{"meta":{"query_hash":"3de55248b53f","filters":{"topic":"Text and Document Classification Technologies"},"cohort_total":374,"direct_labels_cover":2,"predictions_cover":374,"exported":374,"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/3de55248b53f","api":"https://metacan.xera.ac/api/v1/cohort?topic=Text+and+Document+Classification+Technologies"},"results":[{"id":"W1035981622","doi":"10.1007/978-3-642-40846-5_43","title":"MLG: Enchancing Multi-label Classification with Modularity-Based Label Grouping","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ducks Unlimited Canada","funders":"","keywords":"Computer science; Multi-label classification; Modularity (biology); Relevance (law); Binary number; Data mining; Graph; Artificial intelligence; Pattern recognition (psychology); Binary classification; Machine learning; Theoretical computer science; Support vector machine; Mathematics","score_opus":0.04651001208176469,"score_gpt":0.2663176553733737,"score_spread":0.219807643291609,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1035981622","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00025198492,0.00030445555,0.9941186,0.002443212,0.00062368327,0.0006925441,0.0000029408884,0.00082798867,0.0007345936],"genre_scores_gemma":[0.16422379,0.000025094223,0.83415693,0.0009805586,0.000103829385,0.000060713846,0.000010765248,0.00003869068,0.0003996399],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99561423,0.000037202517,0.0005928924,0.0019199547,0.0010867264,0.0007490213],"domain_scores_gemma":[0.9964557,0.00030848687,0.000553778,0.0020981207,0.00042949483,0.00015436845],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006586224,0.0006343089,0.0005182157,0.0011610577,0.0004372124,0.0010489929,0.0038077051,0.0004800614,0.000019812698],"category_scores_gemma":[0.000101643855,0.00053569797,0.00006969118,0.0009849083,0.0008846429,0.0012791103,0.00078729924,0.0009864664,0.00011452021],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004624595,0.00010074528,0.0001412026,0.00005752506,0.000012210033,0.00001941032,0.00026473548,0.0025133132,0.002262351,0.08017732,0.00002272678,0.9144238],"study_design_scores_gemma":[0.0007017969,0.00018608055,0.00033892915,0.0003759676,0.000008430133,0.000014301344,7.600787e-7,0.9580389,0.0034102143,0.03572877,0.00046887065,0.0007269608],"about_ca_topic_score_codex":0.000037628368,"about_ca_topic_score_gemma":0.00006925513,"teacher_disagreement_score":0.9555256,"about_ca_system_score_codex":0.00048039245,"about_ca_system_score_gemma":0.0005798036,"threshold_uncertainty_score":0.999988},"labels":[],"label_agreement":null},{"id":"W123190706","doi":"","title":"Topic Classification of Blog Posts Using Distant Supervision","year":2012,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Blogosphere; Computer science; Classifier (UML); Vocabulary; Binary classification; Artificial intelligence; Class (philosophy); Information retrieval; Sample (material); Natural language processing; Data science; World Wide Web; Support vector machine; The Internet","score_opus":0.06051903039669124,"score_gpt":0.3021238606092946,"score_spread":0.24160483021260334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W123190706","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":[0.56919134,0.0001691481,0.4260618,0.00091810623,0.0002399469,0.00008093791,4.5329668e-7,0.00024256912,0.0030957065],"genre_scores_gemma":[0.96397257,0.000012124262,0.035800736,0.000030640345,0.00001570162,0.000002727528,0.0000014379513,0.0000024685753,0.00016159788],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.999363,0.000019107247,0.00018263688,0.00013150205,0.00015124137,0.00015247907],"domain_scores_gemma":[0.99933267,0.000030575768,0.00007622258,0.00047757514,0.00004822045,0.000034735134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014528465,0.000060819355,0.000075867276,0.00008566248,0.00004692284,0.000031136835,0.0004132775,0.00005199353,0.000036045407],"category_scores_gemma":[0.000022795459,0.00004759428,0.000030285337,0.0002379992,0.00003813648,0.0005876655,0.00013485264,0.00004072651,0.000020562466],"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":[0.0000010033891,0.000068580084,0.025625352,0.0000067587116,0.0000030210251,8.6465384e-8,0.00017074124,6.797654e-7,0.103093974,0.8364867,0.000109579276,0.034433536],"study_design_scores_gemma":[0.0004947448,0.00012471511,0.5008795,0.000038136728,0.000017059578,0.000013018477,0.0012154365,0.05846018,0.39893293,0.029153075,0.010192556,0.00047861008],"about_ca_topic_score_codex":0.00001546881,"about_ca_topic_score_gemma":0.0000010895054,"teacher_disagreement_score":0.8073336,"about_ca_system_score_codex":0.0000308754,"about_ca_system_score_gemma":0.000015441203,"threshold_uncertainty_score":0.19408384},"labels":[],"label_agreement":null},{"id":"W129830436","doi":"10.1007/978-3-642-21402-8_23","title":"Naive Bayesian Classifier Based on the Improved Feature Weighting Algorithm","year":2011,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nipissing University","funders":"","keywords":"Weighting; Computer science; Naive Bayes classifier; Feature (linguistics); Classifier (UML); Text categorization; Artificial intelligence; Search engine indexing; Bayesian probability; Data mining; Categorization; Information retrieval; Machine learning; Pattern recognition (psychology); Support vector machine","score_opus":0.036231446674629415,"score_gpt":0.26089570440606147,"score_spread":0.22466425773143206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W129830436","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000027417782,0.000080482576,0.7194123,0.011211149,0.00020428468,0.000433782,0.000008131448,0.00022092332,0.26842618],"genre_scores_gemma":[0.09254213,0.0018011146,0.88390946,0.011775487,0.00008016842,0.00030373465,0.00008980077,0.000037532507,0.009460562],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998368,0.00004660796,0.0005114738,0.00036082024,0.00044017303,0.0002728765],"domain_scores_gemma":[0.9952272,0.0004841798,0.00047870114,0.0033947292,0.00033881312,0.0000763683],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0011313672,0.00027982253,0.00021456818,0.00091882795,0.00083388784,0.0008662243,0.0055482495,0.00022258684,0.00003102172],"category_scores_gemma":[0.00009427998,0.00020565477,0.00006582181,0.0005706344,0.0011156608,0.0035944816,0.0018432112,0.00080458843,0.000074885145],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.974012e-7,0.000009449984,0.0000062738877,0.000004150764,0.0000025667882,1.2642698e-7,0.00033301403,0.0000033225192,0.0000024335989,0.712882,0.0007507562,0.28600505],"study_design_scores_gemma":[0.00014282728,0.000067824694,0.00025522636,0.00014009164,0.000003359053,0.0000036393697,0.000032661108,0.82160646,0.000075750075,0.033330716,0.1440541,0.0002873792],"about_ca_topic_score_codex":0.0000062776608,"about_ca_topic_score_gemma":0.0000028645757,"teacher_disagreement_score":0.8216031,"about_ca_system_score_codex":0.00014547782,"about_ca_system_score_gemma":0.00028089964,"threshold_uncertainty_score":0.9998322},"labels":[],"label_agreement":null},{"id":"W142320376","doi":"","title":"NTCIR-7 Patent Mining Experiments at RALI","year":2008,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","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":"Computer science; Task (project management); Class (philosophy); Set (abstract data type); Information retrieval; Focus (optics); Bridge (graph theory); Code (set theory); Test (biology); Natural language processing; Data science; Artificial intelligence; Programming language; Engineering","score_opus":0.14456748463194688,"score_gpt":0.27666719370641846,"score_spread":0.13209970907447158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W142320376","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":[0.8044219,0.0002681292,0.15939787,0.0033447118,0.0003980243,0.00015067225,3.949072e-7,0.0020780535,0.029940221],"genre_scores_gemma":[0.9479843,0.000031945667,0.037576932,0.0002478433,0.000007267209,0.00002232937,0.0000011273386,0.0000033035753,0.014124979],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992837,0.00001058063,0.00013067994,0.00023421612,0.00017344658,0.00016738198],"domain_scores_gemma":[0.9994302,0.0000177798,0.000044160395,0.00044853298,0.000020359297,0.000039013426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000039282328,0.00007544071,0.000071136295,0.00006205488,0.0001681219,0.000037454723,0.0005642133,0.000038504484,0.0001457175],"category_scores_gemma":[0.000011392105,0.000060877708,0.000032009837,0.00015948288,0.00005132634,0.00030178053,0.00036350067,0.000029481589,0.00034282112],"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":[0.000015374406,0.00041845985,0.10380643,0.000010700758,0.000057709258,0.00011903734,0.007284229,0.0000150269025,0.046580948,0.37478667,0.3016969,0.16520852],"study_design_scores_gemma":[0.0010455444,0.00015693752,0.03714575,0.0000117960035,0.0000027979097,0.00008141235,0.0006180483,0.0064926934,0.7563683,0.002119443,0.19534704,0.0006102456],"about_ca_topic_score_codex":0.0000114785025,"about_ca_topic_score_gemma":0.000001067386,"teacher_disagreement_score":0.70978737,"about_ca_system_score_codex":0.00004929178,"about_ca_system_score_gemma":0.000012887822,"threshold_uncertainty_score":0.44063863},"labels":[],"label_agreement":null},{"id":"W142552274","doi":"10.1007/978-3-642-41062-8_19","title":"Text Categorization via Similarity Search","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Artificial intelligence; Similarity (geometry); Cluster analysis; Categorization; Centroid; Outlier; Preprocessor; Metric (unit); Similarity measure; Point (geometry); Text categorization; Class (philosophy); Pattern recognition (psychology); Mathematics","score_opus":0.024038456127953765,"score_gpt":0.25591752152998387,"score_spread":0.2318790654020301,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W142552274","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":[0.000042538963,0.00019864297,0.98917234,0.0030350648,0.00094876357,0.0004531645,0.0000018080133,0.0005780847,0.0055695903],"genre_scores_gemma":[0.5316405,0.00012648889,0.46379724,0.0013267938,0.0003308123,0.0000334855,0.000017379789,0.000046595702,0.002680672],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964583,0.000029224124,0.00046176685,0.0014230822,0.0010207848,0.0006068524],"domain_scores_gemma":[0.997292,0.00024761676,0.00022031736,0.0017624092,0.00034777666,0.00012987244],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00058267807,0.00043029926,0.00037395378,0.000964564,0.0002974456,0.000905687,0.004214925,0.00045253447,0.00011646562],"category_scores_gemma":[0.000074995776,0.00038535832,0.00008996726,0.00084644335,0.0007790233,0.0011361979,0.001661406,0.00085057406,0.00043439123],"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":[9.734097e-7,0.000020376914,0.00005445812,0.000017885312,0.000004758585,0.000009738154,0.00022579357,0.0026774788,0.00033078776,0.12924643,0.00009233466,0.867319],"study_design_scores_gemma":[0.00015984883,0.00011100998,0.00035361477,0.000071749404,0.0000038846797,0.00002078606,2.4488017e-7,0.5153852,0.0065769083,0.4734844,0.0032191963,0.0006131771],"about_ca_topic_score_codex":0.000044747987,"about_ca_topic_score_gemma":0.00002325588,"teacher_disagreement_score":0.86670583,"about_ca_system_score_codex":0.00033643123,"about_ca_system_score_gemma":0.00038615867,"threshold_uncertainty_score":0.9998598},"labels":[],"label_agreement":null},{"id":"W1482760454","doi":"10.5555/1793274.1793346","title":"Methods for augmenting semantic models with structural information for text classification","year":2008,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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 Waterloo","funders":"","keywords":"Computer science; Natural language processing; ENCODE; Artificial intelligence; Semantics (computer science); Representation (politics); Feature (linguistics); Word (group theory); Syntactic structure; Information retrieval; Syntax; Linguistics","score_opus":0.07300728272857057,"score_gpt":0.3366887500066414,"score_spread":0.26368146727807085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1482760454","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032960468,0.000017783399,0.9925744,0.0015912974,0.000088242276,0.00072267134,0.0000017911395,0.00058952713,0.0011182764],"genre_scores_gemma":[0.41039413,0.0000038156095,0.5890509,0.00008198419,0.000007901355,0.00019435261,0.000013060193,0.0000032823982,0.0002505624],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921113,0.000016153263,0.00025909013,0.00019849931,0.00011515382,0.00019998949],"domain_scores_gemma":[0.99906963,0.00015771782,0.00017930742,0.00036681056,0.00019829477,0.000028216742],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023791219,0.000106341795,0.000113102615,0.00014463816,0.00031632243,0.00014418113,0.00045263182,0.00006017979,0.0000031600623],"category_scores_gemma":[0.00006208334,0.000078349934,0.000046036865,0.00023862264,0.000049217622,0.002744498,0.00005491797,0.00004306384,0.000004640705],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001089391,0.000006196607,0.00007371762,0.000022979177,0.000010399854,2.4887237e-8,0.0004090248,0.00023713884,0.0007007345,0.73625606,0.0005912669,0.2616816],"study_design_scores_gemma":[0.00047834855,0.000087059714,0.00096316246,0.0000048700176,0.0000061265996,0.000007894764,0.00019919894,0.9308286,0.008926954,0.053717446,0.0046368064,0.0001435836],"about_ca_topic_score_codex":0.000004107605,"about_ca_topic_score_gemma":0.0000012940169,"teacher_disagreement_score":0.9305914,"about_ca_system_score_codex":0.000038950904,"about_ca_system_score_gemma":0.000049969094,"threshold_uncertainty_score":0.31950176},"labels":[],"label_agreement":null},{"id":"W1489199265","doi":"10.1007/11758532_30","title":"An Adaptive Fuzzy kNN Text Classifier","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nipissing University","funders":"Beijing Jiaotong University","keywords":"Computer science; Categorization; Artificial intelligence; Text categorization; Feature selection; Classifier (UML); Selection (genetic algorithm); Machine learning; Dimension (graph theory); Data mining; Pattern recognition (psychology); Mathematics","score_opus":0.023312524362474062,"score_gpt":0.2540993049945257,"score_spread":0.23078678063205166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1489199265","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":[0.0000421766,0.00028143247,0.9694626,0.0013118846,0.0011443177,0.00037406478,0.0000064575274,0.00084989646,0.026527207],"genre_scores_gemma":[0.5026529,0.000043194024,0.4925703,0.0012232865,0.00051624567,0.0000313978,0.000015420062,0.00005695195,0.0028903338],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9954786,0.000037787708,0.0005936783,0.0020356493,0.0010885664,0.00076575414],"domain_scores_gemma":[0.9963507,0.0002684005,0.00039532714,0.002551679,0.00026845446,0.00016541906],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00056959316,0.00063172646,0.00052511,0.0012058673,0.00033657093,0.0009380479,0.005745717,0.000577151,0.000031602405],"category_scores_gemma":[0.000044373894,0.0005654111,0.00014100461,0.00085012,0.0012471572,0.00141952,0.0011240406,0.0009634643,0.00016801969],"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":[0.0000049649743,0.000047968566,0.00004471526,0.000008078979,0.000006588897,0.000039357008,0.00014778001,0.0035563393,0.00021033955,0.26889744,0.0003796597,0.72665673],"study_design_scores_gemma":[0.00032712365,0.0005323384,0.0006482145,0.00016848264,0.000009801549,0.00004037297,7.996302e-7,0.3007243,0.0027240878,0.6832099,0.010389821,0.0012247985],"about_ca_topic_score_codex":0.000033133318,"about_ca_topic_score_gemma":0.000075230724,"teacher_disagreement_score":0.725432,"about_ca_system_score_codex":0.00039601422,"about_ca_system_score_gemma":0.0004980288,"threshold_uncertainty_score":0.99967974},"labels":[],"label_agreement":null},{"id":"W1502037483","doi":"","title":"Spectral Learning with Type-2 Fuzzy Numbers for Question/Answering System.","year":2009,"lang":"en","type":"article","venue":"European Society for Fuzzy Logic and Technology Conference","topic":"Text and Document Classification Technologies","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":"Computer science; Artificial intelligence; Semi-supervised learning; Graph; Fuzzy number; Fuzzy logic; Machine learning; Theoretical computer science; Pattern recognition (psychology); Mathematics; Fuzzy set","score_opus":0.01910307234349519,"score_gpt":0.24663209151925072,"score_spread":0.22752901917575552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1502037483","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":[0.021991814,0.0005340297,0.9335032,0.011116821,0.00017653416,0.00082904147,0.0000046537225,0.004910895,0.02693297],"genre_scores_gemma":[0.866315,0.00010317707,0.1327823,0.00011936587,0.000029957857,0.000029130617,0.000007683174,0.000011749172,0.00060165074],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99873585,0.000026333399,0.0002152481,0.0005421633,0.00010246742,0.00037792258],"domain_scores_gemma":[0.9991411,0.000057107216,0.00016224288,0.0003762101,0.00021429066,0.00004904895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035328025,0.00020583822,0.00022097243,0.00008481843,0.000418917,0.00016845828,0.0006940478,0.00014604635,0.0000011141949],"category_scores_gemma":[0.00008458067,0.00016995048,0.00008672772,0.00042986713,0.0002677432,0.00024187658,0.00011972445,0.00026421234,0.000011050754],"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":[0.000009791329,0.000019489866,0.00041328362,0.000031152842,0.000025882116,0.0000029074224,0.00016004153,0.000009153205,0.0013999266,0.9581269,0.0005167923,0.039284687],"study_design_scores_gemma":[0.007753285,0.011415775,0.010448917,0.00077545596,0.0002680634,0.0004724907,0.019153161,0.026117805,0.0097309025,0.7717714,0.13858825,0.0035045194],"about_ca_topic_score_codex":0.0000012980327,"about_ca_topic_score_gemma":8.5021446e-7,"teacher_disagreement_score":0.84432316,"about_ca_system_score_codex":0.000047782705,"about_ca_system_score_gemma":0.000049823382,"threshold_uncertainty_score":0.6930379},"labels":[],"label_agreement":null},{"id":"W1507852567","doi":"10.1007/11425274_17","title":"Evaluation of Two Systems on Multi-class Multi-label Document Classification","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Document classification; Classifier (UML); Search engine indexing; Artificial intelligence; Class (philosophy); Multi-label classification; Pattern recognition (psychology); Data mining; Information retrieval; Natural language processing; Machine learning","score_opus":0.09346704776640828,"score_gpt":0.3400993522796007,"score_spread":0.2466323045131924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1507852567","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":[0.000230999,0.00085725234,0.9931389,0.0010293813,0.0016362814,0.0011777512,0.000006194378,0.00034329316,0.001579909],"genre_scores_gemma":[0.6168596,0.000106787134,0.38173616,0.0002489346,0.00020867724,0.00010687532,0.000011954424,0.000036771267,0.00068423967],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99388915,0.0001382852,0.00095205434,0.0016408975,0.002866146,0.0005134528],"domain_scores_gemma":[0.9952969,0.00033086378,0.0009371681,0.0022116636,0.0011135845,0.000109845074],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0034578533,0.0005449155,0.00055090437,0.0013426576,0.00020381996,0.0004811847,0.0033939786,0.00038960838,0.000016482965],"category_scores_gemma":[0.00026576046,0.00048754094,0.00010949959,0.00070525554,0.0006469667,0.0007795533,0.00067725225,0.00063818274,0.00010301708],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031725895,0.00013465964,0.000021159509,0.000023164395,0.000016907034,0.0000020190425,0.0002239848,0.04238051,0.00079641416,0.10742627,0.000017779803,0.84895396],"study_design_scores_gemma":[0.0013217322,0.00016148234,0.00021189613,0.00032784944,0.000030223278,0.000007399385,0.0000010833583,0.9738369,0.0029646417,0.020092726,0.0005623599,0.0004816847],"about_ca_topic_score_codex":0.000025891926,"about_ca_topic_score_gemma":0.000059965303,"teacher_disagreement_score":0.9314564,"about_ca_system_score_codex":0.001262763,"about_ca_system_score_gemma":0.00073909975,"threshold_uncertainty_score":0.99975765},"labels":[],"label_agreement":null},{"id":"W1520586504","doi":"10.1007/11424918_39","title":"Vocabulary Completion Through Word Cooccurrence Analysis Using Unlabeled Documents for Text Categorization","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Vocabulary; Text categorization; Categorization; Classifier (UML); Natural language processing; Artificial intelligence; Word (group theory); Vocabulary learning; Set (abstract data type); Training set; Information retrieval; Machine learning; Linguistics","score_opus":0.03748189831121202,"score_gpt":0.29811954903343774,"score_spread":0.2606376507222257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1520586504","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00025042347,0.0004760619,0.99613464,0.0006975381,0.0009009319,0.00075833075,0.000014485801,0.00040146074,0.00036615162],"genre_scores_gemma":[0.31445786,0.00011494668,0.6840863,0.0006115709,0.0002498031,0.00003769882,0.000085432854,0.000029941444,0.0003264346],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99586064,0.000034867735,0.00075897784,0.0017370068,0.0009494122,0.000659105],"domain_scores_gemma":[0.99692845,0.00034531576,0.00066695904,0.0015234709,0.00044500385,0.00009079496],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006054264,0.0005563241,0.00069481705,0.001440697,0.00047175464,0.000818237,0.0031645284,0.0003891087,0.000032822234],"category_scores_gemma":[0.00010199514,0.000538685,0.00023057089,0.0024104444,0.0005994625,0.0015815601,0.0008494482,0.0004571301,0.000023531897],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014379411,0.00008063058,0.00054549135,0.00005341673,0.00012397111,0.000007814587,0.00074010063,0.10687221,0.0005435824,0.12111185,0.000063028485,0.7698435],"study_design_scores_gemma":[0.00038974785,0.00009590799,0.0003086821,0.00011382643,0.0001098885,0.0000084803805,5.577513e-7,0.85566235,0.0016465446,0.13738708,0.0035413862,0.00073553674],"about_ca_topic_score_codex":0.000030345413,"about_ca_topic_score_gemma":0.000057366484,"teacher_disagreement_score":0.769108,"about_ca_system_score_codex":0.00060664356,"about_ca_system_score_gemma":0.00037640065,"threshold_uncertainty_score":0.99970645},"labels":[],"label_agreement":null},{"id":"W1523209510","doi":"10.1007/978-3-642-01347-8_28","title":"Enhancing Text Clustering Performance Using Semantic Similarity","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in business information processing","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"WordNet; Semantic similarity; Computer science; Cluster analysis; Vector space model; Natural language processing; Explicit semantic analysis; Document clustering; Information retrieval; Artificial intelligence; Ambiguity; Similarity (geometry); Ontology; Semantic computing; Probabilistic latent semantic analysis; Semantic technology; Semantic Web; Image (mathematics)","score_opus":0.020265127446488226,"score_gpt":0.2444281122522229,"score_spread":0.22416298480573468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1523209510","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":[0.00037823664,0.0004814097,0.9837454,0.0010202271,0.0002953543,0.0003218594,0.0000017459159,0.0006829306,0.013072855],"genre_scores_gemma":[0.8751344,0.00035460744,0.122219235,0.0012840459,0.00015640269,0.000017505621,0.00006415505,0.00004692777,0.0007226891],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976503,0.000011259408,0.0009821984,0.000404291,0.00052724994,0.00042468891],"domain_scores_gemma":[0.99789107,0.000069196365,0.0009022757,0.0006414788,0.00045120087,0.000044805478],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00032397723,0.00050125056,0.00046590052,0.0010098899,0.00035970367,0.00091615197,0.0010026132,0.0006203901,0.000022612132],"category_scores_gemma":[0.00021659357,0.0004892764,0.0000655441,0.0006466381,0.00009460126,0.0055776294,0.000353931,0.00070502056,0.000038228136],"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":[0.000007870526,0.000008980331,0.00005408114,0.0007989251,0.0000061227615,0.0000031163645,0.0005905654,0.019502798,0.00011786652,0.0028304383,0.000004576607,0.97607464],"study_design_scores_gemma":[0.00065642974,0.000047245867,0.001296923,0.004754464,0.000041322066,0.00008949819,0.000022109429,0.9349735,0.0063909786,0.03217252,0.017833272,0.0017217476],"about_ca_topic_score_codex":0.000008721501,"about_ca_topic_score_gemma":0.000029256214,"teacher_disagreement_score":0.9743529,"about_ca_system_score_codex":0.00034854058,"about_ca_system_score_gemma":0.00032954756,"threshold_uncertainty_score":0.99975586},"labels":[],"label_agreement":null},{"id":"W1524205027","doi":"","title":"Dominant meanings classification model for web information","year":2003,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"Université de Montréal","funders":"","keywords":"Computer science; Hierarchy; Context (archaeology); Domain (mathematical analysis); Set (abstract data type); Task (project management); Information retrieval; Artificial intelligence; Meaning (existential); Word (group theory); Naive Bayes classifier; Natural language processing; Mathematics; Support vector machine","score_opus":0.035331896340517456,"score_gpt":0.2603957226477704,"score_spread":0.22506382630725294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1524205027","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":[0.000947898,0.000008426298,0.98058945,0.00210986,0.000103936974,0.00025046765,0.0000012326495,0.00045251191,0.015536188],"genre_scores_gemma":[0.7829976,0.0000082955985,0.21559806,0.00023506612,0.0000031211327,0.00011040786,0.0000041422213,0.0000023268394,0.0010409454],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993523,0.000009128539,0.00021447534,0.00014651126,0.0001289088,0.0001487124],"domain_scores_gemma":[0.9993218,0.000037511,0.00010956106,0.0003906828,0.000112705326,0.000027741382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024175819,0.000075401236,0.00006861997,0.00012456052,0.00010908887,0.000171859,0.0004021691,0.00006313121,0.000007379941],"category_scores_gemma":[0.00015323864,0.000062312545,0.00003742539,0.0002053967,0.00002310866,0.0017436529,0.00003352535,0.000039726387,0.00007502632],"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":[0.0000012538958,0.000010360621,0.0000291279,0.000004066945,0.0000016780114,1.1238741e-8,0.0001527913,0.000054991284,0.003388695,0.9712806,0.00576472,0.019311713],"study_design_scores_gemma":[0.00027096173,0.000019004454,0.00014355809,0.0000018810031,0.0000019060972,0.0000010411972,0.00013080866,0.8743299,0.010226262,0.060640275,0.054135613,0.00009877508],"about_ca_topic_score_codex":7.8527705e-7,"about_ca_topic_score_gemma":0.0000011952671,"teacher_disagreement_score":0.9106403,"about_ca_system_score_codex":0.000040586983,"about_ca_system_score_gemma":0.00007194188,"threshold_uncertainty_score":0.25410318},"labels":[],"label_agreement":null},{"id":"W1524564918","doi":"10.1007/978-3-642-01818-3_35","title":"An Empirical Study of Category Skew on Feature Selection for Text Categorization","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Skew; Categorical variable; Feature selection; Computer science; Categorization; Text categorization; Selection (genetic algorithm); Feature (linguistics); Measure (data warehouse); Artificial intelligence; Pattern recognition (psychology); Data mining; Machine learning","score_opus":0.026645668405953876,"score_gpt":0.3034475151411274,"score_spread":0.2768018467351735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1524564918","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":[0.0013180287,0.00006126484,0.99525535,0.0010165235,0.0005331772,0.0009945788,0.000002278807,0.00035688028,0.0004619096],"genre_scores_gemma":[0.8961018,0.000012601439,0.10275536,0.0004921725,0.00019277007,0.000033325014,0.000013350207,0.000023710723,0.00037496278],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99705553,0.000039921953,0.00043481844,0.0013487454,0.00074294675,0.00037806603],"domain_scores_gemma":[0.9977625,0.00023069845,0.0003989752,0.0011665126,0.00035866597,0.000082621016],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00048474054,0.00040249206,0.00043852234,0.0010825439,0.00024959922,0.00031511046,0.0023751108,0.0004179574,0.0000042930956],"category_scores_gemma":[0.0000724123,0.00034927597,0.00008134804,0.0008728459,0.0002250867,0.00059970695,0.00020407063,0.000542177,0.0000057830334],"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":[0.000023853341,0.00040784373,0.00046884405,0.000022848935,0.000009852979,0.0000031416732,0.0013826607,0.011438462,0.00043571196,0.035273124,0.00013919086,0.95039445],"study_design_scores_gemma":[0.0012596746,0.009320344,0.0055192243,0.00015352093,0.00003248804,0.00002182687,0.0000066403213,0.495672,0.011030472,0.4731877,0.0025588043,0.001237296],"about_ca_topic_score_codex":0.000013663968,"about_ca_topic_score_gemma":0.00008386292,"teacher_disagreement_score":0.9491572,"about_ca_system_score_codex":0.00025535034,"about_ca_system_score_gemma":0.000315178,"threshold_uncertainty_score":0.99989593},"labels":[],"label_agreement":null},{"id":"W1525194303","doi":"10.1007/11562382_11","title":"Filtering Contents with Bigrams and Named Entities to Improve Text Classification","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Bigram; Computer science; Information retrieval; Call for bids; Window (computing); Artificial intelligence; Measure (data warehouse); Natural language processing; Data mining; World Wide Web; Trigram","score_opus":0.022896628920236126,"score_gpt":0.2413735191497738,"score_spread":0.2184768902295377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1525194303","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":[0.0009618523,0.00022213953,0.9926618,0.003229161,0.0005109177,0.00049306237,0.000004351512,0.00037420823,0.0015425055],"genre_scores_gemma":[0.65890855,0.000082267616,0.3381351,0.0009865506,0.00015893433,0.000050020368,0.0000042361876,0.000027613676,0.0016467561],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971776,0.00001271203,0.00037478583,0.0013293833,0.0006413484,0.00046416948],"domain_scores_gemma":[0.99811536,0.00015272833,0.00024404697,0.0011654786,0.00018354747,0.00013885803],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027867188,0.0004030032,0.0003527395,0.0007908057,0.00021436498,0.0009153111,0.0019972464,0.0002166293,0.000010357781],"category_scores_gemma":[0.000059319507,0.00033094926,0.00004392147,0.00044221166,0.0006513168,0.0007698623,0.00096813944,0.00040980702,0.000034874],"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":[0.0000066741873,0.000014511452,0.0001090537,0.000019972358,0.000007935797,0.0000072728117,0.00046676488,0.00031214382,0.0020334679,0.03507657,0.000018560031,0.96192706],"study_design_scores_gemma":[0.0029696496,0.0029897792,0.011859076,0.002722674,0.000063567706,0.0002637852,0.00002636486,0.64075977,0.059422817,0.21458702,0.05841686,0.005918653],"about_ca_topic_score_codex":0.0000163431,"about_ca_topic_score_gemma":0.000078938625,"teacher_disagreement_score":0.95600843,"about_ca_system_score_codex":0.00022000552,"about_ca_system_score_gemma":0.00013057193,"threshold_uncertainty_score":0.9999142},"labels":[],"label_agreement":null},{"id":"W1528447234","doi":"10.1145/563932.563930","title":"Classifying text documents by associating terms with text categories","year":2002,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":111,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Categorization; Computer science; Text categorization; Association rule learning; Classifier (UML); Artificial intelligence; Text mining; Natural language processing; Information retrieval; Machine learning; Data mining","score_opus":0.018336211844475054,"score_gpt":0.22870159268345128,"score_spread":0.2103653808389762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1528447234","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":[0.018298164,0.00074910244,0.53613126,0.02432651,0.0005643612,0.0005728456,0.0000055256023,0.0055463878,0.41380584],"genre_scores_gemma":[0.9279951,0.00004348593,0.017785216,0.0003907546,0.00001834653,0.000043319378,0.0000030466526,0.000012548673,0.053708185],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984573,0.000029472589,0.00025689893,0.00045200216,0.00039942266,0.0004049177],"domain_scores_gemma":[0.99900705,0.00009326028,0.0001914114,0.00058976054,0.00005150447,0.00006704285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013177504,0.00019293629,0.00017275718,0.000106718595,0.00024443647,0.00061528344,0.0009792477,0.00009982859,0.0002400485],"category_scores_gemma":[0.000052956966,0.000140893,0.00003904826,0.00052895275,0.00009531646,0.0013164913,0.00024343542,0.00017702728,0.00035470098],"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":[0.0000034571774,0.0002366253,0.03897792,0.000020375186,0.0000882823,0.000016537906,0.0018263583,0.0000065521544,0.0029960147,0.21858126,0.2739843,0.46326232],"study_design_scores_gemma":[0.0059780777,0.0013729536,0.017806081,0.00019435545,0.00008123826,0.00012874149,0.005976298,0.09496666,0.07479599,0.056977976,0.7370024,0.004719259],"about_ca_topic_score_codex":0.000037230508,"about_ca_topic_score_gemma":0.0000110422625,"teacher_disagreement_score":0.90969694,"about_ca_system_score_codex":0.0001448338,"about_ca_system_score_gemma":0.000016242544,"threshold_uncertainty_score":0.59331924},"labels":[],"label_agreement":null},{"id":"W1532889113","doi":"10.1007/978-3-540-45237-9_8","title":"A Multilingual Approach to Multilingual Information Retrieval","year":2003,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Search engine indexing; Natural language processing; Information retrieval; Set (abstract data type); Artificial intelligence; Multilingualism; Programming language; Linguistics","score_opus":0.023396323009704394,"score_gpt":0.2649531029623329,"score_spread":0.24155677995262848,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1532889113","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002912911,0.00010558348,0.98880154,0.0007137014,0.0012570099,0.0006657318,0.000005264073,0.00055785984,0.007602032],"genre_scores_gemma":[0.12962908,0.000019957572,0.86665666,0.002973933,0.00016266643,0.000016247466,0.00001379565,0.000025855245,0.00050178036],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99628973,0.00002613974,0.0006988542,0.0011933366,0.0011401783,0.0006517658],"domain_scores_gemma":[0.9972765,0.00021493855,0.00033299296,0.001617617,0.00037120937,0.00018673712],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00090552686,0.0005111647,0.000443029,0.0014986341,0.00026105094,0.0008818569,0.003622871,0.00045894706,0.000007654624],"category_scores_gemma":[0.00054349395,0.00047339682,0.00011482286,0.0011050089,0.0004500681,0.0013884815,0.0011796777,0.000807484,0.00013411087],"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":[0.000011135726,0.000043440417,0.000015778358,0.00003092834,0.000007470112,0.0000069290722,0.002060665,0.010812264,0.00011536077,0.029394086,0.0000813794,0.9574206],"study_design_scores_gemma":[0.0014743587,0.00059656054,0.00021911788,0.00038052787,0.000019838946,0.00015061146,0.000008603848,0.74190646,0.048544176,0.14314301,0.06055653,0.0030001714],"about_ca_topic_score_codex":0.000007892414,"about_ca_topic_score_gemma":0.0000047300355,"teacher_disagreement_score":0.9544204,"about_ca_system_score_codex":0.00036779512,"about_ca_system_score_gemma":0.00044838467,"threshold_uncertainty_score":0.9997718},"labels":[],"label_agreement":null},{"id":"W1535872236","doi":"10.1007/978-3-642-39736-3_16","title":"Matching Semi-structured Documents Using Similarity of Regions through Fuzzy Rule-Based System","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Information retrieval; Fuzzy logic; Similarity (geometry); Categorization; Set (abstract data type); Artificial intelligence; Matching (statistics); Data mining; Representation (politics); Similarity measure; Semantic similarity; Metric (unit); Natural language processing; Image (mathematics); Mathematics","score_opus":0.031460472136494416,"score_gpt":0.2695239977017202,"score_spread":0.23806352556522578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1535872236","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":[0.0010264821,0.00026295506,0.9934348,0.00057977386,0.001275275,0.00058250845,0.0000100977195,0.0005495916,0.0022785289],"genre_scores_gemma":[0.5306166,0.000011254581,0.4688825,0.00028212735,0.00008206144,0.000009823664,0.000005056352,0.000024647827,0.00008596321],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9959043,0.000052664753,0.0008372812,0.0014287643,0.0011471546,0.00062982726],"domain_scores_gemma":[0.9961713,0.0003234944,0.0008712738,0.0021989476,0.00032980638,0.00010517347],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00047682316,0.0005909287,0.0007214052,0.00076844846,0.0003609083,0.000584826,0.0042502694,0.0005296897,0.000017191633],"category_scores_gemma":[0.000047881258,0.0005241996,0.00018954473,0.00079964835,0.00090290763,0.0012091564,0.0013166511,0.0007738443,0.000020631622],"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":[0.000011187154,0.00006719839,0.00024073951,0.0005248039,0.00005389812,0.00005460528,0.00138431,0.08370632,0.003435368,0.7815934,0.00007829855,0.12884991],"study_design_scores_gemma":[0.00043604965,0.00008354527,0.00013615584,0.0011896222,0.000023336905,0.000044130564,0.000003802105,0.26066408,0.011011237,0.72512364,0.00045004563,0.00083435193],"about_ca_topic_score_codex":0.00016502476,"about_ca_topic_score_gemma":0.000021167085,"teacher_disagreement_score":0.5295901,"about_ca_system_score_codex":0.0005842803,"about_ca_system_score_gemma":0.0005472907,"threshold_uncertainty_score":0.99972093},"labels":[],"label_agreement":null},{"id":"W1536461222","doi":"10.11606/t.55.2013.tde-03052013-101143","title":"Organização flexível de documentos","year":2013,"lang":"pt","type":"dissertation","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Cluster analysis; Fuzzy clustering; Computer science; Data mining; Fuzzy logic; Information retrieval; Heuristic; Cluster (spacecraft); Artificial intelligence","score_opus":0.01848219833181003,"score_gpt":0.2807644531478932,"score_spread":0.2622822548160832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1536461222","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":[0.06352695,0.0014814481,0.84512734,0.007084567,0.0042565665,0.002512927,0.000013021123,0.0057797167,0.07021747],"genre_scores_gemma":[0.50739646,0.00045084444,0.014299454,0.0005715711,0.00007289504,0.00021930427,0.00019837903,0.00006336729,0.4767277],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9967349,0.000080148544,0.0007065524,0.001050211,0.0006202585,0.00080793945],"domain_scores_gemma":[0.9972063,0.00010484208,0.0005112957,0.0015471681,0.00041397466,0.00021646867],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00025914924,0.00059810554,0.00045958257,0.0004795283,0.00035112698,0.001499932,0.0029950838,0.0008121651,0.006412033],"category_scores_gemma":[0.00018138987,0.0005526552,0.0001714229,0.0010853054,0.000085187625,0.0012154237,0.00038006812,0.00056954485,0.010100047],"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":[0.000013157637,0.00035428183,0.0016212737,0.00023811786,0.00017638288,0.000014624408,0.006350486,0.000007062065,0.021220468,0.56470233,0.097866535,0.3074353],"study_design_scores_gemma":[0.0030416767,0.0010173112,0.038784176,0.0007333671,0.00038431972,0.00007774862,0.037999097,0.08033972,0.6241515,0.08928153,0.117324926,0.006864588],"about_ca_topic_score_codex":0.00032040384,"about_ca_topic_score_gemma":0.000029104851,"teacher_disagreement_score":0.8308279,"about_ca_system_score_codex":0.00027505282,"about_ca_system_score_gemma":0.0005048211,"threshold_uncertainty_score":0.9996925},"labels":[],"label_agreement":null},{"id":"W1537473998","doi":"10.1007/11510888_57","title":"Text Classification Using Small Number of Features","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Information retrieval","score_opus":0.040018100165544614,"score_gpt":0.2860904354397913,"score_spread":0.24607233527424668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1537473998","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004240463,0.00033780173,0.9901348,0.0011312698,0.0006466002,0.0002738206,0.000003328635,0.00027729128,0.006771073],"genre_scores_gemma":[0.30470434,0.00007889208,0.6937578,0.00033290658,0.00021295316,0.0000064185733,0.0000040771306,0.00002565378,0.00087701145],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99709976,0.000023128463,0.0005828622,0.0011486508,0.0007090988,0.0004365246],"domain_scores_gemma":[0.99719167,0.00024406974,0.00056870695,0.0016398153,0.0002754907,0.000080220794],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00047524736,0.00040442997,0.0004410162,0.0007372057,0.00016144948,0.00031454142,0.0034664301,0.0004362631,0.00003838231],"category_scores_gemma":[0.000087936955,0.00036827102,0.00012711344,0.00070431,0.00085198577,0.00056374824,0.0009306958,0.0006023985,0.00004441568],"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":[0.0000028347213,0.000029009381,0.0001879043,0.000023819108,0.000007710465,0.000004828353,0.00022621185,0.0021661166,0.0013331787,0.1902351,0.000025949155,0.80575734],"study_design_scores_gemma":[0.00053699,0.0001346945,0.0031339366,0.00065655645,0.00002815349,0.00017772825,0.0000018386385,0.513264,0.0244604,0.4490279,0.007032197,0.001545624],"about_ca_topic_score_codex":0.000018747116,"about_ca_topic_score_gemma":0.000032369386,"teacher_disagreement_score":0.80421174,"about_ca_system_score_codex":0.00030056926,"about_ca_system_score_gemma":0.00040597157,"threshold_uncertainty_score":0.9998769},"labels":[],"label_agreement":null},{"id":"W1547865988","doi":"10.1007/978-3-540-88192-6_10","title":"Enhancing Text Categorization Using Sentence Semantics","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Categorization; Natural language processing; Sentence; Phrase; Term (time); Weighting; Artificial intelligence; Set (abstract data type); Semantics (computer science); Meaning (existential); Text categorization; Word (group theory); Information retrieval; Linguistics","score_opus":0.026956552141217945,"score_gpt":0.2548127334415361,"score_spread":0.22785618130031815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1547865988","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00022232515,0.00040217256,0.9957826,0.0007785641,0.0013039055,0.0002815476,0.0000013998807,0.00048285324,0.0007445951],"genre_scores_gemma":[0.39272872,0.00034276702,0.60561913,0.0005458649,0.0002520776,0.0000055388273,0.000005316652,0.000035965844,0.00046459484],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966086,0.000019727504,0.0005599238,0.0013277411,0.00091195124,0.00057202706],"domain_scores_gemma":[0.99757326,0.00020666965,0.00041699997,0.0014181082,0.00028739768,0.00009756046],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003764362,0.00044929565,0.00040630225,0.0009952112,0.0004146527,0.0004923663,0.0029587962,0.00035241147,0.000010518435],"category_scores_gemma":[0.00012106678,0.0004290273,0.00009371008,0.0009419464,0.00073741726,0.0009901457,0.001227603,0.0006045428,0.000050312436],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000043769337,0.00006421811,0.00031556727,0.00009358598,0.000020764606,0.00018236595,0.002110519,0.040907145,0.009097582,0.105420284,0.00006735024,0.84171623],"study_design_scores_gemma":[0.00020934084,0.00009598215,0.000121181525,0.00037636198,0.0000095851265,0.00020723365,0.0000010067587,0.870905,0.036365896,0.088772476,0.0019528588,0.0009830967],"about_ca_topic_score_codex":0.000022894936,"about_ca_topic_score_gemma":0.000031203086,"teacher_disagreement_score":0.8407332,"about_ca_system_score_codex":0.00039544117,"about_ca_system_score_gemma":0.0005718154,"threshold_uncertainty_score":0.9998162},"labels":[],"label_agreement":null},{"id":"W1550901011","doi":"10.1002/9780470176535.ch3","title":"Feature Extraction, Selection, and Creation","year":2007,"lang":"en","type":"other","venue":"","topic":"Text and Document Classification Technologies","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":"Concordia University; École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Selection (genetic algorithm); Computer science; Feature selection; Feature (linguistics); Artificial intelligence","score_opus":0.010262836556326458,"score_gpt":0.28003685267498324,"score_spread":0.26977401611865676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1550901011","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.688662e-7,0.0003570326,0.4777219,0.0018339219,0.00012945823,0.000081667196,3.766297e-7,0.0016614336,0.51821345],"genre_scores_gemma":[0.00022865886,0.0002727475,0.06899961,0.00009810454,0.000080450525,0.000008794945,0.0000048559673,0.000039543193,0.9302672],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.999405,0.000008426568,0.0000663902,0.00028754934,0.00012648304,0.000106096144],"domain_scores_gemma":[0.99956304,0.000018678278,0.00010654739,0.00025303024,0.000031209394,0.000027477708],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007045269,0.00011652453,0.0000896666,0.00048626788,0.000050062,0.00013068039,0.0002270704,0.00031102623,0.00044346924],"category_scores_gemma":[0.0000175874,0.000099227786,0.000017371785,0.00035967003,0.00002803208,0.00015616286,0.0000500997,0.0001356187,0.00010706014],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.9039606e-7,0.0000068312006,0.00010779658,0.000005365835,0.000006606573,3.6380717e-7,0.0000064336973,5.4477784e-8,0.000037572663,0.15663391,0.78632045,0.05687434],"study_design_scores_gemma":[0.000058178248,0.000013112618,0.00047694304,0.000011080627,0.0000034313184,0.000011981201,0.000010656041,0.00021296742,0.00051692285,0.0013465121,0.997218,0.00012018688],"about_ca_topic_score_codex":0.000025920866,"about_ca_topic_score_gemma":0.00006527031,"teacher_disagreement_score":0.4120538,"about_ca_system_score_codex":0.000023380751,"about_ca_system_score_gemma":0.00001917536,"threshold_uncertainty_score":0.48556772},"labels":[],"label_agreement":null},{"id":"W1560461490","doi":"10.1007/978-3-642-13059-5_17","title":"Semi-supervised Probability Propagation on Instance-Attribute Graphs","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Discriminative model; Graph; Theoretical computer science; Nonparametric statistics; Artificial intelligence; Machine learning; Pattern recognition (psychology); Mathematics","score_opus":0.024539000935987827,"score_gpt":0.24331539554980702,"score_spread":0.2187763946138192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1560461490","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":[0.0011248287,0.00010330645,0.99047136,0.0031735746,0.0014870504,0.0008875011,0.000007502461,0.00080966053,0.0019352084],"genre_scores_gemma":[0.57614756,0.00006572259,0.4218357,0.0012628582,0.00019116745,0.00007668968,0.000014361302,0.00003940424,0.00036653175],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99573827,0.000034123943,0.00058976084,0.0018816664,0.0011449577,0.00061121956],"domain_scores_gemma":[0.99634904,0.0003028272,0.00037158528,0.002493907,0.00035020034,0.00013243909],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000902351,0.00055428036,0.0004672368,0.00094296085,0.00037446266,0.0006413459,0.004128053,0.0006113991,0.000022066213],"category_scores_gemma":[0.00023696327,0.0004716899,0.00014093908,0.0009932454,0.0011636823,0.0008472055,0.0009411011,0.0014689466,0.00007718855],"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":[0.000008844844,0.000083587765,0.00018654177,0.00004904935,0.000007873632,0.00001683514,0.00034193665,0.0012255446,0.0019355946,0.34779528,0.00002729246,0.6483216],"study_design_scores_gemma":[0.00039278055,0.00034026874,0.0007340715,0.00027937558,0.0000063188504,0.000013673713,2.6329724e-7,0.05922051,0.030632447,0.9048135,0.0026684601,0.0008983166],"about_ca_topic_score_codex":0.000005828201,"about_ca_topic_score_gemma":0.00004727807,"teacher_disagreement_score":0.6474233,"about_ca_system_score_codex":0.00033735667,"about_ca_system_score_gemma":0.00049687864,"threshold_uncertainty_score":0.9997735},"labels":[],"label_agreement":null},{"id":"W1564407722","doi":"10.1007/978-3-540-30134-9_67","title":"Analyzing the Temporal Sequences for Text Categorization","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Categorization; Computer science; Artificial intelligence; Classifier (UML); Text categorization; Cluster analysis; Pattern recognition (psychology); Representation (politics); Natural language processing","score_opus":0.025440861889619294,"score_gpt":0.2649863272172401,"score_spread":0.23954546532762078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1564407722","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":[0.000023636812,0.0004560735,0.9912056,0.005726082,0.0009139251,0.0005475144,0.000003160118,0.00032883656,0.00079519657],"genre_scores_gemma":[0.66475147,0.00007673112,0.33383125,0.0005472255,0.0002704983,0.000048634352,0.000012222032,0.000022736014,0.00043922017],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99761903,0.000015157943,0.00041656758,0.001027797,0.0004888525,0.00043261304],"domain_scores_gemma":[0.9978713,0.00035409295,0.00035001885,0.0011527104,0.00021717328,0.00005472034],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006919256,0.0003371008,0.00028628774,0.0005609722,0.00047574125,0.00084156357,0.0038440344,0.00024320952,0.000011246545],"category_scores_gemma":[0.00012053536,0.00023394967,0.000112387504,0.0007341977,0.0008216083,0.0007068665,0.0006093899,0.00039937563,0.000017778526],"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":[0.0000018101784,0.00000945861,0.00011213796,0.0000185776,0.000006337985,0.0000037556129,0.00037089878,0.010439201,0.00010115359,0.48707882,0.000026597809,0.50183123],"study_design_scores_gemma":[0.0001636474,0.00010596503,0.000091199865,0.00010393523,0.0000068296877,0.000009722852,7.377824e-7,0.11016761,0.0024657873,0.8843121,0.0021917834,0.0003807043],"about_ca_topic_score_codex":0.00002915206,"about_ca_topic_score_gemma":0.000052513715,"teacher_disagreement_score":0.6647278,"about_ca_system_score_codex":0.00032328186,"about_ca_system_score_gemma":0.0006402599,"threshold_uncertainty_score":0.95401907},"labels":[],"label_agreement":null},{"id":"W1569526680","doi":"10.1007/978-3-540-30115-8_27","title":"An Efficient Method to Estimate Labelled Sample Size for Transductive LDA(QDA/MDA) Based on Bayes Risk","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"University of Toronto","keywords":"Computer science; Artificial intelligence; Machine learning; Gaussian; Linear discriminant analysis; Bayes' theorem; Supervised learning; Bayesian probability; Sample size determination; Semi-supervised learning; Pattern recognition (psychology); Sample (material); Mathematics; Statistics; Artificial neural network","score_opus":0.017771599480654515,"score_gpt":0.3131416018898215,"score_spread":0.295370002409167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1569526680","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011659262,0.00004431591,0.9937164,0.0028317499,0.000809225,0.001416069,0.00007324028,0.0007205372,0.0002718455],"genre_scores_gemma":[0.13025887,0.0000036212505,0.86848176,0.0009779336,0.0001038419,0.00009364461,0.000006837886,0.00003765355,0.000035860103],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99524033,0.000076346674,0.00055756076,0.0023378367,0.0010003078,0.0007875962],"domain_scores_gemma":[0.99340755,0.00362655,0.00035351145,0.0020471779,0.00032540248,0.00023980805],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014885372,0.0006693613,0.00064655853,0.0009921845,0.00052686717,0.00064676016,0.0040585618,0.0003713288,0.00003178175],"category_scores_gemma":[0.00078681076,0.00058229634,0.00020032968,0.00092648854,0.00043863076,0.0003248147,0.0003617693,0.00063967664,0.000021937061],"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":[0.000029885112,0.000087448796,0.000012020957,0.000020683015,0.0000064433502,0.0000045398533,0.00048183856,0.5728508,0.00024729312,0.056107637,0.0000066780117,0.37014472],"study_design_scores_gemma":[0.00056891557,0.00086366397,0.00013529838,0.00016148739,0.000013777571,0.0000025191332,5.2146044e-7,0.6963485,0.012148962,0.28860882,0.00055779313,0.000589768],"about_ca_topic_score_codex":0.00003887241,"about_ca_topic_score_gemma":0.000040360548,"teacher_disagreement_score":0.36955494,"about_ca_system_score_codex":0.00049458444,"about_ca_system_score_gemma":0.00060766935,"threshold_uncertainty_score":0.9996629},"labels":[],"label_agreement":null},{"id":"W1571679273","doi":"10.1007/978-3-642-02611-9_85","title":"A New Fuzzy Hierarchical Classification Based on SVM for Text Categorization","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Artificial intelligence; Support vector machine; Machine learning; Categorization; Preprocessor; Fuzzy logic; Classifier (UML); Data mining; Pattern recognition (psychology); Text categorization","score_opus":0.02621470035049042,"score_gpt":0.2659694151321511,"score_spread":0.2397547147816607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1571679273","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000004223708,0.000071535884,0.9823862,0.010396626,0.0007842517,0.0007640466,0.000004121448,0.0005597999,0.005029216],"genre_scores_gemma":[0.15275922,0.00002279718,0.8420215,0.002821598,0.00047195464,0.000047814032,0.000046282243,0.00003861003,0.0017701621],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964623,0.00002520663,0.0005266986,0.001584967,0.0008721664,0.0005286589],"domain_scores_gemma":[0.9970871,0.0005604129,0.00035900978,0.0016179371,0.00021646309,0.00015904779],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005168717,0.00046821794,0.000389465,0.0012420194,0.00028444268,0.00067028106,0.0030399114,0.00047627083,0.000013344913],"category_scores_gemma":[0.00020415738,0.0004243908,0.00014212402,0.00079018954,0.00032022985,0.0005046569,0.00024954465,0.0005971472,0.000046979796],"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":[0.000009540847,0.000023465032,0.000008302818,0.000009350778,0.0000017469916,0.0000020190093,0.000063189305,0.0060367947,0.00012705952,0.28998733,0.0001825474,0.70354867],"study_design_scores_gemma":[0.00032324166,0.00033279238,0.00030591336,0.000095453564,0.000004716792,0.0000031415389,1.01574805e-7,0.5292954,0.0010871884,0.46161193,0.006554146,0.0003859665],"about_ca_topic_score_codex":0.000005427708,"about_ca_topic_score_gemma":0.000012478426,"teacher_disagreement_score":0.70316267,"about_ca_system_score_codex":0.00039539425,"about_ca_system_score_gemma":0.0009038347,"threshold_uncertainty_score":0.99982077},"labels":[],"label_agreement":null},{"id":"W1585793187","doi":"10.1007/978-3-642-21881-1_35","title":"Incorporating Game Theory in Feature Selection for Text Categorization","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Categorization; Feature selection; Text categorization; Computer science; Selection (genetic algorithm); Feature (linguistics); Artificial intelligence; Demonstrative; Game theory; Machine learning; Natural language processing; Information retrieval; Mathematics; Linguistics; Mathematical economics","score_opus":0.02111208103021165,"score_gpt":0.24479334971361844,"score_spread":0.2236812686834068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1585793187","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":[0.000035948102,0.00025437537,0.9953399,0.0007456852,0.0007776011,0.00063371897,0.0000020969046,0.00036606114,0.0018446379],"genre_scores_gemma":[0.594824,0.000034592915,0.40310758,0.00048618318,0.00022395085,0.00007495829,0.000015295662,0.00003694016,0.0011964701],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99751794,0.00003491507,0.00041628213,0.0011852831,0.0004085332,0.00043706776],"domain_scores_gemma":[0.99820167,0.00034461106,0.0004186181,0.00074727676,0.00023022894,0.000057570298],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009649657,0.0003777353,0.00034649152,0.0012022819,0.00017312662,0.00037869895,0.0020981694,0.00048229942,0.000007961402],"category_scores_gemma":[0.00019482392,0.00034669635,0.000077921846,0.00096143194,0.00037275098,0.0008698502,0.00051020726,0.0006354887,0.000014886392],"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":[0.0000063455495,0.000014709911,0.00018842958,0.000017870123,0.0000025368822,0.0000020076702,0.00037552544,0.0016175436,0.00015477111,0.49537298,0.000018353876,0.5022289],"study_design_scores_gemma":[0.00021646224,0.00014132916,0.0003077201,0.00012763453,0.0000035568569,0.000011870785,5.022703e-7,0.15051858,0.004535016,0.84295774,0.00078270864,0.00039690654],"about_ca_topic_score_codex":0.000014263116,"about_ca_topic_score_gemma":0.00012588786,"teacher_disagreement_score":0.5947881,"about_ca_system_score_codex":0.00034539006,"about_ca_system_score_gemma":0.00038361875,"threshold_uncertainty_score":0.9998985},"labels":[],"label_agreement":null},{"id":"W1586413166","doi":"10.3115/1118935.1118941","title":"Text classification in Asian languages without word segmentation","year":2003,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Text segmentation; Artificial intelligence; Natural language processing; Language model; n-gram; Word (group theory); Segmentation; Feature (linguistics); Character (mathematics); Key (lock); Word lists by frequency; Simple (philosophy); Linguistics; Mathematics","score_opus":0.02359207191929053,"score_gpt":0.29467681341369245,"score_spread":0.2710847414944019,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1586413166","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":[0.055883754,0.00009830817,0.78802854,0.0058274944,0.00014605037,0.00033217392,3.821639e-7,0.0009798049,0.1487035],"genre_scores_gemma":[0.91879624,0.00001549902,0.07888921,0.00012817739,0.0000045691627,0.000043203832,0.000002542957,0.0000038928183,0.0021166755],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9992299,0.000050889907,0.00017528197,0.00025350924,0.00014222093,0.00014820373],"domain_scores_gemma":[0.9994693,0.00002325827,0.00006629037,0.00039262456,0.000023118968,0.000025451376],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017899727,0.000079998805,0.00007437186,0.0001903877,0.0000439871,0.00010026189,0.0003096564,0.000056979265,0.00006977552],"category_scores_gemma":[0.00006194756,0.00006986336,0.000018509958,0.00049907557,0.000028711616,0.00052489125,0.000030500261,0.00007548933,0.00014941822],"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":[9.3944743e-7,0.000044954577,0.02574952,0.000002846835,0.0000021226756,0.0000010197471,0.00031413452,0.0000025144975,0.006358578,0.7895874,0.0005354322,0.17740057],"study_design_scores_gemma":[0.001967231,0.00012449728,0.6795692,0.00004046395,0.00000805998,0.000020043237,0.016621148,0.0102647785,0.19428316,0.051199708,0.044972103,0.0009296359],"about_ca_topic_score_codex":0.000009172792,"about_ca_topic_score_gemma":0.000054536977,"teacher_disagreement_score":0.8629125,"about_ca_system_score_codex":0.000059585316,"about_ca_system_score_gemma":0.000028312972,"threshold_uncertainty_score":0.2848945},"labels":[],"label_agreement":null},{"id":"W158988288","doi":"","title":"Enhancing Cross Document Coreference of Web Documents with Context Similarity and Very Large Scale Text Categorization","year":2010,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"Lockheed Martin (Canada)","funders":"","keywords":"Coreference; Computer science; Categorization; Context (archaeology); Task (project management); Information retrieval; Similarity (geometry); Benchmark (surveying); Set (abstract data type); Natural language processing; Feature (linguistics); Artificial intelligence; Scale (ratio); Resolution (logic)","score_opus":0.009312888888777668,"score_gpt":0.25510209062650036,"score_spread":0.24578920173772267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W158988288","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":[0.7698662,0.000027059481,0.22719146,0.0004967243,0.00016863894,0.00020295987,0.0000037026616,0.00026527554,0.0017779515],"genre_scores_gemma":[0.9865613,0.000034827484,0.012441847,0.00010652962,0.000009429657,0.00002162206,0.0000051244024,0.0000060075477,0.0008133366],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99876595,0.000020607413,0.000284565,0.00039613777,0.00028655934,0.00024619003],"domain_scores_gemma":[0.9989415,0.00006510572,0.00018008094,0.00057709485,0.00016852816,0.000067691595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028015272,0.00014815854,0.0001770433,0.000106711545,0.0001525276,0.00027807654,0.00055359834,0.00010652877,0.000091625414],"category_scores_gemma":[0.000043395987,0.00011238982,0.000022255992,0.00029616922,0.00018255411,0.0011142209,0.0003105161,0.0001848369,0.000016008864],"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":[0.000040817118,0.00024709318,0.18292023,0.000074930955,0.000035632485,0.000002973538,0.0012902747,0.0000053736035,0.11732205,0.66779566,0.0003582426,0.029906726],"study_design_scores_gemma":[0.0024533763,0.00037664207,0.104762144,0.00005184595,0.000017843247,0.000015334597,0.00091481407,0.00540635,0.8593482,0.018898975,0.007161937,0.0005925844],"about_ca_topic_score_codex":0.00006234519,"about_ca_topic_score_gemma":0.00079831673,"teacher_disagreement_score":0.7420261,"about_ca_system_score_codex":0.000022002141,"about_ca_system_score_gemma":0.0000862552,"threshold_uncertainty_score":0.4583124},"labels":[],"label_agreement":null},{"id":"W1590732297","doi":"10.1007/11766247_28","title":"Beyond the Bag of Words: A Text Representation for Sentence Selection","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Selection (genetic algorithm); Sentence; Natural language processing; Representation (politics); Artificial intelligence; Computer science; Linguistics; Psychology; Political science; Philosophy","score_opus":0.020344372462501047,"score_gpt":0.26771300048168784,"score_spread":0.2473686280191868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1590732297","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009931877,0.00022094797,0.9937271,0.0027052977,0.00071270776,0.0006531152,0.000004551568,0.00019714056,0.0016798142],"genre_scores_gemma":[0.44387397,0.000057088462,0.5530033,0.000705137,0.00033190244,0.00009466514,0.000013631555,0.000030809017,0.0018894593],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975155,0.000022984279,0.00050242175,0.00095872366,0.00065320695,0.00034717732],"domain_scores_gemma":[0.9974409,0.0006498548,0.000494964,0.0010562814,0.00032406437,0.00003399021],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059753336,0.00028014893,0.000302001,0.00056745217,0.0002533799,0.0003038354,0.002527498,0.00021425833,0.0000064539227],"category_scores_gemma":[0.00014522678,0.00020959035,0.0001259356,0.00089012657,0.00073345425,0.0005336713,0.0005253655,0.00034253058,0.000006410556],"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":[0.000008364235,0.000030909967,0.00016747008,0.00003304829,0.000010077406,0.0000016855722,0.0003681072,0.015621447,0.0011033429,0.1354791,0.00054205756,0.8466344],"study_design_scores_gemma":[0.00025084184,0.00017198159,0.0004030835,0.000106774256,0.000010953891,0.000018619674,0.0000012439244,0.3961002,0.018771222,0.58154297,0.0022685374,0.00035359664],"about_ca_topic_score_codex":0.000035141984,"about_ca_topic_score_gemma":0.000064622065,"teacher_disagreement_score":0.8462808,"about_ca_system_score_codex":0.000154317,"about_ca_system_score_gemma":0.00023867296,"threshold_uncertainty_score":0.85468465},"labels":[],"label_agreement":null},{"id":"W1595744771","doi":"10.5555/1786374.1786451","title":"Maximum entropy modeling with feature selection for text categorization","year":2008,"lang":"en","type":"article","venue":"Asia Information Retrieval Symposium","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Feature selection; Principle of maximum entropy; Categorization; Computer science; Text categorization; Artificial intelligence; Entropy (arrow of time); Pattern recognition (psychology); Feature (linguistics); Selection (genetic algorithm); Cross entropy; Data mining; Machine learning","score_opus":0.011482431156226472,"score_gpt":0.21436809348240127,"score_spread":0.2028856623261748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1595744771","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":[0.010377985,0.000013781688,0.9818545,0.0048108846,0.00019127666,0.000564802,0.0000033735,0.00078075245,0.0014026738],"genre_scores_gemma":[0.96627456,0.00006865824,0.0329139,0.00019130448,0.000049683636,0.00005880694,0.00010285563,0.000008945204,0.0003313079],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889976,0.000014702221,0.00029170036,0.00019134943,0.00035476702,0.00024775098],"domain_scores_gemma":[0.9989978,0.000027808754,0.0002206753,0.0002872616,0.000411902,0.00005453389],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000130898,0.00015623726,0.00012777439,0.00025205043,0.00040090163,0.00023094229,0.00040139016,0.00015416827,0.000005168443],"category_scores_gemma":[0.000050072937,0.00013100785,0.000049057966,0.0008356893,0.00003504698,0.0038750863,0.000050235773,0.00013417682,0.000051780138],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005332652,0.00013030991,0.003252183,0.00013833688,0.00009597261,0.0000015154403,0.0045512943,0.03953542,0.010661272,0.9106379,0.011226779,0.019235723],"study_design_scores_gemma":[0.0010322506,0.00036151602,0.00049427024,0.000012236046,0.000013247507,0.00007204631,0.00015549157,0.93365663,0.035697572,0.002988543,0.025187768,0.00032840198],"about_ca_topic_score_codex":0.0000106129155,"about_ca_topic_score_gemma":0.0000015081364,"teacher_disagreement_score":0.95589656,"about_ca_system_score_codex":0.00012902022,"about_ca_system_score_gemma":0.0001208829,"threshold_uncertainty_score":0.5342345},"labels":[],"label_agreement":null},{"id":"W160585330","doi":"10.1007/978-3-642-33486-3_23","title":"Semi-supervised Multi-label Classification","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Artificial intelligence; Semi-supervised learning; Machine learning; Subspace topology; Margin (machine learning); Supervised learning; Classifier (UML); Exploit; Pattern recognition (psychology); Labeled data; Unsupervised learning; Artificial neural network","score_opus":0.0571843465909377,"score_gpt":0.28266592207948016,"score_spread":0.22548157548854247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W160585330","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000053272204,0.0012052887,0.99167204,0.002160062,0.0013770071,0.0004404295,0.0000041030366,0.00080587534,0.0022819003],"genre_scores_gemma":[0.17573111,0.0002655489,0.821204,0.0009873203,0.0003162793,0.00003985183,0.000014231054,0.000046018955,0.0013956599],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962173,0.00003080668,0.00059374084,0.0014928567,0.0009106702,0.00075460074],"domain_scores_gemma":[0.9966778,0.00026919678,0.00037916718,0.0022418033,0.0002529122,0.00017909241],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00075034174,0.0005427862,0.0004487654,0.001005178,0.0002964155,0.00059768365,0.0046173315,0.0005427954,0.000044988232],"category_scores_gemma":[0.000116007504,0.0004943804,0.00010556857,0.0007745311,0.0007952281,0.001276826,0.0013602262,0.00082871225,0.0003111232],"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":[0.0000016650671,0.00005835531,0.00013136992,0.00001780061,0.0000062709805,0.0000054173966,0.00029533508,0.00012345755,0.0012195413,0.08054773,0.00004445955,0.9175486],"study_design_scores_gemma":[0.0005906204,0.00010033984,0.00094548194,0.00018060599,0.000012058265,0.000029142288,7.7412625e-7,0.90212405,0.004002756,0.08481736,0.006180732,0.0010161126],"about_ca_topic_score_codex":0.000007483461,"about_ca_topic_score_gemma":0.000016634822,"teacher_disagreement_score":0.91653246,"about_ca_system_score_codex":0.00040097733,"about_ca_system_score_gemma":0.00034306452,"threshold_uncertainty_score":0.9997508},"labels":[],"label_agreement":null},{"id":"W162797994","doi":"","title":"Capturing Temporal Sequences for Text Representation Using Hierarchical SOMs.","year":2004,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"Dalhousie University","funders":"","keywords":"Computer science; Representation (politics); Artificial intelligence; Categorization; Cluster analysis; Curse of dimensionality; Feature (linguistics); Code (set theory); Feature learning; Text categorization; Hierarchical clustering; Architecture; Unsupervised learning; Pattern recognition (psychology); Self-organizing map; Sequence (biology); Natural language processing","score_opus":0.07229402046359994,"score_gpt":0.32926944764510196,"score_spread":0.256975427181502,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W162797994","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":[0.07549995,0.000034516208,0.91710794,0.005838603,0.00012275079,0.00023483021,5.783624e-7,0.000548982,0.0006118428],"genre_scores_gemma":[0.7017297,0.0000029967518,0.29801542,0.00007731705,0.00002216021,0.00002093516,0.0000016833837,0.0000028618074,0.00012692275],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992043,0.000010607018,0.00017850175,0.00028898515,0.00014597809,0.0001716722],"domain_scores_gemma":[0.99950475,0.000049200888,0.00006725096,0.00030748872,0.000037815662,0.000033489534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010726459,0.00007503348,0.00008469989,0.00010186341,0.0001412445,0.00019857135,0.00045360683,0.000052395575,0.0000072172825],"category_scores_gemma":[0.000058924114,0.00006236576,0.00004648533,0.00022548056,0.00007180268,0.00074053084,0.000107542626,0.00006567942,0.000010598704],"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":[0.000004944515,0.000042425774,0.001786276,0.000017268312,0.000008614595,0.0000030979659,0.00047416633,0.0010957838,0.008962796,0.95926064,0.00012274428,0.028221264],"study_design_scores_gemma":[0.0009440636,0.00010929656,0.0015733611,0.00006744892,0.000006664165,0.000023511075,0.0006439596,0.04249061,0.19306031,0.7601282,0.0005926059,0.00035994864],"about_ca_topic_score_codex":0.00015646571,"about_ca_topic_score_gemma":0.000024385914,"teacher_disagreement_score":0.62622976,"about_ca_system_score_codex":0.000056968733,"about_ca_system_score_gemma":0.00009332191,"threshold_uncertainty_score":0.2543202},"labels":[],"label_agreement":null},{"id":"W1632892920","doi":"10.3233/ida-2002-6204","title":"Boosting strategy for classification","year":2002,"lang":"en","type":"article","venue":"Intelligent Data Analysis","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Imperial Bank of Commerce (Canada)","funders":"","keywords":"Boosting (machine learning); Artificial intelligence; Computer science; Pattern recognition (psychology); Machine learning","score_opus":0.31184824777260145,"score_gpt":0.36698307522512075,"score_spread":0.0551348274525193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1632892920","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":[0.00025409242,0.00045188385,0.99511933,0.0022706457,0.00006218083,0.00014178346,0.000047156136,0.0003874203,0.0012654806],"genre_scores_gemma":[0.95196354,0.0003324365,0.04627967,0.000100024845,0.000033884062,0.00004066821,0.00035322199,0.0000060039756,0.00089056586],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99861664,0.000024653391,0.0003382944,0.00061239273,0.00019994927,0.00020808389],"domain_scores_gemma":[0.9972018,0.00015956465,0.00017098727,0.0023270957,0.00009391686,0.000046611567],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030180265,0.00011048302,0.00016716341,0.00037965606,0.00013901052,0.00033586126,0.0026064578,0.00006263039,0.00016426104],"category_scores_gemma":[0.00021419911,0.00010060614,0.000105183324,0.0014640553,0.00004017106,0.0008046205,0.00034194067,0.0000701572,0.00016754791],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016719769,0.00012008328,0.0019344979,0.000009022298,0.00047888226,0.0000015660037,0.00011933944,0.00037508775,0.0004651289,0.16994411,0.0195413,0.80700934],"study_design_scores_gemma":[0.00004434386,0.000022652155,0.00069163594,0.0000021243393,0.00016984738,5.036435e-7,0.00018636626,0.95740384,0.001279174,0.0036187123,0.03644388,0.00013692716],"about_ca_topic_score_codex":0.000017849085,"about_ca_topic_score_gemma":0.000020224967,"teacher_disagreement_score":0.95702875,"about_ca_system_score_codex":0.000035508256,"about_ca_system_score_gemma":0.000009500911,"threshold_uncertainty_score":0.48434904},"labels":[],"label_agreement":null},{"id":"W167522204","doi":"","title":"Beyond TFIDF weighting for text categorization in the vector space model","year":2005,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":232,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Weighting; tf–idf; Vector space model; Computer science; Artificial intelligence; Categorization; Leverage (statistics); Vocabulary; Feature selection; Support vector machine; Text categorization; Word (group theory); Feature vector; Natural language processing; Machine learning; Information retrieval; Pattern recognition (psychology); Mathematics; Term (time)","score_opus":0.02088681033409115,"score_gpt":0.2605201725384578,"score_spread":0.23963336220436662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W167522204","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":[0.003784743,0.00003793399,0.9500412,0.03656249,0.000043762342,0.00022228618,4.6198716e-7,0.00025061198,0.0090565495],"genre_scores_gemma":[0.8762227,0.0000072466214,0.12166339,0.00045391227,0.000030585135,0.00006506559,0.0000021206517,0.0000032440423,0.0015516846],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99939615,0.000012435112,0.00013259058,0.0001889467,0.000118419804,0.00015146796],"domain_scores_gemma":[0.9994859,0.00008719326,0.000049696137,0.00033407423,0.00003152157,0.000011631695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021062467,0.000065996486,0.000056216013,0.00008115535,0.00008920509,0.00014162295,0.0006710455,0.00004463021,0.000006933611],"category_scores_gemma":[0.000044940796,0.00004333883,0.000023525516,0.00030193193,0.000018508938,0.0004982087,0.00006211383,0.00005728816,0.00002748181],"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":[7.4597074e-7,0.000021721115,0.00007295346,0.0000018604384,8.531248e-7,6.2408596e-8,0.0005590461,0.0010265913,0.0007926935,0.9607506,0.0028676663,0.033905216],"study_design_scores_gemma":[0.0001683387,0.00001756063,0.00033137618,0.0000016152088,0.0000012162058,7.2474575e-7,0.0001856786,0.90801656,0.008270115,0.07531867,0.007604068,0.00008408588],"about_ca_topic_score_codex":0.000006283191,"about_ca_topic_score_gemma":0.000036368747,"teacher_disagreement_score":0.90698993,"about_ca_system_score_codex":0.000034243552,"about_ca_system_score_gemma":0.00002650696,"threshold_uncertainty_score":0.17673063},"labels":[],"label_agreement":null},{"id":"W1714192071","doi":"","title":"Categorical proportional difference: a feature selection method for text categorization","year":2008,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":47,"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 Regina","funders":"","keywords":"Artificial intelligence; Computer science; Feature selection; Categorical variable; Word (group theory); Task (project management); Naive Bayes classifier; Mutual information; Natural language processing; Feature (linguistics); Selection (genetic algorithm); Categorization; Measure (data warehouse); Support vector machine; Pattern recognition (psychology); Machine learning; Data mining; Mathematics","score_opus":0.029536126455235182,"score_gpt":0.2917414232733742,"score_spread":0.26220529681813903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1714192071","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":[0.0012692265,0.000018870725,0.99028754,0.0063895406,0.00014351454,0.00031488153,8.113222e-7,0.00084993837,0.0007256875],"genre_scores_gemma":[0.5981073,0.000014418603,0.3902147,0.00014255563,0.000053863016,0.0001786432,0.000020585117,0.0000057777515,0.011262176],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990567,0.000025438674,0.00016044494,0.00035145023,0.00021919425,0.00018677358],"domain_scores_gemma":[0.99940175,0.00006741799,0.00009067329,0.00021535128,0.00018284497,0.000041954143],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000115106566,0.00010951352,0.00011122012,0.00012954355,0.00028180852,0.00006946789,0.00037550277,0.0001291801,0.000023587223],"category_scores_gemma":[0.00008052043,0.00008428883,0.000052949494,0.00054741,0.00003550346,0.00032557745,0.000059298432,0.00010522719,0.000019962677],"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":[0.0000065201643,0.00007506644,0.0017452817,0.0000064190667,0.0000085741185,7.503305e-7,0.00012254587,0.000021564645,0.0049678315,0.93656737,0.012750435,0.043727633],"study_design_scores_gemma":[0.00116468,0.0004855444,0.08880085,0.0000042401607,0.000018123095,0.0002948736,0.00010661556,0.47730762,0.10185667,0.27970985,0.04952803,0.000722897],"about_ca_topic_score_codex":0.000014552514,"about_ca_topic_score_gemma":0.0000045970755,"teacher_disagreement_score":0.65685755,"about_ca_system_score_codex":0.000069856476,"about_ca_system_score_gemma":0.00011885605,"threshold_uncertainty_score":0.3437199},"labels":[],"label_agreement":null},{"id":"W1718341272","doi":"10.1007/3-540-44645-1_18","title":"Multilingual Information Retrieval Based on Parallel Texts from the Web","year":2001,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Clef; Machine translation; Information retrieval; Parallel corpora; Cross-language information retrieval; Artificial intelligence; Natural language processing; Task (project management); Web page; World Wide Web","score_opus":0.018873960000008832,"score_gpt":0.2507413725531626,"score_spread":0.23186741255315377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1718341272","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":[0.00021107048,0.00011770765,0.98752713,0.005567063,0.0011048238,0.00040662906,0.000012585606,0.00046326517,0.0045897383],"genre_scores_gemma":[0.74358547,0.000113809605,0.24696556,0.00839959,0.00049344235,0.00001669601,0.00004913013,0.000029257584,0.00034706827],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997047,0.00003233365,0.00050545577,0.00082699524,0.0011502017,0.00043798386],"domain_scores_gemma":[0.99651206,0.0010028982,0.00037108408,0.0018489257,0.00018809858,0.00007691594],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00061374024,0.00041021316,0.00029543438,0.00054878526,0.00032719088,0.00090348156,0.0043203705,0.00035957884,0.00003966941],"category_scores_gemma":[0.00032495658,0.00028931827,0.00010979323,0.0006722798,0.00061780214,0.0009203049,0.0007132718,0.0008562055,0.00017302488],"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":[0.000022773134,0.000024503597,0.000091542606,0.0000055997116,0.0000056792887,0.000013410536,0.00041144164,0.04451856,0.000030145522,0.015679585,0.00021695867,0.9389798],"study_design_scores_gemma":[0.00045800777,0.00014049206,0.00042785372,0.00016365535,0.000004864393,0.000004917421,6.330976e-7,0.8874511,0.0009736514,0.08609017,0.02382891,0.00045574055],"about_ca_topic_score_codex":0.000018034412,"about_ca_topic_score_gemma":0.000025340702,"teacher_disagreement_score":0.93852407,"about_ca_system_score_codex":0.0002338332,"about_ca_system_score_gemma":0.0005273086,"threshold_uncertainty_score":0.9999559},"labels":[],"label_agreement":null},{"id":"W1749331913","doi":"10.1007/978-3-642-03070-3_50","title":"New Semantic Similarity Based Model for Text Clustering Using Extended Gloss Overlaps","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; WordNet; Semantic similarity; Vector space model; Ambiguity; Cluster analysis; Natural language processing; Artificial intelligence; Explicit semantic analysis; Information retrieval; Similarity (geometry); Semantic computing; Semantic Web; Semantic technology; Image (mathematics)","score_opus":0.043327171249890384,"score_gpt":0.2861407243885287,"score_spread":0.24281355313863834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1749331913","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000020059755,0.00023968641,0.99556595,0.0018484344,0.00067852525,0.00066407956,0.0000065213353,0.00054611906,0.000430634],"genre_scores_gemma":[0.086778335,0.000014277277,0.910976,0.0014040126,0.00016813014,0.0000075879148,0.000004629867,0.000029869896,0.0006171604],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961767,0.000016055126,0.00058216945,0.0016588893,0.00081203965,0.0007541274],"domain_scores_gemma":[0.99720013,0.00030233638,0.0003849472,0.001737917,0.000207255,0.00016740982],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005706816,0.0005796045,0.0005639284,0.000862448,0.00037275057,0.0008547218,0.0037222668,0.00046175826,0.000008327611],"category_scores_gemma":[0.00011339048,0.00055998244,0.00020455565,0.00056170276,0.00032781676,0.0008405647,0.00092434784,0.0005744966,0.000006911111],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008193701,0.000021337524,0.000005740096,0.000038166298,0.0000051063494,0.000008604713,0.00012767939,0.32120597,0.0003472069,0.015554796,0.000047996407,0.6626292],"study_design_scores_gemma":[0.00031419538,0.00008189821,0.000027613027,0.00019038023,0.000009064267,0.000010606972,8.9241595e-8,0.74200547,0.0010465996,0.2555047,0.00033356223,0.00047581276],"about_ca_topic_score_codex":0.000016793047,"about_ca_topic_score_gemma":0.00009145554,"teacher_disagreement_score":0.6621534,"about_ca_system_score_codex":0.0004544244,"about_ca_system_score_gemma":0.0010745456,"threshold_uncertainty_score":0.99968517},"labels":[],"label_agreement":null},{"id":"W1765750589","doi":"10.1007/3-540-32394-5_2","title":"An Evidential Approach to Classification Combination for Text Categorisation","year":2006,"lang":"en","type":"book-chapter","venue":"Studies in fuzziness and soft computing","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Artificial intelligence; Perspective (graphical); Computer science; Categorization; Evidential reasoning approach; Support vector machine; Machine learning; Pattern recognition (psychology); Text categorization; k-nearest neighbors algorithm; Decision support system","score_opus":0.08955658772586585,"score_gpt":0.337119009009146,"score_spread":0.24756242128328015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1765750589","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":[0.00089262036,0.0011061156,0.9748241,0.000819823,0.0007578292,0.0010792366,0.0000052429623,0.0004507092,0.020064374],"genre_scores_gemma":[0.96994007,0.00015099415,0.023657236,0.00008034253,0.00025445587,0.00012936514,0.00010467188,0.000034202913,0.0056486735],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981285,0.000027381304,0.00054967497,0.00078632735,0.00026059305,0.00024756588],"domain_scores_gemma":[0.9985888,0.00021530775,0.00034865818,0.00047718387,0.00033025534,0.000039803166],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005471052,0.00030215012,0.00042254594,0.00044101104,0.00033938917,0.00023690674,0.00057415257,0.00021702361,4.298956e-7],"category_scores_gemma":[0.000097030075,0.00029801487,0.000058160942,0.00015972351,0.00013342514,0.00037365555,0.00031882565,0.00017977487,0.0000039114475],"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":[0.000006800424,0.00006219996,0.00017063253,0.00017834517,0.000027340004,5.494979e-7,0.0011562518,0.00038300565,0.000040217914,0.83902436,0.0021434021,0.15680692],"study_design_scores_gemma":[0.0021537,0.00056998624,0.017211517,0.0006782395,0.00010532072,0.000011494191,0.0024584795,0.4954521,0.00012076651,0.45034933,0.028695323,0.0021937278],"about_ca_topic_score_codex":0.00001500466,"about_ca_topic_score_gemma":0.0000119289225,"teacher_disagreement_score":0.9690474,"about_ca_system_score_codex":0.00016640914,"about_ca_system_score_gemma":0.000039759077,"threshold_uncertainty_score":0.9999472},"labels":[],"label_agreement":null},{"id":"W1772561895","doi":"10.22456/2175-2745.39702","title":"Support Vector Machines and Kernel Functions for Text Processing","year":2013,"lang":"en","type":"article","venue":"Revista de Informática Teórica e Aplicada","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University","keywords":"Support vector machine; Computer science; Preprocessor; Kernel method; Artificial intelligence; Kernel (algebra); Radial basis function kernel; Polynomial kernel; Tree kernel; String kernel; Classifier (UML); Structured support vector machine; Pattern recognition (psychology); Relevance vector machine; Machine learning; Mathematics; Discrete