{"meta":{"query_hash":"326aa782fe05","filters":{"venue":"Machine Learning Science and Technology"},"cohort_total":90,"direct_labels_cover":0,"predictions_cover":90,"exported":90,"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/326aa782fe05","api":"https://metacan.xera.ac/api/v1/cohort?venue=Machine+Learning+Science+and+Technology"},"results":[{"id":"W2979321866","doi":"10.1088/2632-2153/ab6d5e","title":"Deep learning-guided surface characterization for autonomous hydrogen lithography","year":2020,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Advancements in Photolithography Techniques","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; National Institute for Nanotechnology; University of Alberta","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Alberta Innovates - Technology Futures; Compute Canada","keywords":"Characterization (materials science); Lithography; Nanotechnology; Materials science; Surface (topology); Deep learning; Artificial intelligence; Computer science; Optoelectronics; Geometry; Mathematics","score_opus":0.008238386016122916,"score_gpt":0.23863500402829257,"score_spread":0.23039661801216965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979321866","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8158167,0.00060531555,0.17720377,0.0010388466,0.000079790705,0.00051199814,0.0000060706207,0.0042707436,0.00046674864],"genre_scores_gemma":[0.9844722,0.00025710685,0.015004723,0.00010488061,0.000022185939,0.000055661745,0.000022448945,0.000036807865,0.000023998246],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987602,0.00001667981,0.00021994967,0.00041435362,0.00017745745,0.00041133937],"domain_scores_gemma":[0.99952865,0.000027215552,0.000074535616,0.00015372361,0.00012134741,0.00009454709],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003162943,0.00018847268,0.00021246276,0.00040127378,0.00037373003,0.000056448735,0.0003594689,0.00012359659,0.000009692532],"category_scores_gemma":[0.00029679624,0.00019528836,0.000035307705,0.002025541,0.0004465153,0.00025139243,0.000114674316,0.00043037682,0.0000033578467],"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":[0.000011385845,0.000019734502,0.09526533,0.00010041178,0.000036411875,0.000005393963,0.0004990301,0.012844255,0.756833,0.0035887142,0.000016398948,0.13077994],"study_design_scores_gemma":[0.0003260742,0.0004002499,0.0010419533,0.0000149478865,0.000018199475,0.000020160345,0.00007157872,0.82317555,0.09320147,0.0009376297,0.08042615,0.00036601513],"about_ca_topic_score_codex":0.000003452699,"about_ca_topic_score_gemma":7.3089575e-7,"teacher_disagreement_score":0.81033134,"about_ca_system_score_codex":0.00003051892,"about_ca_system_score_gemma":0.000018373212,"threshold_uncertainty_score":0.7963628},"labels":[],"label_agreement":null},{"id":"W2990614671","doi":"10.1088/2632-2153/abb215","title":"Quantum computation with machine-learning-controlled quantum stuff","year":2020,"lang":"en","type":"preprint","venue":"Machine Learning Science and Technology","topic":"Quantum Computing Algorithms and Architecture","field":"Computer Science","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":"Perimeter Institute","funders":"","keywords":"Computation; Set (abstract data type); Quantum computer; Computer science; Quantum; Quantum gate; Quantum circuit; Theoretical computer science; Computer engineering; Algorithm; Artificial intelligence; Quantum error correction; Physics; Programming language; Quantum mechanics","score_opus":0.008791595298409182,"score_gpt":0.24315708159832458,"score_spread":0.2343654862999154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990614671","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38915142,0.0025453686,0.5690442,0.033093173,0.00082286535,0.0010946468,0.000008159495,0.0039168014,0.0003233983],"genre_scores_gemma":[0.9670385,0.00011386362,0.032275625,0.0002783999,0.00010351321,0.000051069153,0.000020823161,0.00004975149,0.000068433495],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945688,0.00030902485,0.00063521916,0.0022824358,0.0011979751,0.0010065171],"domain_scores_gemma":[0.9973113,0.0002836693,0.0007954691,0.00077353965,0.00054954085,0.00028648105],"candidate_categories":["metaepi_narrow","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0017864989,0.0007441276,0.001181856,0.0015529612,0.0015658299,0.0009873349,0.0028846583,0.0004300795,0.0000046861287],"category_scores_gemma":[0.0012065744,0.00057154184,0.00012075101,0.0031951156,0.0012988921,0.00027690674,0.0044867015,0.004886976,0.000025592943],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000443329,0.0006176992,0.034775533,0.00056380744,0.000492754,0.0010021864,0.005976701,0.32165387,0.0057525914,0.21608132,0.00015571031,0.4124845],"study_design_scores_gemma":[0.002111073,0.0012170787,0.000634067,0.00014918658,0.00003896372,0.0002147034,0.00007738203,0.97034085,0.00015509553,0.022396293,0.0019775198,0.00068777817],"about_ca_topic_score_codex":0.00026093348,"about_ca_topic_score_gemma":0.00002369467,"teacher_disagreement_score":0.648687,"about_ca_system_score_codex":0.00009882884,"about_ca_system_score_gemma":0.00070065877,"threshold_uncertainty_score":0.999734},"labels":[],"label_agreement":null},{"id":"W3005694381","doi":"10.1088/2632-2153/ab891b","title":"Predicting drug properties with parameter-free machine learning: pareto-optimal embedded modeling (POEM)","year":2020,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Computational Drug Discovery Methods","field":"Computer Science","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":"Vector Institute","funders":"","keywords":"Overfitting; Machine learning; Hyperparameter; Benchmark (surveying); Computer science; Artificial intelligence; Context (archaeology); Parametric model; Generalization; Pareto principle; Parametric statistics; Algorithm; Mathematical optimization; Mathematics; Statistics; Artificial neural network","score_opus":0.021265928537934825,"score_gpt":0.24685808849383425,"score_spread":0.22559215995589943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3005694381","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66925746,0.0005058685,0.31835476,0.010401583,0.00006986504,0.00019252051,0.0000014906178,0.0010172573,0.00019918497],"genre_scores_gemma":[0.8997347,0.000021676271,0.09980833,0.0002800517,0.00004334728,0.000025417357,0.0000026352832,0.000022827462,0.000061011044],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99671054,0.00021500752,0.00036618626,0.0011742756,0.00085542485,0.00067857833],"domain_scores_gemma":[0.99849147,0.00025488168,0.00020412578,0.0005116447,0.0003296295,0.00020823028],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014777455,0.000320589,0.00037513586,0.0005205443,0.0010456153,0.00045709932,0.002113985,0.00009652491,0.000005397429],"category_scores_gemma":[0.0048984988,0.0002520699,0.000038995448,0.0028526501,0.0008014944,0.0010387726,0.0019826074,0.0013351876,0.00000899379],"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":[0.000051171122,0.00004260474,0.049107164,0.000047035795,0.000028101129,0.000046431214,0.0035290197,0.8999804,0.0034763538,0.0067412592,0.00001333302,0.03693713],"study_design_scores_gemma":[0.00051054545,0.0005199396,0.00012261883,0.000045402307,0.000012402466,0.00010756522,0.00041790804,0.99378675,0.0019074611,0.0017496061,0.0004928648,0.00032695357],"about_ca_topic_score_codex":0.00012620694,"about_ca_topic_score_gemma":0.00002141911,"teacher_disagreement_score":0.23047723,"about_ca_system_score_codex":0.000058458434,"about_ca_system_score_gemma":0.00032079866,"threshold_uncertainty_score":0.99999315},"labels":[],"label_agreement":null},{"id":"W3008125782","doi":"10.1088/2632-2153/abf5b8","title":"Neural message passing on high order paths","year":2021,"lang":"en","type":"preprint","venue":"Machine Learning Science and Technology","topic":"Advanced Graph Neural Networks","field":"Computer Science","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":"Vector Institute; University of Toronto","funders":"Office of Naval Research; Tata Steel","keywords":"Computer science; Graph; Artificial neural network; Aggregate (composite); Theoretical computer science; Message passing; Property (philosophy); Order (exchange); Topology (electrical circuits); Artificial intelligence; Mathematics; Distributed computing; Combinatorics","score_opus":0.007794981430785009,"score_gpt":0.2462904889328129,"score_spread":0.23849550750202791,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008125782","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8047325,0.002597845,0.15957034,0.026849693,0.0022907814,0.0004562129,0.000003447076,0.0026411342,0.000858044],"genre_scores_gemma":[0.9676965,0.00019008364,0.031317517,0.0005464812,0.000047424077,0.00002861691,0.0000066673674,0.000022349564,0.00014435258],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964415,0.000104554565,0.00030207212,0.0017260246,0.00066620123,0.00075965544],"domain_scores_gemma":[0.9979265,0.00011970219,0.00028571373,0.0011750873,0.00037205202,0.00012097312],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00059796905,0.00038355496,0.00044902743,0.0013272475,0.0010081566,0.0010125283,0.002328638,0.00039810996,0.000008956305],"category_scores_gemma":[0.00078612816,0.00035507826,0.000050475915,0.004105814,0.0012985994,0.00044151666,0.0053336592,0.0031721292,0.00000611658],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004661925,0.00007917493,0.0045526787,0.000042983487,0.000018696073,0.00046192552,0.00025327806,0.033992916,0.0052414145,0.053055782,0.000038296104,0.9022582],"study_design_scores_gemma":[0.0004482795,0.00042600473,0.0032484885,0.0002593265,0.000016946344,0.00021479714,0.00008399252,0.9586767,0.00302409,0.029274568,0.0033546085,0.0009722094],"about_ca_topic_score_codex":0.00014087641,"about_ca_topic_score_gemma":0.00005002804,"teacher_disagreement_score":0.92468375,"about_ca_system_score_codex":0.00009911234,"about_ca_system_score_gemma":0.0002870783,"threshold_uncertainty_score":0.99989015},"labels":[],"label_agreement":null},{"id":"W3009321976","doi":"10.1088/2632-2153/aba947","title":"Self-referencing embedded strings (SELFIES): A 100% robust molecular string representation","year":2020,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":596,"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 Institute for Advanced Research; Vector Institute; University of Toronto","funders":"Office of Naval Research","keywords":"String (physics); Intuition; Representation (politics); Interpretation (philosophy); Task (project management); Generative model","score_opus":0.015311517238724521,"score_gpt":0.2579600195144782,"score_spread":0.2426485022757537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009321976","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9827929,0.00016024316,0.0091072675,0.0049506905,0.00018578414,0.00027382124,0.00000270652,0.0015406171,0.0009859506],"genre_scores_gemma":[0.96448517,0.000026240667,0.0349891,0.00035024277,0.00005375462,0.00002079056,0.0000031462043,0.000026964148,0.00004459679],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99640036,0.00016215253,0.0004517807,0.0012649053,0.0009155364,0.00080525107],"domain_scores_gemma":[0.99857986,0.00009609911,0.00033040933,0.00042969896,0.0003123744,0.00025158204],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017964343,0.00030056958,0.0003919695,0.00054980745,0.0009817964,0.0005268979,0.0012390569,0.0001608817,0.00021629749],"category_scores_gemma":[0.00375578,0.00027966325,0.00003384711,0.0030215348,0.0009133753,0.0006911394,0.0010091444,0.00070777244,0.00013675418],"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":[0.00001516132,0.000019975892,0.009794565,0.000046769135,0.000004438455,0.00004423847,0.0010064256,0.0076835835,0.97254866,0.006041454,0.000018036346,0.0027766898],"study_design_scores_gemma":[0.00082854676,0.0006498785,0.0012599493,0.000058389487,0.000040538816,0.0001709502,0.001145747,0.35503936,0.63635993,0.0013405218,0.0023943775,0.00071181706],"about_ca_topic_score_codex":0.00016533711,"about_ca_topic_score_gemma":0.000007297108,"teacher_disagreement_score":0.34735575,"about_ca_system_score_codex":0.00009405947,"about_ca_system_score_gemma":0.0002579745,"threshold_uncertainty_score":0.99996555},"labels":[],"label_agreement":null},{"id":"W3009611342","doi":"10.1088/2632-2153/ab7d30","title":"Machine learning for the solution of the Schrödinger equation","year":2020,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":90,"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":"Schrödinger equation; Construct (python library); Headway; Density functional theory; Structural equation modeling; Chemical equation; Computer science; Applied mathematics; Mathematics; Statistical physics; Physics; Quantum mechanics; Chemistry; Machine learning; Simulation; Physical chemistry","score_opus":0.020326568000964225,"score_gpt":0.26050759911372834,"score_spread":0.24018103111276412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009611342","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8902224,0.0011077281,0.051119845,0.05508505,0.0007213637,0.0008602108,0.000009956053,0.00052211946,0.0003513758],"genre_scores_gemma":[0.9960668,0.000037389014,0.0033169917,0.00030852697,0.00006990589,0.00003924591,0.0000018620344,0.000017193921,0.00014206672],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997697,0.00017089355,0.00036524277,0.0006018778,0.00066135114,0.0005036548],"domain_scores_gemma":[0.9984831,0.000340503,0.00043842377,0.0003420201,0.00032473519,0.0000711912],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.0033590924,0.0001900194,0.0002523965,0.0001835862,0.0020557833,0.00017957641,0.0014337463,0.000106563544,0.00010734053],"category_scores_gemma":[0.009573315,0.000111508954,0.00004886067,0.0018547989,0.0023167857,0.00029821947,0.00078166596,0.0005885918,0.000024411525],"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":[0.000025256499,0.000013535706,0.021308966,0.000037376267,0.000003137735,3.5791987e-7,0.0004708528,0.010789171,0.9530952,0.0071063642,0.000027468037,0.0071223285],"study_design_scores_gemma":[0.00037720695,0.00042591232,0.0023270664,0.000032268403,0.000028809558,0.000018827739,0.00018188037,0.8298432,0.15442021,0.0010851109,0.0110657485,0.00019374228],"about_ca_topic_score_codex":0.00018714413,"about_ca_topic_score_gemma":0.00001570637,"teacher_disagreement_score":0.81905407,"about_ca_system_score_codex":0.000042781376,"about_ca_system_score_gemma":0.00015793493,"threshold_uncertainty_score":0.9992434},"labels":[],"label_agreement":null},{"id":"W3009669482","doi":"10.1088/2632-2153/abc81b","title":"Watch and learn—a generalized approach for transferrable learning in deep neural networks via physical principles","year":2020,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Machine Learning in Materials Science","field":"Materials Science","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":"National Research Council Canada; Vector Institute; University of Waterloo; University of Ottawa","funders":"Basic Energy Sciences; Natural Sciences and Engineering Research Council of Canada; Compute Canada; Lawrence Berkeley National Laboratory; Canadian Institute for Advanced Research; U.S. Department of Energy; Office of Science; National Science Foundation","keywords":"Artificial neural network; Set (abstract data type); Task (project management); Deep learning; Unsupervised learning; Statistical model; Sequence (biology); Statistical learning; Variety (cybernetics)","score_opus":0.015725000874920177,"score_gpt":0.2508074862268727,"score_spread":0.23508248535195253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009669482","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90462786,0.00025880558,0.08885505,0.0050366004,0.00009388679,0.0004511493,0.0000015379206,0.0005023999,0.00017269663],"genre_scores_gemma":[0.9825836,0.00003375774,0.016825674,0.00023323178,0.000099313074,0.00008763119,0.0000072854887,0.000034134515,0.000095378135],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966926,0.00022156714,0.00039480723,0.0012689437,0.00045205734,0.00097003864],"domain_scores_gemma":[0.9991092,0.00015355734,0.00016488171,0.00022486047,0.00013391401,0.00021358504],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0021882732,0.00032996287,0.00056028203,0.00028087225,0.00095861236,0.00032750654,0.0008049185,0.00017515721,0.000032334243],"category_scores_gemma":[0.0015989166,0.00028498762,0.000038654765,0.0016092219,0.0016716655,0.00045551235,0.00047892757,0.00095349073,0.000005486204],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008644083,0.00004948467,0.033749398,0.00008128964,0.000002970909,0.000007478424,0.0012226667,0.3561943,0.5912496,0.0028063587,0.0000025312822,0.014547517],"study_design_scores_gemma":[0.00079739257,0.0005583013,0.001027569,0.0000092754035,0.000012131487,0.00004654897,0.00018389242,0.9854829,0.010205115,0.00034195837,0.0010011477,0.00033380854],"about_ca_topic_score_codex":0.00014714281,"about_ca_topic_score_gemma":0.000018909748,"teacher_disagreement_score":0.62928855,"about_ca_system_score_codex":0.000044268807,"about_ca_system_score_gemma":0.000059791662,"threshold_uncertainty_score":0.99996024},"labels":[],"label_agreement":null},{"id":"W3016820838","doi":"10.1088/2632-2153/ab8aa3","title":"A machine learning workflow for molecular analysis: application to melting points","year":2020,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Computational Drug Discovery Methods","field":"Computer Science","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":"Vector Institute; University of Toronto; Canadian Institute for Advanced Research","funders":"","keywords":"Workflow; Computer science; Autoencoder; Molecular graph; Context (archaeology); Artificial intelligence; Cluster analysis; Machine learning; Representation (politics); Data mining; Graph; Theoretical computer science; Deep learning; Database","score_opus":0.010245958568693512,"score_gpt":0.2886374425979468,"score_spread":0.2783914840292533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3016820838","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.063803256,0.00023591924,0.90621144,0.028871896,0.000029657833,0.00027544616,0.0000014117818,0.00046294346,0.000108037246],"genre_scores_gemma":[0.75417435,0.000004145706,0.24490345,0.00082199724,0.000015409369,0.00005196894,0.0000051175975,0.000008903586,0.000014643324],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978836,0.00009801075,0.00025288571,0.0009296038,0.00042421935,0.00041164004],"domain_scores_gemma":[0.9989302,0.00020383266,0.00014627758,0.0002886181,0.0002634634,0.00016760589],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015652308,0.00016772994,0.00027628828,0.0009776006,0.0005613903,0.0002222313,0.001133753,0.00006981545,0.000002684641],"category_scores_gemma":[0.0028745052,0.00016574726,0.00005992454,0.008649096,0.00017870805,0.00031403097,0.0008338016,0.00041839827,0.00001364991],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015633845,0.000025728561,0.018637301,0.000019633158,0.00006483987,0.0000075816047,0.0007300888,0.33886698,0.027608648,0.10098148,0.0000060641223,0.513036],"study_design_scores_gemma":[0.0001947562,0.00020198486,0.00068852573,0.0000063691746,0.00003187909,0.000007263519,0.000035780267,0.9836555,0.003121218,0.0076847924,0.0041867965,0.00018513326],"about_ca_topic_score_codex":0.000031839303,"about_ca_topic_score_gemma":0.0000066499706,"teacher_disagreement_score":0.6903711,"about_ca_system_score_codex":0.00004836017,"about_ca_system_score_gemma":0.00009938185,"threshold_uncertainty_score":0.6758977},"labels":[],"label_agreement":null},{"id":"W3032990997","doi":"10.1088/2632-2153/ab983b","title":"The influence of sorbitol doping on aggregation and electronic properties of PEDOT:PSS: a theoretical study","year":2020,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Conducting polymers and applications","field":"Materials Science","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":"Canadian Institute for Advanced Research; Vector Institute; University of Toronto","funders":"Bundesministerium für Bildung und Forschung; European Commission; Canadian Institute for Advanced Research","keywords":"PEDOT:PSS; Materials science; Doping; Conductive polymer; Thermoelectric effect; Sorbitol; Conductivity; Nanotechnology; Polymer; Optoelectronics; Chemical physics; Chemistry; Physical chemistry; Composite material; Thermodynamics; Physics; Organic chemistry","score_opus":0.00889818836662518,"score_gpt":0.2443171745871615,"score_spread":0.23541898622053634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3032990997","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9950308,0.0003207114,0.000025866948,0.0043754694,0.000008438556,0.00016608916,3.66505e-7,0.000043946846,0.000028283956],"genre_scores_gemma":[0.99987495,0.000032285905,0.00003178982,0.000032570344,0.0000054675475,0.000015133005,5.0863378e-8,0.000002981358,0.000004772081],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992637,0.00003298184,0.00014507321,0.00022025678,0.00017261211,0.00016539007],"domain_scores_gemma":[0.9996058,0.00005537929,0.00010531079,0.00012497573,0.000085352374,0.000023220504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005330997,0.000058864596,0.0001045936,0.00007310818,0.00039888633,0.000033829543,0.00024385931,0.00002472027,0.0000030392894],"category_scores_gemma":[0.00090053194,0.000036436708,0.0000062338054,0.000529002,0.0020490522,0.00006474738,0.00014874795,0.00017382337,0.0000012305837],"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":[0.000012616411,0.0000197093,0.0067811385,0.000009450779,0.0000015751119,1.603237e-7,0.00083698606,0.00007530589,0.9356093,0.04785436,2.4733615e-7,0.008799155],"study_design_scores_gemma":[0.000224939,0.0012296002,0.0017130503,0.000041167666,0.000011990411,0.000007968282,0.002420156,0.0039720777,0.98697966,0.0032333848,0.00007941611,0.00008658382],"about_ca_topic_score_codex":0.00004305991,"about_ca_topic_score_gemma":0.000006901289,"teacher_disagreement_score":0.05137037,"about_ca_system_score_codex":0.0000069442253,"about_ca_system_score_gemma":0.000069197326,"threshold_uncertainty_score":0.7549818},"labels":[],"label_agreement":null},{"id":"W3036863718","doi":"10.1088/2632-2153/ac362b","title":"Attention-based quantum tomography","year":2021,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Quantum Computing Algorithms and Architecture","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Waterloo","funders":"Basic Energy Sciences; Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Quantum tomography; Quantum; Quantum state; Quantum process; Quantum entanglement; Quantum network; Quantum operation; Quantum information; Density matrix","score_opus":0.004414754458693062,"score_gpt":0.22053186793040316,"score_spread":0.21611711347171011,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3036863718","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78019977,0.0009800527,0.19482817,0.022198133,0.0003323328,0.000067034445,8.2854643e-7,0.0010128071,0.00038088337],"genre_scores_gemma":[0.96359766,0.000008895728,0.035979487,0.00032180946,0.000018166102,0.000003821258,0.0000013263291,0.0000055229816,0.00006334331],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984497,0.000043969383,0.00014064465,0.0006252975,0.00034217327,0.00039821188],"domain_scores_gemma":[0.99910295,0.00006373158,0.00006734071,0.00042062026,0.0002661672,0.000079199745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056193594,0.00012431966,0.0001443301,0.0006682614,0.0007665217,0.00023432757,0.0007733963,0.00007105915,0.000005807614],"category_scores_gemma":[0.00037621422,0.00010891866,0.000035823912,0.004339156,0.0005809652,0.00014947324,0.0004926789,0.0004594369,0.0000098692135],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002695635,0.00015429179,0.13315167,0.0000348859,0.000017999198,0.00027774685,0.00020772024,0.0031265188,0.06939357,0.2668345,0.00006169538,0.52673674],"study_design_scores_gemma":[0.00021232669,0.00012912734,0.006526366,0.000023068746,0.0000028822863,0.0001369104,0.000026300675,0.97282195,0.005236792,0.008811785,0.005898732,0.0001737338],"about_ca_topic_score_codex":0.000016297068,"about_ca_topic_score_gemma":0.0000047310223,"teacher_disagreement_score":0.96969545,"about_ca_system_score_codex":0.000014284992,"about_ca_system_score_gemma":0.00022441398,"threshold_uncertainty_score":0.5895543},"labels":[],"label_agreement":null},{"id":"W3040214011","doi":"10.1088/2632-2153/aba220","title":"A path towards quantum advantage in training deep generative models with quantum annealers","year":2020,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Quantum Computing Algorithms and Architecture","field":"Computer Science","cited_by":52,"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; D-Wave Systems (Canada)","funders":"Air Force Research Laboratory; Intelligence Advanced Research Projects Activity","keywords":"Computer science; MNIST database; Quantum; Autoencoder; Quantum annealing; Boltzmann machine; Inference; Artificial intelligence; Quantum computer; Artificial neural network; Physics; Quantum mechanics","score_opus":0.014796486295433366,"score_gpt":0.23483964151451517,"score_spread":0.2200431552190818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3040214011","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6283392,0.00043676878,0.35545278,0.014821043,0.00006286383,0.0001532051,0.0000012073044,0.00052589877,0.00020707693],"genre_scores_gemma":[0.94598705,0.000029954334,0.053315066,0.0006096526,0.000026971793,0.000010839926,0.0000011123975,0.000013271836,0.0000060565844],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997615,0.000071936236,0.00023943072,0.0009508376,0.0004464431,0.0006763894],"domain_scores_gemma":[0.99925846,0.000049492315,0.00012438193,0.00028027792,0.00011511572,0.00017226998],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006591091,0.00024874296,0.0003329057,0.00056262227,0.00050695386,0.00018734258,0.0011254686,0.00009633296,0.0000021120186],"category_scores_gemma":[0.0002469005,0.00019159766,0.000023697537,0.0034142588,0.00071419135,0.0004930627,0.000570833,0.00092135044,0.0000031587988],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003829281,0.000079261634,0.0071008923,0.000051244515,0.00002048945,0.0005444906,0.033328496,0.27562654,0.009014443,0.21432365,0.000008499584,0.4598637],"study_design_scores_gemma":[0.0004470171,0.0007895116,0.00034968686,0.000037437836,0.0000026287594,0.00010453338,0.001070203,0.9896232,0.00037049272,0.006673615,0.0002624181,0.0002692518],"about_ca_topic_score_codex":0.0000587501,"about_ca_topic_score_gemma":0.000018748533,"teacher_disagreement_score":0.71399665,"about_ca_system_score_codex":0.00003654748,"about_ca_system_score_gemma":0.000273564,"threshold_uncertainty_score":0.7813126},"labels":[],"label_agreement":null},{"id":"W3045102472","doi":"10.1088/2632-2153/abec21","title":"GPU coprocessors as a service for deep learning inference in high energy physics","year":2021,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Computational Physics and Python Applications","field":"Computer Science","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 Sciences and Engineering Research Council of Canada; Strong; High Energy Physics; U.S. Department of Energy; Office of Science; National Science Foundation","keywords":"Large Hadron Collider; Coprocessor; Workflow; Deep