score":0.23862034,"about_ca_system_score_codex":0.0013911817,"about_ca_system_score_gemma":0.0036764524,"threshold_uncertainty_score":0.3403629},"labels":[],"label_agreement":null},{"id":"W6938906722","doi":"10.60692/qvdhh-e2y10","title":"Phenotyping urban built and natural environments with high-resolution satellite images and unsupervised deep learning","year":2023,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Deep learning; Satellite; Cluster analysis; Scale (ratio); Unsupervised learning; Natural (archaeology); Satellite imagery; Scalability; Spatial ecology","score_opus":0.012717553583667085,"score_gpt":0.17216940028902056,"score_spread":0.15945184670535348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6938906722","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73493266,0.00057022675,0.2563211,0.0005831172,0.000070313654,0.00009096191,0.0022967078,0.0018385346,0.003296374],"genre_scores_gemma":[0.88421315,0.00020798366,0.111137986,0.000114465496,0.00003373811,0.00005351517,0.0029910386,0.00009031861,0.0011577358],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998197,0.000039933642,0.000007296995,0.000064937696,0.00003266147,0.000035587193],"domain_scores_gemma":[0.99967,0.000091879854,0.000069910035,0.00006166057,0.00008148585,0.000024927358],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003695685,0.00065103336,0.00025807973,0.0010228904,0.00023873738,0.0006356185,0.0005936354,0.0005043581,0.00044849212],"category_scores_gemma":[0.0011067579,0.00027607314,0.0005527183,0.0011325517,0.00046226857,0.0006605331,0.0006903411,0.0006313578,0.0002705929],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031360873,0.00032123044,0.10115998,0.00019532855,0.0004435989,0.0003552819,0.00058364996,0.5472878,0.05042238,0.003137,0.0060402877,0.28973985],"study_design_scores_gemma":[0.00000842484,0.000029596215,0.028631069,0.000017157638,0.000025651478,0.000045261208,0.00021524593,0.96068704,0.006338312,0.0028972987,0.0010856434,0.000019315406],"about_ca_topic_score_codex":0.021946995,"about_ca_topic_score_gemma":0.045498837,"teacher_disagreement_score":0.021946995,"about_ca_system_score_codex":0.00070710306,"about_ca_system_score_gemma":0.00042930426,"threshold_uncertainty_score":0.043638527},"labels":[],"label_agreement":null},{"id":"W6948851734","doi":"10.5281/zenodo.11984112","title":"the 10 best-ever anxiety management techniques pdf","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Anxiety; Panic; Mindfulness; Arousal; Stress management; Procrastination","score_opus":0.01904190942837452,"score_gpt":0.22787508411959648,"score_spread":0.20883317469122195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6948851734","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016770001,0.0060742246,0.0033750425,0.004057179,0.0051750923,0.00038823797,0.0064687575,0.006704652,0.9660798],"genre_scores_gemma":[0.00420703,0.0051872833,0.0051375264,0.0014998182,0.0016943129,0.00018763164,0.0030980192,0.0016930054,0.9772954],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992968,0.00007565203,0.00003137399,0.0000538933,0.00043329873,0.00010910257],"domain_scores_gemma":[0.99816895,0.00027676002,0.00008768426,0.000106364605,0.00059072155,0.0007695693],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008922415,0.0010841262,0.0007281452,0.0020863186,0.00065670477,0.0034874838,0.0010533204,0.001296129,0.76895624],"category_scores_gemma":[0.003084371,0.00044486692,0.0012377752,0.0013667464,0.00033375187,0.0028936835,0.0020877863,0.0019077739,0.6246547],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052350202,0.00007257654,0.000084053325,0.0002983135,0.0000045298348,0.000039389888,0.00003390369,0.000041815667,0.00058019743,0.00059814926,0.8005822,0.19761258],"study_design_scores_gemma":[0.0000313908,0.00007235914,0.0015149361,0.00022197606,0.0000078011,0.00026308975,0.00008818305,0.00006072002,0.000423794,0.0008657819,0.99643207,0.000017899572],"about_ca_topic_score_codex":0.0006902625,"about_ca_topic_score_gemma":0.0027528573,"teacher_disagreement_score":0.23104376,"about_ca_system_score_codex":0.00058777793,"about_ca_system_score_gemma":0.0010445457,"threshold_uncertainty_score":0.32955587},"labels":[],"label_agreement":null},{"id":"W6949803429","doi":"10.5281/zenodo.3867762","title":"Ophyiulus curvipes","year":2017,"lang":"fr","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Research (Canada)","funders":"","keywords":"Distribution (mathematics); Natural (archaeology); Process (computing); Habitat","score_opus":0.053725192033484345,"score_gpt":0.2610906577937847,"score_spread":0.20736546576030035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6949803429","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.641616,0.009087912,0.0065820147,0.0005670256,0.0003403119,0.0003494523,0.020056145,0.0010589293,0.32034227],"genre_scores_gemma":[0.94862515,0.0015720567,0.0043621915,0.0002444958,0.000069198264,0.00011019091,0.012687161,0.00007010254,0.032259345],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99987257,0.00000837781,0.0000101036885,0.0000381122,0.000041371353,0.0000294531],"domain_scores_gemma":[0.9999157,0.00001099573,0.000032678225,0.000005854431,0.000016384809,0.000018414346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000095962394,0.00046897808,0.00024217651,0.0013274743,0.0009678819,0.00029885207,0.0003850462,0.00021964949,0.015125875],"category_scores_gemma":[0.00022970287,0.00010639468,0.00015496611,0.0008781956,0.00034832172,0.00056847266,0.0008169338,0.0002973792,0.004107561],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008192181,0.00012257273,0.07099973,0.00076184084,0.00007040223,0.0029202756,0.00093002553,0.001581365,0.12241169,0.005502368,0.028710876,0.7651696],"study_design_scores_gemma":[0.000076417484,0.00022937305,0.7103696,0.00016285785,0.000047212077,0.0049758703,0.00090340135,0.0010497854,0.0063986075,0.0016962086,0.2740493,0.000041357038],"about_ca_topic_score_codex":0.024329687,"about_ca_topic_score_gemma":0.0330362,"teacher_disagreement_score":0.024329687,"about_ca_system_score_codex":0.000547538,"about_ca_system_score_gemma":0.0003121536,"threshold_uncertainty_score":0.050601065},"labels":[],"label_agreement":null},{"id":"W6957869829","doi":"10.60692/chjs9-d6p87","title":"The Segment Anything Model (SAM) for remote sensing applications: From zero to one shot","year":2023,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Segmentation; Remote sensing application; Field (mathematics); Bounding overwatch; Image segmentation; Minimum bounding box; Software deployment; Adaptability","score_opus":0.08395335360252199,"score_gpt":0.24426665264353759,"score_spread":0.1603132990410156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6957869829","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042633273,0.000423809,0.9439106,0.00078036654,0.00013208084,0.00018402639,0.0007346833,0.007795852,0.0034054143],"genre_scores_gemma":[0.4310895,0.0003714273,0.5568361,0.00078769744,0.00012255914,0.0003400271,0.0032083376,0.0010327273,0.0062116324],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991934,0.00017809044,0.000036235895,0.00038971828,0.00013056205,0.00007207668],"domain_scores_gemma":[0.9983656,0.00092910463,0.000095827076,0.00030868204,0.0002135989,0.000087220265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015706762,0.001316527,0.000986713,0.000931017,0.00057393295,0.0016694401,0.0029524937,0.0019530144,0.0034134716],"category_scores_gemma":[0.0043714484,0.00063605385,0.0014444834,0.0007507442,0.0010271168,0.0031152708,0.0016140222,0.002384254,0.0014530392],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010632282,0.00034959093,0.005951787,0.00048278828,0.00020851521,0.00040241395,0.00062145793,0.3650127,0.021997463,0.02099509,0.015729789,0.5671852],"study_design_scores_gemma":[0.000012308148,0.00009038539,0.00046365647,0.000029059975,0.000021807507,0.000069332076,0.000068684174,0.9782177,0.0042751245,0.013511109,0.003223651,0.000017126282],"about_ca_topic_score_codex":0.007546234,"about_ca_topic_score_gemma":0.012745596,"teacher_disagreement_score":0.007546234,"about_ca_system_score_codex":0.0011036857,"about_ca_system_score_gemma":0.0010426755,"threshold_uncertainty_score":0.015004635},"labels":[],"label_agreement":null},{"id":"W6963335959","doi":"10.17611/dp/15159475","title":"Magnetotelluric Transfer Functions","year":2017,"lang":"en","type":"other","venue":"NSF Seismological Facility for the Advancement of Geoscience (SAGE)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Geological Survey of Canada","funders":"","keywords":"Magnetotellurics; Transfer function; Field (mathematics); Transfer (computing); Interpretation (philosophy)","score_opus":0.031860542445158894,"score_gpt":0.25652011215602044,"score_spread":0.22465956971086154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6963335959","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051181773,0.00096647773,0.7173413,0.0007331685,0.0009796653,0.00014658019,0.010062101,0.016359758,0.24829282],"genre_scores_gemma":[0.12913214,0.0026109004,0.20264956,0.00059818674,0.0010244232,0.0003347011,0.034865867,0.005280438,0.6235037],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995809,0.000038698134,0.000012872841,0.00010194755,0.00021381346,0.00005178536],"domain_scores_gemma":[0.99965835,0.000029133189,0.000027699158,0.000115889845,0.00014475045,0.000024157353],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043459074,0.0014995685,0.000542325,0.0015398476,0.00055579847,0.0018107262,0.0012409945,0.0010332331,0.09141372],"category_scores_gemma":[0.001335392,0.00025056943,0.0005178733,0.0020410256,0.00033611112,0.0014936258,0.0011831733,0.0010559064,0.124269634],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012571599,0.00008087673,0.00058513397,0.000168632,0.000028726923,0.000090970745,0.000034599405,0.010837211,0.018245095,0.06073101,0.21553749,0.69353455],"study_design_scores_gemma":[0.000047784633,0.000064814405,0.0026644187,0.00009132803,0.000036147005,0.00037582117,0.00004308102,0.11190797,0.05547705,0.048844736,0.7803601,0.000086726795],"about_ca_topic_score_codex":0.0015755076,"about_ca_topic_score_gemma":0.0021173754,"teacher_disagreement_score":0.09141372,"about_ca_system_score_codex":0.0005361877,"about_ca_system_score_gemma":0.0009196229,"threshold_uncertainty_score":0.30580938},"labels":[],"label_agreement":null},{"id":"W6964442630","doi":"10.25549/wpacards-c8-152224","title":"WPA block face card for household census (block 2104) in Los Angeles","year":2014,"lang":"en","type":"dataset","venue":"University of Southern California Digital Library","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Census; Block (permutation group