mathematics","score_opus":0.013212008035483972,"score_gpt":0.25099284871470506,"score_spread":0.2377808406792211,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1772561895","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":[0.011317135,0.0004870322,0.9664187,0.011088287,0.00006759068,0.0012031677,0.0000120968225,0.0012901123,0.008115891],"genre_scores_gemma":[0.93813604,0.00007640609,0.057666924,0.0009989834,0.000057398487,0.00072389515,0.000012595441,0.000018247207,0.0023094844],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987209,0.000010381105,0.0003692324,0.0003405389,0.00016884641,0.00039009983],"domain_scores_gemma":[0.99882525,0.00016591797,0.00016316061,0.00056063343,0.00014531313,0.00013975034],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018188386,0.00018299629,0.00020947671,0.00013142133,0.00027402106,0.00089381705,0.0006503756,0.00010247969,0.0000734945],"category_scores_gemma":[0.00024225972,0.00014897985,0.00006796803,0.0004118857,0.00010905795,0.0010863083,0.00023361003,0.000140786,0.00015025516],"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":[0.000004663749,0.000046388028,0.001663102,0.00014878031,0.000017949134,5.886301e-7,0.00018324528,0.0000014118405,0.0011912233,0.18731229,0.031851076,0.77757925],"study_design_scores_gemma":[0.0006483571,0.00027073067,0.022273725,0.000061218016,0.00003955257,0.00006830049,0.00022359718,0.08268041,0.0007307174,0.014544222,0.87778056,0.0006786425],"about_ca_topic_score_codex":0.000019916031,"about_ca_topic_score_gemma":8.7630167e-7,"teacher_disagreement_score":0.9268189,"about_ca_system_score_codex":0.0000679121,"about_ca_system_score_gemma":0.00011903222,"threshold_uncertainty_score":0.8619098},"labels":[],"label_agreement":null},{"id":"W1806134291","doi":"10.5555/1793274.1793337","title":"Integrating structure and meaning: a new method for encoding structure for text classification","year":2008,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; ENCODE; Natural language processing; Encoding (memory); Artificial intelligence; Representation (politics); Word (group theory); Semantics (computer science); Feature (linguistics); Syntactic structure; Curse of dimensionality; Computation; Scheme (mathematics); Information retrieval; Linguistics; Syntax; Algorithm; Mathematics","score_opus":0.054831259281673025,"score_gpt":0.32242067072547426,"score_spread":0.2675894114438012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1806134291","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030757287,0.00005802229,0.99161625,0.003572539,0.00013819124,0.00050975045,0.000009055364,0.00045799537,0.0005624845],"genre_scores_gemma":[0.41047418,0.0000067831306,0.5887297,0.000126954,0.00004354741,0.00002134088,0.0000071921704,0.0000064662604,0.0005838501],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989516,0.000018694322,0.00023980069,0.00045172815,0.00012417907,0.00021395872],"domain_scores_gemma":[0.9990021,0.00031059186,0.00015609957,0.00036293472,0.00010652822,0.0000617349],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000119235396,0.0001544084,0.0001675653,0.00013446495,0.00033407344,0.00016403577,0.0005105815,0.0001375039,0.000014022222],"category_scores_gemma":[0.00031945566,0.000119265555,0.00005069758,0.000245837,0.00004170766,0.0005092772,0.00009226505,0.00010922247,5.59619e-7],"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":[0.0000049889777,0.000003617713,0.00023244423,0.000013013277,0.000008957629,1.1934796e-7,0.0008503989,0.0000053574367,0.048293855,0.7602622,0.0037822488,0.18654278],"study_design_scores_gemma":[0.0010627621,0.00019929257,0.0017386983,0.00002161761,0.000018483594,0.00006295938,0.00097232265,0.29996574,0.1480797,0.51920503,0.028218085,0.00045527495],"about_ca_topic_score_codex":0.000012612544,"about_ca_topic_score_gemma":0.000024266337,"teacher_disagreement_score":0.40739846,"about_ca_system_score_codex":0.000038448914,"about_ca_system_score_gemma":0.00008294035,"threshold_uncertainty_score":0.4863508},"labels":[],"label_agreement":null},{"id":"W1826301668","doi":"10.1109/ijcnn.2003.1223678","title":"A comparison of SOM based document categorization systems","year":2004,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Categorization; Computer science; Artificial intelligence; Self-organizing map; Architecture; Feature (linguistics); Feature vector; Space (punctuation); Unsupervised learning; Text categorization; Machine learning; Data mining; Pattern recognition (psychology); Cluster analysis","score_opus":0.03131328734871104,"score_gpt":0.3084639845942755,"score_spread":0.27715069724556446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1826301668","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":[0.006979523,0.0000853411,0.9888121,0.0016528566,0.0001762305,0.00014623349,2.7669856e-7,0.00045011067,0.0016973385],"genre_scores_gemma":[0.97261804,0.0000024217356,0.027170233,0.000029731675,0.0000055938726,0.000019189783,0.0000029232815,0.0000023867697,0.00014948848],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992734,0.00001339093,0.0002463638,0.00016274571,0.00020255869,0.00010151695],"domain_scores_gemma":[0.9993683,0.000021128493,0.00012881302,0.00039583043,0.0000629248,0.000023012115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008988882,0.00006453174,0.00011814232,0.00010888688,0.000040674124,0.000087958026,0.00046735426,0.00004400665,0.000009299244],"category_scores_gemma":[0.000015228104,0.00005274698,0.000025229912,0.00031383574,0.000030101917,0.00027980772,0.000059158985,0.000037211557,0.000032567434],"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":[9.240194e-7,0.00007232205,0.0016148749,0.000013388077,0.0000034097168,2.112823e-7,0.00011440749,0.0064949854,0.0021931974,0.9861835,0.00023080675,0.003077962],"study_design_scores_gemma":[0.0019773203,0.00046538727,0.005525938,0.000067413035,0.000013560489,0.00000224083,0.0011076356,0.19972149,0.71605724,0.065897256,0.008684771,0.00047977347],"about_ca_topic_score_codex":0.00008561263,"about_ca_topic_score_gemma":0.000003891031,"teacher_disagreement_score":0.9656385,"about_ca_system_score_codex":0.000057357844,"about_ca_system_score_gemma":0.000060903723,"threshold_uncertainty_score":0.21509594},"labels":[],"label_agreement":null},{"id":"W1828567212","doi":"10.1016/j.eswa.2015.09.044","title":"A latent Beta-Liouville allocation model","year":2015,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Latent Dirichlet allocation; Computer science; Prior probability; Dirichlet distribution; Artificial intelligence; Consistency (knowledge bases); Topic model; Machine learning; Categorization; Latent variable; Beta distribution; Pattern recognition (psychology); Mathematics; Bayesian probability; Statistics","score_opus":0.051503094570884714,"score_gpt":0.2743410845641952,"score_spread":0.2228379899933105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1828567212","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":[0.00035964412,0.00078763365,0.9869913,0.004430991,0.000055955363,0.00069816236,0.0000016042517,0.0010466418,0.0056280843],"genre_scores_gemma":[0.9470816,0.000025347721,0.046792876,0.00016728898,0.00005395343,0.0040548733,0.000014795373,0.000013762254,0.0017954918],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988283,0.000022455604,0.00024466327,0.00038630277,0.00032536846,0.00019290597],"domain_scores_gemma":[0.9984105,0.000020174079,0.00013858748,0.0010783058,0.00022219664,0.00013018485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016181632,0.00013354387,0.00013935064,0.00012435892,0.00013981236,0.0001904387,0.00081137544,0.00007246887,0.0000014018954],"category_scores_gemma":[0.0000075888724,0.00010290486,0.00002599591,0.0005095735,0.000053722317,0.00043366823,0.00010594232,0.00007161616,0.00020957204],"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":[0.0000032422074,0.00010004387,0.00030671107,0.000007269909,0.000018362098,4.8849574e-7,0.00078231836,0.004157771,0.00055734586,0.9683524,0.02196291,0.0037511587],"study_design_scores_gemma":[0.0007596466,0.00008166469,0.00021301459,0.000029007324,0.000009229367,0.000031562162,0.0008445185,0.7636127,0.0022487096,0.006393314,0.2252702,0.000506474],"about_ca_topic_score_codex":0.00007807549,"about_ca_topic_score_gemma":0.0000044562757,"teacher_disagreement_score":0.96195906,"about_ca_system_score_codex":0.00011113726,"about_ca_system_score_gemma":0.0001367209,"threshold_uncertainty_score":0.41963384},"labels":[],"label_agreement":null},{"id":"W1845278523","doi":"10.1007/3-540-70659-3_58","title":"Document Classification Using Phrases","year":2002,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Natural language processing; Computer science; Artificial intelligence; Grammar; Classifier (UML); Naive Bayes classifier; Bayes classifier; Pattern recognition (psychology); Linguistics; Support vector machine","score_opus":0.04930136608321829,"score_gpt":0.27855149538897356,"score_spread":0.22925012930575528,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1845278523","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000108161374,0.0005052806,0.9913718,0.0016335549,0.0010674399,0.0003618735,0.0000022077104,0.0005553152,0.0043943347],"genre_scores_gemma":[0.37186825,0.00026836165,0.6251376,0.00083073135,0.00032120544,0.000021499054,0.0000063708612,0.00004379329,0.0015021794],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963338,0.000024959032,0.0005786484,0.0015088498,0.0009856835,0.0005680876],"domain_scores_gemma":[0.9971371,0.00023685151,0.00043586126,0.0019030564,0.00017248346,0.00011463467],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00047363056,0.00047918694,0.0004054573,0.0011160651,0.00029866004,0.0008326078,0.0035984616,0.0003568641,0.00008039853],"category_scores_gemma":[0.000084301464,0.000443213,0.00011835795,0.0007463154,0.0007339805,0.0010506852,0.0010887757,0.00058282854,0.0001298837],"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":[0.0000015345548,0.000029668145,0.000054459535,0.000018969742,0.000008185415,0.000021618802,0.00024448973,0.003035423,0.0005633286,0.18559803,0.000054975702,0.8103693],"study_design_scores_gemma":[0.0002442487,0.000110481,0.00015358765,0.0002500393,0.000011229324,0.000048693913,5.682325e-7,0.623833,0.004045157,0.364692,0.0057681627,0.00084280374],"about_ca_topic_score_codex":0.000011109089,"about_ca_topic_score_gemma":0.000007180289,"teacher_disagreement_score":0.8095265,"about_ca_system_score_codex":0.0006046181,"about_ca_system_score_gemma":0.00025435403,"threshold_uncertainty_score":0.999802},"labels":[],"label_agreement":null},{"id":"W18794550","doi":"10.24348/coria.2005.50","title":"Étude sur l'impact du sous-langage dans la classification automatique d'appels d'offres.","year":2005,"lang":"fr","type":"article","venue":"Association en Recherche d’Information et Applications","topic":"Text and Document Classification Technologies","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":"Université de Montréal","funders":"","keywords":"Humanities; Philosophy","score_opus":0.06243501596119376,"score_gpt":0.34292259833258215,"score_spread":0.2804875823713884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W18794550","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":[0.0051965225,0.0003294883,0.8064092,0.13122678,0.00021791179,0.0016302735,0.00020512949,0.002138933,0.052645802],"genre_scores_gemma":[0.905419,0.004069906,0.06994002,0.0028815842,0.000500408,0.002568377,0.0013052215,0.00007966461,0.013235848],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99390966,0.0021232518,0.0015898593,0.0005941676,0.0010163169,0.0007667321],"domain_scores_gemma":[0.9915797,0.0037063994,0.0019831911,0.0013574355,0.0011211392,0.00025209805],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008017908,0.0005602066,0.00047512626,0.00055503123,0.00056331704,0.0014842032,0.0016666199,0.0017877045,0.00025532322],"category_scores_gemma":[0.0032772839,0.0006117809,0.00035717487,0.0022265161,0.0001613733,0.009256786,0.0002992413,0.0016795077,0.0038876163],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008754136,0.0005986662,0.005188126,0.000086827466,0.00021703517,7.469333e-7,0.021894934,0.0028882232,0.0011345504,0.6535534,0.06887728,0.24555144],"study_design_scores_gemma":[0.0010343906,0.000054531734,0.20986436,0.00006657905,0.00010968938,0.000037061087,0.0020286639,0.23192783,0.0017416569,0.011437483,0.540859,0.0008387798],"about_ca_topic_score_codex":0.00039269318,"about_ca_topic_score_gemma":0.00022256593,"teacher_disagreement_score":0.9002224,"about_ca_system_score_codex":0.0057904758,"about_ca_system_score_gemma":0.0011153002,"threshold_uncertainty_score":0.9996334},"labels":[],"label_agreement":null},{"id":"W1881830221","doi":"10.1111/coin.12064","title":"Document Clustering With Dual Supervision Through Feature Reweighting","year":2015,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Computer science; Feature (linguistics); Brown clustering; Artificial intelligence; Pairwise comparison; Correlation clustering; Pattern recognition (psychology); Fuzzy clustering; Consensus clustering; Data mining; Conceptual clustering; Machine learning; Canopy clustering algorithm","score_opus":0.05995408911021713,"score_gpt":0.3051056388127768,"score_spread":0.24515154970255967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1881830221","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":[0.0033651444,0.0002686328,0.98838633,0.004954608,0.00024901968,0.00014167416,8.7868943e-7,0.00049975235,0.0021339417],"genre_scores_gemma":[0.5979967,0.000010882235,0.40138468,0.00024574113,0.00003859177,0.00001448647,0.000009100088,0.000006551547,0.0002932383],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99856234,0.000036862024,0.00022428062,0.00042202024,0.00053020875,0.00022428678],"domain_scores_gemma":[0.9990165,0.00013707865,0.000108905864,0.00036584018,0.00029145944,0.00008021694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002121207,0.00015792392,0.00012698016,0.000089181194,0.00014255194,0.00029843315,0.0006972788,0.000065587905,0.000013596736],"category_scores_gemma":[0.000064504,0.00012445773,0.000031836462,0.00051381055,0.000089761495,0.0010720165,0.00037227658,0.00016813446,0.00012628519],"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":[0.00002758804,0.00006838173,0.00050056935,0.000017903492,0.00002572777,0.00003707669,0.002940456,0.18403164,0.00004589419,0.7090959,0.0046806014,0.09852829],"study_design_scores_gemma":[0.00031051823,0.0003880777,0.0007132747,0.00010976508,0.000007191028,0.00016405234,0.0013236556,0.52870655,0.005800617,0.44599962,0.015958104,0.00051859306],"about_ca_topic_score_codex":0.000014292062,"about_ca_topic_score_gemma":0.000004808185,"teacher_disagreement_score":0.59463155,"about_ca_system_score_codex":0.00009938571,"about_ca_system_score_gemma":0.00011231773,"threshold_uncertainty_score":0.5075239},"labels":[],"label_agreement":null},{"id":"W1882783948","doi":"10.1007/978-3-642-32584-7_30","title":"Classifying Websites into Non-topical Categories","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Bigram; Classifier (UML); Information retrieval; Web page; Support vector machine; Set (abstract data type); Artificial intelligence; World Wide Web; Trigram","score_opus":0.022527970990159556,"score_gpt":0.26058073308932184,"score_spread":0.2380527620991623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1882783948","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":[0.000103512764,0.0011759119,0.98877645,0.0028007147,0.0017045044,0.00027371984,0.0000010606365,0.00056704687,0.0045971125],"genre_scores_gemma":[0.53021765,0.00016862317,0.4668486,0.00085805776,0.00058347324,0.000025552965,0.000006159328,0.000036305282,0.001255604],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99649465,0.000020121352,0.00053378445,0.0013055269,0.00087977736,0.0007661548],"domain_scores_gemma":[0.9972473,0.00036947257,0.00029963625,0.0017277017,0.00018168082,0.00017425182],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00054670975,0.0005342366,0.0005049454,0.000921961,0.0003822251,0.0008083961,0.00426693,0.0005125146,0.000058919395],"category_scores_gemma":[0.00010860257,0.00046402108,0.00013140276,0.00066877704,0.0011972139,0.0012826284,0.0021694726,0.00093198055,0.00030928472],"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":[0.00000201508,0.000023847646,0.00051894784,0.00003564189,0.000008350339,0.000017379525,0.0006905124,0.00022666754,0.00039822693,0.16253419,0.00009103889,0.83545315],"study_design_scores_gemma":[0.00035723488,0.0002139269,0.0013762964,0.0002861633,0.000016481776,0.00006118992,0.0000017393978,0.08748128,0.01265317,0.861358,0.03468055,0.0015139992],"about_ca_topic_score_codex":0.00002002822,"about_ca_topic_score_gemma":0.000042412034,"teacher_disagreement_score":0.8339392,"about_ca_system_score_codex":0.00036143398,"about_ca_system_score_gemma":0.00038648577,"threshold_uncertainty_score":0.99978113},"labels":[],"label_agreement":null},{"id":"W1888496803","doi":"10.1007/978-3-642-02976-9_46","title":"Automatic Detecting Documents Containing Personal Health Information","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Artificial intelligence; Decision tree; Support vector machine; Natural language processing; Categorization; Information retrieval; Lexical analysis; Text categorization; Naive Bayes classifier; The Internet; Task (project management); Supervised learning; Machine learning; World Wide Web","score_opus":0.01851048022841444,"score_gpt":0.268608716320946,"score_spread":0.25009823609253157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1888496803","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":[0.00016866936,0.00025864854,0.99240816,0.0031565866,0.0006846512,0.00040496854,0.0000016717047,0.0007806205,0.002136052],"genre_scores_gemma":[0.5670185,0.000054800123,0.42822355,0.004347459,0.00013303851,0.000015635134,0.000009676352,0.000016910697,0.00018044445],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968918,0.000028147067,0.00071811216,0.00075046567,0.0009799814,0.00063152326],"domain_scores_gemma":[0.99797356,0.00022307492,0.0006898054,0.000828648,0.00015672263,0.00012818356],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0010237618,0.00040192713,0.00043794498,0.0011393502,0.00044352192,0.0010907501,0.0023647596,0.00023714782,0.000022689035],"category_scores_gemma":[0.00014829186,0.00037740328,0.000093482995,0.0005946736,0.00028814125,0.0023884638,0.0006855178,0.00070157414,0.000076135024],"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":[0.0000012341723,0.0000065798677,0.000023508528,0.00002348933,0.000003979188,0.0000037981783,0.0013069607,0.00039712948,0.000006875664,0.0124420235,0.000018282242,0.9857661],"study_design_scores_gemma":[0.0004345794,0.0005221139,0.0004939598,0.0006048508,0.0000040129103,0.00006266958,0.000003904412,0.8331494,0.00040077223,0.15961343,0.003988742,0.00072159286],"about_ca_topic_score_codex":0.00002308288,"about_ca_topic_score_gemma":0.00001942988,"teacher_disagreement_score":0.98504454,"about_ca_system_score_codex":0.00069620257,"about_ca_system_score_gemma":0.00067381916,"threshold_uncertainty_score":0.99994624},"labels":[],"label_agreement":null},{"id":"W1888927200","doi":"10.3233/ida-2012-00557","title":"Feature ranking fusion for text classifier","year":2012,"lang":"en","type":"article","venue":"Intelligent Data Analysis","topic":"Text and Document Classification Technologies","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":"University of Waterloo; Ontario Tech University","funders":"","keywords":"Artificial intelligence; Pattern recognition (psychology); Classifier (UML); Computer science; Fusion; Machine learning; Natural language processing; Linguistics","score_opus":0.09784571685237035,"score_gpt":0.34321365686519,"score_spread":0.24536794001281964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1888927200","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":[0.00074817624,0.0011712501,0.9920736,0.0047689048,0.00027193344,0.00016544931,0.000049467842,0.00031633303,0.00043491775],"genre_scores_gemma":[0.8752723,0.00035774612,0.121106766,0.0003472598,0.00015425535,0.00004690755,0.0007223816,0.000011518997,0.001980869],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986066,0.000034517227,0.00021973529,0.0005019043,0.00027703325,0.00036020737],"domain_scores_gemma":[0.99705535,0.00016737312,0.00015040682,0.0024654448,0.000077952354,0.00008344525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060271134,0.00014749539,0.00022757346,0.00045872002,0.00017308435,0.0002427693,0.0026503468,0.000116840296,0.00009248909],"category_scores_gemma":[0.0001787043,0.000119164266,0.0001721701,0.0015587885,0.000042202497,0.0012727673,0.000917249,0.00011994542,0.00012807922],"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":[0.00001420052,0.00021912737,0.022342814,0.000019900166,0.0010852681,0.0000015061736,0.0005034483,0.00006062289,0.0011456258,0.15254372,0.111394234,0.7106695],"study_design_scores_gemma":[0.00013775459,0.000026349031,0.00399578,0.0000090887615,0.0006342862,0.0000019210224,0.00036719936,0.13084659,0.009954855,0.0028252725,0.8508313,0.00036965834],"about_ca_topic_score_codex":0.000011967613,"about_ca_topic_score_gemma":0.00001693267,"teacher_disagreement_score":0.8745241,"about_ca_system_score_codex":0.000045735334,"about_ca_system_score_gemma":0.000018530525,"threshold_uncertainty_score":0.4925048},"labels":[],"label_agreement":null},{"id":"W1902658720","doi":"10.5430/air.v4n2p143","title":"A text feature selection method based on category-distribution divergence","year":2015,"lang":"en","type":"article","venue":"Artificial Intelligence Research","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Feature selection; Selection (genetic algorithm); Divergence (linguistics); Artificial intelligence; Computer science; Feature (linguistics); Natural language processing; Pattern recognition (psychology); Distribution (mathematics); Mathematics; Statistics; Linguistics; Philosophy","score_opus":0.24040444128353383,"score_gpt":0.445637965919208,"score_spread":0.20523352463567418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1902658720","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":[0.0016737827,0.00005077785,0.9833659,0.012198643,0.00026944946,0.00032535882,0.0000045976444,0.00047194614,0.0016395377],"genre_scores_gemma":[0.9748663,0.000015185191,0.024269316,0.00008245995,0.00007798951,0.000096705444,0.000016178623,0.000008733034,0.0005671544],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969063,0.00046350269,0.00025811294,0.00063785905,0.001153569,0.00058066286],"domain_scores_gemma":[0.99777865,0.0004178565,0.00007295575,0.00067895954,0.0008571496,0.00019439729],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0031003626,0.00014965048,0.00013752996,0.0003793136,0.00040855454,0.0004190191,0.0013210911,0.00018421398,0.000052293784],"category_scores_gemma":[0.00147859,0.00013348836,0.00005974423,0.0028072493,0.0001864153,0.0004624847,0.0002602459,0.0006456966,0.0012057818],"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":[0.0000496039,0.00016961139,0.0002047632,0.0000054651905,0.000004659455,0.000005961976,0.00021995464,0.0027049733,0.0022272612,0.58102053,0.013703673,0.39968356],"study_design_scores_gemma":[0.000028416,0.00040853466,0.00016032135,0.000012750867,0.0000017364914,0.000003022417,0.0005358858,0.5914442,0.2316163,0.16316654,0.012455077,0.00016719787],"about_ca_topic_score_codex":0.00019602937,"about_ca_topic_score_gemma":0.00004637824,"teacher_disagreement_score":0.9731925,"about_ca_system_score_codex":0.0003777277,"about_ca_system_score_gemma":0.00038317358,"threshold_uncertainty_score":0.9995719},"labels":[],"label_agreement":null},{"id":"W192243523","doi":"10.1007/978-3-319-06483-3_19","title":"Text Representation Using Multi-level Latent Dirichlet Allocation","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Latent Dirichlet allocation; Representation (politics); Computer science; Granularity; Artificial intelligence; Topic model; Pattern recognition (psychology); Machine learning; Natural language processing","score_opus":0.08373228379650947,"score_gpt":0.3067533469916922,"score_spread":0.22302106319518272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W192243523","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014167494,0.0002030735,0.9960099,0.0013997093,0.0010262068,0.00045129622,0.000002381764,0.0004153931,0.0003503737],"genre_scores_gemma":[0.23998398,0.000068842935,0.75811404,0.00059601763,0.000182164,0.00001664054,0.00001188711,0.000029896039,0.0009965071],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966296,0.0000380509,0.0005700994,0.0014316567,0.00082431675,0.0005062632],"domain_scores_gemma":[0.99727976,0.00026592152,0.00045668858,0.001644547,0.00025050182,0.0001025789],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00067611464,0.00040608205,0.0003893128,0.00092878815,0.00026746967,0.0006149736,0.0027072383,0.00033861934,0.000016384929],"category_scores_gemma":[0.00016276068,0.0003769343,0.00010182649,0.00059188856,0.0005157802,0.0006655033,0.001078273,0.0004682446,0.00007286762],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027922601,0.00003116419,0.00027594037,0.000034439898,0.000009323596,0.000010035631,0.00029841665,0.02092676,0.0014013848,0.04304122,0.000027005968,0.93394154],"study_design_scores_gemma":[0.00031241597,0.000052243933,0.0013107519,0.0004092167,0.000009090442,0.000025854679,3.0108671e-7,0.9393402,0.00612346,0.051284455,0.0005153555,0.00061668665],"about_ca_topic_score_codex":0.000029619621,"about_ca_topic_score_gemma":0.000051098486,"teacher_disagreement_score":0.9333248,"about_ca_system_score_codex":0.00037220135,"about_ca_system_score_gemma":0.00031384395,"threshold_uncertainty_score":0.9998683},"labels":[],"label_agreement":null},{"id":"W1935171541","doi":"10.1109/icassp.1997.596083","title":"Accurate keyword spotting using strictly lexical fillers","year":2002,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Keyword spotting; Computer science; Vocabulary; Set (abstract data type); Task (project management); Range (aeronautics); Directory; Natural language processing; Speech recognition; Artificial intelligence; Spotting; Linguistics","score_opus":0.09808095789106017,"score_gpt":0.2754248937137858,"score_spread":0.17734393582272565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1935171541","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":[0.031578004,0.00010731735,0.92952347,0.003986211,0.00022424929,0.00009885131,4.465546e-7,0.0015132837,0.032968163],"genre_scores_gemma":[0.91684586,0.000023289644,0.080586486,0.00029846482,0.000022348124,0.0000031243464,2.9891544e-7,0.0000042267648,0.0022159321],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991431,0.000016976017,0.00017999997,0.00026115985,0.00016678507,0.00023197688],"domain_scores_gemma":[0.9993857,0.000057492212,0.00007037281,0.00041132272,0.00002950233,0.00004556697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008264241,0.00009218868,0.00008654756,0.0001155305,0.00013930415,0.00021447652,0.000695562,0.00006190767,0.00035388628],"category_scores_gemma":[0.00006272277,0.00007687553,0.000041174702,0.0005038758,0.000041892723,0.00059403526,0.00021607956,0.000101689104,0.00022769332],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019559366,0.00012336399,0.0016082738,0.000009070846,0.000022455511,0.000021881058,0.00043945457,0.000674457,0.0035321924,0.5931776,0.024476675,0.37591264],"study_design_scores_gemma":[0.00022012435,0.00003379303,0.00092632,0.000008280199,0.0000030501333,0.000011697858,0.00018729166,0.9660493,0.0058953846,0.0037678527,0.022642901,0.0002540133],"about_ca_topic_score_codex":0.000009682418,"about_ca_topic_score_gemma":4.7446784e-7,"teacher_disagreement_score":0.9653748,"about_ca_system_score_codex":0.000036077963,"about_ca_system_score_gemma":0.000009129817,"threshold_uncertainty_score":0.38748068},"labels":[],"label_agreement":null},{"id":"W1960913922","doi":"10.1007/3-540-44886-1_41","title":"Feature Selection Strategies for Text Categorization","year":2003,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Feature selection; Categorization; Computer science; Selection (genetic algorithm); Text categorization; Feature (linguistics); Rank (graph theory); Artificial intelligence; Set (abstract data type); Filter (signal processing); Function (biology); Representation (politics); Machine learning; Data mining; Pattern recognition (psychology); Mathematics","score_opus":0.018434168115925784,"score_gpt":0.2540111248480112,"score_spread":0.2355769567320854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1960913922","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000010220316,0.00029106706,0.99141425,0.0036839806,0.0012158728,0.00059553946,0.000003350098,0.00049828197,0.0022874472],"genre_scores_gemma":[0.09378729,0.00010033387,0.9001791,0.0016510511,0.00037126942,0.00009519058,0.000027178194,0.000056561494,0.0037320133],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997418,0.000017878012,0.00029534777,0.0012476244,0.00053378346,0.0004873807],"domain_scores_gemma":[0.9982501,0.00020749439,0.00030193035,0.0008295058,0.00034160915,0.000069345464],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004275457,0.00041671548,0.00033421416,0.000810865,0.00033884804,0.0010793868,0.0019822,0.0004907637,0.000009686974],"category_scores_gemma":[0.000082898645,0.00038096806,0.000102251746,0.00078910484,0.0003640897,0.0011655552,0.00027843125,0.0005086085,0.000017300279],"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":[0.0000034384443,0.000016465996,0.00002315113,0.00003387323,0.000006850931,0.0000022931688,0.00020791499,0.0068446198,0.00044427358,0.61062187,0.0007038043,0.38109145],"study_design_scores_gemma":[0.00025896713,0.00021088659,0.000050628973,0.000077815705,0.000008246497,0.000026463047,0.0000010991589,0.17311838,0.00481138,0.79129636,0.029524788,0.0006149675],"about_ca_topic_score_codex":0.0000041198737,"about_ca_topic_score_gemma":0.00003847121,"teacher_disagreement_score":0.38047647,"about_ca_system_score_codex":0.00031220488,"about_ca_system_score_gemma":0.0005656017,"threshold_uncertainty_score":0.99995756},"labels":[],"label_agreement":null},{"id":"W1970187450","doi":"10.1145/2245276.2245457","title":"Enhancing semi-supervised document clustering with feature supervision","year":2012,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"Dalhousie University","funders":"","keywords":"Cluster analysis; Computer science; Pairwise comparison; Feature (linguistics); Artificial intelligence; Brown clustering; Consensus clustering; Data mining; Correlation clustering; Fuzzy clustering; Pattern recognition (psychology); Conceptual clustering; Machine learning; Canopy clustering algorithm","score_opus":0.014138814128383205,"score_gpt":0.24251825036800329,"score_spread":0.2283794362396201,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970187450","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":[0.048054848,0.00031571565,0.939625,0.004755608,0.00023950009,0.00018955131,2.3641532e-7,0.0012320954,0.005587413],"genre_scores_gemma":[0.8502005,0.000024627001,0.14736313,0.00030666654,0.000042896852,0.000023030472,0.0000018426359,0.000007860943,0.0020294755],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989169,0.000022454164,0.00013868893,0.00026468706,0.00027512456,0.00038209956],"domain_scores_gemma":[0.9991334,0.000040880586,0.00004490734,0.000643321,0.000040876293,0.00009658128],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002087986,0.0001481177,0.00012106893,0.00010416132,0.00013432719,0.00020607,0.0006499081,0.00008043425,0.00008960139],"category_scores_gemma":[0.000013725208,0.000100039535,0.000033272077,0.00034371286,0.000026463922,0.0016032368,0.00036921803,0.00013007094,0.00011799026],"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":[0.000049799648,0.00038950457,0.03398388,0.00015987881,0.000105689185,0.000014373537,0.007739639,0.00012016272,0.1493775,0.35289168,0.013774795,0.44139308],"study_design_scores_gemma":[0.0021529375,0.0005209711,0.026691534,0.00022969335,0.00003091601,0.00012764563,0.0035607535,0.02235755,0.837027,0.0028727793,0.10274299,0.001685211],"about_ca_topic_score_codex":0.000012304991,"about_ca_topic_score_gemma":0.000016677997,"teacher_disagreement_score":0.80214566,"about_ca_system_score_codex":0.00005694072,"about_ca_system_score_gemma":0.000019356725,"threshold_uncertainty_score":0.4079494},"labels":[],"label_agreement":null},{"id":"W1975412704","doi":"10.1109/ifsa-nafips.2013.6608380","title":"Neighborhood Rough Sets based Multi-Label classification","year":2013,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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 Alberta","funders":"","keywords":"Multi-label classification; Pattern recognition (psychology); Artificial intelligence; Computer science; Feature (linguistics); Rough set; Data mining; Correlation; Machine learning; Mathematics","score_opus":0.0625039937731114,"score_gpt":0.29024486199336424,"score_spread":0.22774086822025286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975412704","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":[0.0019742423,0.000033105414,0.96614015,0.021320837,0.00015002771,0.00029418623,6.8321526e-7,0.0017304543,0.008356325],"genre_scores_gemma":[0.72703356,0.00000506547,0.27038714,0.00094846275,0.0000075003654,0.00012471768,0.0000048216025,0.00000594857,0.0014827433],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99892575,0.000030673596,0.00022317911,0.0003799838,0.00020347633,0.00023693762],"domain_scores_gemma":[0.9987862,0.000063505926,0.00009817306,0.0008668476,0.00012129111,0.00006396243],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00009584043,0.00012892428,0.00010002818,0.00012600317,0.000107660664,0.00033217377,0.0009971894,0.00010003432,0.0002504485],"category_scores_gemma":[0.000060602782,0.000104823426,0.000035114015,0.0004294092,0.00005024417,0.0011164233,0.00012659139,0.00010119262,0.0018282086],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.1309406e-7,0.00027563525,0.0033241536,0.000006267365,0.000007678559,6.119006e-7,0.000060269824,0.000006546259,0.008347824,0.4885636,0.021116674,0.47828993],"study_design_scores_gemma":[0.0005535416,0.000039537583,0.029713733,0.0000033559065,0.0000020649409,0.0000011805189,0.000051354535,0.9512386,0.00550959,0.009514159,0.003176367,0.00019653962],"about_ca_topic_score_codex":0.00003120588,"about_ca_topic_score_gemma":0.0000031037562,"teacher_disagreement_score":0.951232,"about_ca_system_score_codex":0.000042655807,"about_ca_system_score_gemma":0.000043682736,"threshold_uncertainty_score":0.998949},"labels":[],"label_agreement":null},{"id":"W1978317631","doi":"10.1108/00220410710743306","title":"Machine learning for Asian language text classification","year":2007,"lang":"en","type":"article","venue":"Journal of Documentation","topic":"Text and Document Classification Technologies","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":"York University","funders":"","keywords":"Computer science; Text segmentation; Artificial intelligence; Segmentation; Natural language processing; Language model; Support vector machine; Principle of maximum entropy; Market segmentation; Naive Bayes classifier; Word (group theory); Pattern recognition (psychology); Machine learning; Mathematics","score_opus":0.02066179093718157,"score_gpt":0.3197743031696622,"score_spread":0.29911251223248064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978317631","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":[0.022831835,0.00024358851,0.97183794,0.0033285106,0.00023890426,0.00013991179,4.296693e-7,0.00009195939,0.001286899],"genre_scores_gemma":[0.9399352,0.000042677937,0.059359852,0.00007800588,0.000077964934,0.0000040082423,0.0000060899715,0.0000058768555,0.00049034576],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999041,0.000027171092,0.00043029143,0.00011270753,0.00024857832,0.00014024436],"domain_scores_gemma":[0.9989243,0.00011151973,0.00062002504,0.0001448393,0.00015406702,0.00004525061],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008624198,0.000074430194,0.0001042847,0.00029026787,0.000099995006,0.00016290095,0.00037773608,0.000051399787,0.000019890074],"category_scores_gemma":[0.0001585734,0.00006391241,0.00007403813,0.00026253265,0.00002040178,0.00117448,0.000026902235,0.00013970757,0.000012497727],"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":[0.00004910182,0.00007238411,0.0034449967,0.00001569845,0.000027943504,0.000005207279,0.002003497,0.000042711472,0.05281972,0.101257615,0.00081136875,0.83944976],"study_design_scores_gemma":[0.009529444,0.003440592,0.22282958,0.00018012636,0.0001578871,0.00035266433,0.02903269,0.04828435,0.4248059,0.07898481,0.181192,0.0012099487],"about_ca_topic_score_codex":0.0000035315693,"about_ca_topic_score_gemma":0.000003864681,"teacher_disagreement_score":0.91710335,"about_ca_system_score_codex":0.00009753708,"about_ca_system_score_gemma":0.000029788567,"threshold_uncertainty_score":0.26062724},"labels":[],"label_agreement":null},{"id":"W1983349993","doi":"10.1016/j.neunet.2006.12.005","title":"The learning vector quantization algorithm applied to automatic text classification tasks","year":2007,"lang":"en","type":"article","venue":"Neural Networks","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Vedecká Grantová Agentúra MŠVVaŠ SR a SAV; McGill University","keywords":"Learning vector quantization; Computer science; Artificial intelligence; Classifier (UML); Artificial neural network; Word-sense disambiguation; Categorization; Linde–Buzo–Gray algorithm; Text categorization; Machine learning; Word (group theory); Natural language processing; Pattern recognition (psychology); Vector quantization; Mathematics; WordNet","score_opus":0.020014776508508893,"score_gpt":0.2704345014242594,"score_spread":0.2504197249157505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983349993","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":[0.0059003476,0.00009799671,0.9880517,0.0032306078,0.0005197202,0.00032720118,1.4527177e-7,0.0011949027,0.0006773683],"genre_scores_gemma":[0.9830504,0.000024288414,0.016225997,0.00028873398,0.00012462218,0.000045816083,0.0000070256974,0.00001221142,0.00022091715],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99861753,0.000047005786,0.0003265078,0.00034352383,0.0002752314,0.00039022425],"domain_scores_gemma":[0.99881715,0.00033108421,0.00017597339,0.00053299504,0.00006606085,0.0000767419],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005551036,0.00014023883,0.00011051179,0.00010147215,0.0005413569,0.0003880635,0.00086114457,0.00011152567,0.0000056171525],"category_scores_gemma":[0.000086800595,0.000104465566,0.000039508213,0.0009203138,0.000058972077,0.00023071727,0.00016535634,0.00029167623,0.00007531566],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002928054,0.000011335461,0.0001470745,0.0000013698518,0.000004007058,7.4369586e-7,0.000085677544,0.005170246,0.00052487815,0.0534569,0.00095671887,0.93963814],"study_design_scores_gemma":[0.000101170575,0.000049746726,0.022803705,0.0000049094488,0.0000031407608,0.0000025534468,0.00013561068,0.96713376,0.00035408902,0.0008592818,0.008413307,0.00013871993],"about_ca_topic_score_codex":0.0000033856504,"about_ca_topic_score_gemma":0.000007770441,"teacher_disagreement_score":0.97715,"about_ca_system_score_codex":0.00006255889,"about_ca_system_score_gemma":0.000012919144,"threshold_uncertainty_score":0.4259982},"labels":[],"label_agreement":null},{"id":"W1988996388","doi":"10.5555/777092.777258","title":"Generalized features: their application to classification","year":2002,"lang":"en","type":"article","venue":"National Conference on Artificial Intelligence","topic":"Text and Document Classification Technologies","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":"University of Ottawa","funders":"","keywords":"Computer science; sort; Focus (optics); Set (abstract data type); Feature (linguistics); Process (computing); Artificial intelligence; Machine learning; Information retrieval; Data mining","score_opus":0.16865849311093994,"score_gpt":0.3426979531147663,"score_spread":0.17403946000382636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988996388","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":[0.0017820856,0.00003560359,0.9482105,0.03091697,0.00022899245,0.00044871948,0.0000111766585,0.0006274742,0.017738514],"genre_scores_gemma":[0.9834061,0.00004962458,0.014015427,0.0014409473,0.000086521315,0.00024565187,0.000014148418,0.000009118272,0.0007324096],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979612,0.00006811323,0.00040816824,0.00064044056,0.00065927004,0.0002627585],"domain_scores_gemma":[0.99842685,0.000121767385,0.00015814457,0.000596325,0.0005865328,0.000110390574],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003304261,0.0001992613,0.00015255428,0.00036643964,0.00024362761,0.0003669927,0.0013316544,0.00013384767,0.0002285433],"category_scores_gemma":[0.00031410164,0.00018010757,0.00006347066,0.0009658728,0.000083793275,0.00040709518,0.000111344896,0.0002071023,0.0025038738],"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":[0.0000052032083,0.00008194943,0.0000049780165,0.0000012466794,0.0000035513258,2.0182094e-7,0.000235945,0.0001745904,0.007004846,0.69956064,0.0016758704,0.291251],"study_design_scores_gemma":[0.00003801417,0.000120979945,0.0011266188,0.000015766287,0.0000021999915,0.000003351266,0.00024957547,0.42875525,0.0798503,0.4782806,0.011194696,0.00036264554],"about_ca_topic_score_codex":0.00001018626,"about_ca_topic_score_gemma":0.000021777792,"teacher_disagreement_score":0.98162407,"about_ca_system_score_codex":0.0001498503,"about_ca_system_score_gemma":0.00006252169,"threshold_uncertainty_score":0.9982728},"labels":[],"label_agreement":null},{"id":"W1990582178","doi":"10.4304/jetwi.4.3.207-220","title":"Query Classification using Wikipedia’s Category Graph","year":2012,"lang":"en","type":"article","venue":"Journal of Emerging Technologies in Web Intelligence","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University; University of Waterloo","funders":"","keywords":"Computer science; Information retrieval; Graph; Artificial intelligence; Theoretical computer science","score_opus":0.06849810695475955,"score_gpt":0.32776206232280003,"score_spread":0.2592639553680405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1990582178","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":[0.16976772,0.0052089836,0.81831473,0.0036437234,0.0014509856,0.00014696199,5.953687e-7,0.0009004507,0.00056586135],"genre_scores_gemma":[0.91477495,0.0019940373,0.0831204,0.000028862032,0.00004745817,0.0000075094727,2.2757197e-7,0.000010108827,0.000016424548],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978783,0.00006130955,0.0009163771,0.00024252778,0.0004060814,0.00049541757],"domain_scores_gemma":[0.99797845,0.00016904893,0.0008185911,0.00078324025,0.00019967664,0.000051003884],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011844198,0.00020404595,0.00029377438,0.0015110269,0.00009741636,0.000092142705,0.002496358,0.00025601155,0.000008717761],"category_scores_gemma":[0.0009118887,0.0001767101,0.00012065922,0.0017480328,0.00028408665,0.0019251581,0.00046442618,0.00067230733,0.000015503294],"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":[0.0000149289535,0.00030308502,0.04964181,0.000034269797,0.000036881618,0.000022223809,0.0010024124,0.0005730504,0.029989092,0.48044255,0.0010475212,0.43689218],"study_design_scores_gemma":[0.00057645934,0.0005146806,0.0086958,0.00062062807,0.000069208334,0.0007250963,0.045418635,0.09206907,0.363535,0.46035752,0.0255964,0.0018215033],"about_ca_topic_score_codex":0.00000738293,"about_ca_topic_score_gemma":0.0000038861044,"teacher_disagreement_score":0.7450072,"about_ca_system_score_codex":0.00023236204,"about_ca_system_score_gemma":0.00012924138,"threshold_uncertainty_score":0.72060287},"labels":[],"label_agreement":null},{"id":"W1990688383","doi":"10.1016/j.fss.2009.05.011","title":"Adaptive learning of ordinal–numerical mappings through fuzzy clustering for the objects of mixed features","year":2009,"lang":"en","type":"article","venue":"Fuzzy Sets and Systems","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Thompson Rivers University","funders":"","keywords":"Mathematics; Ordinal regression; Ordinal data; Ordinal optimization; Feature (linguistics); Fuzzy set; Partition (number theory); Fuzzy clustering; Cluster analysis; Fuzzy logic; Algorithm; Similarity (geometry); Pattern recognition (psychology); Artificial intelligence; Data mining; Computer science; Image (mathematics); Combinatorics; Statistics","score_opus":0.032938078485090866,"score_gpt":0.2695217214324401,"score_spread":0.2365836429473492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1990688383","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":[0.030030837,0.0059801126,0.95476246,0.002753364,0.00071612216,0.0010385574,0.000010204527,0.00032227955,0.004386081],"genre_scores_gemma":[0.9941661,0.000059356906,0.0054578367,0.00002509385,0.000026216174,0.000022911305,0.00000134364,0.0000040106606,0.00023712558],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99912614,0.00004815741,0.0002645943,0.0002173907,0.00017681585,0.00016689683],"domain_scores_gemma":[0.9991202,0.00022665692,0.00026191983,0.00027685473,0.000093163166,0.00002125141],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025349128,0.00010790567,0.00024550434,0.000054207907,0.00013971857,0.000080054895,0.00040223936,0.00007179954,3.8051883e-7],"category_scores_gemma":[0.00007438064,0.00006974174,0.000059362374,0.00021587212,0.00006223766,0.00020618687,0.00009705099,0.00010236675,6.9188e-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":[0.00013438944,0.00012737449,0.0016023738,0.0004070129,0.00017242046,0.0000042802694,0.011423487,0.0030756122,0.008298857,0.7227975,0.007060245,0.24489643],"study_design_scores_gemma":[0.0053665233,0.0081953285,0.17092662,0.0018361626,0.00020851771,0.00024264127,0.057211686,0.5903571,0.020762803,0.08664276,0.056073017,0.0021768245],"about_ca_topic_score_codex":0.000077167904,"about_ca_topic_score_gemma":0.0000021326723,"teacher_disagreement_score":0.9641353,"about_ca_system_score_codex":0.000013189485,"about_ca_system_score_gemma":0.000018768967,"threshold_uncertainty_score":0.2843986},"labels":[],"label_agreement":null},{"id":"W1991215305","doi":"10.1145/2245276.2245306","title":"Semi-supervised document clustering with dual supervision through seeding","year":2012,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer 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":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Cluster analysis; Seeding; Computer science; Document clustering; Pairwise comparison; Artificial intelligence; Cluster (spacecraft); Correlation clustering; Data mining; Pattern recognition (psychology); Machine learning; Engineering","score_opus":0.03048652227191006,"score_gpt":0.26419614324423446,"score_spread":0.2337096209723244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991215305","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":[0.08662919,0.00019496222,0.8923949,0.00366597,0.00031042952,0.00019535284,3.384958e-7,0.0014219641,0.015186879],"genre_scores_gemma":[0.8673853,0.0000346549,0.13142654,0.00030303764,0.000057217963,0.000023852026,0.0000017582018,0.000008676621,0.00075894356],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998753,0.00002041112,0.00019345782,0.000287104,0.00032496374,0.00042102984],"domain_scores_gemma":[0.99922127,0.000047791284,0.000050789375,0.00056247524,0.00004192601,0.00007576673],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020622347,0.00015778076,0.00013068116,0.0000767195,0.00016095827,0.0002388193,0.00055152003,0.000068448244,0.00013031166],"category_scores_gemma":[0.00001313683,0.00010984764,0.000034939083,0.000361674,0.000042905816,0.0028731036,0.0005011698,0.0001095479,0.00012589185],"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":[0.000027698883,0.00026876573,0.027843399,0.000064489584,0.0000709296,0.000010249874,0.0090572415,0.0001329715,0.019142801,0.7868605,0.006577208,0.14994374],"study_design_scores_gemma":[0.007554067,0.0017739789,0.052662317,0.00046194604,0.000097708136,0.0005064932,0.019040477,0.12408494,0.48409116,0.02774895,0.2771416,0.004836346],"about_ca_topic_score_codex":0.000027766358,"about_ca_topic_score_gemma":0.0000041329113,"teacher_disagreement_score":0.7807561,"about_ca_system_score_codex":0.00006051575,"about_ca_system_score_gemma":0.000017233411,"threshold_uncertainty_score":0.44794568},"labels":[],"label_agreement":null},{"id":"W1991547055","doi":"10.1016/j.ipm.2013.08.002","title":"An investigation into the application of ensemble learning for entailment classification","year":2013,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Invest Northern Ireland","keywords":"Ensemble learning; Artificial intelligence; Natural language processing; Computer science; Textual entailment; Logical consequence; Machine learning; Information retrieval","score_opus":0.016242983431172527,"score_gpt":0.2641613966963166,"score_spread":0.24791841326514408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991547055","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":[0.01869374,0.000023927623,0.97563034,0.0033183522,0.000047856338,0.0010529207,1.6024494e-7,0.00034627903,0.00088644883],"genre_scores_gemma":[0.9311954,0.000013974835,0.0671566,0.0002558943,0.0000096444055,0.0012146023,0.00005058853,0.0000040102695,0.000099282406],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989577,0.000027492775,0.0004440363,0.0001614916,0.0002764468,0.00013285903],"domain_scores_gemma":[0.9987262,0.000028349916,0.00051715464,0.00042001004,0.00027842252,0.000029850176],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004144228,0.00009766335,0.000077481935,0.0001962327,0.0003140537,0.0004556287,0.00067585835,0.000046569436,0.0000030984647],"category_scores_gemma":[0.000021330408,0.00007611208,0.00002734063,0.0004241472,0.00006198425,0.0043650134,0.00008647625,0.00006625592,0.000050524555],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017037439,0.000016070951,0.00028555878,0.000103197264,0.000005348565,4.184065e-9,0.0029982238,0.0005840923,0.0014747961,0.16107279,0.0002376478,0.8332206],"study_design_scores_gemma":[0.00033708947,0.00008286645,0.019775933,0.00003114904,0.000014756317,4.1425278e-7,0.0067154034,0.87324715,0.010557345,0.07088366,0.018179176,0.00017503937],"about_ca_topic_score_codex":0.000033173805,"about_ca_topic_score_gemma":0.0000017327299,"teacher_disagreement_score":0.9125017,"about_ca_system_score_codex":0.00007296225,"about_ca_system_score_gemma":0.00002616651,"threshold_uncertainty_score":0.4393638},"labels":[],"label_agreement":null},{"id":"W1992565631","doi":"10.1109/dbkda.2010.32","title":"Clustering Relational Database Entities Using K-means","year":2010,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"Ontario Tech University","funders":"","keywords":"Computer science; Cluster analysis; Homogeneous; Data type; Task (project management); Perspective (graphical); Relational database; Vectorization (mathematics); Data mining; Process (computing); The Internet; Information retrieval; Database; Parallel computing; Artificial intelligence; World Wide Web; Programming language; Mathematics","score_opus":0.04904588250724925,"score_gpt":0.27802594019934707,"score_spread":0.2289800576920978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992565631","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":[0.027175048,0.000007652196,0.96349365,0.001007649,0.00041839704,0.000040940933,0.0000013784311,0.0005370757,0.0073182024],"genre_scores_gemma":[0.50588536,0.000002014134,0.49275333,0.00007216885,0.000025733276,0.0000028312409,0.000002940823,0.0000024485862,0.0012531929],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99947786,0.0000059261383,0.000106843785,0.00016658843,0.0001339889,0.00010877031],"domain_scores_gemma":[0.9994529,0.000033524564,0.000037290316,0.00042248826,0.000029789271,0.000024001141],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010201367,0.00005422301,0.000042334294,0.000091482485,0.00011452197,0.00012827589,0.0004286513,0.000038696206,0.00018533129],"category_scores_gemma":[0.000039515333,0.000048293386,0.000019594185,0.00014200534,0.000049092603,0.0009069307,0.00028684587,0.00011871126,0.00006377117],"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":[4.2024888e-7,0.000012609604,0.0015532577,0.0000027123087,0.0000027703466,0.0000010742581,0.00006189339,0.00005447339,0.031782106,0.95990115,0.00058584346,0.0060416935],"study_design_scores_gemma":[0.00021809209,0.000013187251,0.004353672,0.0000086962855,0.0000035082649,0.000026356422,0.00014819874,0.92356366,0.019471608,0.017114004,0.034822203,0.0002568077],"about_ca_topic_score_codex":0.000019059316,"about_ca_topic_score_gemma":0.000036201764,"teacher_disagreement_score":0.9427871,"about_ca_system_score_codex":0.0000102137155,"about_ca_system_score_gemma":0.000027466609,"threshold_uncertainty_score":0.20292476},"labels":[],"label_agreement":null},{"id":"W1996429742","doi":"10.1145/1188966.1189013","title":"Exploring a new space of features for document classification","year":2006,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"Queen's University","funders":"","keywords":"Computer science; Space (punctuation); Information retrieval; Artificial intelligence; Pattern recognition (psychology)","score_opus":0.1032342966842447,"score_gpt":0.2800124430266422,"score_spread":0.17677814634239747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996429742","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":[0.00706323,0.00010834259,0.97525847,0.011278572,0.00014505902,0.0002434825,5.066565e-7,0.00048251543,0.005419851],"genre_scores_gemma":[0.7769954,0.00002389701,0.21568353,0.00002334374,0.00003910543,0.00008458916,0.0000027930384,0.0000040251816,0.007143281],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993351,0.000006585995,0.0001759344,0.00021265903,0.00013885189,0.0001308741],"domain_scores_gemma":[0.99934393,0.0000607031,0.0001052468,0.00041645142,0.000051448285,0.00002221216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000894652,0.000073261486,0.00008796331,0.000113020724,0.00004451452,0.00007785207,0.00046479856,0.000033004722,0.0000075199346],"category_scores_gemma":[0.00002624908,0.00006126112,0.000048734597,0.00024217006,0.00002284129,0.0006256937,0.00006755131,0.00003283112,0.000008489689],"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":[0.0000024383864,0.000017251528,0.00012526677,0.0000060854045,0.0000026635098,5.264803e-8,0.000044035372,0.000012707585,0.009967353,0.9237913,0.014707479,0.051323395],"study_design_scores_gemma":[0.0006505582,0.0001294493,0.036364708,0.000017883824,0.000007929133,0.0000018096304,0.00032953147,0.0019083662,0.60101175,0.27010444,0.089223586,0.00024999655],"about_ca_topic_score_codex":0.00011625108,"about_ca_topic_score_gemma":0.00001657497,"teacher_disagreement_score":0.7699322,"about_ca_system_score_codex":0.00002941268,"about_ca_system_score_gemma":0.000035238652,"threshold_uncertainty_score":0.2498156},"labels":[],"label_agreement":null},{"id":"W1997305228","doi":"10.1109/nlpke.2010.5587767","title":"Automatic classification of documents by formality","year":2010,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","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 Ottawa","funders":"","keywords":"Formality; Computer science; Naive Bayes classifier; Artificial intelligence; Feature selection; Classifier (UML); Support vector machine; Machine learning; Decision tree; Task (project management); Style (visual arts); Data mining; Natural language processing; Engineering","score_opus":0.01347406047579485,"score_gpt":0.2704840205753174,"score_spread":0.25700996009952254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997305228","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":[0.54231024,0.000015508978,0.42826173,0.004654074,0.00033124103,0.0002125033,0.0000024278675,0.0011366168,0.023075635],"genre_scores_gemma":[0.9631925,0.0000034841853,0.036033884,0.0000486146,0.0000036679714,0.000018144141,0.000003362859,0.0000021681835,0.0006941524],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992801,0.000011892136,0.00023684088,0.00016749036,0.00018622866,0.0001174461],"domain_scores_gemma":[0.9990735,0.000035828034,0.00014051113,0.00066689966,0.00005240953,0.00003085379],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019663313,0.000064725136,0.00008244859,0.0000653203,0.00004533733,0.00006487712,0.000809258,0.000067345565,0.00016272705],"category_scores_gemma":[0.000050982297,0.00005233012,0.000029594836,0.00023149342,0.0000678534,0.0007026963,0.000118066484,0.00009331443,0.00006398232],"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":[3.3886312e-7,0.00005873408,0.0023416197,0.00000768875,0.000003952166,4.6783157e-8,0.000044321143,4.0874088e-8,0.14325112,0.6935045,0.008083038,0.15270458],"study_design_scores_gemma":[0.0005884039,0.00009949904,0.16202375,0.000008327847,0.000007644092,0.00000461413,0.00015651161,0.083970286,0.63303053,0.0816893,0.03806393,0.00035718427],"about_ca_topic_score_codex":0.000014358466,"about_ca_topic_score_gemma":0.0000051424136,"teacher_disagreement_score":0.6118152,"about_ca_system_score_codex":0.000009688242,"about_ca_system_score_gemma":0.000021055565,"threshold_uncertainty_score":0.21339604},"labels":[],"label_agreement":null},{"id":"W1999957058","doi":"10.1109/secon.2012.6196948","title":"An enhanced approach for classifying emotions using customized decision tree algorithm","year":2012,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"University of Windsor","funders":"","keywords":"Computer science; Decision tree; Machine learning; Decision tree learning; Artificial intelligence; Data mining; Conversation; Tree (set theory); Statistical classification; Algorithm; Mathematics","score_opus":0.06251321651385613,"score_gpt":0.3311836594047334,"score_spread":0.26867044289087727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999957058","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00972513,0.000041890624,0.98670584,0.00010358714,0.00026689013,0.0003403354,0.0000015453659,0.0009245047,0.0018902946],"genre_scores_gemma":[0.43632618,0.0000033644167,0.56343454,0.000035993424,0.00004416302,0.00004084968,0.000004573011,0.000005807011,0.00010452393],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885446,0.00003234098,0.00024220996,0.00032375794,0.00018658335,0.00036067388],"domain_scores_gemma":[0.99893045,0.00011895798,0.00009985636,0.000671898,0.00007814046,0.00010070473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003721898,0.00013036681,0.00015910254,0.00019189488,0.000275647,0.00019383903,0.00073855184,0.00011116759,0.000014552262],"category_scores_gemma":[0.0000626025,0.000106412925,0.00007909719,0.0003828362,0.000042558873,0.0017240753,0.0001253704,0.000078723475,0.000013929523],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000055504493,0.00019295192,0.00006070442,0.0000036056492,0.000007555498,4.1995534e-8,0.00018130855,0.00013768913,0.017335307,0.055706456,0.0002666754,0.92610216],"study_design_scores_gemma":[0.00081025786,0.000039996972,0.0006563509,0.000005064727,0.000009091596,0.000003401646,0.0003767765,0.9651347,0.027265737,0.004597221,0.0008940554,0.0002073756],"about_ca_topic_score_codex":0.0000046782993,"about_ca_topic_score_gemma":7.7941496e-7,"teacher_disagreement_score":0.964997,"about_ca_system_score_codex":0.000073168776,"about_ca_system_score_gemma":0.000030771876,"threshold_uncertainty_score":0.4339393},"labels":[],"label_agreement":null},{"id":"W2000918452","doi":"10.1145/1281192.1281260","title":"A concept-based model for enhancing text categorization","year":2007,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Natural language processing; Categorization; Sentence; Artificial intelligence; Phrase; Term (time); Weighting; Graph; Information retrieval; Theoretical computer science","score_opus":0.02597749126124376,"score_gpt":0.28160541450190296,"score_spread":0.2556279232406592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000918452","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":[0.0005468536,0.000013664907,0.9955518,0.0013876989,0.000079080746,0.00017657907,5.4099627e-7,0.0007395489,0.0015042159],"genre_scores_gemma":[0.8124476,5.4524094e-7,0.18578984,0.00033361217,0.000010386071,0.000018964112,0.0000039389897,0.0000033380934,0.0013917736],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99936706,0.000003286548,0.00015838425,0.00019707646,0.00010167003,0.00017254542],"domain_scores_gemma":[0.9994721,0.00008748129,0.000057032143,0.0002800289,0.00007532422,0.00002807202],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020703951,0.00006303743,0.00005970197,0.00009536494,0.000083227096,0.0000735563,0.00037192795,0.00005345253,0.000007813404],"category_scores_gemma":[0.000053285807,0.00005477833,0.000029951454,0.00021829043,0.000025300686,0.00028164926,0.000036692294,0.000031667223,0.000013702164],"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":[0.000002687566,0.000022148297,0.000038080885,0.0000040722525,0.000001770857,1.6628174e-7,0.00017939959,0.0023504067,0.009137586,0.9396791,0.0008059966,0.0477786],"study_design_scores_gemma":[0.00018281348,0.000021857799,0.00005017675,0.0000016441414,0.0000010460719,1.6201683e-7,0.000050967126,0.7843188,0.1988266,0.015666634,0.0008055213,0.00007376039],"about_ca_topic_score_codex":0.0000042536503,"about_ca_topic_score_gemma":0.000058805428,"teacher_disagreement_score":0.9240125,"about_ca_system_score_codex":0.0000362874,"about_ca_system_score_gemma":0.00005388312,"threshold_uncertainty_score":0.22337955},"labels":[],"label_agreement":null},{"id":"W2005656884","doi":"10.1109/iccitechnology.2013.6579523","title":"Truncated singular value decomposition for semantic-based data retrieval","year":2013,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"Université du Québec à Montréal","funders":"Université du Québec à Trois-Rivières","keywords":"Indexation; Vector space model; Computer science; Search engine indexing; Weighting; Dimension (graph theory); Information retrieval; Singular value decomposition; Abstraction; Representation (politics); Explicit semantic analysis; Vector space; Knowledge representation and reasoning; Data mining; Natural language processing; Artificial intelligence; Semantic computing; Mathematics; Semantic technology; Semantic Web","score_opus":0.04307560925490692,"score_gpt":0.3085439826486582,"score_spread":0.26546837339375123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005656884","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":[0.01175824,0.000026157824,0.97488016,0.011289623,0.00015124533,0.00044814643,0.0000047946055,0.0010282662,0.00041334738],"genre_scores_gemma":[0.67456234,0.0000019111449,0.3245518,0.000451252,0.000016574215,0.000018610675,0.000122059224,0.0000060314464,0.00026945787],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898225,0.000021644557,0.00019793502,0.00044315346,0.00016364724,0.00019139698],"domain_scores_gemma":[0.9981513,0.0001244121,0.000077283665,0.0014944958,0.0001127987,0.000039721635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023404004,0.00009478896,0.00010424134,0.000102216545,0.00012196304,0.0003320293,0.001571256,0.00007117926,0.000053799544],"category_scores_gemma":[0.00013303423,0.000079236546,0.00003201044,0.00029627766,0.00004046888,0.00092402345,0.00024977812,0.00005008236,0.00014564588],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027907068,0.00033344567,0.00051341683,0.000051365543,0.00004770084,0.0000019964175,0.000069922404,0.000109733424,0.10943051,0.6814853,0.086197056,0.12173167],"study_design_scores_gemma":[0.00045919133,0.00008517909,0.0018742314,0.000008658789,0.0000076177284,0.0000013019915,0.000015476859,0.8718116,0.089225315,0.030517155,0.005824572,0.00016969339],"about_ca_topic_score_codex":0.000033029737,"about_ca_topic_score_gemma":0.0000012568757,"teacher_disagreement_score":0.8717019,"about_ca_system_score_codex":0.000026749154,"about_ca_system_score_gemma":0.00004842992,"threshold_uncertainty_score":0.32311726},"labels":[],"label_agreement":null},{"id":"W2009275125","doi":"10.4304/jetwi.2.3.160-166","title":"A Novel Class-Based Data Fusion Technique for Information Retrieval","year":2010,"lang":"en","type":"article","venue":"Journal of Emerging Technologies in Web Intelligence","topic":"Text and Document Classification Technologies","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 Ottawa","funders":"","keywords":"Computer science; Class (philosophy); Information retrieval; Fusion; Artificial intelligence; Data mining","score_opus":0.04809799884645045,"score_gpt":0.3307790280869064,"score_spread":0.28268102924045596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009275125","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":[0.0038498251,0.00008158377,0.98566157,0.0085392585,0.0007284226,0.00038382845,0.000012335875,0.00063901884,0.00010416498],"genre_scores_gemma":[0.570331,0.00012097148,0.42945692,0.000044703313,0.000015854293,0.000016972572,0.0000038958806,0.000005189224,0.000004486077],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9980687,0.000013980003,0.0009571794,0.00026825373,0.0003927732,0.00029912597],"domain_scores_gemma":[0.9967816,0.000321768,0.0008614131,0.0015958722,0.0004104909,0.000028852735],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0018268075,0.00017668892,0.00025277512,0.0013312686,0.00010236985,0.00017575252,0.0060636047,0.00035405395,0.0000050681465],"category_scores_gemma":[0.0052441284,0.00014924507,0.00007938097,0.0013828146,0.00022336298,0.002424024,0.0010394942,0.00093446614,0.0000049218074],"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":[0.000092821734,0.00019851909,0.0005790189,0.000064159234,0.000015915957,0.0000061371634,0.000135312,0.00036349066,0.3824166,0.17883097,0.0020936048,0.43520343],"study_design_scores_gemma":[0.000385427,0.00035683188,0.00006847393,0.00016733665,0.000009216999,0.00008021516,0.0010276382,0.16977824,0.7067143,0.04388866,0.077186026,0.00033766017],"about_ca_topic_score_codex":0.0000023754135,"about_ca_topic_score_gemma":0.000014097027,"teacher_disagreement_score":0.5664812,"about_ca_system_score_codex":0.000079573576,"about_ca_system_score_gemma":0.0002670889,"threshold_uncertainty_score":0.99931407},"labels":[],"label_agreement":null},{"id":"W2011200591","doi":"10.7152/acro.v23i1.14234","title":"Classification in Terms of Basic Concepts","year":2013,"lang":"en","type":"article","venue":"Advances in Classification Research Online","topic":"Text and Document Classification Technologies","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 Alberta","funders":"","keywords":"Computer science; Natural language processing; Data science; Artificial intelligence","score_opus":0.10644580374751796,"score_gpt":0.447580356272246,"score_spread":0.3411345525247281,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011200591","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":[0.75877255,0.00444882,0.11715846,0.07005387,0.0008381454,0.0054522944,0.000047446716,0.0011294682,0.04209897],"genre_scores_gemma":[0.9801252,0.0023553083,0.016531153,0.000053411426,0.000025043015,0.00045171968,0.00003664227,0.000011338663,0.00041017705],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99692327,0.0003202597,0.0008306561,0.0006668434,0.00076066883,0.0004982937],"domain_scores_gemma":[0.9974027,0.0006856921,0.00027207658,0.0012109089,0.00035045654,0.00007815622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011168778,0.00015829066,0.00026115729,0.0011656401,0.00007159134,0.00010194532,0.0017902134,0.00015853358,0.00007877342],"category_scores_gemma":[0.00083697936,0.00014588346,0.00004357931,0.0028743802,0.0005351477,0.0023559774,0.00024512428,0.00055569503,0.0001280615],"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":[0.000010159761,0.00060046185,0.0760667,0.000051367744,0.0000029613457,0.0000017701589,0.00026728865,0.00004922096,0.028724886,0.44419232,0.0004282549,0.4496046],"study_design_scores_gemma":[0.00078695326,0.00013901982,0.7406653,0.00011863581,8.996542e-7,0.000001641701,0.0014051653,0.07447743,0.0048470693,0.16143979,0.01586839,0.00024968814],"about_ca_topic_score_codex":0.00007172518,"about_ca_topic_score_gemma":0.00020662975,"teacher_disagreement_score":0.6645986,"about_ca_system_score_codex":0.0002454787,"about_ca_system_score_gemma":0.00010564684,"threshold_uncertainty_score":0.5948955},"labels":[],"label_agreement":null},{"id":"W2012971775","doi":"10.1080/0952813x.2012.721010","title":"Naive Bayes text classifiers: a locally weighted learning approach","year":2012,"lang":"en","type":"article","venue":"Journal of Experimental & Theoretical Artificial Intelligence","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":107,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Naive Bayes classifier; Computer science; Artificial intelligence; Machine learning; Conditional independence; Bayes error rate; Bayesian programming; Bayes' theorem; Benchmark (surveying); Complement (music); Bayes classifier; Bayesian probability; Support vector machine; Bayes factor","score_opus":0.036113385853511676,"score_gpt":0.3060859303784622,"score_spread":0.26997254452495056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012971775","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":[0.053124797,0.0012238293,0.93677765,0.00093139155,0.00060395023,0.00014509082,4.2461423e-7,0.00015778455,0.007035095],"genre_scores_gemma":[0.95501345,0.000043761047,0.04449932,0.00013580834,0.00023386966,0.000010943804,8.113285e-7,0.000014438467,0.000047568865],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9974698,0.00020281629,0.0008520248,0.00027971735,0.0006692237,0.0005264455],"domain_scores_gemma":[0.998501,0.0002479359,0.00042004758,0.00034235048,0.00020553349,0.00028312157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00091446884,0.00023965049,0.0003270722,0.00023734818,0.00021048018,0.0002729346,0.0012912595,0.00017486193,0.00033469303],"category_scores_gemma":[0.00027280318,0.00018329221,0.00021040946,0.00051437883,0.00088985945,0.0011552327,0.00032856414,0.0006530599,0.0001733914],"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":[0.000085470594,0.00060600543,0.00008845663,0.0000034482507,0.000028058705,0.000006149906,0.0015834287,0.000024334468,0.026269354,0.92854416,0.00009306895,0.042668086],"study_design_scores_gemma":[0.00008786885,0.00079570286,0.000033892236,0.000039791255,0.000015261156,0.00012545454,0.0072027193,0.028435882,0.781793,0.18001346,0.0011393143,0.0003176664],"about_ca_topic_score_codex":0.0000018926444,"about_ca_topic_score_gemma":6.1109716e-8,"teacher_disagreement_score":0.90188867,"about_ca_system_score_codex":0.00013729956,"about_ca_system_score_gemma":0.00006618175,"threshold_uncertainty_score":0.7474439},"labels":[],"label_agreement":null},{"id":"W2013023084","doi":"10.1007/s10994-013-5371-6","title":"Beam search algorithms for multilabel learning","year":2013,"lang":"en","type":"article","venue":"Machine Learning","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":90,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Inference; Beam search; Computer science; Machine learning; Artificial intelligence; Probabilistic logic; Classifier (UML); Task (project management); Range (aeronautics); Algorithm; Search algorithm","score_opus":0.031059016798618035,"score_gpt":0.28921241142287696,"score_spread":0.2581533946242589,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013023084","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":[0.039460715,0.00026385646,0.95220774,0.0039168014,0.0001526392,0.0004657455,7.0607626e-7,0.0019241988,0.0016076122],"genre_scores_gemma":[0.8799031,0.00002405072,0.10918187,0.000109933266,0.000051002815,0.00016328624,0.000014766971,0.0000203198,0.010531713],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987253,0.000060504957,0.00020204856,0.00039780943,0.00022230898,0.0003920475],"domain_scores_gemma":[0.9991853,0.0002253539,0.00008975557,0.00031502347,0.000117394266,0.000067138506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036615905,0.00014506347,0.00014942823,0.00017296703,0.00044022218,0.00037148324,0.0007656517,0.000083667706,0.000101856014],"category_scores_gemma":[0.00031967578,0.00012957207,0.000068359375,0.0003135354,0.00004708021,0.00056961353,0.00033942104,0.00044856878,0.0003290929],"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":[0.0000029000173,0.000051733765,0.016837971,0.000024703733,0.000020367277,0.0000013881217,0.00074068265,0.004272901,0.008324143,0.011920179,0.00091141846,0.9568916],"study_design_scores_gemma":[0.00048738113,0.0001861828,0.0051194467,0.000010289276,0.000003086764,0.0000039642655,0.00022140346,0.9297019,0.006100121,0.0013954606,0.056539353,0.0002314131],"about_ca_topic_score_codex":0.00013530823,"about_ca_topic_score_gemma":0.0000020858865,"teacher_disagreement_score":0.9566602,"about_ca_system_score_codex":0.000036759953,"about_ca_system_score_gemma":0.000021623964,"threshold_uncertainty_score":0.5283796},"labels":[],"label_agreement":null},{"id":"W2016325519","doi":"10.1016/j.ipl.2003.09.002","title":"A new differential LSI space-based probabilistic document classifier","year":2003,"lang":"en","type":"article","venue":"Information Processing Letters","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Northern British Columbia","funders":"","keywords":"Classifier (UML); Probabilistic logic; Probabilistic classification; Computer science; Search engine indexing; Artificial intelligence; Pattern recognition (psychology); Data mining; A priori and a posteriori; Document classification; Adaptability; Machine learning; Support vector machine; Naive Bayes classifier","score_opus":0.011591561788639012,"score_gpt":0.22220464448286778,"score_spread":0.21061308269422876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016325519","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":[0.0060921386,0.000019775965,0.9752547,0.015176122,0.00027991188,0.00023709296,5.334801e-7,0.00077043095,0.0021692754],"genre_scores_gemma":[0.9063312,0.0000014037616,0.09048315,0.002885533,0.000021829319,0.000058143884,0.000010084991,0.000006764216,0.00020187724],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986607,0.000033717894,0.00039809832,0.00020360811,0.00041065173,0.00029325584],"domain_scores_gemma":[0.9990957,0.000033178156,0.00028279133,0.00042006213,0.00008020216,0.00008807869],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00015125534,0.00017700059,0.0001288748,0.000267087,0.00019974196,0.0010663603,0.00056625344,0.000077806035,0.00006707586],"category_scores_gemma":[0.0001256397,0.0001550285,0.000054055614,0.0004903569,0.000060640763,0.0033079402,0.000052133866,0.00015268444,0.00015816775],"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":[0.00001879472,0.00006738297,0.00056727347,0.00023943759,0.000021515476,0.0000026807534,0.0020337065,0.0014787947,0.0038331642,0.45346138,0.034815487,0.5034604],"study_design_scores_gemma":[0.0066084564,0.00027355095,0.006397063,0.0004001215,0.00007084514,0.00004452365,0.0006231376,0.11487887,0.08724255,0.062691264,0.71820176,0.0025678305],"about_ca_topic_score_codex":0.0000052933415,"about_ca_topic_score_gemma":6.533801e-7,"teacher_disagreement_score":0.90023905,"about_ca_system_score_codex":0.00013428369,"about_ca_system_score_gemma":0.00025510683,"threshold_uncertainty_score":0.9999706},"labels":[],"label_agreement":null},{"id":"W2018764947","doi":"10.1016/j.ipm.2011.11.001","title":"A three-phase method for patent classification","year":2012,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"McGill University","keywords":"Phase (matter); Computer science; Information retrieval; Chemistry","score_opus":0.07881797612441159,"score_gpt":0.3411085603720877,"score_spread":0.2622905842476761,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2018764947","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015502256,0.00008875235,0.991313,0.002328967,0.00022820904,0.0006231918,0.0000022183606,0.0007531848,0.0045074793],"genre_scores_gemma":[0.3796265,0.0000121821095,0.61898863,0.00055021315,0.00003052516,0.00061514863,0.000039016904,0.0000054894667,0.00013227668],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99886626,0.000011095943,0.00040520835,0.00014497191,0.00027380648,0.0002986437],"domain_scores_gemma":[0.9990601,0.000024977418,0.00032262565,0.00040111435,0.00013287515,0.000058321588],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066073943,0.00012529104,0.0000981699,0.00028390795,0.00023758183,0.0004575102,0.0005704798,0.000056518154,0.000007982271],"category_scores_gemma":[0.000029490544,0.00011154906,0.00004664606,0.00041985788,0.000021218348,0.005439035,0.0001525608,0.000058364934,0.000110971116],"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":[0.000004738677,0.000055950357,0.000038597187,0.00008757296,0.000007898981,3.1062186e-8,0.00038473302,0.000008977382,0.000024602343,0.29044896,0.0021065061,0.7068314],"study_design_scores_gemma":[0.0014842468,0.00006670636,0.00509353,0.000043950797,0.00003367876,0.0000033888987,0.000947761,0.51578045,0.0016373149,0.031780288,0.44277814,0.00035054536],"about_ca_topic_score_codex":0.0000018339113,"about_ca_topic_score_gemma":3.2459755e-7,"teacher_disagreement_score":0.70648086,"about_ca_system_score_codex":0.000091957474,"about_ca_system_score_gemma":0.000019857116,"threshold_uncertainty_score":0.45488384},"labels":[],"label_agreement":null},{"id":"W2022780779","doi":"10.5539/cis.v4n6p48","title":"Semi-Automatic Labeling of Training Data Sets in Text Classification","year":2011,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Carelessness; Computer science; Set (abstract data type); Training set; Process (computing); Reduction (mathematics); Data set; Data mining; Data reduction; Information retrieval; Artificial intelligence; Labeled data","score_opus":0.13891772596855814,"score_gpt":0.30321141967432413,"score_spread":0.164293693705766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022780779","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":[0.1339609,0.00003785998,0.8600116,0.00032206002,0.00024012303,0.00018842319,0.0000035201028,0.0002510984,0.0049844454],"genre_scores_gemma":[0.8671703,0.000030385034,0.13266532,0.00011879905,0.000003522255,0.000004190774,0.000004752513,0.000001025533,0.0000017534217],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891174,0.000014916513,0.00041814486,0.00021327585,0.00027574156,0.00016618118],"domain_scores_gemma":[0.9988643,0.000043629683,0.00021321718,0.0007269015,0.00010934374,0.000042615313],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092246954,0.000074128744,0.00010748787,0.00051074306,0.00009805045,0.00017408124,0.0017025676,0.00003540204,0.0000055355276],"category_scores_gemma":[0.00008698011,0.000065643944,0.000008894547,0.001144739,0.0002418212,0.013202845,0.000663743,0.000072602736,0.000015136543],"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":[7.8305555e-7,0.000015863847,0.0016556905,0.000020967678,0.0000012775918,1.813256e-7,0.007845432,0.000011911037,0.0003430053,0.08522769,0.00007534465,0.90480185],"study_design_scores_gemma":[0.00017410185,0.000031257812,0.10029649,0.000036344358,0.0000010440616,0.0000060350326,0.000583965,0.8954082,0.0011649044,0.0017875382,0.0004127713,0.00009735397],"about_ca_topic_score_codex":0.000008525418,"about_ca_topic_score_gemma":9.38638e-7,"teacher_disagreement_score":0.9047045,"about_ca_system_score_codex":0.000020783928,"about_ca_system_score_gemma":0.000112034075,"threshold_uncertainty_score":0.9571744},"labels":[],"label_agreement":null},{"id":"W2024888043","doi":"10.1145/2340416.2340421","title":"A unified framework for document clustering with dual supervision","year":2012,"lang":"en","type":"article","venue":"ACM SIGAPP Applied Computing Review","topic":"Text and Document Classification Technologies","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":"Dalhousie University","funders":"","keywords":"Cluster analysis; Computer science; Seeding; Document clustering; Correlation clustering; Conceptual clustering; Brown clustering; Data mining; Single-linkage clustering; Artificial intelligence; Clustering high-dimensional data; Pairwise comparison; Constrained clustering; CURE data clustering algorithm; Pattern recognition (psychology); Physics","score_opus":0.03878235484616066,"score_gpt":0.3065368105442365,"score_spread":0.2677544556980758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024888043","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016014398,0.012723146,0.9791993,0.003600666,0.00021818579,0.0012269999,6.194441e-7,0.00088804815,0.00054160587],"genre_scores_gemma":[0.442175,0.001374865,0.5547707,0.001367774,0.00011118644,0.00015164292,0.000006898459,0.000019562372,0.000022374381],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99812204,0.00003514728,0.00045462357,0.0004861394,0.00032528045,0.0005767912],"domain_scores_gemma":[0.99739456,0.00060060684,0.00026317738,0.0015555912,0.00006636799,0.00011967106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008668466,0.00026934737,0.00041741313,0.000080070226,0.00024828475,0.00016651355,0.0014845923,0.00010294497,0.00001377781],"category_scores_gemma":[0.00019958688,0.00020638527,0.000086102,0.0005964527,0.000050255967,0.00030274296,0.0010393898,0.00022424209,0.00007155957],"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":[0.0000066168873,0.000049381964,0.00010161514,0.00073777395,0.000024655174,5.754928e-7,0.00023529297,0.00002065449,0.00013157456,0.5456752,0.0010979734,0.45191866],"study_design_scores_gemma":[0.003902562,0.00096959143,0.0031893738,0.018374704,0.000424719,0.00017841213,0.0007476809,0.011886118,0.012202852,0.3155621,0.6280406,0.00452127],"about_ca_topic_score_codex":0.0000018145331,"about_ca_topic_score_gemma":2.9918988e-7,"teacher_disagreement_score":0.62694263,"about_ca_system_score_codex":0.000063079475,"about_ca_system_score_gemma":0.00003471536,"threshold_uncertainty_score":0.8416147},"labels":[],"label_agreement":null},{"id":"W2036162726","doi":"10.1142/s0218001413500110","title":"THE USE OF WEAK ESTIMATORS TO ACHIEVE LANGUAGE DETECTION AND TRACKING IN MULTILINGUAL DOCUMENTS","year":2013,"lang":"en","type":"article","venue":"International Journal of Pattern Recognition and Artificial Intelligence","topic":"Text and Document Classification Technologies","field":"Computer Science","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":"Carleton University","funders":"","keywords":"Estimator; Computer science; Variety (cybernetics); Perspective (graphical); Class (philosophy); Artificial intelligence; Word (group theory); Tracking (education); Machine learning; Natural language processing; Mathematics; Statistics","score_opus":0.09369886442347809,"score_gpt":0.340577001474837,"score_spread":0.24687813705135891,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036162726","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":[0.70606434,0.000033725166,0.2919609,0.0015599158,0.00027929293,0.000082017425,0.0000020035664,0.000010793262,0.000007007941],"genre_scores_gemma":[0.9963353,0.000115673865,0.0033906954,0.00010698713,0.000032427324,0.000006020551,5.8070447e-7,0.0000029672112,0.000009337249],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99908316,0.00004217842,0.00045293223,0.0001143985,0.00021862698,0.00008872262],"domain_scores_gemma":[0.999112,0.0002355557,0.0002535648,0.0000739207,0.00028294214,0.000042021507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022788458,0.000068367386,0.00008447816,0.00023465905,0.000045399065,0.00036044812,0.00029125254,0.000033527653,0.000013480692],"category_scores_gemma":[0.00029902245,0.000051559648,0.000027560616,0.00011652499,0.00006576869,0.0007772397,0.000088680055,0.00012088033,0.00001355789],"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":[0.000017721728,0.000030375026,0.0010136481,0.000001943375,0.000010317627,0.000003499691,0.0007671411,0.000033848668,0.008912634,0.00022790337,0.000005431094,0.9889755],"study_design_scores_gemma":[0.00037216587,0.0007480595,0.044087876,0.00057350483,0.0000175609,0.00021876078,0.008330316,0.09379746,0.76149,0.089087665,0.0007952519,0.00048137244],"about_ca_topic_score_codex":0.00014452294,"about_ca_topic_score_gemma":0.00013019469,"teacher_disagreement_score":0.98849416,"about_ca_system_score_codex":0.000023338163,"about_ca_system_score_gemma":0.000011503801,"threshold_uncertainty_score":0.34758094},"labels":[],"label_agreement":null},{"id":"W2048541556","doi":"10.1007/s10044-014-0382-x","title":"Discriminative learning of generative models: large margin multinomial mixture models for document classification","year":2014,"lang":"en","type":"article","venue":"Pattern Analysis and Applications","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Discriminative model; Generative model; Artificial intelligence; Computer science; Margin (machine learning); Multinomial distribution; Generative grammar; Pattern recognition (psychology); Machine learning; Mixture model; Support vector