learning; Inference; Graphics; Energy (signal processing); Collider; High energy","score_opus":0.008290392874795395,"score_gpt":0.26320497688719985,"score_spread":0.25491458401240447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3045102472","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12570734,0.00022909815,0.8638846,0.009312861,0.00005427628,0.00008391549,8.685953e-7,0.00024341325,0.00048356588],"genre_scores_gemma":[0.9837326,0.000036787416,0.015533656,0.0004918268,0.00001920069,0.00005785538,0.000008805186,0.0000066832704,0.00011260263],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99875504,0.00002446684,0.00015100499,0.00054531876,0.00023315162,0.0002910366],"domain_scores_gemma":[0.9988078,0.0002512775,0.00009266528,0.00022904036,0.0005672139,0.000052012318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028949714,0.000111377536,0.00014979964,0.00022943963,0.00047278713,0.00016898467,0.0006178906,0.00006012124,0.0000034029156],"category_scores_gemma":[0.00051526347,0.0001161596,0.000015452539,0.0042179,0.00016570276,0.0003004676,0.00047378658,0.0003045543,0.000008825236],"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":[0.0000010863973,0.000029280525,0.0026946808,0.000008250203,0.000002120764,0.0000028743214,0.0001875186,0.00752242,0.0019494073,0.8153228,0.0000012914468,0.17227827],"study_design_scores_gemma":[0.00021934291,0.00006350222,0.0009692116,0.000012007975,0.00000202775,0.000012237609,0.00006236941,0.5864968,0.002421635,0.40550825,0.0041012447,0.00013138173],"about_ca_topic_score_codex":0.00021504634,"about_ca_topic_score_gemma":0.00014630526,"teacher_disagreement_score":0.85802525,"about_ca_system_score_codex":0.000033429897,"about_ca_system_score_gemma":0.0003019672,"threshold_uncertainty_score":0.47368512},"labels":[],"label_agreement":null},{"id":"W3092530885","doi":"10.1088/2632-2153/abedc8","title":"Olympus: a benchmarking framework for noisy optimization and experiment planning","year":2021,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Machine Learning in Materials Science","field":"Materials Science","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":"Canadian Institute for Advanced Research; University of British Columbia; Vector Institute; University of Toronto","funders":"Office of Naval Research; Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency","keywords":"Benchmarking; Suite; Benchmark (surveying); Python (programming language); Probabilistic logic; Software; Task (project management); Automation","score_opus":0.010018387529863637,"score_gpt":0.28854651987860147,"score_spread":0.27852813234873786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092530885","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.735937,0.0013301966,0.25926045,0.0022512272,0.00045850623,0.00020241788,0.0000035127364,0.00034494317,0.0002117859],"genre_scores_gemma":[0.6521312,0.00003716688,0.3474794,0.00016536348,0.000063033534,0.000044446006,0.00000412295,0.000015029368,0.00006024994],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977574,0.00008009357,0.00027641052,0.0009132065,0.00039564038,0.0005772821],"domain_scores_gemma":[0.9988904,0.00023483351,0.00018811907,0.0002994325,0.00027853527,0.00010869892],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.001807351,0.00020062446,0.00027359332,0.00036384302,0.0013253534,0.0004674572,0.0004024846,0.00015688661,0.0001712574],"category_scores_gemma":[0.0032492017,0.00018687682,0.0000181553,0.0010888041,0.001133864,0.0003444352,0.00057984114,0.0003030847,0.0000055941105],"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":[0.000017745433,0.00003477516,0.01800586,0.00005520674,0.000004002068,0.000021952772,0.0009905117,0.029735964,0.90877175,0.03344696,0.000014272496,0.008901],"study_design_scores_gemma":[0.0006401241,0.00051137264,0.0010868795,0.00023856516,0.000023793207,0.000339056,0.0009202742,0.6788179,0.30210987,0.0114561105,0.0032583934,0.0005976188],"about_ca_topic_score_codex":0.00002233636,"about_ca_topic_score_gemma":0.0000020093066,"teacher_disagreement_score":0.649082,"about_ca_system_score_codex":0.000055572094,"about_ca_system_score_gemma":0.00017479365,"threshold_uncertainty_score":0.9999748},"labels":[],"label_agreement":null},{"id":"W3094536971","doi":"10.1088/2632-2153/abd51e","title":"Atomic permutationally invariant polynomials for fitting molecular force fields","year":2020,"lang":"en","type":"preprint","venue":"Machine Learning Science and Technology","topic":"Machine Learning in Materials Science","field":"Materials Science","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":"Engineering and Physical Sciences Research Council; Agence Nationale de la Recherche; Leverhulme Trust","keywords":"Curse of dimensionality; Force field (fiction); Computer science; Invariant (physics); Extrapolation; Set (abstract data type); Body force; Algorithm; Artificial intelligence; Mathematics; Physics; Classical mechanics; Mathematical analysis; Quantum mechanics","score_opus":0.011648605062548787,"score_gpt":0.27406982839418187,"score_spread":0.2624212233316331,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094536971","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93031734,0.00044859614,0.047097933,0.019059515,0.00081547536,0.00090852776,0.00006052645,0.0008270297,0.00046505302],"genre_scores_gemma":[0.9510919,0.00002389603,0.04746563,0.0008225413,0.00014386601,0.00019294399,0.0000345246,0.000050896662,0.00017379658],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99550694,0.00017494797,0.0006974382,0.0018809923,0.00081786775,0.00092181744],"domain_scores_gemma":[0.99760985,0.00031928846,0.00071180693,0.0006351535,0.0005155678,0.00020831161],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003904016,0.000491011,0.00072728883,0.0007550827,0.0011331359,0.00079459115,0.0022027646,0.0005255912,0.00014814913],"category_scores_gemma":[0.009219563,0.00046706016,0.00009041358,0.0009530558,0.0016728026,0.00026792433,0.0031118682,0.001318663,0.000060586084],"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":[0.000029180625,0.00001851905,0.0017351217,0.00021180985,0.000009485382,0.000024200232,0.00039402785,0.00893342,0.9661589,0.020642484,0.00007278127,0.0017700454],"study_design_scores_gemma":[0.0010107767,0.0007027547,0.0010454005,0.00029852556,0.00010387627,0.00017023158,0.00025252323,0.5826142,0.3007788,0.10896365,0.0026040433,0.0014552302],"about_ca_topic_score_codex":0.00020595778,"about_ca_topic_score_gemma":0.000016532147,"teacher_disagreement_score":0.6653801,"about_ca_system_score_codex":0.00014445906,"about_ca_system_score_gemma":0.001000667,"threshold_uncertainty_score":0.9997781},"labels":[],"label_agreement":null},{"id":"W3097904339","doi":"10.1088/2632-2153/abda08","title":"Scientific intuition inspired by machine learning-generated hypotheses","year":2021,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":31,"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 Institute for Advanced Research; National Research Council Canada; Vector Institute; University of Toronto","funders":"H2020 Marie Skłodowska-Curie Actions; Natural Resources Canada; Natural Sciences and Engineering Research Council of Canada; Austrian Science Fund; European Commission","keywords":"Intuition; Realm; Rule of thumb; Boosting (machine learning); Scientific discovery; Scientific modelling; Big data; Focus (optics)","score_opus":0.009798201785643687,"score_gpt":0.23903378763252242,"score_spread":0.22923558584687873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3097904339","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9908518,0.0017431208,0.0013868393,0.002843423,0.00085023855,0.00019673015,0.00002936085,0.0011920795,0.00090639334],"genre_scores_gemma":[0.99200994,0.00010609336,0.004122569,0.00023352586,0.000054806264,0.00003655486,0.000073112955,0.000043054628,0.0033203652],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.994849,0.00044741115,0.00056253024,0.0017987267,0.0012072816,0.0011350412],"domain_scores_gemma":[0.9975297,0.00016233574,0.0003746509,0.00069151964,0.0009932913,0.00024852183],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["sts"],"category_scores_codex":[0.004207779,0.00041454445,0.00050094246,0.00092981517,0.0032979196,0.0016393939,0.0012278316,0.00024870702,0.0011694736],"category_scores_gemma":[0.008033693,0.00037728032,0.00004564151,0.0049882415,0.0044707735,0.0008576149,0.0011027376,0.0010101947,0.0003597024],"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":[0.000015591326,0.00007446567,0.018081293,0.000023904931,0.0000037454945,0.00003506931,0.0001673443,0.0007581744,0.97250146,0.002054549,0.0002065956,0.00607783],"study_design_scores_gemma":[0.0006285079,0.00040538647,0.0011384236,0.000060342023,0.000022656412,0.00032736556,0.00019606986,0.07494785,0.8510791,0.001931727,0.06858784,0.00067474955],"about_ca_topic_score_codex":0.00027067834,"about_ca_topic_score_gemma":0.00008497662,"teacher_disagreement_score":0.12142236,"about_ca_system_score_codex":0.00014671698,"about_ca_system_score_gemma":0.0005304387,"threshold_uncertainty_score":0.9998679},"labels":[],"label_agreement":null},{"id":"W3106718099","doi":"10.1088/2632-2153/abf3ac","title":"Natural evolutionary strategies for variational quantum computation","year":2021,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Quantum Computing Algorithms and Architecture","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Canadian Institute for Advanced Research; University of Toronto","funders":"Office of Naval Research; Office of Science; Canada Research Chairs; Google","keywords":"Gradient descent; Evolutionary computation; Evolutionary algorithm; Quantum; Optimization problem; Computer science; Estimator; Mathematical optimization; Electronic circuit; Quantum circuit; Quantum computer; Applied mathematics; Mathematics; Algorithm; Artificial intelligence; Artificial neural network; Physics; Quantum mechanics; Quantum network; Statistics","score_opus":0.006219557225293274,"score_gpt":0.24822755891903733,"score_spread":0.24200800169374406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3106718099","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1383002,0.0008285907,0.8491349,0.010714768,0.00040016358,0.00008740578,0.0000018889124,0.0004258546,0.00010622532],"genre_scores_gemma":[0.82652134,0.0000041804024,0.17327052,0.00011511926,0.000029126333,0.000006519893,0.0000069805155,0.0000037554762,0.00004244394],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987945,0.000031259457,0.00013656939,0.00047827445,0.000270925,0.00028846157],"domain_scores_gemma":[0.99915504,0.000131033,0.00007323606,0.00015169255,0.00045035532,0.000038640093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041725134,0.000101271915,0.00011650993,0.00032033643,0.0008469903,0.00025008092,0.00041833438,0.000057672525,0.0000015739024],"category_scores_gemma":[0.00038651505,0.00009140981,0.00002220998,0.0015107116,0.00032535984,0.00034881712,0.00034178348,0.00030892802,0.0000024530004],"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":[0.000001815963,0.000029996161,0.0011908202,0.000013066421,0.0000074913187,0.000011739789,0.00023446768,0.012063605,0.009359854,0.8998032,0.000050400886,0.077233516],"study_design_scores_gemma":[0.00017475686,0.000086026506,0.003001656,0.0000085252395,0.0000019576264,0.00012655536,0.00007854425,0.85536647,0.00026893753,0.13932315,0.0014604708,0.00010297596],"about_ca_topic_score_codex":0.000010768885,"about_ca_topic_score_gemma":0.000003494786,"teacher_disagreement_score":0.84330285,"about_ca_system_score_codex":0.000029518125,"about_ca_system_score_gemma":0.0004974796,"threshold_uncertainty_score":0.65144503},"labels":[],"label_agreement":null},{"id":"W3112351343","doi":"10.1088/2632-2153/ac09d6","title":"Deep molecular dreaming: inverse machine learning for de-novo molecular design and interpretability with surjective representations","year":2021,"lang":"en","type":"preprint","venue":"Machine Learning Science and Technology","topic":"Computational Drug Discovery Methods","field":"Computer Science","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":"Canadian Institute for Advanced Research; Vector Institute; University of Toronto","funders":"Office of Naval Research; Tata Steel","keywords":"Chemical space; Artificial intelligence; Computer science; Machine learning; Interpretability; Cheminformatics; Representation (politics); Property (philosophy); Generative model; Generative grammar; Chemistry; Drug discovery; Biology; Computational chemistry; Bioinformatics","score_opus":0.013200568935170052,"score_gpt":0.29761426499023386,"score_spread":0.2844136960550638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3112351343","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3341245,0.00066998275,0.66301614,0.0013424312,0.000066981804,0.00047377698,0.0000014436979,0.0002438562,0.00006089237],"genre_scores_gemma":[0.6293418,0.000028395865,0.37038004,0.00008409587,0.0000056910067,0.00011556738,0.000011257813,0.000018978,0.000014183218],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961541,0.00067945244,0.0003373469,0.0017515395,0.00050973974,0.00056777213],"domain_scores_gemma":[0.9972778,0.0008146919,0.00030662408,0.00071622076,0.00073230104,0.00015235995],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0031072854,0.0003801077,0.00048323156,0.0009451031,0.00064278865,0.00061904115,0.0011553615,0.00025565954,0.0000030744404],"category_scores_gemma":[0.004754788,0.00036812387,0.00006880197,0.0018118116,0.0013016725,0.0004361233,0.003098955,0.0015548517,5.5647e-7],"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":[0.000044873585,0.00008753499,0.028290313,0.0001347401,0.00010822425,0.0001770903,0.0026420522,0.881771,0.015507655,0.018462554,9.769377e-7,0.052772943],"study_design_scores_gemma":[0.0003922801,0.00031105557,0.001143457,0.00008143596,0.000044676803,0.0002541164,0.00030622713,0.9606831,0.009533786,0.026826413,0.000044266413,0.00037915382],"about_ca_topic_score_codex":0.00022208322,"about_ca_topic_score_gemma":0.000055726337,"teacher_disagreement_score":0.29521725,"about_ca_system_score_codex":0.00020328884,"about_ca_system_score_gemma":0.00093878777,"threshold_uncertainty_score":0.9998771},"labels":[],"label_agreement":null},{"id":"W3116279284","doi":"10.1088/2632-2153/abf834","title":"Defence against adversarial attacks using classical and quantum-enhanced Boltzmann machines <sup>†</sup>","year":2021,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","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":"Vector Institute; Creative Destruction Lab; University of Toronto; Perimeter Institute","funders":"“la Caixa” Foundation","keywords":"Boltzmann machine; MNIST database; Computer science; Discriminative model; Probabilistic logic; Relevance (law); Complement (music); Quantum; Artificial intelligence; Machine learning; Artificial neural network; Deep neural networks; Adversarial system; Generative grammar; Theoretical computer science; Physics","score_opus":0.012054372130597568,"score_gpt":0.2660878600578742,"score_spread":0.25403348792727665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3116279284","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71022373,0.0007627451,0.28289697,0.004247029,0.00032620228,0.00015502014,0.0000018761625,0.0006956002,0.0006908463],"genre_scores_gemma":[0.9513561,0.000113049115,0.04789103,0.00032668957,0.00011118959,0.000008626984,0.000004222551,0.00002737192,0.00016172235],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99595547,0.0002306678,0.00044722215,0.0016178974,0.00078351086,0.0009652422],"domain_scores_gemma":[0.99802047,0.0002682962,0.0002503167,0.00076862826,0.00045218618,0.00024010045],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0013287063,0.00041448555,0.0005264164,0.0008031653,0.0017846639,0.0005224134,0.001424492,0.00030900017,0.000015154941],"category_scores_gemma":[0.0036960319,0.00039693175,0.00005874459,0.0036152776,0.0019716737,0.001203095,0.0027402255,0.0015898863,0.000013943308],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006221418,0.0002129025,0.090032235,0.00011984818,0.00008804738,0.0007091119,0.0031735345,0.13927746,0.13921838,0.21362928,0.000066235494,0.41341078],"study_design_scores_gemma":[0.00077808986,0.00014291504,0.00084231305,0.000063736916,0.000020028823,0.0003393588,0.00031533118,0.98858154,0.0023757587,0.0039207987,0.002146434,0.00047369715],"about_ca_topic_score_codex":0.00006790934,"about_ca_topic_score_gemma":0.000015936852,"teacher_disagreement_score":0.8493041,"about_ca_system_score_codex":0.00012639536,"about_ca_system_score_gemma":0.0005241818,"threshold_uncertainty_score":0.99984825},"labels":[],"label_agreement":null},{"id":"W3120552573","doi":"10.1088/2632-2153/ac34db","title":"Miniaturizing neural networks for charge state autotuning in quantum dots","year":2021,"lang":"en","type":"preprint","venue":"Machine Learning Science and Technology","topic":"Advanced Memory and Neural Computing","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 interdisciplinaire d'innovation technologique; Université de Sherbrooke; Perimeter Institute; University of Waterloo","funders":"","keywords":"Computer science; Qubit; Artificial neural network; Quantum computer; Quantum dot; Quantum; Electronic engineering; Topology (electrical circuits); Electrical engineering; Artificial intelligence; Physics; Engineering; Quantum mechanics","score_opus":0.011405911392885482,"score_gpt":0.2516826439136773,"score_spread":0.2402767325207918,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3120552573","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98337966,0.0032822324,0.011209246,0.00032073192,0.00073452824,0.00025465112,0.0000024754054,0.00077146804,0.00004499968],"genre_scores_gemma":[0.99775404,0.0002180108,0.0018089601,0.000042333406,0.000055086257,0.00003720062,0.000014298865,0.000037278325,0.000032776537],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981648,0.000025711977,0.00030821358,0.0006501786,0.00015317953,0.0006979224],"domain_scores_gemma":[0.99938685,0.00010251892,0.0001034521,0.00025257468,0.00009027435,0.00006431442],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006633508,0.00028503747,0.000403609,0.0006899299,0.0003341761,0.00013091086,0.00042598878,0.00025129484,0.0000027652748],"category_scores_gemma":[0.00043907747,0.00029845804,0.000039624683,0.0010098829,0.00026008586,0.00016989475,0.0007349233,0.0022112208,4.8305725e-7],"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":[0.000006338546,0.000008171223,0.0034623179,0.00016499542,0.000008220968,0.000053586995,0.00030715676,0.8957644,0.020000888,0.00024470812,0.0000027518915,0.07997648],"study_design_scores_gemma":[0.00021363943,0.000051765677,0.00033451032,0.00016796033,0.000005961864,0.000033467,0.00008522817,0.99422413,0.003708929,0.000542387,0.00032699425,0.00030499825],"about_ca_topic_score_codex":0.000010535126,"about_ca_topic_score_gemma":0.000018015444,"teacher_disagreement_score":0.09845977,"about_ca_system_score_codex":0.00008223758,"about_ca_system_score_gemma":0.000051476054,"threshold_uncertainty_score":0.9999468},"labels":[],"label_agreement":null},{"id":"W3136819617","doi":"10.1088/2632-2153/ab7657","title":"Establishing an evaluation metric to quantify climate change image realism <sup>*</sup>","year":2020,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Climate Change Communication and Perception","field":"Social Sciences","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":"Université de Montréal","funders":"","keywords":"Generative grammar; Computer science; Metric (unit); Artificial intelligence; Realism; Generative model; Empathy; Deep learning; Machine learning; Classifier (UML); Data science; Psychology; Engineering","score_opus":0.33793072545208047,"score_gpt":0.4590707075245422,"score_spread":0.12113998207246174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3136819617","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9047955,0.00026285896,0.00019926127,0.086357005,0.0000746824,0.00054271374,0.000008761339,0.0005945651,0.0071646273],"genre_scores_gemma":[0.99566287,0.0012781628,0.0015958423,0.0012312497,0.00012773053,0.000053998716,0.000025604772,0.000011002282,0.000013559881],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979518,0.0003063785,0.00017938607,0.000456328,0.00066267047,0.0004434088],"domain_scores_gemma":[0.9988757,0.00008787287,0.00007447384,0.00027229855,0.0004595022,0.00023018656],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0046714433,0.000109952256,0.00015476937,0.0007809892,0.0018398343,0.0003759616,0.0007289133,0.00013077562,0.00017255047],"category_scores_gemma":[0.0056749173,0.0001102161,0.000017336564,0.004952569,0.0006689367,0.0010259057,0.000369342,0.00039833708,0.00006627232],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014437252,0.000041944335,0.03924217,0.000017402654,0.0000026150378,0.0000023761922,0.087624446,0.00007664566,0.008486382,0.020762106,0.000062986284,0.8436665],"study_design_scores_gemma":[0.00073222193,0.00090804225,0.025898274,0.00008048883,0.00006414065,0.000011238522,0.10851506,0.7148858,0.00029517995,0.0021008237,0.14569497,0.0008137809],"about_ca_topic_score_codex":0.001726726,"about_ca_topic_score_gemma":0.0007895424,"teacher_disagreement_score":0.8428527,"about_ca_system_score_codex":0.00011516085,"about_ca_system_score_gemma":0.00008242688,"threshold_uncertainty_score":0.9994596},"labels":[],"label_agreement":null},{"id":"W3151536792","doi":"10.1088/2632-2153/abf5b7","title":"MPGVAE: improved generation of small organic molecules using message passing neural nets","year":2021,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Advanced Graph Neural Networks","field":"Computer Science","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":"Canadian Institute for Advanced Research; Vector Institute; University of Toronto","funders":"","keywords":"Message passing; Computer science; Artificial neural network; Autoencoder; Matching (statistics); Theoretical computer science; Perceptron; Graph; Encoder; Artificial intelligence; Algorithm; Parallel computing; Mathematics","score_opus":0.01654811459114791,"score_gpt":0.24548077609478475,"score_spread":0.22893266150363684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3151536792","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66999406,0.0007364192,0.32744303,0.001447333,0.00013081451,0.000053689193,2.4672534e-7,0.000164169,0.000030262772],"genre_scores_gemma":[0.9190995,0.000030965577,0.0806755,0.00014168878,0.000016013866,0.0000019312824,0.0000012496588,0.0000083595105,0.000024761739],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985954,0.000057727717,0.00021182644,0.00057111366,0.00020292134,0.00036097193],"domain_scores_gemma":[0.9990928,0.000036674515,0.00016596363,0.00037648148,0.00027421562,0.000053850887],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030971147,0.00013357696,0.00018548447,0.0003487627,0.00046497906,0.00012670882,0.00058196386,0.000092870214,0.0000031582038],"category_scores_gemma":[0.0004233579,0.00012576823,0.000022301962,0.0030086273,0.0005086157,0.00040505463,0.0006755311,0.00039130772,4.8935044e-7],"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":[7.3372314e-7,0.000011055766,0.0034248596,0.0000045264796,0.000002723398,0.0000240914,0.00005146069,0.0029212276,0.9103854,0.004913082,0.0000010499073,0.07825983],"study_design_scores_gemma":[0.00013398191,0.00007118912,0.00039791915,0.0000110093615,0.0000042957067,0.00015749231,0.000021921867,0.8488579,0.14894095,0.0011978793,0.0000891361,0.000116368166],"about_ca_topic_score_codex":0.000015633703,"about_ca_topic_score_gemma":0.000035106754,"teacher_disagreement_score":0.84593666,"about_ca_system_score_codex":0.00002952873,"about_ca_system_score_gemma":0.00013777516,"threshold_uncertainty_score":0.512868},"labels":[],"label_agreement":null},{"id":"W3170889573","doi":"10.1088/2632-2153/ac9885","title":"Twin neural network regression is a semi-supervised regression algorithm","year":2022,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Neural Networks and Applications","field":"Computer Science","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 Ottawa; Vector Institute; University of Waterloo; Perimeter Institute","funders":"Natural Sciences and Engineering Research Council of Canada; National Research Council Canada; Compute Canada","keywords":"Regression; Artificial neural network; Artificial intelligence; Computer science; Data point; Regression analysis; Training set; Point (geometry); Linear regression; Pattern recognition (psychology); Machine learning; Algorithm; Mathematics; Statistics","score_opus":0.009164884751049228,"score_gpt":0.2518464698018076,"score_spread":0.24268158505075835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3170889573","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7615062,0.005922529,0.09411341,0.13148369,0.001344005,0.00096889056,0.000010511468,0.0031678732,0.001482877],"genre_scores_gemma":[0.98031574,0.00007367797,0.017561046,0.0012782709,0.00006797493,0.000080099504,0.0000036606784,0.00001135815,0.00060819625],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99793905,0.00007765849,0.00019100196,0.0007491028,0.00050987065,0.0005332871],"domain_scores_gemma":[0.9990787,0.000052933938,0.00013196257,0.00055156584,0.000087370216,0.000097499134],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0007252752,0.0001646695,0.00018076906,0.00032656407,0.0027757925,0.00014635119,0.0015208954,0.00006292259,0.00005034227],"category_scores_gemma":[0.00005336991,0.00012810029,0.000030346517,0.004220864,0.00039044043,0.00030365854,0.0023129855,0.0008795367,0.0000063341363],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036874035,0.000041920826,0.0076322216,0.0000033617287,0.0000032510354,0.00003066059,0.00023137407,0.0028912583,0.005319237,0.011775532,0.003158984,0.9689085],"study_design_scores_gemma":[0.00020041951,0.0001971184,0.0004354646,0.00001392103,0.0000029382966,0.00016216915,0.00006166719,0.93368906,0.0005279382,0.005413068,0.059123036,0.00017322856],"about_ca_topic_score_codex":0.00003567628,"about_ca_topic_score_gemma":0.0000019189924,"teacher_disagreement_score":0.9687353,"about_ca_system_score_codex":0.000047250178,"about_ca_system_score_gemma":0.00007133063,"threshold_uncertainty_score":0.99852246},"labels":[],"label_agreement":null},{"id":"W3171727251","doi":"10.1088/2632-2153/ac4f3f","title":"Probing transfer learning with a model of synthetic correlated datasets","year":2022,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","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":"Canadian Institute for Advanced Research","funders":"European Commission; Royal Society; Wellcome Trust; Wellcome","keywords":"Computer science; Generalization; Transfer of learning; Artificial intelligence; Salient; Machine learning; Task (project management); Synthetic data; Parametric statistics; Feature (linguistics); Artificial neural network; Binary classification; Sample (material); Data