theory); Face (sociological concept); Quarter (Canadian coin); Population","score_opus":0.011737301703362252,"score_gpt":0.16357658868770622,"score_spread":0.15183928698434396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6964442630","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013560712,0.00003451522,0.00015288274,0.000042422394,0.000028379265,0.000042873322,0.9964765,0.00039360486,0.0014727549],"genre_scores_gemma":[0.0010795349,0.00002848844,0.00026954612,0.000017106577,0.0000071643876,0.0001085062,0.9964187,0.000025999476,0.002044996],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99945194,0.000055904733,0.000043600397,0.00015995902,0.00017390067,0.00011465635],"domain_scores_gemma":[0.998844,0.00010011173,0.00009840355,0.00028174988,0.000537331,0.00013836264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046583652,0.0017794135,0.0011043783,0.0028920828,0.0006598947,0.0010152111,0.0020840932,0.0010034259,0.055006497],"category_scores_gemma":[0.002229079,0.0005364231,0.0006942327,0.0038548307,0.0002922899,0.0008383112,0.0012461726,0.0010837297,0.08203902],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006543488,0.000044741042,0.0017961168,0.00010612067,0.000015303609,0.000020783395,0.000014522991,0.0002377531,0.00011657444,0.00009999527,0.9918401,0.005642513],"study_design_scores_gemma":[0.00027907215,0.000050702416,0.052376274,0.00022662975,0.000044057622,0.00013792103,0.00033145948,0.0034712022,0.0013398569,0.0007271113,0.9409418,0.00007390439],"about_ca_topic_score_codex":0.089564286,"about_ca_topic_score_gemma":0.14571215,"teacher_disagreement_score":0.089564286,"about_ca_system_score_codex":0.0011319224,"about_ca_system_score_gemma":0.0022829173,"threshold_uncertainty_score":0.1840151},"labels":[],"label_agreement":null},{"id":"W6968151554","doi":"10.5281/zenodo.16729453","title":"kujaku11/mt_metadata: v0.4.0","year":2025,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre de Géomatique du Québec","funders":"","keywords":"Workflow; Spectrogram; Window (computing); Closing (real estate)","score_opus":0.026302095435029847,"score_gpt":0.22807976601719052,"score_spread":0.20177767058216067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6968151554","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00064054184,0.0004195731,0.024340242,0.0006576413,0.0012267678,0.0003036763,0.07773099,0.837107,0.057573624],"genre_scores_gemma":[0.010435826,0.00053965236,0.022475114,0.0020553633,0.0005414257,0.0007251204,0.17080536,0.68069226,0.11172988],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976451,0.00023975228,0.00023528482,0.00039915976,0.0010034267,0.00047729383],"domain_scores_gemma":[0.99340665,0.00061412214,0.00027178237,0.0025736957,0.002546472,0.00058732374],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0025108985,0.004979401,0.0022969348,0.0029589098,0.0020079948,0.0068640118,0.0066891243,0.0042801467,0.6249635],"category_scores_gemma":[0.01570954,0.003690757,0.0023534757,0.002481704,0.0010617691,0.011750451,0.010643098,0.004453045,0.73920256],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022769964,0.000025762445,0.0003680373,0.00035151906,0.00002067922,0.00012464494,0.00016630956,0.00016581181,0.001148868,0.0007938155,0.9762749,0.02033198],"study_design_scores_gemma":[0.00008943913,0.000030429985,0.00079089496,0.00019640473,0.000023071845,0.00016743805,0.000112148744,0.00070506963,0.006189778,0.001754703,0.98982835,0.000112235946],"about_ca_topic_score_codex":0.009627085,"about_ca_topic_score_gemma":0.008200842,"teacher_disagreement_score":0.37503648,"about_ca_system_score_codex":0.0020166095,"about_ca_system_score_gemma":0.001736301,"threshold_uncertainty_score":0.534944},"labels":[],"label_agreement":null},{"id":"W6976765682","doi":"10.60692/xm8g2-z7q67","title":"IMPROVING DATA QUALITY AND MANAGEMENT FOR REMOTE SENSING ANALYSIS: USE-CASES AND EMERGING RESEARCH QUESTIONS","year":2023,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Data quality; Data management; Geospatial analysis; Data modeling; Data integration; Big data; Data virtualization; Quality (philosophy)","score_opus":0.2647868819306809,"score_gpt":0.35421004143405216,"score_spread":0.08942315950337126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6976765682","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27746788,0.095700465,0.44707498,0.14129937,0.00073051144,0.00085428375,0.00084732164,0.0010697271,0.03495558],"genre_scores_gemma":[0.7512533,0.027685866,0.21662928,0.0015568123,0.0006422647,0.00019217888,0.0004925841,0.00015424301,0.0013935021],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97758305,0.012471428,0.0014961133,0.0016346057,0.0060590277,0.0007558254],"domain_scores_gemma":[0.92142844,0.04812989,0.006857106,0.008847635,0.013549106,0.0011877895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.039067585,0.00082324294,0.00084176596,0.003658148,0.0013378654,0.00951097,0.002988936,0.0033412217,0.0020310015],"category_scores_gemma":[0.04929772,0.0004894744,0.0009318299,0.009162092,0.0048847264,0.012801156,0.0027615028,0.0020533127,0.00042403996],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031836258,0.0007691557,0.09709398,0.005052352,0.00021803033,0.00071989716,0.004527867,0.0197387,0.006071304,0.17108808,0.013887201,0.68051505],"study_design_scores_gemma":[0.00016077806,0.0011873038,0.08296298,0.009099269,0.00039119253,0.0022020682,0.031295314,0.30377898,0.049987897,0.36874792,0.14977996,0.00040633776],"about_ca_topic_score_codex":0.006251832,"about_ca_topic_score_gemma":0.004341003,"teacher_disagreement_score":0.039067585,"about_ca_system_score_codex":0.0037894808,"about_ca_system_score_gemma":0.0047294507,"threshold_uncertainty_score":0.20661157},"labels":[],"label_agreement":null},{"id":"W6980241096","doi":"","title":"In-between Boundaries","year":2016,"lang":"en","type":"dissertation","venue":"UWSpace (University of Waterloo)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Recreation; Traverse; Urban design; Architecture; Urban planning; Bridging (networking); Public space; Architectural design","score_opus":0.00971613017603376,"score_gpt":0.19633200062642103,"score_spread":0.18661587045038727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6980241096","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.077305034,0.0016605281,0.075444296,0.0036152613,0.0010130161,0.00018934775,0.00039645468,0.00063970964,0.8397363],"genre_scores_gemma":[0.72494495,0.0014741062,0.05392823,0.0014719624,0.00021641348,0.00024122621,0.0010297472,0.0006641206,0.21602926],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99843675,0.00037016673,0.00008281909,0.00038143626,0.0004103275,0.0003185407],"domain_scores_gemma":[0.998133,0.00039544268,0.00022462892,0.00052404514,0.00043168775,0.00029124448],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007197003,0.0006010583,0.00038938312,0.0008820847,0.0038572834,0.008054867,0.00135455,0.0013064718,0.03152446],"category_scores_gemma":[0.004022986,0.00038961778,0.0004868502,0.001168374,0.0042496826,0.0063212854,0.005102914,0.0017961302,0.007149816],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013025243,0.00010555399,0.00825477,0.00030457298,0.000023758901,0.0008093492,0.034227703,0.0013045407,0.0046412363,0.73354965,0.032509647,0.1841391],"study_design_scores_gemma":[0.000012526432,0.00006111784,0.0051583014,0.0002519687,0.000033385535,0.0006207217,0.023250964,0.0012287289,0.0026385842,0.10575478,0.86095923,0.000029690344],"about_ca_topic_score_codex":0.0055203075,"about_ca_topic_score_gemma":0.008843935,"teacher_disagreement_score":0.03152446,"about_ca_system_score_codex":0.0017626323,"about_ca_system_score_gemma":0.002629566,"threshold_uncertainty_score":0.10545981},"labels":[],"label_agreement":null},{"id":"W6981306913","doi":"","title":"Edward Snowden: Big Data, Security, and Human Rights","year":2016,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"United States National Security Agency; Agency (philosophy); Queen (butterfly); Human rights; Civil liberties; Conversation; Dream; Public broadcasting; Politics","score_opus":0.01092132809804911,"score_gpt":0.20081911697251933,"score_spread":0.18989778887447023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6981306913","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002254374,0.05463312,0.0012237548,0.32899502,0.016995741,0.00009658551,0.0016910948,0.0003782025,0.5937322],"genre_scores_gemma":[0.014269689,0.029603725,0.0005128984,0.023712404,0.0035076125,0.000067925735,0.00064306596,0.00031504588,0.92736775],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994535,0.000126777,0.000025831583,0.00008752122,0.00021278544,0.00009358234],"domain_scores_gemma":[0.9991429,0.00024784027,0.000050730945,0.00005019015,0.00021798653,0.0002904078],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075859984,0.0007068241,0.00027549415,0.00078509306,0.0032757868,0.0048216106,0.00054142764,0.002484124,0.10066051],"category_scores_gemma":[0.0025811717,0.00030762985,0.00016405151,0.0013530873,0.001305358,0.0057175467,0.0032664323,0.0024336074,0.031187689],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000024930923,0.0000014115757,0.000036741178,0.000023431885,3.774618e-7,0.000031238236,0.00037395905,0.0000067778064,0.000025311998,0.0033957202,0.98925155,0.006850887],"study_design_scores_gemma":[8.830256e-7,0.0000016336239,0.00023094479,0.00010758403,4.055823e-7,0.000030734485,0.00092332426,0.000014400982,0.000043587595,0.0015824005,0.9970606,0.000003454937],"about_ca_topic_score_codex":0.039339438,"about_ca_topic_score_gemma":0.0899689,"teacher_disagreement_score":0.10066051,"about_ca_system_score_codex":0.0026373726,"about_ca_system_score_gemma":0.0025698766,"threshold_uncertainty_score":0.33674294},"labels":[],"label_agreement":null},{"id":"W6982459832","doi":"","title":"Influence du règlement adopté à Sherbrooke pour obliger les moins de 18 ans à porter un casque à vélo sur la pratique du vélo et le port du casque","year":2018,"lang":"fr","type":"other","venue":"Corpus Université Laval (Université Laval)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Institutional change; Ile de