machine; Mathematics; Statistics","score_opus":0.029579852196899705,"score_gpt":0.2820173542255078,"score_spread":0.2524375020286081,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2048541556","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":[0.0023005512,0.00007001024,0.99509895,0.0015547411,0.000008433798,0.0003865246,0.000019525352,0.00010044101,0.00046082598],"genre_scores_gemma":[0.97688335,0.000074216565,0.021779831,0.000077047574,0.000028889364,0.0008431073,0.00010593,0.0000066151583,0.0002010046],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883395,0.00006525381,0.00031998134,0.00045826857,0.00015394375,0.0001686096],"domain_scores_gemma":[0.9989088,0.00012416637,0.00030180105,0.00044934414,0.00016804539,0.000047814785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000294901,0.00013476326,0.00024909465,0.0002530944,0.00024269415,0.000107702916,0.00039662633,0.000069986774,0.0000053827303],"category_scores_gemma":[0.00001641545,0.000116977986,0.00013169911,0.00053321075,0.000059528298,0.00035826617,0.00012366932,0.00009125947,0.0000022746024],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000026548607,0.00010108172,0.0014654397,0.00002071497,0.00016551891,1.8385824e-8,0.0008248245,0.0051655895,0.0012918435,0.7823889,0.00007590415,0.20849751],"study_design_scores_gemma":[0.0002559019,0.000022894887,0.0022491855,0.0000036735555,0.00014812915,1.13936316e-7,0.00032056266,0.9414019,0.0021810767,0.05207989,0.0012059778,0.00013070689],"about_ca_topic_score_codex":0.000025235408,"about_ca_topic_score_gemma":0.000026378688,"teacher_disagreement_score":0.9745828,"about_ca_system_score_codex":0.00002742094,"about_ca_system_score_gemma":0.000011876653,"threshold_uncertainty_score":0.4770224},"labels":[],"label_agreement":null},{"id":"W2054808906","doi":"10.1145/2494266.2494279","title":"Interactive text document clustering using feature labeling","year":2013,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Cluster analysis; Term (time); Discriminative model; Document clustering; Heuristic; Selection (genetic algorithm); Artificial intelligence; Cluster (spacecraft); Information retrieval; Data mining; Pattern recognition (psychology)","score_opus":0.019989052617821218,"score_gpt":0.2722645220177291,"score_spread":0.25227546939990786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054808906","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":[0.027550977,0.00007876521,0.9571991,0.0071984665,0.0003223914,0.00023693185,1.5416153e-7,0.00089656684,0.00651664],"genre_scores_gemma":[0.73481494,0.000007649077,0.26254725,0.00032044432,0.000019178684,0.000021048067,4.5841918e-7,0.0000049625423,0.002264055],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992352,0.000016888058,0.00013192123,0.0002697685,0.0001413698,0.00020484331],"domain_scores_gemma":[0.9993508,0.00004478387,0.00007322018,0.00041947945,0.000071318274,0.000040429488],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006692224,0.00010695511,0.000091967806,0.000112996575,0.000105544816,0.000494062,0.0006244449,0.00005915971,0.00017868001],"category_scores_gemma":[0.000026556305,0.00008472516,0.000034005887,0.00024406565,0.000024382798,0.0015402763,0.00047877154,0.00013403928,0.00029992923],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000049630007,0.00009493405,0.0011775799,0.000028601675,0.00007371306,0.0000071217332,0.0017963625,0.00066040683,0.10202619,0.15634058,0.016930345,0.7208592],"study_design_scores_gemma":[0.00078562053,0.00012846268,0.003437927,0.00012008454,0.0000124187545,0.000050531475,0.0028186452,0.81446236,0.10847504,0.047016855,0.021752428,0.00093961635],"about_ca_topic_score_codex":0.000089303314,"about_ca_topic_score_gemma":0.0000056063423,"teacher_disagreement_score":0.81380194,"about_ca_system_score_codex":0.00008388819,"about_ca_system_score_gemma":0.000016919415,"threshold_uncertainty_score":0.47642514},"labels":[],"label_agreement":null},{"id":"W2055849934","doi":"10.1111/j.1467-8640.2010.00357.x","title":"AN EFFICIENT MODEL FOR ENHANCING TEXT CATEGORIZATION USING SENTENCE SEMANTICS","year":2010,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Text and Document Classification Technologies","field":"Computer 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 Waterloo","funders":"","keywords":"Natural language processing; Categorization; Computer science; Sentence; Phrase; Artificial intelligence; Term (time); Meaning (existential); Semantics (computer science); Set (abstract data type); Word (group theory); Linguistics; Psychology","score_opus":0.050186321382605814,"score_gpt":0.33345492317476794,"score_spread":0.2832686017921621,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055849934","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":[0.03545609,0.000013710152,0.96309835,0.0003997252,0.0004058394,0.00024533502,0.0000041240464,0.00034567245,0.000031168005],"genre_scores_gemma":[0.60317343,0.00000134469,0.39667806,0.0000677257,0.000025467916,0.000013896576,0.000010933104,0.000006174734,0.000022927294],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873495,0.000014532474,0.00032162675,0.00043239215,0.0002715967,0.00022488748],"domain_scores_gemma":[0.9987645,0.00017175713,0.00015666203,0.00040378392,0.0004336771,0.00006960686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025229008,0.0001358497,0.000108491666,0.00016264952,0.00026974187,0.0002454647,0.0008670637,0.000083169914,0.0000068438344],"category_scores_gemma":[0.000129087,0.0001370383,0.000045975576,0.00037495804,0.00009867283,0.00047323204,0.00010708431,0.00014458733,0.000019416671],"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":[0.0000012995961,0.000041349085,0.000037702524,0.000005926459,0.0000019832685,2.2647627e-7,0.00024707,0.6120922,0.008512221,0.37227297,0.000009931422,0.00677711],"study_design_scores_gemma":[0.000035865967,0.000023807233,0.00007107913,0.000007054099,0.0000033742836,0.000006775845,0.00009637201,0.8731547,0.021122439,0.105308466,0.000020523126,0.00014951339],"about_ca_topic_score_codex":0.000005966288,"about_ca_topic_score_gemma":0.000013796783,"teacher_disagreement_score":0.5677174,"about_ca_system_score_codex":0.000033095734,"about_ca_system_score_gemma":0.00015877289,"threshold_uncertainty_score":0.5588259},"labels":[],"label_agreement":null},{"id":"W2061074565","doi":"10.1109/iciinfs.2013.6732014","title":"A term weighting method for identifying emotions from text content","year":2013,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":21,"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":"University of Ottawa","keywords":"Weighting; Computer science; tf–idf; Classifier (UML); Term (time); Support vector machine; Vector space model; Artificial intelligence; The Internet; Information retrieval; Natural language processing; Feature vector; Social media; Oracle; Machine learning; World Wide Web","score_opus":0.11414390337789153,"score_gpt":0.3319322388719783,"score_spread":0.21778833549408677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2061074565","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014097087,0.0000373103,0.9741611,0.007436806,0.00019944416,0.00035026172,0.0000014678448,0.0007842163,0.0029323434],"genre_scores_gemma":[0.35574874,0.00000401207,0.64027447,0.00031957636,0.00002188637,0.00017674506,0.0000032017244,0.000004317856,0.0034470318],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991752,0.000019934574,0.00020604448,0.00030287515,0.000112465095,0.00018347784],"domain_scores_gemma":[0.9990857,0.00023953039,0.00008674447,0.00045080096,0.00009528104,0.00004192888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011970876,0.00008587912,0.00010298303,0.00009152888,0.00016834287,0.000463497,0.00069084426,0.000051714553,0.0002688554],"category_scores_gemma":[0.00010837035,0.000067743174,0.00006813704,0.00015271394,0.000020896863,0.00078776665,0.00020681821,0.000057068955,0.00047281626],"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":[5.235646e-7,0.00003287013,0.00043271147,0.000004665608,0.000019682308,2.976649e-7,0.00030521417,6.918162e-7,0.06577784,0.5367706,0.0045393235,0.39211562],"study_design_scores_gemma":[0.0009535911,0.00009830275,0.040323474,0.000049317932,0.00001933549,0.0000063079683,0.0024548466,0.12087955,0.17255569,0.650503,0.011630806,0.00052579877],"about_ca_topic_score_codex":0.00034943307,"about_ca_topic_score_gemma":0.000009863591,"teacher_disagreement_score":0.39158982,"about_ca_system_score_codex":0.000025684589,"about_ca_system_score_gemma":0.000016206743,"threshold_uncertainty_score":0.6077254},"labels":[],"label_agreement":null},{"id":"W2066207574","doi":"10.1109/memb.2007.335581","title":"Multilabel associative classification categorization of MEDLINE aticles into MeSH keywords","year":2007,"lang":"en","type":"article","venue":"IEEE Engineering in Medicine and Biology Magazine","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Categorization; Classifier (UML); Associative property; Document classification; Data mining; Macro; Scalability; Artificial intelligence; Information retrieval; Pattern recognition (psychology); Machine learning; Database; Mathematics","score_opus":0.03913872556567612,"score_gpt":0.3145223526739983,"score_spread":0.2753836271083222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066207574","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":[0.3060151,0.0003789392,0.6900499,0.0026603395,0.0002952886,0.00014304364,7.2067127e-7,0.00018919053,0.0002674709],"genre_scores_gemma":[0.98007816,0.0002469177,0.019484218,0.000056797046,0.000060113194,0.000009015201,0.000011882792,0.0000052757296,0.000047633774],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9990738,0.000021569114,0.00040031236,0.00023320265,0.00009192156,0.00017917651],"domain_scores_gemma":[0.99923027,0.0002899737,0.00015093466,0.00020154977,0.00009022382,0.000037072117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007174116,0.00011908298,0.0002341958,0.0003703037,0.000024613328,0.0000059631207,0.00025393112,0.00013827266,0.0000034265836],"category_scores_gemma":[0.00042477122,0.0000944394,0.0000149453435,0.00060521753,0.00012547562,0.00014277126,0.000045459423,0.00013828425,0.0000027678716],"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":[0.000016826178,0.000096221476,0.054148156,0.00007739329,0.000036336303,0.0000037151642,0.0020896674,0.00008127627,0.64224225,0.1837096,0.00063041254,0.116868116],"study_design_scores_gemma":[0.0036865696,0.0009503293,0.5362325,0.0002093495,0.000033656775,0.000010092067,0.00075695914,0.36896256,0.07237802,0.012674215,0.0035302136,0.0005755661],"about_ca_topic_score_codex":0.000022454322,"about_ca_topic_score_gemma":0.00002300111,"teacher_disagreement_score":0.674063,"about_ca_system_score_codex":0.000049115486,"about_ca_system_score_gemma":0.000014182194,"threshold_uncertainty_score":0.38511267},"labels":[],"label_agreement":null},{"id":"W2071505781","doi":"10.1007/s10766-013-0245-x","title":"Parallel Training of An Improved Neural Network for Text Categorization","year":2013,"lang":"en","type":"article","venue":"International Journal of Parallel Programming","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Francis Xavier University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Speedup; Computer science; Categorization; Correctness; Artificial neural network; The Internet; Artificial intelligence; Text categorization; Process (computing); Machine learning; Data mining; Parallel computing; Algorithm; World Wide Web","score_opus":0.03387168784162624,"score_gpt":0.2973515778122583,"score_spread":0.26347988997063204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071505781","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":[0.032751255,0.00013579473,0.9631662,0.0026778437,0.00080238626,0.00032701154,9.888925e-7,0.00008573655,0.00005283183],"genre_scores_gemma":[0.60398525,0.000010444227,0.39566824,0.000057057834,0.0001891334,0.000034988978,0.000006162177,0.000006668765,0.000042064745],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998527,0.000035579014,0.00067307503,0.0001756878,0.00035031853,0.00023837545],"domain_scores_gemma":[0.9979346,0.00010664746,0.00087213994,0.00019213516,0.0008199937,0.00007447574],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038185238,0.00012308868,0.00020381145,0.00018737739,0.000064720756,0.00031077935,0.0014133394,0.000073745294,0.000013083945],"category_scores_gemma":[0.00013652185,0.00010498123,0.00013641959,0.0001760978,0.00005942748,0.0016503847,0.00009269413,0.00013750578,0.0000026187677],"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":[0.000047270078,0.00012517672,0.0008012072,0.0000088825445,0.00010715395,0.000003773406,0.0008202303,0.009095717,0.0018149433,0.046997994,0.000371222,0.9398064],"study_design_scores_gemma":[0.003598399,0.0016071097,0.008770955,0.00009324295,0.00003787376,0.00017919055,0.0016099346,0.8621325,0.0013334026,0.10497813,0.015137717,0.00052157143],"about_ca_topic_score_codex":0.000024158599,"about_ca_topic_score_gemma":0.0000054533148,"teacher_disagreement_score":0.93928486,"about_ca_system_score_codex":0.000044901408,"about_ca_system_score_gemma":0.00007792947,"threshold_uncertainty_score":0.42810103},"labels":[],"label_agreement":null},{"id":"W2077512673","doi":"10.1214/07-ba209","title":"Improving classification when a class hierarchy is available using a hierarchy-based prior","year":2007,"lang":"en","type":"article","venue":"Bayesian Analysis","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hierarchy; Multinomial logistic regression; Class hierarchy; Computer science; Class (philosophy); Machine learning; Artificial intelligence; Multinomial distribution; Bayesian probability; Tree (set theory); Data mining; Mathematics; Statistics","score_opus":0.03222386111863169,"score_gpt":0.2757000272695841,"score_spread":0.2434761661509524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077512673","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":[0.0055056247,0.0001401087,0.9868657,0.0026539715,0.00007227575,0.00023564487,0.000005182279,0.0007410078,0.0037804677],"genre_scores_gemma":[0.696539,0.0000063647035,0.30119514,0.0005787318,0.00003598466,0.000017307486,0.000014222888,0.000016425818,0.0015968592],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997104,0.00008442237,0.000655738,0.00093074923,0.00060318684,0.00062189443],"domain_scores_gemma":[0.99733526,0.0001476378,0.0004509182,0.0016886906,0.00019536188,0.0001821662],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010202408,0.00027506935,0.00038802836,0.0018818157,0.0003955406,0.00050621445,0.00138614,0.00020824271,0.00039784174],"category_scores_gemma":[0.000108897,0.0002687766,0.0003562243,0.0040438175,0.00015079991,0.0007715565,0.00020304779,0.00025514016,0.00018627479],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011423136,0.0008372234,0.06725814,0.0001566827,0.001720859,0.00010536975,0.002341725,0.00025813078,0.099664286,0.21377833,0.011518952,0.60224605],"study_design_scores_gemma":[0.00042617368,0.000048974376,0.003992012,0.0000130435665,0.00033621493,0.0000031158215,0.0002111167,0.9663775,0.016845211,0.002210925,0.00907199,0.0004637044],"about_ca_topic_score_codex":0.0002604588,"about_ca_topic_score_gemma":0.00007222577,"teacher_disagreement_score":0.9661194,"about_ca_system_score_codex":0.00045663607,"about_ca_system_score_gemma":0.00024042657,"threshold_uncertainty_score":0.99997646},"labels":[],"label_agreement":null},{"id":"W2079238049","doi":"10.1007/s13042-013-0152-x","title":"Bayesian Citation-KNN with distance weighting","year":2013,"lang":"en","type":"article","venue":"International Journal of Machine Learning and Cybernetics","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Bayesian probability; Machine learning; Benchmark (surveying); k-nearest neighbors algorithm; Weighting; Computational intelligence; Field (mathematics); Naive Bayes classifier; Pattern recognition (psychology); Overhead (engineering); Supervised learning; Data mining; Mathematics; Support vector machine; Artificial neural network","score_opus":0.0059464137161801146,"score_gpt":0.23471035493506628,"score_spread":0.22876394121888616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079238049","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":[0.09322374,0.00052449486,0.8923337,0.011257528,0.00023708519,0.000050602877,5.964334e-7,0.00008435667,0.0022879129],"genre_scores_gemma":[0.9564636,0.00016620639,0.042493053,0.00008496861,0.000055580866,0.000001823951,0.0000011898046,0.0000051714437,0.00072840543],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999181,0.000032623622,0.00023726777,0.00010533141,0.00035281375,0.00009099802],"domain_scores_gemma":[0.99908,0.00011474229,0.0003335927,0.00007510348,0.0003491192,0.00004744765],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014704492,0.000078269135,0.00009079086,0.00014122127,0.000059426642,0.00031164018,0.00047987036,0.000029252644,0.000036895985],"category_scores_gemma":[0.00012479315,0.000056778776,0.000026379512,0.00010426226,0.000050324797,0.00041475994,0.00007437656,0.00024793437,0.000008882545],"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":[0.000028183476,0.000096287054,0.21884674,0.0000100100515,0.00016337687,0.00004747451,0.0014259702,0.00080637,0.0010471343,0.18249714,0.00075345417,0.59427786],"study_design_scores_gemma":[0.004111325,0.0016173691,0.17380111,0.0005041474,0.00005481759,0.0013275074,0.0017264326,0.5607941,0.003933151,0.10308102,0.14803067,0.0010183402],"about_ca_topic_score_codex":0.000018451266,"about_ca_topic_score_gemma":0.0000039067463,"teacher_disagreement_score":0.8632399,"about_ca_system_score_codex":0.000023248196,"about_ca_system_score_gemma":0.00002268322,"threshold_uncertainty_score":0.30051532},"labels":[],"label_agreement":null},{"id":"W2089870669","doi":"10.1016/j.eswa.2011.09.160","title":"Comparison of term frequency and document frequency based feature selection metrics in text categorization","year":2011,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":152,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"Faculty of Graduate Studies and Research, University of Alberta; Natural Sciences and Engineering Research Council of Canada; University of Regina","keywords":"Feature selection; Discriminative model; Computer science; Term (time); Text categorization; Categorization; Word lists by frequency; Feature (linguistics); Frequency; Artificial intelligence; Selection (genetic algorithm); Pattern recognition (psychology); tf–idf; Data mining; Mathematics; Statistics","score_opus":0.031047475942438254,"score_gpt":0.28638712605760935,"score_spread":0.2553396501151711,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089870669","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":[0.004883914,0.0015074074,0.9900603,0.00040392947,0.000055035413,0.0009927601,0.0000023162813,0.00030447284,0.0017898616],"genre_scores_gemma":[0.9390606,0.000031455525,0.059625596,0.00001939772,0.000014597542,0.0011702222,0.000013526728,0.000009036117,0.000055514134],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.998818,0.000048183574,0.00036245107,0.00037790538,0.00022854858,0.00016495248],"domain_scores_gemma":[0.9989477,0.000049317758,0.0003041427,0.00049975206,0.0001482781,0.000050845465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001451599,0.00014493363,0.00021879884,0.00043192686,0.00010839489,0.00007278683,0.0004383797,0.000120782664,0.0000063954285],"category_scores_gemma":[0.000016168886,0.000120190176,0.000019151961,0.0015536778,0.00006929315,0.0004054891,0.00003889412,0.00011894913,0.00000599574],"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":[0.0000066365697,0.000301439,0.35446432,0.00008507377,0.000021439122,6.614484e-7,0.0025621888,0.000033225744,0.009819295,0.6222152,0.000515205,0.009975277],"study_design_scores_gemma":[0.005529375,0.0018546891,0.6391277,0.0006298409,0.00010006282,0.00007703797,0.007982855,0.09260122,0.18816262,0.046866063,0.013868021,0.0032005324],"about_ca_topic_score_codex":0.00038746258,"about_ca_topic_score_gemma":0.000046352478,"teacher_disagreement_score":0.93417674,"about_ca_system_score_codex":0.00011033732,"about_ca_system_score_gemma":0.00007483242,"threshold_uncertainty_score":0.4901213},"labels":[],"label_agreement":null},{"id":"W2091876488","doi":"10.1007/3-540-45665-1_5","title":"A Fast SVM Training Algorithm","year":2002,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"MNIST database; Computer science; Support vector machine; Kernel (algebra); Scalability; Artificial intelligence; Principal component analysis; Algorithm; Scheme (mathematics); Pattern recognition (psychology); Machine learning; Digit recognition; Deep learning; Artificial neural network; Mathematics; Database","score_opus":0.03404040626412898,"score_gpt":0.24908833323087898,"score_spread":0.21504792696675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091876488","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000049314826,0.00040447962,0.9840421,0.0018964448,0.0012388447,0.00026218678,0.0000041272906,0.0007695121,0.011377351],"genre_scores_gemma":[0.023290198,0.00011932255,0.97211945,0.0010567288,0.00034285977,0.00001965704,0.00000406917,0.000036798803,0.003010887],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962858,0.000017740027,0.00049770094,0.0015473362,0.00094601745,0.00070541294],"domain_scores_gemma":[0.99751145,0.00025443386,0.00029683634,0.0016525848,0.00014982399,0.00013486618],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00048205745,0.0005017904,0.00047709577,0.0010834292,0.00027509482,0.0007730615,0.004580664,0.00039218887,0.00007473031],"category_scores_gemma":[0.00007220813,0.0004606687,0.00013362405,0.0007861009,0.0008357815,0.00078227837,0.0013051506,0.00085156725,0.0001758835],"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":[3.6716284e-7,0.000012436798,0.000004443231,0.0000063166335,0.000004949359,0.000037836064,0.0007020609,0.0006458902,0.000024439754,0.040206578,0.00005446551,0.95830023],"study_design_scores_gemma":[0.000268339,0.00015567473,0.000052739426,0.00022038736,0.0000058462097,0.000092675706,9.861972e-7,0.6674568,0.0008960349,0.31577125,0.014203246,0.0008760072],"about_ca_topic_score_codex":0.0000053326166,"about_ca_topic_score_gemma":0.000006815241,"teacher_disagreement_score":0.9574242,"about_ca_system_score_codex":0.0002573947,"about_ca_system_score_gemma":0.0002546137,"threshold_uncertainty_score":0.9997845},"labels":[],"label_agreement":null},{"id":"W2095998031","doi":"10.1109/hicss.2007.98","title":"Automatic Web Page Categorization using Principal Component Analysis","year":2007,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Information retrieval; Web page; World Wide Web; Categorization; Static web page; Web search engine; Web query classification; Web search query; Task (project management); Web navigation; Search engine; Artificial intelligence; Engineering","score_opus":0.030735769628593958,"score_gpt":0.2876970805385032,"score_spread":0.2569613109099092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095998031","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":[0.3016079,0.000012780402,0.6959523,0.00024634288,0.0000668464,0.00006541109,1.9849982e-7,0.0007678144,0.0012804356],"genre_scores_gemma":[0.9067155,0.000002779632,0.09304554,0.000057562276,0.00000919508,0.0000021651306,0.0000041399117,0.0000028266722,0.00016029582],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990577,0.000017530725,0.00026187938,0.00023353816,0.00023210135,0.00019726115],"domain_scores_gemma":[0.99927014,0.000044242755,0.00010980832,0.00048347565,0.00004760294,0.000044710567],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034795474,0.000085425396,0.0001220947,0.0004549203,0.00010609117,0.0001360868,0.00049941696,0.00005364512,0.000093276685],"category_scores_gemma":[0.000021292231,0.000072192626,0.00006294635,0.0016495057,0.00003145655,0.00035141563,0.00015687235,0.000053439595,0.00003916827],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020201728,0.00018247266,0.038624477,0.000017259188,0.00023222712,0.000018994131,0.0004753506,0.00092645665,0.05374307,0.83533764,0.00020333138,0.07023672],"study_design_scores_gemma":[0.00009377978,0.0000108665845,0.028882671,0.0000014649889,0.000036743637,0.0000022445802,0.000096696356,0.96102774,0.008155668,0.0012644365,0.00031229912,0.000115379255],"about_ca_topic_score_codex":0.00002880488,"about_ca_topic_score_gemma":0.000028504859,"teacher_disagreement_score":0.9601013,"about_ca_system_score_codex":0.000081986225,"about_ca_system_score_gemma":0.000028985218,"threshold_uncertainty_score":0.294393},"labels":[],"label_agreement":null},{"id":"W2096794280","doi":"10.1109/ccece.2011.6030580","title":"Classifying the Arabic web — A pilot study","year":2011,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"University of Ottawa","funders":"","keywords":"Computer science; World Wide Web; Arabic; Web crawler; Web page; Globe; Categorization; The Internet; Information retrieval; Artificial intelligence; Linguistics","score_opus":0.15256397385339876,"score_gpt":0.27215516938871803,"score_spread":0.11959119553531927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096794280","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":[0.30635443,0.00014133235,0.4134763,0.008492771,0.0007581174,0.0011751124,3.9269028e-7,0.005367936,0.26423362],"genre_scores_gemma":[0.99150324,0.000005245174,0.0064964807,0.0002166192,0.000009167078,0.000055133325,6.455848e-8,0.0000032136195,0.0017108454],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9992852,0.00003833273,0.00014129558,0.00022611172,0.00015536684,0.00015367975],"domain_scores_gemma":[0.99903387,0.000043282133,0.00005189211,0.0008201283,0.000028766555,0.000022075217],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023473472,0.00007694658,0.00006457556,0.00006528183,0.00015627373,0.00011886808,0.0014385218,0.000014537887,0.00012522968],"category_scores_gemma":[0.0000285646,0.000042231688,0.000019390849,0.00033869824,0.00005687408,0.00033632846,0.00032772822,0.0000985333,0.00029161538],"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":[0.000006319775,0.00079183094,0.021615151,0.0000018302153,0.000022720435,0.000005348795,0.0019801226,2.9638673e-7,0.0008364536,0.92121905,0.0056292964,0.04789156],"study_design_scores_gemma":[0.0025346593,0.008386672,0.70649785,0.000018183833,0.00004307765,0.000032056294,0.018950995,0.021138925,0.012822814,0.18044767,0.047864757,0.0012623145],"about_ca_topic_score_codex":0.00003490128,"about_ca_topic_score_gemma":0.0000507386,"teacher_disagreement_score":0.7407714,"about_ca_system_score_codex":0.000013455325,"about_ca_system_score_gemma":0.000025485155,"threshold_uncertainty_score":0.3748223},"labels":[],"label_agreement":null},{"id":"W2098465658","doi":"10.1136/amiajnl-2012-001072","title":"Direct comparison between support vector machine and multinomial naive Bayes algorithms for medical abstract classification","year":2012,"lang":"en","type":"letter","venue":"Journal of the American Medical Informatics Association","topic":"Text and Document Classification Technologies","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":"University of Ottawa","funders":"","keywords":"Support vector machine; Computer science; Machine learning; Naive Bayes classifier; Artificial intelligence; Algorithm; Bayesian probability; Relevance vector machine; Multinomial distribution; Task (project management); Bayes' theorem; Structured support vector machine; Data mining; Mathematics; Statistics; Engineering","score_opus":0.030097218431528877,"score_gpt":0.3180617413496284,"score_spread":0.2879645229180995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098465658","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006314717,0.00016387925,0.16720317,0.8226756,0.002347709,0.0006218606,0.000118447744,0.000165702,0.00038890753],"genre_scores_gemma":[0.6755643,0.0012322754,0.06508324,0.2434808,0.0131914485,0.00011223645,0.00044332648,0.000112736176,0.0007796327],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9944157,0.00017221313,0.0019237068,0.00015182125,0.0028865165,0.00045006193],"domain_scores_gemma":[0.9888334,0.0023822798,0.0077517433,0.00040375965,0.00039582787,0.00023298671],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035259135,0.00028112452,0.000914386,0.00025971976,0.00019858671,0.0002454523,0.0020213977,0.0007487284,0.0000342353],"category_scores_gemma":[0.0046447427,0.0001872537,0.000299069,0.00033796605,0.0002660875,0.00067709,0.00032054787,0.0022734457,0.000012678785],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009856819,0.00006533179,0.012485651,0.00009221557,0.00030781195,0.0000027228432,0.0008032796,9.594658e-7,0.0000064255714,0.00010778892,0.7525677,0.23355025],"study_design_scores_gemma":[0.0016975267,0.0005795731,0.0978703,0.0003001002,0.0003833551,0.00006180189,0.00047192536,0.045523394,0.0004111887,0.00037502634,0.85163015,0.0006956307],"about_ca_topic_score_codex":0.000023657616,"about_ca_topic_score_gemma":0.0000032392643,"teacher_disagreement_score":0.6692496,"about_ca_system_score_codex":0.00057827344,"about_ca_system_score_gemma":0.00058115326,"threshold_uncertainty_score":0.98771167},"labels":[],"label_agreement":null},{"id":"W2099126842","doi":"10.1109/icdm.2001.989592","title":"A simple KNN algorithm for text categorization","year":2002,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":225,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Interpretability; Artificial intelligence; Text categorization; Feature (linguistics); Context (archaeology); Vocabulary; Feature selection; Word (group theory); Categorization; Simple (philosophy); Class (philosophy); k-nearest neighbors algorithm; Process (computing); Machine learning; Natural language processing; Pattern recognition (psychology); Mathematics","score_opus":0.030164978776939248,"score_gpt":0.25378029008612923,"score_spread":0.22361531130919,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099126842","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":[0.00007800005,0.000031479816,0.99150956,0.0024480564,0.00009333993,0.00016533003,0.0000013045035,0.00083077856,0.0048421468],"genre_scores_gemma":[0.6075973,0.00003884285,0.3773731,0.0004594227,0.00005140491,0.00014273316,0.000010330925,0.000008625558,0.01431825],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994497,0.0000056386325,0.00011274107,0.00020008742,0.000089708476,0.00014212726],"domain_scores_gemma":[0.9995209,0.00004045247,0.000040433522,0.00032351853,0.000050288778,0.000024416424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000050898838,0.00006147106,0.000058530317,0.00007360875,0.00009079086,0.00012464417,0.000437138,0.000044530156,0.0001445838],"category_scores_gemma":[0.000025734122,0.000051805553,0.000029653178,0.00026412256,0.00001873607,0.00039423825,0.00006833048,0.000027671731,0.00017600963],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.980512e-8,0.000020950143,0.000028547793,0.0000011556633,0.000001979119,1.3475032e-7,0.000045845816,0.0000013626725,0.00013568878,0.30664152,0.016537528,0.6765852],"study_design_scores_gemma":[0.00023159666,0.000058479298,0.00019123947,7.566895e-7,0.000001771454,0.0000014943433,0.000046453468,0.80830914,0.00974343,0.04754684,0.13374625,0.0001225462],"about_ca_topic_score_codex":0.0000055057894,"about_ca_topic_score_gemma":0.0000014696673,"teacher_disagreement_score":0.80830777,"about_ca_system_score_codex":0.00001887051,"about_ca_system_score_gemma":0.0000053166414,"threshold_uncertainty_score":0.22623064},"labels":[],"label_agreement":null},{"id":"W2099994538","doi":"","title":"Structured ranking learning using cumulative distribution networks","year":2008,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"University of Toronto","funders":"","keywords":"Learning to rank; Computer science; Ranking (information retrieval); Pairwise comparison; Benchmark (surveying); Rank (graph theory); Machine learning; Probabilistic logic; Object (grammar); Artificial intelligence; Independence (probability theory); Cumulative distribution function; Class (philosophy); Data mining; Graphical model; Mathematics; Statistics","score_opus":0.037738564434568356,"score_gpt":0.26599140352394024,"score_spread":0.22825283908937188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099994538","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":[0.095252216,0.000053247553,0.90315396,0.00015833146,0.00011465586,0.000061775936,2.2863165e-7,0.0007392906,0.0004662846],"genre_scores_gemma":[0.9755983,0.00001581673,0.024074761,0.00002849747,0.000024830142,0.0000022856743,0.000008667333,0.0000033064441,0.00024358806],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992875,0.00003362082,0.00014079471,0.00021456901,0.00014510899,0.00017844822],"domain_scores_gemma":[0.99956894,0.000043821623,0.00008792243,0.00022373418,0.000050799397,0.00002475436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000082546154,0.00008347739,0.000086495595,0.000045312936,0.00037087046,0.000070608476,0.0003338444,0.00006715896,0.000019588724],"category_scores_gemma":[0.00005014745,0.0000718527,0.000034214783,0.00038563393,0.000060788094,0.00048614858,0.00014720773,0.00015370325,0.0000065520658],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011841317,0.000039358703,0.036047745,0.0000051807515,0.000039429553,0.000021679856,0.0010359037,0.160943,0.0029858022,0.6760234,0.0012086252,0.12163799],"study_design_scores_gemma":[0.0001793905,0.00001765705,0.01297828,0.000004796848,0.0000020556106,0.000019672874,0.000056441568,0.9786556,0.0026183003,0.0035831777,0.0017519663,0.00013267569],"about_ca_topic_score_codex":0.000015094966,"about_ca_topic_score_gemma":0.0000010158594,"teacher_disagreement_score":0.88034606,"about_ca_system_score_codex":0.0000579016,"about_ca_system_score_gemma":0.000019853667,"threshold_uncertainty_score":0.2930068},"labels":[],"label_agreement":null},{"id":"W2102282930","doi":"10.1007/978-3-642-31368-4_22","title":"Features’ Weight Learning towards Improved Query Classification","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Weighting; Support vector machine; Naive Bayes classifier; k-nearest neighbors algorithm; Artificial intelligence; Data mining; Entropy (arrow of time); Machine learning; Pattern recognition (psychology); Scheme (mathematics); Mathematics","score_opus":0.021257727760830295,"score_gpt":0.25452082845845103,"score_spread":0.23326310069762074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102282930","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":[0.00003091456,0.0016124974,0.98249847,0.0031700612,0.0018011491,0.00038464504,0.0000019047382,0.0009378433,0.009562503],"genre_scores_gemma":[0.5790547,0.000602032,0.41349414,0.0010000055,0.0009319317,0.000057305493,0.0000258048,0.00007549259,0.0047585517],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99614084,0.00004642074,0.0005589192,0.0015398695,0.0009023547,0.000811617],"domain_scores_gemma":[0.9970066,0.00025315868,0.0005215238,0.0017821378,0.00026096334,0.00017564514],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009420179,0.0005792047,0.00048308674,0.0010785507,0.0003914402,0.000755812,0.0040070247,0.00065301993,0.00004119075],"category_scores_gemma":[0.00018257405,0.0005107291,0.00015674878,0.0007588633,0.0007298153,0.0012642454,0.0014426827,0.0015546898,0.00011812434],"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":[0.0000029554412,0.000020806188,0.00007185318,0.000017540051,0.0000076240103,0.0000050377926,0.0003010078,0.00016063801,0.0011528276,0.089100696,0.000057977624,0.909101],"study_design_scores_gemma":[0.0010680621,0.0005614403,0.010692816,0.0006316233,0.000051736526,0.00018574856,0.0000039238553,0.4014447,0.027187696,0.43870088,0.11560558,0.0038658006],"about_ca_topic_score_codex":0.000018227927,"about_ca_topic_score_gemma":0.000019565947,"teacher_disagreement_score":0.90523523,"about_ca_system_score_codex":0.0004812475,"about_ca_system_score_gemma":0.0004920245,"threshold_uncertainty_score":0.9997344},"labels":[],"label_agreement":null},{"id":"W2106388373","doi":"10.1016/j.ipm.2006.07.006","title":"Contextual feature selection for text classification","year":2006,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bigram; Computer science; Feature selection; Selection (genetic algorithm); Set (abstract data type); Filter (signal processing); Feature (linguistics); Information retrieval; Artificial intelligence; Data set; Simple (philosophy); Data mining","score_opus":0.013551666440469857,"score_gpt":0.24842697285509144,"score_spread":0.2348753064146216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106388373","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":[0.0005657965,0.000047613717,0.97473407,0.0038831653,0.00013365291,0.0005448034,0.0000019023246,0.0010433496,0.019045636],"genre_scores_gemma":[0.9032106,0.000007654725,0.093192615,0.0003962839,0.00004024611,0.00035381396,0.00007857781,0.0000055852256,0.0027146402],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990277,0.0000094415755,0.000320624,0.00018594401,0.00025384632,0.00020241647],"domain_scores_gemma":[0.99921924,0.000017220917,0.00030032438,0.00023379177,0.00020907125,0.000020354946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021191973,0.00012421265,0.000087599656,0.00029859607,0.00031298594,0.00075850275,0.00045699018,0.00007986478,0.000004744578],"category_scores_gemma":[0.0000169741,0.00011695699,0.000040459767,0.00053216045,0.00003147667,0.0036065644,0.00007274961,0.000072630195,0.00007328501],"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":[0.000005299148,0.00002154999,0.00006723826,0.00007507172,0.000004753474,4.280996e-8,0.00009465446,0.000087189284,0.00008632907,0.40511397,0.02218106,0.5722628],"study_design_scores_gemma":[0.00094535126,0.000055823286,0.020613227,0.000045251985,0.0000187537,0.000004343916,0.0006796308,0.22360076,0.0021594372,0.036358267,0.71517795,0.00034117655],"about_ca_topic_score_codex":0.0000049261166,"about_ca_topic_score_gemma":0.0000029077598,"teacher_disagreement_score":0.9026448,"about_ca_system_score_codex":0.0001135724,"about_ca_system_score_gemma":0.000028421375,"threshold_uncertainty_score":0.73142594},"labels":[],"label_agreement":null},{"id":"W2108345839","doi":"10.1177/0165551508092257","title":"A hidden Markov model-based text classification of medical documents","year":2008,"lang":"en","type":"article","venue":"Journal of Information Science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Hidden Markov model; Computer science; Categorization; Artificial intelligence; Markov model; Subject (documents); Natural language processing; Machine learning; Markov chain; World Wide Web","score_opus":0.029640633799022778,"score_gpt":0.2983874154971723,"score_spread":0.26874678169814953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108345839","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":[0.09866388,0.000021013399,0.8929573,0.0054314467,0.00021132699,0.00007655611,8.0480544e-7,0.00005021742,0.0025874146],"genre_scores_gemma":[0.91343635,0.00007101661,0.08619491,0.00025849068,0.000010011752,0.0000026240268,5.000563e-7,0.0000012968817,0.000024781873],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99631476,0.00002148631,0.000882838,0.00009451181,0.0025181186,0.00016825496],"domain_scores_gemma":[0.9973648,0.00006694795,0.0011584108,0.00038893687,0.0008880211,0.00013288617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001973821,0.00008070636,0.00015164494,0.0008803965,0.00017578747,0.00013969305,0.00260537,0.00007644366,0.00002679518],"category_scores_gemma":[0.0008385261,0.00006173714,0.00006665951,0.0014063171,0.00050378405,0.008477471,0.00015780123,0.00017438477,0.000026378815],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056465728,0.00026349313,0.006424019,0.00005883891,0.000018318731,0.0000076096358,0.004034898,0.0014542689,0.0072356276,0.25038904,0.010438537,0.71961886],"study_design_scores_gemma":[0.00094638893,0.00016378392,0.031484608,0.00007038117,0.000004289027,0.0001324859,0.00031677022,0.944443,0.017322887,0.0026050494,0.0023494312,0.00016092407],"about_ca_topic_score_codex":0.000002425456,"about_ca_topic_score_gemma":2.2206045e-7,"teacher_disagreement_score":0.94298875,"about_ca_system_score_codex":0.00011093171,"about_ca_system_score_gemma":0.0014633657,"threshold_uncertainty_score":0.6145962},"labels":[],"label_agreement":null},{"id":"W2110295586","doi":"10.1109/cec.2006.1688611","title":"Evolving Recurrent Linear-GP for Document Classification and Word Tracking","year":2006,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"Dalhousie University","funders":"","keywords":"Computer science; Word (group theory); Document classification; Artificial intelligence; Benchmark (surveying); Genetic programming; Set (abstract data type); Encoding (memory); Sequence (biology); Natural language processing; Data mining; Pattern recognition (psychology); Mathematics","score_opus":0.035148514533766856,"score_gpt":0.29023778707385306,"score_spread":0.2550892725400862,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110295586","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":[0.012827959,0.00044577636,0.976161,0.0068599572,0.00021639589,0.00036599505,9.297694e-7,0.00075987197,0.0023621353],"genre_scores_gemma":[0.8594038,0.00003518678,0.13924941,0.000055931687,0.000050218143,0.00009016739,0.0000061063843,0.000005350302,0.0011038063],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990537,0.000013622467,0.00024337934,0.00035398005,0.00014219664,0.0001931335],"domain_scores_gemma":[0.9993276,0.00010262645,0.000105317704,0.00034846275,0.00008756996,0.000028425327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021362181,0.000103521765,0.00009560655,0.00010988213,0.00015107005,0.00029709726,0.00035382912,0.00005954156,0.00001228862],"category_scores_gemma":[0.000051494677,0.00008898656,0.00003654132,0.00020259817,0.0000395189,0.0006496109,0.00009657709,0.00006273427,0.00001129713],"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":[0.000002869343,0.00003708941,0.0012304286,0.000012704281,0.000003477423,1.8965862e-7,0.000050129325,0.000004596792,0.002092786,0.5960323,0.004295379,0.39623803],"study_design_scores_gemma":[0.0015736506,0.0002907954,0.17169254,0.00008172396,0.000024804882,0.000010497174,0.00050296314,0.287761,0.036266636,0.33649233,0.16438544,0.0009176149],"about_ca_topic_score_codex":0.0000136818335,"about_ca_topic_score_gemma":0.000014176085,"teacher_disagreement_score":0.84657586,"about_ca_system_score_codex":0.000052512998,"about_ca_system_score_gemma":0.000019612016,"threshold_uncertainty_score":0.36287668},"labels":[],"label_agreement":null},{"id":"W2111476725","doi":"10.1016/j.neucom.2014.12.041","title":"Multiview self-learning","year":2014,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"Agence Nationale de la Recherche","keywords":"Computer science; Artificial intelligence; Margin (machine learning); Classifier (UML); Pattern recognition (psychology); Labeled data; Naive Bayes classifier; Majority rule; Contextual image classification; Machine learning; Bounding overwatch; Image (mathematics); Support vector machine","score_opus":0.007415373750483025,"score_gpt":0.21862130427967286,"score_spread":0.21120593052918984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111476725","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":[0.03387129,0.000046799014,0.9505324,0.0014516722,0.00024965714,0.00009898578,3.1034233e-8,0.0042615314,0.009487637],"genre_scores_gemma":[0.9161378,0.0000086472455,0.083324455,0.00030934208,0.000049997187,0.0000045599954,2.3482461e-7,0.0000068364034,0.00015812699],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99905795,0.00008911361,0.00016214362,0.00032037604,0.00015118493,0.00021924032],"domain_scores_gemma":[0.9992758,0.0002087049,0.000102672566,0.00034314804,0.000032059153,0.00003763235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025841736,0.000095341966,0.00010258899,0.0000855623,0.00020365506,0.00017043241,0.000714625,0.00003929292,0.0000031376508],"category_scores_gemma":[0.0001612823,0.000089737536,0.000041518117,0.00026720736,0.000015166314,0.000221838,0.0003610006,0.00020603355,0.0001658063],"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":[2.595347e-7,0.000027023752,0.0029225,0.00001260077,0.0000035566916,0.0000016745757,0.00021397638,0.00027600315,0.0016374307,0.0948132,0.00021246803,0.89987934],"study_design_scores_gemma":[0.00024269763,0.000077555895,0.008021193,0.000017086422,0.0000027618,0.000011728014,0.00001796859,0.7339483,0.0042152316,0.0019124855,0.25132322,0.00020979698],"about_ca_topic_score_codex":0.0000014586298,"about_ca_topic_score_gemma":1.3982891e-7,"teacher_disagreement_score":0.8996695,"about_ca_system_score_codex":0.000012484019,"about_ca_system_score_gemma":0.0000093465405,"threshold_uncertainty_score":0.36593905},"labels":[],"label_agreement":null},{"id":"W2114811742","doi":"10.1145/383952.384075","title":"Construction of a hierarchical classifier schema using a combination of text-based and image-based approaches","year":2001,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Classifier (UML); Hierarchy; Information retrieval; Schema (genetic algorithms); Artificial intelligence; Contextual image classification; Web page; Hierarchical database model; Pattern recognition (psychology); Image (mathematics); Data mining; World Wide Web","score_opus":0.06165531021782302,"score_gpt":0.2653097024452505,"score_spread":0.20365439222742746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114811742","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":[0.29803294,0.000016460262,0.699375,0.0014579189,0.000026209978,0.000103061546,6.4829595e-7,0.000109970715,0.0008778235],"genre_scores_gemma":[0.7024813,0.0000017673117,0.29747012,0.000019366353,0.000002337263,0.0000048936304,0.0000014967303,0.0000025353193,0.000016155704],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99919367,0.000039717597,0.00025359407,0.00021643355,0.00018943971,0.00010715148],"domain_scores_gemma":[0.99931455,0.00009344915,0.00017603116,0.00029893662,0.0000884467,0.00002857324],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016695414,0.00008304272,0.0001474155,0.00024342602,0.000048411646,0.000041195468,0.0002265199,0.000080508136,0.00001424275],"category_scores_gemma":[0.00006159227,0.000074,0.000038235663,0.0004507846,0.00043818547,0.00028529917,0.000058907073,0.00007513867,7.9631815e-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":[0.000041394585,0.00033494266,0.015474279,0.00008155762,0.000015044817,0.0000012120704,0.00007307956,0.000066159635,0.0714832,0.78989995,0.000043265787,0.122485936],"study_design_scores_gemma":[0.0010607868,0.0001200781,0.00601383,0.000029258601,0.000009270931,0.000006538774,0.00018223519,0.7214217,0.2555264,0.015405445,0.00009581011,0.00012863732],"about_ca_topic_score_codex":0.00001169534,"about_ca_topic_score_gemma":0.0000012265104,"teacher_disagreement_score":0.77449447,"about_ca_system_score_codex":0.00002133468,"about_ca_system_score_gemma":0.000081229875,"threshold_uncertainty_score":0.30176324},"labels":[],"label_agreement":null},{"id":"W2120020585","doi":"10.5591/978-1-57735-516-8/ijcai11-410","title":"A new search engine integrating hierarchical browsing and keyword search","year":2011,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Information retrieval; Search engine indexing; Search engine; Hierarchy; Web page; Organic search; Search analytics; World Wide Web; Metasearch engine; Keyword search; Web search engine; Index (typography); Web search query","score_opus":0.05883367762615484,"score_gpt":0.27393613419027013,"score_spread":0.2151024565641153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120020585","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":[0.037083924,0.000077284785,0.9429871,0.002348047,0.00005068995,0.000093899085,1.4671299e-7,0.00065505685,0.016703863],"genre_scores_gemma":[0.58576256,0.000014964203,0.41246712,0.000060394348,0.000015745085,0.000002474256,3.167207e-7,0.000003856796,0.0016725574],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990504,0.000034798242,0.00014765465,0.00030537217,0.00019960606,0.000262198],"domain_scores_gemma":[0.9993817,0.000082037885,0.000016965525,0.00036914472,0.000038414015,0.000111707166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002516335,0.00009341664,0.00009566486,0.00017717456,0.00010733287,0.000189777,0.0006139568,0.000060792005,0.00012737975],"category_scores_gemma":[0.00004897572,0.00007266204,0.000023486058,0.00038509697,0.00007602039,0.0004248572,0.00048221165,0.00026021723,0.00004372938],"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":[0.0000023357409,0.0000117879745,0.001281371,0.0000036116433,0.000003817101,0.000002736272,0.0013986146,3.5040122e-7,0.0010651707,0.41376975,0.0003103937,0.58215004],"study_design_scores_gemma":[0.0023309644,0.0012187259,0.08353184,0.00018408826,0.000016802447,0.00018548567,0.0054375096,0.28456855,0.39185464,0.21604212,0.012907304,0.0017219816],"about_ca_topic_score_codex":0.00021626003,"about_ca_topic_score_gemma":0.000012714001,"teacher_disagreement_score":0.58042806,"about_ca_system_score_codex":0.000019613282,"about_ca_system_score_gemma":0.00007098677,"threshold_uncertainty_score":0.2963072},"labels":[],"label_agreement":null},{"id":"W2122560301","doi":"10.5539/cis.v6n4p125","title":"Abstract Sentence Classification for Scientific Papers Based on Transductive SVM","year":2013,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Fundamental Research Funds for the Central Universities; Ministry of Education, India","keywords":"Computer science; Sentence; Support vector machine; Artificial intelligence; Natural language processing; Machine learning; Pattern recognition (psychology)","score_opus":0.024695993654702143,"score_gpt":0.2510553728594687,"score_spread":0.22635937920476656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122560301","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":[0.019135697,0.0000056327503,0.97014564,0.004755778,0.00060297875,0.0006003489,0.000004008441,0.00032037636,0.0044295546],"genre_scores_gemma":[0.95320857,0.0000047666654,0.045769993,0.00086540007,0.00001613903,0.00010234296,0.000008145637,0.0000019396173,0.00002270954],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998645,0.000008354658,0.0002854264,0.00035470788,0.0004459811,0.00026051947],"domain_scores_gemma":[0.9987175,0.000102981336,0.0001515179,0.000503949,0.0004264015,0.00009765703],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00053794705,0.00011863414,0.00008999706,0.0005067239,0.0006345147,0.001981133,0.00095067034,0.000043861975,0.000014284312],"category_scores_gemma":[0.000070170805,0.00009740276,0.000036453857,0.00092698523,0.00058273796,0.011149677,0.00007934648,0.00007737244,0.00010495242],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000044371873,0.0000387286,0.00017955185,0.000026746677,0.0000018795374,5.0272387e-8,0.00088122697,0.00036152196,0.005086258,0.24611756,0.0015054003,0.7457966],"study_design_scores_gemma":[0.00032998095,0.00010362411,0.10420604,0.00001995659,0.0000012667406,0.0000014163982,0.0001896566,0.874255,0.004375669,0.0022476236,0.01408528,0.00018450523],"about_ca_topic_score_codex":0.0000025277636,"about_ca_topic_score_gemma":1.3891746e-7,"teacher_disagreement_score":0.93407285,"about_ca_system_score_codex":0.00005363315,"about_ca_system_score_gemma":0.0001341833,"threshold_uncertainty_score":0.9990549},"labels":[],"label_agreement":null},{"id":"W2124567055","doi":"10.1109/waina.2009.50","title":"SVM Fuzzy Hierarchical Classification Method for Multi-class Problems","year":2009,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","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 Sherbrooke","funders":"","keywords":"Support vector machine; Artificial intelligence; Multiclass classification; Computer science; Fuzzy logic; Pattern recognition (psychology); Structured support vector machine; Fuzzy classification; Data mining; Transitive closure; Machine learning; Class (philosophy); Binary classification; Hierarchy; Fuzzy set; Mathematics","score_opus":0.08314315804154464,"score_gpt":0.3518369244207198,"score_spread":0.26869376637917514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124567055","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001411612,0.00004741867,0.9587692,0.03324802,0.00012177211,0.00054231304,0.0000016472837,0.001426087,0.0057023675],"genre_scores_gemma":[0.16381174,0.000013870594,0.83234537,0.0008260854,0.00002960671,0.00013581027,0.000007928849,0.000006158801,0.0028234422],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99859333,0.0000491446,0.00031412876,0.00052965473,0.00020337588,0.00031036272],"domain_scores_gemma":[0.99883044,0.00013419108,0.00011647518,0.00073460466,0.00010933698,0.00007497964],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004149029,0.00015002387,0.00016160565,0.00017375356,0.00015979414,0.0002186284,0.0010641606,0.00014270552,0.000009457837],"category_scores_gemma":[0.00012745691,0.000121821045,0.00009151348,0.00041409244,0.000044979788,0.0004890164,0.00008113472,0.00014350573,0.00006015234],"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":[0.0000025481338,0.00009652246,0.000023432918,0.0000040754885,0.0000036913764,1.5473306e-7,0.00006522285,0.0000133398735,0.007371449,0.6807754,0.0025416675,0.30910248],"study_design_scores_gemma":[0.0007584391,0.00024234978,0.0056912643,0.000008133364,0.0000061370697,0.0000049702867,0.00006426334,0.69893175,0.010314732,0.21201868,0.07166925,0.00029005125],"about_ca_topic_score_codex":0.0000034654395,"about_ca_topic_score_gemma":0.0000039651864,"teacher_disagreement_score":0.6989184,"about_ca_system_score_codex":0.00005166401,"about_ca_system_score_gemma":0.000048464415,"threshold_uncertainty_score":0.4967718},"labels":[],"label_agreement":null},{"id":"W2125811916","doi":"10.1109/icsmc.2007.4414079","title":"Learning social networks using multiple resampling method","year":2007,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"University of Waterloo","funders":"","keywords":"Undersampling; Computer science; Resampling; Oversampling; Artificial intelligence; Relation (database); Classifier (UML); Machine learning; Support vector machine; Class (philosophy); Social network (sociolinguistics); Set (abstract data type); Data mining; Social media; World Wide Web","score_opus":0.05936525729498046,"score_gpt":0.3507767445331882,"score_spread":0.29141148723820776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125811916","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":[0.007517304,0.000028640072,0.98880756,0.00034566707,0.00014215292,0.000054270542,3.2860406e-8,0.0010217454,0.0020826168],"genre_scores_gemma":[0.55270696,0.0000015213213,0.44696042,0.00005834939,0.000048956823,8.9129287e-7,3.948993e-7,0.0000034628922,0.00021904659],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99913466,0.0000330796,0.0001804394,0.00023745521,0.00013644483,0.00027789842],"domain_scores_gemma":[0.99940723,0.00025040758,0.00008522656,0.00018458658,0.00004332547,0.000029215389],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008362278,0.00007749194,0.00008863379,0.00011114893,0.00035080613,0.00014211598,0.00045391897,0.00009452289,0.000011689794],"category_scores_gemma":[0.000109598805,0.000071420836,0.000042923955,0.00042121648,0.000027226082,0.00030035136,0.00023332871,0.00019990987,0.000009315901],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004927862,0.000019747275,0.0054607294,0.000002538808,0.00001001573,0.0000035524392,0.00045323189,0.0074787103,0.00499656,0.1938795,0.0002159474,0.7874745],"study_design_scores_gemma":[0.00015362565,0.000016613312,0.0027602948,0.0000030763285,0.0000022655329,0.000003597757,0.00045375645,0.98296964,0.005157877,0.002580153,0.00575473,0.00014436126],"about_ca_topic_score_codex":0.0000300276,"about_ca_topic_score_gemma":0.000007886698,"teacher_disagreement_score":0.9754909,"about_ca_system_score_codex":0.000044939094,"about_ca_system_score_gemma":0.000013518653,"threshold_uncertainty_score":0.29124573},"labels":[],"label_agreement":null},{"id":"W2128133607","doi":"","title":"Semi-supervised Document Classification with a Mislabeling Error Model","year":2009,"lang":"en","type":"article","venue":"NPARC","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Probabilistic latent semantic analysis; Computer science; Artificial intelligence; Extension (predicate logic); Probabilistic logic; Machine learning; Set (abstract data type); Multiclass classification; Topic model; Document classification; Pattern recognition (psychology); Supervised learning; Data mining; Support vector machine; Artificial neural network","score_opus":0.03335914134963362,"score_gpt":0.2681762081773369,"score_spread":0.23481706682770326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128133607","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":[0.035915982,0.000042676984,0.9143257,0.027167723,0.000045707067,0.00024780477,8.661902e-7,0.001140599,0.021112917],"genre_scores_gemma":[0.79635996,0.00001742939,0.20229805,0.00049361907,0.000011397748,0.000029690758,0.0000030302228,0.0000050262333,0.0007818037],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99879485,0.000019084739,0.00020603056,0.00040538813,0.0003194051,0.00025521268],"domain_scores_gemma":[0.998974,0.000021103078,0.00009304108,0.0007660967,0.000083787556,0.00006191727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014348527,0.00014165202,0.00012395748,0.000121197496,0.00013166045,0.00018946848,0.0008156389,0.00007303207,0.000025467534],"category_scores_gemma":[0.000019879282,0.00011277312,0.000034791094,0.00038255609,0.00004043073,0.00062091486,0.000059571867,0.00012753917,0.000054882115],"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":[0.000016217127,0.000110927074,0.000114862116,0.000006831265,0.000011018134,0.000003168575,0.00062179397,0.0007671,0.1245615,0.65838516,0.003313052,0.21208833],"study_design_scores_gemma":[0.0005143036,0.0001574207,0.0009086665,0.00002470313,0.00000789215,0.000005575266,0.00013217624,0.810419,0.014373852,0.17187499,0.0013252201,0.00025618591],"about_ca_topic_score_codex":9.651825e-7,"about_ca_topic_score_gemma":0.0000010518385,"teacher_disagreement_score":0.8096519,"about_ca_system_score_codex":0.00006858379,"about_ca_system_score_gemma":0.00006709302,"threshold_uncertainty_score":0.45987546},"labels":[],"label_agreement":null},{"id":"W2128866918","doi":"10.1109/icsmc.2007.4414080","title":"Combining feature ranking for text classification","year":2007,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Computer science; Ranking (information retrieval); Pattern recognition (psychology); Classifier (UML); Feature (linguistics); Curse of dimensionality; Majority rule; Dimensionality reduction; Support vector machine; Ranking SVM; Data mining; Feature extraction; Feature vector; Machine learning; Feature selection","score_opus":0.03615333796315819,"score_gpt":0.298108691432085,"score_spread":0.26195535346892684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128866918","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":[0.0019456664,0.000054081702,0.9733363,0.007313573,0.0002229802,0.00020615871,3.1111315e-7,0.0009857193,0.015935257],"genre_scores_gemma":[0.8122765,0.000004265878,0.18487781,0.00028808866,0.000025724501,0.000021094596,0.0000037942768,0.0000046495984,0.0024980824],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992332,0.000006586053,0.00015045573,0.00025559243,0.0001364644,0.00021772248],"domain_scores_gemma":[0.99921244,0.00017821226,0.000085846914,0.00041699887,0.00007483661,0.000031661755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004642471,0.00007963039,0.00007834437,0.00013571561,0.00015702128,0.00014908373,0.00062243704,0.00009258032,0.0000074480736],"category_scores_gemma":[0.00007691291,0.00006784799,0.00004434246,0.00032659213,0.000031159947,0.00038631828,0.00007523101,0.000082264356,0.000029651837],"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":[0.0000031087034,0.000014316625,0.00044575153,0.0000031995407,0.0000030877598,2.3036498e-7,0.00009306753,5.4628146e-7,0.0058778543,0.77550536,0.004882429,0.21317104],"study_design_scores_gemma":[0.0022597958,0.00025694864,0.08100662,0.000040437044,0.000015306969,0.000016702275,0.0019359662,0.06509753,0.17007756,0.17015378,0.5082785,0.00086085894],"about_ca_topic_score_codex":0.0000015114545,"about_ca_topic_score_gemma":0.0000043381483,"teacher_disagreement_score":0.8103308,"about_ca_system_score_codex":0.00003562095,"about_ca_system_score_gemma":0.00001754353,"threshold_uncertainty_score":0.2766761},"labels":[],"label_agreement":null},{"id":"W2129206444","doi":"10.1007/978-3-540-37256-1_136","title":"Support Vector Machine for String Vectors","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in control and information sciences","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"String kernel; String (physics); Artificial intelligence; Computer science; String metric; Cluster analysis; Support vector machine; Word (group theory); Pattern recognition (psychology); String searching algorithm; Similarity (geometry); Kernel (algebra); Kernel method; Mathematics; Pattern matching; Radial basis function kernel; Discrete mathematics","score_opus":0.013755027824435629,"score_gpt":0.23965021536354505,"score_spread":0.22589518753910942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129206444","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":[0.000026488375,0.00046884076,0.95570856,0.0037773533,0.00032017435,0.0005011158,0.00004645614,0.00021514442,0.03893587],"genre_scores_gemma":[0.9880833,0.00012871307,0.008633871,0.0014001012,0.00008412994,0.00006573153,0.000053579122,0.000008185153,0.001542374],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987192,0.0000070107144,0.00046331895,0.00026363766,0.0003120898,0.00023475045],"domain_scores_gemma":[0.99895215,0.0003631934,0.0003356638,0.00023119328,0.00008414523,0.00003365876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041227305,0.00021705547,0.0002632885,0.0005142234,0.00020535271,0.0004776025,0.0006424816,0.00021882777,0.000019975401],"category_scores_gemma":[0.00017315034,0.00016755034,0.00006653571,0.00014659227,0.00019945584,0.0020669177,0.00008565606,0.00018658677,0.000012842381],"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":[0.000010111199,0.0000052895625,0.00029082253,0.000042866617,0.000010090955,4.8412215e-7,0.0001544828,0.00072328775,0.000030350926,0.692468,0.0005345752,0.30572966],"study_design_scores_gemma":[0.0021372247,0.0006500958,0.0017866073,0.000116463474,0.000026821794,0.000015067925,0.000009185083,0.13559169,0.0009885889,0.3557954,0.50189704,0.0009857877],"about_ca_topic_score_codex":0.00002707416,"about_ca_topic_score_gemma":0.000040598614,"teacher_disagreement_score":0.98805684,"about_ca_system_score_codex":0.00004643626,"about_ca_system_score_gemma":0.000106118656,"threshold_uncertainty_score":0.6832504},"labels":[],"label_agreement":null},{"id":"W2130734227","doi":"10.1109/ccece.2004.1344986","title":"Evaluation of three dimensionality reduction techniques for document classification","year":2004,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"Dalhousie University","funders":"","keywords":"Dimensionality reduction; Computer science; Curse of dimensionality; Reduction (mathematics); Artificial intelligence; Latent semantic analysis; Categorization; Document classification; Search engine indexing; Machine learning; Data mining; Representation (politics); Measure (data warehouse); Pattern recognition (psychology); Information retrieval; Mathematics","score_opus":0.09872650376107284,"score_gpt":0.34840919105193274,"score_spread":0.2496826872908599,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130734227","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":[0.020421145,0.00005901874,0.96978265,0.006492405,0.00014500564,0.00084001926,0.0000010341143,0.0005441412,0.0017146026],"genre_scores_gemma":[0.80668116,0.000008460209,0.1929598,0.0000145508275,0.000014842245,0.00027824557,0.0000063424573,0.0000030057786,0.000033611777],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998697,0.000032728578,0.00028660364,0.00028092857,0.00059726427,0.000105470506],"domain_scores_gemma":[0.99851435,0.000026606056,0.00019144517,0.00053916615,0.0007082847,0.000020132667],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016252705,0.00007938332,0.000093025716,0.0001243213,0.00008660544,0.00004064674,0.00035967308,0.00007244552,0.000012788797],"category_scores_gemma":[0.0001283392,0.00006761247,0.000053168176,0.00026256245,0.000060325812,0.00055323134,0.00006356077,0.000038958617,0.000006028466],"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":[0.0000027616272,0.000054002383,0.000019631076,0.000004669103,0.0000075189087,8.142579e-9,0.000026660888,0.000039747054,0.027724719,0.74609834,0.00017089951,0.22585106],"study_design_scores_gemma":[0.00028810228,0.00007543992,0.0031541863,0.000009299234,0.000018085942,0.0000012501054,0.000053792344,0.004045337,0.3394064,0.6524231,0.00045317048,0.00007184686],"about_ca_topic_score_codex":0.000024857763,"about_ca_topic_score_gemma":0.000008534151,"teacher_disagreement_score":0.78626,"about_ca_system_score_codex":0.0002298091,"about_ca_system_score_gemma":0.00015344973,"threshold_uncertainty_score":0.27571565},"labels":[],"label_agreement":null},{"id":"W2130987418","doi":"10.1109/wi.2005.79","title":"Integrating Compound Terms in Bayesian Text Classification","year":2005,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Smoothing; Word (group theory); Artificial intelligence; Natural language processing; Bayesian probability; Term (time); Representation (politics); Naive Bayes classifier; Compound; Component (thermodynamics); Machine learning; Mathematics; Support vector machine","score_opus":0.024132435082527756,"score_gpt":0.2743366962494589,"score_spread":0.2502042611669311,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130987418","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":[0.011037079,0.00003183944,0.8972653,0.019557951,0.00007933703,0.00014531812,2.378161e-7,0.0008232354,0.07105971],"genre_scores_gemma":[0.87685186,0.000008082496,0.12180002,0.00028075918,0.000021098102,0.000023122151,0.00000189237,0.0000036661957,0.001009515],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990936,0.000025351575,0.00026669726,0.00029034924,0.00014096973,0.00018306357],"domain_scores_gemma":[0.99931765,0.00005749255,0.00007730911,0.0004934832,0.000023222183,0.00003082766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017771675,0.00009532572,0.00009415135,0.00020996647,0.00006423796,0.00020470607,0.00077301083,0.00006663433,0.00005505182],"category_scores_gemma":[0.000042503954,0.00007828,0.000026497277,0.000449724,0.000045732482,0.00081494666,0.00011387869,0.0001352104,0.00017611138],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.022478e-7,0.000041279694,0.004245098,0.0000014433838,0.000001140148,6.656698e-7,0.00017851082,0.0000061236487,0.00253857,0.6137891,0.0010111537,0.37818635],"study_design_scores_gemma":[0.00075929856,0.00007711258,0.10378783,0.00004250752,0.000002428704,0.000017448552,0.0012292681,0.73600775,0.019590324,0.05509267,0.08281805,0.0005752846],"about_ca_topic_score_codex":0.00001836214,"about_ca_topic_score_gemma":0.00014653099,"teacher_disagreement_score":0.86581475,"about_ca_system_score_codex":0.00009743211,"about_ca_system_score_gemma":0.000021891994,"threshold_uncertainty_score":0.31921655},"labels":[],"label_agreement":null},{"id":"W2131912994","doi":"10.1109/icdew.2007.4401066","title":"Document Representation and Dimension Reduction for Text Clustering","year":2007,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Cluster analysis; Dimensionality reduction; Computer science; Document clustering; Artificial intelligence; Pattern recognition (psychology); Representation (politics); Context (archaeology); Benchmark (surveying); Word (group theory); Dimension (graph theory); Natural language processing; Mathematics","score_opus":0.02785592813353458,"score_gpt":0.3078267137122061,"score_spread":0.2799707855786715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131912994","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":[0.038169205,0.00004274033,0.9575168,0.0024450994,0.0002432149,0.00021596329,7.2391565e-8,0.00036279857,0.0010040955],"genre_scores_gemma":[0.84721345,0.000021100108,0.15164547,0.000043525808,0.000020767455,0.000015600463,0.0000014081483,0.0000025111199,0.0010361708],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99942404,0.000005443623,0.0001390108,0.00022711513,0.000088217224,0.00011615418],"domain_scores_gemma":[0.99960923,0.00004577156,0.000052183277,0.00023157427,0.000036051573,0.000025177977],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025195253,0.000051185332,0.00004886976,0.00009647326,0.00009538406,0.00009624547,0.00012762939,0.000035515404,0.000004375647],"category_scores_gemma":[0.00002651994,0.000044104076,0.000016606495,0.00014107462,0.000022768694,0.0004909618,0.00010919031,0.00002629172,0.0000059475456],"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":[0.000014824846,0.000016578257,0.00020193351,0.000008723651,0.0000051995557,5.3767644e-7,0.0003344176,0.000017736254,0.042103916,0.23774257,0.0016833566,0.71787024],"study_design_scores_gemma":[0.0014667353,0.0003680457,0.020859348,0.000028555516,0.000012830341,0.00007821995,0.0022831422,0.042822804,0.7828527,0.12696251,0.021776991,0.00048812586],"about_ca_topic_score_codex":0.000010759797,"about_ca_topic_score_gemma":0.0000044625463,"teacher_disagreement_score":0.80904424,"about_ca_system_score_codex":0.000027668524,"about_ca_system_score_gemma":0.000004532207,"threshold_uncertainty_score":0.1798512},"labels":[],"label_agreement":null},{"id":"W2133411495","doi":"10.1109/ideas.2007.11","title":"An Approach for Text Categorization in Digital Library","year":2007,"lang":"en","type":"article","venue":"International Database Engineering and Applications Symposium","topic":"Text and Document Classification Technologies","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":"Concordia University","funders":"","keywords":"Categorization; Computer science; Hierarchy; Digital library; Text categorization; Information retrieval; Library classification; Document classification; Artificial intelligence; Data mining; Machine learning; World Wide Web","score_opus":0.0074841454346884365,"score_gpt":0.23153515328483412,"score_spread":0.22405100785014567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133411495","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":[0.0017852553,0.0000404762,0.996079,0.00046834344,0.000058711903,0.00025764017,0.00011446799,0.00038802045,0.0008080692],"genre_scores_gemma":[0.86980945,0.00004340598,0.12804618,0.000040324543,0.00010949175,0.0003135443,0.0014940375,0.000012206296,0.0001313657],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993052,0.0000016546928,0.00018589142,0.00028296874,0.00009790323,0.00012637807],"domain_scores_gemma":[0.9995116,0.00006580027,0.00004144697,0.0003010148,0.000031507243,0.000048637503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011304193,0.00008573445,0.000058710848,0.00025855104,0.000041115254,0.00026217196,0.0005206167,0.00004125093,0.0000016481907],"category_scores_gemma":[0.000014805652,0.000089202396,0.000015581421,0.00026253148,0.000017351007,0.0015647452,0.000095594805,0.00006350965,0.0000038697995],"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":[0.0000053335116,0.00016290705,0.0014585468,0.000021330237,0.00000787511,5.790218e-7,0.000046464505,0.0028088372,0.009134793,0.95895135,0.0001917352,0.02721024],"study_design_scores_gemma":[0.00050232845,0.000032076747,0.00283415,0.000014907537,0.0000037249015,0.000014549161,0.00008940273,0.86753416,0.011482202,0.0035684158,0.113581166,0.00034292915],"about_ca_topic_score_codex":0.000002228113,"about_ca_topic_score_gemma":2.4463333e-7,"teacher_disagreement_score":0.95538294,"about_ca_system_score_codex":0.00002348496,"about_ca_system_score_gemma":0.000013180624,"threshold_uncertainty_score":0.36375684},"labels":[],"label_agreement":null},{"id":"W2133885011","doi":"10.1109/wi.2006.109","title":"Learning Social Networks from Web Documents Using Support Vector Classifiers","year":2006,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"University of Waterloo","funders":"","keywords":"Computer science; Support vector machine; Classifier (UML); Social network (sociolinguistics); Artificial intelligence; Class (philosophy); Machine learning; Data mining; Social media; World Wide Web","score_opus":0.019507911583515523,"score_gpt":0.2566065554475822,"score_spread":0.23709864386406668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133885011","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":[0.14739503,0.00004740928,0.8285048,0.0018359949,0.0006328575,0.00014428995,0.0000017072139,0.0020281398,0.019409763],"genre_scores_gemma":[0.97972554,0.00000647946,0.01679157,0.00012210914,0.00017363785,0.000007786672,0.000016477034,0.000010060058,0.0031463115],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99872535,0.000043979948,0.00025621086,0.00038196752,0.00025417242,0.000338294],"domain_scores_gemma":[0.99946237,0.000048365007,0.00014133501,0.00027316858,0.000038844813,0.00003589496],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012014627,0.00014527151,0.00014835196,0.00010114256,0.00032510198,0.00037486784,0.0006733716,0.00014496598,0.00024245144],"category_scores_gemma":[0.00001294102,0.00013609612,0.00007243403,0.00036474553,0.000075530734,0.0006361596,0.00025299093,0.0002180907,0.000083604435],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024124447,0.0002815529,0.10439672,0.000009967345,0.000121012956,0.000046411355,0.00056478643,0.0049557183,0.02406296,0.5947173,0.11942746,0.15139198],"study_design_scores_gemma":[0.0013236447,0.00012830221,0.057303224,0.000013814555,0.000030740906,0.0000053325625,0.00057231635,0.8093668,0.004408787,0.02177452,0.10412124,0.00095128256],"about_ca_topic_score_codex":0.00021170158,"about_ca_topic_score_gemma":0.000020448499,"teacher_disagreement_score":0.8323305,"about_ca_system_score_codex":0.00010157737,"about_ca_system_score_gemma":0.00006064092,"threshold_uncertainty_score":0.55498385},"labels":[],"label_agreement":null},{"id":"W2135420268","doi":"10.1109/grc.2007.40","title":"Naïve Bayes Text Classifier","year":2007,"lang":"en","type":"article","venue":"2007 IEEE International Conference on Granular Computing (GRC 2007)","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":98,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Acadia University","funders":"","keywords":"Naive Bayes classifier; Computer science; Bayes' theorem; Support vector machine; Artificial intelligence; Machine learning; Detector; Classifier (UML); Bayesian probability; Information retrieval; Data mining","score_opus":0.07050096873332103,"score_gpt":0.32941739982444823,"score_spread":0.2589164310911272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135420268","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":[0.021077555,0.000076104436,0.8960201,0.0024237663,0.005307004,0.0002562521,0.000009928619,0.0009023241,0.073926926],"genre_scores_gemma":[0.94981277,0.000047608428,0.043508213,0.0012205571,0.0005639984,0.000008724181,0.000028311579,0.000029375698,0.0047804615],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962035,0.00008026652,0.0008558437,0.00095299206,0.0011615851,0.0007458274],"domain_scores_gemma":[0.9974197,0.00033405182,0.0004587866,0.0009820425,0.0006064997,0.00019892074],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013251392,0.00043196775,0.0003389218,0.0006879121,0.0003219351,0.0006082693,0.0027517078,0.00027692987,0.00063690834],"category_scores_gemma":[0.00023095438,0.000418536,0.00019955002,0.000538956,0.0002415108,0.00053576333,0.0003288498,0.00062638964,0.0020196212],"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":[0.000065612185,0.00036336645,0.0037959262,0.000016066453,0.00009815882,0.00006853428,0.0004676294,0.00018378414,0.0067405263,0.78018385,0.03503496,0.17298158],"study_design_scores_gemma":[0.0040173912,0.0006914929,0.030335175,0.00072166027,0.000052941312,0.0002600985,0.000932888,0.24736889,0.036072113,0.08312909,0.59287333,0.003544944],"about_ca_topic_score_codex":0.00003160731,"about_ca_topic_score_gemma":0.00001691479,"teacher_disagreement_score":0.9287352,"about_ca_system_score_codex":0.00024221641,"about_ca_system_score_gemma":0.00013158818,"threshold_uncertainty_score":0.99982667},"labels":[],"label_agreement":null},{"id":"W2135718742","doi":"10.1109/icdmw.2007.21","title":"Learning Term Dependency Links Using Information Theoretic Inclusion Measure","year":2007,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"University of Waterloo","funders":"","keywords":"Dependency (UML); Computer science; Dependency graph; Redundancy (engineering); Term (time); Data mining; Feature selection; Support vector machine; Artificial intelligence; Pattern recognition (psychology); Graph; Theoretical computer science","score_opus":0.015203971713335993,"score_gpt":0.260510980564972,"score_spread":0.24530700885163603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135718742","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":[0.07591136,0.000029904486,0.90814024,0.00046707815,0.00011964389,0.00009156216,5.749813e-8,0.0008102529,0.01442991],"genre_scores_gemma":[0.9629219,0.0000092876,0.03678318,0.00014890824,0.000013739803,0.0000015080575,0.0000017349217,0.0000027142942,0.0001170037],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991006,0.00002148273,0.00023598583,0.00012911102,0.0003206071,0.000192197],"domain_scores_gemma":[0.999411,0.000050805866,0.00011887355,0.00028989514,0.00009284821,0.00003659584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007176698,0.00008407686,0.000064783955,0.00022261513,0.00042019202,0.00016067806,0.0006093689,0.00016596697,0.00003055627],"category_scores_gemma":[0.00013287828,0.000068167574,0.000030055657,0.00033964743,0.00003715991,0.001601358,0.0008904824,0.0002870504,0.00006684032],"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":[0.0000032926641,0.000012783471,0.0039895824,0.000007646707,0.0000029934506,0.000001383168,0.0016655512,0.000060889135,0.003922357,0.36187032,0.000022803802,0.6284404],"study_design_scores_gemma":[0.0019154487,0.0005481449,0.051039852,0.00018470264,0.00003132233,0.000109995686,0.004192182,0.36386532,0.24050836,0.31926033,0.016691031,0.0016533274],"about_ca_topic_score_codex":0.000009323212,"about_ca_topic_score_gemma":0.0000029984865,"teacher_disagreement_score":0.8870106,"about_ca_system_score_codex":0.00006575202,"about_ca_system_score_gemma":0.000033320328,"threshold_uncertainty_score":0.323182},"labels":[],"label_agreement":null},{"id":"W2137320444","doi":"","title":"Linear Text Segmentation Using Affinity Propagation","year":2011,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Affinity propagation; Segmentation; Computer science; Cluster analysis; Pairwise comparison; Graph; Image segmentation; Set (abstract data type); Algorithm; Artificial intelligence; Pattern recognition (psychology); Theoretical computer science; Correlation clustering; Canopy clustering algorithm","score_opus":0.10355150825609499,"score_gpt":0.28873001400381515,"score_spread":0.18517850574772016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137320444","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":[0.077695936,0.0000064888263,0.91390836,0.0002097106,0.00009738796,0.00011688888,1.6289495e-7,0.0006371516,0.0073278937],"genre_scores_gemma":[0.67497414,0.0000025607924,0.3247308,0.000046255394,0.0000076215306,0.0000063018515,8.6034106e-7,0.00000200021,0.00022946043],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99949574,0.000016872737,0.00012142843,0.00016344439,0.000108361506,0.000094157236],"domain_scores_gemma":[0.999583,0.000009738606,0.000068060144,0.00027170058,0.000047617938,0.000019899056],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000095151736,0.000055671168,0.0000444803,0.00007989236,0.000077596225,0.000044610908,0.00031666312,0.000037533744,0.00009112891],"category_scores_gemma":[0.000020866624,0.000046234203,0.000017645933,0.0002455595,0.000026723288,0.0007149649,0.000091211004,0.000042025684,0.000121635254],"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":[0.000006326068,0.00022570908,0.005663724,0.000012184673,0.000012553727,0.0000023268187,0.001702646,0.000022654685,0.055361558,0.72910494,0.0005512977,0.20733409],"study_design_scores_gemma":[0.00029839049,0.0001247139,0.011650317,0.000007772502,0.0000062506715,0.0000062935555,0.0004488159,0.13103008,0.8291741,0.026400372,0.0005927319,0.00026015277],"about_ca_topic_score_codex":0.000027809303,"about_ca_topic_score_gemma":0.000002855225,"teacher_disagreement_score":0.77381253,"about_ca_system_score_codex":0.000028020451,"about_ca_system_score_gemma":0.000023938393,"threshold_uncertainty_score":0.18853761},"labels":[],"label_agreement":null},{"id":"W2139676742","doi":"10.48550/arxiv.1307.2669","title":"Text Categorization via Similarity Search: An Efficient and Effective Novel Algorithm","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Text and Document Classification Technologies","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":"University of Ottawa","funders":"","keywords":"Computer science; Similarity (geometry); Centroid; Cluster analysis; Categorization; Artificial intelligence; Outlier; Preprocessor; Metric (unit); Text categorization; Class (philosophy); Point (geometry); Similarity measure; Measure (data warehouse); Nearest neighbor search; Pattern recognition (psychology); Data mining; Mathematics; Image (mathematics)","score_opus":0.06421189842904142,"score_gpt":0.20263899289794898,"score_spread":0.13842709446890755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139676742","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":[0.15814313,0.000027021382,0.83989626,0.00019046375,0.00023675952,0.0006192963,0.00001183442,0.0005907089,0.00028450578],"genre_scores_gemma":[0.9865844,0.00007460447,0.012950925,0.00003906468,0.000030013809,0.0000062365816,0.000031074116,0.000013716112,0.00026995465],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980388,0.00012152425,0.00016617704,0.0012228852,0.0001307214,0.00031983794],"domain_scores_gemma":[0.99815893,0.000102002356,0.00018085461,0.0011555773,0.00024058709,0.00016204725],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026071246,0.00029749158,0.00026177228,0.00036445117,0.00023675409,0.00030279148,0.0013420667,0.0003738699,0.000014867415],"category_scores_gemma":[0.00002959251,0.00031932647,0.00007493717,0.0005755513,0.00023450916,0.0005544542,0.002104305,0.00052866794,0.00005614454],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014219214,0.00058340275,0.0013629238,0.00010325038,0.00010538569,0.000039799947,0.0009300819,0.117124766,0.0007641576,0.7647244,0.00009033735,0.1141573],"study_design_scores_gemma":[0.0003565419,0.000087502485,0.007721097,0.000018196779,0.000024510411,0.000003068071,0.0001146027,0.97094256,0.0012904058,0.018926386,0.00014962185,0.00036552374],"about_ca_topic_score_codex":0.00027907616,"about_ca_topic_score_gemma":0.000007553469,"teacher_disagreement_score":0.85381776,"about_ca_system_score_codex":0.00016563761,"about_ca_system_score_gemma":0.00008802852,"threshold_uncertainty_score":0.99992585},"labels":[],"label_agreement":null},{"id":"W2141501959","doi":"10.1109/icdew.2007.4401067","title":"Incorporating Temporal Information for Document Classification","year":2007,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Document classification; Feature selection; Artificial intelligence; Feature (linguistics); Set (abstract data type); Genetic programming; Sequence (biology); Word (group theory); Selection (genetic algorithm); Data mining; Pattern recognition (psychology); Mathematics","score_opus":0.025939784521459976,"score_gpt":0.28465698527073685,"score_spread":0.2587172007492769,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141501959","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":[0.0022885296,0.000006792656,0.984252,0.0035000516,0.00017684589,0.0003286544,5.8120804e-7,0.0007888698,0.008657721],"genre_scores_gemma":[0.7188201,0.0000011391166,0.2806288,0.00023783118,0.000017047825,0.00004011109,0.000017008875,0.000001884056,0.00023610919],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991624,0.000006378466,0.00034816348,0.0001423049,0.00017143374,0.00016931561],"domain_scores_gemma":[0.9992013,0.000076871984,0.00020950325,0.0003498688,0.00012475073,0.000037692855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068894465,0.00007753081,0.000066010536,0.00018534837,0.00013014364,0.00023727347,0.00047057203,0.00006436883,0.000006515328],"category_scores_gemma":[0.00008397929,0.00006659995,0.000034022545,0.0003139625,0.00002789203,0.00231558,0.00008156321,0.00004926894,0.000066351706],"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":[0.0000029284995,0.000008068625,0.0008374251,0.0000047804833,0.000001929119,5.7258376e-8,0.00007056314,0.0000016728219,0.00048002077,0.78540504,0.0015807718,0.21160676],"study_design_scores_gemma":[0.0016422574,0.00037864878,0.04301662,0.000020177884,0.000008675958,0.000007794567,0.0025783398,0.06905503,0.0840951,0.46524987,0.33318624,0.0007612475],"about_ca_topic_score_codex":0.000008990208,"about_ca_topic_score_gemma":0.000008102475,"teacher_disagreement_score":0.7165316,"about_ca_system_score_codex":0.00006946646,"about_ca_system_score_gemma":0.000035638208,"threshold_uncertainty_score":0.27158672},"labels":[],"label_agreement":null},{"id":"W2142742813","doi":"","title":"Learning from multiple partially observed views - an application to multilingual text categorization","year":2009,"lang":"en","type":"preprint","venue":"NPARC","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":274,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Leverage (statistics); Categorization; Machine learning; Natural language processing; Generalization; Text categorization; Set (abstract data type); Training set; Supervised learning; Artificial neural