mining; Mathematics","score_opus":0.009529413654964517,"score_gpt":0.21710741550436286,"score_spread":0.20757800184939834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3171727251","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5537141,0.0002167973,0.44132298,0.0025585187,0.0000681694,0.00026388405,0.0000055837627,0.00070622767,0.0011437542],"genre_scores_gemma":[0.9918245,0.000010360748,0.007822018,0.00007470909,0.0000018794316,0.000027292388,0.000007207062,0.000011506121,0.00022053774],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99814594,0.000103078,0.00021661638,0.00057391945,0.0005751801,0.00038525654],"domain_scores_gemma":[0.9993297,0.00006469884,0.000109070104,0.0003215966,0.00010760886,0.00006732742],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001294087,0.00014164587,0.00020320794,0.0008152953,0.0012735506,0.0000802463,0.0009776605,0.000046168305,0.000022401417],"category_scores_gemma":[0.0002371005,0.00012575791,0.000017829494,0.0028255691,0.0006475226,0.0003682585,0.00059451605,0.0010531133,0.000003189091],"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":[0.00003612339,0.00009885513,0.010000507,0.000025951342,0.000019446854,0.000034315097,0.0038581868,0.725479,0.047228992,0.12272521,0.000009992998,0.0904834],"study_design_scores_gemma":[0.00041685675,0.0005005091,0.00008991741,0.000017105905,0.000008020866,0.0001538383,0.000572784,0.99394417,0.001036515,0.0007212357,0.0023677691,0.00017129087],"about_ca_topic_score_codex":0.000024789555,"about_ca_topic_score_gemma":0.000003580305,"teacher_disagreement_score":0.4381104,"about_ca_system_score_codex":0.000048644197,"about_ca_system_score_gemma":0.00022857072,"threshold_uncertainty_score":0.97952497},"labels":[],"label_agreement":null},{"id":"W3212195610","doi":"10.1088/2632-2153/ac3845","title":"Gradient domain machine learning with composite kernels: improving the accuracy of PES and force fields for large molecules","year":2021,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":9,"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 British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Ab initio; Generalization; Computer science; Metric (unit); Kernel (algebra); Energy minimization; Force field (fiction); Algorithm; Artificial intelligence; Machine learning; Mathematics; Computational chemistry; Physics; Chemistry; Mathematical analysis","score_opus":0.005665228847731934,"score_gpt":0.24007527585691166,"score_spread":0.23441004700917972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212195610","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9691341,0.0011815517,0.025537731,0.0033653358,0.00012330791,0.000306934,0.0000145471395,0.0001916896,0.00014479256],"genre_scores_gemma":[0.978482,0.000069265276,0.02096318,0.00016337793,0.000025756335,0.000041175113,0.000007119332,0.000022097369,0.00022602272],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99735737,0.00020071714,0.00036669782,0.00087635516,0.0004979069,0.0007009297],"domain_scores_gemma":[0.9981663,0.0005169998,0.00041232866,0.0004315257,0.00037929518,0.000093501476],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0031299493,0.00026140013,0.00039366444,0.0002824384,0.0016516694,0.00031644746,0.00073651294,0.000116356954,0.00004671384],"category_scores_gemma":[0.0033602994,0.00017457972,0.000033880577,0.0010520201,0.0015639822,0.0003182407,0.0008540617,0.0005704356,0.0000029607627],"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":[0.00005133791,0.00003889216,0.037363224,0.00011681777,0.0000076614615,0.000015826272,0.0008920097,0.0014442718,0.94045395,0.014877643,0.0000040881905,0.0047343075],"study_design_scores_gemma":[0.0025097865,0.002046819,0.008325622,0.00025741963,0.00009496905,0.0009763864,0.0028818208,0.3667091,0.60013103,0.008202031,0.0069398843,0.00092511135],"about_ca_topic_score_codex":0.00021172846,"about_ca_topic_score_gemma":0.00014457961,"teacher_disagreement_score":0.36526483,"about_ca_system_score_codex":0.000031579217,"about_ca_system_score_gemma":0.00017043832,"threshold_uncertainty_score":0.99964803},"labels":[],"label_agreement":null},{"id":"W4283787033","doi":"10.1088/2632-2153/ac7ddc","title":"Curiosity in exploring chemical spaces: intrinsic rewards for molecular reinforcement learning","year":2022,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":19,"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 Institute for Advanced Research; Vector Institute; University of Toronto","funders":"Natural Resources Canada; Mitacs; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Austrian Science Fund; Compute Canada","keywords":"Curiosity; Reinforcement learning; Pace; Chemical space; Computer science; Space (punctuation); Field (mathematics); Reinforcement; Artificial intelligence; Human–computer interaction; Cognitive science; Drug discovery; Engineering; Psychology; Neuroscience; Biology; Bioinformatics; Mathematics","score_opus":0.019678158098975926,"score_gpt":0.2802007172333917,"score_spread":0.26052255913441574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283787033","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78715026,0.00016795368,0.20826073,0.0036913834,0.00012964905,0.00019846986,3.1438663e-7,0.00023258798,0.0001686287],"genre_scores_gemma":[0.97435147,0.0000105234585,0.025290301,0.00012589293,0.000009311921,0.00016980588,0.0000023268183,0.0000076291203,0.00003275921],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981398,0.000103455954,0.00021115507,0.00061116327,0.00051348715,0.00042094346],"domain_scores_gemma":[0.9993295,0.00016958412,0.00010325279,0.00024418347,0.00009953486,0.00005391347],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023458116,0.00012564634,0.00017960998,0.0008970116,0.0006406242,0.00011659139,0.00097179477,0.00003502906,0.00000516368],"category_scores_gemma":[0.0013752616,0.00013624974,0.000027920725,0.0027648343,0.00025692358,0.00042569116,0.0020991112,0.00075138296,0.0000013064267],"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":[0.000019488481,0.000050900304,0.011271607,0.000023535382,0.000007543771,0.000036366648,0.0011890627,0.49268138,0.02913209,0.2725867,0.000006590775,0.19299471],"study_design_scores_gemma":[0.0005107545,0.00034672907,0.00047441534,0.000013374279,0.0000031866314,0.000057966456,0.00029407543,0.96116316,0.013247862,0.016623557,0.007027898,0.00023702839],"about_ca_topic_score_codex":0.00004995729,"about_ca_topic_score_gemma":0.0000019707932,"teacher_disagreement_score":0.46848175,"about_ca_system_score_codex":0.00022951687,"about_ca_system_score_gemma":0.00020458992,"threshold_uncertainty_score":0.55561036},"labels":[],"label_agreement":null},{"id":"W4306825440","doi":"10.1088/2632-2153/ac9bcb","title":"‘Flux+Mutability’: a conditional generative approach to one-class classification and anomaly detection","year":2022,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Particle physics theoretical and experimental studies","field":"Physics and Astronomy","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 Regina","funders":"Natural Sciences and Engineering Research Council of Canada; U.S. Department of Energy","keywords":"Anomaly detection; Computer science; Cluster analysis; Artificial intelligence; Inference; Concept drift; Anomaly (physics); Machine learning; Data mining; Particle physics; Physics; Data stream mining","score_opus":0.012790204512549539,"score_gpt":0.2530306228405579,"score_spread":0.24024041832800835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306825440","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98662394,0.000037985978,0.00764893,0.0013388288,0.000018477707,0.000120641205,0.000008309303,0.000046056444,0.0041568493],"genre_scores_gemma":[0.99928564,3.9202945e-7,0.00043826803,0.000040978455,0.000019872912,0.0001597636,0.000009106391,0.0000037155808,0.00004228462],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992375,0.000035603935,0.00008384244,0.00030888186,0.0001608363,0.00017337459],"domain_scores_gemma":[0.9997764,0.000019912068,0.000034013756,0.00007488692,0.000046355748,0.000048406917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023719108,0.00007201809,0.00009501187,0.00010915481,0.0011527844,0.000035541005,0.00009774081,0.0000117755735,0.000034908007],"category_scores_gemma":[0.000025090727,0.00006833613,0.000009952168,0.00062936044,0.00069500686,0.00007865625,0.00030865255,0.00020418271,0.0000047986323],"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":[0.000011155083,0.00013385886,0.075556815,0.0000018058722,0.000011414985,1.010399e-7,0.0003943267,0.00012455987,0.34875265,0.55542624,0.000004612796,0.019582432],"study_design_scores_gemma":[0.0009598601,0.0011741387,0.04694094,0.000004383296,0.000035165973,0.000016649483,0.00953424,0.19662523,0.3293119,0.4100311,0.004794875,0.0005714996],"about_ca_topic_score_codex":0.000047635465,"about_ca_topic_score_gemma":5.629179e-7,"teacher_disagreement_score":0.19650067,"about_ca_system_score_codex":0.000040513536,"about_ca_system_score_gemma":0.000018554012,"threshold_uncertainty_score":0.88664025},"labels":[],"label_agreement":null},{"id":"W4310124277","doi":"10.1088/2632-2153/aca6cd","title":"Training neural networks using Metropolis Monte Carlo and an adaptive variant","year":2022,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","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":"Vector Institute; University of Ottawa","funders":"Lawrence Berkeley National Laboratory; Basic Energy Sciences; U.S. Department of Energy","keywords":"Artificial neural network; Gradient descent; Monte Carlo method; Computer science; Complement (music); Metropolis–Hastings algorithm; Stochastic neural network; Artificial intelligence; Set (abstract data type); Algorithm; Stochastic gradient descent; Stability (learning theory); Monte Carlo algorithm; Function (biology); Machine learning; Time delay neural network; Markov chain Monte Carlo; Mathematics","score_opus":0.025927705537782415,"score_gpt":0.2769468053588732,"score_spread":0.25101909982109083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310124277","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99084586,0.0002643658,0.0077137277,0.00046372574,0.000155215,0.00009226211,0.0000036750464,0.00009716842,0.00036401273],"genre_scores_gemma":[0.99907553,0.0000042071347,0.0006692399,0.000064833366,0.00009355781,0.000012477935,0.0000020132345,0.000010996722,0.000067147805],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99888444,0.00006973135,0.00012059747,0.00039958573,0.00017119724,0.00035447223],"domain_scores_gemma":[0.99963665,0.000018631952,0.000084439926,0.00012699919,0.00004480615,0.0000884882],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0003996955,0.00012127582,0.00016068152,0.00029129977,0.0015134576,0.000068726076,0.00019596322,0.000030019453,0.000067166875],"category_scores_gemma":[0.000012373945,0.00011410395,0.000017282244,0.0009350203,0.0005121064,0.0002101258,0.0003188041,0.0007245883,1.3882692e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003527964,0.000047992937,0.025211819,0.0000015810874,0.000024302073,0.000018441673,0.00091988937,0.45908213,0.0018868911,0.048611615,0.000012711863,0.46414736],"study_design_scores_gemma":[0.00017508572,0.00026117344,0.00015201345,0.0000019064478,0.000011889511,0.00007285598,0.0029787428,0.9946417,0.000026771224,0.00088820246,0.0006620839,0.00012753863],"about_ca_topic_score_codex":0.0006313401,"about_ca_topic_score_gemma":0.000006326125,"teacher_disagreement_score":0.5355596,"about_ca_system_score_codex":0.000028544011,"about_ca_system_score_gemma":0.000042735257,"threshold_uncertainty_score":0.99978644},"labels":[],"label_agreement":null},{"id":"W4311003603","doi":"10.1088/2632-2153/aca9ca","title":"Boost invariant polynomials for efficient jet tagging","year":2022,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Particle physics theoretical and experimental studies","field":"Physics and Astronomy","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":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Interpretability; Invariant (physics); Computer science; Jet (fluid); Artificial intelligence; Representation (politics); Particle physics; Theoretical computer science; Machine learning; Physics; Quantum mechanics","score_opus":0.007407402249508059,"score_gpt":0.2549133672859641,"score_spread":0.24750596503645603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311003603","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9919009,0.00016464047,0.0011829326,0.003842722,0.000071714545,0.00014970389,0.000013889321,0.000071541646,0.00260193],"genre_scores_gemma":[0.9994977,4.890936e-7,0.00023655564,0.000056361812,0.000027668519,0.00011641128,0.0000029805828,0.0000059107524,0.00005589218],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991815,0.000017433138,0.00009822521,0.00025632652,0.00014278026,0.00030373773],"domain_scores_gemma":[0.9997442,0.000046009456,0.000046953835,0.00009065352,0.00003229038,0.00003990485],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0004284908,0.00008240057,0.00012433111,0.00010693959,0.001587776,0.000034314056,0.00019995519,0.000008692216,0.00007602685],"category_scores_gemma":[0.000042424308,0.000070024704,0.000021426713,0.00051108486,0.0005887161,0.000033926066,0.00055183005,0.00017654241,0.000005127054],"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":[0.000016177153,0.00009819193,0.040378854,0.000002381429,0.00001611153,6.781157e-7,0.00031873616,0.00053761946,0.15671456,0.78601557,0.00005517082,0.01584593],"study_design_scores_gemma":[0.0019422914,0.0011070061,0.00072505255,0.000013151736,0.000052277413,0.000013107506,0.006750159,0.18287711,0.5962102,0.15607215,0.053523563,0.0007139613],"about_ca_topic_score_codex":0.000080036596,"about_ca_topic_score_gemma":2.0941988e-7,"teacher_disagreement_score":0.62994343,"about_ca_system_score_codex":0.000028724204,"about_ca_system_score_gemma":0.000030119141,"threshold_uncertainty_score":0.99971205},"labels":[],"label_agreement":null},{"id":"W4318947280","doi":"10.1088/2632-2153/acb895","title":"Supplementing recurrent neural networks with annealing to solve combinatorial optimization problems","year":2023,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Metaheuristic Optimization Algorithms Research","field":"Computer Science","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":"Vector Institute; University of Waterloo","funders":"Vector Institute","keywords":"Travelling salesman problem; Simulated annealing; Mathematical optimization; Combinatorial optimization; Computer science; Markov chain; Optimization problem; Heuristic; Artificial neural network; Extremal optimization; Scheduling (production processes); Convergence (economics); Mathematics; Algorithm; Artificial intelligence; Machine learning","score_opus":0.012655573042973819,"score_gpt":0.27166090448910435,"score_spread":0.2590053314461305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318947280","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009729776,0.00004365764,0.9825656,0.0059943576,0.00037350354,0.00036546265,8.57159e-7,0.0008179776,0.00010882923],"genre_scores_gemma":[0.7105924,0.00005472029,0.2889659,0.00010127594,0.00006779846,0.00008552076,0.000019128294,0.000023109671,0.000090125905],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99775845,0.000045885437,0.00022330863,0.0006589329,0.0006538804,0.0006595488],"domain_scores_gemma":[0.9989417,0.00008079448,0.00010061715,0.00032154267,0.00041486576,0.00014048957],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018672488,0.0001396682,0.00016776752,0.0012206554,0.0008659597,0.00043627885,0.0009406648,0.000063696425,0.000011395135],"category_scores_gemma":[0.00085460016,0.000118385025,0.000011000575,0.008526829,0.000293415,0.00038080776,0.0009974389,0.00044274976,0.000008253266],"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":[0.0000025865834,0.000012160453,0.004668598,0.0000070460255,0.000003879895,0.000010109592,0.00016485975,0.9358701,0.0000676568,0.010652142,0.0000443136,0.048496544],"study_design_scores_gemma":[0.00032001562,0.0003503976,0.00011489521,0.000016772805,0.0000025747104,0.000018770148,0.000048359132,0.99786407,0.00008505138,0.0002265574,0.0008079491,0.0001445776],"about_ca_topic_score_codex":0.000025508163,"about_ca_topic_score_gemma":0.000004292925,"teacher_disagreement_score":0.70086265,"about_ca_system_score_codex":0.00004639956,"about_ca_system_score_gemma":0.000098293895,"threshold_uncertainty_score":0.66603494},"labels":[],"label_agreement":null},{"id":"W4319601507","doi":"10.1088/2632-2153/acb4df","title":"Neural network enhanced measurement efficiency for molecular groundstates","year":2023,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Quantum Computing Algorithms and Architecture","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Perimeter Institute; University of Waterloo","funders":"Institut Périmètre de physique théorique; Natural Sciences and Engineering Research Council of Canada; Mitacs; Canada Research Chairs","keywords":"Observable; Qubit; Estimator; Computer science; Statistical physics; Artificial neural network; Quantum; Scaling; Restricted Boltzmann machine; Boltzmann machine; Algorithm; Quantum tomography; Wave function; Artificial intelligence; Quantum state; Topology (electrical circuits); Theoretical computer science; Physics; Quantum mechanics; Mathematics; Statistics","score_opus":0.008999582188631634,"score_gpt":0.23919591357411593,"score_spread":0.2301963313854843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319601507","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5193425,0.00041084466,0.47153926,0.0066597173,0.00034646777,0.00022756138,4.979777e-7,0.0013836258,0.00008954485],"genre_scores_gemma":[0.98206174,0.0000136401295,0.017672962,0.00014615881,0.00003488729,0.00002692027,0.0000010237183,0.000009249958,0.000033442942],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979458,0.000032067604,0.00016890957,0.0006411283,0.0004929029,0.0007191928],"domain_scores_gemma":[0.9991951,0.00007648951,0.00008198616,0.00031537257,0.00025872997,0.00007229374],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017852815,0.00015128062,0.00016805237,0.0004989797,0.000975128,0.0001975307,0.0010388985,0.000060554234,6.446154e-7],"category_scores_gemma":[0.00060785434,0.000126758,0.0000318157,0.004070203,0.00041224112,0.00013457485,0.00061023864,0.00030784676,0.000007544131],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000059404906,0.00003576797,0.001051651,0.000032603562,0.000013750023,0.000028807564,0.00058756105,0.104709476,0.10906589,0.07885928,0.00010952342,0.70549977],"study_design_scores_gemma":[0.00021377098,0.00032168176,0.00039386164,0.000019763022,0.0000028312902,0.000020293075,0.000025708196,0.97440815,0.006741172,0.016117183,0.0015676494,0.00016791167],"about_ca_topic_score_codex":0.0000111705085,"about_ca_topic_score_gemma":0.000003230744,"teacher_disagreement_score":0.8696987,"about_ca_system_score_codex":0.000031553867,"about_ca_system_score_gemma":0.00009803954,"threshold_uncertainty_score":0.74999946},"labels":[],"label_agreement":null},{"id":"W4319871631","doi":"10.1088/2632-2153/acbb53","title":"Robust simulation-based inference in cosmology with Bayesian neural networks","year":2023,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Cosmology and Gravitation Theories","field":"Physics and Astronomy","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":"University of Waterloo","funders":"Science and Technology Facilities Council","keywords":"Inference; Cosmology; Artificial neural network; Bayesian inference; Computer science; Bayesian probability; Artificial intelligence; Machine learning; Physics; Astrophysics","score_opus":0.009143964899425011,"score_gpt":0.26015496040579356,"score_spread":0.2510109955063685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319871631","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9109027,0.000017795723,0.08771156,0.0010638017,0.000039687253,0.00008397511,0.0000014345542,0.00012313113,0.000055938453],"genre_scores_gemma":[0.9993888,1.9854417e-7,0.00047910056,0.000048019967,0.000011166544,0.000012903387,0.000011149429,0.0000054932693,0.000043137643],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99923843,0.000039145634,0.00010611275,0.0002519608,0.000082749226,0.00028160762],"domain_scores_gemma":[0.99937814,0.00034205784,0.000057110068,0.000110561996,0.00008258301,0.000029555933],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003361414,0.00008998428,0.00012291437,0.0005494761,0.00031149725,0.000024927562,0.00016125037,0.000054261756,0.000026629854],"category_scores_gemma":[0.00017316162,0.000076129734,0.000008167378,0.0023106213,0.0008859476,0.00008691283,0.00006316509,0.00034377797,0.000004905842],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000059634926,0.00000555777,0.49487385,7.4752637e-7,0.0000013386509,0.000003044898,0.000029591714,0.47170743,0.000019035211,0.02711628,3.7137045e-7,0.0062367893],"study_design_scores_gemma":[0.00028287194,0.000083421415,0.02786112,0.000005325997,0.0000034321465,9.179589e-7,0.00017556749,0.9313865,0.00003157967,0.04004745,0.00003360917,0.000088232446],"about_ca_topic_score_codex":0.00014239259,"about_ca_topic_score_gemma":0.000043592652,"teacher_disagreement_score":0.46701273,"about_ca_system_score_codex":0.000010426122,"about_ca_system_score_gemma":0.00007336783,"threshold_uncertainty_score":0.32643107},"labels":[],"label_agreement":null},{"id":"W4322622206","doi":"10.1088/2632-2153/acc008","title":"Developing novel machine-learning-based fire weather indices","year":2023,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Fire effects on ecosystems","field":"Environmental Science","cited_by":21,"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; Warning system; Firefighting; Estimation; Machine learning; Extreme weather; Meteorology; Geography; Climate change; Engineering; Cartography","score_opus":0.008285820825063054,"score_gpt":0.23218869483250476,"score_spread":0.22390287400744172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322622206","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9914146,0.000120751836,0.0007341952,0.0049358346,0.00015484457,0.00023301618,0.0000028514041,0.0012265864,0.0011772843],"genre_scores_gemma":[0.99765164,0.000022214388,0.001208386,0.00019312663,0.000016491816,0.00003735771,0.000007805975,0.000029437426,0.0008335446],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99764556,0.00006272383,0.00022847227,0.00074697286,0.00059939193,0.0007168732],"domain_scores_gemma":[0.9992848,0.00014622606,0.00016088512,0.00027775698,0.000028427516,0.00010192067],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017732622,0.00023433872,0.00024188694,0.00055043696,0.001095348,0.00010788045,0.000736399,0.00017403906,0.00018972004],"category_scores_gemma":[0.0012411618,0.00020280313,0.000027827975,0.0046526035,0.0011844166,0.0002738752,0.00067607395,0.00071785157,0.0008546347],"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":[0.0000069422713,0.000030614636,0.8937871,0.000030199522,0.000007635282,0.000031689367,0.00026591122,0.0039296546,0.02908275,0.0005327323,0.0000788282,0.072215945],"study_design_scores_gemma":[0.0005751176,0.0003174174,0.061372004,0.00006276358,0.000009515444,0.00005771143,0.0001669574,0.86241585,0.0038932317,0.00026757264,0.07039666,0.00046519487],"about_ca_topic_score_codex":0.001073901,"about_ca_topic_score_gemma":0.00027991793,"teacher_disagreement_score":0.8584862,"about_ca_system_score_codex":0.00018920166,"about_ca_system_score_gemma":0.00007244563,"threshold_uncertainty_score":0.9999233},"labels":[],"label_agreement":null},{"id":"W4367182092","doi":"10.1088/2632-2153/acc928","title":"Encrypted machine learning of molecular quantum properties","year":2023,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Machine Learning in Materials Science","field":"Materials Science","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":"Vector Institute; University of Toronto","funders":"","keywords":"Homomorphic encryption; Encryption; Computer science; Kernel (algebra); Theoretical computer science; Process (computing); Machine learning; Data mining; Artificial intelligence; Computer security; Mathematics","score_opus":0.011051128617533138,"score_gpt":0.24467313524328976,"score_spread":0.23362200662575663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367182092","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9939787,0.0005814023,0.0006715263,0.002194482,0.00030981324,0.00023534676,0.000005519684,0.0014807271,0.0005425224],"genre_scores_gemma":[0.99740607,0.00010221894,0.0018846262,0.000061499806,0.00002176515,0.00003251052,0.0000066532625,0.000036389873,0.00044827544],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99617404,0.0002593326,0.00054768584,0.0009850347,0.001057827,0.00097609364],"domain_scores_gemma":[0.9984195,0.00011515032,0.00038833186,0.0005112701,0.00042337217,0.00014232326],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0044970573,0.00032309344,0.0005090911,0.0015590932,0.0010403272,0.00020426461,0.0013485329,0.00017736066,0.00022458174],"category_scores_gemma":[0.005678954,0.00026421368,0.000044293003,0.0049099387,0.0033191657,0.00041717998,0.0011609858,0.00075814454,0.0002855479],"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":[0.000017757584,0.000022200857,0.024034657,0.000062299936,0.0000036156666,0.000026987793,0.00033209444,0.004478083,0.96027166,0.007978255,0.0000109918865,0.0027614236],"study_design_scores_gemma":[0.00040977128,0.00058544654,0.0024615512,0.0000971747,0.000017136363,0.000095499374,0.0003739255,0.33812842,0.6520934,0.002240989,0.0030589562,0.00043773756],"about_ca_topic_score_codex":0.00045587544,"about_ca_topic_score_gemma":0.000010789926,"teacher_disagreement_score":0.33365035,"about_ca_system_score_codex":0.00005323254,"about_ca_system_score_gemma":0.00021771125,"threshold_uncertainty_score":0.999981},"labels":[],"label_agreement":null},{"id":"W4377287490","doi":"10.1088/2632-2153/acd7c3","title":"scGMM-VGAE: a Gaussian mixture model-based variational graph autoencoder algorithm for clustering single-cell RNA-seq data","year":2023,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","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":"Western University; University of Manitoba; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Manitoba Medical Service Foundation","keywords":"Autoencoder; Cluster analysis; Mixture model; Adjacency matrix; Computer science; Algorithm; Pattern recognition (psychology); Artificial intelligence; Gaussian; Graph; Data mining; Deep learning; Theoretical computer science","score_opus":0.020107652138903122,"score_gpt":0.2557871228017925,"score_spread":0.23567947066288938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377287490","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07519078,0.00031490327,0.9207473,0.0025832434,0.00023414473,0.0002789927,0.000114165035,0.00025344416,0.00028303618],"genre_scores_gemma":[0.90235126,0.00005107929,0.09592842,0.00033987217,0.00009712519,0.000035568715,0.0005987798,0.000036938665,0.000560945],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99835306,0.000021882839,0.00019127093,0.0007602077,0.00022139245,0.0004521739],"domain_scores_gemma":[0.999188,0.000024799627,0.00008606215,0.0004730821,0.00015014772,0.00007791387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065318873,0.00018305538,0.00016425186,0.00039991713,0.000543119,0.0000843331,0.00072442315,0.00024309997,0.0000037086843],"category_scores_gemma":[0.0002684459,0.0001722251,0.000036114812,0.0009167457,0.00047891852,0.000020206806,0.00034858068,0.00026127815,0.0000029844198],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033465432,0.000101309844,0.0019855422,0.000044096854,0.000018520412,0.0000053611284,0.00005309064,0.02260413,0.8992289,0.00025942636,0.00033130345,0.07533488],"study_design_scores_gemma":[0.00070087356,0.00028692142,0.000062409046,0.000012775207,0.000016597354,0.000010930525,0.000029263841,0.96755594,0.025557067,0.0007058941,0.004844898,0.00021642787],"about_ca_topic_score_codex":0.000028319995,"about_ca_topic_score_gemma":0.000041062878,"teacher_disagreement_score":0.94495183,"about_ca_system_score_codex":0.000017897626,"about_ca_system_score_gemma":0.00023165513,"threshold_uncertainty_score":0.7023136},"labels":[],"label_agreement":null},{"id":"W4379184278","doi":"10.1088/2632-2153/acdb2e","title":"3D