france","score_opus":0.007362234361075623,"score_gpt":0.1813871156294544,"score_spread":0.17402488126837878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6982459832","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9960155,0.00034646192,0.000101895945,0.00027749402,0.00002620978,0.000016986836,0.00012914631,0.0000052130013,0.0030810346],"genre_scores_gemma":[0.9835248,0.00033874935,0.00025691872,0.00012723554,0.000010012538,0.000048246166,0.00010347788,0.0000062236295,0.015584343],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990575,0.00030360505,0.000039987466,0.00013893135,0.00017654004,0.00028342617],"domain_scores_gemma":[0.99633765,0.0011619036,0.0011287879,0.00012009176,0.00043355473,0.00081798056],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010186548,0.0003203682,0.00033567494,0.0003461165,0.0008490138,0.0015052209,0.00057735003,0.0006941963,0.012849749],"category_scores_gemma":[0.0039847805,0.00022232308,0.00048140343,0.00026621454,0.000539807,0.00046216763,0.00073901284,0.0010921047,0.0007787681],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015824914,0.0008715328,0.9401485,0.00025512656,0.00026993648,0.00063360896,0.019516665,0.00017341202,0.0044701677,0.001132363,0.001306702,0.029639684],"study_design_scores_gemma":[0.000016175203,0.000670747,0.97589,0.00013051377,0.00009463078,0.00005759403,0.018664606,0.00013283483,0.000566592,0.000095489384,0.0036640884,0.0000166829],"about_ca_topic_score_codex":0.10570787,"about_ca_topic_score_gemma":0.26567712,"teacher_disagreement_score":0.8942921,"about_ca_system_score_codex":0.0014438144,"about_ca_system_score_gemma":0.002177363,"threshold_uncertainty_score":0.21018517},"labels":[],"label_agreement":null},{"id":"W6990346847","doi":"","title":"Détection automatique des changements du bâti en milieu urbain sur des images à très haute résolution spatiale (Ikonos et QuickBird) en utilisant des données cartographiques numériques","year":2007,"lang":"en","type":"dissertation","venue":"Knowledge UdeS (Institutional Deposit of the University of Sherbrooke)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Change detection; Segmentation; Scale (ratio); Knowledge base; Image segmentation; Urban planning; Geographic information system; Urban area; Image (mathematics); Image resolution","score_opus":0.018125946193821848,"score_gpt":0.22882245136539608,"score_spread":0.21069650517157423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6990346847","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33434197,0.002551453,0.6444901,0.00027975885,0.00012749978,0.0005032748,0.0023611758,0.005845179,0.0094996225],"genre_scores_gemma":[0.5592064,0.0019495457,0.42813265,0.00007506938,0.000046473997,0.00018941634,0.0034116036,0.00024308925,0.006745728],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991001,0.000071393464,0.00003844922,0.00028305466,0.0003948281,0.00011220976],"domain_scores_gemma":[0.9991374,0.00021466393,0.00011563101,0.000083068866,0.0004047986,0.00004435061],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006673809,0.00096004055,0.00090831745,0.005401779,0.00052276993,0.0019984571,0.0007972908,0.0008698497,0.0013160695],"category_scores_gemma":[0.001403056,0.0005964985,0.0008819641,0.0018839991,0.0004895054,0.0010963639,0.0006648758,0.00075116067,0.0014855801],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029561162,0.00012998772,0.054625828,0.0007502878,0.00025043794,0.00088376587,0.0011317297,0.025266863,0.15562211,0.0013847885,0.0031326513,0.75652593],"study_design_scores_gemma":[0.000053239903,0.00031530624,0.37226886,0.00024934404,0.00041365315,0.0019121562,0.0023798374,0.4386138,0.14526863,0.001790973,0.036534667,0.00019961587],"about_ca_topic_score_codex":0.0387364,"about_ca_topic_score_gemma":0.06514851,"teacher_disagreement_score":0.0387364,"about_ca_system_score_codex":0.00084168825,"about_ca_system_score_gemma":0.00093452487,"threshold_uncertainty_score":0.07702184},"labels":[],"label_agreement":null},{"id":"W6999099325","doi":"","title":"CBERS-4 imagery for mapping urban land cover in the Amazon","year":2023,"lang":"ca","type":"article","venue":"Biblioteca Digital da Memória Científica do INPE (National Institute for Space Research)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Global Affairs Canada; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Amazon rainforest; Amazonian; Land cover; Geographic information system; Random forest; Cover (algebra); Forest cover; Satellite imagery","score_opus":0.1294815001552705,"score_gpt":0.3587501158924814,"score_spread":0.2292686157372109,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6999099325","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7428487,0.0036147968,0.12349791,0.0020751006,0.00019980888,0.0009750849,0.039631892,0.0043587307,0.08279795],"genre_scores_gemma":[0.8540731,0.0006935063,0.12240864,0.00007017992,0.000035763915,0.0001233991,0.014750564,0.00020130727,0.0076435683],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9997466,0.000027526372,0.000015505395,0.000043760694,0.00014003088,0.00002659544],"domain_scores_gemma":[0.999846,0.000023495972,0.000021586815,0.000026768399,0.00007046221,0.000011708297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002702678,0.0002448105,0.00023620088,0.0016564219,0.00035859813,0.0005452769,0.0004102261,0.0002606823,0.002675799],"category_scores_gemma":[0.00072908425,0.00012793229,0.00021147281,0.0021411006,0.00016945228,0.00040017918,0.00021608475,0.00022255997,0.00077986496],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023076081,0.00026181748,0.088910304,0.0006905321,0.00015544776,0.00058978674,0.00039716222,0.02701446,0.07821713,0.0067168386,0.0303936,0.76642215],"study_design_scores_gemma":[0.00010051578,0.00013691178,0.5122587,0.00020872294,0.00018712568,0.00072882423,0.0011168965,0.3320047,0.032474995,0.003410761,0.117283344,0.00008851288],"about_ca_topic_score_codex":0.087953046,"about_ca_topic_score_gemma":0.10616947,"teacher_disagreement_score":0.087953046,"about_ca_system_score_codex":0.0006358202,"about_ca_system_score_gemma":0.0006786065,"threshold_uncertainty_score":0.17488217},"labels":[],"label_agreement":null},{"id":"W7006626904","doi":"","title":"Variational Autoencoders for Heterogeneous Data Integration: Applications in Remote Sensing, Fusion, and Anomaly Detection","year":2025,"lang":"en","type":"dissertation","venue":"MacSphere (McMaster University)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"McMaster University","keywords":"Filter (signal processing); Frame (networking); Key (lock); Identification (biology); Tubulopathy","score_opus":0.01813230978668653,"score_gpt":0.22201839146301142,"score_spread":0.20388608167632488,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7006626904","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033723372,0.0018521606,0.99263483,0.00043138934,0.000059941536,0.000018497474,0.000040258503,0.000103712504,0.0014868462],"genre_scores_gemma":[0.35849017,0.01107055,0.6213619,0.00052171067,0.0005456222,0.0002522526,0.00043237556,0.00024656265,0.007078871],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994677,0.00021665655,0.00003178669,0.00011305012,0.00013632193,0.00003447423],"domain_scores_gemma":[0.9980362,0.0015436265,0.00009224867,0.00010492937,0.00018131189,0.0000417225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017310781,0.0011075098,0.0008342579,0.00069337647,0.00039847495,0.0012263142,0.0009976289,0.0011187643,0.0016736024],"category_scores_gemma":[0.0046531702,0.0006127701,0.0012061829,0.0010183054,0.0012699522,0.0015685144,0.0020414665,0.0027443955,0.00041177525],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051477808,0.00006664284,0.0010355209,0.0002671111,0.00018220156,0.00012855585,0.00023317694,0.7113993,0.006861683,0.13612278,0.002663042,0.14098845],"study_design_scores_gemma":[0.0000024466942,0.000013257367,0.00011790138,0.000017827952,0.000007883908,0.000019380428,0.000011544637,0.97303224,0.00066435273,0.0244881,0.001616145,0.000008917398],"about_ca_topic_score_codex":0.0040560174,"about_ca_topic_score_gemma":0.0041321544,"teacher_disagreement_score":0.0040560174,"about_ca_system_score_codex":0.00087015517,"about_ca_system_score_gemma":0.0006845698,"threshold_uncertainty_score":0.009154975},"labels":[],"label_agreement":null},{"id":"W7024025004","doi":"","title":"REFLECTANCE AND COLORIMETRIC CHARACTERISTICS OF METALLOCOMPLEXES OF FLAVONOIDS FROM CANADIAN GOLDENROD","year":2024,"lang":"en","type":"article","venue":"The Scientific Issues of Ternopil Volodymyr Hnatiuk National Pedagogical University Series pedagogy","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Reflectivity; Pigment; Near infrared reflectance spectroscopy; Flavonoid","score_opus":0.045193261237562336,"score_gpt":0.2932957234703163,"score_spread":0.24810246223275395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024025004","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9955381,0.0007597066,0.0008732969,0.000035524903,0.000008082199,0.000012819908,0.0003811504,0.000018617064,0.002372733],"genre_scores_gemma":[0.9914654,0.00042581206,0.002183792,0.000031368247,0.0000041755097,0.00001011279,0.00080512854,0.000022714512,0.0050515635],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99986255,0.0000068581026,0.0000046569426,0.00005170119,0.00004472228,0.00002947329],"domain_scores_gemma":[0.9998983,0.000021552747,0.000016927404,0.0000070639994,0.00003357685,0.000022532953],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014046552,0.0003358952,0.00022205677,0.0006032248,0.00041016957,0.00029358323,0.00026198916,0.0002176081,0.0011494473],"category_scores_gemma":[0.00020789003,0.00009878768,0.00020360044,0.00038229607,0.0003363018,0.0000989072,0.00011626496,0.00024825588,0.00018818263],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006144747,0.0000037174023,0.0005984138,0.000022613047,0.0000037700345,0.00003014186,0.00007525378,0.000024626514,0.99796873,0.00004375271,0.00002618111,0.0011411476],"study_design_scores_gemma":[0.000014452327,0.0002382035,0.1384926,0.000014508089,0.00006736334,0.0004158909,0.0005087141,0.0006436649,0.8521116,0.00011484973,0.007341185,0.000037099428],"about_ca_topic_score_codex":0.06995301,"about_ca_topic_score_gemma":0.08109414,"teacher_disagreement_score":0.930047,"about_ca_system_score_codex":0.0007759117,"about_ca_system_score_gemma":0.000441267,"threshold_uncertainty_score":0.13909173},"labels":[],"label_agreement":null},{"id":"W7029075502","doi":"","title":"1859 House Bill 0214. Resolve Concerning The Flowage Of Lands In The Towns Of Concord, Sudbury, Wayland, Bedford, And Carlisle.","year":2018,"lang":"en","type":"other","venue":"State Library's electronic repository (State Library of Massachusetts)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Legislature; Legislation; Work (physics); Legislative history; Lower