network; Mathematics","score_opus":0.0694166084151494,"score_gpt":0.29874234639495834,"score_spread":0.22932573797980893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142742813","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":[0.10298077,0.000047709127,0.8917206,0.0018570232,0.00029924305,0.0007943869,0.0000064410588,0.0017234905,0.00057033036],"genre_scores_gemma":[0.83459455,0.000034684872,0.16423938,0.0001881927,0.00014269295,0.00025841108,0.00035282195,0.000018341336,0.00017092295],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975087,0.00016099156,0.00051911373,0.0011309611,0.0003735243,0.0003067017],"domain_scores_gemma":[0.9976572,0.00009008375,0.00038940174,0.0015422924,0.00018012851,0.00014089435],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003265804,0.0003073078,0.0003240968,0.00018504712,0.00018796338,0.0004922353,0.0019494635,0.00037640068,0.00002914979],"category_scores_gemma":[0.00029537448,0.00031765527,0.0000863537,0.00033659607,0.000031931148,0.0003943325,0.0008508241,0.0005563978,0.00020406515],"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":[0.000012690754,0.0001457746,0.0019180538,0.0000135968885,0.000013706129,0.0000016437707,0.0018742337,0.013835194,0.08372882,0.008698211,0.00030181464,0.8894563],"study_design_scores_gemma":[0.00044101616,0.000199671,0.025349319,0.000057221896,0.000022326381,5.945522e-7,0.00019545162,0.7903901,0.06278173,0.097042784,0.02270797,0.000811869],"about_ca_topic_score_codex":0.00015766761,"about_ca_topic_score_gemma":0.00019179609,"teacher_disagreement_score":0.8886444,"about_ca_system_score_codex":0.00012221256,"about_ca_system_score_gemma":0.00012802372,"threshold_uncertainty_score":0.9999276},"labels":[],"label_agreement":null},{"id":"W2143765837","doi":"10.1109/icmla.2005.47","title":"Multi-label Associative Classification of Medical Documents from MEDLINE","year":2006,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Associative property; Information retrieval; Document classification; Point (geometry); Multi-label classification; Data mining; Artificial intelligence; Machine learning","score_opus":0.03854488586979353,"score_gpt":0.3163884499854844,"score_spread":0.27784356411569083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143765837","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":[0.060912453,0.00014201,0.9194327,0.014481882,0.00021975758,0.00016300686,0.000013007753,0.0006617251,0.0039734417],"genre_scores_gemma":[0.78650385,0.000036228066,0.2117833,0.00012471789,0.00003347116,0.000022309156,0.0000404316,0.000005177011,0.0014504911],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99827933,0.00004921057,0.00039930412,0.00031356208,0.00079546944,0.00016310238],"domain_scores_gemma":[0.9989641,0.00016498496,0.00026097763,0.00045324885,0.00011244062,0.000044263797],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030080526,0.00010614656,0.00016579198,0.00010295777,0.000053166015,0.00006655899,0.0012164554,0.00017951214,0.00017741251],"category_scores_gemma":[0.00017634407,0.00008704019,0.00003995423,0.000361833,0.00009182923,0.00042185822,0.0002398385,0.00011965465,0.000085448984],"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":[0.0000046043715,0.000942214,0.029207543,0.0000060740576,0.00005217219,0.0000030900617,0.00021741807,9.2379173e-7,0.025281612,0.7357659,0.018525127,0.18999334],"study_design_scores_gemma":[0.0027290569,0.000075214266,0.32356727,0.00003427048,0.00001565621,8.686605e-7,0.0003309346,0.5488092,0.058677234,0.060918327,0.004463778,0.00037823815],"about_ca_topic_score_codex":0.0006328996,"about_ca_topic_score_gemma":0.00013014466,"teacher_disagreement_score":0.7255914,"about_ca_system_score_codex":0.00006502577,"about_ca_system_score_gemma":0.000065032254,"threshold_uncertainty_score":0.35493958},"labels":[],"label_agreement":null},{"id":"W2145753452","doi":"10.1109/ccece.2007.203","title":"Document Classification with ACM Subject Hierarchy","year":2007,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Categorization; Information retrieval; Hierarchy; Classifier (UML); Document classification; Text categorization; Digital library; Classification scheme; Library classification; Subject (documents); Focus (optics); Context (archaeology); Artificial intelligence; World Wide Web; Natural language processing","score_opus":0.02711306376552129,"score_gpt":0.28022091107257885,"score_spread":0.25310784730705754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145753452","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":[0.0251084,0.0000364308,0.93647474,0.009163386,0.0000947539,0.00018426303,1.5805578e-7,0.0013173311,0.027620547],"genre_scores_gemma":[0.83925766,0.000013762365,0.15819623,0.00023552953,0.000016922992,0.000017143404,0.000002011021,0.000005023779,0.0022556975],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9988625,0.000014884839,0.0001988449,0.00034696955,0.00030216252,0.0002746595],"domain_scores_gemma":[0.9984389,0.000109573055,0.000085549254,0.0012326875,0.00006981637,0.00006348244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042274193,0.00011099956,0.00008608412,0.00019956572,0.00010774286,0.00017907942,0.0013343599,0.00005969958,0.00004681128],"category_scores_gemma":[0.00005577844,0.0000780409,0.000026724505,0.00060365954,0.00007836929,0.0006270581,0.00021877087,0.00010320377,0.00016521719],"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":[0.00000920359,0.000034526358,0.0033799212,0.000002686209,0.0000076866945,0.000004047205,0.00011253087,8.726059e-7,0.0023537474,0.8079497,0.0017290217,0.18441601],"study_design_scores_gemma":[0.0016126258,0.000773238,0.35706323,0.000030372697,0.000015311824,0.000058235157,0.0013780392,0.0018141287,0.25187013,0.1894144,0.1949099,0.0010604195],"about_ca_topic_score_codex":0.0000123246145,"about_ca_topic_score_gemma":0.000024576813,"teacher_disagreement_score":0.81414926,"about_ca_system_score_codex":0.00007554482,"about_ca_system_score_gemma":0.000041694206,"threshold_uncertainty_score":0.31824157},"labels":[],"label_agreement":null},{"id":"W2146327010","doi":"10.5539/cis.v1n4p79","title":"Text Document Pre-Processing Using the Bayes Formula for Classification Based on the Vector Space Model","year":2008,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Naive Bayes classifier; Bayes' theorem; Support vector machine; Bayes classifier; Document classification; Artificial intelligence; Dimensionality reduction; Curse of dimensionality; Classifier (UML); Vector space model; Pattern recognition (psychology); Bayes error rate; Range (aeronautics); Set (abstract data type); Probability distribution; Machine learning; Data mining; Bayesian probability; Mathematics; Statistics","score_opus":0.052435184597413045,"score_gpt":0.2869064813885296,"score_spread":0.23447129679111656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146327010","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":[0.013208166,0.000015662337,0.97804964,0.0075312597,0.0001230512,0.00042135172,0.000001526827,0.00015752777,0.00049181754],"genre_scores_gemma":[0.9067449,0.000013712995,0.091612644,0.001531843,0.000020966625,0.00005171802,0.0000015557027,0.0000023562486,0.000020295096],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880636,0.000017132248,0.000265099,0.00022115221,0.00046168838,0.00022856447],"domain_scores_gemma":[0.9987999,0.00015753676,0.00021288631,0.00054039125,0.0002442981,0.00004495275],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0007007942,0.00011863942,0.00008157291,0.00019362808,0.0015841806,0.0008545336,0.0011587424,0.00003631974,0.0000013592366],"category_scores_gemma":[0.00007804519,0.00006582963,0.000035156474,0.00071595085,0.00043196787,0.005995282,0.00019573832,0.0000911553,0.0000052508417],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015324018,0.000028872117,0.00012973249,0.000028395272,0.0000030411634,8.094702e-8,0.005225435,0.038211606,0.0011057237,0.7821742,0.0015816188,0.17149597],"study_design_scores_gemma":[0.00015783895,0.000047585076,0.0028523924,0.000015633206,0.000001776952,0.0000043998957,0.00009023548,0.98986757,0.0020473278,0.002232073,0.0025823123,0.00010082858],"about_ca_topic_score_codex":0.00000211005,"about_ca_topic_score_gemma":1.5632766e-7,"teacher_disagreement_score":0.951656,"about_ca_system_score_codex":0.00007256985,"about_ca_system_score_gemma":0.00022907865,"threshold_uncertainty_score":0.9997156},"labels":[],"label_agreement":null},{"id":"W2146466957","doi":"10.1109/icmlc.2004.1382026","title":"Combining word based and word co-occurrence based sequence analysis for text categorization","year":2005,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"Dalhousie University","funders":"","keywords":"Categorization; Computer science; Word (group theory); Artificial intelligence; Classifier (UML); Text categorization; Curse of dimensionality; Natural language processing; Encoding (memory); Set (abstract data type); Sequence (biology); Data set; Pattern recognition (psychology); Mathematics","score_opus":0.04847486091432971,"score_gpt":0.3054395120498646,"score_spread":0.25696465113553485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146466957","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":[0.007900533,0.000027474529,0.9856416,0.0052384934,0.000041652598,0.0002077368,0.000013428889,0.00059417204,0.00033488983],"genre_scores_gemma":[0.87758064,0.0000058087976,0.12160551,0.00048924127,0.0000084710855,0.00006558697,0.00007282985,0.0000032954083,0.00016861853],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99888444,0.000027589658,0.00024260802,0.00043782042,0.00018537111,0.00022219207],"domain_scores_gemma":[0.99897015,0.00024886432,0.00013314588,0.0004886176,0.00009779944,0.00006143854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002529034,0.00013275084,0.00016912894,0.00038617558,0.00017714391,0.00028040505,0.0005552862,0.000069762646,0.000047279656],"category_scores_gemma":[0.00009013528,0.00011984611,0.00006308099,0.0012288706,0.0000851532,0.0005802254,0.000051414256,0.00007015352,0.000013368226],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024361489,0.00019765434,0.050473806,0.000041864794,0.0000957683,0.0000013317692,0.00029073888,0.008154235,0.0031691953,0.20510487,0.0025241037,0.72992206],"study_design_scores_gemma":[0.0004750357,0.00004427882,0.005301156,0.0000063758544,0.00003656691,3.0181536e-7,0.000046211284,0.9679119,0.016637972,0.0012380382,0.008076507,0.0002256611],"about_ca_topic_score_codex":0.000010486858,"about_ca_topic_score_gemma":0.000023593577,"teacher_disagreement_score":0.9597577,"about_ca_system_score_codex":0.00004832964,"about_ca_system_score_gemma":0.00007870943,"threshold_uncertainty_score":0.48871827},"labels":[],"label_agreement":null},{"id":"W2146849021","doi":"10.1109/icdmw.2009.88","title":"Document Clustering Using Semantic Kernels Based on Term-Term Correlations","year":2009,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Term (time); Computer science; Cluster analysis; Artificial intelligence; Information retrieval; Natural language processing; Physics","score_opus":0.03233434636012254,"score_gpt":0.29052140675123816,"score_spread":0.2581870603911156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146849021","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":[0.028781075,0.000010761371,0.9611779,0.0036445195,0.00019898805,0.00017336743,3.1314067e-7,0.0008597469,0.005153358],"genre_scores_gemma":[0.95152247,0.0000027348156,0.047051642,0.00070612703,0.00001767656,0.0000055298297,0.0000017193072,0.0000041697776,0.0006879551],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990122,0.000021223954,0.0002153129,0.000312349,0.00022245492,0.00021647637],"domain_scores_gemma":[0.99913186,0.000051230018,0.000085415966,0.0006565385,0.00002834094,0.000046616253],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010541599,0.00012708541,0.00010637136,0.00020038446,0.00016573614,0.00027936875,0.00057392806,0.000059934755,0.00006112253],"category_scores_gemma":[0.00001968522,0.000109534274,0.00005201345,0.0002974133,0.000026083628,0.00047037235,0.00008932728,0.00009689984,0.00008780936],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022922644,0.0005811908,0.012801811,0.000034370965,0.000028913153,0.000046803867,0.000654337,0.03744249,0.03213253,0.48840663,0.0018956877,0.42595232],"study_design_scores_gemma":[0.00039108685,0.00014234733,0.031070882,0.000055744815,0.000006805771,0.000006314982,0.000023895751,0.95326406,0.0075514037,0.0069444748,0.00028915264,0.00025382196],"about_ca_topic_score_codex":0.000004941293,"about_ca_topic_score_gemma":0.0000017714447,"teacher_disagreement_score":0.92274135,"about_ca_system_score_codex":0.00008644366,"about_ca_system_score_gemma":0.000031438947,"threshold_uncertainty_score":0.44666782},"labels":[],"label_agreement":null},{"id":"W2148972377","doi":"10.1145/1571941.1572114","title":"Reciprocal rank fusion outperforms condorcet and individual rank learning methods","year":2009,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":568,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reciprocal; Condorcet method; Rank (graph theory); Computer science; Simple (philosophy); Mean reciprocal rank; Fusion; Fuse (electrical); Artificial intelligence; Learning to rank; Machine learning; Mathematics; Ranking (information retrieval); Combinatorics; Engineering; Voting","score_opus":0.04029236246797672,"score_gpt":0.32614302800545814,"score_spread":0.2858506655374814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148972377","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":[0.048326008,0.0002566224,0.93791306,0.005465303,0.000116427094,0.00016401244,2.2522332e-7,0.0017738278,0.0059845177],"genre_scores_gemma":[0.71538323,0.00008497421,0.28280574,0.0004910077,0.000016855614,0.0000068202753,0.0000022108125,0.0000043174114,0.0012048392],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989361,0.00008060106,0.00020970542,0.0003460079,0.00020429154,0.00022326176],"domain_scores_gemma":[0.99939716,0.0001181975,0.00007602625,0.00031180258,0.000036600217,0.000060244263],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007501042,0.00012442877,0.00016010668,0.0001474123,0.00020606392,0.00026078,0.00055650534,0.00011184701,0.00003670608],"category_scores_gemma":[0.00016293672,0.000090885194,0.00003352474,0.00029488927,0.00006488518,0.00058164843,0.00023595932,0.00024091067,0.00003097756],"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":[0.000005739527,0.000017026843,0.0007480193,0.0000020225712,0.0000046998016,0.0000010046269,0.00036685224,0.0000048469105,0.00296929,0.07665597,0.0006408013,0.91858375],"study_design_scores_gemma":[0.0071489397,0.0029269857,0.16816857,0.00008221654,0.00006198471,0.00014227846,0.0031485232,0.14445777,0.24673413,0.19203664,0.2329379,0.0021540367],"about_ca_topic_score_codex":0.0000039764413,"about_ca_topic_score_gemma":5.527925e-7,"teacher_disagreement_score":0.9164297,"about_ca_system_score_codex":0.000014522763,"about_ca_system_score_gemma":0.000020147963,"threshold_uncertainty_score":0.3706191},"labels":[],"label_agreement":null},{"id":"W2150409896","doi":"10.1007/s10044-006-0044-8","title":"On poem recognition","year":2006,"lang":"en","type":"article","venue":"Pattern Analysis and Applications","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Poetry; Lyrics; Computer science; Fuzzy logic; Field (mathematics); Artificial intelligence; Literature; Art; Mathematics","score_opus":0.014736266615565718,"score_gpt":0.24381536547690044,"score_spread":0.22907909886133473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150409896","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":[0.012679439,0.00003185915,0.9810527,0.0018025056,0.000004480947,0.00007864759,0.0000046990594,0.00020884004,0.0041368064],"genre_scores_gemma":[0.9979672,0.000029439869,0.0013176828,0.0002407636,0.000020532008,0.00015292031,0.00004526664,0.0000020817752,0.00022413852],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994586,0.0000099136205,0.00012241154,0.0002414654,0.00008751408,0.00008010717],"domain_scores_gemma":[0.9995054,0.00003793932,0.00006259294,0.00034626835,0.000028096449,0.00001969964],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000052351283,0.0000588982,0.000078160214,0.00021470492,0.00011331465,0.0001202775,0.00020472224,0.000028144994,0.000029027568],"category_scores_gemma":[0.0000023756209,0.000051866056,0.00005139247,0.00076717214,0.000023048591,0.000089394554,0.00004015203,0.00003997536,0.0001244696],"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":[3.1728865e-7,0.0000988627,0.013141346,0.000002549382,0.000051535462,2.5055726e-7,0.000010622096,0.000020000467,0.00041383086,0.23885067,0.0010778258,0.74633217],"study_design_scores_gemma":[0.00035158795,0.000038963073,0.38077918,0.00000707989,0.00030330766,0.000002088785,0.000048678146,0.029226497,0.009945336,0.55545557,0.023344168,0.0004975338],"about_ca_topic_score_codex":0.00006194532,"about_ca_topic_score_gemma":0.000029077508,"teacher_disagreement_score":0.9852877,"about_ca_system_score_codex":0.00000969931,"about_ca_system_score_gemma":0.0000029478629,"threshold_uncertainty_score":0.21150364},"labels":[],"label_agreement":null},{"id":"W2151849342","doi":"10.1109/hicss.2003.1174243","title":"Support vector machines for text categorization","year":2003,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":146,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Categorization; Text categorization; Sorting; Set (abstract data type); Support vector machine; Artificial intelligence; Vocabulary; Feature (linguistics); Natural language processing; Information retrieval; Process (computing); Feature vector","score_opus":0.019827147917964055,"score_gpt":0.2626373654355585,"score_spread":0.24281021751759443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151849342","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":[0.00062945165,0.0000126496625,0.97665364,0.0021316758,0.00023089652,0.00015412012,7.083727e-7,0.0005892997,0.019597586],"genre_scores_gemma":[0.9184598,0.0000044450503,0.072189644,0.00019875784,0.000011225631,0.000058507714,0.000005572235,0.0000043466257,0.009067714],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995108,0.000009061888,0.00010717231,0.00017845361,0.0000745645,0.000119939476],"domain_scores_gemma":[0.99957085,0.00003705822,0.00003853439,0.00028512007,0.000046851834,0.000021572127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009643464,0.00005992852,0.000055809563,0.00006231396,0.00007105281,0.00009500469,0.00031436808,0.00003760693,0.00011245329],"category_scores_gemma":[0.00009176708,0.000047608435,0.000027004306,0.00019865569,0.00001572319,0.00030721235,0.000026692012,0.000023366909,0.000080125224],"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":[3.9728832e-7,0.0000145032645,0.0003895808,0.0000025667493,0.0000018888968,1.0820121e-7,0.00003048733,0.000001531942,0.0011727168,0.9752176,0.004960276,0.018208362],"study_design_scores_gemma":[0.00061860576,0.0001979388,0.0034710853,0.0000019694603,0.0000058677474,0.000008139508,0.00008002784,0.014219316,0.20521381,0.31578326,0.46003833,0.00036163826],"about_ca_topic_score_codex":0.0000028157879,"about_ca_topic_score_gemma":0.0000026277726,"teacher_disagreement_score":0.91783035,"about_ca_system_score_codex":0.000014487217,"about_ca_system_score_gemma":0.000032669574,"threshold_uncertainty_score":0.19414155},"labels":[],"label_agreement":null},{"id":"W2154923335","doi":"10.1109/compsac.2005.128","title":"Recovering \"Lack of Words\" in Text Categorization for Item Banks","year":2006,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"Dalhousie University","funders":"","keywords":"Categorization; Computer science; Phrase; Text categorization; Feature selection; Artificial intelligence; Classifier (UML); Natural language processing; Support vector machine; Selection (genetic algorithm); Sample (material); Machine learning","score_opus":0.03400157365506067,"score_gpt":0.27748418577074196,"score_spread":0.24348261211568129,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154923335","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":[0.032350853,0.00003183208,0.9595033,0.00092634856,0.000087688495,0.00016033948,6.11886e-7,0.000203367,0.006735653],"genre_scores_gemma":[0.9625087,0.000005707281,0.035728816,0.000023620483,0.000009407147,0.000024345263,0.0000036194876,0.0000027584358,0.0016930682],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994805,0.000005896658,0.00019377358,0.0001500874,0.00006973689,0.00010003301],"domain_scores_gemma":[0.9996038,0.00006875443,0.0000701594,0.00021890245,0.000031752432,0.0000066174043],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000960304,0.00004803992,0.00007333843,0.00013053879,0.000018272343,0.000038117087,0.0002944671,0.000044687,0.000011075516],"category_scores_gemma":[0.000037125832,0.000043547945,0.000021507687,0.00034589533,0.000015193019,0.0003101871,0.00005272016,0.000026807129,0.0000058041164],"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":[0.000002089476,0.00003669606,0.0077486006,0.000013837577,0.0000012426284,1.4647854e-7,0.000055676024,0.00033613146,0.0040659714,0.8953811,0.0011902504,0.09116829],"study_design_scores_gemma":[0.0011436624,0.00012970918,0.09910183,0.000035475518,0.000003717125,0.0000014113881,0.0002072499,0.28535292,0.2711086,0.3223027,0.020207623,0.00040509104],"about_ca_topic_score_codex":0.00007607132,"about_ca_topic_score_gemma":0.000056429824,"teacher_disagreement_score":0.9301578,"about_ca_system_score_codex":0.000029594119,"about_ca_system_score_gemma":0.000016402695,"threshold_uncertainty_score":0.17758337},"labels":[],"label_agreement":null},{"id":"W21569900","doi":"","title":"A self-training method for learning to rank with unlabeled data","year":2009,"lang":"en","type":"preprint","venue":"NPARC","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Ranking (information retrieval); Rank (graph theory); Artificial intelligence; Machine learning; Learning to rank; Extension (predicate logic); Scalability; Process (computing); Labeled data; Training set; Pattern recognition (psychology); Bipartite graph; Co-training; Data mining; Semi-supervised learning; Mathematics; Theoretical computer science","score_opus":0.08011453989954655,"score_gpt":0.34640857441247885,"score_spread":0.2662940345129323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W21569900","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002284992,0.000047898822,0.98211706,0.01070895,0.00014205168,0.000806773,0.000010707572,0.0019897781,0.003948259],"genre_scores_gemma":[0.024132818,0.000023128689,0.97474253,0.0003158605,0.00006316036,0.00020065844,0.00006155407,0.000018364772,0.0004419082],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997858,0.00008967383,0.00026927836,0.0011124378,0.0002994193,0.00037118816],"domain_scores_gemma":[0.997055,0.00024959396,0.00022847392,0.002260386,0.00012270887,0.00008386001],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010165101,0.00025194575,0.0003587664,0.00023105383,0.00015989515,0.0004322498,0.0040279897,0.00020120564,0.0000099923],"category_scores_gemma":[0.00030124746,0.00021708218,0.000049956823,0.000339715,0.000019343579,0.0002727128,0.0024496685,0.00052627444,0.000016826543],"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":[0.000023776569,0.00004793149,0.000025705507,0.00008348645,0.00008107956,0.0000042086594,0.001949088,0.0005033213,0.0012503334,0.089570515,0.0051823375,0.9012782],"study_design_scores_gemma":[0.0010422977,0.0004896141,0.00015291032,0.00022189038,0.0000796742,0.000013356937,0.00044144454,0.5249144,0.0028275745,0.20486346,0.26403305,0.00092032127],"about_ca_topic_score_codex":0.0000035278954,"about_ca_topic_score_gemma":0.000005017574,"teacher_disagreement_score":0.9003579,"about_ca_system_score_codex":0.000061638566,"about_ca_system_score_gemma":0.00025922223,"threshold_uncertainty_score":0.8852354},"labels":[],"label_agreement":null},{"id":"W2159620282","doi":"10.1142/s0218001411009019","title":"IMPACT OF TERM DEPENDENCY AND CLASS IMBALANCE ON THE PERFORMANCE OF FEATURE RANKING METHODS","year":2011,"lang":"en","type":"article","venue":"International Journal of Pattern Recognition and Artificial Intelligence","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Ranking (information retrieval); Feature selection; Computer science; Artificial intelligence; Feature (linguistics); Univariate; Pattern recognition (psychology); Data mining; Curse of dimensionality; Machine learning; Classifier (UML); Ranking SVM; Class (philosophy); Multivariate statistics","score_opus":0.1304311421720087,"score_gpt":0.3653728841263023,"score_spread":0.2349417419542936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159620282","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":[0.7945409,0.00007331382,0.20445938,0.00049193634,0.00023509523,0.00005051043,0.000006376823,0.000009192631,0.00013328943],"genre_scores_gemma":[0.9930879,0.00039626614,0.0064098216,0.000057843245,0.000036095844,0.0000020129971,8.011305e-7,0.0000031697011,0.0000060990947],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999062,0.000074766045,0.0004133065,0.00011992937,0.00024743107,0.00008253773],"domain_scores_gemma":[0.99867606,0.00019878367,0.0005794144,0.00012103298,0.00039500187,0.000029713534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004932074,0.00009012468,0.00014003286,0.00019288757,0.000038139373,0.00005319378,0.00055555237,0.000050182283,0.000062642575],"category_scores_gemma":[0.00011432968,0.000058163812,0.00007989157,0.0001102131,0.00013481901,0.00034862748,0.000084893036,0.00018264583,0.0000032577943],"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":[0.00006653568,0.000085578686,0.019285785,0.000008128116,0.000061120205,0.000003680088,0.0007746958,0.000004443675,0.011926432,0.0029844784,0.000010265619,0.96478885],"study_design_scores_gemma":[0.00016124971,0.0011572831,0.14644001,0.0004987808,0.00002476385,0.0001818958,0.00053404784,0.01207176,0.77185243,0.06684021,0.000021327545,0.00021622391],"about_ca_topic_score_codex":0.000011699703,"about_ca_topic_score_gemma":0.000002272486,"teacher_disagreement_score":0.9645726,"about_ca_system_score_codex":0.000018193923,"about_ca_system_score_gemma":0.000027953602,"threshold_uncertainty_score":0.23718514},"labels":[],"label_agreement":null},{"id":"W2159694214","doi":"10.1007/s10618-005-0013-7","title":"Discovering Classification from Data of Multiple Sources","year":2006,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Hong Kong University of Science and Technology","keywords":"Computer science; Class (philosophy); Artificial intelligence; Perspective (graphical); Machine learning; Supervised learning; Test data; Labeled data; Semi-supervised learning; Data mining; Artificial neural network","score_opus":0.09401072320475932,"score_gpt":0.3028926707297767,"score_spread":0.20888194752501738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159694214","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":[0.744359,0.0032022942,0.24861164,0.00030743596,0.00028009492,0.00010646214,0.0014882238,0.0002547168,0.0013901178],"genre_scores_gemma":[0.97685534,0.00009434215,0.019692713,0.0000065778245,0.00008133326,0.0000048377633,0.0029029865,0.0000075819776,0.00035427866],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867135,0.000034016924,0.00030046958,0.00070150953,0.00013404382,0.000158582],"domain_scores_gemma":[0.99663997,0.00029358073,0.00018089237,0.00283604,0.000025254672,0.000024271161],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024075841,0.00012777731,0.00017170733,0.0000989292,0.00010886681,0.00036076596,0.002715456,0.00006217286,0.0000022674262],"category_scores_gemma":[0.00017479993,0.00011235319,0.00001586423,0.00022781605,0.00013809917,0.0034683256,0.0029708722,0.000063515356,0.000007896276],"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":[0.000035630484,0.0006630691,0.2990901,0.00012811161,0.00010363891,0.0000047662224,0.0023336497,0.000013512382,0.028942667,0.0655508,0.042038992,0.56109506],"study_design_scores_gemma":[0.001411599,0.00007814277,0.3370076,0.00029366423,0.000081288534,0.0000050136205,0.005904335,0.5673396,0.013713083,0.0041876812,0.069073334,0.0009046807],"about_ca_topic_score_codex":0.00041364078,"about_ca_topic_score_gemma":0.00038294547,"teacher_disagreement_score":0.56732607,"about_ca_system_score_codex":0.000010906504,"about_ca_system_score_gemma":0.000058349353,"threshold_uncertainty_score":0.5046038},"labels":[],"label_agreement":null},{"id":"W2162987981","doi":"","title":"A characterization of wordnet features in Boolean models for text classification","year":2006,"lang":"en","type":"article","venue":"Australasian Data Mining Conference","topic":"Text and Document Classification Technologies","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":"University of Regina","funders":"","keywords":"WordNet; Computer science; Artificial intelligence; Naive Bayes classifier; Natural language processing; Classifier (UML); Support vector machine; Weighting; Machine learning; Information retrieval","score_opus":0.08786756615368328,"score_gpt":0.2996306411300966,"score_spread":0.21176307497641328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162987981","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":[0.12921613,0.000018322038,0.8656199,0.003059448,0.00011013973,0.0004250691,0.00016364014,0.0002318218,0.0011555471],"genre_scores_gemma":[0.94358516,0.000013103581,0.05495611,0.000018587261,0.000020583177,0.000045219887,0.0008172205,0.0000069083253,0.00053712894],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99871045,0.000026946454,0.00037966896,0.0005035747,0.00015751863,0.00022185849],"domain_scores_gemma":[0.99837327,0.000061697,0.00027268636,0.001184184,0.000083259685,0.00002488141],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021541472,0.00013023775,0.0001715171,0.00021768395,0.000046295005,0.00016688759,0.0017541748,0.00011053164,0.000006645283],"category_scores_gemma":[0.00005827891,0.00013201195,0.000021039561,0.00037610013,0.0000806949,0.0015816409,0.00023325667,0.00008989969,0.000003281437],"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":[0.000019695555,0.00015695987,0.005425821,0.000056299385,0.000009771071,0.0000015892542,0.0005671293,0.000036549125,0.090668164,0.6431443,0.0024169688,0.2574967],"study_design_scores_gemma":[0.0012715304,0.00017571014,0.5208303,0.00027149954,0.00002226438,0.000009031654,0.0009065743,0.39234975,0.03126755,0.047265645,0.004946199,0.00068397704],"about_ca_topic_score_codex":0.0000462287,"about_ca_topic_score_gemma":0.00010027849,"teacher_disagreement_score":0.814369,"about_ca_system_score_codex":0.000024001578,"about_ca_system_score_gemma":0.000092739276,"threshold_uncertainty_score":0.5383291},"labels":[],"label_agreement":null},{"id":"W2170505850","doi":"10.1016/j.ipm.2009.03.002","title":"A systematic analysis of performance measures for classification tasks","year":2009,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":6477,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal; Université de Montréal; Children's Hospital of Eastern Ontario","funders":"McGill University","keywords":"Confusion matrix; Confusion; Computer science; Artificial intelligence; Classifier (UML); Measure (data warehouse); Binary classification; Machine learning; Binary number; Natural language processing; Set (abstract data type); Class (philosophy); Data mining; Pattern recognition (psychology); Mathematics; Support vector machine; Arithmetic","score_opus":0.022728055734086046,"score_gpt":0.26836196947551794,"score_spread":0.2456339137414319,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170505850","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":[0.0010749451,0.00007709054,0.99305665,0.00074749714,0.000047195503,0.00062568375,0.0000015876009,0.00033926452,0.0040300526],"genre_scores_gemma":[0.9708304,0.00003119811,0.028647413,0.00018952908,0.0000030951571,0.00016749176,0.000023371713,0.0000017561432,0.00010575343],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986649,0.00001372859,0.0006673835,0.0001404787,0.00036647994,0.0001470203],"domain_scores_gemma":[0.9986134,0.000025674924,0.0006158617,0.0004597011,0.00026305835,0.000022257393],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051991106,0.00010597285,0.00022675842,0.00090179,0.00013826946,0.00027844697,0.00065440324,0.0000446479,0.0000015749173],"category_scores_gemma":[0.000052729116,0.000090862246,0.00008432471,0.0015562632,0.000023557961,0.0025187612,0.00004344318,0.000037036534,0.000009626126],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007650897,0.000044201155,0.000054119137,0.003947658,0.00017263638,4.809408e-8,0.00089751347,0.000870404,0.000065559354,0.20562507,0.00018920624,0.78812593],"study_design_scores_gemma":[0.00040452208,0.00009616658,0.02155467,0.00071101607,0.00052370474,6.181966e-7,0.00089642406,0.966887,0.0012403238,0.0038646988,0.0035759634,0.00024490085],"about_ca_topic_score_codex":4.345231e-7,"about_ca_topic_score_gemma":2.2441215e-7,"teacher_disagreement_score":0.9697555,"about_ca_system_score_codex":0.00006142181,"about_ca_system_score_gemma":0.000020691845,"threshold_uncertainty_score":0.37052548},"labels":[],"label_agreement":null},{"id":"W2171392923","doi":"10.1109/icdm.2007.26","title":"A Text Classification Framework with a Local Feature Ranking for Learning Social Networks","year":2007,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Classifier (UML); Artificial intelligence; Ranking (information retrieval); Feature extraction; Machine learning; Feature (linguistics); Pattern recognition (psychology); Data mining","score_opus":0.0181700594687985,"score_gpt":0.2756677619089408,"score_spread":0.2574977024401423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171392923","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":[0.00086483266,0.000058474234,0.99012065,0.0054748137,0.000098587276,0.00024651916,1.3807953e-7,0.0010442929,0.0020916904],"genre_scores_gemma":[0.79964435,0.0000042190563,0.19916685,0.00023892675,0.0001008727,0.000035807585,0.0000041015646,0.000009245794,0.0007956082],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99892783,0.000018512601,0.00015799109,0.00035058765,0.00020289593,0.00034220103],"domain_scores_gemma":[0.99920195,0.00026454317,0.00013488975,0.00025769352,0.00010296795,0.000037937323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043399204,0.00012753924,0.00012486849,0.000111676134,0.0004076006,0.00021549356,0.00053386216,0.00025016567,0.00000830672],"category_scores_gemma":[0.00005887708,0.000098878256,0.00005322794,0.00059160846,0.00010197261,0.0003174141,0.0000761157,0.0003687493,0.000008616778],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033024626,0.00001923623,0.00074689474,0.0000044711883,0.000010221675,8.673544e-7,0.0002633676,0.00017192682,0.00008130668,0.5908933,0.0013976253,0.40637773],"study_design_scores_gemma":[0.0019202838,0.0005666746,0.047268305,0.00009463401,0.000034566103,0.000022111935,0.0051281885,0.76005703,0.0027917996,0.05454963,0.12654296,0.0010238313],"about_ca_topic_score_codex":0.0000022675067,"about_ca_topic_score_gemma":0.000010526139,"teacher_disagreement_score":0.79877955,"about_ca_system_score_codex":0.00006535509,"about_ca_system_score_gemma":0.000030232855,"threshold_uncertainty_score":0.40321383},"labels":[],"label_agreement":null},{"id":"W21952029","doi":"10.12927/hcpap.2011.22560","title":"Learnability of multi-instance multi-label learning","year":2012,"lang":"en","type":"article","venue":"中国科学通报：英文版","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Learnability; Artificial intelligence; Computer science; Machine learning; Mathematics","score_opus":0.06931332554607451,"score_gpt":0.3147405592998234,"score_spread":0.24542723375374892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W21952029","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":[0.31040984,0.0012120072,0.68450844,0.00081202143,0.00046090747,0.00024080614,0.0000020086434,0.0010500966,0.0013039018],"genre_scores_gemma":[0.8578481,0.000043112035,0.14038791,0.00004194791,0.000021050382,0.000019163084,0.0000013879371,0.00000834193,0.0016289899],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99867004,0.00007960821,0.00031088686,0.00031392762,0.00024132058,0.00038421992],"domain_scores_gemma":[0.998792,0.00009321019,0.00021533787,0.0007159224,0.00010121062,0.00008231608],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048137983,0.00014570422,0.00019852881,0.000104754996,0.00013203626,0.00005064259,0.00086767826,0.00011125261,0.00003654143],"category_scores_gemma":[0.00039153374,0.00013304385,0.00006202515,0.00041726185,0.0001535158,0.00083175156,0.00032052543,0.0002690639,0.00015876254],"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":[0.000013015471,0.0013307055,0.27814236,0.000086785294,0.000036487898,0.0000018900989,0.0068693296,0.00007293567,0.028842552,0.106045134,0.0008583234,0.5777005],"study_design_scores_gemma":[0.0047055567,0.00040173947,0.49303085,0.0001116185,0.00003266973,0.000015868496,0.0050025596,0.22538309,0.16713586,0.0015599898,0.10111407,0.0015061374],"about_ca_topic_score_codex":0.00005851513,"about_ca_topic_score_gemma":0.000016625565,"teacher_disagreement_score":0.57619435,"about_ca_system_score_codex":0.000060378006,"about_ca_system_score_gemma":0.00003387895,"threshold_uncertainty_score":0.5425371},"labels":[],"label_agreement":null},{"id":"W2214660060","doi":"10.1609/aaai.v25i1.7895","title":"Adaptive Large Margin Training for Multilabel Classification","year":2011,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Margin (machine learning); Computer science; Exploit; Scalability; Categorization; Machine learning; Generalization; Classifier (UML); Artificial intelligence; Training set; Data mining; Pattern recognition (psychology); Mathematics","score_opus":0.3253993417235344,"score_gpt":0.3314708791762336,"score_spread":0.006071537452699172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2214660060","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":[0.03163686,0.000030703755,0.91700494,0.005141978,0.00066307705,0.0016325883,0.00002282687,0.0006484163,0.043218613],"genre_scores_gemma":[0.9638386,0.000015591793,0.03549369,0.00010526028,0.000023726638,0.00015926028,5.912457e-7,0.000010171914,0.00035313427],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99842376,0.000009967471,0.00045983255,0.0004780089,0.0002809375,0.00034751094],"domain_scores_gemma":[0.99849975,0.00008468141,0.00045224413,0.00034688268,0.0005634374,0.000053016687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048984465,0.00018494684,0.0002007543,0.0001438875,0.0002277559,0.00012118808,0.0020916497,0.00011396048,0.000049236263],"category_scores_gemma":[0.00039876872,0.00014111938,0.00011141961,0.00045101257,0.00021940314,0.0005372854,0.00023866768,0.00018929543,0.000056796584],"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":[0.00004673809,0.00011959026,0.000064586966,0.000010478405,0.0000085169495,4.443264e-8,0.0028291335,4.79537e-7,0.012678356,0.8625808,0.0001301402,0.121531166],"study_design_scores_gemma":[0.000054503125,0.00023750663,0.00092343125,0.00007830931,0.00001014865,9.724092e-7,0.004929273,0.096087605,0.43437472,0.46274015,0.00035298418,0.0002103964],"about_ca_topic_score_codex":0.000008440476,"about_ca_topic_score_gemma":0.0000045388847,"teacher_disagreement_score":0.93220174,"about_ca_system_score_codex":0.000040866347,"about_ca_system_score_gemma":0.0000748836,"threshold_uncertainty_score":0.5754681},"labels":[],"label_agreement":null},{"id":"W2237248385","doi":"10.1007/978-3-642-33460-3_48","title":"Learning and Inference in Probabilistic Classifier Chains with Beam Search","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Inference; Classifier (UML); Probabilistic logic; Artificial intelligence; Machine learning; Beam search; Binary classification; Flexibility (engineering); sort; Algorithm; Search algorithm; Mathematics; Support vector machine; Information retrieval","score_opus":0.02746902263249762,"score_gpt":0.2691181450713802,"score_spread":0.2416491224388826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2237248385","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":[0.0019925763,0.0005043189,0.9941248,0.0009589508,0.00019813665,0.00042970764,8.6669843e-7,0.00026930403,0.0015212889],"genre_scores_gemma":[0.9145082,0.00014778976,0.08450511,0.0001439227,0.00007223192,0.00002319809,0.0000022752836,0.00002044786,0.00057679496],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970107,0.00003565717,0.0003592398,0.0011895292,0.0007192636,0.00068558735],"domain_scores_gemma":[0.99808633,0.0006691149,0.00017477834,0.0007924796,0.00014645794,0.00013080859],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008231634,0.00039941937,0.00039566832,0.0009957973,0.00019580153,0.0005018114,0.0017451918,0.0003020753,0.000013792225],"category_scores_gemma":[0.00019832958,0.00032098513,0.000032251628,0.000770321,0.0012208021,0.00074540335,0.0012632272,0.0012728332,0.000018738005],"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":[0.000006108444,0.000034542678,0.005158886,0.000054932967,0.0000049337114,0.000024314955,0.0014261064,0.0071229776,0.00011469092,0.09906332,0.000001374551,0.8869878],"study_design_scores_gemma":[0.0012669783,0.0013698292,0.013360941,0.0015946608,0.000018173585,0.00011872459,0.00001065174,0.7664655,0.002609963,0.20663626,0.003929618,0.0026187121],"about_ca_topic_score_codex":0.000018795865,"about_ca_topic_score_gemma":0.00010652917,"teacher_disagreement_score":0.91251564,"about_ca_system_score_codex":0.00025104702,"about_ca_system_score_gemma":0.00039191707,"threshold_uncertainty_score":0.99992424},"labels":[],"label_agreement":null},{"id":"W2263083451","doi":"","title":"Bi-parameter space partition for cost-sensitive SVM","year":2015,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Support vector machine; Partition (number theory); Hyperparameter optimization; Regularization (linguistics); Algorithm; Invariant (physics); Parameter space; Piecewise; Grid; Model selection; Computer science; Mathematical optimization; Mathematics; Generalization; Artificial intelligence; Statistics; Combinatorics; Mathematical analysis; Geometry","score_opus":0.08266643554195872,"score_gpt":0.30656398751736963,"score_spread":0.2238975519754109,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2263083451","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":[0.003285284,0.000014462631,0.9757215,0.013532965,0.0002144562,0.00032170714,0.0000019029849,0.00068193354,0.0062258327],"genre_scores_gemma":[0.8335084,0.0000039775846,0.16258207,0.00046170093,0.00002604806,0.000114495495,0.0000049308246,0.0000042240827,0.003294217],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993893,0.000015138368,0.000100729616,0.00021720325,0.00011935344,0.00015830573],"domain_scores_gemma":[0.9993189,0.00010546042,0.000048520404,0.0003360243,0.00013285878,0.0000582272],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001583385,0.00007188682,0.00007824598,0.0000690258,0.000043288026,0.00012617165,0.00026668914,0.000051235096,0.000006142912],"category_scores_gemma":[0.00018415565,0.00005608768,0.000034920893,0.00017297234,0.00004180436,0.00043888658,0.000089389374,0.000038291404,0.00017654063],"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":[0.0000086207865,0.00003686606,0.00016883196,0.0000025492143,0.0000071103004,0.000001061611,0.00022365061,0.000011935098,0.0006979142,0.86170405,0.0744489,0.06268849],"study_design_scores_gemma":[0.0012232637,0.00040731498,0.0014184603,0.000010748226,0.0000105863755,0.000010270408,0.000932639,0.08660285,0.289278,0.26183876,0.3578247,0.00044239048],"about_ca_topic_score_codex":0.000007673701,"about_ca_topic_score_gemma":0.0000055346513,"teacher_disagreement_score":0.8302231,"about_ca_system_score_codex":0.00003859799,"about_ca_system_score_gemma":0.00003313333,"threshold_uncertainty_score":0.22871892},"labels":[],"label_agreement":null},{"id":"W2293405082","doi":"10.1007/s13748-015-0064-y","title":"Multi-label learning in classification of patients’ quasi-identifiers","year":2015,"lang":"en","type":"article","venue":"Progress in Artificial Intelligence","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Identifier; Artificial intelligence; Classifier (UML); Machine learning; Decision tree; Medical diagnosis; Multi-label classification; Demographics; Identification (biology); Class (philosophy); Data mining; Medicine","score_opus":0.13588836037341057,"score_gpt":0.3607449239924772,"score_spread":0.22485656361906664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2293405082","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":[0.45327538,0.0006386764,0.5434437,0.0010119323,0.00055133464,0.0005147125,0.000001337699,0.00035538845,0.00020755189],"genre_scores_gemma":[0.96239537,0.000024060475,0.037432514,0.000009547344,0.000007907934,0.00007841315,0.0000048177067,0.00000707185,0.00004031275],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981677,0.00011896325,0.0006801449,0.00041328938,0.000345445,0.0002744628],"domain_scores_gemma":[0.99896294,0.000077588586,0.00027788657,0.0004072725,0.00021649804,0.00005782372],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007307492,0.0001282883,0.0001835025,0.00045047916,0.000039449194,0.00010952102,0.00093860825,0.00011122709,0.0000047977874],"category_scores_gemma":[0.0005591785,0.00013037858,0.000028159164,0.0011905938,0.00024579858,0.00058214547,0.00021309765,0.00025934936,0.000059863614],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001542435,0.00066638156,0.23618607,0.0000104601195,0.0000019771417,0.0000017745339,0.0014326916,0.00007148598,0.00015388607,0.06638151,0.000011605093,0.69506675],"study_design_scores_gemma":[0.00028309113,0.00031637496,0.11370211,0.0000919194,0.0000032852706,5.142186e-7,0.0032089087,0.8099632,0.031605333,0.04010463,0.00032929573,0.0003913139],"about_ca_topic_score_codex":0.000031186144,"about_ca_topic_score_gemma":0.00009906879,"teacher_disagreement_score":0.80989176,"about_ca_system_score_codex":0.0001202348,"about_ca_system_score_gemma":0.000077904035,"threshold_uncertainty_score":0.5316684},"labels":[],"label_agreement":null},{"id":"W2340990333","doi":"10.1177/0165551515625030","title":"The impact of indexing approaches on Arabic text classification","year":2016,"lang":"en","type":"article","venue":"Journal of Information Science","topic":"Text and Document Classification Technologies","field":"Computer Science","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 New Brunswick","funders":"","keywords":"Computer science; Classifier (UML); Search engine indexing; Arabic; Artificial intelligence; Naive Bayes classifier; Natural language processing; Pattern recognition (psychology); Word (group theory); Mathematics; Support vector machine","score_opus":0.06173573844272501,"score_gpt":0.3028807703285067,"score_spread":0.24114503188578168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2340990333","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":[0.23169066,0.000029684215,0.7531817,0.006925679,0.0002985455,0.00013299535,0.0000011176625,0.000054388536,0.0076852315],"genre_scores_gemma":[0.99706924,0.000051865503,0.002817614,0.000019988543,0.000011528429,0.000002011898,5.2743214e-8,9.050483e-7,0.000026790505],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9985344,0.000022166689,0.00055585324,0.00006602269,0.0006744868,0.00014710796],"domain_scores_gemma":[0.99767846,0.00022501741,0.0011816316,0.00038408826,0.00048176118,0.000049047256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019257852,0.0000642427,0.00008728581,0.00047141,0.0002182553,0.00028089675,0.0016475361,0.00003108321,0.000002960765],"category_scores_gemma":[0.0009535845,0.000026705267,0.00007534585,0.0009720784,0.00038921906,0.0073588355,0.000086191205,0.00008971629,0.000025896235],"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":[0.000014843877,0.000019886951,0.0015031638,0.0000019540228,0.000005814164,7.022848e-8,0.00050777994,0.00016071872,0.007371659,0.33571935,0.0004556811,0.65423906],"study_design_scores_gemma":[0.0014284035,0.0014418596,0.7550424,0.00022798039,0.000006886482,0.00009764985,0.0023606922,0.052171323,0.13307543,0.046358168,0.0074164723,0.00037278366],"about_ca_topic_score_codex":0.0000010582371,"about_ca_topic_score_gemma":9.833091e-8,"teacher_disagreement_score":0.7653786,"about_ca_system_score_codex":0.00017069046,"about_ca_system_score_gemma":0.0003520497,"threshold_uncertainty_score":0.5334978},"labels":[],"label_agreement":null},{"id":"W2368869429","doi":"","title":"Forestry information text classification algorithm based on GMM model","year":2014,"lang":"en","type":"article","venue":"Zhongnan Linye Keji Daxue xuebao","topic":"Text and Document Classification Technologies","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":"Science North","funders":"","keywords":"Mixture model; Computer science; Artificial intelligence; Decision tree; Naive Bayes classifier; Gaussian; Classifier (UML); Pattern recognition (psychology); tf–idf; Statistical classification; Algorithm; Data mining; Machine learning; Support vector machine","score_opus":0.015718890916683177,"score_gpt":0.23350094354469378,"score_spread":0.2177820526280106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2368869429","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":[0.0018569815,0.000012124802,0.9773504,0.004608778,0.0003263124,0.00030664465,0.000011819962,0.0012556962,0.014271237],"genre_scores_gemma":[0.84958893,0.000010012105,0.14784893,0.0013625633,0.000084964224,0.00012358623,0.000090839,0.000017734585,0.00087244186],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979874,0.00006351261,0.00051118934,0.0004706878,0.00056083425,0.0004063866],"domain_scores_gemma":[0.99772865,0.00013915711,0.00032652396,0.0015182153,0.00016531146,0.00012217554],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00042136773,0.00027387217,0.00021989053,0.00043106897,0.00027283994,0.00050446304,0.0014247042,0.0002495673,0.000017849858],"category_scores_gemma":[0.00021848908,0.0002517917,0.000107896114,0.00062073383,0.00010321593,0.0020622415,0.00016255314,0.00030876446,0.0007655836],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009644291,0.00012143788,0.00030426445,0.000024829511,0.000007684991,6.258932e-7,0.00017632397,0.011897878,0.00025262547,0.32025412,0.008940896,0.65800965],"study_design_scores_gemma":[0.000516465,0.000111715846,0.0020539437,0.0000326076,0.0000057454795,0.0000014421339,0.000050375602,0.9494975,0.0021663492,0.015273286,0.0299946,0.000295923],"about_ca_topic_score_codex":0.000010530775,"about_ca_topic_score_gemma":0.0000021523324,"teacher_disagreement_score":0.93759966,"about_ca_system_score_codex":0.00011490614,"about_ca_system_score_gemma":0.00012331955,"threshold_uncertainty_score":0.99999344},"labels":[],"label_agreement":null},{"id":"W2389044726","doi":"","title":"A Method for Web News-Text Classification with Four-dimensional Vector Space Model","year":2010,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Vector space model; Support vector machine; Space (punctuation); Data mining; Information retrieval; Vector space; Hot spot (computer programming); Feature vector; Artificial intelligence; Pattern recognition (psychology); Mathematics","score_opus":0.024163686633332647,"score_gpt":0.28113672520326266,"score_spread":0.25697303856993003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2389044726","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022545045,0.000019361365,0.9798185,0.0152301295,0.000028685627,0.001263589,0.000015874235,0.0009135403,0.0004558165],"genre_scores_gemma":[0.06935015,0.000002752178,0.9271452,0.0005595131,0.00009885151,0.0022531967,0.000032812244,0.000024231136,0.000533312],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983204,0.000021895443,0.00030289244,0.00080626184,0.00021315386,0.0003354218],"domain_scores_gemma":[0.9981095,0.0002032643,0.00020974544,0.0010827744,0.00028105313,0.00011362623],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020271471,0.00023824951,0.00019979283,0.0002121329,0.00034678055,0.00027396032,0.0012974888,0.0001626038,0.000009024011],"category_scores_gemma":[0.0000026179719,0.00020762338,0.00009460142,0.00057322346,0.00009735788,0.00040541575,0.00021784891,0.00027057756,0.00009188193],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008464807,0.00013991132,0.00010881998,0.000013653475,0.000021870273,2.2200136e-7,0.000075775446,0.00031519128,0.2946589,0.5311606,0.01043297,0.16306363],"study_design_scores_gemma":[0.00055421516,0.000036634203,0.0010769853,0.000005812964,0.000016556347,0.000026519005,0.000012780588,0.6519203,0.011292961,0.018882468,0.31585565,0.0003190856],"about_ca_topic_score_codex":0.0000058729725,"about_ca_topic_score_gemma":0.000025856223,"teacher_disagreement_score":0.6516051,"about_ca_system_score_codex":0.000046435624,"about_ca_system_score_gemma":0.0002158522,"threshold_uncertainty_score":0.8466636},"labels":[],"label_agreement":null},{"id":"W2396310706","doi":"","title":"Recommender Systems from “Words of Few Mouths”","year":2012,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"University of Ottawa","funders":"","keywords":"Helpfulness; Phenomenon; Computer science; Probabilistic logic; Recommender system; Context (archaeology); Artificial intelligence; Machine learning; Epistemology; Psychology","score_opus":0.0388953647681684,"score_gpt":0.26215804294752787,"score_spread":0.22326267817935946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2396310706","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":[0.02337264,0.0009505779,0.9368151,0.0035998337,0.001137686,0.00013936445,0.0000032402309,0.0008570417,0.033124503],"genre_scores_gemma":[0.97856086,0.000017164655,0.01935193,0.00006859931,0.000031820888,0.000010916488,0.0000016981372,0.0000027806082,0.0019542144],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994159,0.000022452055,0.00016930219,0.00011833117,0.00012523883,0.0001487759],"domain_scores_gemma":[0.99928254,0.0000647524,0.00008160886,0.00050818484,0.000025354937,0.00003753127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001334587,0.000060747094,0.00009904106,0.000060904524,0.000025767835,0.00004667446,0.0005562469,0.000053395564,0.00007845196],"category_scores_gemma":[0.000018704042,0.00004670724,0.000027222923,0.00017632444,0.000022843471,0.00047437722,0.0001648744,0.00004676741,0.00011285644],"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":[0.0000013039299,0.000099352066,0.026995402,0.000008782329,0.000023781882,1.16481836e-7,0.00071659876,0.0000031341174,0.0011487087,0.8840539,0.031303246,0.055645667],"study_design_scores_gemma":[0.0017727532,0.00021728042,0.1437412,0.00011136497,0.000044873275,0.00000831259,0.008454937,0.02796507,0.17070946,0.0550057,0.5904179,0.0015511053],"about_ca_topic_score_codex":0.0001398531,"about_ca_topic_score_gemma":0.0000015240029,"teacher_disagreement_score":0.9551882,"about_ca_system_score_codex":0.000017265007,"about_ca_system_score_gemma":0.000009371993,"threshold_uncertainty_score":0.1904666},"labels":[],"label_agreement":null},{"id":"W2397694745","doi":"10.63317/5agbhnncc4sh","title":"Experiments in Topic Detection","year":2002,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"University of Lethbridge","funders":"","keywords":"WordNet; Computer science; Thesaurus; Information retrieval; Natural language processing; Precision and recall; Implementation; Artificial intelligence; Recall; Domain (mathematical analysis); Linguistics; Mathematics","score_opus":0.04286456784919886,"score_gpt":0.2522528984422731,"score_spread":0.20938833059307424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2397694745","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":[0.18406874,0.00024076493,0.7285524,0.0038142977,0.00035923303,0.00014709703,3.946917e-8,0.0012708866,0.08154654],"genre_scores_gemma":[0.9926299,0.000011221553,0.0047074757,0.000079545265,0.0000039526417,0.000013904134,2.9154165e-8,8.093001e-7,0.0025531764],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996991,0.0000058677474,0.00006415413,0.0001058678,0.000054891116,0.00007009158],"domain_scores_gemma":[0.999771,0.0000064591795,0.000012245563,0.00019647664,0.00000479971,0.0000090207595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000022395046,0.000028645765,0.000027758892,0.00007378581,0.000018349654,0.000037503934,0.0002299404,0.000023144234,0.000124227],"category_scores_gemma":[0.000007721216,0.000024834046,0.000008648297,0.00018309445,0.000007717242,0.00024597897,0.00005018218,0.000029082166,0.00016882618],"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":[2.5927105e-7,0.00006282261,0.0020325566,0.0000010918391,0.0000011921404,0.000002617728,0.00032033643,0.0000017399208,0.008656616,0.11955314,0.00070425804,0.8686634],"study_design_scores_gemma":[0.0006893719,0.00010755492,0.02654756,0.0000061504293,6.15495e-7,0.000006664553,0.00028312163,0.093051225,0.81227934,0.020972636,0.045766223,0.00028951178],"about_ca_topic_score_codex":0.000008626967,"about_ca_topic_score_gemma":0.000007032916,"teacher_disagreement_score":0.8683739,"about_ca_system_score_codex":0.000020737822,"about_ca_system_score_gemma":8.3683045e-7,"threshold_uncertainty_score":0.21699753},"labels":[],"label_agreement":null},{"id":"W2403597675","doi":"","title":"How Well Do We Know Bernoulli","year":2012,"lang":"en","type":"book-chapter","venue":"Research Padua  Archive (University of Padua)","topic":"Text and Document Classification Technologies","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":"Université de Montréal","funders":"","keywords":"Computer science; Smoothing; Artificial intelligence; Machine learning; Bernoulli's principle; Estimator; Naive Bayes classifier; Bayes' theorem; Bayesian probability; Bernoulli distribution; Visualization; Pattern recognition (psychology); Data mining; Mathematics; Statistics; Random variable; Support vector machine; Computer vision; Engineering","score_opus":0.06880657876078805,"score_gpt":0.2736206561234766,"score_spread":0.20481407736268853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2403597675","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000016749847,0.008101421,0.4664566,0.03508834,0.00023475006,0.0009634513,0.0001674354,0.0006120482,0.4883592],"genre_scores_gemma":[0.0048921905,0.04542396,0.062488534,0.000016114118,0.00014985747,0.0000028025026,0.00005998326,0.000054559237,0.886912],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99635524,0.0001950958,0.00019207918,0.00089315313,0.0015268752,0.0008375595],"domain_scores_gemma":[0.99644667,0.00062966737,0.00033041008,0.0018315694,0.00042898397,0.00033271423],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008138443,0.00036512484,0.0005174213,0.0014393285,0.0005632205,0.00021219095,0.0039549093,0.00039834532,0.00047193986],"category_scores_gemma":[0.00007339403,0.00041479786,0.00033764882,0.00029161366,0.001519402,0.0008745494,0.0030880657,0.0014309597,0.0012692185],"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":[0.00001839146,0.000056727284,0.000028891647,0.000108051885,0.00009119507,0.000051976545,0.0006172148,4.5570465e-7,0.0011624312,0.67412186,0.047706723,0.27603608],"study_design_scores_gemma":[0.00026586078,0.00016618056,0.00012353856,0.00027171313,0.000017292665,0.0000057137513,0.0005356289,0.00041513535,0.00015078881,0.21089064,0.7868259,0.0003316432],"about_ca_topic_score_codex":0.000053213767,"about_ca_topic_score_gemma":0.00006756915,"teacher_disagreement_score":0.7391192,"about_ca_system_score_codex":0.00018123015,"about_ca_system_score_gemma":0.0002739659,"threshold_uncertainty_score":0.99983037},"labels":[],"label_agreement":null},{"id":"W2513020503","doi":"","title":"Combining relevance feedback and genetic algorithms in an internet information filtering engine","year":2000,"lang":"en","type":"article","venue":"RIAO Conference","topic":"Text and Document Classification Technologies","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":"Université du Québec à Montréal","funders":"","keywords":"Relevance (law); Computer science; The Internet; Humanities; Algorithm; Philosophy; Political science; World Wide Web","score_opus":0.021462505151121615,"score_gpt":0.24084826020443992,"score_spread":0.2193857550533183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2513020503","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":[0.6937973,0.00006485199,0.30394506,0.000518075,0.000083859435,0.00012005107,0.0000013023322,0.0003120858,0.0011574179],"genre_scores_gemma":[0.955546,0.00011779054,0.04408353,0.00007136103,0.0000066363787,0.000016786462,0.000004018419,0.0000024941905,0.00015136597],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993206,0.000020815116,0.0002129506,0.00018614845,0.00010104539,0.00015843556],"domain_scores_gemma":[0.99954444,0.000031315805,0.0000529504,0.00029976663,0.000033180066,0.000038324295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000746407,0.00009150255,0.00009799328,0.00010035418,0.000030674688,0.0003035888,0.0004721034,0.000050717736,0.00007360235],"category_scores_gemma":[0.000024921472,0.00009127928,0.000008607777,0.00017720286,0.00004277823,0.0016103245,0.00009777455,0.00010741148,0.00006133289],"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":[0.0000032373857,0.00001167032,0.0008659108,0.000007368654,0.0000013176639,0.00000209993,0.0009965649,0.00007750909,0.00034987368,0.011177023,0.000028540382,0.98647887],"study_design_scores_gemma":[0.00081964204,0.00020556293,0.096143216,0.00010774157,0.0000022130732,0.000022967399,0.00017706725,0.876957,0.0066613248,0.009018117,0.009515095,0.000370053],"about_ca_topic_score_codex":0.00003142575,"about_ca_topic_score_gemma":0.000013805662,"teacher_disagreement_score":0.98610884,"about_ca_system_score_codex":0.000020291156,"about_ca_system_score_gemma":0.00002049704,"threshold_uncertainty_score":0.37222612},"labels":[],"label_agreement":null},{"id":"W2517886881","doi":"10.1109/sai.2016.7555963","title":"VENCE: A new machine learning method enhanced by ontological knowledge to extract summaries","year":2016,"lang":"en","type":"article","venue":"2016 SAI Computing Conference (SAI)","topic":"Text and Document Classification Technologies","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":"Université Laval","funders":"","keywords":"Computer science; Ontology; Set (abstract data type); Jaccard index; Process (computing); Information retrieval; Function (biology); Domain (mathematical analysis); Artificial intelligence; Quality (philosophy); Space (punctuation); Natural language processing; Machine learning; Data mining; Pattern recognition (psychology); Mathematics","score_opus":0.0349061431540296,"score_gpt":0.31863610081922245,"score_spread":0.2837299576651928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2517886881","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":[0.0050639645,0.00046491742,0.9796009,0.006986099,0.00037959387,0.00026921913,0.0000056050503,0.0015358658,0.005693817],"genre_scores_gemma":[0.82416135,0.00009157649,0.15373428,0.00020415493,0.000106168314,0.000017867531,0.000006766891,0.000018559136,0.021659251],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99713266,0.0002820966,0.00051948725,0.0010072194,0.00034225642,0.00071626494],"domain_scores_gemma":[0.99739015,0.0009886299,0.00029865178,0.00081736187,0.0002284917,0.00027670272],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007337276,0.00037137372,0.00046117304,0.00020927141,0.0003367544,0.0004738106,0.002095122,0.00022417567,0.00028219298],"category_scores_gemma":[0.00097421615,0.00025537118,0.00010562041,0.0005275266,0.00014812138,0.00053254166,0.0009954788,0.0003781575,0.0011947709],"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":[0.000015243536,0.00007037018,0.0005350466,0.000008049287,0.000017231541,0.0000024594185,0.00062619895,0.000008359497,0.034070324,0.065543346,0.018612837,0.88049054],"study_design_scores_gemma":[0.001701973,0.0008245721,0.0035425548,0.0006459269,0.000024171057,0.000020606767,0.00019363461,0.033745643,0.10595876,0.017814703,0.83400196,0.0015255011],"about_ca_topic_score_codex":0.000109585904,"about_ca_topic_score_gemma":0.000027255033,"teacher_disagreement_score":0.878965,"about_ca_system_score_codex":0.00013181879,"about_ca_system_score_gemma":0.00031364718,"threshold_uncertainty_score":0.99998987},"labels":[],"label_agreement":null},{"id":"W2552791835","doi":"10.5555/3192424.3192606","title":"Spectral graph-based semi-supervised learning for imbalanced classes","year":2016,"lang":"en","type":"article","venue":"Advances in Social Networks Analysis and Mining","topic":"Text and Document Classification Technologies","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":"Queen's University","funders":"","keywords":"Embedding; Graph; Computer science; Semi-supervised learning; Graph embedding; Theoretical computer science; Pattern recognition (psychology); Artificial intelligence; Mathematics; Algorithm; Combinatorics","score_opus":0.012703246983670374,"score_gpt":0.28063595725781043,"score_spread":0.26793271027414006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2552791835","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":[0.045029126,0.0012692661,0.9522613,0.0008855609,0.00007372158,0.00008508557,8.807104e-7,0.00016970419,0.00022534837],"genre_scores_gemma":[0.9789628,0.0009847336,0.01973901,0.00007348719,0.00008647701,0.000051850664,0.000004899662,0.0000060966527,0.00009064042],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998899,0.00004550952,0.00025016067,0.0003807726,0.00011512472,0.00030947663],"domain_scores_gemma":[0.9992455,0.00037090186,0.00015844603,0.00014958828,0.00004367802,0.000031880525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024501342,0.00012716689,0.00028782757,0.00024832555,0.00026857218,0.000095920856,0.0003031455,0.000086267806,0.000006077456],"category_scores_gemma":[0.000060916707,0.00009564603,0.00014525485,0.001215126,0.00010874066,0.0005198217,0.00005874509,0.00008028182,3.2409682e-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":[0.0000220608,0.000029856328,0.2313069,0.000009356226,0.00010549901,0.000001673445,0.00025302087,0.018374909,0.0003645512,0.02877938,0.00009056059,0.72066224],"study_design_scores_gemma":[0.0018570161,0.00019481452,0.054993555,0.00008489474,0.00020325855,4.4984867e-7,0.0011169042,0.9097817,0.0007865066,0.016903669,0.013366818,0.00071041594],"about_ca_topic_score_codex":0.0000029777711,"about_ca_topic_score_gemma":0.000076557066,"teacher_disagreement_score":0.9339337,"about_ca_system_score_codex":0.000030474228,"about_ca_system_score_gemma":0.000015629848,"threshold_uncertainty_score":0.3900332},"labels":[],"label_agreement":null},{"id":"W2556044468","doi":"10.5430/air.v6n1p59","title":"Re-ranking Google search returned web documents using document classification scores","year":2016,"lang":"en","type":"article","venue":"Artificial Intelligence Research","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Information retrieval; Ranking (information retrieval); Computer science; Search engine; World Wide Web; Web page; Learning to rank; Web search engine; Web search query","score_opus":0.3126960264625327,"score_gpt":0.44704871815383274,"score_spread":0.13435269169130004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2556044468","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":[0.23840979,0.00026310538,0.7323831,0.02298359,0.0005802318,0.001045105,0.000005441401,0.0008650981,0.0034645875],"genre_scores_gemma":[0.98747194,0.00037949483,0.011059512,0.000047272883,0.00013025715,0.00009237804,0.000002420863,0.000024143734,0.00079255964],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9945218,0.0005668369,0.0007738472,0.0010821198,0.0018705246,0.0011848722],"domain_scores_gemma":[0.9963775,0.00087139383,0.00015501035,0.0016608507,0.0007222873,0.0002129524],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0039675618,0.0002481642,0.00024404693,0.00095097185,0.0007939266,0.0009866984,0.0027447056,0.00020968207,0.00036421217],"category_scores_gemma":[0.0008158137,0.00018300887,0.0001081161,0.0022504346,0.00069593184,0.0018152691,0.0010313701,0.00047735052,0.0014734515],"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":[0.00003252206,0.00009414719,0.0010392498,0.000012540735,0.000017224873,0.000009461096,0.00041319884,0.000019682047,0.17615137,0.43045247,0.0004017985,0.39135635],"study_design_scores_gemma":[0.00010742126,0.00023878965,0.00050523906,0.00020483536,0.0000054809366,0.0000053199183,0.0021961932,0.03983342,0.60463727,0.34877586,0.003050937,0.00043926004],"about_ca_topic_score_codex":0.00018472037,"about_ca_topic_score_gemma":0.00009534473,"teacher_disagreement_score":0.7490622,"about_ca_system_score_codex":0.00063615135,"about_ca_system_score_gemma":0.000402082,"threshold_uncertainty_score":0.999304},"labels":[],"label_agreement":null},{"id":"W2560620367","doi":"10.29173/cais341","title":"A Comparative Study on Feature Selection of Text Categorization for Hidden Markov Models","year":2013,"lang":"fr","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Selection (genetic algorithm); Feature selection; Categorization; Context (archaeology); Artificial intelligence; Computer science; Humanities; Natural language processing; Geography; Philosophy","score_opus":0.05343692366918243,"score_gpt":0.2833853176220592,"score_spread":0.22994839395287678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560620367","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":[0.9756039,0.0002581701,0.0055762804,0.01169473,0.0003502847,0.0025713653,0.000105760795,0.000107906475,0.003731604],"genre_scores_gemma":[0.9921963,0.000060400293,0.0037117938,0.000057161786,0.000056118337,0.00022968453,0.000004449443,0.000017448601,0.0036666293],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9978974,0.00004747089,0.0006270619,0.0005011224,0.00053418666,0.00039278154],"domain_scores_gemma":[0.95115244,0.00021108956,0.0013840368,0.0002782354,0.04689792,0.00007628708],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00044706065,0.00034180464,0.000651596,0.0002790145,0.00017326172,0.0021215861,0.0021158815,0.00027756748,0.000021562757],"category_scores_gemma":[0.002992935,0.0002753196,0.00017458125,0.00092938857,0.00045874895,0.013337875,0.0004872727,0.00032009886,0.0000044562757],"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":[0.0004520519,0.0026745412,0.060239386,0.0010793604,0.0005618554,2.9474256e-7,0.18466452,0.00010308968,0.04745297,0.5816901,0.04308281,0.07799906],"study_design_scores_gemma":[0.0035211532,0.008070682,0.25542137,0.0012048521,0.00047253052,0.000024473922,0.057606567,0.12765613,0.34557834,0.18631394,0.012804473,0.0013255058],"about_ca_topic_score_codex":0.00029524683,"about_ca_topic_score_gemma":0.000016032138,"teacher_disagreement_score":0.39537612,"about_ca_system_score_codex":0.00010182938,"about_ca_system_score_gemma":0.0002789598,"threshold_uncertainty_score":0.9999699},"labels":[],"label_agreement":null},{"id":"W2565143233","doi":"10.82308/24058","title":"Text classification using a hidden Markov model","year":2005,"lang":"en","type":"article","venue":"Open MIND","topic":"Text and Document Classification Technologies","field":"Computer Science","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":"McGill University","funders":"","keywords":"Hidden Markov model; Computer science; Artificial intelligence; Categorization; Natural language processing; Naive Bayes classifier; Test set; Machine learning; Bayesian probability; Pattern recognition (psychology); Data mining; Support vector machine","score_opus":0.1071301472310728,"score_gpt":0.3418787696192839,"score_spread":0.2347486223882111,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2565143233","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":[0.13359994,0.00007454054,0.79105294,0.010284615,0.000090836606,0.0004633709,0.0000039346696,0.000059901395,0.06436995],"genre_scores_gemma":[0.5110346,0.0000049788277,0.48580775,0.0000560757,0.000015547961,0.000010352167,0.0000018141442,0.0000036429356,0.0030652524],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990749,0.00001994044,0.00020083996,0.00036780816,0.00015980093,0.00017673774],"domain_scores_gemma":[0.9990765,0.000020724823,0.0001152144,0.00069892564,0.000045139735,0.00004348048],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020818152,0.0000949721,0.00009847583,0.00009685952,0.00012731261,0.00056799105,0.001769485,0.00007293355,0.00022399503],"category_scores_gemma":[0.000025045798,0.0000886282,0.000028129725,0.00027431236,0.000042468368,0.0014198953,0.00052407826,0.00007121642,0.00051850756],"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":[0.0000023037553,0.000038541344,0.00007064388,6.141341e-7,0.0000035987061,4.4018012e-7,0.00021033699,0.00010124042,0.00832504,0.007073171,0.0010709184,0.98310316],"study_design_scores_gemma":[0.00019042275,0.000011484322,0.000344016,0.000007776598,0.0000043080386,0.0000045928823,0.000101108315,0.9517657,0.0113096,0.0016811254,0.034426715,0.00015314654],"about_ca_topic_score_codex":0.000005484699,"about_ca_topic_score_gemma":0.000010600624,"teacher_disagreement_score":0.98295003,"about_ca_system_score_codex":0.00008764882,"about_ca_system_score_gemma":0.000100706864,"threshold_uncertainty_score":0.66645384},"labels":[],"label_agreement":null},{"id":"W2577161492","doi":"","title":"Semisupervised text classification using unsupervised topic information","year":2016,"lang":"en","type":"article","venue":"The Florida AI Research Society","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Artificial intelligence; Natural language processing; Information retrieval","score_opus":0.1233472750172762,"score_gpt":0.36867560219509704,"score_spread":0.24532832717782083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2577161492","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":[0.20095344,0.00016399969,0.68012005,0.11395118,0.00052341114,0.0009414196,0.000009024288,0.0010864395,0.0022510334],"genre_scores_gemma":[0.9931762,0.00028248745,0.004943017,0.0005559628,0.0001410271,0.0000983142,0.000004254267,0.000008350406,0.00079039286],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978576,0.0001922221,0.00029715366,0.00027935457,0.0008777095,0.0004960042],"domain_scores_gemma":[0.99774307,0.00038889464,0.00007438052,0.0012393437,0.00047725078,0.00007707234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017469245,0.00012947744,0.00011428597,0.000108109285,0.0007154886,0.0004550224,0.0019161392,0.00013786522,0.000067883644],"category_scores_gemma":[0.00026828412,0.000071094706,0.00012171141,0.0010836232,0.00034958887,0.0024279042,0.0005443841,0.0003363287,0.00034462192],"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":[0.000016889462,0.000058379996,0.0019336795,0.00006594394,0.00006044456,7.473004e-7,0.0054746876,0.000009319674,0.12366617,0.34132314,0.058349922,0.4690407],"study_design_scores_gemma":[0.0037837299,0.0003118094,0.05171332,0.0002565821,0.00002533934,0.000021499494,0.009061937,0.3133073,0.107410304,0.11256441,0.40034294,0.0012008491],"about_ca_topic_score_codex":0.000031937216,"about_ca_topic_score_gemma":0.0000012198959,"teacher_disagreement_score":0.79222274,"about_ca_system_score_codex":0.0002992993,"about_ca_system_score_gemma":0.00021806976,"threshold_uncertainty_score":0.5503032},"labels":[],"label_agreement":null},{"id":"W2578515274","doi":"10.3233/978-1-61499-672-9-1336","title":"Improved Multi-Label Classification Using Inter-Dependence Structure via a Generative Mixture Model","year":2016,"lang":"en","type":"book-chapter","venue":"Frontiers in artificial intelligence and applications","topic":"Text and Document Classification Technologies","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":"Queen's University","funders":"","keywords":"Generative grammar; Generative model; Artificial intelligence; Pattern recognition (psychology); Materials science; Computer science; Biological system; Biology","score_opus":0.08005437587493122,"score_gpt":0.30664518401851915,"score_spread":0.22659080814358792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2578515274","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000016944412,0.0006958947,0.9949727,0.0009708772,0.00022464347,0.0009116809,0.000067453184,0.00022651294,0.001913299],"genre_scores_gemma":[0.07254308,0.0012864613,0.89593023,0.00034108452,0.00027891117,0.0004945112,0.0000631419,0.000089089044,0.028973503],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99766356,0.0000226135,0.0007020198,0.001064728,0.0002196738,0.0003274078],"domain_scores_gemma":[0.9982309,0.00004311435,0.00046369553,0.0009659917,0.00019696688,0.000099347155],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001382425,0.00042603334,0.00038825185,0.00046659456,0.00027453358,0.00023154984,0.0011644578,0.00058850774,0.000016028049],"category_scores_gemma":[0.000022710656,0.00037979634,0.00007622826,0.00021119989,0.00040725907,0.0004998809,0.00029968037,0.00051991985,0.000020164562],"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":[0.000005644301,0.000033485347,0.000010484974,0.0000120700115,0.000019067205,6.821823e-7,0.00014428567,0.000057381356,0.009306176,0.52100015,0.000151256,0.4692593],"study_design_scores_gemma":[0.000032422944,0.000013362706,0.0000015034225,0.000043268366,0.000013732168,0.0000026548614,0.00006130505,0.56588393,0.0034368543,0.42901736,0.0011967149,0.0002968623],"about_ca_topic_score_codex":0.0000056841545,"about_ca_topic_score_gemma":0.0000389572,"teacher_disagreement_score":0.56582654,"about_ca_system_score_codex":0.00023274383,"about_ca_system_score_gemma":0.0001439383,"threshold_uncertainty_score":0.9998654},"labels":[],"label_agreement":null},{"id":"W2587209668","doi":"10.29173/cais195","title":"Boosting for Text Classification with Subject Headings","year":2013,"lang":"fr","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Classifier (UML); Subject (documents); Boosting (machine learning); Information retrieval; Natural language processing; Artificial intelligence; Library science","score_opus":0.04504300598340083,"score_gpt":0.26069526964263856,"score_spread":0.21565226365923773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2587209668","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":[0.9170225,0.0008418113,0.00827674,0.060532983,0.00045454787,0.0019120051,0.00010297936,0.00027219148,0.010584228],"genre_scores_gemma":[0.9821671,0.00014740146,0.011356999,0.00022177097,0.000096385855,0.00025258254,0.000004020299,0.000033101987,0.005720611],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9972946,0.000026380805,0.0007781895,0.0006480128,0.0005510685,0.00070176355],"domain_scores_gemma":[0.9434701,0.00038621956,0.0016555389,0.00045107672,0.05389145,0.00014560932],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0007215162,0.00041004652,0.0005718088,0.00025285603,0.0003000852,0.006178169,0.0033032226,0.0003158668,0.000040513536],"category_scores_gemma":[0.013001584,0.00031448397,0.00020600445,0.00093073014,0.0011147893,0.020934444,0.0006686053,0.00036866203,0.000017441434],"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":[0.00012669574,0.00034235918,0.09459799,0.0012004946,0.00017168833,4.3496306e-7,0.028940944,0.0000047400495,0.061971206,0.63834906,0.022636712,0.15165767],"study_design_scores_gemma":[0.002340815,0.0024900173,0.3430563,0.0027192226,0.00033170058,0.00011968774,0.01615682,0.027427107,0.25748336,0.08627342,0.26002532,0.0015762429],"about_ca_topic_score_codex":0.000402798,"about_ca_topic_score_gemma":0.00001363201,"teacher_disagreement_score":0.5520756,"about_ca_system_score_codex":0.00012608913,"about_ca_system_score_gemma":0.00044311088,"threshold_uncertainty_score":0.99993074},"labels":[],"label_agreement":null},{"id":"W2587810790","doi":"10.7717/peerj-cs.242","title":"Nearest labelset using double distances for multi-label classification","year":2019,"lang":"en","type":"preprint","venue":"PeerJ Computer Science","topic":"Text and Document Classification Technologies","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 Waterloo; Western University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Multi-label classification; Pattern recognition (psychology); Benchmark (surveying); Hamming code; Feature (linguistics); Mathematics; Function (biology); Hamming distance; Computer science; Artificial intelligence; Measure (data warehouse); k-nearest neighbors algorithm; Binomial (polynomial); Space (punctuation); Algorithm; Statistics; Data mining","score_opus":0.2164557323099007,"score_gpt":0.38397517742362325,"score_spread":0.16751944511372255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2587810790","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01396388,0.00028102592,0.9768309,0.0020476545,0.0044746273,0.0012634833,0.000035788187,0.0009868505,0.000115800416],"genre_scores_gemma":[0.26372412,0.0000274784,0.735468,0.00015237916,0.00013466482,0.00013804976,0.000027312659,0.000018428098,0.0003095891],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957166,0.000036703033,0.00057909713,0.0020099815,0.00092083315,0.0007367893],"domain_scores_gemma":[0.9957919,0.00011711453,0.00064129557,0.0025504942,0.0007514553,0.00014775652],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.001096656,0.00042925202,0.0004500292,0.0005447112,0.000617172,0.0025100384,0.0069308174,0.00026849145,0.0000030467854],"category_scores_gemma":[0.00006588694,0.000403256,0.00013204834,0.0011270914,0.00066314323,0.001542376,0.003981871,0.00043984962,0.000056639936],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047249778,0.0008002339,0.0035809206,0.0006183709,0.0000716813,0.000005678912,0.0017558805,0.012794527,0.012276352,0.479536,0.0048685395,0.48364457],"study_design_scores_gemma":[0.00079275056,0.00006331972,0.002180388,0.00009625705,0.000011538436,0.000004160735,0.000022269349,0.98622286,0.0026018023,0.0045660967,0.0029140152,0.00052452984],"about_ca_topic_score_codex":0.00004180956,"about_ca_topic_score_gemma":0.000010625946,"teacher_disagreement_score":0.97342837,"about_ca_system_score_codex":0.00038594112,"about_ca_system_score_gemma":0.000948567,"threshold_uncertainty_score":0.9998419},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W2590184703","doi":"10.29173/cais539","title":"A Text Categorization Model Based on Hidden Markov Models","year":2013,"lang":"en","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Hidden Markov model; Categorization; Computer science; Artificial intelligence; Speech recognition; Scheme (mathematics); Natural language processing; Pattern recognition (psychology); Markov model; Markov chain; Machine learning; Mathematics","score_opus":0.024126278370148094,"score_gpt":0.23203053909746876,"score_spread":0.20790426072732066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2590184703","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":[0.8053731,0.00006289099,0.13121389,0.022413267,0.00019554514,0.0012387137,0.00005380396,0.0005949123,0.0388539],"genre_scores_gemma":[0.9864096,0.00002571897,0.012386992,0.0003172596,0.000017105343,0.00009695061,0.000002557689,0.00001472998,0.00072907726],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99830234,0.000014851664,0.000426757,0.00039685657,0.0005260139,0.0003331549],"domain_scores_gemma":[0.9799871,0.00008776541,0.00060241483,0.00041804582,0.018821217,0.000083475024],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00028664301,0.00023887517,0.0003029132,0.00025323246,0.0001199579,0.002566639,0.0031377499,0.00016653257,0.00001762498],"category_scores_gemma":[0.0029545368,0.00017912872,0.00011893524,0.0005668741,0.00023785373,0.013202966,0.0005661661,0.00020945242,0.000010223816],"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":[0.00006869939,0.0004018703,0.011499071,0.0002443023,0.000055960238,3.9543534e-7,0.012282682,0.0013744085,0.030859075,0.8229778,0.014039518,0.10619621],"study_design_scores_gemma":[0.0003619605,0.00016915298,0.0060928524,0.000096781085,0.000016309305,0.000002234497,0.00044292805,0.8303863,0.03647765,0.12492902,0.00076490635,0.00025989566],"about_ca_topic_score_codex":0.00008382261,"about_ca_topic_score_gemma":0.0000014776953,"teacher_disagreement_score":0.8290119,"about_ca_system_score_codex":0.00006131256,"about_ca_system_score_gemma":0.0002229669,"threshold_uncertainty_score":0.9984688},"labels":[],"label_agreement":null},{"id":"W2605893001","doi":"10.1007/978-3-319-57351-9_24","title":"Design and Implementation of a Smart Quotation System","year":2017,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Context (archaeology); Process (computing); Order (exchange); Software engineering; Software; Operations research; Industrial engineering; Database; Operating