positioning and autofocus of the particle field based on the depth-from-defocus method and the deep networks","year":2023,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Image Processing Techniques and Applications","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 Alberta","funders":"Natural Science Foundation of Hebei Province; National Natural Science Foundation of China","keywords":"Autofocus; Artificial intelligence; Particle (ecology); Computer science; Computer vision; Position (finance); Particle filter; Artificial neural network; Process (computing); Geology; Optics; Physics; Focus (optics)","score_opus":0.005243854771384907,"score_gpt":0.2423531526777402,"score_spread":0.2371092979063553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379184278","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5613542,0.0015113342,0.3809746,0.053564597,0.00005832177,0.0003632749,0.0000016716174,0.0009938321,0.0011781653],"genre_scores_gemma":[0.9964395,0.00004966266,0.003266941,0.0001810932,0.000007085065,0.00003415153,2.8612791e-7,0.0000060359553,0.000015249182],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995181,0.0000316849,0.00008221856,0.0001324867,0.000089236404,0.00014630066],"domain_scores_gemma":[0.99939907,0.00034861566,0.00003148014,0.00018064176,0.000026680245,0.000013519736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067976123,0.00006191356,0.00007572028,0.000048410435,0.00056793797,0.000057890196,0.0002103898,0.00004799098,0.000002772594],"category_scores_gemma":[0.0002828522,0.000031707714,0.000009712908,0.0008805692,0.00059398316,0.000035393015,0.00012531095,0.00031101095,4.975047e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017984685,0.000015202468,0.023691548,0.000025567933,0.000018125904,0.0000021360834,0.0007636783,0.062689856,0.02235058,0.062221903,0.00013383623,0.82806957],"study_design_scores_gemma":[0.000112969086,0.00002350955,0.002037739,0.000018935707,0.000009420088,0.0000045905117,0.0000610154,0.9800601,0.010767274,0.006613167,0.00024934378,0.000041960444],"about_ca_topic_score_codex":0.000045708388,"about_ca_topic_score_gemma":0.000012181574,"teacher_disagreement_score":0.9173702,"about_ca_system_score_codex":0.0000057739135,"about_ca_system_score_gemma":0.00000841568,"threshold_uncertainty_score":0.4368177},"labels":[],"label_agreement":null},{"id":"W4387899421","doi":"10.1088/2632-2153/ad0652","title":"Neural network Gaussian processes as efficient models of potential energy surfaces for polyatomic molecules","year":2023,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Machine Learning in Materials Science","field":"Materials Science","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":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Gaussian process; Kernel (algebra); Polyatomic ion; Computer science; Gaussian; Function (biology); Gaussian function; Artificial neural network; Kriging; Generalization; Mathematical optimization; Algorithm; Artificial intelligence; Mathematics; Machine learning; Statistical physics; Computational chemistry; Physics; Chemistry; Molecule; Quantum mechanics","score_opus":0.00728694705171877,"score_gpt":0.24717948434925088,"score_spread":0.23989253729753213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387899421","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9893541,0.0004327782,0.0068411455,0.0018121275,0.0004055792,0.00021544484,0.000012876746,0.0006805768,0.00024540207],"genre_scores_gemma":[0.99534285,0.000045474782,0.0041823583,0.0000721628,0.000050243485,0.000049072358,0.00000725489,0.000026313553,0.00022428925],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99707353,0.00009227776,0.00040654806,0.00084592716,0.0006512315,0.0009304842],"domain_scores_gemma":[0.99868685,0.00015737907,0.00032893592,0.00034044418,0.0003752697,0.000111146604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021823053,0.00024795896,0.00038304905,0.00069616653,0.0009912289,0.00019871247,0.0010938732,0.00013567526,0.000042481868],"category_scores_gemma":[0.0014605618,0.0002081145,0.00003579791,0.0033528516,0.0020220368,0.000264961,0.00063367805,0.00020269901,0.000021761805],"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":[0.000029873476,0.000018069304,0.0011499644,0.000058912196,0.0000023226355,0.000006275689,0.000107170905,0.542061,0.44139618,0.013857679,0.000025608997,0.0012870074],"study_design_scores_gemma":[0.00028018997,0.00034295005,0.00038292867,0.000040912233,0.000012989796,0.000055183362,0.00014482364,0.9051879,0.08070195,0.012255686,0.00035126973,0.00024323467],"about_ca_topic_score_codex":0.00034519975,"about_ca_topic_score_gemma":0.00002560868,"teacher_disagreement_score":0.36312693,"about_ca_system_score_codex":0.000030757685,"about_ca_system_score_gemma":0.00032598627,"threshold_uncertainty_score":0.84866637},"labels":[],"label_agreement":null},{"id":"W4388721986","doi":"10.1088/2632-2153/ad0d12","title":"Exploring machine learning to hardware implementations for large data rate x-ray instrumentation","year":2023,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Medical Imaging Techniques and Applications","field":"Medicine","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":"Institut interdisciplinaire d'innovation technologique; Université de Sherbrooke","funders":"Canada Research Chairs","keywords":"Computer science; Instrumentation (computer programming); Detector; Computer hardware; Computer engineering; Pixel; Digital electronics; Software; Field-programmable gate array; Enhanced Data Rates for GSM Evolution; Computation; Sampling (signal processing); Electronic circuit; Focus (optics); Artificial intelligence; Algorithm; Electrical engineering; Engineering","score_opus":0.11590363720541567,"score_gpt":0.39834418124556076,"score_spread":0.28244054404014507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388721986","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88806033,0.000052813157,0.030338677,0.07833913,0.00009534646,0.0010757052,0.00009623557,0.001802802,0.00013896872],"genre_scores_gemma":[0.9732897,0.00018816414,0.024379224,0.00049358077,0.000041578147,0.000428578,0.00065131765,0.000022171893,0.0005056448],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984899,0.000022672051,0.00022959308,0.00055838283,0.00025245134,0.00044700023],"domain_scores_gemma":[0.99914527,0.00009313156,0.00007510953,0.0003807536,0.00016109672,0.00014461088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016899751,0.00012033905,0.00018292732,0.00081747957,0.00091895525,0.000061891245,0.00037936567,0.000043779237,0.000038398055],"category_scores_gemma":[0.0023267586,0.00010803584,0.000017006478,0.002556232,0.00017597392,0.000293419,0.00060488284,0.0004027877,0.00003392559],"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":[0.000059010865,0.00015696972,0.16493797,0.00019939197,0.000056019857,0.000024836334,0.0013872961,0.00014167684,0.38543576,0.025338179,0.006097575,0.41616532],"study_design_scores_gemma":[0.0016706209,0.0007282875,0.0116390195,0.00012232411,0.00008347015,0.000039523828,0.0024326881,0.3976121,0.011824957,0.0010118792,0.5725104,0.00032468667],"about_ca_topic_score_codex":0.00008148104,"about_ca_topic_score_gemma":0.000023530678,"teacher_disagreement_score":0.56641287,"about_ca_system_score_codex":0.00004529158,"about_ca_system_score_gemma":0.00009558655,"threshold_uncertainty_score":0.7067954},"labels":[],"label_agreement":null},{"id":"W4388876471","doi":"10.1088/2632-2153/ad611e","title":"Simultaneous energy and mass calibration of large-radius jets with the ATLAS detector using a deep neural network","year":2024,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Particle physics theoretical and experimental studies","field":"Physics and Astronomy","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":"CHIST-ERA; H2020 Marie Skłodowska-Curie Actions; Institut National de Physique Nucléaire et de Physique des Particules; Agencia Nacional de Promoción Científica y Tecnológica; Fundação para a Ciência e a Tecnologia; Ministry of Education, Culture, Sports, Science and Technology; Bundesministerium für Bildung und Forschung; Natural Sciences and Engineering Research Council of Canada; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Science and Technology Facilities Council; Vetenskapsrådet; Horizon 2020 Framework Programme; Narodowa Agencja Wymiany Akademickiej; Banco Bilbao Vizcaya Argentaria; European Regional Development Fund; British Columbia Knowledge Development Fund; Max-Planck-Gesellschaft; Centre National de la Recherche Scientifique; Knut och Alice Wallenbergs Stiftelse; Israel Science Foundation; Japan Society for the Promotion of Science; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Bundesministerium für Wissenschaft, Forschung und Wirtschaft; Generalitat de Catalunya; Generalitat Valenciana; Agencia Nacional de Investigación y Desarrollo; Istituto Nazionale di Fisica Nucleare; Austrian Science Fund; Ministerstvo Školství, Mládeže a Tělovýchovy; U.S. Department of Energy; National Natural Science Foundation of China; European Commission; Leverhulme Trust; Fundação de Amparo à Pesquisa do Estado de São Paulo; Javna Agencija za Raziskovalno Dejavnost RS; Deutsche Forschungsgemeinschaft; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Agence Nationale de la Recherche; European Social Fund; Centre National pour la Recherche Scientifique et Technique; Royal Society; National Science Foundation; Norges Forskningsråd; Fundación BBVA; Compute Canada; Baden-Württemberg Stiftung; Alexander von Humboldt-Stiftung; TRIUMF; Danmarks Grundforskningsfond; Türkiye Enerji, Nükleer ve Maden Araştırma Kurumu; Canarie; CERN; Centres de Recerca de Catalunya; Ministerio de Ciencia e Innovación","keywords":"Calibration; Artificial neural network; Atlas (anatomy); Detector; Artificial intelligence; Algorithm; Computer science; Energy (signal processing); RADIUS; Physics; Optics; Geology","score_opus":0.004544262645643714,"score_gpt":0.23593397519633205,"score_spread":0.23138971255068833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388876471","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9822782,0.0012614684,0.01561193,0.00064485,0.00002310865,0.000037523027,0.0000013855255,0.00004030534,0.0001011742],"genre_scores_gemma":[0.9996983,0.000003994449,0.00022920268,0.000012266721,0.000035468598,0.0000050899876,6.4892635e-7,0.0000052508326,0.000009782202],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994454,0.000017281598,0.00006573647,0.0001736071,0.000093102404,0.00020489591],"domain_scores_gemma":[0.9997886,0.00007516613,0.000026355925,0.000060352475,0.000024387555,0.000025146204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010239264,0.00007580218,0.00009376802,0.000038982053,0.0003608073,0.000051317827,0.00008047571,0.000015771779,0.0000059924605],"category_scores_gemma":[0.0000104720475,0.0000445624,0.000009784826,0.00051815825,0.0008077542,0.000073814095,0.000105939245,0.000111590416,2.5138218e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000366664,0.00004227841,0.079045884,0.000017508424,0.00007596447,0.000013226506,0.00081406,0.01696673,0.28950953,0.52960855,0.0000070401074,0.08386256],"study_design_scores_gemma":[0.00008803871,0.00012385221,0.000025386273,0.000010499816,0.000014182793,0.000005080401,0.00028928043,0.9495409,0.037810024,0.011746793,0.00028413517,0.000061821185],"about_ca_topic_score_codex":0.00007287044,"about_ca_topic_score_gemma":0.0000056459517,"teacher_disagreement_score":0.93257415,"about_ca_system_score_codex":0.000006641795,"about_ca_system_score_gemma":0.000012221526,"threshold_uncertainty_score":0.2976204},"labels":[],"label_agreement":null},{"id":"W4388978577","doi":"10.1088/2632-2153/ad0fa3","title":"Improved decision making with similarity based machine learning: applications in chemistry","year":2023,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Machine Learning in Materials Science","field":"Materials Science","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":"H2020 European Research Council; Canada First Research Excellence Fund; National Science Foundation","keywords":"Curse of dimensionality; Computer science; Scarcity; Similarity (geometry); Chemical space; Machine learning; Artificial intelligence; Space (punctuation); Feature (linguistics); Data mining; Chemistry; Drug discovery","score_opus":0.00697190578342071,"score_gpt":0.2662006005477507,"score_spread":0.25922869476432997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388978577","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9872043,0.00010751151,0.008912223,0.0014632399,0.00008377589,0.00038453777,0.00000822775,0.0013706604,0.00046549639],"genre_scores_gemma":[0.9868647,0.00001820642,0.012659795,0.000078449826,0.000025014839,0.000119972894,0.000014992366,0.000033920423,0.0001849363],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99650246,0.00011501636,0.000421929,0.0012529417,0.00075344846,0.0009542157],"domain_scores_gemma":[0.9984004,0.0003757,0.00028617127,0.00057450647,0.00023428132,0.00012894686],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0038345288,0.00033123206,0.00039809587,0.0009998694,0.0012889083,0.00033148934,0.0012389789,0.0002066253,0.00025266866],"category_scores_gemma":[0.0028309873,0.00026822864,0.000026309808,0.0059218626,0.0017798947,0.00034391583,0.00070968666,0.001059035,0.00007022877],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005014517,0.000051258932,0.22172558,0.000062257815,0.0000016158807,0.000025748799,0.00011967951,0.021347422,0.74794227,0.00035887968,0.0000058772116,0.008309275],"study_design_scores_gemma":[0.00082780357,0.0002990581,0.015222151,0.00013037235,0.000012180533,0.000058966703,0.00024040183,0.91944623,0.057589855,0.00131307,0.004302355,0.00055754825],"about_ca_topic_score_codex":0.00018612968,"about_ca_topic_score_gemma":0.0001161868,"teacher_disagreement_score":0.8980988,"about_ca_system_score_codex":0.00012790816,"about_ca_system_score_gemma":0.00027981296,"threshold_uncertainty_score":0.999977},"labels":[],"label_agreement":null},{"id":"W4389455450","doi":"10.1088/2632-2153/ad134a","title":"A finite element-convolutional neural network model (FE-CNN) for stress field analysis around arbitrary inclusions","year":2023,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Non-Destructive Testing Techniques","field":"Engineering","cited_by":24,"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","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Convolutional neural network; Computer science; Representation (politics); Field (mathematics); Stress (linguistics); Finite element method; Stress field; Artificial intelligence; Artificial neural network; Surrogate model; Sensitivity (control systems); Pattern recognition (psychology); Algorithm; Machine learning; Mathematics; Engineering; Structural engineering","score_opus":0.01321927609920763,"score_gpt":0.2658957953382874,"score_spread":0.25267651923907974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389455450","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84278905,0.00017208679,0.15061593,0.0014046015,0.00009527638,0.00025073616,0.00002451543,0.0035783844,0.0010694332],"genre_scores_gemma":[0.91926616,0.000025745716,0.08046941,0.000064331536,0.000033781802,0.00006994905,0.0000266372,0.00001634308,0.00002764816],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987544,0.000013142636,0.0001889012,0.0003448051,0.0002023144,0.0004964662],"domain_scores_gemma":[0.99931794,0.000277202,0.000049184717,0.00020212871,0.00009886595,0.00005467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054651167,0.00015010667,0.00020190465,0.0010215747,0.00065722654,0.000051096395,0.0003875048,0.000114541486,0.0000059127515],"category_scores_gemma":[0.00064151135,0.00015011634,0.000045031342,0.00407356,0.0003264374,0.00016179019,0.00034988776,0.00045516517,0.0000026926612],"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":[0.0000094263305,0.00001602101,0.22480547,0.000039452236,0.000105061255,0.000009445218,0.00010993034,0.7023523,0.0074903783,0.055372406,0.00029989082,0.009390227],"study_design_scores_gemma":[0.00009712872,0.00007807259,0.0022706252,0.000012366537,0.000041765667,0.000003913759,0.0000312135,0.8797874,0.00042575685,0.11704477,0.00006579434,0.00014120137],"about_ca_topic_score_codex":0.000032282256,"about_ca_topic_score_gemma":0.000047182686,"teacher_disagreement_score":0.22253484,"about_ca_system_score_codex":0.000052780328,"about_ca_system_score_gemma":0.00004822983,"threshold_uncertainty_score":0.6121566},"labels":[],"label_agreement":null},{"id":"W4389540874","doi":"10.1088/2632-2153/ad1437","title":"High-dimensional reinforcement learning for optimization and control of ultracold quantum gases","year":2023,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Neural Networks and Reservoir Computing","field":"Computer Science","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":"University of Alberta","funders":"Alberta Innovates; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canada Foundation for Innovation; University of Alberta","keywords":"Reinforcement learning; Control (management); Quantum; Set (abstract data type); Computer science; Reinforcement; Artificial intelligence; Physics; Engineering; Quantum mechanics","score_opus":0.007683182522326065,"score_gpt":0.23444605087714782,"score_spread":0.22676286835482176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389540874","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3567784,0.0002980028,0.6381069,0.004071169,0.0001451146,0.00021895701,3.98986e-7,0.0003688243,0.000012219941],"genre_scores_gemma":[0.9930769,0.00007624848,0.0066754306,0.000059342383,0.000017921946,0.000011000162,0.0000024997894,0.0000052690393,0.000075363394],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998866,0.0000265196,0.0001929597,0.00035908207,0.00023692891,0.00031851497],"domain_scores_gemma":[0.999284,0.00021297477,0.00014240244,0.00013110509,0.00018148225,0.000047984093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084054604,0.00009653607,0.00017077003,0.0004645223,0.0006288084,0.00007166838,0.00033687687,0.000058346777,0.0000015734166],"category_scores_gemma":[0.0004927173,0.00007865984,0.000016554766,0.0014551925,0.0003482384,0.00020658488,0.00033228457,0.00021881991,8.195582e-7],"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":[0.0000057404036,0.0000064549567,0.0038954772,0.000015887013,0.0000048651227,0.0000031179418,0.000037791157,0.9504719,0.009085203,0.021979362,0.000019734101,0.014474503],"study_design_scores_gemma":[0.0004344219,0.00040974567,0.00041700897,0.000028068032,0.0000039332112,0.000015830587,0.000022116295,0.995556,0.0017639442,0.000989621,0.00027063047,0.00008869565],"about_ca_topic_score_codex":0.000028339175,"about_ca_topic_score_gemma":0.0000010312436,"teacher_disagreement_score":0.6362985,"about_ca_system_score_codex":0.000010786244,"about_ca_system_score_gemma":0.00004622473,"threshold_uncertainty_score":0.48363492},"labels":[],"label_agreement":null},{"id":"W4390042939","doi":"10.1088/2632-2153/ad17d3","title":"Neural network field theories: non-Gaussianity, actions, and locality","year":2023,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","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":"Perimeter Institute","funders":"National Science Foundation","keywords":"Path integral formulation; Field (mathematics); Field theory (psychology); Auxiliary field; Feynman diagram; Artificial neural network; Locality; Limit (mathematics); Action (physics); Mathematics; Statistical physics; Measure (data warehouse); Physics; Computer science; Mathematical analysis; Pure mathematics; Quantum mechanics; Mathematical physics; Artificial intelligence","score_opus":0.008662183483395319,"score_gpt":0.25987356349536744,"score_spread":0.25121138001197213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390042939","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5602395,0.00070579903,0.3376865,0.090386935,0.00078284985,0.00034849835,0.0000020214218,0.0028851298,0.0069627897],"genre_scores_gemma":[0.9968424,0.00012553734,0.0024331412,0.0003749834,0.00003118004,0.000010177098,5.7991133e-7,0.000004528412,0.00017748863],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985989,0.000026447275,0.00014427603,0.00052559335,0.00022807594,0.00047673556],"domain_scores_gemma":[0.9993145,0.00011045109,0.00007070708,0.00032399636,0.00009153925,0.00008883019],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008272967,0.00012741216,0.00015348011,0.000351843,0.0010178733,0.00031602927,0.00076883106,0.00010199988,0.000007538117],"category_scores_gemma":[0.00045597204,0.000103674975,0.000012785821,0.003787925,0.00069132564,0.0004852451,0.00094942487,0.00048190833,0.000019675565],"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":[0.000003926869,0.000013985362,0.1097644,0.000033065553,0.0000057923744,0.00003206123,0.00028303752,0.00015867074,0.0006372661,0.52350885,0.0003181207,0.3652408],"study_design_scores_gemma":[0.00031273093,0.0005784323,0.041037258,0.00005028868,0.000008326589,0.00023711124,0.00030746928,0.6610682,0.0011330262,0.28517517,0.00965976,0.00043223606],"about_ca_topic_score_codex":0.000065174936,"about_ca_topic_score_gemma":0.000022757966,"teacher_disagreement_score":0.66090953,"about_ca_system_score_codex":0.000013160159,"about_ca_system_score_gemma":0.00009596706,"threshold_uncertainty_score":0.78287613},"labels":[],"label_agreement":null},{"id":"W4391544311","doi":"10.1088/2632-2153/ad2628","title":"Deep quantum graph dreaming: deciphering neural network insights into quantum experiments","year":2024,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Quantum Mechanics and Applications","field":"Physics and Astronomy","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 Ottawa","funders":"","keywords":"Quantum; Cognitive science; Artificial neural network; Computer science; Artificial intelligence; Psychology; Physics; Quantum mechanics","score_opus":0.008457290324882002,"score_gpt":0.26541474966460904,"score_spread":0.256957459339727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391544311","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93754923,0.0027481911,0.05755737,0.00089393114,0.00032159273,0.00014582345,4.543848e-7,0.0003556167,0.00042776737],"genre_scores_gemma":[0.9991963,0.00003035203,0.0005178131,0.000030891762,0.0001017431,0.00006137463,0.000006131853,0.000020467602,0.000034919325],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985937,0.00001861717,0.0001997172,0.00054713676,0.00020888729,0.00043194482],"domain_scores_gemma":[0.99950224,0.00004204418,0.000057245397,0.0002438702,0.00006546898,0.000089138026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027623484,0.0001774764,0.00017091162,0.00032835858,0.0009012214,0.00021694186,0.00038021442,0.00006148846,0.000039309172],"category_scores_gemma":[0.000021698985,0.00015350548,0.000037729576,0.0019459091,0.00037600653,0.00020548145,0.00028231466,0.00047797666,0.000027818289],"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":[0.0000015081175,0.000024572792,0.0052234386,0.000006631262,0.000014341548,0.0000042507177,0.0003286125,0.00031129317,0.015898902,0.9297741,0.000025451842,0.048386917],"study_design_scores_gemma":[0.000081394595,0.00007529471,0.0001251689,0.000025634135,0.000009154474,0.0000044427347,0.00040745485,0.6721751,0.0012761692,0.31679964,0.008862402,0.00015814649],"about_ca_topic_score_codex":0.00020260872,"about_ca_topic_score_gemma":0.000009470896,"teacher_disagreement_score":0.6718638,"about_ca_system_score_codex":0.000023887496,"about_ca_system_score_gemma":0.00006033122,"threshold_uncertainty_score":0.69315577},"labels":[],"label_agreement":null},{"id":"W4391694516","doi":"10.1088/2632-2153/ad27e1","title":"Bridging the gap between high-level quantum chemical methods and deep learning models","year":2024,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":9,"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 British Columbia, Okanagan Campus; University of British Columbia","funders":"Alliance de recherche numérique du Canada; British Columbia Knowledge Development Fund; Natural Sciences and Engineering Research Council of Canada; Ministerio de Ciencia e Innovación; Fundación para el Fomento en Asturias de la Investigación Científica Aplicada y la Tecnología; Canada Foundation for Innovation","keywords":"Bridging (networking); Quantum chemical; Computer science; Physics; Quantum mechanics; Molecule","score_opus":0.03319645398121585,"score_gpt":0.32516115996076894,"score_spread":0.2919647059795531,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391694516","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88464177,0.002241213,0.10416323,0.006880981,0.0004456355,0.000199395,0.0000058845985,0.0011314359,0.00029046767],"genre_scores_gemma":[0.964177,0.0001078767,0.03521166,0.00009366147,0.00014338996,0.000027858101,0.0000035558132,0.000036526035,0.00019844495],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99626315,0.00041664415,0.00043116094,0.0012740784,0.00069281616,0.0009221585],"domain_scores_gemma":[0.9984673,0.00062999927,0.00016083669,0.00042464095,0.00015855895,0.00015862373],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":["sts"],"category_scores_codex":[0.008585639,0.00033757553,0.00043178644,0.00065289007,0.0016332078,0.0011013156,0.0011795211,0.0002020919,0.00009726212],"category_scores_gemma":[0.0029151181,0.00023552612,0.000034650224,0.002075582,0.0036231894,0.0007283378,0.0013529988,0.0014436172,0.00006062786],"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":[0.0000052447745,0.000006973088,0.0028717201,0.000055446417,0.000006380667,0.000014559568,0.00060943177,0.0018519132,0.82326853,0.041651882,0.000011467271,0.12964645],"study_design_scores_gemma":[0.00017280492,0.00016882882,0.0011370335,0.00009499824,0.00004094303,0.00026035958,0.00023131698,0.8851961,0.07920423,0.030238446,0.0028281028,0.00042683468],"about_ca_topic_score_codex":0.0003476419,"about_ca_topic_score_gemma":0.0000057244,"teacher_disagreement_score":0.8833442,"about_ca_system_score_codex":0.00007934163,"about_ca_system_score_gemma":0.00014235794,"threshold_uncertainty_score":0.9999356},"labels":[],"label_agreement":null},{"id":"W4391771030","doi":"10.1088/2632-2153/ad290c","title":"Prediction of 4D stress field evolution around additive manufacturing-induced porosity through progressive deep-learning frameworks","year":2024,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Additive Manufacturing and 3D Printing Technologies","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":"University of Alberta","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Porosity; Field (mathematics); Deep learning; Stress (linguistics); Materials science; Stress field; Artificial intelligence; Computer science; Engineering; Composite material; Structural engineering; Mathematics; Finite element