house","score_opus":0.008857447326650312,"score_gpt":0.19850874732313908,"score_spread":0.18965129999648878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7029075502","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017093692,0.00048605248,0.000498634,0.004145591,0.0011356386,0.00019900374,0.0095034,0.00045833958,0.981864],"genre_scores_gemma":[0.004158714,0.00019222769,0.00018997674,0.0028292108,0.00021067228,0.00011069922,0.0017487805,0.00012159786,0.99043816],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99804485,0.00015511032,0.00010030609,0.00023871988,0.00097351,0.00048759452],"domain_scores_gemma":[0.9985592,0.00019104609,0.00006701949,0.00010938154,0.00092853006,0.00014491928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011333908,0.0011484771,0.00060144346,0.0016834057,0.0051826965,0.0034788372,0.0014463608,0.005758071,0.23773973],"category_scores_gemma":[0.0043565477,0.0010842186,0.00056626275,0.0017924025,0.0010526262,0.0014938312,0.0016635029,0.0050577302,0.16841458],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021827826,0.000031468033,0.00030198606,0.000027759581,0.0000023824857,0.00006738869,0.00011352105,0.00004363045,0.00014498766,0.01576341,0.97368264,0.00979893],"study_design_scores_gemma":[0.000010913025,0.000011779959,0.003004119,0.000037210328,0.000003414994,0.000028919963,0.00008635569,0.000055818313,0.00014428546,0.00072342396,0.99588376,0.000009933486],"about_ca_topic_score_codex":0.22366852,"about_ca_topic_score_gemma":0.4343441,"teacher_disagreement_score":0.23773973,"about_ca_system_score_codex":0.0058614863,"about_ca_system_score_gemma":0.006054554,"threshold_uncertainty_score":0.7953186},"labels":[],"label_agreement":null},{"id":"W7029964224","doi":"","title":"Machine Learning for Biodiversity Monitoring from Remote Sensing and Citizen Science Data","year":2024,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Citizen science; Biodiversity; Environmental monitoring; Remote sensing application","score_opus":0.03723037815256608,"score_gpt":0.25900128484594975,"score_spread":0.22177090669338367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7029964224","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18220413,0.0056285025,0.7562554,0.008166151,0.00066193246,0.0006352497,0.023203172,0.011084115,0.01216144],"genre_scores_gemma":[0.6172792,0.0020628457,0.31783196,0.0010031719,0.0006505199,0.001105296,0.050429646,0.00034232615,0.00929508],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898523,0.00034797748,0.000060062783,0.0003400284,0.00016517227,0.00010160821],"domain_scores_gemma":[0.9976618,0.0013609219,0.00020918356,0.00038046454,0.00029051182,0.000097056436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025815265,0.0013067693,0.0006967504,0.001958501,0.00048728872,0.0012615258,0.0012491014,0.0013378832,0.0026791529],"category_scores_gemma":[0.0074355835,0.00049513695,0.0012941295,0.0019275058,0.0004366242,0.0018706359,0.0013130715,0.002553561,0.002689218],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020777702,0.00080760976,0.02298325,0.00033064303,0.00031174297,0.00014435608,0.00014005233,0.32671687,0.0016661721,0.0044238553,0.044411182,0.5978566],"study_design_scores_gemma":[0.000014475558,0.000057181333,0.0038608557,0.000044011944,0.00001927035,0.000022089962,0.00005319578,0.9787395,0.0006701283,0.011939035,0.0045652324,0.000014999551],"about_ca_topic_score_codex":0.009290194,"about_ca_topic_score_gemma":0.010430444,"teacher_disagreement_score":0.009290194,"about_ca_system_score_codex":0.0011817276,"about_ca_system_score_gemma":0.0009908896,"threshold_uncertainty_score":0.018472254},"labels":[],"label_agreement":null},{"id":"W7034342469","doi":"","title":"This Week...Apartment Vacancy and Rental Rates; 2011 Employment; Retail Sales; Population Trends","year":2012,"lang":"en","type":"report","venue":"oURspace (University of Regina)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Public policy; Point (geometry); Population; Renting; Policy analysis; Population ageing; Empirical research; Current Population Survey","score_opus":0.04346830287808979,"score_gpt":0.23546530318658693,"score_spread":0.19199700030849715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7034342469","genre_codex":"dataset","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.063378036,0.0026410385,0.00087853154,0.0229318,0.0018967346,0.00016516994,0.6864433,0.0011453788,0.2205199],"genre_scores_gemma":[0.12191768,0.0050298604,0.0015920084,0.0012491402,0.0008428529,0.00019582409,0.27489316,0.00028549318,0.5939939],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99976367,0.000012723494,0.000014700456,0.000019949211,0.00012964022,0.000059277198],"domain_scores_gemma":[0.9984675,0.00013822953,0.00018257055,0.000061070125,0.0007608449,0.00038980859],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003410337,0.00036931454,0.00020583541,0.0020888825,0.0010037434,0.0019223465,0.0005045701,0.0005200821,0.056287173],"category_scores_gemma":[0.0020082567,0.00019117759,0.00023422067,0.0041445056,0.00021176902,0.0006570115,0.00045459773,0.00072378,0.020362932],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001803537,0.000043403634,0.054632973,0.00005414248,0.0000065334057,0.000024740692,0.00016235892,0.00014109365,0.00004153509,0.0005750198,0.9064524,0.037847705],"study_design_scores_gemma":[0.000006371629,0.000024481365,0.6327424,0.000120339464,0.0000131090055,0.000050112543,0.0012442899,0.00054962514,0.00021323682,0.00025810208,0.3647588,0.000019217256],"about_ca_topic_score_codex":0.7793431,"about_ca_topic_score_gemma":0.8964474,"teacher_disagreement_score":0.7793431,"about_ca_system_score_codex":0.003524904,"about_ca_system_score_gemma":0.004812369,"threshold_uncertainty_score":0.44391268},"labels":[],"label_agreement":null},{"id":"W7064950107","doi":"","title":"A Creole melting pot: the politics of language, race, and&#13;\\nidentity in southwest Louisiana, 1918-45","year":2016,"lang":"en","type":"dissertation","venue":"Sussex Research Online (University of Sussex)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Creole language; Politics; Resistance (ecology); Elite; Identity (music); Ethnic group; Cultural identity; Colonialism","score_opus":0.023311984954842383,"score_gpt":0.30229619738980634,"score_spread":0.27898421243496396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7064950107","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9270505,0.0012731659,0.00009095774,0.019295687,0.00006283333,0.000007484416,0.00006563134,0.000011180926,0.05214254],"genre_scores_gemma":[0.9795624,0.00038828602,0.00004835949,0.0015924767,0.000022117161,0.000006855283,0.00002106913,0.0000086695345,0.018349864],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99914134,0.00034663166,0.0000100788,0.000071087816,0.00006112265,0.00036974094],"domain_scores_gemma":[0.9994234,0.00013692188,0.000084340645,0.000015470298,0.00013923735,0.00020058957],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008648212,0.00014585145,0.0001523122,0.0005574605,0.01691588,0.0044670543,0.00063832605,0.00097444904,0.0044935565],"category_scores_gemma":[0.00091847224,0.00012912022,0.000100538404,0.0006945262,0.0064836205,0.0017532269,0.0029718843,0.0019954294,0.00029217787],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000120531855,0.00008132006,0.06536615,0.000054802593,0.000025148114,0.0020519071,0.7982672,0.00010275496,0.002295378,0.06527221,0.025633167,0.040729463],"study_design_scores_gemma":[0.0000048332345,0.00003281366,0.068469375,0.000098796816,0.000014947816,0.00015134139,0.7667145,0.00008270101,0.00061065075,0.0013616101,0.16243327,0.000025126928],"about_ca_topic_score_codex":0.49175763,"about_ca_topic_score_gemma":0.77001655,"teacher_disagreement_score":0.49175763,"about_ca_system_score_codex":0.014555291,"about_ca_system_score_gemma":0.0066451873,"threshold_uncertainty_score":0.9777906},"labels":[],"label_agreement":null},{"id":"W7066382500","doi":"","title":"How to legally release Meng Wanzhou in order to bring home Michael Kovrig and Michael Spavor: Gar Pardy","year":2020,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Order (exchange); China","score_opus":0.00579200802103527,"score_gpt":0.17029623073586703,"score_spread":0.16450422271483175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7066382500","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003811762,0.002718879,0.0029491344,0.15479471,0.017058484,0.00034762901,0.0030400062,0.002401499,0.8128779],"genre_scores_gemma":[0.007800077,0.0008189344,0.00064635644,0.014880248,0.00031397186,0.00006033223,0.00060743233,0.00041508127,0.97445756],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99830073,0.000105286,0.00004218863,0.00015010238,0.000865744,0.0005358472],"domain_scores_gemma":[0.9971691,0.00018999974,0.00009892937,0.00021247772,0.0014273974,0.00090216397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014222263,0.0007768795,0.00036768068,0.0010486511,0.0090269055,0.0063887388,0.001090056,0.0040603634,0.21466649],"category_scores_gemma":[0.005317373,0.00044158997,0.00035740464,0.000976141,0.0018404698,0.004688302,0.0024191914,0.0041174446,0.11154673],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011207696,0.000008851604,0.00034022416,0.00001781007,0.0000014582191,0.00009682489,0.00019024767,0.000025132878,0.00022853857,0.0037230593,0.9804121,0.014944508],"study_design_scores_gemma":[0.0000027679803,0.0000043387968,0.0004893465,0.000016822121,9.358336e-7,0.000028566776,0.00033787813,0.000027971319,0.00015516054,0.00023692664,0.99868983,0.000009588019],"about_ca_topic_score_codex":0.4931732,"about_ca_topic_score_gemma":0.5783216,"teacher_disagreement_score":0.50682676,"about_ca_system_score_codex":0.0052666,"about_ca_system_score_gemma":0.014055432,"threshold_uncertainty_score":0.98060524},"labels":[],"label_agreement":null},{"id":"W7073655318","doi":"","title":"From Pixels to Geographic Objects in Remote Sensing Image Analysis","year":2012,"lang":"en","type":"article","venue":"Utrecht University Repository (Utrecht University)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Feature (linguistics); Filter (signal processing); Vegetation (pathology); Noise (video); Context (archaeology); Image processing","score_opus":0.007700206454073195,"score_gpt":0.1784066447111033,"score_spread":0.1707064382570301,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7073655318","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01534692,0.101066425,0.8000273,0.0070898524,0.009050326,0.0011578873,0.0036656081,0.0034737913,0.05912191],"genre_scores_gemma":[0.14893886,0.06353967,0.7429889,0.0030347696,0.0051091616,0.0012116438,0.004709586,0.0014045183,0.029062955],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99613696,0.0012420536,0.00037079438,0.0007107336,0.0014143593,0.00012498739],"domain_scores_gemma":[0.9965056,0.001971797,0.00027793393,0.00037556863,0.00076180225,0.00010720694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026225308,0.0010069789,0.0007249259,0.004841305,0.0005630592,0.006680294,0.0012430979,0.0015529675,0.009235766],"category_scores_gemma":[0.0114845885,0.00056574325,0.0006289797,0.010480982,0.0021188024,0.004036417,0.0020218706,0.0020505737,0.0056493157],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011932177,0.00006282091,0.0033691418,0.0026897516,0.00015236095,0.00052835804,0.0014177806,0.0080125015,0.00436721,0.13306017,0.085767485,0.76045305],"study_design_scores_gemma":[0.00003446616,0.00020659946,0.011036453,0.001573831,0.00016808882,0.0017196068,0.0023402236,0.028066406,0.005825566,0.24350879,0.7053812,0.00013873249],"about_ca_topic_score_codex":0.0019932997,"about_ca_topic_score_gemma":0.0014126686,"teacher_disagreement_score":0.009235766,"about_ca_system_score_codex":0.0008564921,"about_ca_system_score_gemma":0.0009587301,"threshold_uncertainty_score":0.030896723},"labels":[],"label_agreement":null},{"id":"W7084149499","doi":"10.6084/m9.figshare.30038710","title":"Supplementary