system","score_opus":0.02868893627742745,"score_gpt":0.2842081918926632,"score_spread":0.25551925561523575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2605893001","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":[0.00012431749,0.00020229741,0.997764,0.0004582804,0.0004279034,0.00042020078,0.000001534168,0.00016375951,0.00043771634],"genre_scores_gemma":[0.6105397,0.000040667084,0.38922405,0.00004819287,0.000034426517,0.000014310165,0.0000016191178,0.000009581476,0.000087457905],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998253,0.00002208772,0.00036252956,0.0006850779,0.00045477977,0.00022255615],"domain_scores_gemma":[0.9980917,0.0002014473,0.00053350365,0.00097033434,0.00015901511,0.000043981887],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067324535,0.00021828189,0.00027833425,0.00054625474,0.00020510306,0.00037924253,0.0016309469,0.00015431909,0.000003407431],"category_scores_gemma":[0.000030607967,0.00019826321,0.000036251702,0.000120958684,0.00045065553,0.000636322,0.000560636,0.0001853654,0.0000060232437],"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":[0.000002615152,0.0000045673396,0.000099187535,0.000060539744,0.0000059437853,0.0000056114127,0.0005463118,0.00055379915,0.0004071914,0.11302467,0.000009279879,0.8852803],"study_design_scores_gemma":[0.0009822482,0.00075554964,0.0024690656,0.00093089003,0.000029219838,0.00009156005,0.00000866518,0.61901635,0.053016,0.32076487,0.00084504765,0.0010905067],"about_ca_topic_score_codex":0.00002942333,"about_ca_topic_score_gemma":0.000029285016,"teacher_disagreement_score":0.8841898,"about_ca_system_score_codex":0.00013773881,"about_ca_system_score_gemma":0.0002488719,"threshold_uncertainty_score":0.80849385},"labels":[],"label_agreement":null},{"id":"W2609579487","doi":"10.1007/s11280-017-0460-2","title":"Collaborative text categorization via exploiting sparse coefficients","year":2017,"lang":"en","type":"article","venue":"World Wide Web","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Sparse approximation; Pattern recognition (psychology); Categorization; Artificial intelligence; Classifier (UML); Sparse matrix; Representation (politics); Information retrieval; Data mining","score_opus":0.019044466667129008,"score_gpt":0.2666869600097453,"score_spread":0.2476424933426163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2609579487","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":[0.02720687,0.00012912905,0.91645813,0.013269135,0.0012456408,0.00045927882,0.000005538569,0.0013426712,0.03988361],"genre_scores_gemma":[0.98786503,0.000015826874,0.007503513,0.00018753536,0.000038612692,0.00003819998,0.000005017593,0.000009036043,0.004337231],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.998906,0.00003104236,0.00021255169,0.00036666376,0.00024049846,0.00024325252],"domain_scores_gemma":[0.99830776,0.00007460759,0.00032295336,0.0010938606,0.00014618541,0.000054601158],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018038097,0.00013101351,0.00013315557,0.00019458505,0.0007185917,0.0007188632,0.0014099866,0.00004425931,0.000032990723],"category_scores_gemma":[0.00027135122,0.00012419962,0.000030827156,0.00047149355,0.00013132251,0.0010194043,0.0003947787,0.00010755054,0.0003174217],"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":[0.000012519431,0.0001837013,0.042144645,0.00001737512,0.000033146764,0.000023587714,0.001110046,0.00020776545,0.011683137,0.651364,0.02749866,0.26572135],"study_design_scores_gemma":[0.0024930586,0.00017406992,0.094983295,0.00016163738,0.000031888914,0.000007934374,0.00092520413,0.15702607,0.13421296,0.05507298,0.5532948,0.0016161042],"about_ca_topic_score_codex":0.00001744491,"about_ca_topic_score_gemma":0.000107687454,"teacher_disagreement_score":0.96065813,"about_ca_system_score_codex":0.00006153612,"about_ca_system_score_gemma":0.0000763657,"threshold_uncertainty_score":0.6932015},"labels":[],"label_agreement":null},{"id":"W2617799745","doi":"10.29173/cais355","title":"Les méthodes de classification non supervisées appliquées aux textes : mesure de la performance des résultats de clustering de documents","year":2013,"lang":"fr","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Mathematics; Philosophy","score_opus":0.05746759106833514,"score_gpt":0.30748540977171873,"score_spread":0.2500178187033836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2617799745","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":[0.9731208,0.00092900964,0.01517686,0.0054199146,0.000106480264,0.00055865507,0.00003303208,0.00020814328,0.0044470793],"genre_scores_gemma":[0.96418655,0.001980167,0.031737205,0.00015004828,0.00008241877,0.00021978901,0.0000028918023,0.000034309865,0.0016066222],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99698997,0.00014901103,0.0007331008,0.00057371106,0.0005183937,0.0010358454],"domain_scores_gemma":[0.9827532,0.00051098666,0.0009086497,0.00042931546,0.015161915,0.00023593166],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0020949957,0.00048401262,0.0005289155,0.00026412896,0.0005057723,0.0060713394,0.0035997224,0.0005555517,0.000046344878],"category_scores_gemma":[0.008341064,0.0004248177,0.00019031129,0.0006717311,0.0017260098,0.014397541,0.0010852469,0.0006326451,0.000011426153],"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":[0.00006474919,0.00027903344,0.52849567,0.0014112786,0.00011314898,0.0000012093822,0.060970005,0.00008461911,0.14963308,0.055514526,0.0017004795,0.2017322],"study_design_scores_gemma":[0.0005656302,0.00031049683,0.709404,0.0011831062,0.000108365966,0.00010004736,0.008348114,0.071647815,0.16064702,0.038100563,0.009036554,0.0005483064],"about_ca_topic_score_codex":0.002093259,"about_ca_topic_score_gemma":0.000042286596,"teacher_disagreement_score":0.2011839,"about_ca_system_score_codex":0.00039703012,"about_ca_system_score_gemma":0.0008383069,"threshold_uncertainty_score":0.99982035},"labels":[],"label_agreement":null},{"id":"W2738173662","doi":"","title":"Semi-supervised learning and opinion-oriented information extraction","year":2010,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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 New Brunswick","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence; Co-training; Classifier (UML); Graph; Semi-supervised learning; Naive Bayes classifier; Bottleneck; Information extraction; Supervised learning; Decision tree; Algorithm; Data mining; Theoretical computer science; Support vector machine","score_opus":0.008705654857859608,"score_gpt":0.260067979323589,"score_spread":0.25136232446572937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2738173662","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":[0.065441065,0.000014283704,0.9186647,0.0029414664,0.00060949783,0.00010681486,2.186271e-7,0.0012568817,0.010965063],"genre_scores_gemma":[0.96315914,0.00004295166,0.036274645,0.00008094224,0.000017281724,0.000011899259,0.0000065911836,0.0000016812079,0.0004048514],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995716,0.000008577483,0.00012120323,0.00010402664,0.00010563341,0.00008893328],"domain_scores_gemma":[0.99966323,0.000035190504,0.000054451426,0.00016532418,0.00005200775,0.000029767645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000113901544,0.000053938835,0.000042501775,0.000107157,0.00012113902,0.00017956653,0.00015708565,0.00006505297,0.000051455598],"category_scores_gemma":[0.00009551633,0.000046399564,0.000011785604,0.00018193155,0.000027289638,0.002148699,0.000091688285,0.00018619024,0.00007146012],"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":[0.0000020083146,0.000013854489,0.005250959,0.0000066899306,0.000003034509,1.1489646e-7,0.00035060654,0.0000031821212,0.016874848,0.4828302,0.0009983011,0.4936662],"study_design_scores_gemma":[0.000493858,0.00007432138,0.023864232,0.000006485955,0.0000017275374,0.00002115984,0.00075941347,0.12551826,0.021894675,0.004161613,0.8229613,0.00024298448],"about_ca_topic_score_codex":0.00000879593,"about_ca_topic_score_gemma":0.000002028506,"teacher_disagreement_score":0.8977181,"about_ca_system_score_codex":0.0000063440107,"about_ca_system_score_gemma":0.000012790069,"threshold_uncertainty_score":0.18921193},"labels":[],"label_agreement":null},{"id":"W2740468505","doi":"10.24963/ijcai.2017/443","title":"Incomplete Label Distribution Learning","year":2017,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"Novelis (Canada)","funders":"National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Relevance (law); Minification; Exploit; Annotation; Machine learning; Algorithm","score_opus":0.041912464323893436,"score_gpt":0.2960959009144437,"score_spread":0.25418343659055026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2740468505","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":[0.012520838,0.000011683216,0.9617971,0.007993007,0.0001272961,0.00004197793,6.375146e-7,0.00088176044,0.016625686],"genre_scores_gemma":[0.9856563,0.000008538889,0.011011968,0.000034365563,0.000011181461,0.0000056513445,0.0000036806512,0.0000014210831,0.0032669],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995782,0.000008817367,0.00006971793,0.00014748755,0.000089323345,0.00010646921],"domain_scores_gemma":[0.99922633,0.00001582965,0.00008436483,0.0006248737,0.000028705044,0.000019868563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000096651944,0.00004452644,0.000046392055,0.000017453605,0.0005516133,0.000491238,0.0010521938,0.000029958079,0.000022664382],"category_scores_gemma":[0.00014394039,0.000036989994,0.000014566956,0.00003787813,0.000053568536,0.000623773,0.00040281776,0.00007483886,0.00020235789],"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":[3.388351e-7,0.0000075484127,0.004629956,9.11646e-7,0.0000017534375,7.3278426e-7,0.000011420129,9.234342e-7,0.00065063796,0.81683356,0.0019843902,0.17587784],"study_design_scores_gemma":[0.00072879257,0.00012182223,0.24943246,0.000012672344,0.0000034863428,0.0000061954556,0.00006305896,0.088762954,0.019083358,0.095390946,0.5460006,0.00039365262],"about_ca_topic_score_codex":0.000018097911,"about_ca_topic_score_gemma":0.0000033274791,"teacher_disagreement_score":0.9731355,"about_ca_system_score_codex":0.000016931954,"about_ca_system_score_gemma":0.000008992407,"threshold_uncertainty_score":0.47370195},"labels":[],"label_agreement":null},{"id":"W2756654724","doi":"10.18653/v1/d17-1202","title":"Shortest-Path Graph Kernels for Document Similarity","year":2017,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Graph; Similarity measure; Shortest path problem; Kernel (algebra); Similarity (geometry); Macro; Data mining; Artificial intelligence; Pattern recognition (psychology); Theoretical computer science; Mathematics; Combinatorics","score_opus":0.04094903064209897,"score_gpt":0.31369760833261384,"score_spread":0.27274857769051486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2756654724","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":[0.0056085438,0.000035362023,0.97125816,0.011897228,0.0003429043,0.00034206256,0.0000026630623,0.00079054065,0.009722557],"genre_scores_gemma":[0.9089508,0.000035035304,0.0879635,0.0002577048,0.000024129127,0.00009648561,0.0000015912274,0.0000043994023,0.002666323],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991156,0.0000071908453,0.00015524894,0.00034153223,0.00015752007,0.00022292472],"domain_scores_gemma":[0.9981591,0.00005249089,0.00012406099,0.0015457801,0.000068268666,0.000050316197],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022389747,0.000103637176,0.000111013505,0.000058036312,0.0004940039,0.0007744386,0.002076445,0.000066791865,0.00002947793],"category_scores_gemma":[0.00013272169,0.00008333742,0.00007942157,0.00005100374,0.00009181792,0.000915802,0.0004165021,0.00006124202,0.000034901004],"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":[0.000001846973,0.0000342465,0.003814014,0.0000034787483,0.000009293375,0.0000010383716,0.000036401598,0.0000021125718,0.0003291697,0.9292241,0.011173009,0.05537129],"study_design_scores_gemma":[0.00066193106,0.0001654583,0.05026225,0.000011536129,0.000009831933,0.0000028316574,0.00006159761,0.0075028916,0.038504045,0.8436001,0.05881664,0.00040088774],"about_ca_topic_score_codex":0.000028165254,"about_ca_topic_score_gemma":0.000012743917,"teacher_disagreement_score":0.9033423,"about_ca_system_score_codex":0.00002140419,"about_ca_system_score_gemma":0.000027581425,"threshold_uncertainty_score":0.7467929},"labels":[],"label_agreement":null},{"id":"W2763406350","doi":"10.1017/s1351324917000389","title":"Emerging trends: A tribute to Charles Wayne","year":2017,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Alberta-Pacific Forest Industries","keywords":"Tribute; Order (exchange); Government (linguistics); Computer science; sort; Management; Law; Political science; Economics; Finance; Philosophy; Linguistics","score_opus":0.007743718129550689,"score_gpt":0.2627037147876462,"score_spread":0.2549599966580955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2763406350","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":[0.3229645,0.008195444,0.6063191,0.04880725,0.0042364374,0.00037612751,0.000016556694,0.006801171,0.0022833908],"genre_scores_gemma":[0.9726377,0.000008446574,0.024905745,0.00005516427,0.00008310281,0.000016171069,0.0000028540642,0.000008046289,0.0022827752],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992539,0.000003459158,0.00010985364,0.00023441724,0.00015039362,0.00024797732],"domain_scores_gemma":[0.9990559,0.000020136444,0.00005406214,0.00079229305,0.000021368292,0.000056198904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009070981,0.00011673734,0.00011234256,0.00020113718,0.0001670577,0.00035241304,0.0012847917,0.000046847334,0.0000115512885],"category_scores_gemma":[0.00023191846,0.00010192754,0.000048414677,0.00016913912,0.00001002839,0.00057507167,0.0003467984,0.00016399419,0.000046385587],"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":[0.0000019232461,0.000008249309,0.0000957124,0.000009701785,0.000014867111,0.00003343097,0.00095418293,0.00012998219,0.041780192,0.024301074,0.0013620628,0.9313086],"study_design_scores_gemma":[0.0015878063,0.00014626524,0.08566999,0.000233003,0.000023446393,0.000054175714,0.00066634826,0.32522935,0.31699347,0.00031210974,0.26706204,0.0020220221],"about_ca_topic_score_codex":0.000018595367,"about_ca_topic_score_gemma":0.0000067313026,"teacher_disagreement_score":0.9292866,"about_ca_system_score_codex":0.000036518544,"about_ca_system_score_gemma":0.0000051248035,"threshold_uncertainty_score":0.41564843},"labels":[],"label_agreement":null},{"id":"W2783366437","doi":"10.1109/bigdata.2017.8258136","title":"Semi-supervised learning and social media text analysis towards multi-labeling categorization","year":2017,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Artificial intelligence; WordNet; Categorization; Machine learning; Natural language processing; Supervised learning; Annotation; Graph; Task (project management); Labeled data; Pattern recognition (psychology); Artificial neural network","score_opus":0.045480703077475496,"score_gpt":0.2997944648698337,"score_spread":0.2543137617923582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2783366437","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":[0.05270782,0.00005379179,0.9411021,0.003925411,0.000114094015,0.00006420247,6.700206e-7,0.00063870975,0.0013931954],"genre_scores_gemma":[0.97026515,0.000055280783,0.028870445,0.000032523905,0.000025332212,0.000007606841,0.00000828854,0.000004243404,0.00073109975],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991754,0.000026480602,0.00015612983,0.0003079579,0.00017502505,0.0001589717],"domain_scores_gemma":[0.9993626,0.00004288301,0.0001429255,0.00033885118,0.000081242346,0.000031499378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002030554,0.000096607146,0.00015240726,0.00018937257,0.0008253062,0.00075665856,0.0006636632,0.00009091617,0.000036174253],"category_scores_gemma":[0.00023526077,0.00008411642,0.000048775128,0.00024988834,0.00008636577,0.00070471223,0.00036541367,0.000111788075,0.000017950893],"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":[0.0000028229852,0.000053301883,0.060062725,0.000013335467,0.00017240745,0.000002749266,0.0049678413,0.000051795378,0.006365461,0.10347145,0.00012007545,0.82471603],"study_design_scores_gemma":[0.00089602714,0.000024819738,0.17027348,0.000004584783,0.00013021036,0.0000010596611,0.0018256502,0.8114092,0.010087967,0.0027203239,0.0021838183,0.00044287083],"about_ca_topic_score_codex":0.000055179415,"about_ca_topic_score_gemma":0.00006384354,"teacher_disagreement_score":0.91755736,"about_ca_system_score_codex":0.000021127582,"about_ca_system_score_gemma":0.000023544148,"threshold_uncertainty_score":0.72964764},"labels":[],"label_agreement":null},{"id":"W2799784710","doi":"","title":"Learning Activation Functions in Deep Neural Networks","year":2017,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Text and Document Classification Technologies","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":"Mitacs","keywords":"Humanities; Art","score_opus":0.015045228808938172,"score_gpt":0.24236834086929476,"score_spread":0.2273231120603566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2799784710","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":[0.061142825,0.000121011566,0.92605346,0.009935529,0.00016675926,0.00028777568,5.257943e-7,0.0014044803,0.0008876476],"genre_scores_gemma":[0.9742923,0.000042160165,0.024212018,0.00036058127,0.00005889943,0.00028441843,0.000006853848,0.000018538445,0.0007242677],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99844944,0.0000774095,0.00031074404,0.00044238515,0.0002175447,0.0005024496],"domain_scores_gemma":[0.99797547,0.00008833967,0.0003382092,0.0014340645,0.00006563045,0.00009826489],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004146699,0.00020165075,0.00019325931,0.0004034312,0.00081254967,0.0009022479,0.0015895313,0.00023459923,0.0000119141],"category_scores_gemma":[0.00043530014,0.0002069026,0.00008252361,0.0003681746,0.000097663185,0.001761936,0.000547694,0.00061093766,0.000014374307],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023056682,0.00013774597,0.21393724,0.000007480583,0.000015218761,0.000019420013,0.00021859535,0.051238045,0.002127174,0.12236666,0.0005802443,0.6093291],"study_design_scores_gemma":[0.00021755346,0.000057385278,0.23707978,0.000011179639,0.0000025383026,0.000008743137,0.00007584171,0.75758827,0.0012667764,0.0026781566,0.0008287894,0.00018500804],"about_ca_topic_score_codex":0.0017678124,"about_ca_topic_score_gemma":0.0010945437,"teacher_disagreement_score":0.9131494,"about_ca_system_score_codex":0.0002582949,"about_ca_system_score_gemma":0.000044157783,"threshold_uncertainty_score":0.87003976},"labels":[],"label_agreement":null},{"id":"W2806223921","doi":"","title":"NEC and Tokyo Institute of Technology in TAC KBP 2017: Multichannel Encoding and Stochastic Voting for Event Detection Model.","year":2017,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Voting; Event (particle physics); Computer science; Encoding (memory); Artificial intelligence; Political science; Law; Physics","score_opus":0.02043233040435181,"score_gpt":0.28750442671107534,"score_spread":0.2670720963067235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806223921","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":[0.18515228,0.00027993828,0.8136599,0.0005281469,0.000018855793,0.00028101148,0.000003065877,0.000044509146,0.000032311655],"genre_scores_gemma":[0.99314517,0.000061728446,0.0065198825,0.0000033257595,0.0000063989783,0.00023175341,7.939341e-7,0.0000028148847,0.000028158847],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994909,0.000007685196,0.00018043026,0.0001903663,0.000041033472,0.00008955404],"domain_scores_gemma":[0.99930304,0.00008697871,0.00021019448,0.00032468428,0.000058751306,0.000016377124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030788523,0.00007152319,0.00013091754,0.00017250303,0.0002767589,0.000044320812,0.0002934576,0.00006755333,1.2748329e-7],"category_scores_gemma":[0.00015603153,0.000067343695,0.000011565877,0.000088666,0.0005042901,0.0003877588,0.0002021849,0.00005486069,1.150247e-7],"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":[0.000010781603,0.000014811773,0.000081618266,0.00003646077,0.0000040789096,3.2662836e-8,0.00029665255,0.00018028187,0.0097685065,0.88217056,6.684769e-7,0.107435554],"study_design_scores_gemma":[0.00030089455,0.00005450553,0.00049270596,0.00002348917,0.000010432304,0.0000039783044,0.00070279377,0.05633822,0.05209294,0.88982356,0.0000652848,0.00009119031],"about_ca_topic_score_codex":0.0000113395945,"about_ca_topic_score_gemma":0.000012620104,"teacher_disagreement_score":0.8079929,"about_ca_system_score_codex":0.0000071146715,"about_ca_system_score_gemma":0.000016475893,"threshold_uncertainty_score":0.2746196},"labels":[],"label_agreement":null},{"id":"W2808417254","doi":"10.24963/ijcai.2018/395","title":"Does Tail Label Help for Large-Scale Multi-Label Learning","year":2018,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Novelis (Canada)","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Trimming; Computer science; Multi-label classification; Artificial intelligence; Scale (ratio); Machine learning; Learning to rank; Fraction (chemistry); Pattern recognition (psychology); Ranking (information retrieval)","score_opus":0.03686393115797922,"score_gpt":0.30143857486617326,"score_spread":0.26457464370819406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2808417254","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008930873,0.000033375436,0.98339176,0.0043106624,0.00039162562,0.00020389871,0.0000021806,0.0015071863,0.0012284501],"genre_scores_gemma":[0.31937292,0.000014611436,0.6401939,0.00038929182,0.0000793107,0.00007640252,0.000003367237,0.000010166295,0.039860073],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989955,0.000017857456,0.00016621946,0.0003683501,0.00013337843,0.0003187121],"domain_scores_gemma":[0.9992258,0.000069336464,0.00007654189,0.0004393662,0.00014431015,0.00004464067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019950146,0.00010934291,0.00010980732,0.0000878964,0.00030704928,0.00018384543,0.00077563303,0.00008667797,0.000070343696],"category_scores_gemma":[0.00011795252,0.00006657001,0.00003218123,0.00024963674,0.000071249466,0.00045480832,0.00029399607,0.00009391988,0.00027745805],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015478907,0.0005925569,0.016246943,0.000032830256,0.000032587042,0.0000011691793,0.00154642,0.0000010953713,0.017470688,0.42299145,0.026880048,0.5141887],"study_design_scores_gemma":[0.0023487376,0.0004263899,0.0013290546,0.000015307802,0.0000072429507,0.0000013842352,0.0018809856,0.60149056,0.07006983,0.009781491,0.3122219,0.00042711824],"about_ca_topic_score_codex":0.000007718696,"about_ca_topic_score_gemma":0.000059184367,"teacher_disagreement_score":0.6014895,"about_ca_system_score_codex":0.000021499049,"about_ca_system_score_gemma":0.00002316359,"threshold_uncertainty_score":0.35662547},"labels":[],"label_agreement":null},{"id":"W2887261712","doi":"10.1007/978-981-13-2122-1_4","title":"Learning Safe Graph Construction from Multiple Graphs","year":2018,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Novelis (Canada)","funders":"","keywords":"Computer science; Graph; Information retrieval; Theoretical computer science","score_opus":0.03168101659383128,"score_gpt":0.2651982043060919,"score_spread":0.23351718771226065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2887261712","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011877564,0.00044168675,0.84317344,0.001571884,0.00075947965,0.00049965444,0.000020028612,0.0007251919,0.15162085],"genre_scores_gemma":[0.23769489,0.008422094,0.7505514,0.0007973004,0.000071062736,0.00007131192,0.00023190863,0.000019706198,0.0021403476],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983159,0.00003232075,0.00065113057,0.00036599123,0.0004169803,0.00021772986],"domain_scores_gemma":[0.9966659,0.00027354882,0.00048740619,0.0021093776,0.00038683673,0.00007694377],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058061606,0.00022456748,0.00022664345,0.0013609568,0.0007072395,0.0008207116,0.0035026171,0.00018814573,0.000030239791],"category_scores_gemma":[0.000096192525,0.00022798851,0.000053950564,0.0006066957,0.0020592317,0.0071329637,0.002319132,0.00051916303,0.00014424123],"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":[0.0000014621536,0.0000068362942,0.000487252,0.0000050238073,0.0000053634394,1.0514505e-7,0.0010654643,0.000024926201,0.000007608931,0.6283709,0.0002621095,0.369763],"study_design_scores_gemma":[0.000703524,0.00015936965,0.00580432,0.0002647144,0.000011597122,0.00002082417,0.0003492858,0.2533155,0.0001727825,0.37452412,0.36386317,0.0008107797],"about_ca_topic_score_codex":0.000021931022,"about_ca_topic_score_gemma":0.0000128944785,"teacher_disagreement_score":0.36895218,"about_ca_system_score_codex":0.000100028636,"about_ca_system_score_gemma":0.00015417018,"threshold_uncertainty_score":0.92971015},"labels":[],"label_agreement":null},{"id":"W2892021372","doi":"10.1111/exsy.12520","title":"A supervised learning approach for heading detection","year":2020,"lang":"en","type":"preprint","venue":"Expert Systems","topic":"Text and Document Classification Technologies","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":"Lakehead University","funders":"","keywords":"Computer science; Classifier (UML); Popularity; Artificial intelligence; Heading (navigation); Supervised learning; Automation; Variety (cybernetics); Field (mathematics); Machine learning; Feature extraction; Data mining; Pattern recognition (psychology); Engineering; Artificial neural network; Mathematics","score_opus":0.07321958308784908,"score_gpt":0.2929786932019226,"score_spread":0.2197591101140735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2892021372","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":[0.00048587637,0.001695751,0.99100655,0.0009103891,0.0015302444,0.0010691534,0.0000021291924,0.0023967354,0.00090316456],"genre_scores_gemma":[0.9507717,0.000046389505,0.04630835,0.00005398848,0.0003770053,0.001910175,0.00003288296,0.00002741822,0.0004720852],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981692,0.000098848875,0.00037784033,0.00083147036,0.00025772033,0.0002649566],"domain_scores_gemma":[0.99882364,0.00007398238,0.00024643028,0.0006991878,0.00008704046,0.000069738366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027921872,0.00024991584,0.00037324513,0.0001724014,0.00022329659,0.0006862224,0.0012457812,0.00033472275,0.0000012551513],"category_scores_gemma":[0.00013929252,0.00023817367,0.00016174307,0.0002132674,0.000025256993,0.00021787759,0.00074835075,0.00043640615,0.000018213554],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013368597,0.00047816252,0.0006377795,0.005981681,0.00077052275,0.00001867867,0.046563916,0.035648335,0.19645077,0.23918615,0.03446557,0.43966475],"study_design_scores_gemma":[0.00022661182,0.00007146596,0.000012383599,0.00007151055,0.000004217818,0.000005455875,0.0010362183,0.9567788,0.006497162,0.0006637385,0.03429398,0.00033844364],"about_ca_topic_score_codex":0.0001048236,"about_ca_topic_score_gemma":6.695196e-7,"teacher_disagreement_score":0.95028585,"about_ca_system_score_codex":0.00015152343,"about_ca_system_score_gemma":0.000058744492,"threshold_uncertainty_score":0.9712441},"labels":[],"label_agreement":null},{"id":"W2898491562","doi":"10.1109/icde.2018.00271","title":"Enhancing Binary Classification by Modeling Uncertain Boundary in Three-Way Decisions (Extended Abstract)","year":2018,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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 Regina","funders":"","keywords":"Computer science; Scalability; Class (philosophy); Set (abstract data type); Boundary (topology); Artificial intelligence; Binary classification; Machine learning; Training set; Subject (documents); Information retrieval; Support vector machine; World Wide Web; Database; Mathematics","score_opus":0.0552643509655733,"score_gpt":0.3070639071558011,"score_spread":0.2517995561902278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898491562","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":[0.15887217,0.00017469151,0.831807,0.0030412653,0.00020949898,0.00018435087,0.0000015281103,0.0007260568,0.0049834047],"genre_scores_gemma":[0.95045257,0.000049080554,0.048765913,0.0001850249,0.000030759962,0.000042400065,0.0000087907365,0.0000097789525,0.00045567946],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99823135,0.000024372399,0.0004869598,0.0005799137,0.00032353494,0.00035388258],"domain_scores_gemma":[0.9986517,0.00015360698,0.00011625632,0.0008866391,0.00012382233,0.000067977715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047427104,0.00016697637,0.00015639872,0.00031563628,0.00027693616,0.0002952566,0.0011225704,0.00015089288,0.00008658374],"category_scores_gemma":[0.0001784402,0.00014725448,0.00004699241,0.0007754382,0.00013398503,0.0010452125,0.00025765074,0.00020876757,0.0002601765],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029200655,0.00043697684,0.0010521259,0.000011206022,0.000018808301,0.000009593467,0.00081095955,0.00027352103,0.2227531,0.30247825,0.008654647,0.46347162],"study_design_scores_gemma":[0.00036306362,0.00011423415,0.008047283,0.00005473236,0.0000028556735,0.0000037673371,0.00056421256,0.8635639,0.020695496,0.1026209,0.003611978,0.00035757132],"about_ca_topic_score_codex":0.00012772487,"about_ca_topic_score_gemma":0.00045702403,"teacher_disagreement_score":0.86329037,"about_ca_system_score_codex":0.00014561739,"about_ca_system_score_gemma":0.00012442103,"threshold_uncertainty_score":0.6004864},"labels":[],"label_agreement":null},{"id":"W2906685695","doi":"10.1007/s10115-018-1278-7","title":"Combining semantic and term frequency similarities for text clustering","year":2019,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Fundação de Amparo à Pesquisa do Estado de Minas Gerais; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Natural Sciences and Engineering Research Council of Canada; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Cluster analysis; Semantic similarity; Computer science; Document clustering; Similarity (geometry); Measure (data warehouse); Information retrieval; Similarity measure; Natural language processing; Term (time); Artificial intelligence; Word (group theory); Data mining; Mathematics","score_opus":0.01570786528100131,"score_gpt":0.24286185679499328,"score_spread":0.22715399151399196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2906685695","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":[0.13045011,0.0036708564,0.7936513,0.00082191743,0.002156708,0.0018954383,0.000013558962,0.0010731603,0.06626697],"genre_scores_gemma":[0.99802655,0.00007045909,0.0012926948,0.00004641076,0.000017348028,0.000058070847,0.0000068938552,0.0000028902643,0.00047866488],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994033,0.0000120253435,0.00027825584,0.0001083929,0.00007038647,0.00012763162],"domain_scores_gemma":[0.9994855,0.00007406912,0.00011557959,0.00020667829,0.000088344554,0.000029822528],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020370024,0.00008688413,0.00013291523,0.00015652434,0.00012129542,0.00047806703,0.00018965198,0.000064885025,0.0000016493498],"category_scores_gemma":[0.000022472974,0.000075906886,0.00001730354,0.00010404798,0.000026884376,0.0032144445,0.00012706552,0.00004718287,0.000054209937],"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":[0.00000482765,0.000016573083,0.012695805,0.0015646797,0.000024362287,1.4369368e-7,0.011226255,0.00001200933,0.00057555217,0.8524855,0.001452804,0.119941525],"study_design_scores_gemma":[0.0028039503,0.00044998951,0.021527573,0.00064936926,0.000017236733,0.00006820701,0.008267388,0.757913,0.0010846716,0.0041264566,0.20225959,0.00083259126],"about_ca_topic_score_codex":0.0000054741954,"about_ca_topic_score_gemma":0.0000015590794,"teacher_disagreement_score":0.8675765,"about_ca_system_score_codex":0.000017304614,"about_ca_system_score_gemma":0.000018560128,"threshold_uncertainty_score":0.46100113},"labels":[],"label_agreement":null},{"id":"W2914754426","doi":"10.1007/978-3-030-12598-1_44","title":"Opposition-Based Multi-objective Binary Differential Evolution for Multi-label Feature Selection","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Feature selection; Computer science; Artificial intelligence; Differential evolution; Binary number; Preprocessor; Binary classification; Pattern recognition (psychology); Machine learning; Feature (linguistics); Pareto principle; Optimization problem; Mathematical optimization; Algorithm; Support vector machine; Mathematics","score_opus":0.030661377136293477,"score_gpt":0.2787367194164769,"score_spread":0.2480753422801834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914754426","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000148863,0.00022281482,0.99444,0.0011095259,0.0020186915,0.0013215271,0.000027700025,0.0006395049,0.00007133354],"genre_scores_gemma":[0.18706691,0.000010393871,0.8109917,0.00035856568,0.00020068845,0.00007993315,0.000047465524,0.000039766033,0.0012045652],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965799,0.000038328588,0.00039503182,0.0017165092,0.00065836305,0.00061188685],"domain_scores_gemma":[0.9976558,0.00035402656,0.00041601024,0.0009809575,0.0004967924,0.00009641616],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00033313507,0.00056850567,0.00047070222,0.0012153223,0.00045640324,0.00053063384,0.0022129342,0.000681171,0.000009775139],"category_scores_gemma":[0.00010842838,0.000526703,0.00017797056,0.0007019401,0.00045567477,0.00075745356,0.0005189059,0.0007819743,0.000036979643],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000107658845,0.00072396407,0.0006516767,0.00028383793,0.000083742714,0.000019971552,0.0005782944,0.028329803,0.026225436,0.11517542,0.00041826596,0.82740194],"study_design_scores_gemma":[0.0012919098,0.0004115895,0.0009102071,0.00020569073,0.000016048523,0.000010470153,4.367565e-7,0.97700226,0.0074687805,0.0118635185,0.00019969372,0.00061939395],"about_ca_topic_score_codex":0.00001120112,"about_ca_topic_score_gemma":0.00006906439,"teacher_disagreement_score":0.9486725,"about_ca_system_score_codex":0.0009357487,"about_ca_system_score_gemma":0.00085004733,"threshold_uncertainty_score":0.9997184},"labels":[],"label_agreement":null},{"id":"W2914990229","doi":"","title":"Proceedings of the fourth workshop on Analytics for noisy unstructured text data","year":2010,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Listing (finance); Analytics; Key (lock); Data science; Library science; World Wide Web; Information retrieval","score_opus":0.04627194771488053,"score_gpt":0.28945382929743696,"score_spread":0.24318188158255644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914990229","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":[0.2213943,0.000023999413,0.6542463,0.08298352,0.002414453,0.0019230542,0.000052495398,0.0015649395,0.035396993],"genre_scores_gemma":[0.8977822,0.0000030545903,0.10025643,0.000181513,0.000027874841,0.000008022356,0.000001980303,0.000004014281,0.0017349164],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99930274,0.0000014320242,0.00014402601,0.00026611422,0.00016481079,0.00012089224],"domain_scores_gemma":[0.998708,0.000080523474,0.00012133339,0.00097418483,0.00009618628,0.000019776404],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014228701,0.00007419937,0.000082576924,0.00005896541,0.00007402366,0.00011051787,0.0030557183,0.0000734473,0.000012817499],"category_scores_gemma":[0.00028187357,0.000042399864,0.00003359308,0.0003658604,0.000089063724,0.00030463768,0.000554264,0.00013812858,0.0000037073276],"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":[0.0000030364802,0.000021357955,0.00059789384,0.000006455444,0.000007785315,1.838734e-8,0.000046385037,0.0000024553894,0.0064180056,0.8989049,0.021292232,0.072699465],"study_design_scores_gemma":[0.0011852175,0.00015880012,0.025845293,0.000050989238,0.00004414251,0.0000076548995,0.0007546209,0.24900043,0.25828966,0.21098046,0.25308004,0.0006026872],"about_ca_topic_score_codex":0.0000015621017,"about_ca_topic_score_gemma":0.000015572692,"teacher_disagreement_score":0.68792444,"about_ca_system_score_codex":0.0000056821773,"about_ca_system_score_gemma":0.000028382663,"threshold_uncertainty_score":0.5678336},"labels":[],"label_agreement":null},{"id":"W2918429485","doi":"","title":"A Best Match KNN-based Approach for Large-scale Product Categorization.","year":2018,"lang":"en","type":"article","venue":"International ACM SIGIR Conference on Research and Development in Information Retrieval","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trent University; York University","funders":"","keywords":"Categorization; Computer science; Scale (ratio); Product (mathematics); Artificial intelligence; Data mining; Pattern recognition (psychology); Mathematics; Cartography; Geography","score_opus":0.09819718700532777,"score_gpt":0.35379098916930884,"score_spread":0.2555938021639811,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2918429485","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":[0.017343912,0.000009675084,0.96540487,0.0065105073,0.0003431346,0.0008850237,0.000023131373,0.0001812752,0.009298472],"genre_scores_gemma":[0.8701008,0.000023829,0.12867832,0.0002068102,0.000051157804,0.0002157887,0.00022718761,0.0000050903623,0.00049099437],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997869,0.000037604663,0.00045896697,0.00035862226,0.000893124,0.0003826857],"domain_scores_gemma":[0.99762654,0.00023105355,0.00012705904,0.00043105453,0.0015012028,0.00008306408],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012541459,0.0001391225,0.00012537601,0.0008719358,0.0002844935,0.00070766226,0.0013006801,0.00009109637,0.00005575741],"category_scores_gemma":[0.0012279928,0.00012444104,0.000018441482,0.00061511283,0.00014034023,0.0013089894,0.00035633935,0.00021752817,0.00014447099],"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":[0.0006287003,0.0007454381,0.010079639,0.00012905088,0.000040541854,0.0000012870925,0.004149735,0.000057954105,0.00048278816,0.8789428,0.0056900904,0.09905197],"study_design_scores_gemma":[0.006787441,0.0016667802,0.020887269,0.00024229608,0.0000032210808,0.000010885343,0.0041307732,0.4969812,0.115626104,0.054427568,0.2980124,0.0012240612],"about_ca_topic_score_codex":0.000008947524,"about_ca_topic_score_gemma":0.000007802681,"teacher_disagreement_score":0.8527569,"about_ca_system_score_codex":0.00017859897,"about_ca_system_score_gemma":0.00055523973,"threshold_uncertainty_score":0.68240035},"labels":[],"label_agreement":null},{"id":"W2922481072","doi":"10.48550/arxiv.1903.08351","title":"Distributed Maximization of Submodular plus Diversity Functions for Multi-label Feature Selection on Huge Datasets","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Text and Document Classification Technologies","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":"University of British Columbia","funders":"","keywords":"Submodular set function; Feature selection; Redundancy (engineering); Computer science; Automatic summarization; Feature (linguistics); Greedy algorithm; Maximization; Function (biology); Data mining; Mathematical optimization; Optimization problem; Minimum redundancy feature selection; Selection (genetic algorithm); Artificial intelligence; Machine learning; Algorithm; Mathematics","score_opus":0.12415862055537509,"score_gpt":0.22536086640708697,"score_spread":0.10120224585171188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2922481072","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":[0.030944766,0.000020294432,0.9656709,0.00024856624,0.0004930661,0.0007209199,0.0014239219,0.0004328135,0.00004478003],"genre_scores_gemma":[0.9871445,0.00006899652,0.008914089,0.000027015652,0.000018077904,0.000003734191,0.0023146134,0.000011124337,0.001497872],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852246,0.00006096226,0.0001580907,0.000912353,0.000113808324,0.00023231929],"domain_scores_gemma":[0.998113,0.00007369726,0.0004074003,0.0010874206,0.0002592904,0.000059202324],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00014095912,0.00024967198,0.0002856743,0.00034150336,0.0003333625,0.00006926294,0.0013745999,0.00041986874,0.000007964362],"category_scores_gemma":[0.00008063397,0.00028482152,0.00013802925,0.00070379773,0.00008114068,0.00045102753,0.0019203454,0.00035904185,0.000025731062],"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":[0.00039026682,0.000993292,0.014617832,0.00043191842,0.0004053492,0.000015239544,0.00020718238,0.55822,0.00041293245,0.39156762,0.029490165,0.003248145],"study_design_scores_gemma":[0.001504988,0.00014742772,0.005860685,0.000048805985,0.000102646394,7.706772e-7,0.00007178067,0.98505086,0.0008203713,0.0046343375,0.0014100472,0.0003472697],"about_ca_topic_score_codex":0.00007192809,"about_ca_topic_score_gemma":0.000034020217,"teacher_disagreement_score":0.9567568,"about_ca_system_score_codex":0.00038573673,"about_ca_system_score_gemma":0.00013579126,"threshold_uncertainty_score":0.9999604},"labels":[],"label_agreement":null},{"id":"W2938956725","doi":"10.1016/j.eswa.2019.04.020","title":"Empirical evaluation of feature projection algorithms for multi-view text classification","year":2019,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Text and Document Classification Technologies","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":"University of Alberta","funders":"","keywords":"Computer science; Feature (linguistics); Projection (relational algebra); Artificial intelligence; Pattern recognition (psychology); Algorithm","score_opus":0.13574058111207438,"score_gpt":0.39200477001377315,"score_spread":0.2562641889016988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2938956725","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":[0.001213503,0.0012294266,0.98882794,0.0019570715,0.00016209067,0.0054303296,0.000007671801,0.0004202622,0.0007516853],"genre_scores_gemma":[0.8378969,0.00005678107,0.14113559,0.00008014612,0.00010566687,0.019242205,0.00008604838,0.000027159771,0.0013695367],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982774,0.000088542445,0.00035662448,0.0005580103,0.00053267425,0.0001867058],"domain_scores_gemma":[0.99761224,0.00008848783,0.00039164443,0.0010617024,0.0007998118,0.00004612162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006271754,0.00016305805,0.00023049921,0.0001917371,0.00014216408,0.00010544264,0.00059986964,0.00015710849,0.0000058879714],"category_scores_gemma":[0.000036406615,0.00012664487,0.000060760707,0.0007592308,0.0000545839,0.00041780467,0.00004647155,0.00009538533,0.000059381768],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000064861364,0.0015918107,0.01607769,0.0006374427,0.00024812415,1.692801e-7,0.0036124743,0.0006274613,0.035439547,0.44202223,0.0301047,0.4695735],"study_design_scores_gemma":[0.0015498558,0.00016138624,0.009327626,0.00009003246,0.000034080087,0.000012511371,0.0013692564,0.81865394,0.0029331155,0.0004664056,0.16505428,0.00034750934],"about_ca_topic_score_codex":0.000017897743,"about_ca_topic_score_gemma":0.0000034277157,"teacher_disagreement_score":0.8476924,"about_ca_system_score_codex":0.0001680172,"about_ca_system_score_gemma":0.00019588957,"threshold_uncertainty_score":0.5164428},"labels":[],"label_agreement":null},{"id":"W2941695365","doi":"10.48550/arxiv.1904.10403","title":"Optimizing Search API Queries for Twitter Topic Classifiers Using a Maximum Set Coverage Approach","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Text and Document Classification Technologies","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":"University of Toronto","funders":"","keywords":"Computer science; Classifier (UML); Information retrieval; Set (abstract data type); Precision and recall; Data mining; Training set; Machine learning; Artificial intelligence","score_opus":0.2023589357258472,"score_gpt":0.2432152504124623,"score_spread":0.0408563146866151,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2941695365","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":[0.11539545,0.000054668897,0.8806947,0.00028910136,0.00048614084,0.0007344627,0.000018837693,0.00047565674,0.0018510135],"genre_scores_gemma":[0.9511432,0.00010338182,0.04528035,0.00011530937,0.00004803307,0.0000064325095,0.00003731429,0.000024142668,0.003241838],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99773693,0.00009274619,0.00023823463,0.0012884067,0.00013606819,0.0005076342],"domain_scores_gemma":[0.997803,0.000116679934,0.0002432714,0.0015876066,0.0001565349,0.00009295045],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027157602,0.0003530944,0.00040065995,0.00041891253,0.00024120083,0.00039981338,0.0021627576,0.00046182983,0.00001466475],"category_scores_gemma":[0.000027314552,0.00038957092,0.0002560446,0.00046519193,0.00018279819,0.00062279316,0.0022205664,0.0005687813,0.00002627414],"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":[0.000077411925,0.00013667133,0.0032597259,0.0006109001,0.00023578605,0.000046072295,0.001840316,0.5827487,0.00034232967,0.40724516,0.0012590024,0.0021978936],"study_design_scores_gemma":[0.0007428511,0.00006523017,0.00020686889,0.00006970618,0.000054181262,0.0000043837135,0.0010692601,0.9438224,0.00073118246,0.049535397,0.0030317148,0.0006668383],"about_ca_topic_score_codex":0.00005676405,"about_ca_topic_score_gemma":0.0000021033009,"teacher_disagreement_score":0.8357478,"about_ca_system_score_codex":0.00037728797,"about_ca_system_score_gemma":0.0002859937,"threshold_uncertainty_score":0.99985564},"labels":[],"label_agreement":null},{"id":"W2942010367","doi":"","title":"تطوير خوارزمية جينية لتحديد الخصائص الهامة من صور الرنين المغناطيسي للدماغ للحصول على مصنف أسرع وأدق","year":2019,"lang":"ar","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Pattern recognition (psychology); Computer science; Feature selection; Preprocessor; Feature (linguistics); Gaussian filter; Image (mathematics)","score_opus":0.28700696101328854,"score_gpt":0.5599785983457948,"score_spread":0.27297163733250623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2942010367","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":[0.838749,0.06608386,0.007751658,0.008919528,0.012065852,0.0041994792,0.00020756364,0.001544905,0.06047816],"genre_scores_gemma":[0.9583132,0.024135573,0.002607319,0.0011523643,0.00051390374,0.00014095301,0.00003292461,0.00018700791,0.012916717],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9885024,0.00064442033,0.0032298663,0.0026148062,0.0030018736,0.002006679],"domain_scores_gemma":[0.98852116,0.0008764394,0.0038878315,0.004650518,0.0011753544,0.00088870106],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaepi_narrow","open_science","insufficient_payload"],"category_scores_codex":[0.0034556238,0.001511181,0.0026484898,0.002933179,0.0010668712,0.009949888,0.023153206,0.0008858203,0.024097387],"category_scores_gemma":[0.0006952146,0.0014369786,0.00094932644,0.004915759,0.00081314816,0.012128466,0.008925962,0.0021524513,0.004058882],"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":[0.00047341702,0.0019085213,0.5134887,0.00065757625,0.0010947086,0.00022602476,0.001560541,0.00044799835,0.08243375,0.02563626,0.2173224,0.15475008],"study_design_scores_gemma":[0.0037940762,0.00022622393,0.45405266,0.002256928,0.0004135656,0.00013247663,0.0012471785,0.0041081873,0.11365033,0.050460912,0.36552435,0.0041331234],"about_ca_topic_score_codex":0.0008199104,"about_ca_topic_score_gemma":0.0000511572,"teacher_disagreement_score":0.15061694,"about_ca_system_score_codex":0.00057176827,"about_ca_system_score_gemma":0.000851048,"threshold_uncertainty_score":0.9997637},"labels":[],"label_agreement":null},{"id":"W2943818116","doi":"10.5539/mas.v13n5p88","title":"Arabic Text Classification: A Review","year":2019,"lang":"en","type":"review","venue":"Modern Applied Science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Arabic; Weighting; Artificial intelligence; Classifier (UML); Decision tree; Natural language processing; Naive Bayes classifier; Support vector machine; Set (abstract data type); Data mining; Information retrieval; Machine learning; Linguistics","score_opus":0.126081744370099,"score_gpt":0.36112822664570676,"score_spread":0.23504648227560776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2943818116","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":[1.0351261e-8,0.7031172,0.27945557,0.00043883265,0.00024967408,0.0012435432,0.0000029159182,0.00064871926,0.014843536],"genre_scores_gemma":[0.000047191854,0.9900385,0.006960151,0.00042300994,0.000034925546,0.0006795048,0.000011418387,0.000026339156,0.0017789487],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9952954,0.000049403883,0.0008738509,0.0019362392,0.0011677865,0.00067728537],"domain_scores_gemma":[0.99473023,0.00014011272,0.00081775954,0.0040125144,0.00014408189,0.00015531134],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012597435,0.0005413587,0.0014431912,0.0005965381,0.00035277611,0.00062515354,0.009007856,0.0002532192,0.000037279624],"category_scores_gemma":[0.00011170709,0.00041526376,0.00029654364,0.0038935656,0.00065608294,0.00075726816,0.0012954345,0.0005560976,0.0036857072],"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":[1.1930344e-7,0.000020466297,7.418936e-8,0.0058723115,0.000005479724,6.1498355e-7,0.000015548703,1.09153554e-7,0.000028300457,0.13986386,0.0014619393,0.85273117],"study_design_scores_gemma":[0.000051449584,0.000012495267,0.0000020982727,0.0060114926,0.00007633518,0.000017603961,0.0000036256372,0.0025969418,0.0000063252373,0.0032284001,0.9874792,0.00051403843],"about_ca_topic_score_codex":7.1603324e-7,"about_ca_topic_score_gemma":2.2435663e-7,"teacher_disagreement_score":0.9860172,"about_ca_system_score_codex":0.00035450826,"about_ca_system_score_gemma":0.0014823497,"threshold_uncertainty_score":0.99982995},"labels":[],"label_agreement":null},{"id":"W2950347869","doi":"10.17863/cam.32314","title":"The 3rd Joint Symposium of the International and National Neurotrauma Societies and AANS/CNS Section on Neurotrauma and Critical Care August 11–16, 2018 Toronto, Canada","year":2018,"lang":"en","type":"article","venue":"Apollo (University of Cambridge)","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Cluster analysis; Class (philosophy); Trajectory; Artificial intelligence; Computer science; Latent class model; Biomarker; Machine learning; Biology","score_opus":0.020113545867294417,"score_gpt":0.22458285838546932,"score_spread":0.2044693125181749,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950347869","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":[0.9605646,0.00019264269,0.0022395444,0.02849565,0.0008805925,0.00017443883,0.00003622888,0.000057134333,0.0073591634],"genre_scores_gemma":[0.998662,0.000102431055,0.00021333019,0.00018058452,0.000034694112,4.7753497e-7,9.833632e-7,0.000002798609,0.0008026912],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99923366,0.00003585361,0.00008986382,0.00020369257,0.00033370376,0.0001032111],"domain_scores_gemma":[0.99937713,0.00011530877,0.00008438181,0.0001875014,0.00020093798,0.0000347449],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009250028,0.00007753685,0.00008192241,0.000030116054,0.0004668649,0.000060874463,0.0003896739,0.00004463675,0.0000059215486],"category_scores_gemma":[0.000049557442,0.000064337095,0.00002891311,0.00007479608,0.00067820534,0.00030952555,0.00030207128,0.00007842006,2.156952e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010540121,0.00009640045,0.017894993,0.00013898156,0.00010666325,0.0000049758974,0.005402898,0.000008203242,0.010795754,0.7551273,0.17897521,0.03134322],"study_design_scores_gemma":[0.0010941616,0.0005382338,0.8901702,0.00006583337,0.000042416785,0.000047756264,0.020927086,0.004757007,0.008386262,0.0013295442,0.07229614,0.0003453605],"about_ca_topic_score_codex":0.038659375,"about_ca_topic_score_gemma":0.07650496,"teacher_disagreement_score":0.87227523,"about_ca_system_score_codex":0.00012693218,"about_ca_system_score_gemma":0.00013209993,"threshold_uncertainty_score":0.96774226},"labels":[],"label_agreement":null},{"id":"W2958588221","doi":"","title":"Specifying Distinct Groups in Multivariate Data using Machine Learning","year":2019,"lang":"en","type":"article","venue":"MacEwan University Student Research Proceedings","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University","funders":"","keywords":"Multivariate statistics; Computer science; Artificial intelligence; Machine learning","score_opus":0.21457271135770284,"score_gpt":0.3929637549346773,"score_spread":0.17839104357697444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2958588221","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":[0.98598033,0.00004811087,0.0050300625,0.0010446856,0.00007997168,0.0005666699,0.000004212639,0.00037778533,0.0068681487],"genre_scores_gemma":[0.9916747,0.000042129246,0.0059534707,0.0000072259654,0.00001992987,8.968799e-7,0.000008039371,0.000009260843,0.0022843007],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9974895,0.00007741719,0.00016900575,0.00082618697,0.00086768635,0.0005701754],"domain_scores_gemma":[0.9989442,0.00012702972,0.00009754746,0.00054908806,0.00019479383,0.00008733265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017283824,0.00014467296,0.0001870212,0.00077409495,0.0004023225,0.0004166102,0.0041687586,0.000083698134,0.000048016704],"category_scores_gemma":[0.00018201646,0.00015086771,0.00002910862,0.001645699,0.000115918294,0.001770268,0.006841844,0.0008347881,0.00009816538],"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":[0.000039068946,0.00017481751,0.91382736,0.000060789014,0.000025215206,0.00004939375,0.002667725,0.000022364622,0.009350359,0.06875475,0.00019843306,0.004829741],"study_design_scores_gemma":[0.0036095276,0.00037630918,0.5036038,0.00026655,0.000012804541,0.000015803102,0.031071154,0.3714591,0.0016501088,0.0017670536,0.085280046,0.0008877158],"about_ca_topic_score_codex":0.00056665513,"about_ca_topic_score_gemma":0.00008419776,"teacher_disagreement_score":0.4102235,"about_ca_system_score_codex":0.0004440195,"about_ca_system_score_gemma":0.00006822253,"threshold_uncertainty_score":0.8527869},"labels":[],"label_agreement":null},{"id":"W2962851649","doi":"","title":"Distributed Maximization of \"Submodular plus Diversity\" Functions for Multi-label Feature Selection on Huge Datasets","year":2019,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Text and Document Classification Technologies","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":"University of British Columbia","funders":"","keywords":"Submodular set function; Feature selection; Computer science; Redundancy (engineering); Automatic summarization; Feature (linguistics); Greedy algorithm; Maximization; Optimization problem; Mathematical optimization; Data mining; Function (biology); Artificial intelligence; Machine learning; Algorithm; Mathematics","score_opus":0.14797393125353175,"score_gpt":0.3478739285134115,"score_spread":0.19989999725987972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962851649","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":[0.002328874,0.00000537548,0.9934265,0.0012160207,0.00048773858,0.00029004295,0.0019990732,0.00007749857,0.00016889637],"genre_scores_gemma":[0.90915847,0.00005293087,0.08908912,0.00009781445,0.000023034776,0.000021597865,0.0010642097,0.000005809698,0.000487002],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989989,0.000027261158,0.00023346103,0.00033643108,0.00027185102,0.00013208853],"domain_scores_gemma":[0.99902904,0.00016664331,0.00017674085,0.0002135584,0.00037570667,0.000038337224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013138787,0.00012374284,0.00013160855,0.00017318735,0.00016484619,0.00013983023,0.00045690653,0.00008474519,0.00006288245],"category_scores_gemma":[0.0002475445,0.0001200874,0.000024010698,0.0001828932,0.000075787895,0.0002562959,0.000159653,0.00011971899,0.00004970618],"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":[0.00010014782,0.00013474646,0.00022937775,0.000010569652,0.000022587472,6.274144e-7,0.00010330128,0.00068870484,0.0009577684,0.9185342,0.0011629183,0.07805504],"study_design_scores_gemma":[0.0001516387,0.00037946558,0.000767373,0.000029828372,0.0000096021595,0.0000015338479,0.0002725579,0.9255025,0.0054557114,0.066637106,0.0006433763,0.00014933498],"about_ca_topic_score_codex":0.000024335706,"about_ca_topic_score_gemma":0.00003895972,"teacher_disagreement_score":0.92481375,"about_ca_system_score_codex":0.0000677104,"about_ca_system_score_gemma":0.000055066528,"threshold_uncertainty_score":0.48970222},"labels":[],"label_agreement":null},{"id":"W2963381796","doi":"","title":"Text Categorization via Similarity Search - An Efficient and Effective Novel Algorithm.","year":2013,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"University of Ottawa","funders":"","keywords":"Computer science; Similarity (geometry); Artificial intelligence; Centroid; Cluster analysis; Preprocessor; Outlier; Metric (unit); Categorization; Text categorization; Point (geometry); Class (philosophy); Similarity measure; Pattern recognition (psychology); Algorithm; Mathematics; Image (mathematics)","score_opus":0.013069408635282848,"score_gpt":0.24933238222463994,"score_spread":0.23626297358935708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963381796","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":[0.041251726,0.00001612628,0.9554493,0.0013322404,0.00007671833,0.00045922754,8.1705195e-7,0.00055022794,0.00086361635],"genre_scores_gemma":[0.8953956,0.0000042308748,0.10421176,0.000108441025,0.000013296753,0.00006577409,0.0000041145727,0.000004589062,0.00019219622],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990711,0.000034576547,0.00012266591,0.0003743971,0.00019926025,0.00019797574],"domain_scores_gemma":[0.99927926,0.000067517794,0.000034838085,0.0004120806,0.0001288637,0.000077448414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001799395,0.000103612976,0.00009162618,0.00012220794,0.00014861976,0.00031115583,0.000417194,0.000077941055,0.000040568797],"category_scores_gemma":[0.000022141108,0.00008290616,0.000016139838,0.00034564757,0.00008586613,0.0006579751,0.00024961762,0.000105240855,0.00009381462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.498363e-7,0.0001778967,0.00059904734,0.0000061024484,0.0000067547953,3.8595408e-7,0.00037136907,0.0001350254,0.009223146,0.1359031,0.00014032354,0.8534361],"study_design_scores_gemma":[0.00024554977,0.00012386926,0.05175988,0.0000019334218,0.0000019509725,0.00000422531,0.00012495361,0.9173972,0.026163073,0.003782525,0.00024378466,0.00015103752],"about_ca_topic_score_codex":0.00021827426,"about_ca_topic_score_gemma":0.0000029983696,"teacher_disagreement_score":0.9172622,"about_ca_system_score_codex":0.00002836293,"about_ca_system_score_gemma":0.000017743358,"threshold_uncertainty_score":0.3380815},"labels":[],"label_agreement":null},{"id":"W2967878674","doi":"10.1109/cec.2019.8790287","title":"A Novel Multi-objective Binary Differential Evolution Algorithm for Multi-label Feature Selection","year":2019,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"Ontario Tech University","funders":"","keywords":"Feature selection; Computer science; Differential evolution; Artificial intelligence; Multi-label classification; Pattern recognition (psychology); Binary number; Evolutionary algorithm; Feature (linguistics); Machine learning; Binary classification; Data mining; Algorithm; Support vector machine; Mathematics","score_opus":0.030288772619659343,"score_gpt":0.2836045411106485,"score_spread":0.25331576849098913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2967878674","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005619265,0.000039500457,0.99131763,0.00055434735,0.000609918,0.000746392,0.0000111321215,0.0010314084,0.000070409376],"genre_scores_gemma":[0.17021762,0.000003808234,0.8196037,0.00004771872,0.0000361587,0.0001259827,0.00001398194,0.000010462762,0.009940603],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998894,0.000016691127,0.00014598023,0.0005084681,0.00016668208,0.00026818796],"domain_scores_gemma":[0.9993127,0.000044160926,0.00010509709,0.00032920708,0.00017039178,0.000038446116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000079543046,0.00016495393,0.00014873651,0.0001998835,0.00015343887,0.00012470841,0.00048588554,0.00018797335,0.000017594482],"category_scores_gemma":[0.00002928226,0.00013903592,0.00007281541,0.00042721917,0.00003520914,0.0006602876,0.00016690997,0.0001575772,0.000077599216],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002974969,0.0015583772,0.001684698,0.000033097844,0.000092227834,4.3416162e-7,0.0003268826,0.000022588058,0.33108565,0.11073351,0.0037741147,0.55065864],"study_design_scores_gemma":[0.0021766245,0.00021817458,0.015710574,0.000007937459,0.0000070081505,0.0000049829723,0.00010678268,0.9680845,0.012629491,0.0003421195,0.0005061508,0.00020564979],"about_ca_topic_score_codex":0.000032445903,"about_ca_topic_score_gemma":0.000016415559,"teacher_disagreement_score":0.9680619,"about_ca_system_score_codex":0.00017025073,"about_ca_system_score_gemma":0.00005456949,"threshold_uncertainty_score":0.566972},"labels":[],"label_agreement":null},{"id":"W2969546362","doi":"10.1177/0894439319869210","title":"Automatic Classification of Open-Ended Questions: Check-All-That-Apply Questions","year":2019,"lang":"en","type":"article","venue":"Social Science Computer Review","topic":"Text and Document Classification Technologies","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":"Western University; University of Waterloo","funders":"","keywords":"Computer science; Bivariate analysis; Code (set theory); Classifier (UML); Artificial intelligence; Natural language processing; Open data; Relevance (law); Information retrieval; Machine learning; Set (abstract data type); World Wide Web","score_opus":0.07185242578354825,"score_gpt":0.36881044594546614,"score_spread":0.29695802016191786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2969546362","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":[0.015490012,0.018100739,0.84120494,0.07102908,0.0035954649,0.008804062,0.000014966772,0.0055775666,0.036183152],"genre_scores_gemma":[0.8972406,0.0040354705,0.09625803,0.0018746781,0.00006743162,0.0002548023,0.000008826033,0.000018747973,0.0002414248],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976001,0.00014133264,0.0005611209,0.0006580826,0.0006878664,0.0003515259],"domain_scores_gemma":[0.9979652,0.000076971555,0.00055317685,0.0010197365,0.00029657598,0.000088336026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015583397,0.00018261334,0.00042984524,0.00021345293,0.00027872142,0.0005171794,0.0049010883,0.00007759828,0.000050102797],"category_scores_gemma":[0.00011183701,0.00016083903,0.00011447104,0.002365608,0.0004653615,0.002184688,0.0012065835,0.00017302825,0.00020841465],"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":[2.8078307e-7,0.00007568184,0.00025795726,0.00023158378,0.0000065606505,2.7516523e-7,0.00014826599,6.5199373e-7,0.0011003781,0.6809048,0.0029700166,0.31430358],"study_design_scores_gemma":[0.0017287056,0.00063793,0.30867413,0.008662897,0.000178823,0.000054493863,0.0004495504,0.13807186,0.003009873,0.14522563,0.3907124,0.0025936854],"about_ca_topic_score_codex":0.000022247963,"about_ca_topic_score_gemma":0.0000018394134,"teacher_disagreement_score":0.8817506,"about_ca_system_score_codex":0.00017103822,"about_ca_system_score_gemma":0.00041578108,"threshold_uncertainty_score":0.9107523},"labels":[],"label_agreement":null},{"id":"W2971394479","doi":"10.1109/codit.2019.8820298","title":"An Improved K-medoids Algorithm Based on Binary Sequences Similarity Measures","year":2019,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"Concordia University","funders":"Agence Nationale de la Recherche","keywords":"Cluster analysis; Computer science; Medoid; Similarity (geometry); Binary number; Euclidean distance; Data mining; k-medoids; Binary data; Algorithm; Fuzzy clustering; CURE data clustering algorithm; Artificial intelligence; Mathematics","score_opus":0.018019523491294175,"score_gpt":0.26179368937266595,"score_spread":0.24377416588137177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2971394479","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":[0.014467809,0.000033251185,0.96103674,0.009730952,0.00050881295,0.00041312643,0.000004926337,0.0026532842,0.011151066],"genre_scores_gemma":[0.8599024,0.000005153259,0.13801728,0.0012613942,0.00001667275,0.000022721095,0.000003976234,0.0000057704283,0.0007646526],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99875975,0.00005545859,0.0001610599,0.00047632473,0.00031820597,0.00022919424],"domain_scores_gemma":[0.998611,0.000069037895,0.00006536342,0.0011161327,0.000071949384,0.00006653186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002982213,0.0001399543,0.0001284561,0.0001590348,0.0000924471,0.00022633161,0.0012892572,0.000106378386,0.00006427953],"category_scores_gemma":[0.000027089563,0.0001064586,0.000049027116,0.00034378035,0.000065442655,0.0007117941,0.00009044887,0.00014273296,0.00018215147],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016798978,0.00049971754,0.0036624514,0.000016597342,0.0000163364,0.000008519503,0.00013395463,0.0004638582,0.043904472,0.11792174,0.0037945183,0.82956105],"study_design_scores_gemma":[0.00032732423,0.0006921973,0.0037017758,0.0000059180315,0.0000020678729,8.852537e-7,0.0000889684,0.94626796,0.034922693,0.0065872073,0.0071516014,0.0002514177],"about_ca_topic_score_codex":0.000043954708,"about_ca_topic_score_gemma":0.0000042537035,"teacher_disagreement_score":0.94580406,"about_ca_system_score_codex":0.000042064712,"about_ca_system_score_gemma":0.00008722297,"threshold_uncertainty_score":0.4341256},"labels":[],"label_agreement":null},{"id":"W2979091142","doi":"10.5539/mas.v13n11p31","title":"Application of Naïve Bayes, Decision Tree, and K-Nearest Neighbors for Automated Text Classification","year":2019,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Naive Bayes classifier; Decision tree; k-nearest neighbors algorithm; Artificial intelligence; Precision and recall; Data mining; Tree (set theory); Process (computing); Arabic; Bayes' theorem; Machine learning; The Internet; Translation (biology); Pattern recognition (psychology); Bayesian probability; Mathematics; Support vector machine; World Wide Web","score_opus":0.012841370283785819,"score_gpt":0.26464840268583656,"score_spread":0.2518070324020507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979091142","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":[0.06252325,0.00004027276,0.9336798,0.0003640086,0.000077903125,0.0007823789,0.000003433037,0.00063922774,0.0018897206],"genre_scores_gemma":[0.91260666,0.0000106847465,0.08712852,0.000046410925,0.0000058027513,0.00013805127,0.000004135278,0.000007137273,0.000052593823],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982244,0.0000072752227,0.00031021296,0.0007410896,0.00045423847,0.0002627903],"domain_scores_gemma":[0.9984378,0.00017217861,0.00024694644,0.0009196653,0.00015493405,0.000068469686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054199056,0.00013285744,0.00017151037,0.00029515603,0.00019034799,0.0001790237,0.0012965611,0.00008836005,0.0000023214193],"category_scores_gemma":[0.000064383,0.00011786668,0.000028299277,0.0009856054,0.00034419357,0.000582686,0.0002640872,0.00006951325,0.00003476748],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010305174,0.000030174206,0.00069728086,0.000011809932,0.0000014616112,2.0448756e-8,0.0001370287,0.000084152234,0.40286142,0.26123622,0.00006481834,0.33486533],"study_design_scores_gemma":[0.00033578457,0.000045141373,0.0346214,0.0000075683524,0.0000026643659,9.2521276e-7,0.000066389795,0.9058512,0.023809714,0.03456743,0.0005575649,0.00013422224],"about_ca_topic_score_codex":0.0000062127315,"about_ca_topic_score_gemma":0.0000034284706,"teacher_disagreement_score":0.905767,"about_ca_system_score_codex":0.00006805326,"about_ca_system_score_gemma":0.000107562744,"threshold_uncertainty_score":0.48064637},"labels":[],"label_agreement":null},{"id":"W2980905101","doi":"10.1016/j.knosys.2019.105066","title":"Granular structure-based incremental updating for multi-label classification","year":2019,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Key Research and Development Program of China; Ministry of Public Security of the People's Republic of China; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Feature (linguistics); Machine learning; Computation; Mechanism (biology); Data mining; Granular computing; Ensemble learning; Incremental learning; Pattern recognition (psychology); Algorithm; Rough set","score_opus":0.059306806226372834,"score_gpt":0.3079401080915744,"score_spread":0.24863330186520158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2980905101","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":[0.054293495,0.0005028704,0.9389976,0.00042818717,0.0018625167,0.002046775,0.000046650304,0.0011848859,0.0006369643],"genre_scores_gemma":[0.93765163,8.2772755e-7,0.061303932,0.00007468453,0.00007311246,0.00031608978,0.00011931015,0.000028868586,0.00043154432],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99778426,0.00014449161,0.0005859334,0.000741267,0.00032174165,0.0004223287],"domain_scores_gemma":[0.9978015,0.00023043505,0.0003919152,0.0011705406,0.00031541538,0.0000902161],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005584362,0.00029164212,0.0003337689,0.00035384955,0.00024952146,0.00039029575,0.0012562599,0.00021290586,0.00001963525],"category_scores_gemma":[0.00010843609,0.0002676797,0.0001131301,0.0005813775,0.000068094494,0.0004196051,0.000090354304,0.0001684273,0.00024963723],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000095410585,0.0011348573,0.046337407,0.0016173405,0.000074714415,0.00000235078,0.00052056735,0.00077192445,0.45530865,0.42157847,0.0058091506,0.06674916],"study_design_scores_gemma":[0.0029891513,0.00015528046,0.0014342178,0.00010468935,0.000012656497,0.0000011010974,0.00023800776,0.9437999,0.042735297,0.00019293018,0.007967291,0.00036945657],"about_ca_topic_score_codex":0.000020653084,"about_ca_topic_score_gemma":0.00001720865,"teacher_disagreement_score":0.943028,"about_ca_system_score_codex":0.00026685258,"about_ca_system_score_gemma":0.00024429304,"threshold_uncertainty_score":0.9999775},"labels":[],"label_agreement":null},{"id":"W2994962128","doi":"10.1007/978-981-15-1922-2_26","title":"Hybrid Machine Learning Models of Classifying Residential Requests for Smart Dispatching","year":2019,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Naive Bayes classifier; Classifier (UML); Perceptron; Word embedding; Cluster analysis; Convolutional neural network; Benchmarking; Artificial neural network; Multilayer perceptron; Embedding; Support vector machine","score_opus":0.0672727803263816,"score_gpt":0.29967899170562595,"score_spread":0.23240621137924433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994962128","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":[0.000083060484,0.00044307119,0.9543816,0.0009681039,0.00023627984,0.0004924823,0.00001832248,0.00016370091,0.043213405],"genre_scores_gemma":[0.5818003,0.00469442,0.4092362,0.00031771476,0.000028416765,0.00006565413,0.00019579957,0.000021234979,0.0036402778],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982836,0.000026949774,0.00078683376,0.0002966615,0.0003962695,0.00020967958],"domain_scores_gemma":[0.9968113,0.00032851266,0.00066668657,0.0017714464,0.0003745619,0.000047524252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011223096,0.00019254007,0.00028852597,0.0010474983,0.000398573,0.00046270422,0.0033293716,0.00010583066,0.0000024637022],"category_scores_gemma":[0.00008555186,0.00019361876,0.00006679618,0.00022947254,0.00053027226,0.0080346465,0.0023331442,0.00042393318,0.000010641746],"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":[0.000002617239,0.0000070605115,0.00006440476,0.00004883917,0.0000042102124,5.6915113e-8,0.00044077577,0.00074662006,0.000012543041,0.8737696,0.00008597284,0.12481732],"study_design_scores_gemma":[0.00026599455,0.000060229067,0.00018251473,0.0002059442,0.0000048791344,0.0000059684726,0.00001539961,0.88439053,0.00008935871,0.07935613,0.03520422,0.00021883332],"about_ca_topic_score_codex":0.00002053027,"about_ca_topic_score_gemma":0.000008261625,"teacher_disagreement_score":0.8836439,"about_ca_system_score_codex":0.00010842535,"about_ca_system_score_gemma":0.00028106206,"threshold_uncertainty_score":0.7895544},"labels":[],"label_agreement":null},{"id":"W2997205428","doi":"10.1609/aaai.v34i04.5822","title":"Nonlinear Mixup: Out-Of-Manifold Data Augmentation for Text Classification","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":81,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Nonlinear system; Mixing (physics); Manifold (fluid mechanics); Computer science; Regularization (linguistics); Scalar (mathematics); Interpolation (computer graphics); Benchmark (surveying); Mathematics; Artificial intelligence; Pattern recognition (psychology); Algorithm; Machine learning","score_opus":0.2956569575793979,"score_gpt":0.36300084100343927,"score_spread":0.06734388342404135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997205428","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":[0.031353723,0.000049340124,0.88381666,0.07606008,0.0008698027,0.0018680226,0.00010631442,0.00049237674,0.005383696],"genre_scores_gemma":[0.97262824,0.00003836573,0.026897095,0.00023477613,0.00005787928,0.00003773192,0.000009349051,0.000009065433,0.00008748028],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998278,0.000009456557,0.00060080073,0.0005517531,0.00036969164,0.00019026123],"domain_scores_gemma":[0.9981022,0.00010927951,0.0006415391,0.00054805813,0.00054439215,0.000054572316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033476995,0.00015705635,0.00020904327,0.00008331267,0.00011694455,0.00016238258,0.003697287,0.00008678984,0.000021872773],"category_scores_gemma":[0.00080690125,0.00012397082,0.00007277098,0.0004992922,0.00016579634,0.0007066545,0.0005505591,0.00014412182,0.00004941087],"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":[0.000046216213,0.000091143425,0.000081012426,0.00005556144,0.0000111957925,2.5982251e-8,0.00082752254,0.000003800869,0.13462147,0.7711114,0.00088696065,0.09226366],"study_design_scores_gemma":[0.000043998098,0.00022864918,0.00011539773,0.000057215108,0.000015448823,2.0860813e-7,0.0011850446,0.26047254,0.6817673,0.054617226,0.0013524736,0.00014453878],"about_ca_topic_score_codex":0.0000058039,"about_ca_topic_score_gemma":0.0000032331393,"teacher_disagreement_score":0.9412745,"about_ca_system_score_codex":0.000023352373,"about_ca_system_score_gemma":0.00008345805,"threshold_uncertainty_score":0.6870541},"labels":[],"label_agreement":null},{"id":"W2997669297","doi":"10.1609/aaai.v34i04.6034","title":"Hierarchically Clustered Representation Learning","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"National Research Foundation of Korea; National Research Foundation","keywords":"Cluster analysis; Embedding; Representation (politics); Feature learning; Artificial intelligence; Computer science; Abstraction; Hierarchy; Focus (optics); Pattern recognition (psychology); Space (punctuation); Hierarchical clustering; Machine learning","score_opus":0.12446907518370981,"score_gpt":0.31134846949460937,"score_spread":0.18687939431089956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997669297","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":[0.17996942,0.000046293477,0.5546765,0.21481405,0.00055262836,0.0011324703,0.0000030033632,0.0016176259,0.047188047],"genre_scores_gemma":[0.9939347,0.000032745593,0.005321213,0.00043982675,0.000036748803,0.000018384326,3.7630986e-7,0.000006623999,0.0002094028],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985246,0.000019001516,0.00041325245,0.00043585288,0.00040078806,0.00020650937],"domain_scores_gemma":[0.99897784,0.00007783066,0.00033458273,0.00021629123,0.00032115105,0.00007232505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001920345,0.00013751735,0.00017297173,0.00007638296,0.00017262007,0.00027199817,0.0020009694,0.000073416006,0.000047793565],"category_scores_gemma":[0.0010329868,0.00010412136,0.00008494287,0.00079663546,0.00020216826,0.00044780405,0.0005097288,0.00036024937,0.00011868737],"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":[0.000026913416,0.000029889577,0.00029923153,0.000012790945,0.000005528343,1.6985574e-7,0.0012363849,0.00005562789,0.05239802,0.78513056,0.00017521919,0.16062966],"study_design_scores_gemma":[0.000029561355,0.00024361552,0.0003520388,0.000050386538,0.0000055226615,0.0000012816474,0.0009552988,0.13245107,0.66681755,0.19829297,0.0006295937,0.00017112271],"about_ca_topic_score_codex":0.000006251417,"about_ca_topic_score_gemma":6.2262217e-7,"teacher_disagreement_score":0.81396526,"about_ca_system_score_codex":0.000019551648,"about_ca_system_score_gemma":0.000046743873,"threshold_uncertainty_score":0.4245946},"labels":[],"label_agreement":null},{"id":"W2998605053","doi":"10.1609/aaai.v34i04.6132","title":"Partial Label Learning with Batch Label Correction","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"China Scholarship Council; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Consistency (knowledge bases); Artificial intelligence; Machine learning; Set (abstract data type); Multi-label classification; Stability (learning theory)","score_opus":0.1001122140207756,"score_gpt":0.2912905940668809,"score_spread":0.19117838004610532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998605053","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":[0.37565985,0.000054408876,0.4983231,0.096530795,0.001373588,0.0012428198,0.0000035452156,0.0022392236,0.024572657],"genre_scores_gemma":[0.99564767,0.000025660283,0.003589393,0.0002927013,0.000048131627,0.000028129514,3.4010674e-7,0.000009615615,0.00035834295],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99849266,0.000014587533,0.0003436798,0.00046380714,0.0004247311,0.00026056118],"domain_scores_gemma":[0.99890774,0.00006181883,0.00034998276,0.00019382162,0.00040850413,0.00007814398],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019670793,0.00018065966,0.00019266007,0.00006815733,0.00022928882,0.0002881696,0.0015125892,0.000082893835,0.00004232773],"category_scores_gemma":[0.0004644689,0.00012606548,0.000041900832,0.0008986824,0.00023178634,0.00050343643,0.00030398,0.00041241583,0.00012578603],"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":[0.000091803806,0.00011202434,0.0008126945,0.000019625646,0.00001346318,4.0061207e-7,0.0015033431,0.00007222029,0.051627457,0.7457023,0.0005376262,0.199507],"study_design_scores_gemma":[0.000055584784,0.0006459429,0.000113075934,0.000081060665,0.000009863948,0.0000025897975,0.0011630473,0.23511957,0.7455462,0.016302891,0.00075246557,0.00020769634],"about_ca_topic_score_codex":0.000014953189,"about_ca_topic_score_gemma":0.000002389584,"teacher_disagreement_score":0.72939944,"about_ca_system_score_codex":0.000028070463,"about_ca_system_score_gemma":0.000071899776,"threshold_uncertainty_score":0.5140801},"labels":[],"label_agreement":null},{"id":"W3008638314","doi":"10.1016/j.ijar.2020.02.003","title":"Label distribution learning: A local collaborative mechanism","year":2020,"lang":"en","type":"article","venue":"International Journal of Approximate Reasoning","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Robustness (evolution); Ambiguity; Computer science; Artificial intelligence; Machine learning; Feature learning; Representation (politics); Pattern recognition (psychology)","score_opus":0.016666892514749204,"score_gpt":0.26690031547458176,"score_spread":0.25023342295983253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008638314","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":[0.0103459,0.00012404805,0.97703636,0.0115612075,0.0002919213,0.000054687192,0.0000051637617,0.00014888553,0.00043182276],"genre_scores_gemma":[0.9514133,0.000105616724,0.04814651,0.00018142251,0.00010676441,0.000003425551,0.000008482189,0.0000061609694,0.000028323459],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99876153,0.000051652285,0.0003484946,0.00016367914,0.00054114044,0.00013352418],"domain_scores_gemma":[0.9985489,0.000058948444,0.00052538386,0.00008756086,0.00069013756,0.000089024776],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025891254,0.00010337548,0.00015424986,0.00007968155,0.00006897705,0.00026760367,0.001056982,0.000058631478,0.000016389808],"category_scores_gemma":[0.0004348961,0.00008991195,0.000059775204,0.00032995248,0.0000495066,0.0007825179,0.0002153074,0.0002862126,0.000017664204],"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":[0.00006606374,0.000060927836,0.00021827458,0.0000057402663,0.000114232265,0.00008520655,0.00097367814,0.00036661894,0.004263502,0.9099582,0.000950666,0.08293691],"study_design_scores_gemma":[0.0032079683,0.0010362036,0.0004256582,0.00024562725,0.000034893183,0.00039279863,0.0034866955,0.73887163,0.13857074,0.057294216,0.055885702,0.0005478908],"about_ca_topic_score_codex":0.0000014433369,"about_ca_topic_score_gemma":1.3052528e-7,"teacher_disagreement_score":0.9410674,"about_ca_system_score_codex":0.000119001095,"about_ca_system_score_gemma":0.00011280192,"threshold_uncertainty_score":0.36665028},"labels":[],"label_agreement":null},{"id":"W3009458272","doi":"10.7717/peerj-cs.261","title":"An evolutionary decomposition-based multi-objective feature selection for multi-label classification","year":2020,"lang":"en","type":"article","venue":"PeerJ Computer Science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Feature selection; Multi-label classification; Artificial intelligence; Feature (linguistics); Data mining; Selection (genetic algorithm); Field (mathematics); Machine learning; Evolutionary algorithm; Genetic algorithm; Pattern recognition (psychology); Optimization problem; Mathematics; Algorithm","score_opus":0.0639818680707189,"score_gpt":0.33944606510245007,"score_spread":0.2754641970317312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009458272","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005797497,0.0000424049,0.9820167,0.009660914,0.0004218147,0.0006151589,0.000009452894,0.0014235985,0.00001245969],"genre_scores_gemma":[0.42757073,0.0000012999687,0.57139003,0.00083974237,0.000074392156,0.00008560067,0.000015060993,0.0000071221893,0.000016048274],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975435,0.00006344998,0.0002605851,0.0011853338,0.00051774905,0.00042939046],"domain_scores_gemma":[0.99814975,0.000098475684,0.00020556043,0.0005769397,0.0007371023,0.00023217981],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037526464,0.00022623067,0.00018369831,0.00030604182,0.0008421026,0.0005839603,0.0021380961,0.00011775975,0.0000031050565],"category_scores_gemma":[0.00011149966,0.00022078388,0.00007169111,0.0019222628,0.00032307298,0.0021671392,0.000189955,0.00020730069,0.000033611064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011228905,0.002148129,0.0129815955,0.00009700658,0.00004045316,0.0000037738848,0.0027788484,0.011152433,0.32101533,0.1287898,0.008124213,0.5127561],"study_design_scores_gemma":[0.00090782443,0.0003928248,0.03554131,0.000009347048,0.000005629405,0.0000043884693,0.000032459167,0.94751763,0.014452702,0.00041045717,0.00045282926,0.00027259218],"about_ca_topic_score_codex":0.000008670199,"about_ca_topic_score_gemma":0.000004649314,"teacher_disagreement_score":0.9363652,"about_ca_system_score_codex":0.00023744634,"about_ca_system_score_gemma":0.00041407353,"threshold_uncertainty_score":0.90033054},"labels":[],"label_agreement":null},{"id":"W3022446017","doi":"10.1007/978-3-030-47358-7_26","title":"Partial Label Learning by Entropy Minimization","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Ground truth; Training set; Minification; Artificial intelligence; Entropy (arrow of time); Machine learning; Set (abstract data type)","score_opus":0.018584185021082743,"score_gpt":0.243421951344673,"score_spread":0.22483776632359026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3022446017","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000021258978,0.00034640013,0.9914219,0.0052897073,0.0007235261,0.00022808778,0.0000026991054,0.00068270706,0.0012837555],"genre_scores_gemma":[0.3386806,0.00029413096,0.65485066,0.0031421632,0.0005736637,0.000033936463,0.00005447821,0.00007217635,0.0022981637],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971055,0.00003009612,0.00041591743,0.0012722587,0.000748235,0.0004280319],"domain_scores_gemma":[0.9984884,0.00020525444,0.0003157522,0.00074956444,0.000121147816,0.00011987923],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025009495,0.00036835822,0.00034360954,0.00037736335,0.00024953837,0.00065410667,0.0026891173,0.0002930983,0.00003161708],"category_scores_gemma":[0.00018481299,0.00035010558,0.000066450215,0.000598119,0.00046331424,0.00061431236,0.0010643763,0.00076419563,0.00011497388],"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":[0.0000052115693,0.00002828916,0.00010836656,0.000018600595,0.000009390855,0.00002113256,0.00040692632,0.0046745287,0.0011129513,0.1334756,0.00063185836,0.85950714],"study_design_scores_gemma":[0.00040231593,0.00026320494,0.000021853812,0.0000980524,0.000007551707,0.000010530705,4.3118095e-7,0.84495157,0.0099986475,0.09799845,0.045552164,0.0006952149],"about_ca_topic_score_codex":0.000003947258,"about_ca_topic_score_gemma":0.0000022743764,"teacher_disagreement_score":0.8588119,"about_ca_system_score_codex":0.00017215182,"about_ca_system_score_gemma":0.00022901727,"threshold_uncertainty_score":0.9998951},"labels":[],"label_agreement":null},{"id":"W3035531049","doi":"10.1145/3397271.3401135","title":"Coding Electronic Health Records with Adversarial Reinforcement Path Generation","year":2020,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"National Natural Science Foundation of China; Tencent","keywords":"Computer science; Coding (social