method","score_opus":0.00816484800610854,"score_gpt":0.23344042508429977,"score_spread":0.22527557707819124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391771030","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95259875,0.001340888,0.041243978,0.00037878926,0.0003135869,0.00016439614,0.000014000239,0.0033529229,0.00059271423],"genre_scores_gemma":[0.9982247,0.00012706885,0.0015004795,0.000007791001,0.000051413914,0.000030566483,0.000011294372,0.00002340009,0.000023294511],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99858147,0.000027548429,0.00022862291,0.00047730457,0.0002681339,0.00041690716],"domain_scores_gemma":[0.9993844,0.00017574028,0.00008029321,0.00022167133,0.000102288286,0.000035578203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032186168,0.00021991602,0.00022998152,0.0005706043,0.00048789594,0.00013103848,0.00033366666,0.00048469272,0.00002460475],"category_scores_gemma":[0.0008143211,0.00020150666,0.000036721667,0.000804752,0.0007593368,0.00035605376,0.00027562477,0.0022910207,0.0000057976504],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020344027,0.000057615922,0.018945929,0.00045599515,0.00016051733,0.000093456685,0.0014314657,0.012331813,0.020415263,0.031313132,0.00006787318,0.9147066],"study_design_scores_gemma":[0.00016877234,0.00057036075,0.0066575343,0.00051288307,0.00003969311,0.000076862496,0.0015536224,0.20892838,0.76146394,0.018412462,0.0012887361,0.00032676628],"about_ca_topic_score_codex":0.000054809032,"about_ca_topic_score_gemma":0.0000072409393,"teacher_disagreement_score":0.91437984,"about_ca_system_score_codex":0.00012096576,"about_ca_system_score_gemma":0.000039432274,"threshold_uncertainty_score":0.99534726},"labels":[],"label_agreement":null},{"id":"W4391782195","doi":"10.1088/2632-2153/ad2493","title":"Qualitative and quantitative enhancement of parameter estimation for model-based diagnostics using automatic differentiation with an application to inertial fusion","year":2024,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Laser-Plasma Interactions and Diagnostics","field":"Physics and Astronomy","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":"Air Force Office of Scientific Research; National Nuclear Security Administration; University of Rochester; U.S. Department of Energy","keywords":"Hessian matrix; Computer science; Algorithm; Artificial intelligence; Leverage (statistics); Estimation theory; Differentiable function; Machine learning; Applied mathematics; Mathematics; Mathematical analysis","score_opus":0.017254959383966702,"score_gpt":0.350563045502461,"score_spread":0.3333080861184943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391782195","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.503131,0.000005615937,0.49651188,0.00015310447,0.000012524794,0.00015370769,0.000007953234,0.00001957339,0.000004662905],"genre_scores_gemma":[0.8860526,0.000001107901,0.11381777,0.000008313411,0.0000049065015,0.000077989,0.000026003569,0.0000058949895,0.0000054140587],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994093,0.000017893062,0.0001356908,0.00022368495,0.000107225016,0.000106203224],"domain_scores_gemma":[0.9993181,0.00033707975,0.000074213756,0.000075465905,0.00016405048,0.000031061507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002111658,0.00007924984,0.000102382364,0.00028838505,0.00018191586,0.000060725335,0.000051863153,0.000024352446,0.0000057884517],"category_scores_gemma":[0.00020941296,0.00006213667,0.000008209823,0.00041081107,0.00016760778,0.00017605725,0.000027638804,0.00008274709,0.0000010841537],"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":[0.000112332695,0.0004394883,0.012784284,0.0003001417,0.000057538797,5.791223e-7,0.008269079,0.30749762,0.15254234,0.23849972,0.000010402654,0.27948648],"study_design_scores_gemma":[0.00015873241,0.0006356044,0.0001364212,0.00008404935,0.0000334704,3.9310402e-7,0.0006206879,0.96838397,0.023252359,0.006604567,0.000013453172,0.000076319455],"about_ca_topic_score_codex":0.00011219034,"about_ca_topic_score_gemma":0.000012917424,"teacher_disagreement_score":0.6608863,"about_ca_system_score_codex":0.000022803164,"about_ca_system_score_gemma":0.000064300686,"threshold_uncertainty_score":0.25338596},"labels":[],"label_agreement":null},{"id":"W4392350883","doi":"10.1088/2632-2153/ad2f52","title":"Autonomous data extraction from peer reviewed literature for training machine learning models of oxidation potentials","year":2024,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Machine Learning in Materials Science","field":"Materials Science","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":"Vector Institute; University of Toronto","funders":"Canada First Research Excellence Fund; University of Toronto; European Commission","keywords":"Computer science; Training (meteorology); Data extraction; Peer review; Extraction (chemistry); Artificial intelligence; Machine learning; MEDLINE; Chemistry; Geography","score_opus":0.0426779243544447,"score_gpt":0.3172604992317604,"score_spread":0.27458257487731574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392350883","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85510045,0.01243811,0.121470384,0.00637985,0.0016196911,0.00080180087,0.0003075099,0.0014880833,0.00039413507],"genre_scores_gemma":[0.9553175,0.00036562543,0.043151245,0.000052836273,0.00013684279,0.00004077863,0.00032349757,0.00004094475,0.0005707338],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960741,0.00022805866,0.00068820984,0.0015134875,0.000864752,0.0006314209],"domain_scores_gemma":[0.9977355,0.00040497453,0.0004209979,0.0007649845,0.00056749384,0.000106070984],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0077767647,0.00032666596,0.00055374805,0.0009035841,0.00083521823,0.00082768826,0.0015284732,0.00024697886,0.00020153845],"category_scores_gemma":[0.0059775673,0.0002767906,0.000051827166,0.0019249849,0.0009479991,0.0020420682,0.0007663773,0.0008311371,0.000028385235],"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":[0.000024583473,0.000021539227,0.00040201025,0.00017068029,0.000009585012,0.000010289699,0.0009819003,0.0052373917,0.9372402,0.005173741,0.00005322439,0.050674897],"study_design_scores_gemma":[0.00028856855,0.00025902293,0.00014654943,0.0004495491,0.00006658786,0.00009987946,0.00020027877,0.91766214,0.04911268,0.00927129,0.022086157,0.00035730877],"about_ca_topic_score_codex":0.00033829932,"about_ca_topic_score_gemma":0.000029315897,"teacher_disagreement_score":0.91242474,"about_ca_system_score_codex":0.000075155214,"about_ca_system_score_gemma":0.0002995766,"threshold_uncertainty_score":0.9999684},"labels":[],"label_agreement":null},{"id":"W4392975775","doi":"10.1088/2632-2153/ad360e","title":"Efficient interpolation of molecular properties across chemical compound space with low-dimensional descriptors","year":2024,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Analytical Chemistry and Chromatography","field":"Chemistry","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":"","keywords":"Interpolation (computer graphics); Space (punctuation); Chemical space; Mathematics; Materials science; Biological system; Chemistry; Computer science; Artificial intelligence; Biology; Biochemistry","score_opus":0.004303825758755411,"score_gpt":0.22075103059918283,"score_spread":0.21644720484042743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392975775","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99773324,0.0006545877,0.00024575365,0.00047281885,0.000013481616,0.000022762575,0.0000021059884,0.0001720771,0.00068317924],"genre_scores_gemma":[0.99953145,0.0000019338345,0.00035806117,0.000009630326,0.00000728442,0.0000036733466,0.0000027556102,0.000008351397,0.00007683971],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990296,0.000003882026,0.00012902965,0.0003278547,0.00027679873,0.00023286814],"domain_scores_gemma":[0.9996618,0.00001990456,0.00003883336,0.00012953678,0.00010057555,0.000049335133],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015976543,0.00011341418,0.00013621774,0.00010965553,0.00013854935,0.000050855615,0.00017761454,0.00009583256,0.00003552216],"category_scores_gemma":[0.00011310584,0.00008099737,0.00002525214,0.000825164,0.0019618464,0.000038482514,0.00014836818,0.0003704021,0.000002337686],"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":[0.000016697593,0.000030203271,0.0047946326,0.00015496917,0.00001607342,0.000020008876,0.00012440768,0.00026971367,0.99262697,0.0013475518,0.0000029424157,0.00059582473],"study_design_scores_gemma":[0.00011054551,0.000037781145,0.000019653713,0.00022681305,0.000013188161,0.00009357144,0.0002977982,0.15659969,0.84218794,0.00013926828,0.00016781811,0.00010592512],"about_ca_topic_score_codex":0.000015340782,"about_ca_topic_score_gemma":7.1915593e-7,"teacher_disagreement_score":0.15632997,"about_ca_system_score_codex":0.00002538953,"about_ca_system_score_gemma":0.00006270814,"threshold_uncertainty_score":0.7228505},"labels":[],"label_agreement":null},{"id":"W4393852203","doi":"10.1088/2632-2153/ad3a32","title":"GRINN: a physics-informed neural network for solving hydrodynamic systems in the presence of self-gravity","year":2024,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Computational Physics and Python Applications","field":"Computer Science","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":"Western University","funders":"","keywords":"Artificial neural network; Physics; Theoretical physics; Classical mechanics; Statistical physics; Computer science; Artificial intelligence","score_opus":0.00790493171980084,"score_gpt":0.2633431877719144,"score_spread":0.25543825605211357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393852203","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5969271,0.001418288,0.39133805,0.00812898,0.00039565918,0.00086559786,0.0000052558194,0.0005513254,0.0003697128],"genre_scores_gemma":[0.9952234,0.000011070382,0.0046133744,0.000030421073,0.000035604477,0.00006844686,0.000001814644,0.0000033143747,0.00001253381],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990938,0.000018667186,0.00015295164,0.00029047436,0.00021596912,0.00022819552],"domain_scores_gemma":[0.99917436,0.0004169981,0.00006225426,0.00023427834,0.00009436677,0.00001777466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008023322,0.000075476215,0.00010540452,0.00016605349,0.0002847173,0.00020142095,0.0008183147,0.000030430809,1.2404288e-7],"category_scores_gemma":[0.000096331256,0.000055325243,0.000020945256,0.0026149477,0.00022446703,0.00026925202,0.00022113828,0.00023882026,0.0000012406512],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.866101e-7,0.00001740436,0.002378328,0.00004984329,0.0000037512846,0.0000010611307,0.0005440481,0.043286417,0.0005919531,0.9084312,0.00003447575,0.044660967],"study_design_scores_gemma":[0.00005214922,0.00005755765,0.0013030285,0.00002506416,0.0000025427662,0.000015278236,0.000032463555,0.93322545,0.00002215878,0.06380084,0.0014057613,0.000057690188],"about_ca_topic_score_codex":0.00007633423,"about_ca_topic_score_gemma":0.00001742168,"teacher_disagreement_score":0.88993907,"about_ca_system_score_codex":0.000025034811,"about_ca_system_score_gemma":0.00015050719,"threshold_uncertainty_score":0.2256098},"labels":[],"label_agreement":null},{"id":"W4394867215","doi":"10.1088/2632-2153/ad7226","title":"Leveraging normalizing flows for orbital-free density functional theory","year":2024,"lang":"en","type":"preprint","venue":"Machine Learning Science and Technology","topic":"Machine Learning in Materials Science","field":"Materials Science","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":"Hamilton Health Sciences","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Density functional theory; Computer science; Lagrange multiplier; Mathematical optimization; Initialization; Flexibility (engineering); Maximization; Statistical physics; Inference; Applied mathematics; Physics; Artificial intelligence; Mathematics; Quantum mechanics","score_opus":0.013425810982679386,"score_gpt":0.2560554195600629,"score_spread":0.2426296085773835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394867215","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96919644,0.0015431993,0.017709756,0.004578494,0.0037323108,0.00063001964,0.000046948702,0.0016910181,0.00087182765],"genre_scores_gemma":[0.97045994,0.000026615442,0.027972588,0.00017962593,0.0003021353,0.00017564317,0.000023932345,0.000068197456,0.00079129735],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99483913,0.00020371401,0.0006337629,0.0021617902,0.0010345873,0.0011269917],"domain_scores_gemma":[0.9972707,0.00039808993,0.00041527112,0.0011367142,0.0006067711,0.00017245261],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.009572063,0.00057567674,0.000677922,0.0014510953,0.001794633,0.0011778348,0.0023365312,0.0004849371,0.00026236952],"category_scores_gemma":[0.007814671,0.0005077329,0.00010486538,0.0012731614,0.002326679,0.00028562552,0.009433233,0.0021119385,0.00015663276],"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":[0.00010302523,0.000053428805,0.0048062033,0.00081165,0.0000282775,0.000068989844,0.00085719035,0.014203015,0.89947194,0.06868765,0.0005933564,0.010315294],"study_design_scores_gemma":[0.00070586015,0.0003533974,0.0012732109,0.00053866795,0.00015906732,0.00058449694,0.00040337146,0.3560816,0.0771485,0.55563414,0.0056532677,0.0014644453],"about_ca_topic_score_codex":0.0002489091,"about_ca_topic_score_gemma":0.000037234524,"teacher_disagreement_score":0.82232344,"about_ca_system_score_codex":0.00024614925,"about_ca_system_score_gemma":0.00077323534,"threshold_uncertainty_score":0.99985904},"labels":[],"label_agreement":null},{"id":"W4394947070","doi":"10.1088/2632-2153/ad652c","title":"Molecular relaxation by reverse diffusion with time step prediction","year":2024,"lang":"en","type":"preprint","venue":"Machine Learning Science and Technology","topic":"Photochemistry and Electron Transfer Studies","field":"Chemistry","cited_by":6,"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":"Berlin Center for Machine Learning; Institute for Information and Communications Technology Promotion; Korea University; Banting and Best Diabetes Centre, University of Toronto; Ministry of Science and ICT, South Korea; Bundesministerium für Bildung und Forschung","keywords":"Diffusion; Statistical physics; Relaxation (psychology); Computer science; Algorithm; Econometrics; Mathematics; Psychology; Physics; Thermodynamics; Social psychology","score_opus":0.0026254636338099145,"score_gpt":0.2045204557730672,"score_spread":0.2018949921392573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394947070","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9897458,0.0020344988,0.0002408122,0.0021550867,0.000040564908,0.00011203424,0.000037397313,0.00066222175,0.0049715685],"genre_scores_gemma":[0.9974277,0.00028730492,0.00014455874,0.000022352986,0.000020568354,0.00006998362,0.00010472096,0.00002181072,0.0019009822],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983778,0.0000094238285,0.00016672345,0.0007756716,0.00035209564,0.00031828045],"domain_scores_gemma":[0.99943674,0.000014159614,0.00008707752,0.00029844514,0.00011338688,0.00005016795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002466633,0.00024581372,0.00022914712,0.00020071138,0.00034804957,0.00008011072,0.00031412827,0.00036218425,0.000054422755],"category_scores_gemma":[0.0001404427,0.0002059689,0.00002582903,0.0005418272,0.000709342,0.00004501825,0.00059942773,0.0018594956,0.000011986926],"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":[0.00002180497,0.000026874228,0.002205955,0.00027316864,0.000040509578,0.0000205582,0.00009202327,0.00006041579,0.9900455,0.00013447633,0.00025644148,0.0068222857],"study_design_scores_gemma":[0.00056646776,0.00028158465,0.000055120076,0.00075313705,0.00021198667,0.00014170403,0.00018821281,0.050108187,0.92703444,0.003967951,0.016071253,0.00061996543],"about_ca_topic_score_codex":0.00007653367,"about_ca_topic_score_gemma":0.000004274737,"teacher_disagreement_score":0.06301106,"about_ca_system_score_codex":0.00011231828,"about_ca_system_score_gemma":0.00012905143,"threshold_uncertainty_score":0.8399168},"labels":[],"label_agreement":null},{"id":"W4396517212","doi":"10.1088/2632-2153/ad45b0","title":"Closed-loop Koopman operator approximation","year":2024,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","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":"McGill University","funders":"Institut de Valorisation des Données; Centre de Recherches Mathématiques; Natural Sciences and Engineering Research Council of Canada; Mitacs; Canadian Institute for Advanced Research","keywords":"Loop (graph theory); Operator (biology); Mathematics; Control theory (sociology); Applied mathematics; Computer science; Combinatorics; Artificial intelligence; Control (management)","score_opus":0.006926701183660988,"score_gpt":0.25296885051432516,"score_spread":0.24604214933066418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396517212","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98267466,0.00042726248,0.0057009608,0.004283848,0.0002518835,0.000101616584,0.0000014097474,0.00037167218,0.0061867107],"genre_scores_gemma":[0.99799615,0.000011471308,0.0002892926,0.000033778408,0.00008611401,0.00001265943,0.000004098276,0.000006973072,0.0015594534],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992946,0.000011138229,0.00008939582,0.00028991056,0.0001225753,0.00019242655],"domain_scores_gemma":[0.99978364,0.000011293011,0.000019086292,0.000097274904,0.000047701487,0.000041025607],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023123008,0.00007954752,0.000078352525,0.00027521732,0.0003251001,0.00014539223,0.0001354217,0.000036748155,0.00014369967],"category_scores_gemma":[0.000016372183,0.00006365113,0.0000144051755,0.001008121,0.0003144518,0.00018717353,0.00008090589,0.0003640683,0.000040824907],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017992853,0.000017105836,0.011662891,0.000009950087,0.000008286528,0.000002439379,0.000105965824,0.00025333875,0.019882023,0.29958946,0.0002537228,0.668213],"study_design_scores_gemma":[0.0002024313,0.00012905315,0.00038710487,0.000043295575,0.000014187382,0.00002033868,0.00033099545,0.89592016,0.0143716335,0.014802264,0.073517285,0.00026122693],"about_ca_topic_score_codex":0.000027978687,"about_ca_topic_score_gemma":6.6361844e-7,"teacher_disagreement_score":0.89566684,"about_ca_system_score_codex":0.0000114674385,"about_ca_system_score_gemma":0.000051623138,"threshold_uncertainty_score":0.2595618},"labels":[],"label_agreement":null},{"id":"W4396849416","doi":"10.1088/2632-2153/ad4ae5","title":"Reducing training data needs with minimal multilevel machine learning (M3L)","year":2024,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":18,"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":"H2020 European Research Council; Canada First Research Excellence Fund; Vetenskapsrådet; University of Toronto; European Commission; Canadian Institute for Advanced Research","keywords":"Training (meteorology); Computer science; Machine learning; Artificial intelligence; Training set; Geography","score_opus":0.026599850877349746,"score_gpt":0.2837103781007253,"score_spread":0.2571105272233756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396849416","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9824846,0.0019061527,0.0059989463,0.0042269994,0.00078383903,0.00031938017,0.000039133298,0.0026217753,0.0016192122],"genre_scores_gemma":[0.9720285,0.000068685236,0.026289998,0.00009847913,0.00015173247,0.000028832614,0.000036467387,0.00007567998,0.001221621],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994541,0.00023498459,0.0005824038,0.0020364977,0.0012039396,0.0014012089],"domain_scores_gemma":[0.9977946,0.00036431928,0.00025674328,0.0010852276,0.00024159889,0.00025746232],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":["sts"],"category_scores_codex":[0.006692573,0.0005243569,0.0005794838,0.0019539073,0.0019271235,0.0013792631,0.0027326827,0.00022362238,0.0004667375],"category_scores_gemma":[0.0036917513,0.0004070601,0.000031838146,0.0041263714,0.0033140276,0.0016015554,0.002096079,0.0017652462,0.00020439966],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051002407,0.000040233666,0.012028684,0.00014668184,0.00001683277,0.00018517341,0.0031736358,0.0050499034,0.88547605,0.0047903485,0.00006234392,0.088979125],"study_design_scores_gemma":[0.00051129924,0.00081239094,0.0008590545,0.00040046865,0.000057737318,0.0013034273,0.0013340772,0.9360831,0.020920016,0.00041456954,0.0364716,0.0008322855],"about_ca_topic_score_codex":0.0006148388,"about_ca_topic_score_gemma":0.000052343115,"teacher_disagreement_score":0.9310332,"about_ca_system_score_codex":0.00012003536,"about_ca_system_score_gemma":0.0006588875,"threshold_uncertainty_score":0.9998381},"labels":[],"label_agreement":null},{"id":"W4401899025","doi":"10.1088/2632-2153/ad7457","title":"An exponential reduction in training data sizes for machine learning derived entanglement witnesses","year":2024,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","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 Toronto","funders":"","keywords":"Quantum entanglement; Reduction (mathematics); Data reduction; Training (meteorology); Exponential function; Computer science; Artificial intelligence; Mathematics; Statistics; Physics; Mathematical analysis; Geometry; Quantum mechanics","score_opus":0.029663286882694092,"score_gpt":0.3137040867244099,"score_spread":0.2840407998417158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401899025","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29221475,0.0007969821,0.6999511,0.0048333486,0.0001798754,0.00035062974,0.0000063098646,0.0015867555,0.0000802523],"genre_scores_gemma":[0.9616876,0.000114098664,0.037924737,0.00002308144,0.000041941494,0.00010755341,0.000024464598,0.000011517435,0.0000649823],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99832064,0.000037829017,0.00022533168,0.00087176985,0.00020579193,0.00033866725],"domain_scores_gemma":[0.9992765,0.000051880088,0.00007070482,0.0004701952,0.00007557419,0.00005511074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011922762,0.00013470941,0.00015004881,0.0008087031,0.0006464866,0.00033952465,0.0011167544,0.000082015475,0.000008430061],"category_scores_gemma":[0.00019894057,0.00012608388,0.000016379767,0.0019744162,0.00036296961,0.0009989546,0.00048035607,0.00043046873,0.0000025317152],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000065434015,0.000050392584,0.0016006134,0.000026640464,0.0000075579524,0.000007127851,0.00092207536,0.0003170107,0.24618536,0.051912803,0.000015967478,0.6989479],"study_design_scores_gemma":[0.00019864997,0.00041723103,0.00024931945,0.00003867989,0.0000083425575,0.000120684635,0.0006116284,0.9498372,0.022579422,0.006185637,0.019542245,0.00021098091],"about_ca_topic_score_codex":0.000119085824,"about_ca_topic_score_gemma":0.000054934844,"teacher_disagreement_score":0.9495202,"about_ca_system_score_codex":0.00005536683,"about_ca_system_score_gemma":0.00012780554,"threshold_uncertainty_score":0.51415515},"labels":[],"label_agreement":null},{"id":"W4402589817","doi":"10.1088/2632-2153/ad7cc1","title":"Benchmarking of quantum fidelity kernels for Gaussian process regression","year":2024,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","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 British Columbia","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","keywords":"Benchmarking; Fidelity; Gaussian process; Kriging; Process (computing); Regression; Gaussian; Computer science; Statistics; Artificial intelligence; Mathematics; Machine learning; Physics; Business; Quantum mechanics; Programming language; Telecommunications","score_opus":0.009658262107674597,"score_gpt":0.2903121539643625,"score_spread":0.2806538918566879,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402589817","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13379158,0.002055517,0.8535436,0.008572927,0.0003599683,0.0002623534,0.0000035345915,0.00067641964,0.000734119],"genre_scores_gemma":[0.98773646,0.000053065378,0.012062604,0.00003571424,0.000023456028,0.000022470342,0.0000010742223,0.0000068803433,0.000058256825],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983818,0.000015351556,0.00025039804,0.0006618026,0.0003152194,0.00037545766],"domain_scores_gemma":[0.99919397,0.000082004444,0.000113150665,0.00029182635,0.00025510252,0.000063934756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009876388,0.0001427483,0.00019972652,0.00063685805,0.000393393,0.00023680355,0.0009839672,0.00010490992,0.000006212485],"category_scores_gemma":[0.00047314775,0.00010395096,0.000028744651,0.0025549564,0.00060063903,0.00060642994,0.00031888948,0.00032822473,0.0000025624881],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000042827605,0.000022343844,0.0058424775,0.00036362337,0.0000059824874,0.000010337683,0.00048002173,0.000034901113,0.0075386004,0.58848464,0.00003642937,0.39717633],"study_design_scores_gemma":[0.00012312597,0.000363956,0.0010550104,0.00033449408,0.0000067315405,0.000068775145,0.000086442364,0.8522093,0.010857466,0.1323548,0.0023550722,0.00018476408],"about_ca_topic_score_codex":0.000018644354,"about_ca_topic_score_gemma":0.000002871847,"teacher_disagreement_score":0.8539449,"about_ca_system_score_codex":0.00002465149,"about_ca_system_score_gemma":0.0003286442,"threshold_uncertainty_score":0.4238997},"labels":[],"label_agreement":null},{"id":"W4403528304","doi":"10.1088/2632-2153/ad88d5","title":"Robust quantum dots charge autotuning using neural network uncertainty","year":2024,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Neural Networks and Applications","field":"Computer Science","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":"Perimeter Institute; University of Waterloo; National Research Council Canada; Institut interdisciplinaire d'innovation technologique; Université de Sherbrooke","funders":"Fonds de recherche du Québec – Nature et technologies; Innovation, Science and Economic Development Canada; Institut Périmètre de physique théorique; Natural Sciences and Engineering Research Council of Canada; Government of Canada; Ministero dello Sviluppo Economico","keywords":"Charge (physics); Artificial neural network; Quantum dot; Computer science; Quantum; Artificial intelligence; Neuroscience; Physics; Biology; Optoelectronics; Quantum mechanics","score_opus":0.022674843618693777,"score_gpt":0.2638208348481396,"score_spread":0.24114599122944586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403528304","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8010075,0.004607153,0.16882399,0.020545354,0.00091946067,0.00029769834,0.0000016399777,0.0030658818,0.0007313502],"genre_scores_gemma":[0.9931044,0.000052984855,0.006380363,0.00018049433,0.00010567008,0.000011288402,0.0000011664472,0.000010458741,0.00015319562],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982528,0.000028850054,0.0001773455,0.0006931804,0.00025686072,0.00059096207],"domain_scores_gemma":[0.9993631,0.00006629012,0.000057220586,0.000341892,0.00008407569,0.000087387285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007207365,0.00015378637,0.00015465231,0.00037515064,0.001098347,0.000500589,0.0009123406,0.00008389938,0.0000091978045],"category_scores_gemma":[0.000080055564,0.00012729225,0.000026408123,0.0042855577,0.0005285464,0.00049944833,0.00064994395,0.00065350067,0.000017443861],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000111688,0.0000128073825,0.0031781506,0.000015000407,0.000007021372,0.000044812034,0.00011709589,0.15912968,0.007483596,0.64573246,0.00022853781,0.18404971],"study_design_scores_gemma":[0.00004947727,0.00006893286,0.00013718595,0.000036975216,0.000004543174,0.00014577653,0.000011947022,0.98020035,0.00008976417,0.006350766,0.012752917,0.00015139444],"about_ca_topic_score_codex":0.00007215576,"about_ca_topic_score_gemma":0.00000677796,"teacher_disagreement_score":0.8210706,"about_ca_system_score_codex":0.000047787144,"about_ca_system_score_gemma":0.0001124883,"threshold_uncertainty_score":0.8447708},"labels":[],"label_agreement":null},{"id":"W4404033260","doi":"10.1088/2632-2153/ad8ea8","title":"Accelerating