Material 2. PRISMA Flow Chart Outlining Review.pdf","year":2025,"lang":"en","type":"other","venue":"Figshare","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Psychological intervention; Transfer of training; Supervisor; Transfer of learning; Work (physics); Intervention (counseling); Organizational culture; Flow chart","score_opus":0.02053242066735093,"score_gpt":0.24934301219867344,"score_spread":0.22881059153132252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7084149499","genre_codex":"dataset","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005085043,0.010621027,0.0054789856,0.0036181381,0.0016879175,0.03171448,0.9380452,0.0018616616,0.0064640534],"genre_scores_gemma":[0.008177176,0.032767933,0.07337223,0.0100566065,0.0012461221,0.54723287,0.2955477,0.0021589298,0.029440377],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.9878549,0.0033337316,0.0050004045,0.0016654825,0.0016107212,0.0005347024],"domain_scores_gemma":[0.88250446,0.08333786,0.012518574,0.0044752643,0.015839998,0.0013238979],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01793941,0.0027294932,0.0063588927,0.024758004,0.001601475,0.0052831303,0.003445102,0.0027364139,0.5488834],"category_scores_gemma":[0.13329329,0.002246421,0.007289695,0.024754643,0.0011984679,0.0044720042,0.0032348575,0.0027857253,0.055396624],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004640512,0.000045005763,0.00046193952,0.6801576,0.0008741794,0.00008861032,0.00018030347,0.0004398787,0.0002544916,0.0023061077,0.28987247,0.024855422],"study_design_scores_gemma":[0.002817324,0.00020484066,0.00567303,0.38669056,0.0029241994,0.00041409506,0.00065193843,0.0006093006,0.00037213985,0.011637381,0.58781,0.00019515805],"about_ca_topic_score_codex":0.011655598,"about_ca_topic_score_gemma":0.019763004,"teacher_disagreement_score":0.5488834,"about_ca_system_score_codex":0.00569244,"about_ca_system_score_gemma":0.025770681,"threshold_uncertainty_score":0.64346313},"labels":[],"label_agreement":null},{"id":"W7091187891","doi":"","title":"Knowledge-Aware Mamba for Joint Change Detection and Classification from MODIS Times Series","year":2025,"lang":"en","type":"article","venue":"ArXiv.org","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Change detection; Leverage (statistics); Series (stratigraphy); Joint (building); Time series","score_opus":0.07816189538791798,"score_gpt":0.2662108885370209,"score_spread":0.18804899314910292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7091187891","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06933632,0.0011558501,0.9158342,0.0006771003,0.00014362573,0.00013101462,0.0011863058,0.01008952,0.0014461325],"genre_scores_gemma":[0.592634,0.0004454914,0.3975226,0.00068151765,0.00013248475,0.00031045548,0.005041562,0.00034986934,0.0028821328],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99949026,0.000105352054,0.00003358438,0.0002112386,0.000104080995,0.000055342563],"domain_scores_gemma":[0.99918324,0.00035662646,0.000087459855,0.00015946037,0.00016322504,0.000050054317],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014332373,0.0011596422,0.0009487292,0.0009592469,0.0005021493,0.00089840876,0.001692409,0.0011335058,0.001341307],"category_scores_gemma":[0.0036416918,0.00039069998,0.0011633376,0.0008259282,0.0004578476,0.0019514663,0.0014519299,0.0022709288,0.0007658088],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006065616,0.0004470641,0.009631284,0.00027829176,0.00030492287,0.00017767987,0.00018702184,0.32664195,0.027627427,0.0047508925,0.011929177,0.6174177],"study_design_scores_gemma":[0.0000072488465,0.000026117023,0.0010312976,0.000007158542,0.00001301967,0.000018031531,0.000018840201,0.9921659,0.0032352787,0.0023571646,0.00111144,0.000008510006],"about_ca_topic_score_codex":0.01170017,"about_ca_topic_score_gemma":0.015980328,"teacher_disagreement_score":0.01170017,"about_ca_system_score_codex":0.0009135838,"about_ca_system_score_gemma":0.0012126508,"threshold_uncertainty_score":0.02326417},"labels":[],"label_agreement":null},{"id":"W7097292593","doi":"","title":"Published by Canadian Center of Science and Education Unmixing and Target Recognition in Airborne Hyper-Spectral Images","year":2014,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Center (category theory); Decomposition; Extension (predicate logic); Linear algebra; Pattern recognition (psychology); Spectrum (functional analysis); Image (mathematics); Spectral signature","score_opus":0.005763113354489687,"score_gpt":0.19228808602828565,"score_spread":0.18652497267379597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7097292593","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017632783,0.0026845725,0.01080261,0.014588559,0.0040887394,0.0001866981,0.009938865,0.0015388792,0.9544078],"genre_scores_gemma":[0.010675695,0.0022913807,0.007067632,0.0006550319,0.00011073922,0.000037679063,0.0029918333,0.00025741992,0.9759125],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984402,0.000054792603,0.000057261164,0.00019821199,0.0010794613,0.00017010701],"domain_scores_gemma":[0.99385756,0.0003191071,0.00010596723,0.0005385425,0.0045261416,0.0006526687],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016973774,0.0007699259,0.00088780705,0.0030475147,0.0032011576,0.0063702343,0.0015615032,0.001985182,0.47639683],"category_scores_gemma":[0.0032749604,0.0004878741,0.0005012459,0.0043663457,0.0022696317,0.0018016445,0.0017654165,0.001327526,0.15541145],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039566545,0.000044336943,0.0017772967,0.0001842543,0.0000122414895,0.00015602974,0.00015692465,0.0007956753,0.0013565106,0.033843182,0.7326105,0.22902338],"study_design_scores_gemma":[0.0000040392656,0.0000038026606,0.0011992856,0.000053949305,0.0000033292827,0.00003718501,0.000097810385,0.0008457513,0.0003041685,0.0013237412,0.9961159,0.000010926693],"about_ca_topic_score_codex":0.7707839,"about_ca_topic_score_gemma":0.8573623,"teacher_disagreement_score":0.7707839,"about_ca_system_score_codex":0.013387356,"about_ca_system_score_gemma":0.046726122,"threshold_uncertainty_score":0.74685633},"labels":[],"label_agreement":null},{"id":"W7099186676","doi":"","title":"a Canadian Forces;","year":2010,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Radiance; Hyperspectral imaging; Oblique case; Reflectivity; Compensation (psychology); Process (computing)","score_opus":0.005175365253035579,"score_gpt":0.18436172206603,"score_spread":0.1791863568129944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7099186676","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0068711205,0.0016903181,0.0011562629,0.0065118023,0.0010188785,0.00010466082,0.0059956815,0.00021137169,0.9764399],"genre_scores_gemma":[0.021494498,0.0010885778,0.0015765285,0.0008698114,0.000046063815,0.000034641776,0.0024363436,0.00008325122,0.9723704],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991279,0.00005599443,0.000020967096,0.00019090292,0.0004067224,0.00019744581],"domain_scores_gemma":[0.9990594,0.00006020936,0.00004103162,0.000058514182,0.00056072185,0.0002201023],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00059681636,0.00094990426,0.00038811663,0.0012670622,0.0073423013,0.002806457,0.0009906301,0.0014267912,0.4004638],"category_scores_gemma":[0.001478542,0.00031924044,0.00029828274,0.0018519079,0.0010335501,0.0010680992,0.0018685716,0.001361531,0.13703288],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024541537,0.0001516175,0.011714194,0.00027158787,0.00002509408,0.0012688931,0.0010883269,0.00076667184,0.0027903314,0.05505795,0.55317163,0.37344822],"study_design_scores_gemma":[0.00000833898,0.000020039992,0.0041009192,0.00007984867,0.0000037884338,0.000195679,0.0006997957,0.00026395096,0.0003249632,0.0008129734,0.9934762,0.00001349549],"about_ca_topic_score_codex":0.6778023,"about_ca_topic_score_gemma":0.8514863,"teacher_disagreement_score":0.6778023,"about_ca_system_score_codex":0.010046031,"about_ca_system_score_gemma":0.018580668,"threshold_uncertainty_score":0.8551656},"labels":[],"label_agreement":null},{"id":"W7099379772","doi":"","title":"This study was conducted by the Working Group on Library Instruction of the","year":2015,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Graduate students; Selection (genetic algorithm); Higher education; Discussion group; Working group","score_opus":0.04066754963074071,"score_gpt":0.21911845406472705,"score_spread":0.17845090443398634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7099379772","genre_codex":"empirical","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8042761,0.000863326,0.010695343,0.018908158,0.0015501797,0.07904337,0.0095552495,0.0005062707,0.074602075],"genre_scores_gemma":[0.70498985,0.0017085542,0.06190429,0.011171623,0.0007701384,0.13518581,0.0038936273,0.00036640806,0.08000967],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9895873,0.0059927437,0.0007792618,0.0007414801,0.0018356061,0.0010635564],"domain_scores_gemma":[0.93680537,0.018535849,0.0030622242,0.005745092,0.02727429,0.008577102],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.024415875,0.00062023546,0.0011415798,0.0043967366,0.008204624,0.003293094,0.0016065057,0.0014982875,0.03211625],"category_scores_gemma":[0.038774423,0.0009809289,0.00028483765,0.0044644726,0.0023401503,0.0027727687,0.0027824568,0.002131359,0.0053213616],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000994245,0.0066081225,0.16567276,0.0011216395,0.000028561435,0.0006804723,0.29402658,0.0003809539,0.007210258,0.0060190023,0.16524546,0.352012],"study_design_scores_gemma":[0.0002478127,0.0014651052,0.22131367,0.00064328016,0.000016152577,0.000078171106,0.29677618,0.0005186038,0.0019622443,0.00080543495,0.47608283,0.00009047931],"about_ca_topic_score_codex":0.022506751,"about_ca_topic_score_gemma":0.05021811,"teacher_disagreement_score":0.96788377,"about_ca_system_score_codex":0.004460706,"about_ca_system_score_gemma":0.022800878,"threshold_uncertainty_score":0.12912506},"labels":[],"label_agreement":null},{"id":"W7114891871","doi":"10.1049/cvi2.70050","title":"A