sciences); ENCODE; Reinforcement learning; Path (computing); Encoder; Adversarial system; Artificial intelligence; Computer network","score_opus":0.03366987630125309,"score_gpt":0.2511299121722091,"score_spread":0.217460035870956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035531049","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":[0.0012260298,0.00003228551,0.96338236,0.032705925,0.0000764203,0.00016994483,2.0300075e-7,0.00062281115,0.0017840026],"genre_scores_gemma":[0.9700944,0.00008547462,0.026652671,0.002763337,0.00007430533,0.00001715062,0.000007711222,0.000003834126,0.00030111248],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916685,0.000018216952,0.0001605154,0.0002511878,0.00017983916,0.00022340975],"domain_scores_gemma":[0.99957806,0.000008750967,0.00009326551,0.00023281355,0.000027802369,0.000059289425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011190465,0.00007793978,0.00008713765,0.000035901707,0.000114136026,0.00011030083,0.00034343178,0.000026023712,0.000042861946],"category_scores_gemma":[0.000014328532,0.000059759026,0.000017777164,0.0002728454,0.00001451006,0.00038536542,0.00008208373,0.00008773237,0.000035295554],"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":[0.000010532824,0.000010716843,0.00014705538,0.0000063755188,0.000010573614,7.215258e-7,0.00042970086,0.00032457712,0.0009103816,0.9274075,0.013745807,0.056996047],"study_design_scores_gemma":[0.0015338726,0.0028743292,0.00029890114,0.00001434313,0.0000057297843,0.0000049945947,0.00038407723,0.8636737,0.02365955,0.0017548734,0.10533894,0.00045670164],"about_ca_topic_score_codex":0.00003167209,"about_ca_topic_score_gemma":0.00002091696,"teacher_disagreement_score":0.9688684,"about_ca_system_score_codex":0.00010417924,"about_ca_system_score_gemma":0.0001954531,"threshold_uncertainty_score":0.24369024},"labels":[],"label_agreement":null},{"id":"W3037074101","doi":"10.5539/cis.v13n3p66","title":"Improvements of Automatic Extraction of FA Words Tendency using Non_linear Approach","year":2020,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Field (mathematics); Measure (data warehouse); Subject (documents); Artificial intelligence; Data mining; Natural language processing; Mathematics; World Wide Web","score_opus":0.033079219552338515,"score_gpt":0.2794702536111031,"score_spread":0.2463910340587646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037074101","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":[0.08175416,0.000014962597,0.91708785,0.00020532674,0.00010438649,0.000120843935,0.0000011874637,0.00009559282,0.0006156863],"genre_scores_gemma":[0.76706237,0.000010347164,0.23276672,0.00014742461,0.000008427917,0.0000019080119,9.0108324e-7,8.1581845e-7,0.0000011202452],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896884,0.000008833418,0.00039797652,0.0001396887,0.00037293346,0.00011175277],"domain_scores_gemma":[0.99920446,0.000017791932,0.0003249542,0.00022382714,0.00017563101,0.000053354168],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027976342,0.00006876012,0.00011470494,0.00023062393,0.00008803604,0.00013442888,0.00063465274,0.000028985729,0.00000279619],"category_scores_gemma":[0.000043338034,0.00005842959,0.000022142816,0.001016779,0.00020907342,0.0075734644,0.00030755872,0.00005541608,0.000003243738],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000045059037,0.00006811717,0.001449164,0.00030741378,0.000009197658,1.2239558e-7,0.006872103,0.0011438176,0.02542253,0.08977058,0.00011213621,0.8748403],"study_design_scores_gemma":[0.00015837103,0.000079339385,0.0048231017,0.000011949808,0.0000018386133,0.0000026722516,0.00017996888,0.9806283,0.013598178,0.00020799333,0.00024403908,0.00006423936],"about_ca_topic_score_codex":0.000003291,"about_ca_topic_score_gemma":1.2522631e-8,"teacher_disagreement_score":0.9794845,"about_ca_system_score_codex":0.00001577711,"about_ca_system_score_gemma":0.000085238134,"threshold_uncertainty_score":0.5490579},"labels":[],"label_agreement":null},{"id":"W3037796656","doi":"10.1007/978-3-030-51517-1_31","title":"Machine Learning Classification Models with SPD/ED Dataset: Comparative Study of Abstract Versus Full Article Approach","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","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":"Université de Moncton","funders":"","keywords":"Computer science; Artificial intelligence; Boosting (machine learning); Machine learning; Support vector machine; Decision tree; Gradient boosting; Random forest; Precision and recall; Context (archaeology); Recall","score_opus":0.08655538543899494,"score_gpt":0.2932814416779184,"score_spread":0.20672605623892348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037796656","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":[0.0014075912,0.00015006923,0.99490976,0.00031571498,0.00016195513,0.0006531386,0.000021305688,0.0002551182,0.0021253293],"genre_scores_gemma":[0.86965585,0.000013565326,0.13014364,0.00004283415,0.000034291654,0.000017576016,0.000060576087,0.000014265298,0.000017379229],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968578,0.00004110898,0.0005255762,0.0013216123,0.0009314745,0.00032240557],"domain_scores_gemma":[0.9976259,0.00029016702,0.0005703946,0.0012388149,0.00017632174,0.00009838948],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00039198168,0.00039579588,0.0005191397,0.0004214283,0.00020540641,0.0003111706,0.0025961376,0.00015574538,0.00000817896],"category_scores_gemma":[0.000037206268,0.00032183455,0.000044673867,0.0007040375,0.00054228125,0.0008911062,0.0007839472,0.0008434749,0.000019135126],"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":[0.00043271575,0.0009026081,0.00028196082,0.00009909643,0.00013786896,0.000043672597,0.008813753,0.57726514,0.0013876801,0.14781484,0.00007454087,0.2627461],"study_design_scores_gemma":[0.0009800227,0.001153482,0.00026355643,0.00004501841,0.000017091246,0.000005781003,0.000026932623,0.9863724,0.00065760815,0.009910262,0.00017203014,0.00039582254],"about_ca_topic_score_codex":0.000028522425,"about_ca_topic_score_gemma":0.000044561126,"teacher_disagreement_score":0.8682483,"about_ca_system_score_codex":0.00013555965,"about_ca_system_score_gemma":0.00019312535,"threshold_uncertainty_score":0.99992335},"labels":[],"label_agreement":null},{"id":"W3085586451","doi":"10.5281/zenodo.3993874","title":"Multi-label Pathway Prediction based on Active Dataset Subsampling","year":2020,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Text and Document Classification Technologies","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":"University of British Columbia","funders":"","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology)","score_opus":0.0849203007829528,"score_gpt":0.2799977735206358,"score_spread":0.195077472737683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3085586451","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000042886595,0.000012856253,0.086491756,0.00094108534,0.00021056458,0.0004883004,0.9095118,0.001926752,0.00041259237],"genre_scores_gemma":[0.00035228438,0.00007350104,0.0040158895,0.00039027326,0.00010287304,2.7983654e-7,0.9945873,0.00043377068,0.00004385379],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972971,0.00029811842,0.00035652425,0.0010063249,0.0006511496,0.0003907973],"domain_scores_gemma":[0.99751294,0.000067825225,0.00030423756,0.0016250481,0.00030433503,0.0001856371],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00039598238,0.00030170384,0.00023943764,0.0004947011,0.0016771845,0.0015787347,0.004161377,0.00019116103,0.0014298238],"category_scores_gemma":[0.001116289,0.00031227164,0.00005599091,0.00089467247,0.00014776112,0.0005320784,0.0023484097,0.0007763964,0.015022356],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030566312,0.00022896758,6.7703425e-8,0.000053756816,0.000023359613,0.0000138886935,0.00004822587,0.000026936275,0.00024125513,0.00048202398,0.93348855,0.065362394],"study_design_scores_gemma":[0.00061869354,0.00039514285,0.00002818205,0.000049004153,0.000013024234,0.000009673514,0.00004249991,0.01767688,0.00037401007,0.000055119457,0.9804662,0.00027158012],"about_ca_topic_score_codex":0.000010346334,"about_ca_topic_score_gemma":3.389466e-7,"teacher_disagreement_score":0.085075475,"about_ca_system_score_codex":0.00024302855,"about_ca_system_score_gemma":0.000016444536,"threshold_uncertainty_score":0.99993294},"labels":[],"label_agreement":null},{"id":"W3086863200","doi":"10.1002/ett.3977","title":"Digital Hadith authentication: Recent advances, open challenges, and future directions","year":2020,"lang":"en","type":"article","venue":"Transactions on Emerging Telecommunications Technologies","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Northern British Columbia","funders":"Deanship of Scientific Research, King Saud University","keywords":"Authentication (law); Islam; Computer science; Field (mathematics); Legislation; Task (project management); Computer security; Political science; Law; History; Engineering; Systems engineering; Mathematics; Archaeology","score_opus":0.04322460988914023,"score_gpt":0.2839163424881219,"score_spread":0.2406917325989817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3086863200","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000664896,0.04576434,0.3035754,0.6325813,0.00017700408,0.00069096044,0.000032941152,0.008055569,0.00905601],"genre_scores_gemma":[0.23328044,0.6377399,0.12733684,0.00044152295,0.000029664316,0.0007777677,0.000022897639,0.000035897552,0.00033509132],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985072,0.000048790735,0.0003676384,0.00060896523,0.00019149864,0.00027591272],"domain_scores_gemma":[0.99748564,0.00013421963,0.00017094823,0.0020142659,0.00012085765,0.00007408549],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012403878,0.00024511386,0.00023776578,0.0003071878,0.00082653307,0.00037793702,0.0036862402,0.00017325174,0.00003436268],"category_scores_gemma":[0.00008974242,0.00023804931,0.00005824344,0.0012454115,0.00027165198,0.0020032502,0.0003110984,0.0005428162,0.00006700899],"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":[0.000004672271,0.00013038603,0.0000049448213,0.000008809824,0.000027951746,3.5827446e-7,0.00056412176,0.0000116201945,0.000028849654,0.08633071,0.00027329815,0.9126143],"study_design_scores_gemma":[0.0002509614,0.00012871892,0.00020539176,0.000017532207,0.000014158981,0.000008652756,0.0038292017,0.0016739039,0.00088907767,0.010530719,0.98216504,0.00028661801],"about_ca_topic_score_codex":0.000002131314,"about_ca_topic_score_gemma":0.000013032417,"teacher_disagreement_score":0.98189175,"about_ca_system_score_codex":0.000072307506,"about_ca_system_score_gemma":0.0000529771,"threshold_uncertainty_score":0.9707369},"labels":[],"label_agreement":null},{"id":"W3093607642","doi":"10.18280/ria.340418","title":"Text Sentiment Classification Based on Feature Fusion","year":2020,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Social Science Fund of China; National Science Foundation","keywords":"Softmax function; Computer science; Artificial intelligence; Convolutional neural network; Classifier (UML); Pattern recognition (psychology); Deep learning; Sentiment analysis; Artificial neural network; Feature (linguistics); Natural language processing; Machine learning","score_opus":0.05547955289847228,"score_gpt":0.27746885442471153,"score_spread":0.22198930152623925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3093607642","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":[0.0018468746,0.0000720339,0.9037543,0.08533414,0.00022670947,0.0003004663,0.0000024573924,0.0007751184,0.0076879286],"genre_scores_gemma":[0.98439866,0.000033098375,0.012252586,0.0020089326,0.00006140787,0.00003944445,0.000011636002,0.000011678009,0.001182581],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984682,0.00004989918,0.00029190493,0.00063387497,0.00029477265,0.00026133482],"domain_scores_gemma":[0.998677,0.000105358944,0.0001510477,0.000861921,0.00008341493,0.00012121495],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00016894193,0.00017793228,0.00015328919,0.00012264046,0.00018846683,0.00019781046,0.0010471086,0.00011815429,0.00015875117],"category_scores_gemma":[0.00012917204,0.00016297001,0.000096619144,0.00087364006,0.00006498042,0.00025540564,0.00014866836,0.00024052412,0.001937593],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051304996,0.0004487031,0.0004987963,0.000076673234,0.000014242379,0.00001906031,0.0016830557,0.022671303,0.065870754,0.3333889,0.036699302,0.5385779],"study_design_scores_gemma":[0.0000399682,0.00015539514,0.00020710328,0.000026902382,0.0000032262842,0.0000011845019,0.00028449885,0.8219402,0.12965767,0.0009764728,0.046535727,0.00017167295],"about_ca_topic_score_codex":0.0000017015866,"about_ca_topic_score_gemma":4.5931262e-7,"teacher_disagreement_score":0.98255175,"about_ca_system_score_codex":0.00005953669,"about_ca_system_score_gemma":0.000040000137,"threshold_uncertainty_score":0.9988395},"labels":[],"label_agreement":null},{"id":"W3095042565","doi":"10.1007/978-3-030-63128-4_52","title":"Binary Text Representation for Feature Selection","year":2020,"lang":"en","type":"book-chapter","venue":"Advances in intelligent systems and computing","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Redundancy (engineering); Feature selection; Computer science; Binary number; Relevance (law); Minimum redundancy feature selection; Mutual information; Selection (genetic algorithm); Representation (politics); Feature (linguistics); Filter (signal processing); Artificial intelligence; Binary classification; Data mining; Machine learning; Pattern recognition (psychology); Mathematics; Support vector machine","score_opus":0.03133614524783514,"score_gpt":0.2986975766940242,"score_spread":0.26736143144618907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095042565","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":[0.000030439596,0.020784829,0.95061713,0.00074709975,0.0012348744,0.0009450293,0.000006235769,0.0004737476,0.02516063],"genre_scores_gemma":[0.7319133,0.016484471,0.095693134,0.000502296,0.0018523274,0.00030177258,0.00022345276,0.00019887138,0.15283038],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985129,0.000018852388,0.0004427076,0.00066070876,0.00018454788,0.00018027618],"domain_scores_gemma":[0.99897826,0.00021161945,0.00041828526,0.00026252813,0.000088159475,0.000041164694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015745599,0.00024157247,0.00035016597,0.00021808194,0.00013724114,0.00019584385,0.0004137841,0.0002126071,0.0000017636746],"category_scores_gemma":[0.000043121257,0.00023268705,0.00007282606,0.0001323412,0.00004469114,0.0003900174,0.00020144391,0.00027614387,0.000010941033],"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":[0.0000069353064,0.0000064214223,0.00014163725,0.00016314464,0.000014565558,0.0000029026344,0.00014959587,0.001342855,0.000028917033,0.78012645,0.00073232513,0.21728428],"study_design_scores_gemma":[0.00025174316,0.00029344088,0.00006890617,0.0008241672,0.000016955397,0.000029834046,0.0003003884,0.2796368,0.00049223535,0.07060572,0.64685494,0.0006248682],"about_ca_topic_score_codex":0.000007908388,"about_ca_topic_score_gemma":0.0000051293896,"teacher_disagreement_score":0.85492396,"about_ca_system_score_codex":0.000088288245,"about_ca_system_score_gemma":0.000025585867,"threshold_uncertainty_score":0.94887024},"labels":[],"label_agreement":null},{"id":"W310827894","doi":"","title":"Identification of Web Information using Concept Hierarchies and On-line Updates of Concept Importance","year":2009,"lang":"en","type":"article","venue":"European Society for Fuzzy Logic and Technology Conference","topic":"Text and Document Classification Technologies","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":"University of Alberta","funders":"","keywords":"Hierarchy; Computer science; Identification (biology); Domain (mathematical analysis); Information retrieval; Ontology; Semantic Web; Web page; The Internet; Term (time); Social Semantic Web; World Wide Web; Mathematics","score_opus":0.030330483356404314,"score_gpt":0.26653893821362384,"score_spread":0.23620845485721953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W310827894","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":[0.41187087,0.0013494294,0.5749643,0.008748289,0.000111969006,0.0006664276,0.00007240963,0.0007283415,0.0014879567],"genre_scores_gemma":[0.9781868,0.00029835952,0.021305945,0.00015470192,0.0000066654657,0.0000043426126,0.000012975762,0.0000030657861,0.000027188335],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990548,0.000019912679,0.00043816675,0.00023737631,0.0001023352,0.00014740293],"domain_scores_gemma":[0.9988792,0.000052298063,0.00047543962,0.0003535224,0.00021719662,0.000022333268],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023814963,0.00012592663,0.00020281148,0.000121339865,0.000117682335,0.000051803312,0.0004622955,0.00010140146,0.0000015124186],"category_scores_gemma":[0.00012113521,0.000110346205,0.00005351374,0.0003394316,0.0007539278,0.0004494853,0.00013343716,0.000119728225,8.3249165e-7],"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":[0.000004778101,0.00002930406,0.0003965935,0.000019336361,0.000016279386,2.1820424e-7,0.0005934458,0.000012473159,0.012021242,0.8851217,0.00021107857,0.10157356],"study_design_scores_gemma":[0.0031156745,0.0025435162,0.010838104,0.0001769978,0.00007628138,0.000029206189,0.0064531197,0.068282686,0.17915373,0.7249801,0.0034894876,0.00086111546],"about_ca_topic_score_codex":5.265727e-7,"about_ca_topic_score_gemma":1.210534e-7,"teacher_disagreement_score":0.5663159,"about_ca_system_score_codex":0.000010649149,"about_ca_system_score_gemma":0.000037794547,"threshold_uncertainty_score":0.44997877},"labels":[],"label_agreement":null},{"id":"W3108841339","doi":"10.1109/tcyb.2020.3032707","title":"Semisupervised Learning via Axiomatic Fuzzy Set Theory and SVM","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Cybernetics","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Interpretability; Artificial intelligence; Computer science; Support vector machine; Machine learning; Fuzzy logic; Exploit; Classifier (UML); Schema (genetic algorithms); Set (abstract data type); Frame (networking); Natural language processing; Data mining","score_opus":0.022938232563160438,"score_gpt":0.2413329743429583,"score_spread":0.21839474177979787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3108841339","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":[0.021011788,0.00008165748,0.97418046,0.0029818658,0.00011781522,0.0001302255,0.0000024144708,0.0007974752,0.00069630565],"genre_scores_gemma":[0.99057853,0.000114442584,0.008356292,0.00046991537,0.000013419476,0.00001973454,8.8854165e-7,0.000012467888,0.00043431207],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990218,0.0000982978,0.0001927418,0.00031627537,0.00019050376,0.00018035187],"domain_scores_gemma":[0.99929893,0.00021314775,0.000055275068,0.00029699254,0.00003153354,0.00010413894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014273095,0.00014350734,0.00013419727,0.00008448449,0.00017413676,0.00013351032,0.0004151625,0.00009183195,0.00004718242],"category_scores_gemma":[0.000019841671,0.00013727335,0.000049348324,0.00035060584,0.00008893931,0.00020686607,0.0000070164633,0.00028248268,0.00013251742],"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":[0.000070973634,0.0002259532,0.00014079205,0.0001679169,0.00013627054,0.00002129558,0.012841294,0.0076571037,0.03441811,0.07390473,0.00071781507,0.86969775],"study_design_scores_gemma":[0.002748051,0.0016863712,0.0013429067,0.00012752757,0.00016011132,0.00007195514,0.002995345,0.5963575,0.30413428,0.07650633,0.012194307,0.0016752571],"about_ca_topic_score_codex":0.0000033470337,"about_ca_topic_score_gemma":0.0000015445046,"teacher_disagreement_score":0.96956676,"about_ca_system_score_codex":0.000019410389,"about_ca_system_score_gemma":0.000019620487,"threshold_uncertainty_score":0.5597845},"labels":[],"label_agreement":null},{"id":"W3109675915","doi":"10.1109/iccit-144147971.2020.9213733","title":"Performance Comparison of Qur’anic Search Engines","year":2020,"lang":"en","type":"article","venue":"2020 International Conference on Computing and Information Technology (ICCIT-1441)","topic":"Text and Document Classification Technologies","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":"University of Northern British Columbia","funders":"","keywords":"Computer science; Arabic; The Internet; Meaning (existential); Reading (process); Search engine; Information retrieval; Islam; World Wide Web; Natural language processing; Linguistics; History","score_opus":0.04188735145897918,"score_gpt":0.30084940025285617,"score_spread":0.25896204879387696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3109675915","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":[0.53452086,0.00008929737,0.3887132,0.06196853,0.00059268303,0.00036113994,0.000015888032,0.0017482007,0.0119901905],"genre_scores_gemma":[0.9899313,0.00016738988,0.009319926,0.00047358926,0.000034651643,0.000008652921,0.000023768944,0.0000050492154,0.000035689973],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983972,0.000024008905,0.0006507507,0.0002888425,0.0004120788,0.00022711909],"domain_scores_gemma":[0.9987664,0.00006925216,0.0003651503,0.0003206098,0.00041183768,0.00006672241],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001934962,0.00019154779,0.00027356073,0.00046663664,0.0001541445,0.00018401549,0.0013967542,0.00019034192,0.00004983609],"category_scores_gemma":[0.00019122464,0.00018297439,0.000045929308,0.0007086093,0.00018018374,0.0013361269,0.000582464,0.00042991887,0.00013341672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002586427,0.000043661385,0.007495851,0.00005553238,0.00003867365,6.5556077e-7,0.0012982789,0.0004299688,0.0016629734,0.6683208,0.0008761543,0.3197516],"study_design_scores_gemma":[0.000480332,0.00037709094,0.0023310839,0.000071014314,0.000004169957,0.000007977496,0.0011117656,0.96908516,0.020408062,0.0012203528,0.004688087,0.00021491264],"about_ca_topic_score_codex":0.0000044485664,"about_ca_topic_score_gemma":4.2022242e-7,"teacher_disagreement_score":0.96865517,"about_ca_system_score_codex":0.0000387499,"about_ca_system_score_gemma":0.00008161011,"threshold_uncertainty_score":0.74614793},"labels":[],"label_agreement":null},{"id":"W3109677655","doi":"10.1109/tfuzz.2020.3036848","title":"Editorial: Fuzzy Logic and Artificial Intelligence: A Special Issue on Emerging Techniques and Their Applications","year":2020,"lang":"en","type":"editorial","venue":"IEEE Transactions on Fuzzy Systems","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Taiwan University of Science and Technology; National Taiwan University; Universidad de Granada; University of Alberta","keywords":"Fuzzy logic; Computer science; Artificial intelligence","score_opus":0.02130487360459542,"score_gpt":0.27736873287886427,"score_spread":0.25606385927426883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3109677655","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.086471e-7,0.00019485387,0.38993397,0.0010485455,0.6050017,0.0009468891,0.00013501082,0.0011126517,0.0016257487],"genre_scores_gemma":[0.0026409028,0.0009029151,0.0010793746,0.000028997467,0.9936657,0.001182948,0.000023316392,0.000051694842,0.00042417875],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99674714,0.00013862866,0.0007508039,0.0012188097,0.0007632573,0.00038134004],"domain_scores_gemma":[0.9976348,0.00065014104,0.00037517038,0.00093449344,0.00023471752,0.000170659],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00039622356,0.00057978794,0.0006400206,0.000562911,0.0005570751,0.00085396017,0.0010758444,0.0010860396,0.000009036491],"category_scores_gemma":[0.000041376872,0.0005072433,0.0001347148,0.0007182306,0.00022866964,0.000348314,0.000023717985,0.001332732,0.00012588112],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033071312,0.000104102815,6.3073784e-8,0.00012958668,0.000052100477,0.0000029030437,0.00037964925,0.000035966717,0.000096115946,0.01319327,0.7291507,0.25682247],"study_design_scores_gemma":[0.00008418576,0.00038936373,6.355233e-8,0.0001381033,0.000029097333,0.0000048593015,0.0005284851,0.00036114966,0.0027123392,0.011123044,0.98414004,0.0004892471],"about_ca_topic_score_codex":0.000053364412,"about_ca_topic_score_gemma":0.000013425865,"teacher_disagreement_score":0.38885462,"about_ca_system_score_codex":0.00016649043,"about_ca_system_score_gemma":0.00016105213,"threshold_uncertainty_score":0.9997379},"labels":[],"label_agreement":null},{"id":"W3110889378","doi":"10.1109/smc42975.2020.9283208","title":"Binary Hybrid Differential Evolution Algorithm for Multi-label Feature Selection","year":2020,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"Ontario Tech University","funders":"","keywords":"Feature selection; Computer science; Artificial intelligence; Feature (linguistics); Metaheuristic; Differential evolution; Machine learning; Pattern recognition (psychology); Field (mathematics); Selection (genetic algorithm); Algorithm; Data mining; Mathematics","score_opus":0.04131484145864265,"score_gpt":0.2767897758277696,"score_spread":0.23547493436912695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3110889378","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016801382,0.00005211046,0.98737144,0.008941991,0.00021859126,0.00026886593,0.00000523804,0.0014085831,0.000053014523],"genre_scores_gemma":[0.2600159,0.0000075297157,0.7381976,0.00026800705,0.00008932646,0.000064586464,0.000014535026,0.0000071601517,0.0013352943],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992383,0.000014334063,0.00010956808,0.00034034537,0.00012427034,0.00017316357],"domain_scores_gemma":[0.99963653,0.00001878266,0.00005769856,0.00016114449,0.000073068164,0.000052748488],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000033574604,0.00010431363,0.0000945004,0.000065554545,0.00014348584,0.00011204834,0.00043056256,0.00006628089,0.000015665522],"category_scores_gemma":[0.000032139655,0.00008947521,0.000047252117,0.00028839367,0.000026266713,0.00042519715,0.00012816607,0.000102480175,0.00003731885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009621255,0.00015544219,0.00016004173,0.000014726765,0.000021367408,0.0000010212744,0.0000734836,0.000004793135,0.028093943,0.065616354,0.047288034,0.85856116],"study_design_scores_gemma":[0.0006179656,0.00017866348,0.0009886009,0.0000020610746,0.000004948141,0.0000024816593,0.00002500885,0.97326326,0.020380627,0.0009992402,0.003412811,0.00012432829],"about_ca_topic_score_codex":0.000004012282,"about_ca_topic_score_gemma":9.914033e-7,"teacher_disagreement_score":0.9732585,"about_ca_system_score_codex":0.000049512106,"about_ca_system_score_gemma":0.000028808685,"threshold_uncertainty_score":0.3648693},"labels":[],"label_agreement":null},{"id":"W3117033303","doi":"10.5539/elt.v14n1p74","title":"A Methodological Review of Machine Learning in Applied Linguistics","year":2020,"lang":"en","type":"review","venue":"English Language Teaching","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Software; Applied linguistics; Artificial intelligence; Computational linguistics; Normality; Natural language processing; Machine learning; Linguistics; Programming language; Mathematics; Statistics","score_opus":0.10015196501792106,"score_gpt":0.38367126546512764,"score_spread":0.2835193004472066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3117033303","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":[1.3399253e-7,0.96137804,0.023276176,0.000050250037,0.00023019886,0.00048184162,0.000005561598,0.0009075944,0.013670179],"genre_scores_gemma":[0.00007933637,0.911731,0.08770799,0.00009949718,0.00017251393,0.00006542508,0.00005477178,0.000024773384,0.00006466084],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968099,0.001063436,0.00095436507,0.0006042465,0.00029991567,0.0002681514],"domain_scores_gemma":[0.9970518,0.0014106027,0.00074330246,0.0007038356,0.000030675703,0.00005977871],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0026703628,0.00036093374,0.0019654185,0.00028152796,0.000055970948,0.00006561095,0.0017639007,0.00026398402,0.000025434805],"category_scores_gemma":[0.031731788,0.00028307748,0.00030066207,0.00067025755,0.000044073367,0.000045768178,0.0007649005,0.002234206,0.000016348346],"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":[4.1774712e-7,0.000022451453,0.0000010767986,0.023597173,0.000017665074,0.00003012339,0.0019629258,5.070841e-7,7.356025e-7,0.04990823,0.000098228345,0.92436045],"study_design_scores_gemma":[0.00007561204,0.000026792612,1.2148486e-7,0.022794068,0.00006678934,0.0000030958192,0.0002446541,0.00012417627,0.0000047057647,0.00012245172,0.976268,0.0002695297],"about_ca_topic_score_codex":0.000012151034,"about_ca_topic_score_gemma":0.0000011942531,"teacher_disagreement_score":0.97616976,"about_ca_system_score_codex":0.00009246558,"about_ca_system_score_gemma":0.000110274195,"threshold_uncertainty_score":0.99996215},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W3121217868","doi":"10.1016/j.is.2021.101718","title":"Multi-label legal document classification: A deep learning-based approach with label-attention and domain-specific pre-training","year":2021,"lang":"en","type":"article","venue":"Information Systems","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thomson Reuters (Canada)","funders":"","keywords":"Computer science; Artificial intelligence; Multi-label classification; Domain (mathematical analysis); Training (meteorology); Machine learning; Training set","score_opus":0.03582749930198761,"score_gpt":0.2545681606306928,"score_spread":0.2187406613287052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3121217868","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":[0.014680444,0.00037036775,0.9808335,0.00080717984,0.00021198542,0.00045598924,0.0000021544095,0.0007042507,0.0019341431],"genre_scores_gemma":[0.843629,0.000034998513,0.1554356,0.00008078929,0.000026344238,0.00026816866,0.00009810821,0.000008532191,0.00041845182],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99819386,0.00012043306,0.00057619,0.00033077187,0.00051423424,0.0002645055],"domain_scores_gemma":[0.99850684,0.000056033823,0.00045828774,0.0005418338,0.00035455136,0.000082459774],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00047992865,0.00019650903,0.0002139572,0.0002374666,0.0003335836,0.0015643698,0.00037753017,0.00012743063,0.000004134928],"category_scores_gemma":[0.000023464372,0.00016947235,0.000029243301,0.0006576794,0.000088719506,0.0031151464,0.00009989538,0.00021799435,0.000055845656],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005427674,0.00029507396,0.0032399087,0.00044538672,0.00010709319,0.0000107400965,0.009492532,0.0043999227,0.003346255,0.7562264,0.00051761343,0.22186475],"study_design_scores_gemma":[0.0038622809,0.00019335999,0.012470156,0.00014050356,0.000013001074,0.00015973118,0.015612348,0.7643647,0.0003320122,0.00011696398,0.20217083,0.0005641083],"about_ca_topic_score_codex":0.000008880105,"about_ca_topic_score_gemma":0.0000029814391,"teacher_disagreement_score":0.82894856,"about_ca_system_score_codex":0.00012042632,"about_ca_system_score_gemma":0.000113254144,"threshold_uncertainty_score":0.9994721},"labels":[],"label_agreement":null},{"id":"W3153416049","doi":"10.1007/s13042-021-01291-y","title":"A novel binary many-objective feature selection algorithm for multi-label data classification","year":2021,"lang":"en","type":"article","venue":"International Journal of Machine Learning and Cybernetics","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Feature selection; Computer science; Multi-label classification; Feature (linguistics); Pattern recognition (psychology); Artificial intelligence; Computational intelligence; Data mining; Computational complexity theory; Binary number; Benchmarking; Binary classification; Selection (genetic algorithm); Machine learning; Algorithm; Mathematics; Support vector machine","score_opus":0.05021316710036461,"score_gpt":0.3376043278010533,"score_spread":0.2873911607006887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3153416049","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022507985,0.0010605847,0.9908525,0.005152518,0.0004706122,0.00005891377,0.000024063303,0.00006366579,0.00006637818],"genre_scores_gemma":[0.11565643,0.00065961934,0.88118815,0.00012333016,0.000193067,0.0000045116553,0.00010938484,0.000012085991,0.0020533956],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990086,0.000047927504,0.00026136593,0.0002583561,0.00031418088,0.000109590466],"domain_scores_gemma":[0.99848324,0.00013361473,0.00039622604,0.00016765716,0.0007756263,0.000043606706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033033697,0.000105404695,0.00013077879,0.00016557012,0.00010152489,0.0002493367,0.00075823657,0.000087805216,0.000005095152],"category_scores_gemma":[0.0004036388,0.000096023294,0.000041635914,0.0001720226,0.00003790356,0.0004422852,0.00030706832,0.0003859866,0.0000017776651],"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":[0.000023437733,0.00030566417,0.0027631212,0.0000069738244,0.0001687753,0.00001411073,0.00023661568,0.00007565556,0.012351882,0.012819663,0.00094565935,0.97028846],"study_design_scores_gemma":[0.0012595957,0.00015205439,0.006831858,0.000035094974,0.000022338494,0.00038496873,0.00018899553,0.9630537,0.0014524113,0.00061995577,0.025887066,0.00011193573],"about_ca_topic_score_codex":0.000007514911,"about_ca_topic_score_gemma":0.0000061788724,"teacher_disagreement_score":0.9701765,"about_ca_system_score_codex":0.000059326307,"about_ca_system_score_gemma":0.00009949885,"threshold_uncertainty_score":0.3915716},"labels":[],"label_agreement":null},{"id":"W3160128317","doi":"10.3233/jifs-210336","title":"From granulation-degranulation mechanisms to fuzzy rule-based models: Augmentation of granular-based models with a double fuzzy clustering","year":2021,"lang":"en","type":"article","venue":"Journal of Intelligent & Fuzzy Systems","topic":"Text and Document Classification Technologies","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":"University of Alberta","funders":"","keywords":"Granulation; Degranulation; Cluster analysis; Fuzzy logic; Data mining; Fuzzy clustering; Computer science; Granular computing; Artificial intelligence; Mathematics; Engineering; Chemistry; Rough set","score_opus":0.048718047028115774,"score_gpt":0.27044402099357323,"score_spread":0.22172597396545746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160128317","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":[0.04951477,0.00052390917,0.94663596,0.0013113342,0.0008238534,0.00055389135,0.000017480226,0.00014977716,0.00046901146],"genre_scores_gemma":[0.87368166,0.000023716624,0.12591608,0.00012290968,0.00009441774,0.000044547003,0.000035555324,0.000027987096,0.000053134376],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960999,0.00019044231,0.0015515647,0.0004989822,0.0013142803,0.00034481756],"domain_scores_gemma":[0.99607337,0.00019195185,0.0013702011,0.0008491731,0.0013228504,0.00019248099],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007988868,0.00033940643,0.0006817522,0.0007325861,0.00015186575,0.00043934834,0.000953431,0.00017974003,0.0000098396085],"category_scores_gemma":[0.000034803048,0.0002871278,0.00025262043,0.0010501638,0.00004677099,0.0013646405,0.00010566614,0.00025528693,0.000011759097],"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":[0.00044430324,0.00023373666,0.00019012865,0.00012042559,0.00009109556,0.000027630598,0.0009447788,0.91133386,0.014993121,0.067040496,0.00013504262,0.0044453954],"study_design_scores_gemma":[0.0025364377,0.00048749777,0.00015124404,0.0008312115,0.00009552635,0.00003077631,0.0015814251,0.7741119,0.12295711,0.09669349,0.00010066657,0.000422681],"about_ca_topic_score_codex":0.0002928188,"about_ca_topic_score_gemma":0.00005533083,"teacher_disagreement_score":0.8241669,"about_ca_system_score_codex":0.00032076825,"about_ca_system_score_gemma":0.00039486095,"threshold_uncertainty_score":0.9999581},"labels":[],"label_agreement":null},{"id":"W3165295356","doi":"10.48550/arxiv.2105.12364","title":"Basic and Depression Specific Emotion Identification in Tweets: Multi-label Classification Experiments","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Identification (biology); Depression (economics); Multi-label classification; Psychology; Emotion classification; Computer science; Cognitive psychology; Artificial intelligence; Biology; Economics","score_opus":0.1548741197765774,"score_gpt":0.24150600543745362,"score_spread":0.08663188566087623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3165295356","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":[0.53342575,0.0003946804,0.46496546,0.0001432822,0.0003952488,0.0002857479,0.0000026706105,0.0002761681,0.00011095861],"genre_scores_gemma":[0.9917513,0.001615257,0.0060193283,0.00002005078,0.000022674198,0.000009772573,0.00006921033,0.000014886096,0.00047753146],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99757636,0.00017346109,0.00037203523,0.0014893622,0.00013218664,0.00025658435],"domain_scores_gemma":[0.99786824,0.00005300845,0.00041658134,0.0014161783,0.00016371113,0.00008226764],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027142998,0.00028201737,0.00026470356,0.0005413005,0.00015188195,0.00040889168,0.0011037871,0.00040059088,0.000013991198],"category_scores_gemma":[0.000056881945,0.00033964706,0.00006757924,0.0007658821,0.0001164105,0.0010616609,0.0012766509,0.000428462,0.00003327286],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013481974,0.0039511663,0.24304035,0.0005629371,0.00021032032,0.00042411295,0.006900047,0.0077152736,0.12182166,0.36688095,0.001170994,0.24718738],"study_design_scores_gemma":[0.0015242405,0.000023857572,0.27319002,0.0002527715,0.000024030776,0.0000037860882,0.0024349783,0.7015421,0.012020926,0.008123592,0.00017966959,0.0006800633],"about_ca_topic_score_codex":0.000042425338,"about_ca_topic_score_gemma":0.00002098641,"teacher_disagreement_score":0.6938268,"about_ca_system_score_codex":0.00034234938,"about_ca_system_score_gemma":0.00007751733,"threshold_uncertainty_score":0.9999055},"labels":[],"label_agreement":null},{"id":"W3176185023","doi":"10.1609/aaai.v35i12.17264","title":"Adversarial Partial Multi-Label Learning with Label Disambiguation","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Text and Document Classification Technologies","field":"Computer Science","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":"Carleton University","funders":"China Scholarship Council; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Artificial intelligence; Machine learning; Feature (linguistics); Encoder; Minimax; Generative adversarial network; Feature vector; Adversarial system; Deep learning; Pattern recognition (psychology); Mathematics","score_opus":0.1163529464583123,"score_gpt":0.3151711112700287,"score_spread":0.19881816481171644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176185023","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":[0.30445293,0.000063430045,0.66626066,0.019140683,0.00094010076,0.00069456716,0.0000048827856,0.0008400093,0.0076027587],"genre_scores_gemma":[0.97547746,0.00003268821,0.023583593,0.0000898899,0.000039990726,0.00003237016,0.0000012443007,0.000009598521,0.0007331548],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99830437,0.000023577064,0.0003902352,0.00050990307,0.0004855984,0.00028631455],"domain_scores_gemma":[0.9984859,0.00006956291,0.0003642217,0.00030144033,0.00072376867,0.00005509768],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027698945,0.0001876937,0.00020018635,0.00008590614,0.0002744646,0.00035134458,0.0012288534,0.00009977919,0.000048818416],"category_scores_gemma":[0.00064599136,0.00013663077,0.000052040505,0.000814484,0.00026409753,0.00059368,0.0003741348,0.0003448763,0.00007303154],"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":[0.000044779797,0.00024866685,0.00050237327,0.0000141610735,0.000015021634,8.245527e-7,0.0006942032,0.000039607374,0.06533845,0.76845604,0.000043122945,0.16460274],"study_design_scores_gemma":[0.00012745742,0.00021684563,0.00023994074,0.000106704014,0.000014471455,0.0000041426692,0.0011564563,0.19049065,0.7783468,0.028877212,0.00020441775,0.00021494132],"about_ca_topic_score_codex":0.000016916536,"about_ca_topic_score_gemma":0.000013490618,"teacher_disagreement_score":0.73957884,"about_ca_system_score_codex":0.000045344237,"about_ca_system_score_gemma":0.00015440836,"threshold_uncertainty_score":0.55716413},"labels":[],"label_agreement":null},{"id":"W3180937499","doi":"10.5220/0011532400003318","title":"Multi-label Emotion Classification using Machine Learning and Deep Learning Methods","year":2022,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Laurentian University","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Deep learning","score_opus":0.08875717388121936,"score_gpt":0.36689611242939263,"score_spread":0.2781389385481733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3180937499","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021132408,0.0004417565,0.97607565,0.00081039255,0.00012618992,0.00011873276,2.2763341e-7,0.0009607818,0.00033385592],"genre_scores_gemma":[0.36224675,0.00005808289,0.63647956,0.00004016599,0.0000061315172,0.000019792446,0.00000539499,0.0000076219994,0.0011364949],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985934,0.00040997317,0.00021248405,0.000399804,0.00019646487,0.0001878616],"domain_scores_gemma":[0.9994083,0.000111969755,0.00017392267,0.00022548225,0.000041249234,0.00003908054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00083172816,0.00011249472,0.0001163849,0.00022510086,0.0008952693,0.00017392011,0.0003779633,0.00004553962,0.00008434969],"category_scores_gemma":[0.00016314867,0.00011204451,0.000025351135,0.0005315236,0.00004491182,0.0004427155,0.0006314642,0.00042418632,0.0000065953022],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029530172,0.00006519622,0.009608019,0.000006584248,0.0000098231785,0.0000010768565,0.00054795627,0.00041426066,0.110727005,0.033381402,0.0000065218437,0.8452292],"study_design_scores_gemma":[0.00029458507,0.00006983409,0.0027805779,0.000001668651,0.0000051823577,0.000016134583,0.0011274174,0.98558885,0.0018234412,0.0007083668,0.007442958,0.0001409574],"about_ca_topic_score_codex":0.00003398403,"about_ca_topic_score_gemma":0.0000028035308,"teacher_disagreement_score":0.9851746,"about_ca_system_score_codex":0.00010221664,"about_ca_system_score_gemma":0.000017574725,"threshold_uncertainty_score":0.6885778},"labels":[],"label_agreement":null},{"id":"W3194282644","doi":"10.1186/s10033-021-00598-9","title":"ML-ANet: A Transfer Learning Approach Using Adaptation Network for Multi-label Image Classification in Autonomous Driving","year":2021,"lang":"en","type":"article","venue":"Chinese Journal of Mechanical Engineering","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Shenzhen Fundamental Research and Discipline Layout project; National Natural Science Foundation of China","keywords":"Reproducing kernel Hilbert space; Artificial intelligence; Computer science; Pattern recognition (psychology); Transfer of learning; Kernel (algebra); Embedding; Image (mathematics); Domain adaptation; Feature (linguistics); Adaptation (eye); Matching (statistics); Mathematics; Hilbert space; Statistics","score_opus":0.04901093335217047,"score_gpt":0.28099182056678207,"score_spread":0.2319808872146116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3194282644","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":[0.08756585,0.0002688186,0.9114491,0.00021378718,0.0002697309,0.00011557289,3.5247928e-7,0.00010956825,0.000007271689],"genre_scores_gemma":[0.50915027,0.000021600357,0.49072692,0.000008173273,0.000064719745,0.000006997091,0.0000018662876,0.000011432862,0.000008017878],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986568,0.00005708219,0.0005886953,0.00023809761,0.00020368237,0.00025562398],"domain_scores_gemma":[0.9992186,0.00018388663,0.00015871604,0.00019352521,0.00017702924,0.00006827673],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082138245,0.00016291681,0.00030138504,0.00019381427,0.00007364069,0.00013993995,0.0004100465,0.00012271108,0.000002170147],"category_scores_gemma":[0.00068020343,0.00014289122,0.0001139283,0.00065058446,0.000009771564,0.00068378256,0.00006253903,0.00042972527,6.268866e-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":[0.0000136330245,0.00019395196,0.00022771682,0.000072842224,0.000041481922,0.00001974484,0.000494451,0.68130076,0.2494347,0.03212643,0.0000066416146,0.036067627],"study_design_scores_gemma":[0.00083787553,0.000046743986,0.0009509714,0.000073174335,0.000011196061,0.000065264125,0.00010507343,0.99508065,0.0019098434,0.0007086266,0.000062496576,0.00014806919],"about_ca_topic_score_codex":0.0000014206994,"about_ca_topic_score_gemma":0.0000025410363,"teacher_disagreement_score":0.42158443,"about_ca_system_score_codex":0.00013338667,"about_ca_system_score_gemma":0.00009779524,"threshold_uncertainty_score":0.58269346},"labels":[],"label_agreement":null},{"id":"W3195874243","doi":"10.3390/bdcc5030035","title":"Deep Neural Network and Boosting Based Hybrid Quality Ranking for e-Commerce Product Search","year":2021,"lang":"en","type":"article","venue":"Big Data and Cognitive Computing","topic":"Text and Document Classification Technologies","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":"Université du Québec à Chicoutimi","funders":"","keywords":"Computer science; Search engine; Ranking (information retrieval); Metric (unit); Product (mathematics); Information retrieval; Quality (philosophy); Context (archaeology); Machine learning; Artificial intelligence; Artificial neural network; Data mining; Task (project management); Boosting (machine learning); Mathematics; Engineering","score_opus":0.17758062056518018,"score_gpt":0.35664461575547407,"score_spread":0.1790639951902939,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3195874243","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":[0.10335762,0.0016996025,0.8924614,0.0017325457,0.00019481774,0.00023296685,0.000025716827,0.0001986752,0.00009662895],"genre_scores_gemma":[0.9588913,0.0000176946,0.040070217,0.0006033543,0.00020672532,0.000006372985,0.00018405495,0.000008095451,0.000012195118],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99823225,0.00017549952,0.00026337215,0.0008129736,0.00016728544,0.00034864768],"domain_scores_gemma":[0.9977229,0.0013297233,0.0001155718,0.0005401736,0.00023483696,0.000056797635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010390255,0.00014192295,0.00019754705,0.000050657054,0.00056402077,0.00047209486,0.0005268959,0.000029074215,0.0000011513617],"category_scores_gemma":[0.0009996016,0.0001417884,0.000023935949,0.00029064386,0.00010685905,0.00034841953,0.0016729303,0.0001609378,0.0000010192149],"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":[0.000009980824,0.000020270665,0.008699242,0.000056675814,0.000015111256,0.0000062394593,0.000096626565,0.000025737598,0.00018364702,0.0017429197,0.000093469724,0.9890501],"study_design_scores_gemma":[0.0008662064,0.000040003073,0.03769672,0.0001352674,0.000023825169,0.000028392404,0.00045723392,0.9555669,0.0029097076,0.0011529203,0.00083551154,0.0002873477],"about_ca_topic_score_codex":0.000009121321,"about_ca_topic_score_gemma":0.0000072953717,"teacher_disagreement_score":0.98876274,"about_ca_system_score_codex":0.000008177275,"about_ca_system_score_gemma":0.000058944283,"threshold_uncertainty_score":0.5781963},"labels":[],"label_agreement":null},{"id":"W3210819377","doi":"10.1109/tai.2021.3120043","title":"Smoothed Generalized Dirichlet: A Novel Count-Data Model for Detecting Emotional States","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Artificial Intelligence","topic":"Text and Document Classification Technologies","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":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Dirichlet distribution; Burstiness; Count data; Generalized Dirichlet distribution; Mathematics; Computer science; Hierarchical Dirichlet process; Applied mathematics; Multinomial distribution; Cluster analysis; Algorithm; Artificial intelligence; Statistics; Dirichlet series; Mathematical analysis","score_opus":0.16196338292156895,"score_gpt":0.3418206002684397,"score_spread":0.17985721734687074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210819377","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":[0.0023307418,0.000043720174,0.993204,0.0028597133,0.00059676607,0.00025273702,0.00017697903,0.0004976603,0.000037682643],"genre_scores_gemma":[0.75774825,0.00007272398,0.24109998,0.00037544474,0.000037417827,0.00010508965,0.000022389739,0.00001817873,0.0005205391],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981257,0.000030722396,0.00046124385,0.00073926896,0.00031413222,0.00032898123],"domain_scores_gemma":[0.9981057,0.00026907603,0.00011976298,0.0011493433,0.00028703068,0.000069101734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003005511,0.00019066132,0.00018388782,0.00016405189,0.0004425633,0.00031847256,0.0011560862,0.00010814515,0.00005481763],"category_scores_gemma":[0.000068988,0.00019482542,0.00010618953,0.00060396164,0.000097165845,0.00060141046,0.000018313758,0.00020234383,0.000059094444],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057914127,0.00067015446,0.000001491736,0.000024445862,0.0000666517,0.00000335289,0.0006848649,0.3582894,0.054111473,0.13384795,0.00025377233,0.45198855],"study_design_scores_gemma":[0.000050478222,0.000027576718,0.0000015277361,0.000012297405,0.000009773199,0.000004565909,0.00013245556,0.6841832,0.28675273,0.028282173,0.00038718505,0.00015605886],"about_ca_topic_score_codex":0.000020046466,"about_ca_topic_score_gemma":0.00018553216,"teacher_disagreement_score":0.75541747,"about_ca_system_score_codex":0.00007753112,"about_ca_system_score_gemma":0.00019176642,"threshold_uncertainty_score":0.794475},"labels":[],"label_agreement":null},{"id":"W4205732624","doi":"10.1007/s40747-021-00611-7","title":"Semi-supervised multi-label classification using an extended graph-based manifold regularization","year":2022,"lang":"en","type":"article","venue":"Complex & Intelligent Systems","topic":"Text and Document Classification Technologies","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":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; China Scholarship Council","keywords":"Semi-supervised learning; Artificial intelligence; Weighting; Regularization (linguistics); Pattern recognition (psychology); Graph; Labeled data; Manifold alignment; Benchmark (surveying); Computer science; Multi-label classification; Supervised learning; Manifold (fluid mechanics); Extension (predicate logic); Machine learning; Mathematics; Algorithm; Nonlinear dimensionality reduction; Artificial neural network; Theoretical computer science; Dimensionality reduction","score_opus":0.19632244367245735,"score_gpt":0.3285660267384981,"score_spread":0.13224358306604075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205732624","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":[0.014099576,0.00029853277,0.98169637,0.00043519255,0.0009959377,0.0009093734,0.000019088295,0.0013441792,0.00020176849],"genre_scores_gemma":[0.96369714,0.000008909532,0.03505534,0.00016142923,0.00004996698,0.0002884674,0.00019887177,0.000033357708,0.0005065043],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996841,0.0004439248,0.00073951116,0.00086154154,0.0007091802,0.00040483163],"domain_scores_gemma":[0.99751693,0.00006496399,0.0004531744,0.0016195986,0.00022266318,0.00012264556],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00065164006,0.0002886196,0.00030147147,0.0005680967,0.00083860767,0.00048576374,0.0021575983,0.00010367181,0.0000979076],"category_scores_gemma":[0.00003905642,0.00030725688,0.00010363054,0.0012307212,0.000076091004,0.00061829586,0.00040996686,0.00024575533,0.000041663585],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004257046,0.002232732,0.0018517007,0.00015510198,0.00008657636,0.000018142433,0.0011077676,0.020821473,0.2309478,0.7093817,0.002089107,0.031265315],"study_design_scores_gemma":[0.00044141177,0.00015595595,0.0011446957,0.000020762569,0.000014357628,0.000019282148,0.0012698009,0.9864131,0.003921017,0.0016553287,0.004580026,0.00036422844],"about_ca_topic_score_codex":0.00008532679,"about_ca_topic_score_gemma":0.000008265909,"teacher_disagreement_score":0.96559167,"about_ca_system_score_codex":0.0004274813,"about_ca_system_score_gemma":0.0001200805,"threshold_uncertainty_score":0.99993795},"labels":[],"label_agreement":null},{"id":"W4206897013","doi":"10.1109/dasa53625.2021.9682402","title":"A Moroccan News Articles Dataset (MNAD) For Arabic Text Categorization","year":2021,"lang":"en","type":"article","venue":"2021 International Conference on Decision Aid Sciences and Application (DASA)","topic":"Text and Document Classification Technologies","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":"Université du Québec à Chicoutimi","funders":"","keywords":"Computer science; Artificial intelligence; Natural language processing; Support vector machine; Naive Bayes classifier; Confusion matrix; Categorization; Context (archaeology); Arabic; Random forest; Gradient boosting; Confusion; Machine learning; Linguistics; Geography","score_opus":0.06935459005021938,"score_gpt":0.3509310044313946,"score_spread":0.2815764143811752,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206897013","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":[0.013933868,0.000080001635,0.95377326,0.029188454,0.00029776111,0.00029787055,0.0001254003,0.000097594944,0.002205808],"genre_scores_gemma":[0.94632083,0.0004675199,0.05107859,0.00096742285,0.00006872504,0.00020753323,0.0002880091,0.000006195503,0.0005951638],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980342,0.000031547923,0.00035640755,0.00080460485,0.0005665286,0.00020671639],"domain_scores_gemma":[0.99858993,0.00023129626,0.00020227954,0.00052031386,0.00036241187,0.000093794246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003532027,0.00015098415,0.0001463048,0.00020482705,0.0003432708,0.00092826196,0.0011255915,0.00007257625,0.00022417775],"category_scores_gemma":[0.00028957514,0.00013063752,0.00004384591,0.0006612779,0.00017658494,0.0007609808,0.0002828519,0.00009065665,0.00010689546],"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":[0.000010052203,0.00005784464,0.00033528436,0.0000020688155,0.0000048510697,7.176464e-7,0.000040137846,0.00008056823,0.0037924433,0.663856,0.005283009,0.326537],"study_design_scores_gemma":[0.00088290515,0.00016269491,0.0021057702,0.000041288276,0.000007656895,0.000017246519,0.0009003715,0.48406205,0.014661274,0.30424288,0.19254822,0.00036765562],"about_ca_topic_score_codex":0.000021659413,"about_ca_topic_score_gemma":0.000051770305,"teacher_disagreement_score":0.932387,"about_ca_system_score_codex":0.000044167846,"about_ca_system_score_gemma":0.00016955983,"threshold_uncertainty_score":0.89512515},"labels":[],"label_agreement":null},{"id":"W4211256381","doi":"10.1109/access.2022.3151048","title":"MLCM: Multi-Label Confusion Matrix","year":2022,"lang":"en","type":"article","venue":"IEEE Access","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":409,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; Vector Institute; McMaster University","funders":"Ministère de la Défense Nationale","keywords":"Computer science; Confusion; Confusion matrix; Artificial intelligence; Classifier (UML); Class (philosophy); Ambiguity; Machine learning; Programming language","score_opus":0.08270770067299012,"score_gpt":0.36757054662201094,"score_spread":0.28486284594902084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211256381","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":[0.12761466,0.0003526577,0.85797435,0.007166324,0.0023157822,0.00038597788,0.0000101004825,0.0021175721,0.0020625538],"genre_scores_gemma":[0.9831483,0.000022327744,0.013728443,0.0004697015,0.000022372846,0.00011434758,0.0000029837188,0.0000070826454,0.0024844427],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904716,0.00004016093,0.000157127,0.00030003066,0.00027214483,0.00018335033],"domain_scores_gemma":[0.9992073,0.00003875991,0.0001002456,0.0005852787,0.00003546053,0.000032937747],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015672228,0.00008557954,0.00009010234,0.00014398542,0.00034515368,0.00028369325,0.0025739188,0.00003113496,0.0002112564],"category_scores_gemma":[0.000017599046,0.000082232684,0.00002815927,0.0005314158,0.000033989563,0.0007091648,0.0010876023,0.00016135383,0.00008706904],"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":[0.000019198524,0.00076082937,0.005156224,0.000027337224,0.000030149702,0.00005734683,0.00074851257,0.00040890113,0.038533367,0.19867784,0.09197998,0.6636003],"study_design_scores_gemma":[0.004623064,0.00040844257,0.015125191,0.000018385668,0.000021782498,0.000069484166,0.00057342503,0.51438564,0.12835573,0.034270443,0.30067432,0.0014741069],"about_ca_topic_score_codex":0.00003165556,"about_ca_topic_score_gemma":0.0000026889225,"teacher_disagreement_score":0.85553366,"about_ca_system_score_codex":0.000053966472,"about_ca_system_score_gemma":0.000039452243,"threshold_uncertainty_score":0.47830242},"labels":[],"label_agreement":null},{"id":"W4213112533","doi":"10.3758/s13428-022-01801-y","title":"Machine learning to detect invalid text responses: Validation and comparison to existing detection methods","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Natural language processing; Artificial intelligence; Coding (social sciences); Word (group theory); Machine learning; Code (set theory); Quality (philosophy); Information retrieval; Linguistics; Statistics","score_opus":0.421437191862916,"score_gpt":0.5856823952146699,"score_spread":0.1642452033517539,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213112533","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11762687,0.00022184236,0.87911755,0.0011783997,0.00019457252,0.00089472247,0.0000032327853,0.00057422306,0.00018858953],"genre_scores_gemma":[0.3259832,0.0000086726495,0.67180336,0.00003296527,0.000014233938,0.0011677729,0.0000027276924,0.00001921232,0.0009678506],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.98662406,0.0105249155,0.00047195688,0.00087304873,0.00090858527,0.00059740845],"domain_scores_gemma":[0.9960991,0.0024801071,0.0001304137,0.00081301614,0.00023128538,0.0002460471],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.022758607,0.00018515177,0.00028483922,0.0015162235,0.0016540632,0.0005400796,0.001253708,0.000079806916,0.00007271101],"category_scores_gemma":[0.0065024476,0.00019430261,0.000056872355,0.0031227013,0.00008473345,0.0003389998,0.0029649267,0.0011505609,0.000025611334],"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":[0.000046855792,0.000032360185,0.0010421448,0.000006853205,0.0000034235234,0.0000036520003,0.0010968142,0.00012470201,0.27026817,0.0007376681,0.000046255413,0.7265911],"study_design_scores_gemma":[0.00037417686,0.0017904832,0.013482491,0.000017407137,0.000015007157,0.000054232885,0.0031304164,0.020734888,0.8468761,0.0029430813,0.11010959,0.00047215473],"about_ca_topic_score_codex":0.0002259169,"about_ca_topic_score_gemma":0.000011922558,"teacher_disagreement_score":0.7261189,"about_ca_system_score_codex":0.0003834141,"about_ca_system_score_gemma":0.00008714058,"threshold_uncertainty_score":0.99964565},"labels":[],"label_agreement":null},{"id":"W4224262247","doi":"10.1007/s42488-022-00066-6","title":"Classifying multi-level product categories using dynamic masking and transformer models","year":2022,"lang":"en","type":"article","venue":"Journal of Data Information and Management","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Categorization; Transformer; Generalizability theory; Machine learning; Artificial intelligence; Product (mathematics); Deep learning; Natural language processing; Engineering; Mathematics","score_opus":0.14411948755080517,"score_gpt":0.3142199106093222,"score_spread":0.17010042305851703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224262247","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":[0.0025015553,0.00026791517,0.99509966,0.001615929,0.00014051808,0.0001475074,0.0000138825935,0.000033618973,0.00017938706],"genre_scores_gemma":[0.76040715,0.0011532768,0.23813035,0.0002118782,0.0000061040055,0.0000060631487,0.000022606304,0.000002909227,0.000059681883],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991726,0.000016403037,0.00036346752,0.00009465605,0.0002545564,0.00009829424],"domain_scores_gemma":[0.99934596,0.000008105779,0.0003015316,0.00027781233,0.000039991522,0.000026589427],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000533114,0.00006901592,0.00009055549,0.00030609054,0.00025741366,0.0002718616,0.00059728866,0.000011207602,0.0000034190723],"category_scores_gemma":[0.0000067779183,0.00005987774,0.000013249442,0.00018489806,0.000026992408,0.0077679064,0.00059783825,0.00011514899,4.432483e-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":[0.000011097774,0.000031340365,0.00005407081,0.0001206807,0.000053022595,0.000003486318,0.0017044029,0.0028817235,0.000060081675,0.068819635,0.00059328426,0.92566717],"study_design_scores_gemma":[0.0007201938,0.00004732531,0.0012895464,0.000019319705,0.000027301703,0.00009829992,0.004671457,0.939689,0.000046484533,0.0025492806,0.05070797,0.0001338607],"about_ca_topic_score_codex":0.000003988587,"about_ca_topic_score_gemma":0.0000016743522,"teacher_disagreement_score":0.9368072,"about_ca_system_score_codex":0.00005056345,"about_ca_system_score_gemma":0.000025525453,"threshold_uncertainty_score":0.56315446},"labels":[],"label_agreement":null},{"id":"W4225401927","doi":"10.32473/flairs.v35i.130667","title":"Integration of Multivariate Beta-based Hidden Markov Models and Support Vector Machines with Medical Applications","year":2022,"lang":"en","type":"article","venue":"Proceedings of the ... International Florida Artificial Intelligence Research Society Conference","topic":"Text and Document Classification Technologies","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":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hidden Markov model; Discriminative model; Support vector machine; Artificial intelligence; Computer science; Fisher kernel; Pattern recognition (psychology); Kernel (algebra); Generative model; Machine learning; Multivariate statistics; Decision boundary; Kernel method; Generative grammar; Mathematics; Kernel Fisher discriminant analysis","score_opus":0.11285070093023435,"score_gpt":0.3615773986869301,"score_spread":0.24872669775669576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225401927","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":[0.06164354,0.000058041092,0.8946281,0.037837267,0.0003371715,0.0013217255,0.000064910884,0.00020416222,0.003905063],"genre_scores_gemma":[0.980639,0.000048336708,0.018542757,0.00006423431,0.000041669115,0.00041590715,0.000007669147,0.00000852583,0.00023192227],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967593,0.000036307116,0.00047615843,0.00043695714,0.0020435348,0.00024775564],"domain_scores_gemma":[0.9974758,0.00036837065,0.00029621023,0.00025749113,0.0015261347,0.00007599542],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017322456,0.00013819382,0.000182102,0.00016270345,0.0003985953,0.00018875496,0.0029574158,0.000071446084,0.00015742399],"category_scores_gemma":[0.00034209568,0.00010172864,0.00010445317,0.00087815087,0.0006705998,0.0005244341,0.0012873429,0.00057661755,0.0000021451065],"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":[0.000045025092,0.00012725046,0.00027350767,0.000028302096,0.00003959802,1.9499781e-7,0.0010972697,0.000072236944,0.021775952,0.9019112,0.00030306107,0.0743264],"study_design_scores_gemma":[0.00008659988,0.00019363014,0.00031783938,0.000066094064,0.000008637675,0.0000055728483,0.002588348,0.66946346,0.18361858,0.14297073,0.0005275344,0.00015301774],"about_ca_topic_score_codex":0.00012144764,"about_ca_topic_score_gemma":0.000013960568,"teacher_disagreement_score":0.91899544,"about_ca_system_score_codex":0.00013166423,"about_ca_system_score_gemma":0.00043766867,"threshold_uncertainty_score":0.5495663},"labels":[],"label_agreement":null},{"id":"W4235920966","doi":"10.1007/978-1-4939-7131-2_101098","title":"Social Classification","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science","score_opus":0.069286367992859,"score_gpt":0.28920243843250193,"score_spread":0.21991607043964292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235920966","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000012204381,0.000036573332,0.13343006,0.0048308494,0.00018071481,0.00010622949,0.000001343353,0.0013242519,0.86008877],"genre_scores_gemma":[0.0034658974,0.000039057297,0.008358987,0.00022483818,0.00021038586,0.000012038698,0.000013937913,0.000016334427,0.9876585],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989198,0.0000048647908,0.00022924785,0.0004402755,0.00026301414,0.00014280908],"domain_scores_gemma":[0.9989421,0.000021389325,0.00020792132,0.00068328826,0.00011753091,0.000027776561],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00008838192,0.00018446587,0.00015868168,0.00017428867,0.00014448658,0.00018037333,0.0012065482,0.00038136545,0.0011688393],"category_scores_gemma":[0.00000920846,0.00016592871,0.00009307911,0.000044835295,0.0001639242,0.0002442233,0.0002738158,0.00016942523,0.004048915],"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":[3.858946e-7,0.0000032057108,6.193466e-7,0.000002449969,0.0000075035964,4.3207032e-7,0.000037721322,2.149206e-9,0.000023816572,0.79967326,0.1512416,0.049009],"study_design_scores_gemma":[0.00003688208,0.00001768368,0.000042594103,0.0000043428267,0.0000036713107,9.856085e-7,0.0000057871316,0.00015335811,0.0001124581,0.38449883,0.6149723,0.00015112184],"about_ca_topic_score_codex":5.952286e-7,"about_ca_topic_score_gemma":0.0000017927133,"teacher_disagreement_score":0.46373066,"about_ca_system_score_codex":0.000068586916,"about_ca_system_score_gemma":0.000056060424,"threshold_uncertainty_score":0.99974424},"labels":[],"label_agreement":null},{"id":"W4236164787","doi":"10.1016/s1365-6937(09)70136-4","title":"Alfa Laval AB, Sweden","year":2009,"lang":"en","type":"article","venue":"Filtration Industry Analyst","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Natural language processing; Knowledge base; Artificial intelligence; Sentence; Leverage (statistics); Text processing; Information retrieval; Task (project management); Set (abstract data type); Text graph; Question answering; Ranking (information retrieval); Noisy text analytics; Text mining","score_opus":0.027229634078762832,"score_gpt":0.2810259457960668,"score_spread":0.253796311717304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236164787","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":[0.116151564,0.00024176545,0.69620323,0.09793506,0.0006959302,0.000462989,0.000012357618,0.0037123056,0.084584825],"genre_scores_gemma":[0.99267673,0.000010796857,0.004223208,0.00053710537,0.00009181299,0.000008473022,0.000016630409,0.0000024937228,0.0024327533],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9990263,0.00003338418,0.00024079744,0.0002850373,0.00023795679,0.00017654075],"domain_scores_gemma":[0.99917454,0.000023520457,0.00012123652,0.0005555953,0.000065648186,0.000059485494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015027817,0.00010737532,0.00011004715,0.00015323258,0.00015182074,0.00027004778,0.0006878226,0.00027345886,0.00014105724],"category_scores_gemma":[0.00006245142,0.00009942199,0.000054523334,0.0006935246,0.00003118744,0.000803886,0.00003669134,0.00033613047,0.00014704865],"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":[0.0000066257753,0.00021896251,0.011045537,0.000004770153,0.00004620647,0.000018698784,0.0003253338,0.00042064904,0.017101593,0.65556514,0.15255111,0.16269535],"study_design_scores_gemma":[0.0015159313,0.0006664844,0.40463954,0.00007154529,0.00008109485,0.00008425225,0.0011253257,0.050910097,0.22106092,0.092947036,0.22514632,0.0017514612],"about_ca_topic_score_codex":0.000009813517,"about_ca_topic_score_gemma":0.0000040315585,"teacher_disagreement_score":0.87652516,"about_ca_system_score_codex":0.00003289261,"about_ca_system_score_gemma":0.000058554997,"threshold_uncertainty_score":0.4054311},"labels":[],"label_agreement":null},{"id":"W4238938492","doi":"10.31436/iiumej.v22i2.2108","title":"Editorial","year":2021,"lang":"en","type":"editorial","venue":"IIUM Engineering Journal","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Islam; Malay; Engineering; Library science; Management; Theology; Philosophy; Computer science","score_opus":0.00472315591617843,"score_gpt":0.21937804233084546,"score_spread":0.21465488641466704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4238938492","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.917498e-7,0.00064948265,0.2558571,0.00026542228,0.74262655,0.000028362607,0.0000039990514,0.0004652954,0.000103060906],"genre_scores_gemma":[0.000019713578,0.00041408418,0.021348968,0.000005406481,0.9774498,0.000009098728,0.000015091622,0.000028508888,0.0007093743],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99771756,0.00002298493,0.00038413575,0.0003454733,0.0011560371,0.0003738262],"domain_scores_gemma":[0.99828744,0.000288527,0.00022374242,0.0006473318,0.0004262657,0.00012669506],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00039720497,0.00027576156,0.00031200517,0.00029203517,0.000117488366,0.0012365212,0.001910918,0.00083028816,0.000024675383],"category_scores_gemma":[0.0014077012,0.0002658454,0.00017700151,0.0003330418,0.000017193377,0.00051050045,0.00036444052,0.002211699,0.00004783409],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.8940976e-7,0.000012820489,3.7216648e-7,0.000017080978,0.00003212449,0.00003089372,0.000023408402,0.00022146986,0.00015014409,0.0010567073,0.99650145,0.0019526548],"study_design_scores_gemma":[0.00021795782,0.000033499255,0.000001657303,0.000085997635,0.000009959819,0.000019892615,0.0000048901884,0.0010529651,0.00019616327,0.0002516565,0.99784076,0.0002845962],"about_ca_topic_score_codex":0.0000014652178,"about_ca_topic_score_gemma":2.474588e-7,"teacher_disagreement_score":0.23482318,"about_ca_system_score_codex":0.00020410158,"about_ca_system_score_gemma":0.0005348864,"threshold_uncertainty_score":0.9999794},"labels":[],"label_agreement":null},{"id":"W4242574039","doi":"10.1007/978-1-4614-6170-8_100825","title":"Friend Recommender System","year":2014,"lang":"en","type":"book-chapter","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Recommender system; Computer science; World Wide Web","score_opus":0.024773685038852206,"score_gpt":0.22016842015434493,"score_spread":0.1953947351154927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4242574039","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.8982444e-8,0.00006949639,0.41295883,0.001836026,0.00032579602,0.00007781773,9.625658e-7,0.0015015231,0.5832295],"genre_scores_gemma":[0.0044448967,0.00003145347,0.017323937,0.00022161294,0.00006609021,0.000013530058,0.0000062698923,0.000019453732,0.9778727],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988526,0.000008143707,0.00027444388,0.00046962607,0.00022665037,0.00016852916],"domain_scores_gemma":[0.9983986,0.000042957316,0.00019487992,0.001255358,0.000058138292,0.00005005837],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00013775575,0.00022495839,0.00024407808,0.0001831256,0.000077882076,0.0001769098,0.0013391469,0.00031416683,0.00027972253],"category_scores_gemma":[0.0000074241248,0.0001850907,0.000095824245,0.000030215593,0.000045343055,0.00012540277,0.00039997522,0.00021083678,0.0021279098],"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":[2.2836356e-7,0.0000012747703,4.2785598e-7,0.00001603069,0.000010807081,0.000001671188,0.000009862489,1.02334354e-7,0.000001336956,0.8549697,0.08632098,0.058667593],"study_design_scores_gemma":[0.0000634522,0.000024886042,0.0000016168192,0.000043060878,0.0000053099634,0.000008526218,0.0000146253315,0.00066543656,0.00008017801,0.057763867,0.9410906,0.00023843149],"about_ca_topic_score_codex":0.0000023113857,"about_ca_topic_score_gemma":0.0000017559772,"teacher_disagreement_score":0.85476965,"about_ca_system_score_codex":0.00009003834,"about_ca_system_score_gemma":0.000028650304,"threshold_uncertainty_score":0.99864906},"labels":[],"label_agreement":null},{"id":"W4245584151","doi":"10.1145/564437.564438","title":"Using self-supervised word segmentation in Chinese information retrieval","year":2002,"lang":"en","type":"article","venue":"Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '02","topic":"Text and Document Classification Technologies","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 Waterloo","funders":"","keywords":"Computer science; Artificial intelligence; Character (mathematics); Word (group theory); Text segmentation; Natural language processing; Segmentation; Pattern recognition (psychology)","score_opus":0.08421405815381645,"score_gpt":0.335416479760529,"score_spread":0.2512024216067126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245584151","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":[0.98730004,0.000026103042,0.0013604473,0.0034844717,0.0003356652,0.00091365085,0.000023685705,0.00015973132,0.006396198],"genre_scores_gemma":[0.9817844,0.0001998213,0.017649809,0.00016741414,0.000019378796,0.00003254889,0.00001956539,0.0000055404053,0.000121513425],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965603,0.000029472441,0.0010319153,0.00026863723,0.0016832227,0.00042650494],"domain_scores_gemma":[0.9974813,0.00018177196,0.00044535688,0.00024278364,0.0015475496,0.00010123312],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013012263,0.00023582272,0.0002274276,0.0015487502,0.00022164136,0.00075212773,0.0019287401,0.000171137,0.00007671304],"category_scores_gemma":[0.0019218791,0.00018584881,0.000040254865,0.001822111,0.00015230129,0.00794639,0.00092787837,0.0005530443,0.000062353145],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022616677,0.0017556574,0.2520891,0.0009855743,0.00022719752,0.0000048128977,0.094635844,0.00039325946,0.008719482,0.4273816,0.004664174,0.20688161],"study_design_scores_gemma":[0.009402172,0.0011578896,0.27412143,0.0012758862,0.000009326386,0.000044286404,0.019790286,0.53513324,0.09578827,0.050983377,0.010483654,0.0018101395],"about_ca_topic_score_codex":0.000022301225,"about_ca_topic_score_gemma":0.0000032857,"teacher_disagreement_score":0.53474003,"about_ca_system_score_codex":0.00045159124,"about_ca_system_score_gemma":0.00019294048,"threshold_uncertainty_score":0.7578695},"labels":[],"label_agreement":null},{"id":"W4245642361","doi":"10.1109/ideas.2007.4318085","title":"An Approach for Text Categorization in Digital Library","year":2007,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"Concordia University","funders":"","keywords":"Categorization; Computer science; Hierarchy; Text categorization; Information retrieval; Digital library; Document classification; Library classification; Artificial intelligence; World Wide Web","score_opus":0.016244597061944043,"score_gpt":0.2479245301932853,"score_spread":0.23167993313134128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245642361","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":[0.005092622,0.000009881316,0.97706425,0.00034771248,0.00002991736,0.00014382794,0.0000010932577,0.0006691599,0.016641546],"genre_scores_gemma":[0.85381144,0.0000013736259,0.14531125,0.00007220349,0.000012751092,0.000013366367,0.00003693329,0.0000035594137,0.0007371104],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994941,0.0000021312528,0.0001221597,0.0001891084,0.00006305851,0.0001294915],"domain_scores_gemma":[0.9996525,0.000028816521,0.000027436967,0.00025452592,0.000011665321,0.000025067642],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000086356624,0.000048735918,0.000044908375,0.00014032735,0.000027555065,0.00027155044,0.0004735745,0.000047414866,0.0000054173242],"category_scores_gemma":[0.00001402629,0.00004094139,0.0000137459065,0.00035335714,0.000017253982,0.0024089473,0.000054634667,0.000030751267,0.000008676444],"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":[0.0000028002833,0.00008631114,0.0083430335,0.000002944885,7.2213504e-7,2.794811e-7,0.00006723114,0.000017444041,0.00017163229,0.7947533,0.0005903449,0.19596395],"study_design_scores_gemma":[0.0014489423,0.00038707763,0.070398614,0.0000058211904,0.0000024116396,0.0000069305775,0.0016637433,0.46634692,0.0815481,0.34290043,0.034475006,0.0008160058],"about_ca_topic_score_codex":0.0000012150925,"about_ca_topic_score_gemma":5.4712166e-7,"teacher_disagreement_score":0.8487188,"about_ca_system_score_codex":0.000010102025,"about_ca_system_score_gemma":0.000015614733,"threshold_uncertainty_score":0.26185673},"labels":[],"label_agreement":null},{"id":"W4245824053","doi":"10.1007/978-3-540-68636-1_62","title":"Maximum Entropy Modeling with Feature Selection for Text Categorization","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Feature selection; Categorization; Principle of maximum entropy; Text categorization; Computer science; Artificial intelligence; Entropy (arrow of time); Pattern recognition (psychology); Feature (linguistics); Selection (genetic algorithm); Data mining; Machine learning; Natural language processing","score_opus":0.018386091831786494,"score_gpt":0.23345593499830458,"score_spread":0.2150698431665181,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245824053","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005573432,0.0002608563,0.9957011,0.0018062865,0.0005420227,0.00064857944,0.0000027144224,0.0005505344,0.00043217448],"genre_scores_gemma":[0.20139496,0.00016248027,0.7968208,0.00044643253,0.00030024938,0.000059361737,0.000022491442,0.000044249384,0.000748964],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99720967,0.000011845366,0.00031151416,0.0012991487,0.00066246244,0.00050533586],"domain_scores_gemma":[0.998315,0.00013034449,0.0002661474,0.00080276653,0.00040764466,0.00007813687],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00023569781,0.00043058593,0.0003495031,0.00080174796,0.0004288919,0.0004630553,0.0018505312,0.000391934,0.000004568636],"category_scores_gemma":[0.000049207243,0.00035461184,0.00008290538,0.00074312947,0.00031358548,0.000817481,0.00032322327,0.0005327918,0.000011303389],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002809788,0.00003885617,0.000090458765,0.00004843606,0.00001813225,0.000009660719,0.00061100733,0.23454972,0.0004519168,0.12087428,0.00023617383,0.6430433],"study_design_scores_gemma":[0.0002875994,0.00022613567,0.000012920328,0.00008452001,0.0000067328333,0.000059482678,2.901019e-7,0.8805625,0.0021889508,0.11372919,0.002402408,0.00043931569],"about_ca_topic_score_codex":0.000009668761,"about_ca_topic_score_gemma":0.000036960362,"teacher_disagreement_score":0.6460127,"about_ca_system_score_codex":0.00034627682,"about_ca_system_score_gemma":0.00046032676,"threshold_uncertainty_score":0.99989057},"labels":[],"label_agreement":null},{"id":"W4248349546","doi":"10.1007/978-0-387-39940-9_3794","title":"Text Data Mining","year":2009,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Database Systems","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Information retrieval; Data science; Data mining","score_opus":0.046639542449223234,"score_gpt":0.26920340928072506,"score_spread":0.2225638668315018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248349546","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000004735462,0.0057475767,0.039210547,0.0003503767,0.0014256674,0.00050847273,0.0010863466,0.0006657619,0.9510005],"genre_scores_gemma":[0.0010887544,0.0068499874,0.045157366,0.00006650325,0.00059173646,0.000026346355,0.0028981098,0.00006678874,0.9432544],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99712056,0.000030334535,0.0008553441,0.001030198,0.0006746503,0.00028889696],"domain_scores_gemma":[0.99266446,0.00017868381,0.00084263994,0.0061076568,0.00011020842,0.0000963489],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00050429715,0.00039677453,0.0006005181,0.0003903019,0.0000778538,0.00012540376,0.0051993406,0.0002995494,0.000059987735],"category_scores_gemma":[0.00013633851,0.00036983215,0.00007695149,0.00011981731,0.00010954646,0.0011097278,0.0018616129,0.0003142877,0.00028297884],"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":[0.0000027651686,0.000029039662,0.00001656457,0.0001680069,0.000054573527,0.000038212816,0.00007756065,0.0000017248764,0.000026198442,0.5974157,0.21088476,0.19128491],"study_design_scores_gemma":[0.00014852687,0.000051314448,0.0000139721415,0.00047536322,0.00003153059,0.00001762009,0.00003940814,0.0011135963,0.000018640656,0.0011886915,0.9964935,0.0004078292],"about_ca_topic_score_codex":0.000034108623,"about_ca_topic_score_gemma":0.000008660669,"teacher_disagreement_score":0.78560877,"about_ca_system_score_codex":0.000046500914,"about_ca_system_score_gemma":0.00020939841,"threshold_uncertainty_score":0.99987537},"labels":[],"label_agreement":null},{"id":"W4250326346","doi":"10.1162/coli_r_00106","title":"Briefly Noted","year":2012,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.028066313871546286,"score_gpt":0.2845006114861258,"score_spread":0.25643429761457953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4250326346","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":[0.0008992796,0.00015231254,0.9846731,0.0005809663,0.0011568422,0.000056061715,0.000003071678,0.0006235207,0.011854839],"genre_scores_gemma":[0.7512671,0.0000018033833,0.24800707,0.00028103724,0.00026225718,0.0000038916864,0.000013466517,0.000003963615,0.00015941172],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992785,0.000014862302,0.00016301294,0.00013405476,0.00021398814,0.00019561383],"domain_scores_gemma":[0.9992053,0.00017728584,0.00007121139,0.0002300432,0.00024744155,0.00006873436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012383048,0.00007763308,0.00007096436,0.000081119724,0.00010470568,0.00008385441,0.0004294763,0.00004505741,0.00001860109],"category_scores_gemma":[0.0009910046,0.000077304685,0.000028700302,0.0002414149,0.000045776185,0.000099637226,0.00014038845,0.000080603546,0.00027614817],"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":[5.973178e-7,0.00004264635,0.0018319822,0.000002724883,0.0000046082337,7.0170466e-7,0.000084637526,0.0005714396,0.000008972668,0.9854346,0.004348788,0.007668334],"study_design_scores_gemma":[0.00031833458,0.000037700105,0.048416197,0.000010097488,0.000008220517,0.0000099451645,0.00002441749,0.137531,0.00067118893,0.3207998,0.49181825,0.00035486303],"about_ca_topic_score_codex":0.0000016628061,"about_ca_topic_score_gemma":9.9117926e-8,"teacher_disagreement_score":0.7503678,"about_ca_system_score_codex":0.000030547137,"about_ca_system_score_gemma":0.00004307582,"threshold_uncertainty_score":0.35494182},"labels":[],"label_agreement":null},{"id":"W4252608527","doi":"10.1007/978-1-4939-7131-2_100956","title":"Recommendation System","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science","score_opus":0.031229254184842396,"score_gpt":0.23884589371208095,"score_spread":0.20761663952723855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4252608527","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.1935745e-7,0.000011261148,0.3044601,0.0011709309,0.00037047538,0.000084658604,0.000001428043,0.0015627312,0.69233817],"genre_scores_gemma":[0.0013543641,0.000029398749,0.021390697,0.00012587094,0.0000957045,0.000010073803,0.000020958556,0.000013129689,0.9769598],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991934,0.0000046245063,0.00021211659,0.0003559443,0.00013044933,0.00010347899],"domain_scores_gemma":[0.99899405,0.000024411956,0.00017584492,0.00069695315,0.00008159085,0.000027133448],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00010873539,0.0001475867,0.00013666763,0.00016245114,0.00006695154,0.00014946374,0.0007889548,0.00022196217,0.0022842914],"category_scores_gemma":[0.000005821258,0.00012573203,0.000054770913,0.000029374203,0.0000433037,0.00023714174,0.00027261284,0.00010658272,0.0044958354],"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":[2.3566673e-7,0.0000012283389,2.8984843e-7,0.000007847173,0.000006636153,4.878717e-7,0.000010003973,8.542731e-9,0.0000024486317,0.87372667,0.052559324,0.07368485],"study_design_scores_gemma":[0.000044941768,0.000033205248,0.0000020632253,0.000026457697,0.000003947164,0.000005012329,0.000013935445,0.00065953017,0.00023077158,0.06538423,0.9334281,0.0001677949],"about_ca_topic_score_codex":0.0000013256753,"about_ca_topic_score_gemma":0.00000172388,"teacher_disagreement_score":0.8808688,"about_ca_system_score_codex":0.00010283564,"about_ca_system_score_gemma":0.000028413126,"threshold_uncertainty_score":0.9986278},"labels":[],"label_agreement":null},{"id":"W4254319338","doi":"10.1007/978-1-4939-7131-2_100396","title":"Friend Recommender System","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Recommender system; Computer science; World Wide Web; Information