data acquisition with FPGA-based edge machine learning: a case study with LCLS-II","year":2024,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Neural Networks and Applications","field":"Computer Science","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":"Institut interdisciplinaire d'innovation technologique","funders":"Basic Energy Sciences; Office of Science; Canada Research Chairs; U.S. Department of Energy","keywords":"Field-programmable gate array; Enhanced Data Rates for GSM Evolution; Computer science; Data acquisition; Computer architecture; Artificial intelligence; Embedded system; Operating system","score_opus":0.02373263902774665,"score_gpt":0.28496313777567295,"score_spread":0.2612304987479263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404033260","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8994452,0.0005246077,0.089385904,0.008607674,0.00005684095,0.00044688987,0.0000038136154,0.0013634153,0.00016566264],"genre_scores_gemma":[0.9895891,0.000008223217,0.01001813,0.000120613724,0.00003681772,0.00005098884,0.00001246999,0.000017367716,0.00014630242],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977417,0.00006031967,0.00019086755,0.0011763067,0.0003957529,0.00043503277],"domain_scores_gemma":[0.99871856,0.000101659105,0.00009362257,0.00085312733,0.00013864458,0.000094412084],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0009285979,0.00021885955,0.00019481644,0.0005361972,0.0019904668,0.00069472805,0.0013107337,0.00006167432,0.000007880521],"category_scores_gemma":[0.00007006847,0.00014857693,0.000010954192,0.004103781,0.0005137023,0.00082987966,0.0011588982,0.00090351753,0.000007003721],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005266584,0.0007425371,0.12654641,0.0001003649,0.00009208788,0.008482257,0.0021864711,0.019676685,0.006877873,0.028916044,0.00018832105,0.8061383],"study_design_scores_gemma":[0.00038393037,0.0018925853,0.00023135784,0.000052833628,0.000022892153,0.00275378,0.00031726455,0.9882138,0.00032487145,0.00014613212,0.0054130354,0.00024751798],"about_ca_topic_score_codex":0.00027591718,"about_ca_topic_score_gemma":0.0003006588,"teacher_disagreement_score":0.9685371,"about_ca_system_score_codex":0.00003340673,"about_ca_system_score_gemma":0.00020296052,"threshold_uncertainty_score":0.9993088},"labels":[],"label_agreement":null},{"id":"W4404350920","doi":"10.1088/2632-2153/adf595","title":"Calculated solvation and ionization energies for thousands of organic molecules relevant to battery design","year":2025,"lang":"en","type":"preprint","venue":"Machine Learning Science and Technology","topic":"Machine Learning in Materials Science","field":"Materials Science","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":"HORIZON EUROPE Climate, Energy and Mobility; Canada First Research Excellence Fund; Vetenskapsrådet; University of Toronto; European Commission; Canadian Institute for Advanced Research","keywords":"Solvation; Battery (electricity); Organic molecules; Ionization; State (computer science); Molecule; Computational chemistry; Materials science; Chemical physics; Chemistry; Computer science; Physics; Organic chemistry; Thermodynamics; Ion","score_opus":0.010431301104734348,"score_gpt":0.26653778058635574,"score_spread":0.2561064794816214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404350920","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.727373,0.00027532803,0.26874417,0.0022922158,0.00036712014,0.00059145055,0.00001928455,0.00030300152,0.00003441247],"genre_scores_gemma":[0.9096877,0.00009551694,0.08975377,0.00012388303,0.000025755402,0.00009124123,0.000015593765,0.000020050376,0.00018651097],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99737436,0.00016119579,0.0005018319,0.0010692462,0.00043711418,0.00045627225],"domain_scores_gemma":[0.99813527,0.00024659117,0.00042532777,0.00044613224,0.0006693074,0.00007734703],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003061565,0.00029876607,0.0004982707,0.0012596666,0.0006078899,0.00026597732,0.00082237663,0.00031544158,0.00002863605],"category_scores_gemma":[0.0053483914,0.00026788894,0.000023916544,0.0014217026,0.0010636644,0.00016091319,0.0016697379,0.00039177077,0.0000033745462],"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":[0.00003109877,0.000016984264,0.0033096424,0.0002017719,0.0000047478916,0.0000015321112,0.00030600477,0.062609844,0.92863214,0.002119888,0.000027475486,0.002738866],"study_design_scores_gemma":[0.0003873178,0.0005396695,0.0016553006,0.00042157984,0.00005931123,0.00002806018,0.00011791526,0.35742792,0.6305753,0.00790361,0.00037633217,0.0005077041],"about_ca_topic_score_codex":0.000106665575,"about_ca_topic_score_gemma":0.00001536362,"teacher_disagreement_score":0.29805687,"about_ca_system_score_codex":0.000075853095,"about_ca_system_score_gemma":0.00042826205,"threshold_uncertainty_score":0.99997735},"labels":[],"label_agreement":null},{"id":"W4404581601","doi":"10.1088/2632-2153/ad95dd","title":"Paired autoencoders for likelihood-free estimation in inverse problems","year":2024,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Ultrasonics and Acoustic Wave Propagation","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 British Columbia; Geoscience BC","funders":"Department of Energy National Nuclear Security Administration Laboratory Residency Graduate Fellowship; National Science Foundation","keywords":"Inverse problem; Computer science; Estimator; Mathematical optimization; Regularization (linguistics); Discretization; Algorithm; Applied mathematics; Mathematics; Artificial intelligence; Statistics","score_opus":0.005661746177421075,"score_gpt":0.21229360311556486,"score_spread":0.2066318569381438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404581601","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6246934,0.0014636108,0.36557138,0.0046258606,0.00040335194,0.00053067127,0.000007018349,0.0020547048,0.0006500076],"genre_scores_gemma":[0.98647594,0.000050232957,0.013368497,0.000012064867,0.000007219451,0.000039458395,0.000004169893,0.000010978642,0.00003142037],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993822,0.00000390031,0.00010806157,0.00018992567,0.00009797986,0.00021796096],"domain_scores_gemma":[0.9998029,0.000037397298,0.000011362389,0.00009191528,0.000033212666,0.000023211076],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049910514,0.000072484065,0.00007455001,0.0005047634,0.00009848023,0.00007216188,0.00014314608,0.00006649477,0.0000030456235],"category_scores_gemma":[0.00048237282,0.000066963556,0.0000089024925,0.00095983275,0.00015295572,0.00016969698,0.00003875475,0.00022567529,0.0000041054504],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000026260473,0.000017570484,0.003769284,0.00042957728,0.000011918006,0.00000781721,0.00085046917,0.42260468,0.08914675,0.012393824,0.00031074454,0.47045475],"study_design_scores_gemma":[0.00013531685,0.00005764786,0.00013912258,0.000055205703,0.00000436186,0.0000075390903,0.000057463447,0.9757522,0.0012006812,0.021273416,0.0012380119,0.00007903673],"about_ca_topic_score_codex":0.000020224663,"about_ca_topic_score_gemma":0.00005071653,"teacher_disagreement_score":0.55314755,"about_ca_system_score_codex":0.00005999442,"about_ca_system_score_gemma":0.000045292083,"threshold_uncertainty_score":0.27306944},"labels":[],"label_agreement":null},{"id":"W4404581783","doi":"10.1088/2632-2153/ad95d9","title":"Illuminating new and known relations between knot invariants","year":2024,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Botulinum Toxin and Related Neurological Disorders","field":"Medicine","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 British Columbia","funders":"National Research Foundation; Simons Foundation; Department of Science and Innovation, South Africa; National Science Foundation","keywords":"Knot invariant; Mathematics; Quantum invariant; Knot (papermaking); Invariant (physics); Knot theory; Conjecture; Jones polynomial; Knot polynomial; Pure mathematics; Discrete mathematics","score_opus":0.01317818936643306,"score_gpt":0.2754535084697703,"score_spread":0.26227531910333723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404581783","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94078195,0.0038942893,0.0004069008,0.04865011,0.00007387394,0.00013250126,8.638259e-7,0.0005291315,0.0055303564],"genre_scores_gemma":[0.99648756,0.00022841891,0.00072704395,0.00017758018,0.000028328226,0.0000021810129,0.0000019485994,0.000008701707,0.0023382674],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9991021,0.000016949167,0.00013131014,0.0003698192,0.00014829816,0.00023149123],"domain_scores_gemma":[0.99962956,0.00010469592,0.000024352448,0.00009675219,0.00003626267,0.00010837267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034165868,0.0000923222,0.00014588481,0.0004777417,0.00032748817,0.00005251407,0.00008495066,0.00018095573,0.000050474413],"category_scores_gemma":[0.0010575383,0.00006696265,0.000014194525,0.0014998465,0.0008824415,0.000101863654,0.00014318031,0.00089475064,0.00003707945],"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":[0.0000075897815,0.000022855547,0.29978925,0.000046215184,0.000029716948,0.000107910186,0.00039229981,0.000010056612,0.015976517,0.022155328,0.00026069643,0.6612016],"study_design_scores_gemma":[0.003420068,0.0046400926,0.5296764,0.000900285,0.0005015355,0.0020176948,0.0009570647,0.17327347,0.003634003,0.072344996,0.20758612,0.0010482664],"about_ca_topic_score_codex":0.00003056903,"about_ca_topic_score_gemma":0.0000033389726,"teacher_disagreement_score":0.6601533,"about_ca_system_score_codex":0.000014264774,"about_ca_system_score_gemma":0.00011477406,"threshold_uncertainty_score":0.3887296},"labels":[],"label_agreement":null},{"id":"W4405190256","doi":"10.1088/2632-2153/ad9ba8","title":"Process tomography of structured optical gates with convolutional neural networks","year":2024,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Laser Design and Applications","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":"National Research Council Canada; University of Ottawa","funders":"National Research Council Canada; Canada Research Chairs; University of Ottawa","keywords":"Convolutional neural network; Process (computing); Computer science; Tomography; Artificial intelligence; Optics; Physics; Programming language","score_opus":0.003093267437099724,"score_gpt":0.20828731991469768,"score_spread":0.20519405247759795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405190256","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9857471,0.0014210477,0.01080046,0.0008619569,0.000047319754,0.00008763511,0.0000026987955,0.0006562371,0.00037553653],"genre_scores_gemma":[0.99938196,0.000012815129,0.0005515433,0.000006824966,0.000011045941,0.000012751328,0.0000027546948,0.000006695014,0.0000136247945],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995171,0.0000025611416,0.000070496244,0.00015031887,0.00010798261,0.00015156082],"domain_scores_gemma":[0.99982244,0.000021008267,0.000008856683,0.00006708439,0.000051866293,0.000028770914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008872438,0.00006479059,0.000073431365,0.0002518051,0.00009151782,0.000029761439,0.0001272056,0.000047366077,0.00000779996],"category_scores_gemma":[0.000017682218,0.000047362315,0.000007814303,0.0014864551,0.000692137,0.000079838865,0.000021321517,0.00025784943,6.549322e-7],"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":[0.00001976641,0.00003794895,0.12815689,0.0003241067,0.000091668975,0.000029071945,0.0003491752,0.40112537,0.11004933,0.26504096,0.00018308435,0.094592616],"study_design_scores_gemma":[0.000063594176,0.00006475869,0.0022178814,0.000016838063,0.0000082122115,0.000050380186,0.000034092336,0.9904305,0.005142118,0.0015332361,0.00036683376,0.00007157795],"about_ca_topic_score_codex":0.0000030391711,"about_ca_topic_score_gemma":0.000003155188,"teacher_disagreement_score":0.5893051,"about_ca_system_score_codex":0.0000070959663,"about_ca_system_score_gemma":0.000021808297,"threshold_uncertainty_score":0.25502077},"labels":[],"label_agreement":null},{"id":"W4405431858","doi":"10.1088/2632-2153/ad9fd0","title":"Closed-form interpretation of neural network classifiers with symbolic gradients","year":2024,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Neural Networks and Applications","field":"Computer Science","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":"Regional Municipality of Waterloo; Perimeter Institute; University of Waterloo","funders":"Mitacs","keywords":"Interpretation (philosophy); Artificial neural network; Artificial intelligence; Computer science; Pattern recognition (psychology); Mathematics; Programming language","score_opus":0.005275268148137342,"score_gpt":0.2337410787661297,"score_spread":0.22846581061799237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405431858","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9040148,0.0008670611,0.08646139,0.006635778,0.00023283745,0.00018207551,6.806524e-7,0.0006253651,0.000979988],"genre_scores_gemma":[0.9968078,0.000032972246,0.0029626214,0.000072890514,0.000019432522,0.000013752425,8.8688785e-7,0.0000051651537,0.00008445179],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999018,0.000012611649,0.00013114161,0.00037189375,0.00019535102,0.0002710141],"domain_scores_gemma":[0.9995618,0.000043697608,0.000055760447,0.00021939314,0.00007399711,0.00004535431],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027996057,0.00009032526,0.000112837835,0.0003089678,0.00026551468,0.00013031362,0.0005605665,0.00004471006,0.0000014884134],"category_scores_gemma":[0.000029859408,0.0000651331,0.000014834189,0.0029979646,0.0005924582,0.00033829827,0.00021238752,0.000317621,0.0000036019626],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000416511,0.0000133189305,0.01598905,0.000018651148,0.000008898874,0.000009140939,0.00032075553,0.0036269145,0.0017568277,0.3667979,0.00007532529,0.6113791],"study_design_scores_gemma":[0.00006790655,0.00022392909,0.002746463,0.00004685915,0.00000536095,0.00004807644,0.000026781965,0.9840757,0.00031128636,0.010112413,0.0022459137,0.000089255875],"about_ca_topic_score_codex":0.000016404623,"about_ca_topic_score_gemma":0.000011619254,"teacher_disagreement_score":0.98044884,"about_ca_system_score_codex":0.000018939301,"about_ca_system_score_gemma":0.000054439006,"threshold_uncertainty_score":0.2656051},"labels":[],"label_agreement":null},{"id":"W4405466521","doi":"10.1088/2632-2153/ada087","title":"Automation of quantum dot measurement analysis via explainable machine learning","year":2024,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":6,"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":"Army Research Office; National Science Foundation","keywords":"Automation; Quantum dot; Computer science; Artificial intelligence; Engineering; Physics; Optoelectronics; Mechanical engineering","score_opus":0.017960715525358908,"score_gpt":0.2645482183081211,"score_spread":0.24658750278276217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405466521","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12905842,0.0030039868,0.8610709,0.0043224255,0.00023809298,0.00020114247,9.408393e-7,0.0013037123,0.00080038584],"genre_scores_gemma":[0.9943298,0.00008913631,0.005288502,0.000030008037,0.00001385427,0.000020705851,0.0000022942684,0.000010895843,0.0002148185],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99704397,0.00011320385,0.0004390307,0.0008416971,0.0009845766,0.0005775488],"domain_scores_gemma":[0.9985766,0.00010478872,0.00017137559,0.00049157895,0.00056233275,0.00009332599],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038886976,0.00021021954,0.0003439844,0.0029331017,0.00073102466,0.0003411917,0.0011266759,0.00012077808,0.000037643185],"category_scores_gemma":[0.0011795436,0.0001867789,0.000073576004,0.011307944,0.00063582085,0.00096374954,0.00058203493,0.000657893,0.000057451096],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009096802,0.00011048529,0.030352283,0.00014996582,0.00020232669,0.000090267495,0.0022853478,0.02521483,0.18679567,0.45116568,0.000030014888,0.30359405],"study_design_scores_gemma":[0.000051642608,0.00028528995,0.00046513023,0.000039181912,0.00005181236,0.00002975982,0.00020920785,0.9462202,0.039640833,0.009339092,0.003474888,0.00019295678],"about_ca_topic_score_codex":0.000628422,"about_ca_topic_score_gemma":0.00008712302,"teacher_disagreement_score":0.92100537,"about_ca_system_score_codex":0.00017810846,"about_ca_system_score_gemma":0.00018707008,"threshold_uncertainty_score":0.7616622},"labels":[],"label_agreement":null},{"id":"W4405624724","doi":"10.1088/2632-2153/ada248","title":"Machine learning configuration-dependent friction tensors in Langevin heatbaths","year":2024,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","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 British Columbia","funders":"Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada; University of Warwick; Leverhulme Trust; UK Research and Innovation","keywords":"Homogeneous space; Formalism (music); Langevin equation; Tensor (intrinsic definition); Configuration space; Statistical physics; Euclidean space; Classical mechanics; Physics; Dissipation; Langevin dynamics; Mathematics; Mathematical analysis; Pure mathematics; Quantum mechanics; Geometry","score_opus":0.0038734124174243543,"score_gpt":0.23576282946636165,"score_spread":0.23188941704893729,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405624724","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9863954,0.0066057076,0.0020647326,0.0020553118,0.00013235603,0.00016782612,0.0000045706133,0.00018584583,0.0023882543],"genre_scores_gemma":[0.9980279,0.00048354347,0.0002991197,0.000066946646,0.000044691395,0.000015465932,0.000034156434,0.000012955768,0.0010151813],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99893117,0.000036282712,0.00014692222,0.00045941933,0.00016301768,0.00026319988],"domain_scores_gemma":[0.9997033,0.0000125314045,0.000035845456,0.00014426782,0.0000645507,0.000039520794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004804789,0.00012769914,0.000117381955,0.00042195598,0.00022733187,0.000079084326,0.00017734934,0.00017258116,0.000015148157],"category_scores_gemma":[0.00039959786,0.00011022069,0.0000186817,0.000719599,0.00027812127,0.000015204347,0.00014017784,0.0005120257,0.000010647492],"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":[0.000023575136,0.000019833335,0.083382465,0.00003649291,0.000016619097,0.0000464509,0.00015433147,0.001759714,0.817375,0.009434746,0.000028498856,0.08772227],"study_design_scores_gemma":[0.0016906823,0.002539484,0.014918309,0.00019933755,0.000057397974,0.0010450911,0.00095391565,0.48930684,0.17912994,0.007707985,0.301056,0.0013950226],"about_ca_topic_score_codex":0.00015846652,"about_ca_topic_score_gemma":0.000161212,"teacher_disagreement_score":0.63824505,"about_ca_system_score_codex":0.00003178058,"about_ca_system_score_gemma":0.0000890858,"threshold_uncertainty_score":0.4494669},"labels":[],"label_agreement":null},{"id":"W4405745687","doi":"10.1088/2632-2153/ada33b","title":"Asymptotically stable data-driven koopman operator approximation with inputs using total extended DMD","year":2024,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","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":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Toyota Research Institute; Office of Naval Research Global; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Operator (biology); Applied mathematics; Mathematics; Stability (learning theory); Stability theory; Control theory (sociology); Computer science; Physics; Artificial intelligence; Biology; Nonlinear system","score_opus":0.015482969197065417,"score_gpt":0.2737657493641807,"score_spread":0.25828278016711526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405745687","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93855476,0.000118991404,0.05835863,0.0014100574,0.000114519935,0.0001370737,0.0000068011345,0.00023998416,0.0010591925],"genre_scores_gemma":[0.99507713,0.0000039373085,0.0045082616,0.000023008892,0.00007189035,0.000005695587,0.00002040244,0.000011120333,0.0002785678],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99893993,0.000018485784,0.00011480289,0.00047349415,0.00018983574,0.00026342866],"domain_scores_gemma":[0.9995881,0.000014746645,0.000032738295,0.00023451557,0.00007206529,0.000057873374],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026170554,0.000111502144,0.00011985141,0.00023668991,0.00038672262,0.00023084074,0.0002467577,0.00004258467,0.000071138704],"category_scores_gemma":[0.000018654906,0.00008305881,0.000008940869,0.0009822315,0.00040963155,0.0004866905,0.00025263405,0.00042091942,0.000008503966],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004270564,0.00017052823,0.028724723,0.00007152559,0.00010625425,0.000031110412,0.0003900899,0.03436156,0.100480355,0.26540774,0.0001826785,0.57003075],"study_design_scores_gemma":[0.00012853928,0.00011215476,0.00010147419,0.000041221378,0.000015173609,0.000039394392,0.000084372805,0.99521613,0.0014980233,0.00073697226,0.0019005536,0.00012601624],"about_ca_topic_score_codex":0.000047604244,"about_ca_topic_score_gemma":0.0000022187787,"teacher_disagreement_score":0.96085453,"about_ca_system_score_codex":0.000019889836,"about_ca_system_score_gemma":0.00014138302,"threshold_uncertainty_score":0.338704},"labels":[],"label_agreement":null},{"id":"W4406120973","doi":"10.1088/2632-2153/ada71c","title":"rule4ml: an open-source tool for resource utilization and latency estimation for ML models on FPGA","year":2025,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","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":"Institut interdisciplinaire d'innovation technologique; Université de Sherbrooke","funders":"","keywords":"Field-programmable gate array; Open source; Latency (audio); Computer science; Estimation; Resource (disambiguation); Embedded system; Operating system; Engineering; Computer network; Telecommunications; Software; Systems engineering","score_opus":0.02588689577435285,"score_gpt":0.3162581162998396,"score_spread":0.29037122052548675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406120973","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016557217,0.0001200326,0.97775817,0.0037127126,0.000036397796,0.0005425422,0.0000012677797,0.0007394386,0.00053225073],"genre_scores_gemma":[0.6691845,0.000026719475,0.32985595,0.00038820086,0.000006032784,0.00008694978,0.000008386831,0.000008056374,0.0004351881],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987961,0.000034795765,0.00018348939,0.0006032485,0.00013158632,0.00025077086],"domain_scores_gemma":[0.99919647,0.0001243059,0.0001029165,0.00032450721,0.00021618138,0.000035640693],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011954006,0.00012010929,0.0001538729,0.0006188537,0.0009703939,0.00041699636,0.0009370046,0.00010645645,3.4489318e-7],"category_scores_gemma":[0.00069555925,0.00011204958,0.000010755548,0.0011021036,0.00023129088,0.00064293883,0.00048587268,0.0001495406,3.027245e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001580868,0.000038210404,0.000324461,0.000018955288,0.000002867011,1.8712522e-7,0.00015185331,0.047483105,0.00031054337,0.3970059,0.00013364677,0.55451447],"study_design_scores_gemma":[0.000337324,0.0004701812,0.00010417344,0.000035238598,0.00000399266,0.0000042001893,0.000016028218,0.91503084,0.0016073892,0.07638402,0.0058909683,0.00011565936],"about_ca_topic_score_codex":0.000015653291,"about_ca_topic_score_gemma":0.0000023598545,"teacher_disagreement_score":0.8675477,"about_ca_system_score_codex":0.00003004164,"about_ca_system_score_gemma":0.00008989857,"threshold_uncertainty_score":0.74635834},"labels":[],"label_agreement":null},{"id":"W4406135959","doi":"10.1088/2632-2153/ada71d","title":"A reinforcement learning approach to the design of quantum chains for optimal energy and state transfer","year":2025,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Spectroscopy and Quantum Chemical Studies","field":"Physics and Astronomy","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":"HORIZON EUROPE European Innovation Council; HORIZON EUROPE Framework Programme; Queen's University; Queen's University Belfast; Royal Society; Engineering and Physical Sciences Research Council; Leverhulme Trust; Department for the Economy","keywords":"Reinforcement learning; Markov chain; Chain (unit); Excitation; Markov decision process; Computer science; Mathematical optimization; Quantum; Optimal design; Q-learning; Markov process; Statistical physics; Physics; Mathematics; Quantum mechanics; Artificial intelligence","score_opus":0.009277254475842508,"score_gpt":0.2495382329383942,"score_spread":0.24026097846255168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406135959","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1830294,0.0001832864,0.814522,0.0014685461,0.000016627686,0.0001646646,0.0000013780742,0.00003022373,0.00058386684],"genre_scores_gemma":[0.998231,0.000023948918,0.0012350493,0.0000551837,0.0000088732895,0.00007960398,0.0000016517262,0.000003949719,0.00036077248],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992716,0.000016469667,0.00012857138,0.0002429168,0.000090885354,0.0002495627],"domain_scores_gemma":[0.9997246,0.00007443036,0.00002872107,0.00008245206,0.0000645538,0.000025207555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040583045,0.00009543091,0.00015816459,0.00015555101,0.0005230835,0.000026105354,0.00017361435,0.000024203906,0.000002457718],"category_scores_gemma":[0.000066163106,0.0000645099,0.000017081054,0.0005991923,0.0004458368,0.000036659407,0.00012274212,0.00016078407,1.2462839e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000073315685,0.000049431335,0.006768208,0.0000258765,0.00005938428,1.2469593e-7,0.0009155494,0.047468908,0.048456967,0.85761845,0.00005946782,0.038504317],"study_design_scores_gemma":[0.0005830227,0.0006053243,0.00015943917,0.000028866676,0.000030453033,8.024081e-7,0.0013588989,0.8977692,0.08060883,0.008747061,0.009936869,0.000171216],"about_ca_topic_score_codex":0.000117651325,"about_ca_topic_score_gemma":0.0000012651644,"teacher_disagreement_score":0.8503003,"about_ca_system_score_codex":0.000010224045,"about_ca_system_score_gemma":0.00003861968,"threshold_uncertainty_score":0.40231884},"labels":[],"label_agreement":null},{"id":"W4408391914","doi":"10.1088/2632-2153/adc072","title":"Hybrid vision transformer framework for efficient and explainable SEM image-based nanomaterial classification","year":2025,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Machine