Lightweight Dual‐Branch Meta‐Learner for Few‐Shot HSI Classification With Cross‐Domain Adaptation","year":2025,"lang":"en","type":"article","venue":"IET Computer Vision","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Field (mathematics); Software deployment; Adaptation (eye); Domain (mathematical analysis); Hyperspectral imaging; Domain adaptation; Mode (computer interface); Deep learning","score_opus":0.03629882502189064,"score_gpt":0.2887237501737893,"score_spread":0.2524249251518987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7114891871","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023420021,0.0007237696,0.9681503,0.00032367866,0.000111549074,0.00007090991,0.00021813938,0.004860965,0.0021207202],"genre_scores_gemma":[0.58883816,0.00036092242,0.39509374,0.0010361667,0.00015870693,0.0003086406,0.0019231921,0.0006900755,0.0115903625],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995453,0.00010708489,0.000019693476,0.00017170935,0.00008401223,0.00007221341],"domain_scores_gemma":[0.9992945,0.0002580405,0.000042407635,0.00015446804,0.00018302524,0.00006757199],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014006144,0.0011921398,0.0010113034,0.00069441,0.00051217,0.0009800988,0.003537723,0.0019499823,0.004412329],"category_scores_gemma":[0.0025894346,0.00063305843,0.0011156099,0.0006591879,0.00048787778,0.001793598,0.0022101253,0.0026208775,0.0020932436],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044753077,0.0003806793,0.0025698121,0.0001389026,0.0002883703,0.00015320725,0.00013545826,0.4413594,0.016598262,0.0062854276,0.011913319,0.5197297],"study_design_scores_gemma":[0.000008771997,0.000027904322,0.000110265784,0.000006650791,0.000012480501,0.00001617526,0.00000759989,0.99525034,0.002119424,0.0017974605,0.0006375833,0.0000053362687],"about_ca_topic_score_codex":0.005829083,"about_ca_topic_score_gemma":0.00848814,"teacher_disagreement_score":0.005829083,"about_ca_system_score_codex":0.0008556038,"about_ca_system_score_gemma":0.0010801253,"threshold_uncertainty_score":0.014760673},"labels":[],"label_agreement":null},{"id":"W7115717852","doi":"10.1109/lgrs.2025.3645681","title":"A Novel Unsupervised Change Detection Network Based on Legendre Multiwavelet Theory and Depthwise Convolution With Channel Gating","year":2025,"lang":"","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Chongqing University of Technology","keywords":"Pattern recognition (psychology); Convolution (computer science); Change detection; Synthetic aperture radar; Discriminative model; Cluster analysis; Feature extraction; Channel (broadcasting); Feature (linguistics)","score_opus":0.01822346877617121,"score_gpt":0.22051434112100696,"score_spread":0.20229087234483575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7115717852","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031493697,0.0001440266,0.9657981,0.00011273674,0.00004000833,0.000044149732,0.00006875533,0.0008452242,0.0014533111],"genre_scores_gemma":[0.6180915,0.0002613425,0.37401432,0.00032133434,0.00007410535,0.0001731864,0.00051534246,0.000106060455,0.006442878],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997782,0.000032260352,0.000008995788,0.00008433013,0.000055028788,0.00004125815],"domain_scores_gemma":[0.9997414,0.00007152805,0.000030520172,0.000032573935,0.00009843834,0.000025568255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039877015,0.000642499,0.00047344118,0.0005549632,0.00033816718,0.00049370807,0.0012456819,0.00072146277,0.0012144459],"category_scores_gemma":[0.00075297244,0.00029995674,0.00048560344,0.00056690164,0.00050574983,0.0011737446,0.0007450677,0.00067609857,0.00041804338],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028548363,0.00030785063,0.003989147,0.000094365525,0.00012937759,0.00016992455,0.00015185625,0.32565016,0.08145175,0.015301032,0.005351477,0.56711763],"study_design_scores_gemma":[0.0000051209604,0.00004753751,0.0005306416,0.0000028195639,0.000012742017,0.00003630112,0.0000058626665,0.9894639,0.007204168,0.0018485802,0.0008334751,0.000008805001],"about_ca_topic_score_codex":0.0041992418,"about_ca_topic_score_gemma":0.006193116,"teacher_disagreement_score":0.0041992418,"about_ca_system_score_codex":0.000722607,"about_ca_system_score_gemma":0.00070009136,"threshold_uncertainty_score":0.008349597},"labels":[],"label_agreement":null},{"id":"W7117319661","doi":"10.1142/s0218126626500969","title":"Enhanced Multi-Level Deep Fusion UNET with Dual Attention for Land Cover Segmentation","year":2025,"lang":"en","type":"article","venue":"Journal of Circuits Systems and Computers","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Segmentation; Land cover; Pattern recognition (psychology); Image segmentation; Pixel; Dice; Classifier (UML); Feature extraction","score_opus":0.020436028106503634,"score_gpt":0.23787359320699097,"score_spread":0.21743756510048734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117319661","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24670532,0.0016177304,0.72939855,0.00047974204,0.000291124,0.00016180714,0.002060976,0.011460223,0.007824444],"genre_scores_gemma":[0.82867736,0.0002696083,0.15912373,0.0003426066,0.00006685389,0.0001270445,0.003405144,0.00020455477,0.007783043],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997904,0.000018630071,0.000010445719,0.00006882292,0.00005468673,0.000056990775],"domain_scores_gemma":[0.9998074,0.000039855888,0.00001710713,0.000032967313,0.00008275652,0.000019845225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005049495,0.0008138457,0.00077315205,0.0008583483,0.0003328977,0.00081231364,0.0012158193,0.0008208941,0.002610992],"category_scores_gemma":[0.0008569938,0.00029560237,0.0007491055,0.00065683434,0.0002842891,0.0010027202,0.0012052428,0.00080517546,0.0008516812],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00063569745,0.00046004122,0.006228339,0.0001966166,0.0002779834,0.00030372612,0.00013130582,0.3233497,0.04345467,0.0037374701,0.011332377,0.6098921],"study_design_scores_gemma":[0.0000067382757,0.000063564454,0.000954489,0.000008561845,0.000027945178,0.000049129438,0.000014480729,0.98801875,0.008456384,0.0012654267,0.0011250748,0.000009428192],"about_ca_topic_score_codex":0.012262389,"about_ca_topic_score_gemma":0.016968463,"teacher_disagreement_score":0.012262389,"about_ca_system_score_codex":0.0010455765,"about_ca_system_score_gemma":0.000878671,"threshold_uncertainty_score":0.024382055},"labels":[],"label_agreement":null},{"id":"W7117532950","doi":"10.48550/arxiv.2512.21948","title":"Interpretable Machine Learning-Derived Spectral Indices for Vegetation Monitoring","year":2025,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Discriminative model; Pairwise comparison; Polynomial; Feature (linguistics); Pattern recognition (psychology); Simple (philosophy); Feature selection; Base (topology); Product (mathematics)","score_opus":0.054521832435917086,"score_gpt":0.1989603753915632,"score_spread":0.14443854295564612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117532950","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019106425,0.00044667133,0.97444147,0.00023745827,0.000027528033,0.000053888274,0.0009468535,0.0033929655,0.0013467638],"genre_scores_gemma":[0.28424653,0.0007922176,0.70696545,0.00016138333,0.00008058466,0.00020871892,0.0051175687,0.00047105696,0.001956587],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995919,0.00008285768,0.000028089196,0.00013039843,0.00013293303,0.000033724333],"domain_scores_gemma":[0.9990963,0.0003881819,0.00014149475,0.0001496863,0.0002013268,0.000023117753],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011197025,0.001159787,0.0005296476,0.0012171302,0.00019075094,0.00096257246,0.0008886225,0.0005584113,0.0021023033],"category_scores_gemma":[0.0037210423,0.00033515037,0.000826014,0.0011382147,0.00038716762,0.0014074971,0.00069785287,0.0012723458,0.0011609565],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018107556,0.00026880504,0.009365814,0.00039858342,0.00012746637,0.00016974434,0.0001882949,0.22776176,0.085668005,0.01823652,0.009120052,0.64851385],"study_design_scores_gemma":[0.000015792071,0.0000527745,0.0032505707,0.000034709592,0.00002914365,0.00008166332,0.00005564962,0.95549166,0.0138940755,0.020863984,0.0062033464,0.000026562559],"about_ca_topic_score_codex":0.0024916788,"about_ca_topic_score_gemma":0.0040735896,"teacher_disagreement_score":0.0024916788,"about_ca_system_score_codex":0.0005966449,"about_ca_system_score_gemma":0.00076671975,"threshold_uncertainty_score":0.007032931},"labels":[],"label_agreement":null},{"id":"W7117631858","doi":"","title":"Automated Discovery of Parsimonious Spectral Indices via Normalized Difference Polynomials","year":2025,"lang":"","type":"article","venue":"ArXiv.org","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Ministry of Agriculture - Saskatchewan","keywords":"Discriminative model; Pairwise comparison; Polynomial; Feature (linguistics); Pattern recognition (psychology); Simple (philosophy); Feature selection; Base (topology); Product (mathematics)","score_opus":0.01919149347444892,"score_gpt":0.25862421102738886,"score_spread":0.23943271755293993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117631858","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04111599,0.00020559265,0.9550286,0.00015059565,0.000027361291,0.00004741419,0.000275606,0.0020434086,0.0011053644],"genre_scores_gemma":[0.32927576,0.00021527777,0.6668512,0.00009947715,0.000065609,0.00010420622,0.0015569585,0.0004244273,0.001407106],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99903,0.00017515202,0.000041002444,0.00027392412,0.00031691382,0.00016307352],"domain_scores_gemma":[0.99833953,0.000710596,0.00027207437,0.00025629488,0.00032363753,0.00009792706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013866106,0.0016969097,0.0014601237,0.0026442849,0.0005181121,0.0016878889,0.0016983292,0.00076012244,0.0017448615],"category_scores_gemma":[0.0052838167,0.00072664855,0.00153016,0.0017273568,0.0007973709,0.0023307598,0.0015702262,0.0017371228,0.0017070303],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004227186,0.00026087544,0.0098200645,0.00025043267,0.00014090304,0.00030399027,0.0003053677,0.18670912,0.059749354,0.015590306,0.006016055,0.72043085],"study_design_scores_gemma":[0.000020070223,0.00005204251,0.00076008023,0.000010283953,0.000019318433,0.00005773825,0.000041731437,0.9823632,0.0054893773,0.009742043,0.0014272892,0.000016753378],"about_ca_topic_score_codex":0.003447044,"about_ca_topic_score_gemma":0.004833656,"teacher_disagreement_score":0.003447044,"about_ca_system_score_codex":0.00071193627,"about_ca_system_score_gemma":0.0013237623,"threshold_uncertainty_score":0.007333219},"labels":[],"label_agreement":null},{"id":"W7123337241","doi":"10.1109/icspis67605.2025.11318387","title":"SceneMixer: Exploring Convolutional Mixing Networks for Remote Sensing Scene Classification","year":2025,"lang":"","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Convolutional neural network; Land cover; Pointwise; Identification (biology); Feature extraction; Computation; Remote sensing application; Channel (broadcasting)","score_opus":0.07059593135919698,"score_gpt":0.27755747111483103,"score_spread":0.20696153975563406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7123337241","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05238241,0.0010407049,0.92804724,0.00040474357,0.000104513434,0.00015810477,0.0011436716,0.012142736,0.004575795],"genre_scores_gemma":[0.42910007,0.0009362014,0.54640377,0.00041248137,0.00011414463,0.00020637801,0.007961048,0.0011021064,0.013763789],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997696,0.000041082214,0.000007789313,0.00008793718,0.000057399717,0.0000361468],"domain_scores_gemma":[0.9997942,0.0000689426,0.000021825796,0.000048643422,0.000050669412,0.000015795791],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007743517,0.0015401747,0.0004853658,0.0009501355,0.00027784097,0.0009753575,0.0016035945,0.0006340382,0.0029677404],"category_scores_gemma":[0.0011531888,0.0004332751,0.0007639163,0.0008516691,0.00034632062,0.0018940964,0.0011820868,0.0013117408,0.0013622021],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039836293,0.00026835446,0.003445048,0.00021743117,0.00030366261,0.00012650782,0.000113320544,0.3215215,0.03327487,0.01554077,0.013705264,0.6110849],"study_design_scores_gemma":[0.000010523656,0.000026431098,0.00027914846,0.000008722321,0.000017061166,0.000019884264,0.000011792749,0.9884163,0.004767527,0.0043149665,0.0021212674,0.0000064103656],"about_ca_topic_score_codex":0.009435982,"about_ca_topic_score_gemma":0.016322426,"teacher_disagreement_score":0.009435982,"about_ca_system_score_codex":0.0009432876,"about_ca_system_score_gemma":0.0007603068,"threshold_uncertainty_score":0.018762112},"labels":[],"label_agreement":null},{"id":"W7125495772","doi":"10.1109/icicsp66564.2025.11338376","title":"A Multiscale Autoencoder Framework for Hyperspectral Unmixing","year":2025,"lang":"","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Petro-Canada","funders":"","keywords":"Autoencoder; Hyperspectral imaging; Pattern recognition (psychology); Feature (linguistics); Artificial neural network","score_opus":0.019338356103141136,"score_gpt":0.2935597010261405,"score_spread":0.2742213449229993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125495772","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0062130927,0.00014769456,0.99272037,0.00006132968,0.000027965678,0.000011759597,0.000046573048,0.00032474572,0.000446443],"genre_scores_gemma":[0.24794725,0.00044831497,0.7447417,0.00014519332,0.00013027935,0.00011268955,0.00053418096,0.0002175247,0.005722834],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99976116,0.00004899789,0.0000136202825,0.000059618913,0.00009003862,0.000026706288],"domain_scores_gemma":[0.99977404,0.000068067435,0.0000201387,0.000041399555,0.000082281666,0.000014136709],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051832496,0.00055917824,0.00065760134,0.00031446706,0.00020871806,0.00042208942,0.0007012559,0.00067616015,0.001642625],"category_scores_gemma":[0.00092710624,0.00033565736,0.0006965489,0.00040845605,0.00028713563,0.0007259373,0.0010496691,0.0011238379,0.00070465007],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010819667,0.00012294034,0.00049382495,0.00010161675,0.00012569073,0.00007761155,0.000059215403,0.44753814,0.046573073,0.016543053,0.0036024773,0.48465407],"study_design_scores_gemma":[0.0000020166653,0.00001169412,0.00011393639,0.0000025745228,0.000006801697,0.000010530577,0.0000025749846,0.99594754,0.0018832828,0.0014178423,0.00059748377,0.0000038874355],"about_ca_topic_score_codex":0.0041473643,"about_ca_topic_score_gemma":0.006787845,"teacher_disagreement_score":0.0041473643,"about_ca_system_score_codex":0.00025756843,"about_ca_system_score_gemma":0.0004973251,"threshold_uncertainty_score":0.008246422},"labels":[],"label_agreement":null},{"id":"W7130709778","doi":"10.5281/zenodo.18717100","title":"AI-Powered Satellite Imagery in Land Use Mapping and Monitoring in Uganda","year":2000,"lang":"en","type":"article","venue":"Open MIND","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Satellite imagery; Satellite; Convolutional neural network; Land use; Deep learning; Artificial neural network; Focus (optics); Earth observation satellite","score_opus":0.043191016930657654,"score_gpt":0.2724724206313738,"score_spread":0.22928140370071612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7130709778","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9838837,0.0002302066,0.011275204,0.00023370207,0.000012657909,0.00008401088,0.00086614164,0.0002490029,0.0031653892],"genre_scores_gemma":[0.97947717,0.0000939932,0.018885894,0.000015661008,0.0000053225235,0.000035010762,0.0006424054,0.000012769763,0.00083167973],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99953675,0.00027390293,0.000020545911,0.000065610184,0.00007104464,0.000032275206],"domain_scores_gemma":[0.9993862,0.00025838328,0.00007630421,0.00008345485,0.00016008828,0.00003559297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011465646,0.0003329523,0.00023805117,0.0012698966,0.00034121322,0.00049434777,0.00038144752,0.00036686313,0.0006736542],"category_scores_gemma":[0.0031651545,0.0001720371,0.0001823574,0.0019823397,0.00031173188,0.0006420246,0.00045142378,0.00029734126,0.00024371523],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000633765,0.00034084346,0.21842588,0.00036067562,0.00014705815,0.0005608722,0.001402858,0.28391337,0.01108239,0.003451152,0.0055735144,0.47410762],"study_design_scores_gemma":[0.00005183898,0.00016377334,0.17098963,0.00008435034,0.00006913838,0.00020187272,0.0013479261,0.80124116,0.015515974,0.002638067,0.007649642,0.000046725367],"about_ca_topic_score_codex":0.034603886,"about_ca_topic_score_gemma":0.036792025,"teacher_disagreement_score":0.034603886,"about_ca_system_score_codex":0.0006937883,"about_ca_system_score_gemma":0.00044723568,"threshold_uncertainty_score":0.06880498},"labels":[],"label_agreement":null},{"id":"W7130723106","doi":"10.5281/zenodo.18717101","title":"AI-Powered Satellite Imagery in Land Use Mapping and Monitoring in Uganda","year":2000,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Satellite imagery; Satellite; Convolutional neural network; Land use; Deep learning; Artificial neural network; Focus (optics); Earth observation satellite","score_opus":0.034823838724669716,"score_gpt":0.2282589980768465,"score_spread":0.19343515935217678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7130723106","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98599964,0.00025121964,0.009678069,0.00018312699,0.000010952697,0.00008683889,0.0010326225,0.00020325363,0.0025542353],"genre_scores_gemma":[0.9784324,0.000114624774,0.019580033,0.000013914769,0.0000054444267,0.000043438788,0.0008995042,0.00001492666,0.0008956965],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99956566,0.00025021055,0.000019475281,0.00006400715,0.00006691944,0.00003371123],"domain_scores_gemma":[0.9994721,0.00020337763,0.000072512994,0.00007725029,0.00013962404,0.000035091252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010451952,0.00034372573,0.00024891406,0.0013694253,0.00031872737,0.00045589937,0.0003883335,0.00038934618,0.0006415396],"category_scores_gemma":[0.0026028682,0.00018573862,0.00018270356,0.0021674929,0.00030750845,0.0006098459,0.0004491463,0.00027076117,0.00025498235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00075288146,0.00035515035,0.24457222,0.00040862392,0.00015232756,0.00059510395,0.0012794151,0.27856514,0.012981649,0.003055624,0.005342536,0.45193925],"study_design_scores_gemma":[0.00006746622,0.00019714444,0.22363676,0.00009426134,0.00008253469,0.00023220321,0.0012692272,0.74521023,0.018294618,0.0022806136,0.008582406,0.000052563144],"about_ca_topic_score_codex":0.033280898,"about_ca_topic_score_gemma":0.035192862,"teacher_disagreement_score":0.033280898,"about_ca_system_score_codex":0.0006911676,"about_ca_system_score_gemma":0.00044270649,"threshold_uncertainty_score":0.06617439},"labels":[],"label_agreement":null},{"id":"W7131266497","doi":"10.1109/icoiics67115.2025.11390470","title":"GeoMAE-CLIPNet: Self-Supervised Transformer with Vision—Language Adaptors for Remote Sensing Image Classification","year":2025,"lang":"","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Interpretability; Discriminative model; Autoencoder; Pattern recognition (psychology); Contextual image classification; Iterative reconstruction; Transformer; Benchmark (surveying)","score_opus":0.010976799863646133,"score_gpt":0.2615134738818251,"score_spread":0.250536674018179,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7131266497","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06588786,0.0005275426,0.91309816,0.0003288261,0.00020797805,0.00022854906,0.0009589232,0.011892525,0.0068696705],"genre_scores_gemma":[0.7273848,0.0003116464,0.25052336,0.00071620225,0.000114224546,0.00033335446,0.0048728157,0.00057805446,0.015165549],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997917,0.00003937444,0.000008206162,0.00007917922,0.000047233247,0.000034319193],"domain_scores_gemma":[0.9996735,0.00008646486,0.0000310945,0.00008575092,0.00009445942,0.000028657238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006462904,0.0010539145,0.00048013128,0.00046034344,0.00022920906,0.00053274824,0.0019212863,0.00069896237,0.004158943],"category_scores_gemma":[0.0014744293,0.00032128274,0.00059077406,0.00041529402,0.00050698064,0.0014698341,0.0011383416,0.001110489,0.0015042237],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006340215,0.00057851634,0.0035871805,0.00026998552,0.00024185012,0.00028526355,0.00013378503,0.24064349,0.035723183,0.013018773,0.027059713,0.6778242],"study_design_scores_gemma":[0.0000142122835,0.0000789342,0.00033026372,0.0000079827605,0.000014182361,0.00005619604,0.000016544514,0.9839274,0.008825748,0.0045499695,0.0021695993,0.00000896963],"about_ca_topic_score_codex":0.0037982808,"about_ca_topic_score_gemma":0.006933636,"teacher_disagreement_score":0.004158943,"about_ca_system_score_codex":0.0005757902,"about_ca_system_score_gemma":0.0006758528,"threshold_uncertainty_score":0.013913035},"labels":[],"label_agreement":null},{"id":"W7133003146","doi":"","title":"Image-Based