retrieval","score_opus":0.03278790746785005,"score_gpt":0.23560029599278515,"score_spread":0.2028123885249351,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254319338","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.9386416e-7,0.000100223326,0.21344386,0.0016017694,0.00054829876,0.00011226083,0.0000022936745,0.0020007945,0.7821902],"genre_scores_gemma":[0.0013408797,0.00003402337,0.022553194,0.00015814892,0.00010208283,0.000012041617,0.0000058973164,0.00001878046,0.97577494],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99883425,0.0000059770773,0.00026508296,0.0004920599,0.00022791169,0.0001746955],"domain_scores_gemma":[0.9983935,0.000027472106,0.0001837109,0.0012581433,0.00008881654,0.000048410202],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00011556281,0.00022196604,0.00021076846,0.00018689944,0.00008934339,0.00018959625,0.0013896824,0.0003206318,0.0013197245],"category_scores_gemma":[0.0000063741527,0.0001819789,0.000087465385,0.00003779654,0.00008187815,0.00022853236,0.0004890007,0.00017329615,0.0045363973],"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":[3.085593e-7,0.0000019145994,3.0763434e-7,0.000010463236,0.000012569315,0.0000023864852,0.000026515794,1.1956185e-8,0.0000014263097,0.7894345,0.19504397,0.015465618],"study_design_scores_gemma":[0.000056391615,0.000037047274,0.0000013103285,0.00004516904,0.0000052926284,0.0000098815435,0.000041365853,0.00026379255,0.00016093052,0.09322882,0.9059188,0.00023119277],"about_ca_topic_score_codex":0.0000019045049,"about_ca_topic_score_gemma":0.0000023476384,"teacher_disagreement_score":0.71087486,"about_ca_system_score_codex":0.000105723244,"about_ca_system_score_gemma":0.00004021156,"threshold_uncertainty_score":0.9995932},"labels":[],"label_agreement":null},{"id":"W4281675176","doi":"10.36227/techrxiv.19498769.v1","title":"Detecting Anomalies in Logs by Combining NLP features with Embedding or TF-IDF","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Text and Document Classification Technologies","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":"Lakehead University","funders":"Lakehead University","keywords":"Categorization; Computer science; Artificial intelligence; Natural language processing; Sentence; Set (abstract data type); Focus (optics); Embedding; Text categorization; Information retrieval","score_opus":0.023159451330024405,"score_gpt":0.2890592490640066,"score_spread":0.2658997977339822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281675176","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":[0.26655576,0.0020117802,0.6792967,0.009459996,0.0017054401,0.0017483395,0.000023074403,0.008243693,0.030955246],"genre_scores_gemma":[0.91131467,0.0000579003,0.0830125,0.00021005305,0.000015118442,0.00025533015,0.000017229475,0.00002343622,0.005093749],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978246,0.00008769385,0.00036977194,0.0009119131,0.00040299122,0.00040303732],"domain_scores_gemma":[0.998305,0.00025167078,0.0003208268,0.0010387696,0.000039829676,0.000043863536],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000388742,0.00032779676,0.0003699004,0.00042946456,0.0002510723,0.0006500525,0.0022126457,0.0002222634,0.00017837688],"category_scores_gemma":[0.00011929438,0.00024982644,0.00005806075,0.0006281323,0.000084858475,0.0003636097,0.0036987073,0.0011356511,0.000006915786],"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":[0.00031687744,0.0008796337,0.06826885,0.00088478025,0.00043284608,0.0005340784,0.016672023,0.01565856,0.0044751344,0.28868392,0.047586303,0.555607],"study_design_scores_gemma":[0.011900609,0.006156967,0.047198765,0.0033772828,0.00021848288,0.00069989107,0.107007295,0.3711201,0.15896001,0.15733828,0.11868327,0.01733905],"about_ca_topic_score_codex":0.00020541014,"about_ca_topic_score_gemma":0.00016695181,"teacher_disagreement_score":0.64475894,"about_ca_system_score_codex":0.00019697123,"about_ca_system_score_gemma":0.00015470377,"threshold_uncertainty_score":0.9999954},"labels":[],"label_agreement":null},{"id":"W4281747386","doi":"10.3390/math10111871","title":"Robust Multi-Label Classification with Enhanced Global and Local Label Correlation","year":2022,"lang":"en","type":"article","venue":"Mathematics","topic":"Text and Document Classification Technologies","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":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Robustness (evolution); Correlation; Artificial intelligence; Subspace topology; Computer science; Pattern recognition (psychology); Missing data; Machine learning; Ambiguity; Feature learning; Mathematics","score_opus":0.061293310949191424,"score_gpt":0.27035612154802885,"score_spread":0.2090628105988374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281747386","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":[0.021800255,0.000058609658,0.9757035,0.00088887993,0.000075877295,0.00021531178,0.000004695537,0.00042441476,0.0008284894],"genre_scores_gemma":[0.6256431,0.000006802402,0.37387073,0.00005369769,0.0000038254125,0.000077054334,0.0000058872442,0.0000055132214,0.00033338522],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906963,0.000027533833,0.0002015811,0.0002654356,0.000286437,0.00014935198],"domain_scores_gemma":[0.9992655,0.000050800878,0.00017558901,0.00042128103,0.000051704577,0.00003514402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016978539,0.00010997358,0.000116275085,0.000053421292,0.00026230418,0.00010573914,0.00042574774,0.000042248554,0.000015480318],"category_scores_gemma":[0.000030328836,0.000095826195,0.000011209804,0.00043973554,0.00009103175,0.00026350262,0.0002635184,0.00012189504,0.000021531901],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009388841,0.00062233064,0.00065174926,0.00004693585,0.000021004354,0.0000029265918,0.0012863157,0.0007756239,0.0011879173,0.82563514,0.00061114563,0.1691495],"study_design_scores_gemma":[0.00072267465,0.00012915894,0.0012630605,0.000009954865,0.000009559492,0.000021275055,0.001389391,0.98361886,0.00040535064,0.0120342225,0.00023981434,0.00015669687],"about_ca_topic_score_codex":0.0000031789446,"about_ca_topic_score_gemma":0.0000058179553,"teacher_disagreement_score":0.9828432,"about_ca_system_score_codex":0.00012895855,"about_ca_system_score_gemma":0.000038794085,"threshold_uncertainty_score":0.39076787},"labels":[],"label_agreement":null},{"id":"W4281764099","doi":"10.36227/techrxiv.19498769","title":"Detecting Anomalies in Logs by Combining NLP features with Embedding or TF-IDF","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","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":"Lakehead University","funders":"Lakehead University","keywords":"Categorization; Computer science; Artificial intelligence; Natural language processing; Set (abstract data type); Sentence; Focus (optics); Embedding; Information retrieval; Text categorization; Text mining; Meaning (existential); Psychology","score_opus":0.023159451330024405,"score_gpt":0.2890592490640066,"score_spread":0.2658997977339822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281764099","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":[0.26655576,0.0020117802,0.6792967,0.009459996,0.0017054401,0.0017483395,0.000023074403,0.008243693,0.030955246],"genre_scores_gemma":[0.91131467,0.0000579003,0.0830125,0.00021005305,0.000015118442,0.00025533015,0.000017229475,0.00002343622,0.005093749],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978246,0.00008769385,0.00036977194,0.0009119131,0.00040299122,0.00040303732],"domain_scores_gemma":[0.998305,0.00025167078,0.0003208268,0.0010387696,0.000039829676,0.000043863536],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000388742,0.00032779676,0.0003699004,0.00042946456,0.0002510723,0.0006500525,0.0022126457,0.0002222634,0.00017837688],"category_scores_gemma":[0.00011929438,0.00024982644,0.00005806075,0.0006281323,0.000084858475,0.0003636097,0.0036987073,0.0011356511,0.000006915786],"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":[0.00031687744,0.0008796337,0.06826885,0.00088478025,0.00043284608,0.0005340784,0.016672023,0.01565856,0.0044751344,0.28868392,0.047586303,0.555607],"study_design_scores_gemma":[0.011900609,0.006156967,0.047198765,0.0033772828,0.00021848288,0.00069989107,0.107007295,0.3711201,0.15896001,0.15733828,0.11868327,0.01733905],"about_ca_topic_score_codex":0.00020541014,"about_ca_topic_score_gemma":0.00016695181,"teacher_disagreement_score":0.64475894,"about_ca_system_score_codex":0.00019697123,"about_ca_system_score_gemma":0.00015470377,"threshold_uncertainty_score":0.9999954},"labels":[],"label_agreement":null},{"id":"W4283798078","doi":"10.1007/s11517-022-02604-1","title":"Modeling global and local label correlation with graph convolutional networks for multi-label chest X-ray image classification","year":2022,"lang":"en","type":"article","venue":"Medical & Biological Engineering & Computing","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Computer science; Correlation; Convolutional neural network; Artificial intelligence; Multi-label classification; Graph; Machine learning; Pattern recognition (psychology); Task (project management); Representation (politics); Computer-aided diagnosis; Data mining; Theoretical computer science; Mathematics","score_opus":0.0392016277018329,"score_gpt":0.26747420164264885,"score_spread":0.22827257394081596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283798078","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":[0.03469682,0.00036179804,0.96282506,0.0008738623,0.00025975626,0.00027868644,0.0000060532193,0.0006803608,0.000017622011],"genre_scores_gemma":[0.7711482,0.000013602951,0.22854654,0.00012638654,0.000047037578,0.00006391545,0.000042912838,0.0000071700224,0.0000042592033],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982244,0.000055589222,0.0003713742,0.0005693216,0.00037665045,0.00040266334],"domain_scores_gemma":[0.9992078,0.00023880953,0.00010265146,0.00021918131,0.0000829208,0.00014866448],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006728623,0.00020551909,0.00022924492,0.000073581796,0.00041512706,0.00008557425,0.00060893013,0.00017306935,0.000014326926],"category_scores_gemma":[0.0002545941,0.00016739126,0.00004171494,0.0005014263,0.0001755898,0.00014935719,0.00049291644,0.00043590035,0.0000025568045],"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":[0.00004520718,0.0003209866,0.0058567496,0.000033269465,0.00004551472,0.000009660179,0.0000691671,0.66298294,0.00036279796,0.17475915,0.00012292658,0.15539166],"study_design_scores_gemma":[0.0010203791,0.00020189863,0.006725766,0.000023095747,0.000006193659,0.00002668024,0.000083139916,0.9911472,0.0000029441867,0.0003920961,0.00014568833,0.00022489084],"about_ca_topic_score_codex":0.000009809092,"about_ca_topic_score_gemma":8.598592e-7,"teacher_disagreement_score":0.7364513,"about_ca_system_score_codex":0.00013033903,"about_ca_system_score_gemma":0.00005752411,"threshold_uncertainty_score":0.6826018},"labels":[],"label_agreement":null},{"id":"W4284989007","doi":"10.48175/ijarsct-5715","title":"Study of Recommendation System","year":2022,"lang":"en","type":"article","venue":"International Journal of Advanced Research in Science Communication and Technology","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Globe; Set (abstract data type); Point of interest; Data science; Quarter (Canadian coin); World Wide Web; Artificial intelligence; Geography; Psychology","score_opus":0.09041018752325591,"score_gpt":0.442330979164459,"score_spread":0.3519207916412031,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4284989007","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":[0.9685374,0.00036244534,0.003967342,0.025194956,0.00036555607,0.00028570576,0.0000013877483,0.00007135331,0.0012138475],"genre_scores_gemma":[0.99127126,0.00019575928,0.00847065,0.000009408661,0.00000328865,0.000036254973,4.5622974e-7,0.0000021192202,0.000010790948],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9980364,0.00023472692,0.00048714812,0.00017365249,0.00092104805,0.00014703897],"domain_scores_gemma":[0.9976232,0.00021092016,0.00041131227,0.00052090385,0.0012056633,0.000027986276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004152439,0.000047854628,0.00012237234,0.0034628045,0.00029346198,0.00006963068,0.0046681785,0.000024760056,0.000006264179],"category_scores_gemma":[0.00040661794,0.000044932185,0.0000132237,0.0030424227,0.000533118,0.00081807905,0.002504065,0.00057288056,6.0904523e-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":[0.00003835259,0.0006746008,0.007630138,0.00000421808,0.000014419743,0.000016499767,0.0016107613,0.00032273453,0.009559303,0.48058298,0.000047456335,0.49949855],"study_design_scores_gemma":[0.010646632,0.007479667,0.033675667,0.00032649806,0.000009076648,0.0015604612,0.5839102,0.02554707,0.042249873,0.2581924,0.03577751,0.00062491326],"about_ca_topic_score_codex":0.0000120930445,"about_ca_topic_score_gemma":0.000007247801,"teacher_disagreement_score":0.5822995,"about_ca_system_score_codex":0.00036890653,"about_ca_system_score_gemma":0.00019267076,"threshold_uncertainty_score":0.86747146},"labels":[],"label_agreement":null},{"id":"W4286449976","doi":"10.18280/ria.360307","title":"A New Supervised Term Weight Measure Based Approach for Text Classification","year":2022,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Term (time); Computer science; Measure (data warehouse); Task (project management); Identification (biology); Support vector machine; tf–idf; Categorization; Text categorization; Artificial intelligence; Information retrieval; Document classification; Natural language processing; Pattern recognition (psychology); Data mining","score_opus":0.07099948823014113,"score_gpt":0.2729647282679941,"score_spread":0.201965240037853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286449976","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":[0.00045435494,0.00026972307,0.9897358,0.004753737,0.00031256556,0.0007515175,0.000009399748,0.00062401034,0.0030889239],"genre_scores_gemma":[0.8362714,0.000012331979,0.1588137,0.00026176873,0.00006762872,0.00070029986,0.00005352289,0.000021718839,0.0037976124],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979701,0.00008362723,0.00045574157,0.0007467961,0.00036171573,0.00038203536],"domain_scores_gemma":[0.9981765,0.00017057317,0.00018685719,0.0012471994,0.00011401474,0.00010485255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005582798,0.00019860755,0.00020467647,0.0002735192,0.0005939251,0.00019869294,0.001957466,0.00008015799,0.00029417974],"category_scores_gemma":[0.00010542036,0.00020342693,0.00017172824,0.0010487885,0.00005787709,0.00033472915,0.00026771222,0.00023929257,0.000079022124],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005729685,0.00043549316,0.00029650243,0.000063118765,0.000021450325,0.0000020790008,0.0010506065,0.014760513,0.022974625,0.33851653,0.015948037,0.60587376],"study_design_scores_gemma":[0.0001307363,0.0001813593,0.0000762051,0.000008414831,0.000009547644,0.000006758341,0.000771962,0.9015503,0.053277366,0.0044892863,0.03921439,0.0002836789],"about_ca_topic_score_codex":0.000008904285,"about_ca_topic_score_gemma":0.0000010627723,"teacher_disagreement_score":0.8867898,"about_ca_system_score_codex":0.0001535736,"about_ca_system_score_gemma":0.0001972165,"threshold_uncertainty_score":0.8295509},"labels":[],"label_agreement":null},{"id":"W4288075349","doi":"10.18280/ts.390319","title":"A Deep Learning-Based Cluster Analysis Method for Large-Scale Multi-Label Images","year":2022,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Pattern recognition (psychology); Computer science; Image (mathematics); Graph; Feature extraction; Scale (ratio); Feature (linguistics); Theoretical computer science","score_opus":0.02557382948783619,"score_gpt":0.3002978727212843,"score_spread":0.27472404323344807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288075349","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011886248,0.00009510383,0.994068,0.003526632,0.00007118674,0.00042257138,0.000022939703,0.00055496773,0.0000499684],"genre_scores_gemma":[0.4061429,0.0000018093939,0.5914836,0.0008268113,0.000017660672,0.00070870406,0.000060016526,0.000011659884,0.00074684055],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99817175,0.00021135515,0.00032136083,0.00052960083,0.00039790414,0.0003680207],"domain_scores_gemma":[0.9990583,0.00023701998,0.00018968177,0.00037663602,0.00007987029,0.000058473506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010214122,0.0001671874,0.00023928407,0.00043382103,0.0005779693,0.00015904862,0.0009517439,0.000041695977,0.0004937763],"category_scores_gemma":[0.000030388961,0.00016188578,0.00021722654,0.001025176,0.00002630272,0.00022846715,0.0003180338,0.00019489737,0.000011172356],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003126968,0.0050485604,0.017587433,0.00012185946,0.0016846574,0.00001894856,0.00500145,0.41636282,0.016538125,0.02833998,0.014822948,0.49416053],"study_design_scores_gemma":[0.0019362812,0.00025382903,0.001541701,0.0000012249802,0.00012135992,7.5038656e-7,0.00040958106,0.9753792,0.0023416895,0.00032696003,0.01748031,0.0002071004],"about_ca_topic_score_codex":0.000008337353,"about_ca_topic_score_gemma":0.000017217772,"teacher_disagreement_score":0.5590164,"about_ca_system_score_codex":0.00009227703,"about_ca_system_score_gemma":0.00003588573,"threshold_uncertainty_score":0.66015106},"labels":[],"label_agreement":null},{"id":"W4292837269","doi":"10.1016/j.ijar.2022.08.008","title":"Selective label enhancement for multi-label classification based on three-way decisions","year":2022,"lang":"en","type":"article","venue":"International Journal of Approximate Reasoning","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Multi-label classification; Computer science; Ambiguity; Artificial intelligence; Machine learning; Trustworthiness; Semantics (computer science)","score_opus":0.08242627889891666,"score_gpt":0.344599262681396,"score_spread":0.26217298378247933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292837269","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":[0.012306855,0.00007274188,0.98230493,0.00373127,0.0008269732,0.00025952264,0.00001533906,0.00008860535,0.00039377648],"genre_scores_gemma":[0.56604826,0.000019452855,0.4334206,0.0002249818,0.00005237587,0.000127459,0.000011198673,0.000010845742,0.00008483066],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980605,0.000057367633,0.00050554774,0.0002802926,0.0008973783,0.0001988982],"domain_scores_gemma":[0.99788636,0.00035123294,0.0007785014,0.00026969315,0.0006581083,0.00005608258],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00083263917,0.00013882208,0.00017251885,0.00046840627,0.00030071617,0.00020077637,0.001627404,0.000042492677,0.000026869224],"category_scores_gemma":[0.0005165329,0.00012614521,0.000102799175,0.00032816315,0.00003462207,0.00042466508,0.00021938479,0.0002965358,0.0000053677413],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045218188,0.0020031985,0.0010934282,0.000008201246,0.00021676609,0.000018031447,0.000471039,0.0020509872,0.017472005,0.40727305,0.0025013844,0.56643975],"study_design_scores_gemma":[0.002173561,0.0004915546,0.0011247711,0.00006909632,0.000010245853,0.000024126333,0.00019178145,0.9777325,0.008341326,0.0072331266,0.0024565558,0.00015138903],"about_ca_topic_score_codex":0.0000027115054,"about_ca_topic_score_gemma":0.0000014634707,"teacher_disagreement_score":0.9756815,"about_ca_system_score_codex":0.00052414247,"about_ca_system_score_gemma":0.00017485814,"threshold_uncertainty_score":0.51440525},"labels":[],"label_agreement":null},{"id":"W4293863379","doi":"10.1109/siu55565.2022.9864993","title":"Banking Order Classification and Information Extraction","year":2022,"lang":"en","type":"article","venue":"2022 30th Signal Processing and Communications Applications Conference (SIU)","topic":"Text and Document Classification Technologies","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":"Stantec (Canada)","funders":"","keywords":"Computer science; Workload; Communication source; Information extraction; Preprocessor; Database transaction; Process (computing); Support vector machine; Transaction processing; Transfer (computing); Order (exchange); Statistical classification; Artificial intelligence; Data mining; Information retrieval; Database; Operating system; Telecommunications","score_opus":0.0369949697109424,"score_gpt":0.28695350757049615,"score_spread":0.24995853785955374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293863379","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":[0.0018068656,0.001774498,0.97477835,0.0141456425,0.000029440904,0.0006369754,0.000017866356,0.0006895555,0.0061208247],"genre_scores_gemma":[0.95918274,0.0009104409,0.03694621,0.00032357464,0.000012284308,0.002293176,0.0001447084,0.000009285552,0.00017757568],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984667,0.00013713932,0.00045401408,0.00038859237,0.00033674808,0.00021685316],"domain_scores_gemma":[0.99778306,0.00014033652,0.00042395142,0.0012386997,0.00033918303,0.0000747422],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0005083716,0.00017743718,0.000155939,0.00036855295,0.0026454555,0.00074641994,0.0015085317,0.00007430884,0.00007810779],"category_scores_gemma":[0.000023967348,0.00019592984,0.000025445335,0.0013190634,0.00026749255,0.0025990051,0.001145883,0.00049705675,0.000016639875],"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":[0.0000029540038,0.000064605345,0.00025375932,0.00001811283,0.000005871543,5.739426e-8,0.00054671353,0.000016427595,0.0011373084,0.43155548,0.00012624603,0.5662725],"study_design_scores_gemma":[0.00050056673,0.00010174836,0.0064732907,0.000027564163,0.000039547194,0.00006275424,0.007031009,0.48680115,0.00026763443,0.06459821,0.4335177,0.00057882676],"about_ca_topic_score_codex":0.00002160276,"about_ca_topic_score_gemma":0.000005599963,"teacher_disagreement_score":0.9573759,"about_ca_system_score_codex":0.00009715212,"about_ca_system_score_gemma":0.00023550537,"threshold_uncertainty_score":0.99865294},"labels":[],"label_agreement":null},{"id":"W4311843543","doi":"","title":"Vers une étude comparative de différentes approches de classification automatique de textes provenant des secteurs métiers","year":2021,"lang":"fr","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Text and Document Classification Technologies","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":"Berger (Canada)","funders":"","keywords":"Computer science","score_opus":0.03285696509734804,"score_gpt":0.2624052596048865,"score_spread":0.22954829450753844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311843543","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":[0.2624196,0.0021848963,0.70345414,0.021143075,0.00019468604,0.000711409,0.000028877306,0.0010190383,0.008844295],"genre_scores_gemma":[0.72025883,0.0017927306,0.27277538,0.00013664513,0.000023004226,0.0004154445,0.00023863946,0.000049110204,0.0043102335],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9866704,0.008760672,0.0010506059,0.0016467811,0.00066777144,0.001203785],"domain_scores_gemma":[0.9897508,0.0028655718,0.0012618125,0.003040651,0.002619433,0.000461752],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.007066452,0.00078021863,0.0007880657,0.00038380377,0.0010485084,0.0022025027,0.0036812949,0.0007453073,0.00006639162],"category_scores_gemma":[0.003306204,0.0008539788,0.00041422242,0.0016127607,0.0018567347,0.0008965463,0.0018345576,0.0013407217,0.00004445306],"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":[0.000021837719,0.0017038926,0.01829892,0.00053245097,0.00028837123,0.000017609456,0.12154343,0.00067606976,0.056534342,0.68859464,0.0008767455,0.110911705],"study_design_scores_gemma":[0.00087132346,0.000004841446,0.18981403,0.003789296,0.00015450225,0.00009234291,0.00995497,0.4629516,0.28623077,0.036942117,0.007896988,0.0012972276],"about_ca_topic_score_codex":0.0028879214,"about_ca_topic_score_gemma":0.0038177285,"teacher_disagreement_score":0.6516525,"about_ca_system_score_codex":0.0016305204,"about_ca_system_score_gemma":0.0024663399,"threshold_uncertainty_score":0.9993911},"labels":[],"label_agreement":null},{"id":"W4312543622","doi":"10.1007/978-3-031-16719-5_3","title":"An Introduction of ML Through PCG","year":2022,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on games and computational intelligence","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"History; Computer science","score_opus":0.02523895594200046,"score_gpt":0.2703429659458372,"score_spread":0.24510401000383672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312543622","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":[0.000104857085,0.001739016,0.9474996,0.008317431,0.00044979266,0.0003587514,0.000047950365,0.00046532587,0.04101728],"genre_scores_gemma":[0.9042567,0.002069561,0.07463955,0.0009489987,0.00038670507,0.00013262924,0.00011845098,0.00008101522,0.017366396],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99818015,0.00004607262,0.00041378455,0.00071574183,0.00049085316,0.00015339376],"domain_scores_gemma":[0.9983664,0.00048188784,0.00036733554,0.0006126964,0.00013047876,0.000041175674],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001610047,0.00028620748,0.0003227612,0.00026357727,0.00016970227,0.00011415809,0.00089436607,0.00015721952,0.0007476613],"category_scores_gemma":[0.00008168426,0.00026376313,0.00010683653,0.00010835012,0.00023309341,0.0002983936,0.00018211851,0.00032167378,0.000017272741],"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":[0.000012149564,0.00003218188,0.0000014406227,0.000016607755,0.00003516592,0.0000014775133,0.00014985069,0.011338889,0.000020280726,0.7633206,0.00084409583,0.22422723],"study_design_scores_gemma":[0.000025177618,0.00034460955,0.00005830329,0.000032224354,0.000022199658,0.00001804392,0.000054668424,0.008595104,0.0050294404,0.84144247,0.14402679,0.00035099348],"about_ca_topic_score_codex":0.000009720103,"about_ca_topic_score_gemma":0.0000020584732,"teacher_disagreement_score":0.90415186,"about_ca_system_score_codex":0.000062407795,"about_ca_system_score_gemma":0.000074774754,"threshold_uncertainty_score":0.99998146},"labels":[],"label_agreement":null},{"id":"W4313021298","doi":"10.23952/jano.4.2022.3.06","title":"Hierarchical reinforcement learning with advantage function for entity relation extraction","year":2022,"lang":"en","type":"article","venue":"Journal of Applied and Numerical Optimization","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Reinforcement learning; Relation (database); Relationship extraction; Reinforcement; Computer science; Function (biology); Extraction (chemistry); Artificial intelligence; Psychology; Data mining; Biology; Chemistry; Social psychology; Chromatography","score_opus":0.008532871366860002,"score_gpt":0.23142409086263183,"score_spread":0.22289121949577181,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313021298","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":[0.0023348732,0.000024392757,0.99618274,0.00064584095,0.00010757327,0.0001542852,2.096874e-7,0.000058517635,0.00049155677],"genre_scores_gemma":[0.8871481,0.000034400055,0.11261997,0.000061353676,0.000029161218,0.000027803933,0.000009247099,0.0000050129706,0.0000649385],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992385,0.000023696488,0.0002565156,0.00012935346,0.00026282415,0.00008912381],"domain_scores_gemma":[0.99934345,0.0000661815,0.00040940844,0.00007727532,0.00006738617,0.00003630475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027449746,0.000066102184,0.00010654226,0.00014256747,0.0003166701,0.0000636604,0.00011984728,0.000029569163,0.000025163223],"category_scores_gemma":[0.000022118147,0.00005497122,0.000030110241,0.00022865961,0.000018874292,0.00046313615,0.000055867473,0.00023491173,3.7455223e-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":[0.0003853236,0.00004958135,0.00010989025,0.000005716623,0.000014978536,7.551158e-7,0.000105383486,0.90616727,0.00085069984,0.05941372,0.000058687427,0.032838017],"study_design_scores_gemma":[0.0012279239,0.0016932791,0.00087668415,0.0000054837233,0.000032861568,0.000040979845,0.0003891211,0.97549176,0.00057692145,0.0057398123,0.013784526,0.00014065996],"about_ca_topic_score_codex":3.8009978e-7,"about_ca_topic_score_gemma":2.2634831e-8,"teacher_disagreement_score":0.88481325,"about_ca_system_score_codex":0.000070494265,"about_ca_system_score_gemma":0.000029605628,"threshold_uncertainty_score":0.24356024},"labels":[],"label_agreement":null},{"id":"W4313343225","doi":"10.1007/978-3-031-23028-8","title":"Structural, Syntactic, and Statistical Pattern Recognition","year":2022,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Artificial intelligence; Natural language processing; Pattern recognition (psychology); Sketch recognition; Speech recognition; Gesture recognition","score_opus":0.024316487183609348,"score_gpt":0.26366775665991143,"score_spread":0.2393512694763021,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313343225","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00027782947,0.00023492644,0.9961443,0.0011247685,0.0010206463,0.00027049647,0.000024140105,0.00033086317,0.00057200826],"genre_scores_gemma":[0.3779749,0.00020240984,0.6183221,0.002399426,0.00034048644,0.00008979748,0.00011111265,0.00005024219,0.00050952536],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971894,0.00006465805,0.000348034,0.0012235128,0.0007382152,0.00043617832],"domain_scores_gemma":[0.99806,0.0006833366,0.00021829571,0.00086089765,0.00008234114,0.00009511347],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00043840872,0.00031238282,0.00031157117,0.0006179782,0.00034601503,0.000704299,0.0020093243,0.00017629264,0.00014130984],"category_scores_gemma":[0.00017063192,0.0002897701,0.00003705206,0.00062507426,0.00060555735,0.00067575485,0.0017646063,0.00079783954,0.000023918095],"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":[0.000001465582,0.000008927791,0.00009763393,0.000024525662,0.0000038972757,0.000033418688,0.00024315821,0.00012889525,0.000016176555,0.0019189983,0.0002280784,0.99729484],"study_design_scores_gemma":[0.0003662569,0.00035004408,0.0018082274,0.00012132815,0.000013452268,0.00019111966,0.0000020826626,0.37813467,0.00055113685,0.61382955,0.003654861,0.000977271],"about_ca_topic_score_codex":0.000018384766,"about_ca_topic_score_gemma":0.000015345258,"teacher_disagreement_score":0.99631757,"about_ca_system_score_codex":0.0003866545,"about_ca_system_score_gemma":0.00045276992,"threshold_uncertainty_score":0.9999554},"labels":[],"label_agreement":null},{"id":"W4313343334","doi":"10.1007/978-3-031-23028-8_4","title":"Interactive Generalized Dirichlet Mixture Allocation Model","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Latent Dirichlet allocation; Computer science; Inference; Topic model; Dirichlet distribution; Task (project management); Artificial intelligence; Hierarchical Dirichlet process; Machine learning; Prior probability; Data mining; Mathematics","score_opus":0.021942706797824202,"score_gpt":0.2639456888059402,"score_spread":0.242002982008116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313343334","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000059066148,0.00036903642,0.98855865,0.004081785,0.0011297384,0.0004047831,0.000008105953,0.0005700083,0.0048188353],"genre_scores_gemma":[0.19763361,0.00024448373,0.79542166,0.0032327648,0.00022111503,0.000107627115,0.000043156928,0.00005659823,0.0030390003],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99640495,0.0000376045,0.00048476725,0.001560563,0.0010184306,0.0004936671],"domain_scores_gemma":[0.9973595,0.00020879885,0.00040902704,0.001722374,0.00020523358,0.00009503681],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00051058363,0.0004791878,0.00042603715,0.001044245,0.00035938591,0.00052832766,0.0045266435,0.0002842361,0.00009747089],"category_scores_gemma":[0.000097965996,0.00044866002,0.00013532212,0.00075765507,0.00044509047,0.0011624376,0.0023577202,0.0010433769,0.000036626567],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009288631,0.000044758603,0.00001193152,0.000015686857,0.000016364864,0.000023093167,0.0010189705,0.09453621,0.00047878796,0.41890186,0.00033667524,0.4846064],"study_design_scores_gemma":[0.00017918783,0.00006997164,0.000014229035,0.00004153335,0.0000054353427,0.000016227352,3.5943748e-7,0.7155934,0.001604473,0.27496833,0.0070579313,0.0004489405],"about_ca_topic_score_codex":0.000017610273,"about_ca_topic_score_gemma":0.000024610563,"teacher_disagreement_score":0.62105715,"about_ca_system_score_codex":0.00063939847,"about_ca_system_score_gemma":0.00049644994,"threshold_uncertainty_score":0.9997965},"labels":[],"label_agreement":null},{"id":"W4313495625","doi":"10.31449/inf.v46i4.3476","title":"OMCOKE: A Machine Learning Outlier-based Overlapping Clustering Technique for Multi-Label Data Analysis","year":2022,"lang":"en","type":"article","venue":"Informatica","topic":"Text and Document Classification Technologies","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":"Fanshawe College","funders":"","keywords":"Cluster analysis; Outlier; Computer science; Anomaly detection; Data mining; Artificial intelligence; Unsupervised learning; Cluster (spacecraft); CURE data clustering algorithm; Machine learning; Pattern recognition (psychology); Correlation clustering","score_opus":0.09572787538383581,"score_gpt":0.3254020660487998,"score_spread":0.22967419066496397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313495625","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002273274,0.000037887185,0.9971337,0.0008799319,0.00006496393,0.0004874584,0.00005508096,0.0007895619,0.00032410194],"genre_scores_gemma":[0.2596744,0.0000035650867,0.7389923,0.00033365123,0.0000048474394,0.000519328,0.00023094138,0.000008555696,0.00023244593],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986808,0.00004002984,0.00043341168,0.00027553595,0.00029887597,0.0002713785],"domain_scores_gemma":[0.9982278,0.00013849078,0.0002712599,0.0012775293,0.00004296303,0.00004199574],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008078322,0.00013513252,0.00021523192,0.00053669425,0.00055782375,0.0002401763,0.002374854,0.000043668308,0.000041843217],"category_scores_gemma":[0.00023701775,0.00013312476,0.00007420864,0.0011683576,0.000033214557,0.000957998,0.002008992,0.00027591092,0.000011483435],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014127874,0.0011722506,0.009117218,0.0008519482,0.0016155185,0.0000184458,0.007230658,0.124631755,0.008533042,0.08329624,0.0066643646,0.7567273],"study_design_scores_gemma":[0.0004715898,0.0000752695,0.00012474162,0.0000057322995,0.000041085623,0.000002648575,0.0002386244,0.980212,0.00041716258,0.00018027474,0.018057782,0.0001731143],"about_ca_topic_score_codex":0.00001998716,"about_ca_topic_score_gemma":0.000009643749,"teacher_disagreement_score":0.8555802,"about_ca_system_score_codex":0.000092260656,"about_ca_system_score_gemma":0.00006702463,"threshold_uncertainty_score":0.542867},"labels":[],"label_agreement":null},{"id":"W4313644201","doi":"10.31219/osf.io/2t53f","title":"An Empirical Study of Supervised and Active Learning Methodologies for Classifying Research Papers","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Text and Document Classification Technologies","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":"University of Toronto","funders":"","keywords":"Machine learning; Artificial intelligence; Computer science; Random forest; Naive Bayes classifier; Supervised learning; Semi-supervised learning; Class (philosophy); Active learning (machine learning); Oversampling; Set (abstract data type); Empirical research; Instance-based learning; Ensemble learning; Support vector machine; Artificial neural network; Mathematics","score_opus":0.536340079485524,"score_gpt":0.5289477743316955,"score_spread":0.007392305153828493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313644201","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":[0.6360734,0.00006638997,0.35413632,0.003957956,0.0003141433,0.0021290565,0.000005464946,0.0025036526,0.0008136121],"genre_scores_gemma":[0.86849624,0.00008934256,0.1303748,0.000013022668,0.000020807065,0.00047804852,0.0000074961213,0.000018679704,0.0005015377],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99681944,0.0009213862,0.00037964946,0.0010302898,0.0004898368,0.00035942334],"domain_scores_gemma":[0.99520457,0.003226309,0.0001676556,0.0010153062,0.00032461534,0.000061533035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028675252,0.00020504952,0.00043363162,0.00063522905,0.000290717,0.00030490273,0.0017126924,0.00033215497,0.000005923935],"category_scores_gemma":[0.0017989274,0.00016850008,0.0000700434,0.0005007811,0.00021712015,0.00026892856,0.0031775972,0.00096125755,0.0000023000514],"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":[0.00017680344,0.00076301827,0.045001034,0.0004655656,0.00036308283,0.00000910195,0.034237646,0.0013396858,0.011431145,0.022571333,0.0010401594,0.88260144],"study_design_scores_gemma":[0.0025969062,0.0067892517,0.25872737,0.00016715447,0.00007898883,0.000002480422,0.36029872,0.15645419,0.021727981,0.19006877,0.0017661303,0.0013220583],"about_ca_topic_score_codex":0.00009598468,"about_ca_topic_score_gemma":0.000045915338,"teacher_disagreement_score":0.88127935,"about_ca_system_score_codex":0.00006477104,"about_ca_system_score_gemma":0.00013059855,"threshold_uncertainty_score":0.68712336},"labels":[],"label_agreement":null},{"id":"W4318604488","doi":"10.1109/ssci51031.2022.10022072","title":"Bayesian Folding-In Using Generalized Dirichlet and Beta-Liouville Kernels for Information Retrieval","year":2022,"lang":"en","type":"article","venue":"2022 IEEE Symposium Series on Computational Intelligence (SSCI)","topic":"Text and Document Classification Technologies","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":"Concordia University","funders":"","keywords":"Latent Dirichlet allocation; Probabilistic latent semantic analysis; Dirichlet distribution; Computer science; Kernel (algebra); Bayesian probability; Topic model; Mixture model; Folding (DSP implementation); Artificial intelligence; Pattern recognition (psychology); Mathematics","score_opus":0.028716928617994703,"score_gpt":0.28293088036610475,"score_spread":0.25421395174811007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318604488","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":[0.05230389,0.000088331944,0.9408935,0.004412625,0.0009873806,0.0007202415,0.00007229832,0.00029465285,0.00022707657],"genre_scores_gemma":[0.94659674,0.00005054476,0.052159052,0.00069332053,0.000046053003,0.00016612188,0.00008430866,0.000016671302,0.00018720218],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978163,0.0001061952,0.00061657507,0.00048871187,0.00062650273,0.0003457078],"domain_scores_gemma":[0.99888134,0.00024781394,0.00030070377,0.00034881744,0.00014855848,0.00007278655],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005804918,0.00023377773,0.0002562477,0.0006089929,0.0006408639,0.00036066823,0.0008235708,0.0000730467,0.00004967697],"category_scores_gemma":[0.000056570014,0.00025539528,0.00008863973,0.0011205415,0.00011589857,0.0015857443,0.00035764943,0.0002371564,0.000009285148],"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":[0.00014474995,0.00010026941,0.0002677151,0.00003243359,0.00002589288,0.000003972441,0.0011344472,0.5459478,0.0013175543,0.44550925,0.00079968985,0.0047162073],"study_design_scores_gemma":[0.00036931227,0.0005293095,0.0002552091,0.000015296864,0.000009670512,0.000036412817,0.0007486224,0.92743367,0.0111540295,0.050821494,0.008212791,0.0004141643],"about_ca_topic_score_codex":0.000031316496,"about_ca_topic_score_gemma":0.000005688848,"teacher_disagreement_score":0.89429283,"about_ca_system_score_codex":0.00028727317,"about_ca_system_score_gemma":0.00014163286,"threshold_uncertainty_score":0.9999898},"labels":[],"label_agreement":null},{"id":"W4318771398","doi":"10.1007/s10489-022-04350-1","title":"Multi-label learning with Relief-based label-specific feature selection","year":2023,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Computer science; Lift (data mining); Redundancy (engineering); Artificial intelligence; Machine learning; Feature selection; Feature (linguistics); Multi-label classification; Pattern recognition (psychology)","score_opus":0.04294951323901801,"score_gpt":0.2772003155390294,"score_spread":0.23425080230001138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318771398","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":[0.004567108,0.00008958543,0.9879714,0.0025456427,0.00012185833,0.00026421706,5.7599175e-7,0.0034884308,0.0009511804],"genre_scores_gemma":[0.7257293,0.00016423885,0.2709945,0.00017244714,0.00002775201,0.0001640207,0.000013846675,0.000023977695,0.0027098947],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852943,0.000023209057,0.00018170258,0.00059093954,0.00031226486,0.00036242921],"domain_scores_gemma":[0.99913275,0.00011973016,0.00012349014,0.00047460152,0.00009387983,0.00005554793],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00021707738,0.00019125747,0.00014301021,0.00026601044,0.0004098996,0.00021104695,0.0008803118,0.00013507031,0.000018817967],"category_scores_gemma":[0.000031391573,0.00016211369,0.00002264576,0.0023632701,0.0001171793,0.00021730142,0.00013775475,0.00043155666,0.0009793094],"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":[0.00003628072,0.00015813769,0.0006288547,0.000022606866,0.000018523313,0.000009236445,0.0004663332,0.003490547,0.044828523,0.19775565,0.00633715,0.7462482],"study_design_scores_gemma":[0.00061955635,0.00037840527,0.0017822734,0.000052536165,0.000008131525,0.000008602619,0.0006609108,0.6288998,0.31891397,0.0049141035,0.043028314,0.00073341036],"about_ca_topic_score_codex":0.0000051499737,"about_ca_topic_score_gemma":0.0000065768945,"teacher_disagreement_score":0.74551475,"about_ca_system_score_codex":0.00008236603,"about_ca_system_score_gemma":0.0000526263,"threshold_uncertainty_score":0.99979854},"labels":[],"label_agreement":null},{"id":"W4321851655","doi":"10.1007/978-3-031-24340-0_22","title":"Basic and Depression Specific Emotions Identification in Tweets: Multi-label Classification Experiments","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Emotion classification; Artificial intelligence; Identification (biology); Macro; Deep learning; Machine learning; Sentiment analysis; Empirical research; Natural language processing","score_opus":0.07319826536210684,"score_gpt":0.3081987816288172,"score_spread":0.23500051626671037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321851655","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":[0.001495426,0.0005355702,0.9942092,0.00096403033,0.0013555776,0.0005685847,0.0000048254897,0.0005372569,0.00032954535],"genre_scores_gemma":[0.7388014,0.0008791104,0.25826856,0.00020609751,0.00016776331,0.00011742314,0.000034331097,0.00006138554,0.0014638954],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963607,0.000042580315,0.00070840574,0.0017318128,0.00069923454,0.0004572625],"domain_scores_gemma":[0.9975938,0.00025784026,0.00039127603,0.0014940517,0.00016574563,0.00009727092],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007296642,0.0004005864,0.0003481254,0.0017142728,0.00027995824,0.0007068734,0.002113332,0.00037714597,0.000007276624],"category_scores_gemma":[0.00013449536,0.00039246175,0.000050319926,0.0011277095,0.0005697095,0.0010524709,0.0010162456,0.00057919294,0.00010952145],"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":[0.0000035559606,0.00009355096,0.0010250544,0.000025181229,0.0000049286173,0.000015287831,0.000865158,0.00035639273,0.006272244,0.030083062,0.00005243748,0.96120316],"study_design_scores_gemma":[0.0011143553,0.000081039485,0.05361016,0.00064622477,0.0000071677946,0.000018816474,0.000010798624,0.7862521,0.0087490715,0.14782673,0.00062167377,0.0010618957],"about_ca_topic_score_codex":0.000011932537,"about_ca_topic_score_gemma":0.000045631805,"teacher_disagreement_score":0.96014124,"about_ca_system_score_codex":0.0003508509,"about_ca_system_score_gemma":0.00013759611,"threshold_uncertainty_score":0.9998527},"labels":[],"label_agreement":null},{"id":"W4327499178","doi":"10.1007/978-3-031-28241-6","title":"Advances in Information Retrieval","year":2023,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Leibniz-Gemeinschaft; University of Massachusetts Amherst; City, University of London; National Institute of Standards and Technology; La Rochelle Université; National Institute of Informatics; Indian Institute of Science Education and Research Mohali; University of Chinese Academy of Sciences; National Institute of Technology Hamirpur; Université de Lyon; Masarykova Univerzita; Ural Federal University; Université de Nantes; Stockholms Universitet; Institut National des Sciences Appliquées de Lyon; Universität Duisburg-Essen; Università di Pisa; Technische Universität Berlin; Bauhaus-Universität Weimar; Universidad de Granada; Università di Bologna; Universität Regensburg; Universitetet i Bergen; University of Windsor; Technische Universität Wien; Radboud Universiteit; University of Waterloo; Commonwealth Scientific and Industrial Research Organisation; Orta Doğu Teknik Üniversitesi; Instituto Superior Técnico; Université de Bretagne Occidentale; Tsinghua University; Chinese Academy of Sciences; Birkbeck, University of London; Universidade de Lisboa; Renmin University of China; Universität Innsbruck; Technische Universiteit Delft; Région Normandie; University of Minnesota; TU Graz, Internationale Beziehungen und Mobilitätsprogramme; Universiteit Utrecht; RMIT University; Haute école Spécialisée de Suisse Occidentale; University of Southampton; Universidade da Coruña; Istituto di Scienza e Tecnologie dell'Informazione; Universidad Nacional de Educación a Distancia; Universiteit Leiden; York University; University of Glasgow; Universität Passau; Universidade do Porto; Dublin City University; Politecnico di Torino; Friedrich-Schiller-Universität Jena; Universitetet i Stavanger; University of Regina; Université Grenoble Alpes; University of Southern Maine; Centre National de la Recherche Scientifique; University of Roehampton; Norges Teknisk-Naturvitenskapelige Universitet; Sun Yat-sen University; Universiteit van Amsterdam; Universidade de Santiago de Compostela; Università degli Studi di Cagliari; Aix-Marseille Université; University of Wolverhampton; Universidade Federal de Minas Gerais; Chinese University of Hong Kong; Aalborg Universitet; Kaiser Permanente; Indian Institute of Technology Kharagpur; Indian Institute of Science; Qatar University; Universidad Autónoma de Madrid; University of Tsukuba; Georgetown University; Universitatea din București; Università degli Studi di Padova; Zürcher Hochschule für Angewandte Wissenschaften; Johns Hopkins University; Indian National Science Academy","keywords":"Computer science; Information retrieval; State (computer science); Artificial intelligence; Programming language","score_opus":0.012864160102574714,"score_gpt":0.2606042818289115,"score_spread":0.24774012172633678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327499178","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000028601648,0.00038653152,0.9923408,0.0013356637,0.0017010197,0.0003046065,0.0000024400501,0.0007023911,0.0031979342],"genre_scores_gemma":[0.16093746,0.0042216424,0.82248765,0.0046597524,0.0010153549,0.00013990686,0.00012060557,0.0001083941,0.006309245],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973144,0.000027714354,0.00054458977,0.0007289505,0.00086526724,0.00051911187],"domain_scores_gemma":[0.99807113,0.0003943428,0.00028439425,0.001059126,0.00013294037,0.00005803732],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00084053294,0.00028995692,0.0003169416,0.0019287794,0.00011707083,0.0006179182,0.00362444,0.00030123064,0.0000041706753],"category_scores_gemma":[0.00037927032,0.00026711528,0.0000567943,0.0032574306,0.0004240106,0.0038951002,0.0011931716,0.0006715202,0.00020552296],"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":[0.0000033309104,0.0000103197,0.00009167994,0.000037717804,9.225093e-7,0.000011655057,0.00045356626,0.0071284403,0.000010975355,0.014438877,0.00016251334,0.97765],"study_design_scores_gemma":[0.00039152827,0.0001386987,0.0009093247,0.0003928367,0.0000018923287,0.000012360451,0.0000013221074,0.33980167,0.0012870021,0.6325015,0.02386153,0.0007003275],"about_ca_topic_score_codex":0.000004471214,"about_ca_topic_score_gemma":0.000043669945,"teacher_disagreement_score":0.9769497,"about_ca_system_score_codex":0.00055489683,"about_ca_system_score_gemma":0.00079187524,"threshold_uncertainty_score":0.9999781},"labels":[],"label_agreement":null},{"id":"W4327644040","doi":"10.1007/978-3-031-28238-6","title":"Advances in Information Retrieval","year":2023,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Zürcher Hochschule für Angewandte Wissenschaften; Leibniz-Gemeinschaft; National Institute of Standards and Technology; La Rochelle Université; Université de Caen Normandie; National Institute of Informatics; Indian Institute of Science Education and Research Mohali; University of Chinese Academy of Sciences; National Institute of Technology Hamirpur; Université de Lyon; Masarykova Univerzita; Universität Konstanz; Ural Federal University; Université de Nantes; Stockholms Universitet; Universität Leipzig; Universität Duisburg-Essen; Università degli Studi di Udine; Università di Pisa; Universidade Federal de Minas Gerais; University of Cape Town; Tsinghua University; Chinese Academy of Sciences; Université de Bretagne Occidentale; Georgetown University; University of Tsukuba; Technion-Israel Institute of Technology; Università di Bologna; Universitetet i Bergen; University of Windsor; Technische Universität Wien; Radboud Universiteit; University of Waterloo; Commonwealth Scientific and Industrial Research Organisation; Orta Doğu Teknik Üniversitesi; Universitatea din București; Università degli Studi di Padova; Universidad de Granada; Universität Innsbruck; Technische Universiteit Delft; Université de Neuchâtel; Région Normandie; TU Graz, Internationale Beziehungen und Mobilitätsprogramme; Universiteit Utrecht; National Institute of Advanced Industrial Science and Technology; RMIT University; Universidade da Coruña; Universidad Nacional de Educación a Distancia; University of Glasgow; York University; Universiteit Leiden; University of Regina; Université Grenoble Alpes; Universitetet i Stavanger; Universität Passau; Centre National de la Recherche Scientifique; Aix-Marseille Université; University of Wolverhampton; Universidade de Santiago de Compostela; Università degli Studi di Cagliari; Universidade do Porto; Dublin City University; Politecnico di Torino; Friedrich-Schiller-Universität Jena; Norges Teknisk-Naturvitenskapelige Universitet; Universiteit van Amsterdam; Qatar University; Universidad Autónoma de Madrid; Renmin University of China; University of Otago; Aalborg Universitet; Kaiser Permanente; Indian Institute of Technology Kharagpur; Indian Institute of Science; Sorbonne Université; Accenture","keywords":"Computer science; Information retrieval; State (computer science); Human–computer information retrieval; Artificial intelligence; Search engine; Programming language","score_opus":0.012864160102574714,"score_gpt":0.2606042818289115,"score_spread":0.24774012172633678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327644040","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000028601648,0.00038653152,0.9923408,0.0013356637,0.0017010197,0.0003046065,0.0000024400501,0.0007023911,0.0031979342],"genre_scores_gemma":[0.16093746,0.0042216424,0.82248765,0.0046597524,0.0010153549,0.00013990686,0.00012060557,0.0001083941,0.006309245],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973144,0.000027714354,0.00054458977,0.0007289505,0.00086526724,0.00051911187],"domain_scores_gemma":[0.99807113,0.0003943428,0.00028439425,0.001059126,0.00013294037,0.00005803732],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00084053294,0.00028995692,0.0003169416,0.0019287794,0.00011707083,0.0006179182,0.00362444,0.00030123064,0.0000041706753],"category_scores_gemma":[0.00037927032,0.00026711528,0.0000567943,0.0032574306,0.0004240106,0.0038951002,0.0011931716,0.0006715202,0.00020552296],"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":[0.0000033309104,0.0000103197,0.00009167994,0.000037717804,9.225093e-7,0.000011655057,0.00045356626,0.0071284403,0.000010975355,0.014438877,0.00016251334,0.97765],"study_design_scores_gemma":[0.00039152827,0.0001386987,0.0009093247,0.0003928367,0.0000018923287,0.000012360451,0.0000013221074,0.33980167,0.0012870021,0.6325015,0.02386153,0.0007003275],"about_ca_topic_score_codex":0.000004471214,"about_ca_topic_score_gemma":0.000043669945,"teacher_disagreement_score":0.9769497,"about_ca_system_score_codex":0.00055489683,"about_ca_system_score_gemma":0.00079187524,"threshold_uncertainty_score":0.9999781},"labels":[],"label_agreement":null},{"id":"W4327657211","doi":"10.1007/978-3-031-28244-7","title":"Advances in Information Retrieval","year":2023,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Massachusetts Amherst; Universität Innsbruck; Universität Konstanz; Universität Leipzig; Universität Duisburg-Essen; Università di Pisa; Wuhan University; Universidade do Porto; National Institute of Standards and Technology; Technion-Israel Institute of Technology; Rheinische Friedrich-Wilhelms-Universität Bonn; University of Cape Town; Sichuan University; University of Waterloo; Institute of Computing Technology, Chinese Academy of Sciences; Université de Caen Normandie; University of Crete; RMIT University; Tsinghua University; Edinburgh Napier University; Accenture; Renmin University of China; Università degli Studi di Milano-Bicocca; Chinese Academy of Sciences; Technische Universiteit Delft; Universiteit van Amsterdam; Dublin City University; University College London; University of Essex; Sorbonne Université; Università degli Studi di Milano; York University; Montclair State University; National Institute of Advanced Industrial Science and Technology; Universiteit Leiden; University of Otago; Université de Neuchâtel; Région Normandie; Università degli Studi di Udine; Johns Hopkins University","keywords":"Computer science; Information retrieval; State (computer science); Artificial intelligence; Programming language","score_opus":0.012864160102574714,"score_gpt":0.2606042818289115,"score_spread":0.24774012172633678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327657211","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000028601648,0.00038653152,0.9923408,0.0013356637,0.0017010197,0.0003046065,0.0000024400501,0.0007023911,0.0031979342],"genre_scores_gemma":[0.16093746,0.0042216424,0.82248765,0.0046597524,0.0010153549,0.00013990686,0.00012060557,0.0001083941,0.006309245],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973144,0.000027714354,0.00054458977,0.0007289505,0.00086526724,0.00051911187],"domain_scores_gemma":[0.99807113,0.0003943428,0.00028439425,0.001059126,0.00013294037,0.00005803732],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00084053294,0.00028995692,0.0003169416,0.0019287794,0.00011707083,0.0006179182,0.00362444,0.00030123064,0.0000041706753],"category_scores_gemma":[0.00037927032,0.00026711528,0.0000567943,0.0032574306,0.0004240106,0.0038951002,0.0011931716,0.0006715202,0.00020552296],"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":[0.0000033309104,0.0000103197,0.00009167994,0.000037717804,9.225093e-7,0.000011655057,0.00045356626,0.0071284403,0.000010975355,0.014438877,0.00016251334,0.97765],"study_design_scores_gemma":[0.00039152827,0.0001386987,0.0009093247,0.0003928367,0.0000018923287,0.000012360451,0.0000013221074,0.33980167,0.0012870021,0.6325015,0.02386153,0.0007003275],"about_ca_topic_score_codex":0.000004471214,"about_ca_topic_score_gemma":0.000043669945,"teacher_disagreement_score":0.9769497,"about_ca_system_score_codex":0.00055489683,"about_ca_system_score_gemma":0.00079187524,"threshold_uncertainty_score":0.9999781},"labels":[],"label_agreement":null},{"id":"W4365518837","doi":"10.54254/2755-2721/2/20220540","title":"A Novel Method for Text Classification Dealing with Local Data Structures and High Data Dimensionality","year":2023,"lang":"en","type":"article","venue":"Applied and Computational Engineering","topic":"Text and Document Classification Technologies","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":"University of British Columbia","funders":"","keywords":"Computer science; Curse of dimensionality; Pattern recognition (psychology); Artificial intelligence; k-nearest neighbors algorithm; Feature vector; Correlation; Text categorization; Data mining; Data set; Set (abstract data type); Support vector machine; Mathematics","score_opus":0.060627553714363805,"score_gpt":0.29863529543887635,"score_spread":0.23800774172451256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4365518837","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":[0.0027419068,0.00004743331,0.9954544,0.0010882918,0.000034704895,0.00016398178,0.00006828627,0.0003893635,0.000011647336],"genre_scores_gemma":[0.50988233,0.0000051936745,0.48965645,0.000034284287,0.000013458716,0.00001528695,0.00038478198,0.0000055018254,0.0000026953007],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99905366,0.0000035306823,0.00014413332,0.0005067694,0.00016427522,0.00012765331],"domain_scores_gemma":[0.99897337,0.0003802542,0.000053580512,0.00051858614,0.00003476261,0.000039475086],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026022465,0.00010650971,0.00010843635,0.00009455433,0.00011636418,0.00011552248,0.00055474904,0.000041729138,6.8273465e-7],"category_scores_gemma":[0.00002475916,0.00009262518,0.0000052522346,0.00022619619,0.0000386847,0.00028441698,0.0006077415,0.00006752712,0.0000011318599],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000053975546,0.000005546889,0.000013129804,0.000023214388,0.000019671916,2.480068e-7,0.000026397733,0.06505388,0.0017749688,0.83920145,0.00008826833,0.09378783],"study_design_scores_gemma":[0.00031431307,0.000010476614,0.014698951,0.000006893061,0.000008090632,0.000009907784,0.00005037416,0.9546636,0.00009890628,0.029036293,0.0009813552,0.000120859906],"about_ca_topic_score_codex":0.000009177982,"about_ca_topic_score_gemma":0.0000013211011,"teacher_disagreement_score":0.8896097,"about_ca_system_score_codex":0.000008983395,"about_ca_system_score_gemma":0.000025728337,"threshold_uncertainty_score":0.37771454},"labels":[],"label_agreement":null},{"id":"W4366150675","doi":"10.2139/ssrn.4420262","title":"Criteria Rating Prediction with Aspect Representation Learning for Multi-Criteria Recommendation","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Representation (politics); Computer science; Artificial intelligence; Machine learning; Natural language processing; Political science","score_opus":0.07678940015155605,"score_gpt":0.3574067475961836,"score_spread":0.2806173474446276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366150675","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":[0.005879793,0.00015778869,0.98592985,0.005037268,0.0011446872,0.0006026333,0.000007024239,0.0011678637,0.0000730703],"genre_scores_gemma":[0.8987168,0.00180988,0.09523736,0.00004381042,0.00061600114,0.00041551745,0.00040350453,0.00008466204,0.0026724595],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99692327,0.00021346555,0.00058905996,0.00071399694,0.0002933331,0.0012668702],"domain_scores_gemma":[0.99823767,0.00012929103,0.0008363503,0.0004405624,0.00030483527,0.00005129172],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0022388436,0.00028582467,0.00028910875,0.00044138354,0.0005589316,0.0010225333,0.00084558787,0.00023948739,0.000011970377],"category_scores_gemma":[0.0004133279,0.00026213133,0.00013691702,0.00035982602,0.000038950297,0.00093777815,0.00030869534,0.002600206,0.000014009892],"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":[0.00036452294,0.00035676095,0.00828854,0.00028053185,0.0011985179,0.000009716167,0.0037373097,0.0058531896,0.008536702,0.19799992,0.0050865756,0.7682877],"study_design_scores_gemma":[0.0022857354,0.0012073279,0.0034370478,0.00028263876,0.00010437952,0.00020721178,0.004976523,0.64179647,0.0023591043,0.34052846,0.0020620553,0.0007530617],"about_ca_topic_score_codex":0.00004212741,"about_ca_topic_score_gemma":0.00014762093,"teacher_disagreement_score":0.892837,"about_ca_system_score_codex":0.0010490619,"about_ca_system_score_gemma":0.0010784394,"threshold_uncertainty_score":0.9999831},"labels":[],"label_agreement":null},{"id":"W4368755400","doi":"10.48550/arxiv.2305.02156","title":"Zero-Shot Listwise Document Reranking with a Large Language Model","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Pointwise; Ranking (information retrieval); Relevance (law); Information retrieval; Encoder; Pointwise mutual information; Task (project management); Natural language processing; Zero (linguistics); Language model; Identifier; Artificial intelligence; Mathematics; Mutual information; Linguistics","score_opus":0.09702878345608794,"score_gpt":0.2197408233135964,"score_spread":0.12271203985750846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4368755400","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":[0.096284054,0.000060589926,0.89834106,0.0006913357,0.00020122573,0.00033917834,0.00001952341,0.0022789675,0.0017840596],"genre_scores_gemma":[0.98235655,0.00017798951,0.006363506,0.00010181769,0.000020216914,0.0000063373764,0.000029075618,0.000028113007,0.010916393],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99787956,0.00005739363,0.00020073979,0.0012255044,0.00017197097,0.00046482251],"domain_scores_gemma":[0.99751943,0.00006381717,0.00026763068,0.0019429411,0.00010058602,0.0001055845],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002719708,0.00033788296,0.0003087277,0.00041715876,0.00019748353,0.00028874938,0.0024157101,0.00027185376,0.000017709106],"category_scores_gemma":[0.000027295722,0.0003340349,0.00014146557,0.00075934065,0.000094707015,0.000514687,0.0027717536,0.0005549284,0.00016106888],"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":[0.000030399702,0.00009359215,0.0008754882,0.00008095171,0.000100711564,0.0004676621,0.0011818573,0.14951408,0.000087670815,0.84539974,0.0014833405,0.0006845027],"study_design_scores_gemma":[0.0008350962,0.0000643144,0.00036829742,0.00017664683,0.00006611396,0.0000035965738,0.00047625692,0.8257931,0.0005449471,0.17012319,0.0008139885,0.0007344678],"about_ca_topic_score_codex":0.00009166445,"about_ca_topic_score_gemma":0.00008196499,"teacher_disagreement_score":0.89197755,"about_ca_system_score_codex":0.00023778666,"about_ca_system_score_gemma":0.00018534002,"threshold_uncertainty_score":0.9999112},"labels":[],"label_agreement":null},{"id":"W4376269558","doi":"10.1016/j.knosys.2023.110602","title":"SPRF: A semantic Pseudo-relevance Feedback enhancement for information retrieval via ConceptNet","year":2023,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; York University","funders":"Natural Science Foundation of Zhejiang Province; Natural Sciences and Engineering Research Council of Canada; China Scholarship Council; Hebei Normal University","keywords":"Computer science; Relevance feedback; Information retrieval; Relevance (law); Query expansion; Baseline (sea); Process (computing); Learning to rank; Ranking (information retrieval); Term Discrimination; Term (time); Concept search; Artificial intelligence; Data mining; Search engine; Web search query; Image retrieval","score_opus":0.0248971567349397,"score_gpt":0.27642516854207805,"score_spread":0.25152801180713835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376269558","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":[0.008868387,0.0003864373,0.9824845,0.001019759,0.002464795,0.0014233972,0.000013782872,0.0019334921,0.0014054285],"genre_scores_gemma":[0.99385816,0.000020718873,0.0028099008,0.00007533568,0.00011140567,0.00042768673,0.000073173804,0.000014613939,0.0026089998],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99807143,0.00007354506,0.0006353374,0.00039023237,0.00036278617,0.00046666688],"domain_scores_gemma":[0.99802166,0.00035913612,0.00032717158,0.0008308101,0.00037650552,0.00008470891],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007400268,0.00022843982,0.00029424476,0.0003849268,0.00023473441,0.00038136894,0.0009782113,0.00015144527,0.000007781394],"category_scores_gemma":[0.00023359411,0.0002119266,0.000110979854,0.001412528,0.00008744326,0.0008785721,0.00013906747,0.00011737764,0.002053143],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031443528,0.00063888676,0.0012950846,0.004838084,0.00024768934,0.0000117054415,0.0067198602,0.0028210615,0.06409614,0.4155193,0.253009,0.25048876],"study_design_scores_gemma":[0.0017778011,0.00033356747,0.00038574357,0.0002331673,0.00001525964,0.0000036703507,0.0003584584,0.6811158,0.0498031,0.0011795388,0.26430157,0.00049235433],"about_ca_topic_score_codex":0.0000084235535,"about_ca_topic_score_gemma":0.0000042907686,"teacher_disagreement_score":0.98498976,"about_ca_system_score_codex":0.00018672073,"about_ca_system_score_gemma":0.00018236654,"threshold_uncertainty_score":0.99872386},"labels":[],"label_agreement":null},{"id":"W4378418331","doi":"10.18280/ria.370219","title":"BalBERT: A New Approach to Improving Dataset Balancing for Text Classification","year":2023,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Natural language processing; Information retrieval; Artificial intelligence","score_opus":0.09182440662175224,"score_gpt":0.31381214502686405,"score_spread":0.22198773840511182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378418331","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":[0.00060099724,0.00003264205,0.9896689,0.005868196,0.000297297,0.00065913395,0.00003881934,0.0008113375,0.0020226631],"genre_scores_gemma":[0.7852168,0.000050697374,0.19554225,0.00072137144,0.00023915221,0.00062767626,0.0006701998,0.000046321406,0.016885545],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981253,0.000023628018,0.00042428632,0.0007835951,0.00018720987,0.00045595798],"domain_scores_gemma":[0.9980976,0.00024978648,0.0001329499,0.0012959202,0.00007780301,0.00014591322],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00056248903,0.0001690814,0.00017794498,0.00032663884,0.00026745556,0.00031602755,0.0015005587,0.00009647251,0.000023646538],"category_scores_gemma":[0.00053063396,0.00016838459,0.00007186236,0.0016598979,0.000039737864,0.00048069193,0.00035690828,0.00011826376,0.0024320493],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009453669,0.00008078614,0.00006232543,0.0000711818,0.000009831642,0.0000010290605,0.0012031326,0.0050454354,0.021729276,0.25243378,0.15803647,0.5613173],"study_design_scores_gemma":[0.000043203734,0.000050757124,0.00013684518,0.00002019234,0.0000052217783,0.000004415799,0.00086946867,0.83643824,0.027210405,0.0063767177,0.12860273,0.00024181695],"about_ca_topic_score_codex":0.000042408636,"about_ca_topic_score_gemma":0.0000063261227,"teacher_disagreement_score":0.8313928,"about_ca_system_score_codex":0.000073102536,"about_ca_system_score_gemma":0.000081010425,"threshold_uncertainty_score":0.99834466},"labels":[],"label_agreement":null},{"id":"W4382202851","doi":"10.1609/aaai.v37i11.26579","title":"Multi-Mask Label Mapping for Prompt-Based Learning","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Text and Document Classification Technologies","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":"University of Ottawa","funders":"Fundamental Research Funds for the Central Universities; State Key Laboratory of Software Development Environment","keywords":"Computer science; Natural language processing; Artificial intelligence; Task (project management); Context (archaeology); Exploit; Word (group theory); Machine learning; Linguistics","score_opus":0.19232711549277473,"score_gpt":0.3382618546859622,"score_spread":0.14593473919318747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382202851","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":[0.14582004,0.000027689926,0.81909275,0.027647575,0.0007992774,0.0019035457,0.000008868757,0.0026151915,0.0020850408],"genre_scores_gemma":[0.9622319,0.000014389481,0.036511797,0.00010313263,0.000023155326,0.00018046536,0.0000012927512,0.000012597119,0.00092132046],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983854,0.0000102040085,0.0004248776,0.00047857384,0.00033151096,0.00036939696],"domain_scores_gemma":[0.99870586,0.00014960674,0.00035629762,0.000274202,0.00046716435,0.000046894947],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005864269,0.00018024378,0.00020360721,0.0002649336,0.00032439682,0.0002786772,0.0020002478,0.00009868916,0.000013134642],"category_scores_gemma":[0.0009702646,0.00013963076,0.00010002564,0.0012660598,0.00019406938,0.00032208447,0.00032568988,0.0002459625,0.00013734157],"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":[0.000019857427,0.000108198175,0.00039684883,0.00007352163,0.000010057201,1.7186028e-7,0.00078767317,0.00015302752,0.14870878,0.71176344,0.00033912723,0.13763931],"study_design_scores_gemma":[0.000055109977,0.00013325433,0.00028339535,0.00012338547,0.0000040923287,3.3791062e-7,0.00076490885,0.49582767,0.44178522,0.059933115,0.0009166849,0.00017284723],"about_ca_topic_score_codex":0.000006295232,"about_ca_topic_score_gemma":0.0000018787766,"teacher_disagreement_score":0.8164118,"about_ca_system_score_codex":0.000036705278,"about_ca_system_score_gemma":0.00008537223,"threshold_uncertainty_score":0.56939775},"labels":[],"label_agreement":null},{"id":"W4382931899","doi":"10.31436/iiumej.v24i2.2893","title":"Editorial","year":2023,"lang":"en","type":"editorial","venue":"IIUM Engineering Journal","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Islam; Engineering; Library science; Management; Theology; Philosophy","score_opus":0.006782703567458102,"score_gpt":0.23237174770403143,"score_spread":0.22558904413657332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382931899","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.4743884e-7,0.00012481996,0.176483,0.0003169833,0.8213573,0.000038569087,0.000006670395,0.0016180348,0.000054057065],"genre_scores_gemma":[0.000010098186,0.00032622446,0.007586758,0.0000024941353,0.99100685,0.000014299739,0.000011310418,0.00004707987,0.0009948566],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976387,0.000016554639,0.0003881092,0.00032444607,0.0011911092,0.00044110764],"domain_scores_gemma":[0.9981741,0.00061342143,0.00022700019,0.0005889105,0.00026750358,0.0001291178],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000562248,0.00027550865,0.00028210517,0.00047708568,0.00012531498,0.00093843584,0.0023194596,0.0008170885,0.000008049052],"category_scores_gemma":[0.0023156716,0.00025846975,0.00015633395,0.0004578636,0.000018565734,0.00048461027,0.00036876855,0.0020821374,0.00031263288],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011482462,0.0000068853396,2.842838e-7,0.000016537266,0.000028272612,0.000018105604,0.000023658708,0.00037928854,0.000058146357,0.00088557287,0.9968641,0.0017180034],"study_design_scores_gemma":[0.00019724487,0.000043254226,0.0000030772196,0.00006973156,0.000008271207,0.0000057313287,0.0000034422346,0.002121699,0.000048732738,0.00054555014,0.9966772,0.00027606275],"about_ca_topic_score_codex":0.0000023864068,"about_ca_topic_score_gemma":3.2344676e-7,"teacher_disagreement_score":0.16964957,"about_ca_system_score_codex":0.00019363503,"about_ca_system_score_gemma":0.0003042101,"threshold_uncertainty_score":0.99998677},"labels":[],"label_agreement":null},{"id":"W4384570015","doi":"10.23977/acss.2023.070516","title":"Prediction and Classification Model Based on Wordle's Date","year":2023,"lang":"en","type":"article","venue":"Advances in Computer Signals and Systems","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Interpretability; Popularity; Computer science; Cluster analysis; Interval (graph theory); Word (group theory); A priori and a posteriori; Reliability (semiconductor); Artificial intelligence; Promotion (chess); Machine learning; Mathematics; Psychology","score_opus":0.04978831599525085,"score_gpt":0.2853793996480487,"score_spread":0.23559108365279785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384570015","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":[0.009995558,0.00074154505,0.98697066,0.0007556391,0.00039322872,0.00023344427,0.000005551155,0.00052962324,0.0003747448],"genre_scores_gemma":[0.99111545,0.000718445,0.007870705,0.000093005896,0.00003936895,0.00007945752,0.00000848948,0.000005949222,0.00006913941],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988829,0.000055536642,0.0002635852,0.00043225804,0.00019314868,0.00017260207],"domain_scores_gemma":[0.99932146,0.00015509826,0.00010029334,0.00035156755,0.00003116864,0.00004040169],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035557518,0.00011761986,0.00015187691,0.00028164903,0.00009150209,0.0002204331,0.00027680778,0.000064449705,3.9429992e-7],"category_scores_gemma":[0.000010494506,0.000101631005,0.000015453828,0.00044629766,0.000048050555,0.00070470053,0.00010103985,0.00008715925,0.000010428923],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011861845,0.000052413197,0.0061336616,0.00011200364,0.000005984038,0.000005906689,0.00026630476,0.35597205,0.00065635925,0.14537291,0.0009840499,0.49042648],"study_design_scores_gemma":[0.00023572208,0.00007807375,0.00502644,0.00008704965,0.0000011367916,0.0000016574426,0.00002708953,0.9879311,0.000047844132,0.004015728,0.002444656,0.00010350751],"about_ca_topic_score_codex":0.0000021259011,"about_ca_topic_score_gemma":0.0000014239952,"teacher_disagreement_score":0.9811199,"about_ca_system_score_codex":0.0000157944,"about_ca_system_score_gemma":0.000014598534,"threshold_uncertainty_score":0.4144392},"labels":[],"label_agreement":null},{"id":"W4384788087","doi":"10.1007/978-3-031-36819-6_4","title":"A Selective Supervised Latent Beta-Liouville Allocation for Document Classification","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Latent Dirichlet allocation; Inference; Artificial intelligence; Bernoulli's principle; Dirichlet distribution; Machine learning; Simple (philosophy); Prior probability; Gibbs sampling; Topic model; Word (group theory); Pattern recognition (psychology); Bayesian probability; Mathematics","score_opus":0.041366077434778034,"score_gpt":0.2744832432710408,"score_spread":0.23311716583626274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384788087","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005634531,0.00012708185,0.98853767,0.0068052243,0.0012789547,0.0012836681,0.000008137548,0.0009522107,0.00095069804],"genre_scores_gemma":[0.4670009,0.00031083392,0.5258436,0.0011457594,0.00046206033,0.0006546789,0.00010740074,0.00011756206,0.0043571643],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99607533,0.000028388937,0.00065228075,0.0017413811,0.00087671453,0.0006258818],"domain_scores_gemma":[0.9969337,0.0005346711,0.0004045327,0.0015068024,0.0005102267,0.00011009606],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000951001,0.00048335895,0.00045617294,0.0012335451,0.00035934075,0.00065716996,0.0029863354,0.00041258815,0.0000095175],"category_scores_gemma":[0.00014512084,0.00044785847,0.0001726618,0.0010990674,0.000424973,0.00078522495,0.00076161505,0.00047182068,0.000113183036],"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":[0.000009641351,0.000033467408,0.000049407026,0.000050721763,0.000025501857,0.0000034051359,0.0005024795,0.00291819,0.0008902133,0.37385234,0.0002561769,0.62140846],"study_design_scores_gemma":[0.00055180467,0.00031695835,0.00103291,0.00019599994,0.00001840894,0.000006590604,0.0000013893349,0.42826012,0.008812909,0.5574574,0.002539144,0.0008064136],"about_ca_topic_score_codex":0.000016078797,"about_ca_topic_score_gemma":0.000055203735,"teacher_disagreement_score":0.620602,"about_ca_system_score_codex":0.0006552235,"about_ca_system_score_gemma":0.00050369865,"threshold_uncertainty_score":0.99979734},"labels":[],"label_agreement":null},{"id":"W4384934940","doi":"10.1007/s00521-023-08793-6","title":"Multi-graph embedding for partial label learning","year":2023,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Dongguan Science and Technology Bureau","keywords":"Computer science; Graph; Artificial intelligence; Embedding; Graph embedding; Pattern recognition (psychology); Classifier (UML); Theoretical computer science; Machine learning; Data mining; Algorithm","score_opus":0.055677746595602796,"score_gpt":0.34710596727854287,"score_spread":0.29142822068294005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384934940","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":[0.044578794,0.000082373364,0.9511379,0.0018465737,0.000052202897,0.0002642393,0.0000011333453,0.0019832202,0.0000535606],"genre_scores_gemma":[0.95104027,0.000029028728,0.048425373,0.00008331822,0.000059620532,0.00015739932,0.0000105756635,0.000007153527,0.00018727897],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925894,0.000015819964,0.00014292084,0.00030688173,0.000070953494,0.00020446657],"domain_scores_gemma":[0.9994453,0.00019740414,0.00006933887,0.00021020854,0.000038953633,0.000038782786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014923069,0.000079403326,0.000080957456,0.00010505383,0.00056913454,0.00016263749,0.00031776362,0.00003998876,4.7069594e-7],"category_scores_gemma":[0.000029788414,0.00007699773,0.000029686635,0.0005444561,0.000042765958,0.00011094817,0.00018714956,0.00010793356,0.000020909827],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020348978,0.000051536743,0.0022848947,0.000028671355,0.0000106951575,5.5674604e-7,0.00035230638,0.0035386952,0.01234541,0.1867188,0.001949967,0.79271644],"study_design_scores_gemma":[0.00026008463,0.000020249327,0.0018982247,0.0000049345786,0.000002405688,0.0000019706106,0.0000856207,0.966763,0.00075264194,0.0024027112,0.027700087,0.00010804657],"about_ca_topic_score_codex":0.0000014802999,"about_ca_topic_score_gemma":1.9355703e-7,"teacher_disagreement_score":0.96322435,"about_ca_system_score_codex":0.000006185228,"about_ca_system_score_gemma":0.000006622052,"threshold_uncertainty_score":0.43773806},"labels":[],"label_agreement":null},{"id":"W4385078273","doi":"10.18280/isi.280317","title":"A Distributed Densely Connected Convolutional Network Approach for Enhanced Recognition of Health-Related Topics: A Societal Analysis Case Study","year":2023,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Social network analysis; Convolutional neural network; Computer network; Artificial intelligence; World Wide Web; Social media","score_opus":0.041564059756349324,"score_gpt":0.2769928398837452,"score_spread":0.23542878012739585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385078273","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":[0.32958427,0.000029336754,0.66878533,0.00010101404,0.00008623738,0.0007168606,0.00006353497,0.00056766934,0.00006575699],"genre_scores_gemma":[0.9827602,0.0000070125684,0.015297312,0.000025379999,0.000013914449,0.00035394097,0.0015178155,0.0000040755845,0.00002036901],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981973,0.00011486434,0.000967936,0.00019808224,0.00023158905,0.00029018382],"domain_scores_gemma":[0.99830157,0.00014552347,0.00075003906,0.0003034614,0.00045868574,0.00004070255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009381065,0.00013556032,0.00033582374,0.0003900319,0.00039915493,0.00014460301,0.00027489313,0.000109961424,0.0000058378287],"category_scores_gemma":[0.00026345035,0.00013448129,0.00014523677,0.0032682314,0.00009384331,0.0013173068,0.000095473435,0.000085934385,0.000010774596],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017161357,0.0008847178,0.011407082,0.0012827321,0.004409059,0.00002773698,0.083034046,0.054093048,0.0002807621,0.055252414,0.0073190965,0.7818377],"study_design_scores_gemma":[0.0023622573,0.00069373974,0.024878165,0.0000530757,0.00023304834,0.00010176314,0.034331024,0.9121404,0.0006031047,0.023895102,0.00019948922,0.0005088175],"about_ca_topic_score_codex":0.00009818424,"about_ca_topic_score_gemma":0.0000145465965,"teacher_disagreement_score":0.85804737,"about_ca_system_score_codex":0.00017958181,"about_ca_system_score_gemma":0.00011376269,"threshold_uncertainty_score":0.5483988},"labels":[],"label_agreement":null},{"id":"W4385386810","doi":"10.18280/ria.370311","title":"Machine Learning-Based Recommendations and Classification System for Unstructured Resume Documents","year":2023,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Natural language processing","score_opus":0.057340242705371136,"score_gpt":0.3059013143271985,"score_spread":0.2485610716218274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385386810","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":[0.0022238055,0.00015374806,0.9817913,0.011982817,0.0004939469,0.0005713802,0.000016603042,0.0018135377,0.0009528494],"genre_scores_gemma":[0.9853428,0.0001492145,0.011739602,0.000048498514,0.000025364614,0.00021597843,0.00010245057,0.000014713725,0.002361392],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986026,0.00006222323,0.0004029659,0.00050852605,0.00014005532,0.0002836303],"domain_scores_gemma":[0.9987416,0.00030104912,0.00019642516,0.0005799436,0.00011493006,0.00006603571],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048750849,0.00014773593,0.0001573305,0.0003091385,0.0004152255,0.00024248211,0.0005872543,0.00009738987,0.000017780469],"category_scores_gemma":[0.00021763718,0.00014385108,0.00006122293,0.0009419564,0.00007635605,0.00031002527,0.00012347916,0.00014323366,0.00023778561],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002514644,0.00006456899,0.001114653,0.00021605538,0.000026596113,0.0000024816063,0.0007029579,0.010539618,0.007850902,0.5909135,0.0045612482,0.3839823],"study_design_scores_gemma":[0.000086931395,0.00007762378,0.00020073868,0.000059065896,0.0000068351287,0.0000036538488,0.0007828785,0.9198582,0.024111941,0.0056707826,0.04897381,0.0001675452],"about_ca_topic_score_codex":0.0000089520345,"about_ca_topic_score_gemma":0.0000048645793,"teacher_disagreement_score":0.98311895,"about_ca_system_score_codex":0.0000738426,"about_ca_system_score_gemma":0.000032896078,"threshold_uncertainty_score":0.5866077},"labels":[],"label_agreement":null},{"id":"W4385486397","doi":"10.1007/978-3-031-33390-3_7","title":"Nearest Neighbors","year":2023,"lang":"en","type":"book-chapter","venue":"Statisctics and computing/Statistics and computing","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"k-nearest neighbors algorithm; Computer science; Pattern recognition (psychology); Naive Bayes classifier; Artificial intelligence; Classifier (UML); Similarity (geometry); Data mining; Machine learning; Support vector machine","score_opus":0.025564252508237035,"score_gpt":0.25865924454697137,"score_spread":0.23309499203873432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385486397","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014378644,0.00069821224,0.9655215,0.0006881821,0.0008577871,0.00030428992,0.00015612942,0.000974073,0.030656021],"genre_scores_gemma":[0.1274056,0.0039232844,0.7139563,0.0009102091,0.0006346993,0.000008475196,0.00031460947,0.00035304631,0.1524938],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99718547,0.000031249336,0.00075078517,0.0010363907,0.00044751883,0.00054858637],"domain_scores_gemma":[0.99742216,0.00093563617,0.00062814774,0.00065213075,0.00015745954,0.00020449272],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003087306,0.0005771513,0.0006153883,0.00033249683,0.0006868925,0.0010282317,0.0007096131,0.00030007283,0.000012210281],"category_scores_gemma":[0.000086294574,0.0005932801,0.00006340119,0.00015507003,0.00033346142,0.00012446614,0.0016563156,0.0006746995,0.000048169048],"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":[0.0000015289298,0.000007363566,0.000057828776,0.00007603842,0.00004649634,0.00004674835,0.00024447392,0.000027948827,0.0000021800245,0.69546187,0.002507172,0.30152035],"study_design_scores_gemma":[0.00041958454,0.00022790435,0.0012584289,0.0002973815,0.00006478435,0.000057995043,0.00011806329,0.35037977,0.0000070823285,0.61598295,0.030217733,0.00096832553],"about_ca_topic_score_codex":0.000017241435,"about_ca_topic_score_gemma":0.000008170062,"teacher_disagreement_score":0.35035184,"about_ca_system_score_codex":0.00003267646,"about_ca_system_score_gemma":0.00010394365,"threshold_uncertainty_score":0.99965185},"labels":[],"label_agreement":null},{"id":"W4385572319","doi":"10.18653/v1/2023.acl-industry.55","title":"Weighted Contrastive Learning With False Negative Control to Help Long-tailed Product Classification","year":2023,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Categorical variable; Categorization; Computer science; Regularization (linguistics); Artificial intelligence; Task (project management); Taxonomy (biology); Machine learning; Pattern recognition (psychology); Natural language