Learning in Materials Science","field":"Materials Science","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 Winnipeg","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Nanomaterials; Computer science; Artificial intelligence; Computer vision; Transformer; Pattern recognition (psychology); Materials science; Nanotechnology; Engineering; Electrical engineering","score_opus":0.005869917712779618,"score_gpt":0.28002272347817975,"score_spread":0.27415280576540013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408391914","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8416682,0.00013891821,0.15049653,0.0060036336,0.0005270748,0.00047300075,0.000011111131,0.0004054185,0.00027610405],"genre_scores_gemma":[0.9413594,0.000012655571,0.058154263,0.0001866492,0.000027884913,0.000113849426,0.0000057339303,0.000015808666,0.00012378095],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99749345,0.00009708521,0.00036520552,0.0009824581,0.0003908771,0.00067092635],"domain_scores_gemma":[0.998809,0.00024782796,0.00018085395,0.00037595956,0.00029580272,0.00009054684],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0029740962,0.0002469663,0.00031901253,0.0007899334,0.0016234515,0.0005619329,0.00063910556,0.00015395747,0.00007722739],"category_scores_gemma":[0.0022819953,0.00021108307,0.000027035378,0.0010551489,0.0022048946,0.00029548805,0.00017930941,0.00029586483,0.00001822903],"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":[0.00006899308,0.0000410393,0.0014817964,0.00010020962,0.0000014980643,0.0000020938076,0.00007514649,0.0005603139,0.95315063,0.03736596,0.00002781146,0.0071245176],"study_design_scores_gemma":[0.0008845098,0.00051412464,0.0025107954,0.00016401238,0.000024890885,0.000027147027,0.00018017374,0.3506052,0.623529,0.015298347,0.0058920216,0.00036980127],"about_ca_topic_score_codex":0.0000498042,"about_ca_topic_score_gemma":0.0000030650092,"teacher_disagreement_score":0.35004488,"about_ca_system_score_codex":0.00008995194,"about_ca_system_score_gemma":0.0002466277,"threshold_uncertainty_score":0.9996763},"labels":[],"label_agreement":null},{"id":"W4409136717","doi":"10.1088/2632-2153/adc8fc","title":"Wilsonian renormalization of neural network Gaussian processes<sup>*</sup>","year":2025,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Neural Networks and Applications","field":"Computer Science","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":"Perimeter Institute","funders":"Institut Périmètre de physique théorique; Israel Science Foundation; Gordon and Betty Moore Foundation; National Science Foundation","keywords":"Renormalization; Statistical physics; Artificial neural network; Gaussian; Physics; Mathematical physics; Computer science; Artificial intelligence; Quantum mechanics","score_opus":0.004768710325753749,"score_gpt":0.23745112930346415,"score_spread":0.23268241897771041,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409136717","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56011266,0.0026494917,0.37738734,0.05115155,0.00023107207,0.0006315234,0.0000017931441,0.0013400688,0.006494462],"genre_scores_gemma":[0.9944851,0.00006782353,0.004940693,0.00023108468,0.000018536557,0.000015850499,0.0000012363007,0.0000034294005,0.00023624346],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988924,0.000021928457,0.0001909719,0.00039774404,0.0001767993,0.00032012264],"domain_scores_gemma":[0.9992861,0.000043134914,0.00010425834,0.0003248922,0.00020118857,0.000040411953],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037775032,0.0000998829,0.00014162732,0.00035562727,0.0005735917,0.00009936101,0.0008982792,0.0000698254,0.0000024181309],"category_scores_gemma":[0.00019633041,0.00008551263,0.0000123172795,0.0063315565,0.00052270637,0.00032323683,0.0004297087,0.00026059823,0.0000017849137],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037995756,0.00004427363,0.09396851,0.000056968416,0.000007232629,0.0000035442577,0.0002224607,0.056817096,0.0012295013,0.5863583,0.00031664892,0.26097164],"study_design_scores_gemma":[0.0001496826,0.00010470308,0.002576736,0.000046620687,0.0000056545027,0.000019381701,0.000034545614,0.97037405,0.0009093965,0.013911925,0.011749877,0.00011743383],"about_ca_topic_score_codex":0.000025858571,"about_ca_topic_score_gemma":0.000011743068,"teacher_disagreement_score":0.91355693,"about_ca_system_score_codex":0.000014887787,"about_ca_system_score_gemma":0.0001440805,"threshold_uncertainty_score":0.44116613},"labels":[],"label_agreement":null},{"id":"W4410022944","doi":"10.1088/2632-2153/add3bb","title":"LLM4Mat-bench: benchmarking large language models for materials property prediction","year":2025,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Machine Learning in Materials Science","field":"Materials Science","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":"Schwartz/Reisman Emergency Medicine Institute; Vector Institute; Structural Genomics Consortium; University of Toronto","funders":"Office of Advanced Cyberinfrastructure; National Science Foundation","keywords":"Benchmarking; Property (philosophy); Computer science; Natural language processing; Business; Philosophy","score_opus":0.007163373249796719,"score_gpt":0.26042733231801074,"score_spread":0.25326395906821403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410022944","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9555829,0.00031334683,0.035778932,0.0033101328,0.0012439281,0.0007722676,0.000064395266,0.0009927773,0.0019412966],"genre_scores_gemma":[0.984908,0.000026834452,0.013098438,0.00029502917,0.0000806263,0.0001666747,0.000018251561,0.00002033185,0.0013858175],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9969782,0.00012381608,0.0004664271,0.0010413569,0.00048597073,0.00090417615],"domain_scores_gemma":[0.99874836,0.00011698272,0.00022856671,0.00048530934,0.00033639173,0.00008438173],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.004934681,0.00027579538,0.00039491808,0.00091038534,0.0016229391,0.0004812069,0.0009896313,0.00019856099,0.0002249266],"category_scores_gemma":[0.0018242658,0.00019840688,0.000029611194,0.0015971267,0.0010865858,0.0007051547,0.0007328772,0.0003190526,0.000024269588],"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":[0.000028026443,0.00003861727,0.0026834696,0.00009237203,0.00000369949,0.000003178822,0.00033965375,0.0010066752,0.9623359,0.027475014,0.00015811792,0.0058353078],"study_design_scores_gemma":[0.001122951,0.0005127015,0.0010550361,0.0001936281,0.000042031294,0.000057836703,0.00061061676,0.42827007,0.54142314,0.012209243,0.013986859,0.0005158768],"about_ca_topic_score_codex":0.00021257519,"about_ca_topic_score_gemma":0.000030224981,"teacher_disagreement_score":0.4272634,"about_ca_system_score_codex":0.00010791797,"about_ca_system_score_gemma":0.0002559245,"threshold_uncertainty_score":0.9996768},"labels":[],"label_agreement":null},{"id":"W4412534222","doi":"10.1088/2632-2153/adf278","title":"Feature learning and generalization in deep networks with orthogonal weights","year":2025,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Neural Networks and Applications","field":"Computer Science","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":"Vector Institute; University of Toronto","funders":"High Energy Physics","keywords":"Generalization; Feature (linguistics); Artificial intelligence; Pattern recognition (psychology); Feature learning; Computer science; Deep learning; Mathematics; Philosophy","score_opus":0.0023080742995250235,"score_gpt":0.21947355951038824,"score_spread":0.2171654852108632,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412534222","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5202516,0.0019226717,0.45651907,0.01997322,0.000058982616,0.00018449248,9.7485284e-8,0.0003399738,0.00074992044],"genre_scores_gemma":[0.9902195,0.00020048051,0.008998873,0.0001803432,0.000010761778,0.000016108741,0.0000014687816,0.000003307985,0.00036918191],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990949,0.000026473284,0.000079910205,0.00042785401,0.00011936407,0.00025150226],"domain_scores_gemma":[0.9996721,0.00003682126,0.000049702794,0.00013472956,0.00007245098,0.00003420518],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027905838,0.00009473133,0.00010833282,0.00044017192,0.00054243294,0.00014018247,0.0003208406,0.0000813721,9.55997e-7],"category_scores_gemma":[0.000048677055,0.00007276996,0.0000056283725,0.0031744023,0.00035986563,0.0002086265,0.0002828169,0.00050340313,4.7385973e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003320552,0.000013819242,0.4097114,0.000005352993,0.0000031765946,0.0000083441555,0.0000560126,0.014554234,0.0007104365,0.35745418,0.00002074552,0.21745896],"study_design_scores_gemma":[0.00019937013,0.00007378171,0.018586408,0.00002652125,0.0000026410175,0.00003480139,0.000020103582,0.96762997,0.000114753966,0.0031757087,0.010031963,0.00010397965],"about_ca_topic_score_codex":0.000012478978,"about_ca_topic_score_gemma":0.0000975623,"teacher_disagreement_score":0.9530757,"about_ca_system_score_codex":0.000016903356,"about_ca_system_score_gemma":0.00004477468,"threshold_uncertainty_score":0.41720107},"labels":[],"label_agreement":null},{"id":"W4412618004","doi":"10.1088/2632-2153/adf376","title":"Lattice protein folding with variational annealing","year":2025,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Biochemical and Structural Characterization","field":"Biochemistry, Genetics and Molecular Biology","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":"Vector Institute; Perimeter Institute; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Innovation, Science and Economic Development Canada; Institut Périmètre de physique théorique; Alliance de recherche numérique du Canada; Government of Canada; Ministero dello Sviluppo Economico","keywords":"Lattice (music); Protein folding; Annealing (glass); Statistical physics; Crystallography; Materials science; Physics; Mathematics; Chemistry; Thermodynamics; Nuclear magnetic resonance","score_opus":0.0025994029083763557,"score_gpt":0.21610803850728078,"score_spread":0.21350863559890443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412618004","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99423355,0.00014338532,0.0028286565,0.002209472,0.000020460522,0.00007246489,0.0000010251225,0.000035281926,0.00045568947],"genre_scores_gemma":[0.99695295,0.00000787632,0.0024978828,0.00012375972,0.000018300258,0.000008719664,0.000015898084,0.0000030426206,0.00037157457],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994431,0.000009037824,0.00006863393,0.00025298982,0.00008565236,0.00014057952],"domain_scores_gemma":[0.9997344,0.0000038468406,0.000035598412,0.00008578934,0.00012038421,0.000020004172],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001539722,0.000065376895,0.000058021506,0.00012128361,0.00025114676,0.000031825442,0.00012685047,0.00008278847,0.0000029794408],"category_scores_gemma":[0.00025489973,0.00005018329,0.000006048519,0.00057031744,0.0002827224,0.000006963174,0.00011026674,0.00012891619,5.284713e-7],"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":[0.000013617743,0.0000033984486,0.023389032,0.0000074257096,0.000005015641,4.7255648e-7,0.000005814011,0.00001278465,0.9612257,0.00810133,0.00000251067,0.007232918],"study_design_scores_gemma":[0.00046173122,0.00034294283,0.015499389,0.000046011788,0.000011952006,0.000032233576,0.000048729562,0.007611993,0.9640006,0.0024992444,0.009238038,0.00020716296],"about_ca_topic_score_codex":0.0000075941116,"about_ca_topic_score_gemma":0.0000027684407,"teacher_disagreement_score":0.009235527,"about_ca_system_score_codex":0.000008071343,"about_ca_system_score_gemma":0.000065784814,"threshold_uncertainty_score":0.20464152},"labels":[],"label_agreement":null},{"id":"W4412618013","doi":"10.1088/2632-2153/adf375","title":"Beyond Euclid: an illustrated guide to modern machine learning with geometric, topological, and algebraic structures","year":2025,"lang":"en","type":"review","venue":"Machine Learning Science and Technology","topic":"Computational Physics and Python Applications","field":"Computer Science","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; Chan Zuckerberg Initiative; Gordon and Betty Moore Foundation; European Research Council; National Science Foundation; National Institutes of Health; Agence Nationale de la Recherche","keywords":"Algebraic number; Algebra over a field; Topology (electrical circuits); Mathematics; Computer science; Pure mathematics; Combinatorics; Mathematical analysis","score_opus":0.014538959341185419,"score_gpt":0.31309942948032216,"score_spread":0.2985604701391367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412618013","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011380067,0.8088472,0.18460946,0.0025170827,0.000102130485,0.0009095969,0.000020311263,0.0009009866,0.00095522037],"genre_scores_gemma":[0.039615694,0.8856384,0.07261242,0.00058124814,0.00010675013,0.00021824357,0.00012686364,0.000057426747,0.0010429323],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972276,0.00010976168,0.0003921497,0.0013403818,0.00043972902,0.00049038464],"domain_scores_gemma":[0.9983596,0.0002971541,0.00026875033,0.0005675356,0.00030872005,0.00019819163],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00068021903,0.00041470354,0.0007992497,0.0021025075,0.0010989307,0.0005043848,0.001561646,0.0002339837,0.0000069484418],"category_scores_gemma":[0.0004619202,0.0003056342,0.000043653625,0.007955578,0.00068865897,0.0002829046,0.0012459483,0.001145807,0.00000633882],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011298563,0.00001978088,0.0001261284,0.00018410609,0.000015960417,0.000007155426,0.000042505253,0.0004736944,0.0000116936635,0.106350616,0.000018926015,0.8927483],"study_design_scores_gemma":[0.00032012627,0.001072384,0.0002026716,0.00056958146,0.00011840873,0.00034146904,0.00003533142,0.09827477,0.000012785949,0.0714816,0.8265792,0.0009916842],"about_ca_topic_score_codex":0.0001377964,"about_ca_topic_score_gemma":0.00003618168,"teacher_disagreement_score":0.8917566,"about_ca_system_score_codex":0.00006303488,"about_ca_system_score_gemma":0.00049786735,"threshold_uncertainty_score":0.99993956},"labels":[],"label_agreement":null},{"id":"W4412834632","doi":"10.1088/2632-2153/adf521","title":"Exploring the energy landscape of RBMs: reciprocal space insights into bosons, hierarchical learning and symmetry breaking","year":2025,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","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; Perimeter Institute; TRIUMF","funders":"Office of Advanced Cyberinfrastructure; Basic Energy Sciences; National Research Council Canada; Mitacs","keywords":"Statistical physics; Symmetry breaking; Symmetry (geometry); Saddle point; Mathematics; Theoretical physics; Physics; Quantum mechanics; Geometry","score_opus":0.008793077527168259,"score_gpt":0.23569560271463158,"score_spread":0.22690252518746332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412834632","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8173177,0.0035075806,0.1640905,0.012225119,0.00017703601,0.00008877535,1.4213029e-7,0.00034590022,0.0022471966],"genre_scores_gemma":[0.99420094,0.0006256926,0.0049335696,0.00009026749,0.000013775105,0.000016412721,2.5593175e-7,0.0000053107583,0.000113762544],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99847436,0.00007093449,0.00022913897,0.0005812858,0.0002904609,0.0003538005],"domain_scores_gemma":[0.9991861,0.00020018699,0.00012440023,0.0002851366,0.00014262542,0.00006156463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006213727,0.00015903787,0.00023505649,0.00087329076,0.0009787031,0.00020998025,0.00094312,0.0000858258,0.0000014781368],"category_scores_gemma":[0.00082665577,0.000110378576,0.00001963668,0.003527568,0.0010660576,0.0005070525,0.0012098666,0.0007111169,8.52937e-7],"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":[0.0000042248676,0.000013385054,0.045415685,0.000035382214,0.0000067512524,0.000006354465,0.0005536112,0.000017744327,0.0026747729,0.56143045,0.000004616756,0.389837],"study_design_scores_gemma":[0.0013100242,0.0016168127,0.033621244,0.0009487325,0.00005335342,0.00033142878,0.0034030161,0.59524983,0.049593076,0.25108477,0.061687082,0.0011006396],"about_ca_topic_score_codex":0.00013527059,"about_ca_topic_score_gemma":0.000035104327,"teacher_disagreement_score":0.59523207,"about_ca_system_score_codex":0.000021265909,"about_ca_system_score_gemma":0.00018918708,"threshold_uncertainty_score":0.7527492},"labels":[],"label_agreement":null},{"id":"W4412866368","doi":"10.1088/2632-2153/adf701","title":"SIDDA: SInkhorn Dynamic Domain Adaptation for image classification with equivariant neural networks","year":2025,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","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":"Canadian Institute for Theoretical Astrophysics; University of Toronto","funders":"Fermilab; Oak Ridge Institute for Science and Education; National Science Foundation","keywords":"Equivariant map; Domain adaptation; Adaptation (eye); Computer science; Domain (mathematical analysis); Image (mathematics); Artificial neural network; Artificial intelligence; Pattern recognition (psychology); Mathematics; Pure mathematics; Psychology; Mathematical analysis; Neuroscience","score_opus":0.009021148630347827,"score_gpt":0.2581942054823836,"score_spread":0.24917305685203575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412866368","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022900734,0.00017225035,0.96196896,0.013269786,0.00014043238,0.00028169045,5.4798085e-7,0.00045339583,0.0008122029],"genre_scores_gemma":[0.90369433,0.00001301879,0.095686495,0.00024990816,0.00000872968,0.00005146757,0.0000065163435,0.000007751687,0.0002818093],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99845076,0.00005552419,0.00021183921,0.00062579266,0.00023689974,0.00041916055],"domain_scores_gemma":[0.9990809,0.0001320727,0.00015423515,0.000325298,0.00025190247,0.00005559077],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010096702,0.00015233981,0.00016594108,0.0007440849,0.0009400699,0.0003378173,0.00068055914,0.00010367517,0.0000018810399],"category_scores_gemma":[0.0003725562,0.00012953984,0.00002084304,0.0026871515,0.0006570139,0.0005681448,0.00020675277,0.00041180433,0.0000026049377],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003501335,0.000037779595,0.0029895564,0.000018191822,0.000013591011,0.000009042076,0.00043929918,0.013792252,0.011630737,0.6075572,0.000014648461,0.36346272],"study_design_scores_gemma":[0.00051752233,0.00022886631,0.004299497,0.000018709681,0.000007184945,0.000028389755,0.000443736,0.9837905,0.00006683543,0.007933394,0.0025193407,0.00014602886],"about_ca_topic_score_codex":0.000017056775,"about_ca_topic_score_gemma":0.000035093653,"teacher_disagreement_score":0.96999824,"about_ca_system_score_codex":0.00008142183,"about_ca_system_score_gemma":0.00016357219,"threshold_uncertainty_score":0.7230353},"labels":[],"label_agreement":null},{"id":"W4412979458","doi":"10.1088/2632-2153/adf7fe","title":"Uncertainty quantification from ensemble variance scaling laws in deep neural networks","year":2025,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","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":"Vector Institute; University of Toronto","funders":"High Energy Physics","keywords":"Variance (accounting); Artificial neural network; Scaling law; Deep neural networks; Scaling; Law; Computer science; Artificial intelligence; Econometrics; Statistical physics; Mathematics; Political science; Economics; Physics; Accounting","score_opus":0.006595860381345152,"score_gpt":0.2530018814771641,"score_spread":0.24640602109581897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412979458","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10324641,0.00033722914,0.8903908,0.0049045705,0.000079598336,0.000119305936,2.8782884e-7,0.00046418587,0.0004576073],"genre_scores_gemma":[0.9846098,0.00004102948,0.015018771,0.00020407181,0.000008953641,0.000042874024,0.0000017063713,0.0000030562608,0.00006976498],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884623,0.000032785974,0.00019471293,0.0005425024,0.00012207641,0.00026166707],"domain_scores_gemma":[0.9993255,0.000071248134,0.00008156611,0.00038892456,0.00010281234,0.000029929968],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005476082,0.00009472624,0.00012662308,0.000519169,0.0004901466,0.00015022118,0.00077495875,0.00010764575,0.0000024410404],"category_scores_gemma":[0.00018017055,0.00009126846,0.000013851727,0.0036101963,0.00033532787,0.00025146484,0.00032472584,0.00041785577,0.0000028126592],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028320674,0.000027833054,0.020701542,0.0000028123013,0.0000023777777,0.0000023724072,0.000071302355,0.018717255,0.009782397,0.31735325,0.000008990554,0.633327],"study_design_scores_gemma":[0.00009680323,0.00002371468,0.0047463425,0.000010435485,0.0000018229496,0.0000039374268,0.00003513305,0.97151625,0.0020291351,0.019769983,0.0016784038,0.0000880358],"about_ca_topic_score_codex":0.0005061394,"about_ca_topic_score_gemma":0.00015546275,"teacher_disagreement_score":0.952799,"about_ca_system_score_codex":0.00005500727,"about_ca_system_score_gemma":0.000044270888,"threshold_uncertainty_score":0.3769861},"labels":[],"label_agreement":null},{"id":"W4413753506","doi":"10.1088/2632-2153/adfffd","title":"Development and application of a high-dimensional neural network potential for boron carbide","year":2025,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Nuclear Physics and Applications","field":"Physics and Astronomy","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 Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Boron carbide; Artificial neural network; Carbide; Boron; Materials science; Artificial intelligence; Computer science; Chemistry; Metallurgy; Organic chemistry","score_opus":0.002686815886740126,"score_gpt":0.2305443058831197,"score_spread":0.22785748999637956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413753506","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98207325,0.000053827996,0.01616699,0.0013120673,0.000022780301,0.00014665193,0.0000024885499,0.000025571167,0.00019638368],"genre_scores_gemma":[0.9921029,5.81912e-7,0.007749121,0.00002331337,0.000020207646,0.00004200197,0.000008671688,0.0000032035593,0.000050000053],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995251,0.0000034531722,0.00009450238,0.00018904581,0.000059937676,0.00012792746],"domain_scores_gemma":[0.9997497,0.000013641427,0.00005446792,0.00009250226,0.000072746116,0.000016893624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013428062,0.000053773416,0.00008669729,0.00008369815,0.00035306113,0.000015077736,0.00011179166,0.000020573967,0.000001841469],"category_scores_gemma":[0.0000073778633,0.00004966517,0.000008490141,0.0003864091,0.00023838885,0.00003325737,0.0001576176,0.00008871892,4.8032484e-7],"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":[0.000004969438,0.000024687517,0.012940804,0.000006934768,0.000010171439,3.5003094e-8,0.00002207989,0.001214113,0.026162267,0.5163057,0.00003674113,0.4432715],"study_design_scores_gemma":[0.0011960766,0.00013211074,0.036776755,0.0000353202,0.00005550393,0.000002364956,0.00022751011,0.68623924,0.02499604,0.2164112,0.033597663,0.00033017993],"about_ca_topic_score_codex":0.00009966079,"about_ca_topic_score_gemma":0.0000038802004,"teacher_disagreement_score":0.68502516,"about_ca_system_score_codex":0.000006417019,"about_ca_system_score_gemma":0.000050509647,"threshold_uncertainty_score":0.27154964},"labels":[],"label_agreement":null},{"id":"W4413778014","doi":"10.1088/2632-2153/adfffc","title":"Does this smell the same? Learning representations of olfactory mixtures using inductive biases","year":2025,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Olfactory and Sensory Function Studies","field":"Neuroscience","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":"Vector Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Vector Institute; Government of Ontario; Canada First Research Excellence Fund; University of Toronto; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Olfactory perception; Olfaction; Olfactory system; Psychology; Communication; Cognitive psychology; Computer science; Neuroscience","score_opus":0.08598939039221916,"score_gpt":0.318652377945101,"score_spread":0.23266298755288184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413778014","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99391496,0.00019807188,0.00017747236,0.0027492675,0.00032993202,0.00012791916,0.0000025325726,0.00016058107,0.0023392667],"genre_scores_gemma":[0.9973534,0.00008784298,0.00009148139,0.00018888596,0.000015401278,0.000006407973,2.8414135e-7,0.000005292651,0.0022510092],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99864954,0.00018207633,0.00020106985,0.00047008507,0.00024647496,0.00025072877],"domain_scores_gemma":[0.99868876,0.00072792574,0.00016585697,0.00022651596,0.00016740982,0.000023516459],"candidate_categories":["metaresearch","sts"],"consensus_categories":["sts"],"category_scores_codex":[0.00045513496,0.00012645406,0.00018897331,0.000670539,0.0019131626,0.00005524705,0.000328442,0.000077879806,0.00003903843],"category_scores_gemma":[0.008444522,0.00006863803,0.00003072989,0.0022604181,0.0031721187,0.00021068053,0.00031674266,0.0006812798,0.000003208665],"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":[0.000012515106,0.000027451,0.16079155,0.000011373171,0.000010251585,0.00000310533,0.00093764305,0.00067938835,0.8232785,0.008127405,0.000020636886,0.006100184],"study_design_scores_gemma":[0.00039942336,0.00023324457,0.02039379,0.00008618196,0.000059150167,0.000028601915,0.011168699,0.010883471,0.93477273,0.004838304,0.01684955,0.00028684505],"about_ca_topic_score_codex":0.00015904555,"about_ca_topic_score_gemma":0.000020779235,"teacher_disagreement_score":0.14039776,"about_ca_system_score_codex":0.000029804756,"about_ca_system_score_gemma":0.00009648698,"threshold_uncertainty_score":0.9999078},"labels":[],"label_agreement":null},{"id":"W4413820841","doi":"10.1088/2632-2153/ae011a","title":"32 examples of LLM applications in materials science and chemistry: towards automation, assistants, agents, and accelerated scientific discovery","year":2025,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Machine Learning in Materials Science","field":"Materials Science","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; McGill University","funders":"Material Measurement Laboratory; Office of Advanced Cyberinfrastructure","keywords":"Scientific discovery; Automation; Nanotechnology; Data science; Engineering; Computer science; Engineering ethics; Chemistry; Materials science; Mechanical engineering; Psychology; Cognitive