Prediction of Building Attributes with Deep Learning","year":2023,"lang":"","type":"dissertation","venue":"TSpace","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Deep learning; Satellite; Feature (linguistics); Mean absolute error; Regression analysis; Regression; Mean absolute percentage error; Baseline (sea)","score_opus":0.021280782110775456,"score_gpt":0.28419505068186657,"score_spread":0.2629142685710911,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133003146","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.51168644,0.0016288357,0.47144988,0.00056445337,0.00022741084,0.00008199487,0.003090598,0.0046852008,0.006585285],"genre_scores_gemma":[0.9403315,0.00030079327,0.05266408,0.0000994327,0.000058827427,0.0000406406,0.0030288107,0.000050139857,0.0034258184],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99985147,0.000015040072,0.0000056114686,0.00005820029,0.000034652407,0.00003504189],"domain_scores_gemma":[0.9997441,0.00006905714,0.00003902052,0.00003535486,0.00009521272,0.000017265651],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027272425,0.0008614993,0.00045330258,0.0009447585,0.000120517536,0.00039280902,0.0006075004,0.00056617864,0.0012658222],"category_scores_gemma":[0.0006745411,0.00029339464,0.0005791705,0.0007998191,0.00021111219,0.0006681962,0.00036987758,0.00083043706,0.00079410133],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018820477,0.0004668448,0.01666897,0.000064171974,0.000104796985,0.00008771218,0.000028535456,0.5747755,0.0126748355,0.0010564355,0.0059680045,0.38791594],"study_design_scores_gemma":[0.0000020886714,0.000008642322,0.001569374,0.0000023709133,0.000004907833,0.0000043018954,0.0000029886955,0.9964045,0.0014197989,0.00039766307,0.00018067623,0.0000025634808],"about_ca_topic_score_codex":0.012012589,"about_ca_topic_score_gemma":0.018655358,"teacher_disagreement_score":0.012012589,"about_ca_system_score_codex":0.0006592875,"about_ca_system_score_gemma":0.00036968073,"threshold_uncertainty_score":0.02388537},"labels":[],"label_agreement":null},{"id":"W7134125570","doi":"10.14358/pers.25-00112r3","title":"Semantic Change Detection with Constrained Dual-Head Convolutional Neural Network Architecture for Oil/Gas Well Site Monitoring","year":2025,"lang":"en","type":"article","venue":"Photogrammetric Engineering & Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Natural Resources Canada; University of Waterloo","funders":"","keywords":"Change detection; Convolutional neural network; Land cover; Set (abstract data type); Segmentation; Binary number; Semantics (computer science); Pixel; Intersection (aeronautics)","score_opus":0.01611355089452916,"score_gpt":0.22713136911115214,"score_spread":0.211017818216623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7134125570","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5764995,0.0035115501,0.39537272,0.0009286278,0.00025314573,0.00018386121,0.002696909,0.011963898,0.008589734],"genre_scores_gemma":[0.92935497,0.00051673304,0.060478836,0.00024394294,0.000047466296,0.00006811013,0.0041998485,0.00010684828,0.0049833073],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997725,0.00002332093,0.000009586036,0.00008292886,0.00005311331,0.00005853244],"domain_scores_gemma":[0.9998684,0.000026221041,0.000017268916,0.000021753562,0.000052379128,0.00001403479],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003427086,0.0009628247,0.00053495105,0.0008784371,0.00029932684,0.0005019442,0.0011732861,0.0007009595,0.00095798826],"category_scores_gemma":[0.00070387387,0.0003162846,0.00057542446,0.0007975324,0.00033617168,0.0009911177,0.0005951469,0.0009024789,0.00036494422],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005856504,0.0004860447,0.012340612,0.00013703835,0.00025561964,0.00027607116,0.00011512338,0.48549747,0.020937085,0.0026398338,0.012517949,0.46421143],"study_design_scores_gemma":[0.0000061349,0.000025134554,0.0013269432,0.0000042550287,0.00002200467,0.000019742754,0.000015173631,0.99456906,0.0026337132,0.0007821651,0.0005885061,0.000007119202],"about_ca_topic_score_codex":0.050451282,"about_ca_topic_score_gemma":0.06841478,"teacher_disagreement_score":0.050451282,"about_ca_system_score_codex":0.0011568773,"about_ca_system_score_gemma":0.0011247172,"threshold_uncertainty_score":0.10031521},"labels":[],"label_agreement":null},{"id":"W7134176301","doi":"10.5281/zenodo.18907329","title":"AI-Aided Satellite Imagery for Land Use Mapping and Monitoring in Benin: A Computational Perspective","year":2010,"lang":"en","type":"article","venue":"Open MIND","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Satellite imagery; Perspective (graphical); Satellite; Convolutional neural network; Support vector machine; Land use","score_opus":0.05120714145637244,"score_gpt":0.3063163249748427,"score_spread":0.25510918351847023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7134176301","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8439543,0.00039352023,0.14540002,0.00093954307,0.000036552156,0.000088807385,0.00069152215,0.0014149251,0.0070808083],"genre_scores_gemma":[0.9505058,0.00006612452,0.04784021,0.000027426455,0.0000104206565,0.000029788629,0.00027169392,0.00001720545,0.0012313308],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.99992216,0.00003776559,0.0000028788097,0.000015012889,0.000013040663,0.000009147922],"domain_scores_gemma":[0.9997718,0.0001341862,0.00002019934,0.000016444152,0.00004591847,0.00001159465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000288893,0.00034334598,0.00019211756,0.0005538804,0.00025969747,0.0004737818,0.00032185632,0.00032882366,0.001672755],"category_scores_gemma":[0.00083952316,0.000110145855,0.00013190506,0.000592438,0.00017367394,0.0004125861,0.00025598568,0.00019690415,0.0001951074],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038258894,0.00017025568,0.02770658,0.0001335975,0.00007421651,0.00018207505,0.00019926271,0.70446414,0.013547271,0.0032647108,0.002166011,0.24770927],"study_design_scores_gemma":[0.0000031963605,0.000010309814,0.0022570628,0.0000031966013,0.000003497923,0.000007952308,0.00003795148,0.9952259,0.0017474177,0.00036327526,0.00033762679,0.0000025642655],"about_ca_topic_score_codex":0.028948503,"about_ca_topic_score_gemma":0.0461615,"teacher_disagreement_score":0.028948503,"about_ca_system_score_codex":0.00060814695,"about_ca_system_score_gemma":0.00037536578,"threshold_uncertainty_score":0.057560027},"labels":[],"label_agreement":null},{"id":"W7134182047","doi":"10.5281/zenodo.18907328","title":"AI-Aided Satellite Imagery for Land Use Mapping and Monitoring in Benin: A Computational Perspective","year":2010,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Satellite imagery; Perspective (graphical); Satellite; Convolutional neural network; Support vector machine; Land use","score_opus":0.03766738550050995,"score_gpt":0.24985000314393044,"score_spread":0.2121826176434205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7134182047","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8002137,0.0005210097,0.18868591,0.0009908415,0.000042239368,0.000097182565,0.0009860251,0.0018446785,0.0066184737],"genre_scores_gemma":[0.938541,0.00009133594,0.059424847,0.000029913575,0.000013969015,0.000038841805,0.0004294976,0.000025271953,0.0014052815],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9999318,0.00003230829,0.0000024466349,0.0000132846735,0.000011956065,0.000008194095],"domain_scores_gemma":[0.9998047,0.00011284476,0.000017992284,0.000014266389,0.00003940305,0.00001084138],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024904462,0.00036883834,0.0002068167,0.0005432835,0.00023013559,0.00043788736,0.00033115927,0.0003583753,0.0015844677],"category_scores_gemma":[0.0006897663,0.000112254755,0.00012836108,0.00063232996,0.00015954197,0.00037273575,0.00022913545,0.00019631925,0.00021392855],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034893455,0.00012995617,0.019206021,0.00012704227,0.00006064111,0.00013469301,0.00012081129,0.7649456,0.012460912,0.0024653848,0.0020313933,0.19796862],"study_design_scores_gemma":[0.0000032523178,0.00000835244,0.001840408,0.0000026413154,0.0000030165431,0.000006750067,0.000021145614,0.9959552,0.0015620762,0.00028353158,0.00031126165,0.0000023234002],"about_ca_topic_score_codex":0.03048257,"about_ca_topic_score_gemma":0.04229143,"teacher_disagreement_score":0.03048257,"about_ca_system_score_codex":0.000571381,"about_ca_system_score_gemma":0.00035810296,"threshold_uncertainty_score":0.060610235},"labels":[],"label_agreement":null},{"id":"W7163158604","doi":"10.1109/icsm64417.2025.11541561","title":"Multi-Temporal Latent Diffusion Transformers for Cloud Removal in Remote Sensing Images","year":2025,"lang":"","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Cloud computing; Transformer; Scale (ratio); Diffusion","score_opus":0.023033820147284296,"score_gpt":0.27147949196723725,"score_spread":0.24844567181995295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7163158604","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042124238,0.00033799832,0.95502174,0.00018815382,0.000028190567,0.000042759784,0.00016323393,0.0011581103,0.0009355772],"genre_scores_gemma":[0.7381693,0.00064046367,0.2563139,0.00014959542,0.00005217911,0.000062175255,0.00081871205,0.00029749665,0.0034961295],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99980813,0.000031749823,0.000010440158,0.000054979602,0.000061541126,0.000033227832],"domain_scores_gemma":[0.9995882,0.0001277253,0.000067243185,0.00009235152,0.000085644555,0.00003889644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005271148,0.0006280955,0.00048684553,0.000776717,0.000326414,0.0007461132,0.00080499134,0.0004921132,0.0014602649],"category_scores_gemma":[0.0017750341,0.0002309969,0.00067810225,0.00075034366,0.00061409076,0.001723316,0.00096703204,0.0011934828,0.00056159275],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041326854,0.00019516064,0.004110454,0.00023860963,0.00010292092,0.00018942714,0.00023920179,0.34266523,0.094075374,0.02906564,0.0046517886,0.524053],"study_design_scores_gemma":[0.000008263638,0.00002734124,0.00043708202,0.000006821615,0.000012259028,0.00006900687,0.000031633685,0.9790679,0.011708976,0.0072888564,0.0013321538,0.000009599032],"about_ca_topic_score_codex":0.0056388383,"about_ca_topic_score_gemma":0.01085114,"teacher_disagreement_score":0.0056388383,"about_ca_system_score_codex":0.00066206866,"about_ca_system_score_gemma":0.0007802099,"threshold_uncertainty_score":0.011212051},"labels":[],"label_agreement":null}]}