science","score_opus":0.011508329970952164,"score_gpt":0.2825833235286461,"score_spread":0.27107499355769393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413820841","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99646795,0.0002866331,0.000695124,0.0014188378,0.00018748525,0.00034366894,0.000028703724,0.0001868387,0.00038473695],"genre_scores_gemma":[0.99702823,0.00006135142,0.0025366198,0.000044453704,0.000008597827,0.000051742616,0.000007516653,0.000009086989,0.00025241473],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9969632,0.000087285116,0.0005243355,0.001174592,0.0006638198,0.00058677077],"domain_scores_gemma":[0.9984682,0.00009815847,0.00030860925,0.0004893927,0.00054241245,0.000093224146],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":["sts"],"category_scores_codex":[0.005916823,0.0002332128,0.00040502902,0.001229794,0.0014382161,0.0013178551,0.0010572905,0.00012096827,0.00007406004],"category_scores_gemma":[0.0032575289,0.00020160878,0.000009453348,0.0054939627,0.010001151,0.0010343455,0.001201087,0.00024146315,0.000002975204],"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":[0.000007665212,0.000040003466,0.025297139,0.000104288505,0.000001440296,0.0000010445954,0.00015351395,0.000039324048,0.9620167,0.008650738,0.000011521718,0.003676631],"study_design_scores_gemma":[0.00047059395,0.000082109924,0.15054278,0.00015569506,0.000016493928,0.000027124112,0.00044759386,0.009646618,0.8302909,0.005444273,0.0025450243,0.00033076666],"about_ca_topic_score_codex":0.00042025044,"about_ca_topic_score_gemma":0.000035138335,"teacher_disagreement_score":0.13172577,"about_ca_system_score_codex":0.00012408296,"about_ca_system_score_gemma":0.0008417603,"threshold_uncertainty_score":0.9998618},"labels":[],"label_agreement":null},{"id":"W4413956711","doi":"10.1088/2632-2153/ae6416","title":"Multi-task Attention for Doped Thermoelectric Properties Prediction","year":2025,"lang":"en","type":"preprint","venue":"Machine Learning Science and Technology","topic":"Advanced Thermoelectric Materials and Devices","field":"Materials Science","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":"Army Research Office; Nanyang Technological University","keywords":"Thermoelectric effect; Task (project management); Doping; Materials science; Thermoelectric materials; Computer science; Engineering physics; Optoelectronics; Physics; Engineering; Systems engineering; Thermodynamics","score_opus":0.014399252310976923,"score_gpt":0.26489356380348583,"score_spread":0.2504943114925089,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413956711","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9770948,0.0031917363,0.015500029,0.0011118684,0.0008492903,0.0011044226,0.000058532743,0.00088028674,0.00020900069],"genre_scores_gemma":[0.9932013,0.0002817367,0.004937752,0.000055991597,0.00006542498,0.00036873703,0.000020621845,0.00001665933,0.0010517389],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99775016,0.000067077846,0.00036881797,0.0009823852,0.00029884285,0.00053272455],"domain_scores_gemma":[0.99876606,0.000044243803,0.00032813963,0.00036469742,0.00044742817,0.00004944188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001268681,0.0002894775,0.0004050464,0.00083415885,0.00084408827,0.00025095238,0.0006849795,0.0003382603,0.00002006163],"category_scores_gemma":[0.0008794167,0.00022670043,0.000043055345,0.00091259106,0.000650129,0.00019144492,0.0007516374,0.0004998791,0.000008794006],"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":[0.00003823631,0.000037748396,0.000768564,0.00021037765,0.000007962093,9.0465136e-7,0.000072498115,0.00028091425,0.97409534,0.00093757873,0.000009032209,0.023540817],"study_design_scores_gemma":[0.0011069302,0.0006511713,0.0011985761,0.00038987273,0.00011224429,0.000028947114,0.00012911989,0.2133901,0.7688782,0.0070888675,0.006350443,0.000675542],"about_ca_topic_score_codex":0.00012461931,"about_ca_topic_score_gemma":0.00001781552,"teacher_disagreement_score":0.21310918,"about_ca_system_score_codex":0.00010923136,"about_ca_system_score_gemma":0.0003274679,"threshold_uncertainty_score":0.92445755},"labels":[],"label_agreement":null},{"id":"W4414050276","doi":"10.1088/2632-2153/ae04c1","title":"High- <mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"> <mml:mrow> <mml:msub> <mml:mi>T</mml:mi> <mml:mrow> <mml:mi>c</mml:mi> </mml:mrow> </mml:msub> </mml:mrow> </mml:math> superconductor candidates proposed by machine learning","year":2025,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Superconducting Materials and Applications","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":"Vector Institute; University of Toronto","funders":"Canada First Research Excellence Fund; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Stability (learning theory); Ranking (information retrieval); Regression; Training set; Superconductivity; Regression analysis; Relation (database); Experimental data","score_opus":0.009641321875892256,"score_gpt":0.22587216928945344,"score_spread":0.2162308474135612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414050276","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92224324,0.0009981019,0.00041830222,0.0014549035,0.0010503696,0.000036540387,0.000064727676,0.000620285,0.07311352],"genre_scores_gemma":[0.9955412,0.0005695755,0.0018404473,0.00038355964,0.0003538813,0.00043502855,0.0003482472,0.00024766944,0.00028038895],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99569917,0.00013706446,0.00080358016,0.0011249685,0.00085740775,0.0013777949],"domain_scores_gemma":[0.9976676,0.0004274417,0.00041646208,0.001048344,0.00010370362,0.00033644232],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013786913,0.00045831024,0.00023654327,0.000611076,0.0016308081,0.0008029919,0.0013810323,0.0010184363,0.06613185],"category_scores_gemma":[0.0014465712,0.00075670955,0.0002927258,0.0015279945,0.0015420018,0.00087688625,0.0010466799,0.0014804142,0.00050341303],"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":[0.00016685431,0.00014569765,0.00036711764,0.00073431886,0.00046240725,0.00025045132,0.0013605236,0.0037236167,0.28646925,0.6499628,0.049634095,0.0067228805],"study_design_scores_gemma":[0.00072555715,0.00053734647,0.00007959486,0.00029456627,0.00024341869,0.00040309937,0.0011814113,0.046987552,0.9427077,0.00023334913,0.00589364,0.0007127257],"about_ca_topic_score_codex":0.0025959671,"about_ca_topic_score_gemma":0.0007615781,"teacher_disagreement_score":0.6562385,"about_ca_system_score_codex":0.000015519128,"about_ca_system_score_gemma":0.0005165315,"threshold_uncertainty_score":0.99966896},"labels":[],"label_agreement":null},{"id":"W4414141643","doi":"10.1088/2632-2153/ae054c","title":"Resolving turbulent magnetohydrodynamics: a hybrid operator-diffusion framework","year":2025,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","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 British Columbia","funders":"Oak Ridge National Laboratory; Argonne National Laboratory; University of Illinois at Urbana-Champaign; U.S. Department of Energy; Office of Science; National Science Foundation","keywords":"Turbulence; Magnetohydrodynamic drive; Range (aeronautics); Generalization; Resistive touchscreen; Diffusion; Energy (signal processing); Magnetic field","score_opus":0.0035296163500074733,"score_gpt":0.2418683785337877,"score_spread":0.23833876218378022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414141643","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97417104,0.00036638096,0.015091202,0.006865473,0.00018530949,0.00011310226,9.166045e-7,0.00017372181,0.0030328755],"genre_scores_gemma":[0.9973197,0.00003104552,0.001164986,0.0001772874,0.00004536948,0.000012886023,0.0000029654161,0.0000062830677,0.0012395057],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99899125,0.000021697484,0.00014144149,0.00039730806,0.000145683,0.0003026236],"domain_scores_gemma":[0.9995764,0.000028963916,0.000048820522,0.00020880612,0.00008720373,0.000049837785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026511628,0.000120319964,0.00013893418,0.00041244153,0.0006795132,0.00009846907,0.00027534997,0.000053986303,0.00010972799],"category_scores_gemma":[0.000071022325,0.0001038367,0.000021538133,0.0011615711,0.00044449704,0.0001061655,0.00025282067,0.0006374359,0.000008853232],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017074371,0.00009097053,0.14469266,0.000014673398,0.000019388319,0.000009528211,0.00011746957,0.002325766,0.018672299,0.4187538,0.0004410473,0.41484532],"study_design_scores_gemma":[0.00041178183,0.00013155122,0.0010825379,0.00012566552,0.000018558483,0.000020773232,0.00024655426,0.9097735,0.0043676137,0.048833203,0.034681164,0.00030708392],"about_ca_topic_score_codex":0.00007128944,"about_ca_topic_score_gemma":0.0000012189475,"teacher_disagreement_score":0.90744776,"about_ca_system_score_codex":0.000024936879,"about_ca_system_score_gemma":0.000071494454,"threshold_uncertainty_score":0.5226335},"labels":[],"label_agreement":null},{"id":"W4414625112","doi":"10.1088/2632-2153/ae11f8","title":"Generative diffusion model surrogates for mechanistic agent-based biological models","year":2025,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","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":"Perimeter Institute; TRIUMF","funders":"Advanced Scientific Computing Research; National Institute of Biomedical Imaging and Bioengineering; National Institute of General Medical Sciences","keywords":"Leverage (statistics); Surrogate model; Generative model; Probabilistic logic; Computational model; Classifier (UML); Generative grammar; Model selection","score_opus":0.01842598599032087,"score_gpt":0.25830012888499165,"score_spread":0.2398741428946708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414625112","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62813866,0.00032544087,0.37017694,0.0008942051,0.00006237773,0.00015530759,0.000008063552,0.00004901371,0.00018997089],"genre_scores_gemma":[0.990561,0.000081235616,0.008654946,0.000306097,0.000013139299,0.000039253253,0.000034917553,0.0000070345336,0.00030237748],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990575,0.000019942112,0.000123924,0.00045468437,0.000080463564,0.00026349424],"domain_scores_gemma":[0.99959093,0.000019958354,0.000039668077,0.00015359206,0.00015929053,0.000036568406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030722134,0.00012766263,0.00013785526,0.00020408042,0.00046119103,0.00003427358,0.0002504953,0.00018469046,0.0000016500213],"category_scores_gemma":[0.00032876353,0.00010339861,0.000032313477,0.00034295765,0.00050533755,0.0000049882406,0.00011831489,0.00014139018,4.4073744e-7],"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":[0.00004410825,0.000045598597,0.003240619,0.000010172695,0.000006770984,4.2653485e-7,0.000012392647,0.0073873675,0.96672964,0.016998362,0.000019887522,0.005504656],"study_design_scores_gemma":[0.0004595302,0.0003294362,0.000036147587,0.000008709713,0.0000085680385,0.0000015290053,0.000026551501,0.775078,0.21160935,0.011646439,0.00068437395,0.000111364316],"about_ca_topic_score_codex":0.0000170917,"about_ca_topic_score_gemma":0.000024234381,"teacher_disagreement_score":0.76769066,"about_ca_system_score_codex":0.000016059576,"about_ca_system_score_gemma":0.00013686105,"threshold_uncertainty_score":0.4216473},"labels":[],"label_agreement":null},{"id":"W4414673944","doi":"10.1088/2632-2153/ae0d5d","title":"Perspective on artificial intelligence for accelerated materials design (AI4Mat) workshops in 2024","year":2025,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Machine Learning in Materials Science","field":"Materials Science","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":"Government (linguistics); Field (mathematics); Domain (mathematical analysis); Generative grammar; Perspective (graphical); Grand Challenges","score_opus":0.0284836765137168,"score_gpt":0.33255537925588197,"score_spread":0.30407170274216516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414673944","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92733157,0.00022069794,0.05532992,0.01208173,0.0015950997,0.0012303455,0.000013798571,0.0005962591,0.0016005714],"genre_scores_gemma":[0.985196,0.000022908038,0.013591905,0.0002862024,0.000042243926,0.0001792774,0.0000020784014,0.000018816423,0.0006605799],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9967192,0.00023537021,0.0005553077,0.001218146,0.00042053833,0.00085144525],"domain_scores_gemma":[0.9983836,0.0004888881,0.00020242519,0.00042074168,0.00043105593,0.000073291005],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005377958,0.0003079688,0.00045201025,0.001786483,0.0008625975,0.0005950458,0.0011841925,0.00022018797,0.00033507566],"category_scores_gemma":[0.0070660287,0.00026870752,0.000024079469,0.0037639523,0.00174194,0.0003434677,0.00043637856,0.00051816134,0.00008883029],"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":[0.00017282982,0.00007308816,0.00052256393,0.000026561018,0.0000029246696,0.000008732427,0.00030134903,0.006888132,0.82698005,0.15331239,0.00006037261,0.011651005],"study_design_scores_gemma":[0.00026642648,0.000583734,0.00069973205,0.0001834964,0.000012903782,0.00001699687,0.0011168243,0.062048648,0.82900983,0.10491477,0.0007257792,0.00042084916],"about_ca_topic_score_codex":0.00024409841,"about_ca_topic_score_gemma":0.000049286005,"teacher_disagreement_score":0.05786441,"about_ca_system_score_codex":0.00033786384,"about_ca_system_score_gemma":0.0004060395,"threshold_uncertainty_score":0.9999765},"labels":[],"label_agreement":null},{"id":"W4414797459","doi":"10.1088/2632-2153/ae0f38","title":"HPGe-Compton Net: a physics-guided CNN for fast gamma spectra analysis via Compton region learning","year":2025,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Nuclear Physics and Applications","field":"Physics and Astronomy","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":"McMaster University","funders":"Mitacs","keywords":"Detector; Convolutional neural network; Semiconductor detector; Data set; Compton scattering; Feature (linguistics); Gamma spectroscopy; Artificial neural network; Radioactive waste","score_opus":0.0072778378833859994,"score_gpt":0.2664585059010178,"score_spread":0.2591806680176318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414797459","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4765004,0.00007730301,0.50517166,0.0052305153,0.00007303794,0.00046861407,0.000006291703,0.00033879516,0.012133398],"genre_scores_gemma":[0.9970704,0.0000052150594,0.0016018342,0.000053262418,0.000078125064,0.00005883477,0.00003459262,0.000014617934,0.0010831235],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985952,0.00002386425,0.0002202966,0.0005856616,0.00015946555,0.00041550957],"domain_scores_gemma":[0.9991664,0.00006105379,0.00016817915,0.00035392924,0.00019474463,0.00005567927],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027852933,0.0001892757,0.00032056877,0.00054043625,0.0011228959,0.00013269408,0.00047273553,0.00005916342,0.00002450633],"category_scores_gemma":[0.000034003744,0.00018392818,0.0001037486,0.0036608265,0.0005198331,0.00013187276,0.0002578286,0.00048634908,0.000012414461],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010850298,0.00014737557,0.20518461,0.000017200302,0.0002266857,7.1386506e-7,0.00017549089,0.0034114288,0.029049104,0.41219303,0.00025249438,0.34933102],"study_design_scores_gemma":[0.0011600322,0.00026001732,0.010778079,0.00004496186,0.00045573348,0.0000031947213,0.00066399504,0.7578405,0.015178429,0.16568914,0.047305614,0.0006202955],"about_ca_topic_score_codex":0.00024145075,"about_ca_topic_score_gemma":0.0000067658416,"teacher_disagreement_score":0.7544291,"about_ca_system_score_codex":0.000037431695,"about_ca_system_score_gemma":0.00006883167,"threshold_uncertainty_score":0.8636521},"labels":[],"label_agreement":null},{"id":"W4415449377","doi":"10.1088/2632-2153/ae1655","title":"Neural network enhanced cross entropy benchmark for monitored circuits","year":2025,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Fault Detection and Control Systems","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; Perimeter Institute; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; Institut Périmètre de physique théorique; Industry Canada; Ministry of Colleges and Universities; Courtois Foundation; Government of Canada","keywords":"Benchmark (surveying); Quantum; Generative grammar; Artificial neural network; Generative model; Entropy (arrow of time); Electronic circuit; Cross entropy","score_opus":0.0036581963398728155,"score_gpt":0.24165913645600912,"score_spread":0.2380009401161363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415449377","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9799055,0.0013077544,0.013840252,0.0005087614,0.0012918867,0.0002955298,0.000001716099,0.0009773263,0.0018712945],"genre_scores_gemma":[0.9992314,0.000019004287,0.000106502666,0.00004368851,0.00006235787,0.000076596894,0.0000013383549,0.000008505717,0.0004506029],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990832,0.000011091377,0.00015998022,0.00025271252,0.00010728027,0.00038572375],"domain_scores_gemma":[0.9996518,0.00004643384,0.000029296798,0.00014518142,0.00009104191,0.0000362442],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032001865,0.00011170804,0.00016374225,0.00028941737,0.0004706087,0.00010170985,0.00023595121,0.000108786866,0.000003988013],"category_scores_gemma":[0.0002547209,0.00010554751,0.000023656014,0.0011851019,0.00027512023,0.000096035335,0.00004733065,0.0002664843,0.0000032711705],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024820403,0.000016190885,0.056548048,0.0001116135,0.000051406896,0.0000036280542,0.00013450053,0.12045954,0.27921966,0.009687364,0.00034393824,0.5333993],"study_design_scores_gemma":[0.000798117,0.00012180583,0.0047150995,0.000030556905,0.000009919811,0.000010071094,0.00007703288,0.95212626,0.016298119,0.0015173766,0.024107885,0.00018772735],"about_ca_topic_score_codex":0.000013198385,"about_ca_topic_score_gemma":0.000008396775,"teacher_disagreement_score":0.83166677,"about_ca_system_score_codex":0.000046693647,"about_ca_system_score_gemma":0.000025135805,"threshold_uncertainty_score":0.43041024},"labels":[],"label_agreement":null},{"id":"W4415599437","doi":"10.1088/2632-2153/ae1807","title":"An atomic cluster expansion potential for twisted multilayer graphene","year":2025,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Machine Learning in Materials Science","field":"Materials Science","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 British Columbia","funders":"National Defense Science and Engineering Graduate; Directorate for Computer and Information Science and Engineering; Natural Sciences and Engineering Research Council of Canada; Flatiron Health; National Science Foundation","keywords":"Robustness (evolution); Cluster (spacecraft); Twist; Interatomic potential; Graphene; Density functional theory; Cluster expansion; Work (physics); Supercell","score_opus":0.004981621797622274,"score_gpt":0.27522330960184,"score_spread":0.2702416878042177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415599437","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9627225,0.00014165587,0.032360658,0.002706554,0.0007656512,0.00043535643,0.0000073260026,0.00068107893,0.00017925554],"genre_scores_gemma":[0.9779664,0.000012145051,0.021086877,0.00042346658,0.0000405851,0.00007530525,0.0000066330444,0.000018631976,0.00036995512],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971685,0.00013851096,0.0003831063,0.0011137078,0.00043788736,0.0007582927],"domain_scores_gemma":[0.99861395,0.00009948686,0.00018823757,0.0005809249,0.00040131147,0.000116100906],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.003006961,0.00026132318,0.00033758802,0.0011360237,0.0014591871,0.00039187926,0.001213259,0.00019908934,0.00009663242],"category_scores_gemma":[0.0013678618,0.00022284633,0.00003802701,0.0017535277,0.0018932195,0.0005507841,0.00047365832,0.0003583967,0.00003156653],"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":[0.00006076453,0.00004803051,0.0073580807,0.000032048178,0.000002337394,0.0000028835486,0.00010119757,0.0018036492,0.97480136,0.007075222,0.00004772793,0.008666694],"study_design_scores_gemma":[0.0015607997,0.0006160291,0.0066378918,0.000071278,0.000036488476,0.00006391263,0.00024857998,0.69012207,0.2827252,0.01262821,0.004774886,0.00051467185],"about_ca_topic_score_codex":0.00015287068,"about_ca_topic_score_gemma":0.000029248822,"teacher_disagreement_score":0.69207615,"about_ca_system_score_codex":0.000069317655,"about_ca_system_score_gemma":0.00022901478,"threshold_uncertainty_score":0.9998408},"labels":[],"label_agreement":null},{"id":"W4415678236","doi":"10.1088/2632-2153/ae1927","title":"MatMMFuse: Multimodal fusion model for material property prediction","year":2025,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Machine Learning in Materials Science","field":"Materials Science","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":"École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Embedding; Graph; Convolution (computer science); Encoder; Encoding (memory); Property (philosophy); ENCODE; Data modeling","score_opus":0.007586592448563075,"score_gpt":0.2597565640646196,"score_spread":0.25216997161605653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415678236","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9110839,0.00006762788,0.07945805,0.005733051,0.0011112612,0.000695316,0.000030840038,0.0010668176,0.00075317046],"genre_scores_gemma":[0.9482461,0.000015789607,0.045837987,0.00018693334,0.000069475194,0.000092702365,0.0000096329195,0.000018628592,0.005522734],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975158,0.00005754685,0.00037544366,0.00094659074,0.00043857208,0.0006660458],"domain_scores_gemma":[0.9989639,0.000058784815,0.0001642039,0.0003993032,0.00030857895,0.000105239626],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0022541082,0.00024156802,0.00029918473,0.00073688914,0.0013602509,0.00036765978,0.0008919798,0.00019625163,0.00011925449],"category_scores_gemma":[0.002060004,0.00017028856,0.000026996004,0.0012023586,0.0012442705,0.00046538786,0.00064841413,0.00029823248,0.000027705617],"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":[0.00007131928,0.00002987034,0.004528524,0.000044630124,0.0000018821127,0.0000010081343,0.0001284882,0.006812014,0.9699817,0.0060132686,0.0003323225,0.012055019],"study_design_scores_gemma":[0.0005585529,0.00019693193,0.000545208,0.000045557696,0.000014532321,0.000017839935,0.00003832769,0.84607166,0.1417869,0.0052509475,0.0052842656,0.00018928984],"about_ca_topic_score_codex":0.00023438099,"about_ca_topic_score_gemma":0.000022731332,"teacher_disagreement_score":0.8392596,"about_ca_system_score_codex":0.00010431131,"about_ca_system_score_gemma":0.0004908321,"threshold_uncertainty_score":0.99993986},"labels":[],"label_agreement":null},{"id":"W4416015605","doi":"10.1088/2632-2153/ae1d0b","title":"RydbergGPT","year":2025,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Quantum many-body systems","field":"Physics and Astronomy","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":"Perimeter Institute; University of Waterloo","funders":"Kavli Institute for Theoretical Physics, University of California, Santa Barbara; Wallenberg Center for Quantum Technology, Chalmers University of Technology; Institut Périmètre de physique théorique; Vetenskapsrådet; Knut och Alice Wallenbergs Stiftelse; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Scaling; Quantum; Qubit; Quantum computer; Hamiltonian (control theory); Transformer; Lattice (music); Generative grammar","score_opus":0.0027272678955293293,"score_gpt":0.24176927764809544,"score_spread":0.23904200975256612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416015605","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95036805,0.00018924105,0.0021420878,0.0036091725,0.00018969252,0.000096136784,0.0000010394637,0.00020478872,0.04319982],"genre_scores_gemma":[0.99694496,0.0000012903388,0.0001504605,0.000042016174,0.000022758299,0.000012289155,0.0000011022994,0.0000039886177,0.002821109],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99920875,0.000014981825,0.00011229473,0.0002866738,0.00012089888,0.00025641854],"domain_scores_gemma":[0.99962646,0.000024296303,0.000046679437,0.00018981587,0.0000848372,0.0000279381],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039248104,0.000084325235,0.00012289181,0.0004925382,0.00043093966,0.00006387737,0.0003015744,0.000036793223,0.000047064375],"category_scores_gemma":[0.000079998514,0.000073314826,0.000013308837,0.0015625068,0.0005992758,0.0000937477,0.00021174068,0.0002863905,0.000034489993],"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":[8.1634073e-7,0.000011277335,0.37397102,0.000003991104,0.000005912501,7.243783e-7,0.000034319473,0.000008412904,0.0050976323,0.57425267,0.000096650256,0.04651657],"study_design_scores_gemma":[0.0017200633,0.00036569932,0.03603152,0.00017792622,0.000055997283,0.00002168426,0.0031285302,0.2217104,0.029504422,0.1781538,0.5282491,0.0008808531],"about_ca_topic_score_codex":0.00024795323,"about_ca_topic_score_gemma":0.0000046543228,"teacher_disagreement_score":0.52815247,"about_ca_system_score_codex":0.00001627884,"about_ca_system_score_gemma":0.00009346825,"threshold_uncertainty_score":0.3314483},"labels":[],"label_agreement":null},{"id":"W4416163443","doi":"10.1088/2632-2153/ae1f05","title":"Towards instance-wise calibration: local amortized diagnostics and reshaping of conditional densities (LADaR)","year":2025,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Galaxies: Formation, Evolution, Phenomena","field":"Physics and Astronomy","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 Toronto","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico; Fundação de Amparo à Pesquisa do Estado de São Paulo; U.S. Department of Energy; Office of Science; Division of Mathematical Sciences; National Science Foundation","keywords":"Python (programming language); Probabilistic logic; Benchmark (surveying); Probability density function; Conditional probability distribution; Calibration; Key (lock); Density estimation; Feature (linguistics)","score_opus":0.004579382784567398,"score_gpt":0.2234420570774178,"score_spread":0.2188626742928504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416163443","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9843898,0.00041087676,0.013182243,0.0013047075,0.000049300823,0.00008448066,0.000009031976,0.000058258378,0.0005113424],"genre_scores_gemma":[0.9992136,0.000019958425,0.0006069393,0.00001600564,0.000014782279,0.000011622884,0.000017856271,0.0000034508482,0.00009578327],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99924755,0.00001952535,0.0002041636,0.00018812434,0.00016823078,0.00017239973],"domain_scores_gemma":[0.9995028,0.000053720054,0.00010588397,0.00010316408,0.0002045109,0.000029954406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002623944,0.00008946928,0.00014943896,0.00035408683,0.0004444434,0.000042261887,0.00012374372,0.000041056464,0.00003080431],"category_scores_gemma":[0.00015129326,0.000086326276,0.000011927654,0.0007349403,0.001723036,0.00025808054,0.00014214842,0.00019167345,8.669853e-7],"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":[0.0000034463303,0.000010377785,0.7603223,0.00001153076,0.0000074908307,2.9187515e-8,0.00015715172,0.0000606268,0.0002328918,0.23738213,0.00004435232,0.0017676892],"study_design_scores_gemma":[0.00051605963,0.00007169228,0.8721498,0.00004657515,0.000016841223,0.000003866664,0.0014565851,0.054603443,0.0023665158,0.067823395,0.0008196168,0.00012556216],"about_ca_topic_score_codex":0.00012672436,"about_ca_topic_score_gemma":0.000018966344,"teacher_disagreement_score":0.16955873,"about_ca_system_score_codex":0.00003136247,"about_ca_system_score_gemma":0.000231078,"threshold_uncertainty_score":0.6348598},"labels":[],"label_agreement":null}]}