processing; Engineering","score_opus":0.01927232653048668,"score_gpt":0.2567327726888022,"score_spread":0.2374604461583155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385572319","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":[0.089694016,0.000021262244,0.8821945,0.020573534,0.00012488403,0.0010520353,0.0000024212873,0.0041408744,0.0021964419],"genre_scores_gemma":[0.9852179,0.000009884465,0.008021231,0.000225358,0.000033508786,0.00029521494,0.000009338469,0.000013475829,0.006174042],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99825615,0.00009781831,0.0002519886,0.00066651497,0.00035240775,0.00037512157],"domain_scores_gemma":[0.99862194,0.00027007915,0.00015290432,0.0005477857,0.00030571697,0.00010159051],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00031037605,0.00019231916,0.00022019923,0.00035285993,0.0002304618,0.00025139019,0.0006865713,0.000060987066,0.000040026836],"category_scores_gemma":[0.0003437384,0.00014070708,0.000036701807,0.0019705002,0.00009482726,0.0005900107,0.00012393622,0.00020250247,0.0011326926],"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":[0.0003267805,0.00025390828,0.096055545,0.000034373217,0.00026052987,0.000048538386,0.0031667298,0.0008836312,0.032910146,0.40191883,0.012009697,0.45213127],"study_design_scores_gemma":[0.0041555124,0.0013160477,0.73736614,0.00009578111,0.00004343254,0.0000132133555,0.004754453,0.15725155,0.076176204,0.007968021,0.009643347,0.0012163081],"about_ca_topic_score_codex":0.000015020767,"about_ca_topic_score_gemma":0.000026309599,"teacher_disagreement_score":0.8955239,"about_ca_system_score_codex":0.00007472343,"about_ca_system_score_gemma":0.00007953156,"threshold_uncertainty_score":0.99964505},"labels":[],"label_agreement":null},{"id":"W4385573359","doi":"10.18653/v1/2022.findings-emnlp.291","title":"Parameter-free Automatically Prompting: A Latent Pseudo Label Mapping Model for Prompt-based Learning","year":2022,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"University of Ottawa","funders":"Fundamental Research Funds for the Central Universities; State Key Laboratory of Software Development Environment","keywords":"Computer science; Artificial intelligence; Probabilistic logic; Machine learning; Multi-label classification; Task (project management); Pattern recognition (psychology)","score_opus":0.0630347075920334,"score_gpt":0.2732431962514197,"score_spread":0.2102084886593863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385573359","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01938797,0.000014123389,0.9677753,0.00896817,0.00009005171,0.00073815207,0.0000031800087,0.0026274116,0.0003956433],"genre_scores_gemma":[0.3907071,4.19366e-7,0.6060635,0.00028752282,0.000006279858,0.00094652,0.0000056235667,0.000011133179,0.0019719487],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99835277,0.000051738345,0.00034316897,0.00048896595,0.0003838025,0.00037954692],"domain_scores_gemma":[0.99874294,0.00019427824,0.000171685,0.00076338614,0.00007219769,0.00005549293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053461373,0.00015478944,0.00017816808,0.00019598908,0.0005333312,0.00023356856,0.0016779982,0.000047554844,0.00004486986],"category_scores_gemma":[0.00034075082,0.00014209737,0.000080987294,0.00041615963,0.00004100061,0.00026390803,0.00090182817,0.00024767968,0.000011040772],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003455888,0.0008736388,0.0014515073,0.00019632488,0.00006874984,0.000007723917,0.0015607461,0.1049088,0.009899719,0.72534806,0.014865468,0.1407847],"study_design_scores_gemma":[0.000717087,0.00020107703,0.000114741495,0.00000814296,0.000004327318,0.000002751772,0.00007816927,0.9591239,0.00075889076,0.03705901,0.0017307994,0.00020107086],"about_ca_topic_score_codex":0.0000030298822,"about_ca_topic_score_gemma":7.299507e-7,"teacher_disagreement_score":0.85421515,"about_ca_system_score_codex":0.00010321796,"about_ca_system_score_gemma":0.00013704182,"threshold_uncertainty_score":0.57945627},"labels":[],"label_agreement":null},{"id":"W4385573558","doi":"10.18653/v1/2022.wanlp-1.7","title":"A Benchmark Study of Contrastive Learning for Arabic Social Meaning","year":2022,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"University of British Columbia","funders":"","keywords":"Meaning (existential); Benchmark (surveying); Arabic; Computer science; Natural language processing; Linguistics; Artificial intelligence; Contrastive analysis; Psychology; Philosophy; Geology","score_opus":0.02750089901426163,"score_gpt":0.2749420696812646,"score_spread":0.247441170667003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385573558","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":[0.3586984,0.00002465102,0.6320052,0.0013132446,0.00018645941,0.00077794684,0.0000014875795,0.0006167736,0.006375821],"genre_scores_gemma":[0.9964276,2.8425646e-7,0.0028484738,0.000026702186,0.000008268098,0.00018974674,0.0000012261997,0.0000028075585,0.0004949127],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9992991,0.000051531246,0.00014989315,0.00018715714,0.0001836441,0.00012864904],"domain_scores_gemma":[0.9995828,0.00012452141,0.00011712173,0.000116110656,0.000049012222,0.000010394732],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000269889,0.000052412666,0.00010638924,0.00008787281,0.0004140954,0.00003187193,0.00048120227,0.000013190293,0.000049694103],"category_scores_gemma":[0.00006599645,0.00004972053,0.000034568217,0.00027277844,0.000019923586,0.00013344859,0.0003111498,0.00010418617,9.064546e-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":[0.000028941155,0.0005722632,0.00738199,0.0000076801525,0.000060654078,0.0000013682351,0.015286524,0.00058529846,0.0019701875,0.8856935,0.0019477549,0.086463876],"study_design_scores_gemma":[0.01219797,0.01405795,0.09288262,0.000011593876,0.00010000818,0.000010337561,0.4213762,0.24973392,0.01156528,0.15418464,0.04239004,0.0014894356],"about_ca_topic_score_codex":0.000012922732,"about_ca_topic_score_gemma":0.0000047157237,"teacher_disagreement_score":0.73150885,"about_ca_system_score_codex":0.000036092642,"about_ca_system_score_gemma":0.000025933714,"threshold_uncertainty_score":0.3184929},"labels":[],"label_agreement":null},{"id":"W4385573784","doi":"10.18653/v1/2022.emnlp-industry.39","title":"Developing Prefix-Tuning Models for Hierarchical Text Classification","year":2022,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","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":"Queen's University","funders":"","keywords":"Prefix; Computer science; Hierarchy; Task (project management); Set (abstract data type); Key (lock); Process (computing); Artificial intelligence; Machine learning; Engineering","score_opus":0.10234311420757611,"score_gpt":0.3022484223928824,"score_spread":0.1999053081853063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385573784","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":[0.0010698072,0.000037971895,0.9746034,0.017966261,0.00015765967,0.0002829207,0.00000212604,0.0009476923,0.0049321423],"genre_scores_gemma":[0.6765091,0.0000062016625,0.32109582,0.00041440895,0.000012095267,0.00049225683,0.000009602016,0.000006455573,0.0014540809],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890625,0.000039326376,0.00021739009,0.00037380436,0.00024107665,0.00022213231],"domain_scores_gemma":[0.9992342,0.00013058522,0.000086061766,0.00046724206,0.000050425548,0.000031479438],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030575728,0.00008913382,0.00009297154,0.00017059059,0.0005395554,0.00013206586,0.0011039745,0.000035931895,0.0000293347],"category_scores_gemma":[0.000040977036,0.000085578926,0.00004692981,0.00042477323,0.0000334256,0.00052597094,0.00055614056,0.00014213096,0.000009263143],"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":[0.0000029874716,0.000017635251,0.000028843757,0.0000036769472,0.0000039012784,1.6981049e-7,0.00014755498,0.00034979254,0.0006941575,0.9084231,0.0016193024,0.088708825],"study_design_scores_gemma":[0.00017752168,0.00004778354,0.00026034127,0.0000019098682,0.0000015503758,0.0000033842214,0.00032953624,0.6037657,0.0010073617,0.3465093,0.047754608,0.00014094828],"about_ca_topic_score_codex":0.0000030779377,"about_ca_topic_score_gemma":0.0000010114677,"teacher_disagreement_score":0.67543924,"about_ca_system_score_codex":0.00015283069,"about_ca_system_score_gemma":0.00012100453,"threshold_uncertainty_score":0.41498783},"labels":[],"label_agreement":null},{"id":"W4386106544","doi":"10.1007/978-3-031-42795-4_6","title":"GNN-DES: A New End-to-End Dynamic Ensemble Selection Method Based on Multi-label Graph Neural Network","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Computer science; ENCODE; Artificial intelligence; Artificial neural network; Graph; Pattern recognition (psychology); Machine learning; Context (archaeology); Selection (genetic algorithm); Data mining; Theoretical computer science","score_opus":0.04133797308664411,"score_gpt":0.30452895542362235,"score_spread":0.26319098233697824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386106544","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000045052075,0.00009452405,0.9926769,0.002624032,0.001957563,0.0006425634,0.0000039651613,0.0015267594,0.00042865064],"genre_scores_gemma":[0.02485238,0.000025744983,0.9708958,0.0020286639,0.00021338307,0.00003406904,0.000009226698,0.000060257626,0.0018804639],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99504817,0.00008700144,0.0005879644,0.0021561068,0.0010997754,0.001020981],"domain_scores_gemma":[0.9967393,0.0009355605,0.0003412255,0.0015157608,0.00020607485,0.00026203817],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011050694,0.0006843565,0.00056773925,0.0018587848,0.0005227719,0.00080776104,0.0035183553,0.00046111544,0.000020321912],"category_scores_gemma":[0.0002097946,0.0006354794,0.00017091211,0.0031911691,0.00042265875,0.00054410927,0.0009580213,0.0010514456,0.0001324548],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009980472,0.000029159264,0.000027574237,0.000014898476,0.000007880673,0.00001650912,0.00016585628,0.21962106,0.00031447018,0.010216754,0.00013901548,0.76943684],"study_design_scores_gemma":[0.0003814813,0.00037669274,0.0002880146,0.00022661172,0.0000089029845,0.000014678221,3.039604e-7,0.85917,0.00070318475,0.13784124,0.00041216402,0.0005766937],"about_ca_topic_score_codex":0.000070374306,"about_ca_topic_score_gemma":0.00046728546,"teacher_disagreement_score":0.76886016,"about_ca_system_score_codex":0.0004907563,"about_ca_system_score_gemma":0.00056963577,"threshold_uncertainty_score":0.99960965},"labels":[],"label_agreement":null},{"id":"W4386163333","doi":"10.1016/j.neucom.2023.126729","title":"Within- cross- consensus-view representation-based multi-view multi-label learning with incomplete data","year":2023,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Representation (politics); Feature (linguistics); Feature learning; Artificial intelligence; Machine learning; Exploit; Data mining","score_opus":0.2010044733352705,"score_gpt":0.3881169748434069,"score_spread":0.1871125015081364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386163333","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":[0.13090257,0.00025202698,0.8573481,0.0032830762,0.0004790937,0.00079890294,0.000009838651,0.0067937425,0.0001326501],"genre_scores_gemma":[0.631913,0.000024387522,0.36694124,0.0005500888,0.000046322948,0.000031593983,0.00007516861,0.000043672695,0.0003745334],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970055,0.00022556388,0.0005863543,0.0012223631,0.0004561983,0.000504014],"domain_scores_gemma":[0.9967105,0.0007414959,0.0004669107,0.001805445,0.0001793551,0.00009631937],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007457837,0.00028289037,0.00031524053,0.0002752639,0.00068184955,0.0006557605,0.0024005391,0.000082117105,0.0000057212624],"category_scores_gemma":[0.00069031864,0.00025100596,0.000042341675,0.0018849846,0.00020514696,0.00045170073,0.0015186935,0.0004906907,0.00023600392],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035414203,0.00043188475,0.21525392,0.00042816336,0.00010167255,0.00048747862,0.0011996812,0.099884056,0.005102645,0.0069728945,0.0016250468,0.6684771],"study_design_scores_gemma":[0.0013296974,0.00006851294,0.022270342,0.00010839731,0.0000082650395,0.000019249494,0.00008092249,0.9714037,0.0007034881,0.000058396596,0.003654068,0.00029494194],"about_ca_topic_score_codex":0.00003920869,"about_ca_topic_score_gemma":0.00001544316,"teacher_disagreement_score":0.8715197,"about_ca_system_score_codex":0.000030662828,"about_ca_system_score_gemma":0.00014193385,"threshold_uncertainty_score":0.9999942},"labels":[],"label_agreement":null},{"id":"W4386196569","doi":"10.1007/978-3-031-42519-6_29","title":"A Machine-Learning Based Approach to Validating Learning Materials","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University","funders":"","keywords":"Machine learning; Artificial intelligence; Computer science; Instance-based learning; Process (computing); Active learning (machine learning); Scalability; Unsupervised learning; Similarity (geometry); Online machine learning; Database","score_opus":0.030786557036258502,"score_gpt":0.2373420897512575,"score_spread":0.206555532714999,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386196569","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":[0.000033356515,0.0014446444,0.98417336,0.0002315421,0.0006987609,0.0005383815,0.0000033642411,0.0009665571,0.011910034],"genre_scores_gemma":[0.9734191,0.00023413777,0.0059115873,0.00014895937,0.0004273914,0.00015150505,0.0001174129,0.0001099928,0.01947995],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978959,0.0001311423,0.0005358224,0.0007621163,0.00029083944,0.000384194],"domain_scores_gemma":[0.9985527,0.00051363965,0.00034708585,0.00046557444,0.000049174694,0.0000718599],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008296016,0.00038691977,0.0005889773,0.00039016115,0.00020842144,0.00076528615,0.0006170166,0.0005739601,0.0000070169804],"category_scores_gemma":[0.000214224,0.00033541786,0.00006214141,0.00023820718,0.00003763011,0.00009561536,0.00036080505,0.00084726786,0.000020402924],"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":[0.000008075778,0.000007722592,0.00028748089,0.0002054532,0.000031125575,0.000014990575,0.0002635031,0.8634278,0.00009436795,0.10365006,0.00009216327,0.031917263],"study_design_scores_gemma":[0.00020932073,0.000092643,0.000024555673,0.0007150754,0.000012536658,0.000011818805,0.000015051425,0.97505975,0.0000620723,0.0032190378,0.02000375,0.0005743906],"about_ca_topic_score_codex":0.00006589274,"about_ca_topic_score_gemma":0.000008504283,"teacher_disagreement_score":0.97826177,"about_ca_system_score_codex":0.000062676125,"about_ca_system_score_gemma":0.000026897405,"threshold_uncertainty_score":0.99990976},"labels":[],"label_agreement":null},{"id":"W4386214112","doi":"10.1016/j.knosys.2023.110938","title":"Label correlation guided borderline oversampling for imbalanced multi-label data learning","year":2023,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Oversampling; Weighting; Computer science; Machine learning; Class (philosophy); Multi-label classification; Artificial intelligence; Decision boundary; Range (aeronautics); Code (set theory); Correlation; Data mining; Source code; Tree (set theory); Macro; Pattern recognition (psychology); Support vector machine; Mathematics","score_opus":0.17484913156105525,"score_gpt":0.37731699735897584,"score_spread":0.2024678657979206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386214112","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":[0.0022613287,0.00063980464,0.990483,0.00066632696,0.0017410005,0.0007930902,0.00003596526,0.0030995728,0.00027995263],"genre_scores_gemma":[0.89608675,0.000036222074,0.09402797,0.000046353132,0.0002400634,0.00043787717,0.001078723,0.00005766303,0.007988366],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99793047,0.000107396634,0.00053455605,0.0007544884,0.0002441866,0.00042888834],"domain_scores_gemma":[0.99728394,0.0006205363,0.00031240925,0.0013931813,0.0003178579,0.0000720761],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011776272,0.00021791349,0.00029106776,0.00035311398,0.00038874164,0.0003367006,0.0016528178,0.00017204187,0.000002836721],"category_scores_gemma":[0.0009891435,0.00021126439,0.00004606545,0.0012093814,0.00004888095,0.0005680956,0.00041050103,0.00019599481,0.00034720023],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013556931,0.0017281546,0.036006417,0.0023070849,0.00035662402,0.00002104008,0.0029668347,0.05966929,0.052324507,0.1839386,0.21179442,0.44875145],"study_design_scores_gemma":[0.0022059998,0.00007132708,0.00038225876,0.000109547465,0.000011173028,0.000001131586,0.00018369977,0.9578734,0.00047092684,0.00014238391,0.03830162,0.0002465256],"about_ca_topic_score_codex":0.000027645394,"about_ca_topic_score_gemma":0.000019760557,"teacher_disagreement_score":0.8982041,"about_ca_system_score_codex":0.00012351015,"about_ca_system_score_gemma":0.00017951823,"threshold_uncertainty_score":0.8615112},"labels":[],"label_agreement":null},{"id":"W4386266758","doi":"10.1109/access.2023.3309697","title":"MCNN-LSTM: Combining CNN and LSTM to Classify Multi-Class Text in Imbalanced News Data","year":2023,"lang":"en","type":"article","venue":"IEEE Access","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Artificial intelligence; Convolutional neural network; Machine learning; Margin (machine learning); Deep learning; Class (philosophy); Feature (linguistics); Sentence; Document classification; Categorization; Natural language processing","score_opus":0.15525568721357122,"score_gpt":0.38574696803104114,"score_spread":0.23049128081746992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386266758","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":[0.7069339,0.00021625437,0.24346961,0.039653156,0.002461603,0.001141395,0.000043870332,0.0039632786,0.0021169323],"genre_scores_gemma":[0.9927286,0.0001250742,0.0053322446,0.0009082628,0.000037683618,0.00007046541,0.000020354411,0.000015609263,0.0007617046],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99810153,0.00004881342,0.00034011615,0.00081900554,0.00026029052,0.00043025077],"domain_scores_gemma":[0.9979042,0.00016866047,0.00011528438,0.0016667437,0.000041793002,0.000103322294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033701328,0.0001827046,0.0002427622,0.00044620075,0.0001251985,0.0007097174,0.0041204914,0.00011973575,0.000008184219],"category_scores_gemma":[0.0001844186,0.00017279365,0.000020878926,0.0017963351,0.000075038726,0.0018233298,0.0023494016,0.00022545304,0.00023547183],"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":[0.000040317525,0.0003398743,0.17034112,0.00010761672,0.00005336578,0.00013083854,0.0019477408,0.0005907568,0.018309597,0.021044401,0.1524752,0.6346192],"study_design_scores_gemma":[0.0034941607,0.00015824688,0.3949886,0.00020056865,0.000013633276,0.000011516837,0.0008979039,0.4931268,0.013490569,0.008055352,0.08426645,0.0012961935],"about_ca_topic_score_codex":0.00013268601,"about_ca_topic_score_gemma":0.00031139224,"teacher_disagreement_score":0.633323,"about_ca_system_score_codex":0.000045813566,"about_ca_system_score_gemma":0.000055006803,"threshold_uncertainty_score":0.76569664},"labels":[],"label_agreement":null},{"id":"W4386708820","doi":"10.32920/24132588","title":"MLCM: Multi-Label Confusion Matrix","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Ministère de la Défense Nationale","keywords":"Confusion matrix; Classifier (UML); Computer science; Ambiguity; Confusion; Artificial intelligence; Machine learning; Class (philosophy); Multi-label classification; Pattern recognition (psychology); Data mining","score_opus":0.13508193415366992,"score_gpt":0.3652572450979859,"score_spread":0.23017531094431598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386708820","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010572644,0.00017167159,0.97538847,0.01121321,0.0016749969,0.00037462497,0.0000067750775,0.007886742,0.0022262533],"genre_scores_gemma":[0.07959813,0.0006088852,0.81344175,0.00030378782,0.000075490745,0.00021860797,0.00004790861,0.00003937037,0.10566605],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983561,0.000029376673,0.00031995992,0.00074022415,0.00029485446,0.00025948772],"domain_scores_gemma":[0.9980234,0.00007051109,0.00018289752,0.0015739361,0.000094675466,0.00005461652],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00022462178,0.00022620789,0.00022814081,0.00029001042,0.000096516225,0.00042858697,0.0024996633,0.00037555993,0.00008398392],"category_scores_gemma":[0.00008394988,0.0001935638,0.000080432095,0.00029766816,0.000060382066,0.00017669528,0.0052996203,0.00043632102,0.0019912417],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003269841,0.00019552477,0.00035270565,0.000115056646,0.000047075413,0.000023440896,0.00024845803,0.00006257963,0.0020185767,0.6563748,0.076822914,0.2637356],"study_design_scores_gemma":[0.000998703,0.000086368134,0.004131004,0.00014263586,0.00001882252,0.0000051633738,0.00019357039,0.8317978,0.009203466,0.12817937,0.024082122,0.0011610027],"about_ca_topic_score_codex":0.00008212319,"about_ca_topic_score_gemma":0.0000142533145,"teacher_disagreement_score":0.8317352,"about_ca_system_score_codex":0.000058197827,"about_ca_system_score_gemma":0.000101197154,"threshold_uncertainty_score":0.9987858},"labels":[],"label_agreement":null},{"id":"W4386709454","doi":"10.32920/24132588.v1","title":"MLCM: Multi-Label Confusion Matrix","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Text and Document Classification Technologies","field":"Computer 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":"Ministère de la Défense Nationale","keywords":"Confusion matrix; Classifier (UML); Computer science; Ambiguity; Confusion; Artificial intelligence; Machine learning; Class (philosophy); Multi-label classification; Pattern recognition (psychology); Data mining","score_opus":0.13508193415366992,"score_gpt":0.3652572450979859,"score_spread":0.23017531094431598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386709454","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010572644,0.00017167159,0.97538847,0.01121321,0.0016749969,0.00037462497,0.0000067750775,0.007886742,0.0022262533],"genre_scores_gemma":[0.07959813,0.0006088852,0.81344175,0.00030378782,0.000075490745,0.00021860797,0.00004790861,0.00003937037,0.10566605],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983561,0.000029376673,0.00031995992,0.00074022415,0.00029485446,0.00025948772],"domain_scores_gemma":[0.9980234,0.00007051109,0.00018289752,0.0015739361,0.000094675466,0.00005461652],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00022462178,0.00022620789,0.00022814081,0.00029001042,0.000096516225,0.00042858697,0.0024996633,0.00037555993,0.00008398392],"category_scores_gemma":[0.00008394988,0.0001935638,0.000080432095,0.00029766816,0.000060382066,0.00017669528,0.0052996203,0.00043632102,0.0019912417],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003269841,0.00019552477,0.00035270565,0.000115056646,0.000047075413,0.000023440896,0.00024845803,0.00006257963,0.0020185767,0.6563748,0.076822914,0.2637356],"study_design_scores_gemma":[0.000998703,0.000086368134,0.004131004,0.00014263586,0.00001882252,0.0000051633738,0.00019357039,0.8317978,0.009203466,0.12817937,0.024082122,0.0011610027],"about_ca_topic_score_codex":0.00008212319,"about_ca_topic_score_gemma":0.0000142533145,"teacher_disagreement_score":0.8317352,"about_ca_system_score_codex":0.000058197827,"about_ca_system_score_gemma":0.000101197154,"threshold_uncertainty_score":0.9987858},"labels":[],"label_agreement":null},{"id":"W4386773820","doi":"10.5267/j.ijiec.2023.8.002","title":"A kernel-free L1 norm regularized ν-support vector machine model with application","year":2023,"lang":"en","type":"article","venue":"International Journal of Industrial Engineering Computations","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Support vector machine; Overfitting; Computer science; Kernel method; Artificial intelligence; Kernel (algebra); Binary classification; Machine learning; Polynomial kernel; Benchmark (surveying); Computational complexity theory; Mathematical optimization; Algorithm; Mathematics; Artificial neural network","score_opus":0.025864387485464106,"score_gpt":0.2603472942397424,"score_spread":0.2344829067542783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386773820","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":[0.010384176,0.000010419691,0.9785666,0.009648625,0.00069850124,0.00013197743,0.000016094114,0.00043628778,0.00010735319],"genre_scores_gemma":[0.92640346,0.000013569238,0.07302221,0.000056980385,0.00026041103,0.000022399865,0.000031856795,0.000017449502,0.00017167242],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852186,0.000013522976,0.0004873155,0.00017729445,0.0006368236,0.00016318455],"domain_scores_gemma":[0.9986442,0.00013960726,0.00036031904,0.00031130423,0.0004665657,0.00007805952],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030299017,0.00013637962,0.00017294596,0.0006749693,0.00005629216,0.00019311742,0.0016218422,0.00009260499,0.000006244528],"category_scores_gemma":[0.00026930516,0.00011972225,0.000084017265,0.00073561544,0.000028758406,0.0005904945,0.00021116275,0.00030908705,0.000022948025],"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":[0.000043714615,0.00006943833,0.00020771501,0.0000033483395,0.00017221794,0.000036249432,0.00020747923,0.87533706,0.0018854768,0.09163472,0.004433774,0.025968801],"study_design_scores_gemma":[0.001602617,0.00009931158,0.00064522686,0.000038878028,0.000013592535,0.000086848704,0.000020053136,0.98964286,0.0008476723,0.0044122846,0.0024457257,0.00014494163],"about_ca_topic_score_codex":0.000006739926,"about_ca_topic_score_gemma":0.000001574982,"teacher_disagreement_score":0.91601926,"about_ca_system_score_codex":0.00013867418,"about_ca_system_score_gemma":0.00021651239,"threshold_uncertainty_score":0.48821318},"labels":[],"label_agreement":null},{"id":"W4387506342","doi":"10.23977/acss.2023.070806","title":"WXGCB: A Clustering Prior Weighting Semi-Supervised Learning Method Based on Space Level Constraint and Mixed Variable Metrics","year":2023,"lang":"en","type":"article","venue":"Advances in Computer Signals and Systems","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Semi-supervised learning; Cluster analysis; Computer science; Supervised learning; Artificial intelligence; Machine learning; Unsupervised learning; Constrained clustering; Benchmark (surveying); Correlation clustering; Pattern recognition (psychology); Canopy clustering algorithm; Artificial neural network","score_opus":0.04618434634799053,"score_gpt":0.29861706043144637,"score_spread":0.25243271408345586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387506342","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":[0.0070197796,0.0014411565,0.98950845,0.00040204142,0.00054427533,0.00029763815,0.0000031774505,0.0005248005,0.0002587033],"genre_scores_gemma":[0.71195453,0.00027641098,0.28747717,0.00008544481,0.000054872864,0.000050454575,0.000003472733,0.0000132002515,0.00008441908],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99803555,0.0002646884,0.0004221687,0.0006235353,0.00029389298,0.00036018086],"domain_scores_gemma":[0.9978201,0.0015265164,0.00019178215,0.00032232812,0.00006336166,0.000075921685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001474095,0.00021607452,0.00037667673,0.00055129355,0.00021856558,0.00045625778,0.0004088562,0.00010436112,0.0000017991168],"category_scores_gemma":[0.00012096722,0.00019078248,0.000032750868,0.0012526427,0.000056513,0.00054008875,0.0003419752,0.00023884098,0.000004908603],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011937104,0.000040896677,0.0042352458,0.00038786628,0.000021704509,0.00003591866,0.000665781,0.33917204,0.0016135433,0.034136783,0.000110432615,0.6195679],"study_design_scores_gemma":[0.0005350767,0.00013056782,0.00050610997,0.00030258912,0.000003432737,0.00001235478,0.00025978204,0.99225444,0.00043336122,0.0009806365,0.004346145,0.00023551237],"about_ca_topic_score_codex":0.000023775063,"about_ca_topic_score_gemma":0.0000032374103,"teacher_disagreement_score":0.7049348,"about_ca_system_score_codex":0.000041193416,"about_ca_system_score_gemma":0.000032985703,"threshold_uncertainty_score":0.7779884},"labels":[],"label_agreement":null},{"id":"W4388144777","doi":"10.14569/ijacsa.2023.0141080","title":"A Novel Multidimensional Reference Model for Heterogeneous Textual Datasets using Context, Semantic and Syntactic Clues","year":2023,"lang":"en","type":"article","venue":"International Journal of Advanced Computer Science and Applications","topic":"Text and Document Classification Technologies","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":"Western University","funders":"Universiti Teknologi Petronas","keywords":"Computer science; Context (archaeology); Natural language processing; Information retrieval; Synonym (taxonomy); Dimension (graph theory); Search engine indexing; Semantics (computer science); Artificial intelligence","score_opus":0.05753518558212063,"score_gpt":0.34597527862950467,"score_spread":0.28844009304738405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388144777","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":[0.051882815,0.00007885476,0.9458901,0.0017441984,0.000113230235,0.00017976672,0.000038336897,0.00006847025,0.00000421951],"genre_scores_gemma":[0.74128056,0.000085976644,0.2583102,0.0002374185,0.00004598534,0.000023028833,0.000006690617,0.000003829588,0.000006308035],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986671,0.0000065785657,0.00032648304,0.00033713647,0.00048370022,0.00017900424],"domain_scores_gemma":[0.9984992,0.00017892783,0.00028789014,0.0002391043,0.00070204836,0.00009281529],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036073642,0.00010677713,0.00013442677,0.0003993894,0.00026251012,0.00024412194,0.00102941,0.00003124169,3.8156557e-7],"category_scores_gemma":[0.00006743947,0.00009382114,0.00003001249,0.00039972787,0.000269912,0.0011945312,0.00048850756,0.00009191151,0.000001972876],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032152533,0.00016042887,0.00009666226,0.00001688043,0.00005706255,0.000008964314,0.00035095518,0.03923295,0.121361636,0.28068632,0.00026805355,0.55772793],"study_design_scores_gemma":[0.00044309488,0.000048801267,0.00031859407,0.000032465472,0.0000067900774,0.0002611785,0.000053762073,0.98605466,0.002560294,0.007854444,0.0022519098,0.00011399031],"about_ca_topic_score_codex":0.0000027097144,"about_ca_topic_score_gemma":0.0000016382529,"teacher_disagreement_score":0.94682175,"about_ca_system_score_codex":0.00006249396,"about_ca_system_score_gemma":0.00018130381,"threshold_uncertainty_score":0.3825915},"labels":[],"label_agreement":null},{"id":"W4388348936","doi":"10.1007/978-3-031-46674-8_27","title":"Label Correlation Guided Feature Selection for Multi-label Learning","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Feature selection; Minimum redundancy feature selection; Redundancy (engineering); Artificial intelligence; Discriminative model; Pattern recognition (psychology); Feature (linguistics); Curse of dimensionality; Correlation; Dimensionality reduction; Exploit; Machine learning; Feature learning; Multi-label classification; Mathematics","score_opus":0.06536076908770279,"score_gpt":0.3104444183153377,"score_spread":0.24508364922763493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388348936","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000028488985,0.00014377358,0.993363,0.002051808,0.0018178133,0.0006856731,0.0000035238313,0.0015045562,0.00040134814],"genre_scores_gemma":[0.0073704277,0.00006868463,0.9778801,0.00038519237,0.00024836222,0.0000677395,0.00002866888,0.000055861175,0.013894955],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99691826,0.000026867314,0.00042946546,0.0014058861,0.0006503625,0.00056914886],"domain_scores_gemma":[0.9979057,0.00046318775,0.0004231874,0.0007118353,0.00041457015,0.00008154447],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00078977685,0.0004376589,0.00038361643,0.0010659267,0.0005343476,0.00062119914,0.0020795527,0.0005967399,0.0000048686366],"category_scores_gemma":[0.00046578725,0.00041781386,0.00009188943,0.001115969,0.00031293827,0.00073373807,0.00070126966,0.0009838364,0.00008100412],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005448659,0.00003163635,0.00018622952,0.000037557857,0.000012944407,0.0000039695665,0.0002996626,0.013352666,0.00057524734,0.077373914,0.0004689211,0.9076518],"study_design_scores_gemma":[0.0005589723,0.00017434207,0.00012201678,0.00014078527,0.000008000329,0.000014206928,4.1402797e-7,0.9268362,0.0010153328,0.068239056,0.0024434165,0.0004472686],"about_ca_topic_score_codex":0.000009326142,"about_ca_topic_score_gemma":0.000055550612,"teacher_disagreement_score":0.9134835,"about_ca_system_score_codex":0.00035276127,"about_ca_system_score_gemma":0.00030653816,"threshold_uncertainty_score":0.9998274},"labels":[],"label_agreement":null},{"id":"W4388780004","doi":"10.1515/9781552384039-021","title":"Tapor: Building a Portal for Text Analysis","year":2006,"lang":"en","type":"book-chapter","venue":"University of Calgary Press eBooks","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science","score_opus":0.021800647478887526,"score_gpt":0.21131237931871086,"score_spread":0.18951173183982334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388780004","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000085674355,0.000094078576,0.4588965,0.000017687846,0.000036366404,0.00017939086,0.000020184805,0.00019689856,0.54055035],"genre_scores_gemma":[0.0031296364,0.000024137136,0.048493836,0.000015725067,0.000016971153,9.444398e-7,0.000044464603,0.00001328238,0.948261],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989022,0.000007961602,0.00020770241,0.00046022865,0.00024814205,0.00017378808],"domain_scores_gemma":[0.9986273,0.000064421285,0.00040781352,0.0007238274,0.00012825093,0.000048377056],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000082734136,0.00020482087,0.0003960715,0.0004673293,0.00012604502,0.000041845724,0.0012201848,0.00029057858,0.00002848755],"category_scores_gemma":[0.0000047425356,0.00024157739,0.00043090282,0.000027603266,0.0001923955,0.00013440216,0.0004068428,0.00015297695,0.000002457722],"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":[0.00001015383,0.000008498196,0.0000053532262,0.000026151078,0.000322114,0.000016379441,0.000052770123,0.000016753349,0.0000427751,0.9698345,0.0034819639,0.026182607],"study_design_scores_gemma":[0.0003811161,0.00006610221,0.00005097294,0.000037813203,0.0006750908,0.000002096067,0.000011223342,0.0065313173,0.00072715955,0.020230427,0.9708914,0.0003952885],"about_ca_topic_score_codex":0.00021018967,"about_ca_topic_score_gemma":0.000074898264,"teacher_disagreement_score":0.96740943,"about_ca_system_score_codex":0.00004176442,"about_ca_system_score_gemma":0.00005835565,"threshold_uncertainty_score":0.985124},"labels":[],"label_agreement":null},{"id":"W4389352596","doi":"10.1109/tsmc.2023.3327925","title":"Multiclass and Multilabel Classifications by Consensus and Complementarity-Based Multiview Latent Space Projection","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Systems Man and Cybernetics Systems","topic":"Text and Document Classification Technologies","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":"Wilfrid Laurier University","funders":"National Natural Science Foundation of China","keywords":"Complementarity (molecular biology); Pairwise comparison; Artificial intelligence; Computer science; Matching (statistics); Representation (politics); Machine learning; Projection (relational algebra); Similarity (geometry); Pattern recognition (psychology); Mathematics; Data mining; Algorithm; Image (mathematics); Statistics","score_opus":0.040587114601292704,"score_gpt":0.2655434968731882,"score_spread":0.22495638227189546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389352596","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":[0.2521243,0.0015498934,0.7288533,0.006996255,0.0024071338,0.004385249,0.0003765936,0.0027746647,0.00053262507],"genre_scores_gemma":[0.99667865,0.00032751233,0.0006370761,0.000051395637,0.000015196466,0.00038457473,0.000010206409,0.000022493958,0.0018728848],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997989,0.00019946352,0.0004738864,0.00067618146,0.00034052483,0.00032096208],"domain_scores_gemma":[0.99867254,0.0003490636,0.00020102719,0.00053253723,0.00009637671,0.00014843972],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00037225967,0.00028595218,0.00032139014,0.00036653664,0.0004707021,0.00050003827,0.00021652973,0.00015674249,0.0000012935258],"category_scores_gemma":[0.000009313077,0.0002624461,0.00004158656,0.00047131503,0.0002085551,0.00011471123,0.0000096318045,0.0002325027,0.000041828756],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047667892,0.0056897984,0.013208613,0.008506689,0.0018974475,0.00013217222,0.01388094,0.039989408,0.1303111,0.40049636,0.07393365,0.31147715],"study_design_scores_gemma":[0.0021506415,0.0004234276,0.0022711104,0.000353016,0.000055709083,0.000046264657,0.0020834634,0.9671406,0.0035456491,0.000059464826,0.021294707,0.0005759436],"about_ca_topic_score_codex":0.0005189437,"about_ca_topic_score_gemma":0.000060101975,"teacher_disagreement_score":0.9271512,"about_ca_system_score_codex":0.000086394335,"about_ca_system_score_gemma":0.000031141837,"threshold_uncertainty_score":0.9999828},"labels":[],"label_agreement":null},{"id":"W4389505417","doi":"10.1016/j.comcom.2023.12.003","title":"Robust multimodal federated learning for incomplete modalities","year":2023,"lang":"en","type":"article","venue":"Computer Communications","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Modalities; Computer science; Multimodal learning; Modality (human–computer interaction); Artificial intelligence; Machine learning; Representation (politics); Feature (linguistics); Dependency (UML); Feature learning","score_opus":0.13377088027244857,"score_gpt":0.3101905550907414,"score_spread":0.17641967481829282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389505417","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":[0.0018655316,0.00009443804,0.97784185,0.015077367,0.00020815965,0.00033756212,0.000005061567,0.0037466043,0.0008234167],"genre_scores_gemma":[0.6236566,0.00010309864,0.37461388,0.00017954786,0.000041879928,0.00029736134,0.00014050382,0.000015385247,0.0009517813],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988312,0.00011640467,0.0002985407,0.00031562315,0.00013947315,0.00029876255],"domain_scores_gemma":[0.9972739,0.00066279666,0.00012211136,0.0017005266,0.00018852195,0.00005213616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029454925,0.00014401802,0.00016647161,0.0002753211,0.0010453083,0.0004670747,0.0029485708,0.00007792405,0.0000041601124],"category_scores_gemma":[0.000079693724,0.00014853461,0.00008771992,0.0008338864,0.0001437027,0.00045970213,0.0018992611,0.0002213216,0.00016701958],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004044562,0.00010653028,0.0009206005,0.000028121825,0.000058127105,0.00000102354,0.0013036986,0.012903693,0.00044728772,0.73815346,0.020211842,0.22586158],"study_design_scores_gemma":[0.00028527968,0.000046181234,0.0030629993,0.000013544706,0.0000033547497,0.0000020201053,0.0001279208,0.9158622,0.00013498936,0.0108555695,0.06943187,0.00017404513],"about_ca_topic_score_codex":0.000017271681,"about_ca_topic_score_gemma":0.0000114429895,"teacher_disagreement_score":0.9029585,"about_ca_system_score_codex":0.000046933506,"about_ca_system_score_gemma":0.000051998974,"threshold_uncertainty_score":0.8039772},"labels":[],"label_agreement":null},{"id":"W4390873538","doi":"10.1109/iccv51070.2023.00166","title":"Parametric Information Maximization for Generalized Category Discovery","year":2023,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","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":"Institut National de la Recherche Scientifique; Thales (Canada)","funders":"","keywords":"Parameterized complexity; Maximization; Computer science; Parametric statistics; Mutual information; Class (philosophy); Code (set theory); Data mining; Nonparametric statistics; Artificial intelligence; Theoretical computer science; Machine learning; Algorithm; Mathematics; Mathematical optimization; Statistics; Set (abstract data type); Programming language","score_opus":0.028113675131419043,"score_gpt":0.2630281952364658,"score_spread":0.23491452010504676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390873538","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":[0.0046979464,0.000010035204,0.9889295,0.0027988488,0.00021942295,0.00023457006,0.0000023058906,0.00163326,0.0014741179],"genre_scores_gemma":[0.916238,0.00009073549,0.077626415,0.00050100865,0.000022254924,0.00028483558,0.0001637218,0.0000057303696,0.0050673145],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994488,0.000008360731,0.00016761202,0.00011534721,0.00012206925,0.00013781329],"domain_scores_gemma":[0.9994981,0.00006801845,0.000070222224,0.0002906657,0.00005617487,0.000016793558],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014333085,0.00005834184,0.00006118869,0.00042452532,0.00008417819,0.00035478335,0.00038468395,0.000047155325,0.0000059348195],"category_scores_gemma":[0.00013769614,0.00004819731,0.00003492632,0.001346285,0.000014489162,0.0028430363,0.000099324345,0.000024963227,0.0001969352],"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":[0.0000020844784,0.0000059728013,0.000122041056,0.000009502709,0.000003376825,7.38619e-8,0.0000532007,0.0005313189,0.00009074639,0.9067972,0.021109663,0.071274824],"study_design_scores_gemma":[0.00083620084,0.00007470295,0.0076360963,0.0000030594647,0.0000065636773,0.0000012580293,0.00021671034,0.66843164,0.0126600405,0.23900604,0.07084309,0.00028460674],"about_ca_topic_score_codex":0.0000093462595,"about_ca_topic_score_gemma":8.891717e-7,"teacher_disagreement_score":0.91154003,"about_ca_system_score_codex":0.00002426299,"about_ca_system_score_gemma":0.00002628481,"threshold_uncertainty_score":0.3421184},"labels":[],"label_agreement":null},{"id":"W4391018555","doi":"10.1016/j.cmpb.2024.108032","title":"Label correlation guided discriminative label feature learning for multi-label chest image classification","year":2024,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Multi-label classification; Discriminative model; Artificial intelligence; Computer science; Pattern recognition (psychology); Feature (linguistics); Correlation; Machine learning; Consistency (knowledge bases); Off-label use; Mathematics; Medicine","score_opus":0.18679557094948226,"score_gpt":0.4398610810705291,"score_spread":0.25306551012104683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391018555","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011326855,0.002338876,0.98484117,0.009161507,0.0008970582,0.0007818499,0.0000021304995,0.00077961705,0.000065097105],"genre_scores_gemma":[0.013449829,0.00022028698,0.9851663,0.00010984844,0.00013221841,0.00022915518,0.00009174086,0.000019497451,0.00058110635],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99818414,0.00021281117,0.000391066,0.0007151529,0.00018194434,0.00031486456],"domain_scores_gemma":[0.998867,0.0004247157,0.00014217546,0.000341962,0.00014653025,0.000077622615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015507191,0.00024244873,0.0002967606,0.0004314042,0.00015712317,0.0004150955,0.0004636137,0.00020211651,0.0000016861427],"category_scores_gemma":[0.00016445124,0.00018839778,0.000038092483,0.0011494819,0.00026326338,0.0005537001,0.00023662443,0.00038618167,0.000004578807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006539624,0.00014251532,0.00033818546,0.00016281505,0.00002114679,0.000004418843,0.0013809234,6.2709256e-7,0.005066037,0.036517408,0.000854081,0.9555053],"study_design_scores_gemma":[0.001387239,0.00048574974,0.0036394163,0.00024966977,0.000023299757,0.000014464831,0.00024973467,0.9613413,0.00046166204,0.006802787,0.025112469,0.00023216296],"about_ca_topic_score_codex":0.00000915622,"about_ca_topic_score_gemma":0.0000022044762,"teacher_disagreement_score":0.9613407,"about_ca_system_score_codex":0.00007803814,"about_ca_system_score_gemma":0.00003899835,"threshold_uncertainty_score":0.7682638},"labels":[],"label_agreement":null},{"id":"W4392200326","doi":"10.18280/isi.290123","title":"Augmenting Document Classification Accuracy Through the Integration of Deep Contextual Embeddings","year":2024,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Information retrieval; Computer science; Artificial intelligence; Natural language processing; Data science","score_opus":0.030381369283085935,"score_gpt":0.28908779751152497,"score_spread":0.25870642822843903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392200326","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":[0.017923879,0.0004376652,0.9701226,0.001462198,0.0005145847,0.00041201335,0.0000034739462,0.00076392497,0.0083596865],"genre_scores_gemma":[0.9880732,0.000088643596,0.011428035,0.00012442826,0.000030860978,0.00012332248,0.00003840013,0.0000062310837,0.00008685312],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99841577,0.000057680798,0.00076122256,0.00018346554,0.00036910898,0.00021277956],"domain_scores_gemma":[0.9985463,0.0002729045,0.000419643,0.00049599353,0.00024208578,0.000023050754],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005581399,0.00016028137,0.00014557343,0.00021602235,0.00027096385,0.0011072956,0.00075382576,0.000098775155,0.000027040734],"category_scores_gemma":[0.00045659667,0.00011256147,0.000087105574,0.0008217171,0.00019016994,0.009652778,0.00016819213,0.00017288615,0.00011554464],"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":[0.00000315048,0.000006384178,0.000019866764,0.00007458757,0.000017594986,1.9883534e-7,0.012584463,0.000040851533,0.0013723639,0.5433845,0.00051497424,0.44198105],"study_design_scores_gemma":[0.0005459855,0.00023797,0.0046056854,0.00071094866,0.00005840479,0.000050737657,0.032140072,0.5256039,0.06671398,0.30091858,0.06777197,0.0006417964],"about_ca_topic_score_codex":0.00004785143,"about_ca_topic_score_gemma":0.0000054007,"teacher_disagreement_score":0.97014934,"about_ca_system_score_codex":0.00023754036,"about_ca_system_score_gemma":0.00007064805,"threshold_uncertainty_score":0.99992967},"labels":[],"label_agreement":null},{"id":"W4392425987","doi":"10.48550/arxiv.2403.00143","title":"Tree-Averaging Algorithms for Ensemble-Based Unsupervised Discontinuous Constituency Parsing","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; Alberta Innovates; DeepMind; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Parsing; Tree (set theory); Computer science; Artificial intelligence; Ensemble learning; Natural language processing; Machine learning; Mathematics; Combinatorics","score_opus":0.10414774333138964,"score_gpt":0.2212843106027825,"score_spread":0.11713656727139286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392425987","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":[0.021265423,0.00027038305,0.97042334,0.0016822864,0.0013425803,0.00066830334,0.000038197075,0.0017682881,0.0025412028],"genre_scores_gemma":[0.97677815,0.000065407374,0.021414442,0.00009836287,0.00006105772,0.0000117449845,0.0000387099,0.000026649328,0.0015054742],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976283,0.000060398394,0.0002939869,0.0014395202,0.00011253966,0.00046530992],"domain_scores_gemma":[0.99799156,0.00020629693,0.00021225047,0.0013215705,0.00015274531,0.00011556846],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00023408995,0.00040101126,0.0003975663,0.00053501385,0.00023974279,0.00048424618,0.001913786,0.00032765896,0.000014704951],"category_scores_gemma":[0.000052203613,0.00043591642,0.00033944345,0.00067639555,0.00021119145,0.0003071292,0.0014083111,0.000531544,0.00007311913],"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":[0.000031362648,0.00013136605,0.00040192492,0.00034503677,0.00013960677,0.00024788457,0.00022612033,0.014723044,0.00044494035,0.9244916,0.0015705057,0.057246625],"study_design_scores_gemma":[0.0007291346,0.00005347637,0.00006444948,0.00026919195,0.000109244036,0.0000028013733,0.000175817,0.78660965,0.0022639611,0.20684136,0.0022891916,0.0005917214],"about_ca_topic_score_codex":0.000050923525,"about_ca_topic_score_gemma":0.00002089204,"teacher_disagreement_score":0.9555127,"about_ca_system_score_codex":0.0002271317,"about_ca_system_score_gemma":0.00042558135,"threshold_uncertainty_score":0.99980927},"labels":[],"label_agreement":null},{"id":"W4392669860","doi":"10.18653/v1/2023.ijcnlp-main.10","title":"MasakhaNEWS: News Topic Classification for African languages","year":2023,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute; University of Waterloo","funders":"DeepMind","keywords":"Computer science; Languages of Africa; Natural language processing; Artificial intelligence; Linguistics","score_opus":0.0562600828557314,"score_gpt":0.32059695456432447,"score_spread":0.26433687170859305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392669860","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":[0.0054384065,0.000050718285,0.90914446,0.04733341,0.00026331865,0.0004172356,0.0000030816218,0.0047057467,0.03264362],"genre_scores_gemma":[0.9313816,0.000048661313,0.040121514,0.00032718663,0.00004698272,0.000244924,0.000018635632,0.0000075890825,0.027802926],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992981,0.000011166096,0.00013502335,0.00025922703,0.000111749876,0.00018471782],"domain_scores_gemma":[0.99927324,0.0000980737,0.000051407293,0.0005113359,0.000036604713,0.000029339346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011273269,0.00007014954,0.00007505851,0.00016486114,0.000080567865,0.0001246917,0.00063950376,0.000051792562,0.00002302684],"category_scores_gemma":[0.000083409686,0.00005793105,0.000042026004,0.00058957713,0.000024613513,0.0002525262,0.00010437386,0.00003660432,0.00028030507],"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":[9.901377e-7,0.000010789267,0.0004190927,0.0000065031204,0.00000381913,5.520779e-7,0.00015648865,0.0000015483322,0.002609421,0.7358885,0.040468574,0.22043373],"study_design_scores_gemma":[0.0006408709,0.00016279744,0.0366671,0.000009683935,0.000008042339,0.0000027036685,0.007380658,0.048520688,0.023458155,0.109434,0.7732463,0.0004690138],"about_ca_topic_score_codex":0.000015758134,"about_ca_topic_score_gemma":0.00001683457,"teacher_disagreement_score":0.9259432,"about_ca_system_score_codex":0.000022450344,"about_ca_system_score_gemma":0.000020262645,"threshold_uncertainty_score":0.3602848},"labels":[],"label_agreement":null},{"id":"W4392904215","doi":"10.1109/icassp48485.2024.10447400","title":"ProbMCL: Simple Probabilistic Contrastive Learning for Multi-Label Visual Classification","year":2024,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Interpretability; Artificial intelligence; Machine learning; Probabilistic logic; Feature learning; Visualization; Contextual image classification; Pattern recognition (psychology); Image (mathematics)","score_opus":0.08465635311122566,"score_gpt":0.3599581659110958,"score_spread":0.27530181279987015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392904215","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":[0.0020804952,0.000133541,0.99136883,0.0019948161,0.0001913646,0.0007332914,0.0000017490004,0.002808036,0.0006878931],"genre_scores_gemma":[0.8843848,0.000009270747,0.11197837,0.000052071096,0.000031846386,0.00047365463,0.0000144179385,0.000013077936,0.0030424737],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99879414,0.000029912979,0.00023703942,0.00050233415,0.00018924607,0.00024732735],"domain_scores_gemma":[0.99922276,0.00027348506,0.000058201906,0.00022046245,0.0001823073,0.000042798507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032027843,0.00013145918,0.000118928976,0.00014106302,0.00015962185,0.00047191593,0.0004190749,0.00008639414,0.000016300497],"category_scores_gemma":[0.00049810146,0.000106754,0.000049199585,0.00039392873,0.00007249961,0.0005544315,0.000099399025,0.00014885001,0.00010473279],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004003603,0.00008478154,0.000103506194,0.000052357595,0.000015143745,7.395561e-7,0.00017379942,0.000019652036,0.0049154414,0.6773162,0.001643663,0.31567076],"study_design_scores_gemma":[0.00029573005,0.00015923816,0.00076379156,0.00001607176,0.000007920162,0.0000017894552,0.0001918122,0.9639949,0.002412372,0.014789508,0.0172108,0.00015606708],"about_ca_topic_score_codex":0.0000047496364,"about_ca_topic_score_gemma":0.000007006935,"teacher_disagreement_score":0.96397525,"about_ca_system_score_codex":0.00011159503,"about_ca_system_score_gemma":0.00011510805,"threshold_uncertainty_score":0.45506963},"labels":[],"label_agreement":null},{"id":"W4393160207","doi":"10.1609/aaai.v38i15.29562","title":"Federated Partial Label Learning with Local-Adaptive Augmentation and Regularization","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Text and Document Classification Technologies","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":"Canadian Institute for Advanced Research; Carleton University","funders":"","keywords":"Regularization (linguistics); Computer science; Artificial intelligence","score_opus":0.06017459565364345,"score_gpt":0.2866706267842369,"score_spread":0.22649603113059344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393160207","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":[0.04938832,0.00005597533,0.9412482,0.0056130406,0.00015320882,0.0003094152,9.927046e-7,0.000440736,0.0027901477],"genre_scores_gemma":[0.99659616,0.00003827493,0.0028220355,0.0000399208,0.00001480652,0.00002730144,7.292759e-7,0.0000073865695,0.0004533719],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989367,0.000013058712,0.00024308404,0.00037118603,0.00027964628,0.00015629636],"domain_scores_gemma":[0.99941605,0.000050381965,0.00014266097,0.00008697485,0.00027179118,0.00003214119],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021097573,0.00013129691,0.0001126047,0.00011309184,0.00020982801,0.0005961283,0.0003917206,0.000064103326,0.000013738989],"category_scores_gemma":[0.00007966542,0.00008947469,0.000020873787,0.00065678067,0.00028081512,0.00062225934,0.00014166355,0.0002119502,0.000022720182],"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":[0.000028720799,0.000022825065,0.00004767706,0.00001754558,0.000009665284,2.9628768e-7,0.00052837876,0.00004236892,0.016005207,0.76092696,0.000027191452,0.22234318],"study_design_scores_gemma":[0.000021826614,0.00025956487,0.00006303262,0.00016827778,0.000008954226,0.0000029645269,0.0010891346,0.44172284,0.4628116,0.09366988,0.00007281531,0.00010913021],"about_ca_topic_score_codex":0.000011994585,"about_ca_topic_score_gemma":0.0000034577665,"teacher_disagreement_score":0.94720787,"about_ca_system_score_codex":0.000037335896,"about_ca_system_score_gemma":0.000062547915,"threshold_uncertainty_score":0.5748479},"labels":[],"label_agreement":null},{"id":"W4393161100","doi":"10.1609/aaai.v38i19.30157","title":"Toward Robustness in Multi-Label Classification: A Data Augmentation Strategy against Imbalance and Noise","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; National Research Foundation of Korea; National Research Foundation","keywords":"Robustness (evolution); Computer science; Artificial intelligence; Machine learning; Noise (video); Pattern recognition (psychology); Biology","score_opus":0.30698202867343055,"score_gpt":0.37346752807819505,"score_spread":0.0664854994047645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393161100","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":[0.29704818,0.00079221703,0.6631922,0.031604044,0.0010426049,0.001493023,0.0000628706,0.0009371165,0.003827732],"genre_scores_gemma":[0.986823,0.00034904777,0.012536637,0.000060858856,0.000018326218,0.00004508458,0.00000466831,0.000008344125,0.00015399902],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982919,0.000014654823,0.0004762106,0.000688664,0.00030479854,0.00022378055],"domain_scores_gemma":[0.9990295,0.00007231622,0.00018530576,0.00046867516,0.00020074868,0.00004340994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044933116,0.00017682159,0.00017237206,0.00019989998,0.00009047122,0.0006321154,0.002258604,0.000094775474,0.000010704344],"category_scores_gemma":[0.00018055186,0.00013734527,0.000023201203,0.000864155,0.00026254405,0.0012200272,0.00056955044,0.00027266133,0.00002755797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011754464,0.000097174365,0.0002566547,0.00007085901,0.00000640615,7.88939e-7,0.00046676525,0.000031426745,0.027514609,0.6502076,0.00014172793,0.32119426],"study_design_scores_gemma":[0.000044564335,0.000052420644,0.0013306095,0.00024018179,0.0000057615184,0.0000025032587,0.0011404662,0.91582495,0.050716996,0.030415792,0.00005566765,0.00017008012],"about_ca_topic_score_codex":0.000016800393,"about_ca_topic_score_gemma":0.000017156124,"teacher_disagreement_score":0.91579354,"about_ca_system_score_codex":0.000053799453,"about_ca_system_score_gemma":0.000113477014,"threshold_uncertainty_score":0.60955036},"labels":[],"label_agreement":null},{"id":"W4393168550","doi":"10.23919/icact60172.2024.10471992","title":"Multi-Class Document Classification using LayoutLMv1 and V2","year":2024,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Class (philosophy); Computer science; Artificial intelligence; Information retrieval; Natural language processing","score_opus":0.062262732467935386,"score_gpt":0.3185489801885477,"score_spread":0.2562862477206123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393168550","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":[0.022033626,0.00088478933,0.965232,0.007174391,0.00040213467,0.0001782693,9.477448e-7,0.0020376556,0.0020561758],"genre_scores_gemma":[0.8751454,0.000086542896,0.12266162,0.00011892951,0.000019412953,0.000016641587,0.0000014552598,0.0000070125157,0.0019429828],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990551,0.000020937761,0.00018248736,0.00041393435,0.00015837007,0.00016915315],"domain_scores_gemma":[0.9994278,0.000050113307,0.00003344084,0.0004117028,0.00003018097,0.000046739897],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017285073,0.000109454995,0.000083970444,0.0001789246,0.00009579355,0.0006930833,0.00037670275,0.00007116129,0.000027613956],"category_scores_gemma":[0.000019991601,0.00008799203,0.000030270223,0.00036774285,0.00006599853,0.00083284976,0.0002103676,0.000098506374,0.00010022677],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.3433995e-7,0.00002348072,0.00028658903,0.000024076813,0.000014448506,0.0000045721627,0.00023644004,0.000009533054,0.02393085,0.84533715,0.0011336103,0.1289985],"study_design_scores_gemma":[0.0001769557,0.00002993571,0.0030589735,0.00003142702,0.000009237948,0.000018514671,0.00027043116,0.9324946,0.007406766,0.011269564,0.045001693,0.00023191479],"about_ca_topic_score_codex":0.000018908588,"about_ca_topic_score_gemma":0.0000040587715,"teacher_disagreement_score":0.93248504,"about_ca_system_score_codex":0.00006995535,"about_ca_system_score_gemma":0.000042173328,"threshold_uncertainty_score":0.66834176},"labels":[],"label_agreement":null},{"id":"W4393343556","doi":"10.36227/techrxiv.171177556.62647395/v1","title":"MediCaption: Integrating YOLO-Driven Computer Vision and NLP for Advanced Pharmaceutical Package Recognition and Annotation","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Text and Document Classification Technologies","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":"Lakehead University","funders":"","keywords":"Annotation; Computer science; Artificial intelligence; Natural language processing; Information retrieval","score_opus":0.05480120033226021,"score_gpt":0.3483446999975729,"score_spread":0.2935434996653127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393343556","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":[0.029649157,0.0007007342,0.9570067,0.009766141,0.00079058355,0.00073024456,0.000025704752,0.0010180285,0.00031272453],"genre_scores_gemma":[0.51105314,0.0006973783,0.4871759,0.00033778264,0.00014912552,0.0002484713,0.00016431666,0.000017278007,0.00015660697],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984494,0.0000447259,0.00034412666,0.00078858243,0.00019411554,0.00017906175],"domain_scores_gemma":[0.9991254,0.0002285252,0.00013963446,0.000303411,0.00012764278,0.00007537512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028928008,0.00023129692,0.00022971265,0.00021486956,0.000109856104,0.0005515365,0.00030479135,0.00025917136,0.0000128199845],"category_scores_gemma":[0.00007254264,0.00018494297,0.000056240577,0.00013779251,0.0001240647,0.00033410813,0.001328019,0.00045088457,0.000020253563],"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":[0.000010752245,0.000021431331,0.000011710871,0.00024108491,0.000020918074,0.0000023674795,0.00036325332,0.0000061763467,0.001666339,0.02833377,0.0009926095,0.9683296],"study_design_scores_gemma":[0.00065436575,0.00029506235,0.00025228836,0.00054646336,0.000048733535,0.000022295573,0.0002539606,0.718548,0.004515831,0.2700837,0.0043447395,0.00043454484],"about_ca_topic_score_codex":0.0000032319508,"about_ca_topic_score_gemma":0.000004611208,"teacher_disagreement_score":0.96789503,"about_ca_system_score_codex":0.00004537336,"about_ca_system_score_gemma":0.000040274794,"threshold_uncertainty_score":0.75417554},"labels":[],"label_agreement":null},{"id":"W4393371926","doi":"10.1109/tfuzz.2024.3382981","title":"Takagi–Sugeno–Kang Fuzzy Systems for High-Dimensional Multilabel Classification","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Fuzzy Systems","topic":"Text and Document Classification Technologies","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":"University of Alberta","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Fuzzy logic; Computer science; Fuzzy control system; Artificial intelligence; Pattern recognition (psychology); Mathematics","score_opus":0.03851565968555158,"score_gpt":0.2744791117419057,"score_spread":0.2359634520563541,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393371926","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":[0.0027521865,0.0023254354,0.97622067,0.0017880514,0.011354691,0.0016059933,0.00015484683,0.0029768224,0.0008213283],"genre_scores_gemma":[0.9895303,0.000100948426,0.0030658522,0.00004562095,0.00019205792,0.0015621046,0.00002151242,0.00004953296,0.0054320516],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970775,0.00011865538,0.0007189748,0.0009818787,0.00061600574,0.0004869753],"domain_scores_gemma":[0.9979246,0.00041837606,0.00017651357,0.0010958051,0.00024390234,0.00014076853],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00052791764,0.00036214024,0.00037231267,0.0006549367,0.00047668832,0.0009797683,0.00088601134,0.0003122985,0.000007563817],"category_scores_gemma":[0.00001380724,0.00032364967,0.00019725152,0.00090243644,0.00009507958,0.00087692915,0.0000066481475,0.00033955477,0.0005607431],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000067356676,0.00064246845,0.000008586338,0.0011169387,0.0004207396,0.000023944604,0.0006418611,0.034998443,0.034576856,0.80755967,0.027004588,0.092938535],"study_design_scores_gemma":[0.0013184256,0.0005776763,0.00011690094,0.00074053236,0.00013284732,0.00010179015,0.0007735422,0.9256623,0.013653463,0.003971331,0.051823765,0.0011274565],"about_ca_topic_score_codex":0.00017282287,"about_ca_topic_score_gemma":0.000010553194,"teacher_disagreement_score":0.98677814,"about_ca_system_score_codex":0.00034229527,"about_ca_system_score_gemma":0.00016904579,"threshold_uncertainty_score":0.99992156},"labels":[],"label_agreement":null},{"id":"W4394987794","doi":"10.1016/j.datak.2024.102306","title":"Effective text classification using BERT, MTM LSTM, and DT","year":2024,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada); University of Calgary","funders":"","keywords":"Security token; Computer science; Artificial intelligence; Encoder; Binary classification; Transformer; Recall; Deep learning; Long short term memory; Natural language processing; Artificial neural network; Machine learning; Recurrent neural network; Support vector machine","score_opus":0.04931219236959951,"score_gpt":0.3094819476933262,"score_spread":0.2601697553237267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394987794","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":[0.008288466,0.0063180053,0.98179084,0.0003773586,0.00075738324,0.00021887469,0.000024008546,0.0015926622,0.00063237426],"genre_scores_gemma":[0.94384235,0.0001292412,0.055550065,0.000009459266,0.00015163663,0.00004043996,0.0000644263,0.00002555523,0.00018679751],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989894,0.000016946315,0.00016094184,0.0005411881,0.000096554475,0.00019498325],"domain_scores_gemma":[0.9988191,0.00019002262,0.000024734452,0.00088751456,0.00002819763,0.000050400842],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002519094,0.00014727216,0.00011803977,0.00024724327,0.00007370016,0.00040714658,0.00089407194,0.00007670767,0.000004944014],"category_scores_gemma":[0.00012315382,0.00014004766,0.000019875775,0.0005601778,0.00003425457,0.0012863459,0.00077190466,0.00018001288,0.00009020637],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.676244e-7,0.00002347563,0.000098252094,0.00015274437,0.000036249865,0.0000058395176,0.0004128938,0.000016724518,0.022230068,0.14869931,0.0023505052,0.82597303],"study_design_scores_gemma":[0.000060775048,0.000011904033,0.0018155862,0.00008393756,0.000010802101,0.000012950435,0.000026068747,0.92512316,0.0019048546,0.0002897153,0.070500895,0.00015934315],"about_ca_topic_score_codex":0.000005098803,"about_ca_topic_score_gemma":0.0000022201873,"teacher_disagreement_score":0.9355539,"about_ca_system_score_codex":0.00007620501,"about_ca_system_score_gemma":0.00003418062,"threshold_uncertainty_score":0.5710978},"labels":[],"label_agreement":null},{"id":"W4396797825","doi":"10.3390/electronics13101859","title":"Hidden Variable Models in Text Classification and Sentiment Analysis","year":2024,"lang":"en","type":"article","venue":"Electronics","topic":"Text and Document Classification Technologies","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":"Concordia University","funders":"","keywords":"Variable (mathematics); Sentiment analysis; Artificial intelligence; Computer science; Natural language processing; Pattern recognition (psychology); Mathematics","score_opus":0.017311466224837296,"score_gpt":0.2570866683851846,"score_spread":0.23977520216034734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396797825","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":[0.021421108,0.017702615,0.94995964,0.0059898915,0.00009144055,0.00017889738,0.0000014718914,0.00080002483,0.0038549283],"genre_scores_gemma":[0.9874503,0.0009678281,0.010464591,0.000045229488,0.000008170068,0.000034760713,0.0000054459983,0.000005078607,0.0010186138],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990842,0.000023576484,0.00016585941,0.00036204173,0.00014239128,0.00022196425],"domain_scores_gemma":[0.9995181,0.0000449941,0.000029682147,0.0003641174,0.000018659022,0.000024438239],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023557142,0.00008344884,0.00010767457,0.00041079152,0.000042160176,0.00029720142,0.00032178807,0.00006448886,0.000014381591],"category_scores_gemma":[0.000008052756,0.00007787528,0.000032716885,0.0017930059,0.000021361537,0.00053903955,0.00009655157,0.0001479441,0.000021331161],"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":[7.564768e-7,0.000019229585,0.00026919803,0.00000654259,0.000054282544,0.0000011926917,0.00013930729,0.00019277474,0.0010562844,0.9267522,0.00036412652,0.071144074],"study_design_scores_gemma":[0.00006310749,0.00002405651,0.0013795953,0.000006446661,0.000034500084,0.0000017041401,0.00003165508,0.8094445,0.00085778657,0.17127766,0.01677321,0.000105792715],"about_ca_topic_score_codex":0.0000073993115,"about_ca_topic_score_gemma":0.000020319956,"teacher_disagreement_score":0.96602917,"about_ca_system_score_codex":0.00014920354,"about_ca_system_score_gemma":0.000089502326,"threshold_uncertainty_score":0.3175662},"labels":[],"label_agreement":null},{"id":"W4396964204","doi":"10.23977/jeis.2024.090205","title":"A Comprehensive Review of Text Classification Algorithms","year":2024,"lang":"en","type":"review","venue":"Journal of Electronics and Information Science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Algorithm; Artificial intelligence","score_opus":0.048905006203252895,"score_gpt":0.35917823473218735,"score_spread":0.31027322852893446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396964204","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":[5.6612816e-7,0.9812576,0.017148944,0.00056033087,0.0002503318,0.00022841594,0.0000033830872,0.000028445309,0.0005219714],"genre_scores_gemma":[0.000017913804,0.9960881,0.0037098858,0.00013807364,0.000017454264,0.000007470846,0.0000034745651,0.0000033600072,0.000014287172],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.997443,0.00003400382,0.0014303625,0.00015517467,0.0007339613,0.00020347393],"domain_scores_gemma":[0.9962463,0.00008025391,0.0022257587,0.00039472964,0.0009836372,0.00006935256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001339747,0.00017915948,0.0007288781,0.0010572545,0.000087553824,0.0003299487,0.0014914946,0.00009402012,0.00000347427],"category_scores_gemma":[0.00022173607,0.00011688173,0.00020267873,0.0024141897,0.0002407673,0.0055824094,0.00023581706,0.00043368497,0.000021630934],"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":[2.6480353e-7,0.000005672042,4.3454865e-8,0.01336266,0.000011115868,2.2868768e-7,0.000035865945,9.851333e-8,0.000002827617,0.1073115,0.00093474647,0.878335],"study_design_scores_gemma":[0.00004542905,0.0001320893,0.000003111786,0.0160305,0.000094019786,0.00015613351,0.000023506977,0.00080788584,0.000012286802,0.0008800681,0.98170286,0.00011210252],"about_ca_topic_score_codex":3.206083e-7,"about_ca_topic_score_gemma":2.2011672e-8,"teacher_disagreement_score":0.98076814,"about_ca_system_score_codex":0.00018051203,"about_ca_system_score_gemma":0.0017482339,"threshold_uncertainty_score":0.47662988},"labels":[],"label_agreement":null},{"id":"W4398162687","doi":"10.1109/access.2024.3403569","title":"Multi-Label Lifelong Machine Learning: A Scoping Review of Algorithms, Techniques, and Applications","year":2024,"lang":"en","type":"review","venue":"IEEE Access","topic":"Text and Document Classification Technologies","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 Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Lifelong learning; Computer science; Machine learning; Artificial intelligence; Forgetting; Process (computing); Adaptability; Adaptation (eye); Stability (learning theory); Multi-label classification; Intersection (aeronautics); Engineering","score_opus":0.13773303840081133,"score_gpt":0.44577431195005823,"score_spread":0.30804127354924693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398162687","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":[6.4261774e-9,0.836873,0.16004838,0.00016294119,0.000099465615,0.0018015443,0.000012677486,0.000885013,0.000116988165],"genre_scores_gemma":[1.809538e-7,0.957178,0.040748894,0.00004962101,0.00006634643,0.0015991175,0.000026688836,0.000029627068,0.00030150873],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979876,0.0000894254,0.00080276426,0.00068694894,0.000233379,0.00019986273],"domain_scores_gemma":[0.99820584,0.00013048512,0.0006284479,0.00088065857,0.00009739843,0.000057168036],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00041633315,0.0003378811,0.0011004239,0.00039588247,0.00009710798,0.00030584182,0.0022544356,0.00021895122,0.0000054908437],"category_scores_gemma":[0.0000628125,0.00026165356,0.00015233918,0.0013087149,0.000102861195,0.00046391744,0.000882095,0.00053482916,0.000031109696],"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":[5.342409e-8,0.000022585886,7.4984456e-7,0.1624266,0.000023336068,0.0000030159422,0.0000033248398,1.006935e-8,3.611917e-7,0.0008807076,0.00034108298,0.83629817],"study_design_scores_gemma":[0.000041950112,0.000017086748,8.061939e-8,0.2930782,0.00018595626,0.000032665972,5.446348e-7,0.00039259606,0.000032172542,0.00013850462,0.70583487,0.00024537064],"about_ca_topic_score_codex":0.000014148554,"about_ca_topic_score_gemma":0.0000024519434,"teacher_disagreement_score":0.8360528,"about_ca_system_score_codex":0.000048781032,"about_ca_system_score_gemma":0.0002343682,"threshold_uncertainty_score":0.99998355},"labels":[],"label_agreement":null},{"id":"W4399554982","doi":"10.48550/arxiv.2406.05631","title":"CCSI: Continual Class-Specific Impression for Data-free Class Incremental Learning","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Text and Document Classification Technologies","field":"Computer 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":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Impression; Class (philosophy); Computer science; Psychology; Artificial intelligence; World Wide Web","score_opus":0.1322242034962122,"score_gpt":0.23236020368046958,"score_spread":0.10013600018425739,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399554982","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":[0.07548391,0.000936283,0.9066275,0.002622754,0.003094809,0.001243143,0.00027604366,0.0036096966,0.0061058654],"genre_scores_gemma":[0.98734146,0.0004579672,0.005397283,0.00004668996,0.00013508226,0.000007786232,0.00029577775,0.000034207664,0.0062837196],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99694526,0.00010386094,0.00033836765,0.0019784283,0.00017671712,0.0004573347],"domain_scores_gemma":[0.9956885,0.00023989078,0.00035633348,0.0034570321,0.00014397572,0.00011424795],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00047547973,0.00039605878,0.00037675744,0.00042835774,0.00028771348,0.000565751,0.006800949,0.00048254596,0.000037995884],"category_scores_gemma":[0.00013720393,0.00042156084,0.00020075374,0.00051318196,0.00018904763,0.00068423274,0.019158881,0.0011201786,0.00015698267],"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":[0.000070696515,0.000120583485,0.0005847074,0.00018781585,0.00016346572,0.000096194504,0.00020879196,0.0026746783,0.0013662328,0.8904415,0.084820524,0.019264827],"study_design_scores_gemma":[0.0011811431,0.00013604296,0.00019098863,0.00021657662,0.000097969474,0.000004379716,0.00057367195,0.613084,0.0017326839,0.14405453,0.23791449,0.00081350695],"about_ca_topic_score_codex":0.00003908186,"about_ca_topic_score_gemma":0.000023627512,"teacher_disagreement_score":0.9118576,"about_ca_system_score_codex":0.000285675,"about_ca_system_score_gemma":0.00017503113,"threshold_uncertainty_score":0.99982363},"labels":[],"label_agreement":null},{"id":"W4399906408","doi":"10.18280/ria.380307","title":"A New Algorithm for Arabic Document Clustering Utilizing Maximal Wordsets","year":2024,"lang":"fr","type":"article","venue":"Revue d intelligence artificielle","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Arabic; Cluster analysis; Document clustering; Computer science; Artificial intelligence; Information retrieval; Algorithm; Natural language processing; Pattern recognition (psychology); Linguistics","score_opus":0.07427204738448545,"score_gpt":0.3190446043352724,"score_spread":0.24477255695078692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399906408","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000801753,0.039913073,0.9246999,0.02435437,0.0070344657,0.00079907733,0.000019379673,0.0009521493,0.0021474028],"genre_scores_gemma":[0.12703566,0.0026564016,0.66781074,0.0003366834,0.0013435449,0.00032186665,0.000024579933,0.00011084197,0.20035969],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99652904,0.00005863659,0.00089507416,0.0012363611,0.0003190777,0.00096180267],"domain_scores_gemma":[0.99798864,0.0004502852,0.00015198259,0.0010323066,0.00013981649,0.00023699712],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007192574,0.00042925007,0.0003740037,0.00036283492,0.00032380494,0.0018574557,0.0013396683,0.00028339747,0.0007027671],"category_scores_gemma":[0.00012643289,0.00045973537,0.0003443717,0.0012947374,0.00019104505,0.001399913,0.00054631056,0.00044210814,0.0019405513],"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":[0.00000504354,0.00004470728,0.0000027746255,0.00024778635,0.000037379225,0.00003655463,0.0015790287,0.0016036939,0.0003439692,0.24164261,0.00795224,0.7465042],"study_design_scores_gemma":[0.00003912424,0.00016595912,0.000004199201,0.00068563636,0.00003060235,0.00007322297,0.0008792715,0.63252234,0.020621033,0.044249732,0.30038342,0.000345461],"about_ca_topic_score_codex":0.00016886966,"about_ca_topic_score_gemma":0.00003160916,"teacher_disagreement_score":0.7461587,"about_ca_system_score_codex":0.0002995316,"about_ca_system_score_gemma":0.00032939992,"threshold_uncertainty_score":0.9997854},"labels":[],"label_agreement":null},{"id":"W4400612757","doi":"10.31436/iiumej.v25i2.3364","title":"Editorial","year":2024,"lang":"en","type":"editorial","venue":"IIUM Engineering Journal","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Engineering; Islam; Library science; Management; Theology; Philosophy; Computer science","score_opus":0.004789427579921352,"score_gpt":0.22719978476527677,"score_spread":0.22241035718535543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400612757","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.3091296e-7,0.0009918441,0.17512013,0.00043791078,0.8221005,0.00004003459,0.000007123907,0.0011298909,0.0001721334],"genre_scores_gemma":[0.000027578282,0.00032164247,0.009814687,0.000003808061,0.9884041,0.000011922793,0.0000074832765,0.000040084273,0.0013686938],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99779665,0.000012831495,0.00037708634,0.0003560492,0.0010918848,0.0003655032],"domain_scores_gemma":[0.9987558,0.00023873751,0.00014246097,0.0005336116,0.00021293669,0.00011643238],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0004428976,0.00029353792,0.00026575572,0.00047790512,0.000085658015,0.0016474526,0.0020125692,0.0008139929,0.000013487069],"category_scores_gemma":[0.000716906,0.00025901504,0.00017883012,0.0003502645,0.00001870639,0.0004859424,0.00037017927,0.002752228,0.00030405278],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.748711e-7,0.0000070290494,9.3792664e-8,0.00003761103,0.00003717444,0.000026681799,0.000031729105,0.0001532997,0.00007140765,0.0027464554,0.9947909,0.0020966472],"study_design_scores_gemma":[0.00012453603,0.000044854532,4.774768e-7,0.00012977447,0.000015846023,0.000020361736,0.0000026696666,0.00264001,0.00006848557,0.0014930079,0.9951808,0.00027918484],"about_ca_topic_score_codex":0.0000014149649,"about_ca_topic_score_gemma":1.6507548e-7,"teacher_disagreement_score":0.16630359,"about_ca_system_score_codex":0.00023058824,"about_ca_system_score_gemma":0.00036815106,"threshold_uncertainty_score":0.99998623},"labels":[],"label_agreement":null},{"id":"W4400653413","doi":"10.5267/j.ijdns.2024.6.012","title":"An improved multi-stage framework for large-scale hierarchical text classification problems using a modified feature hashing and bi-filtering strategy","year":2024,"lang":"en","type":"article","venue":"International Journal of Data and Network Science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Hierarchy; Reduction (mathematics); Hash function; Pattern recognition (psychology); Artificial intelligence; Dimensionality reduction; Data mining; Feature (linguistics); Multi-label classification; Feature hashing; Task (project management); Scale (ratio); Machine learning; Hash table; Mathematics","score_opus":0.12167052302534487,"score_gpt":0.39335622059897357,"score_spread":0.2716856975736287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400653413","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":[0.03591241,0.0007242339,0.9604787,0.0019926708,0.0006413063,0.00012758856,0.000044939443,0.00006673705,0.000011363527],"genre_scores_gemma":[0.634934,0.00015725763,0.36464763,0.000051724983,0.00017968389,0.0000027692536,0.0000071991426,0.000004731312,0.0000149907955],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985641,0.000026862192,0.00030761678,0.00047734173,0.00037741737,0.00024663415],"domain_scores_gemma":[0.9989184,0.00016142504,0.00021490357,0.00039116808,0.00020428392,0.00010978135],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001372165,0.00011291844,0.00012937094,0.00025347955,0.0002539653,0.0021286074,0.00225574,0.00008098744,0.0000017959825],"category_scores_gemma":[0.000119362114,0.000090018926,0.000026540087,0.00041026526,0.00019452021,0.0043739122,0.00055419584,0.00031922097,2.611737e-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":[0.00007476439,0.00018330193,0.0013283022,0.00007444728,0.00008871795,0.00002138315,0.0018090243,0.0039995075,0.120466486,0.42178267,0.00033190346,0.4498395],"study_design_scores_gemma":[0.00022096543,0.00008703665,0.0014544274,0.0001729027,0.0000076206097,0.00006188142,0.0002310882,0.98393625,0.0002641263,0.011669452,0.0017850627,0.00010920954],"about_ca_topic_score_codex":0.0000033420044,"about_ca_topic_score_gemma":0.000007524277,"teacher_disagreement_score":0.9799367,"about_ca_system_score_codex":0.000043152286,"about_ca_system_score_gemma":0.0002127918,"threshold_uncertainty_score":0.99890727},"labels":[],"label_agreement":null},{"id":"W4400725186","doi":"10.1007/978-3-031-64359-0_24","title":"Limitations of the Utility of Categorization in eDiscovery Review Efforts","year":2024,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Categorization; Computer science; Information retrieval; Data science; Artificial intelligence","score_opus":0.09306055483829982,"score_gpt":0.2995506511540169,"score_spread":0.20649009631571708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400725186","genre_codex":"other","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":[0.00017924234,0.019961203,0.3892952,0.0197903,0.0012145721,0.0023757394,0.000053858523,0.00021835252,0.5669116],"genre_scores_gemma":[0.8282842,0.13024639,0.038773406,0.0007854744,0.0000131908355,0.00008382103,0.000058098845,0.00001052325,0.0017448883],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984414,0.000022709342,0.0008888861,0.00017906885,0.00036519126,0.000102773025],"domain_scores_gemma":[0.9969857,0.00022148051,0.00048805293,0.0020039147,0.00028193754,0.000018920522],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00088792644,0.0001228565,0.0002273564,0.00069359236,0.00009850112,0.00010293766,0.0027973363,0.00008260805,0.0000030137533],"category_scores_gemma":[0.00013247541,0.00009616417,0.000054650158,0.0010838946,0.0009095195,0.0031738414,0.0019728662,0.0002654388,0.0000065219865],"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":[2.934592e-7,0.0000087309845,0.00006594279,0.00019597831,0.0000018105701,2.609756e-8,0.00036900767,0.000016394073,0.0000021731457,0.9042227,0.00024604984,0.09487084],"study_design_scores_gemma":[0.00033629467,0.000073544754,0.015605899,0.007298551,0.00003195427,0.0000125387805,0.000077945224,0.3155322,0.0003359552,0.39680642,0.26336107,0.0005276088],"about_ca_topic_score_codex":0.000011196703,"about_ca_topic_score_gemma":0.000019062194,"teacher_disagreement_score":0.828105,"about_ca_system_score_codex":0.000067591325,"about_ca_system_score_gemma":0.00032674757,"threshold_uncertainty_score":0.5198193},"labels":[],"label_agreement":null},{"id":"W4400868692","doi":"10.1007/s10489-024-05639-z","title":"Multi-kernel partial label learning using graph contrast disambiguation","year":2024,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Dongguan Science and Technology Bureau","keywords":"Computer science; Artificial intelligence; Contrast (vision); Graph; Kernel (algebra); Pattern recognition (psychology); Natural language processing; Theoretical computer science; Discrete mathematics; Mathematics","score_opus":0.06580646160920452,"score_gpt":0.3192109118102478,"score_spread":0.2534044502010433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400868692","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":[0.011414149,0.00035975577,0.9855395,0.0002990051,0.00034447192,0.00017519324,8.4383663e-7,0.0013446189,0.0005224667],"genre_scores_gemma":[0.9406402,0.000078129684,0.05897533,0.000055624594,0.000030952146,0.000043137286,0.0000035325907,0.0000111731915,0.00016189062],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998752,0.000021111393,0.0002670958,0.00047777922,0.00021834843,0.00026369435],"domain_scores_gemma":[0.999413,0.00010716702,0.00006509512,0.00033117295,0.000037060967,0.000046473706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023599082,0.00014666656,0.00011689179,0.00015566003,0.00016803216,0.0004379568,0.0006251962,0.00008748401,0.000028868157],"category_scores_gemma":[0.00005032462,0.00013598087,0.000042683634,0.0006883191,0.00011464411,0.0004112457,0.00016915341,0.0002552462,0.00030193749],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003164056,0.000045302862,0.00013422387,0.000016941278,0.000016785969,0.0000042114943,0.00060155726,0.0012242293,0.054348852,0.5938638,0.000061302744,0.34967965],"study_design_scores_gemma":[0.00007273188,0.000028777948,0.00018172339,0.000034186298,0.000009845057,0.000005071168,0.0003345154,0.8451705,0.13155358,0.019928757,0.0024339175,0.00024642196],"about_ca_topic_score_codex":0.000024892159,"about_ca_topic_score_gemma":0.0000029320984,"teacher_disagreement_score":0.9292261,"about_ca_system_score_codex":0.00005304625,"about_ca_system_score_gemma":0.000044666933,"threshold_uncertainty_score":0.55451393},"labels":[],"label_agreement":null},{"id":"W4401009136","doi":"10.1016/j.inffus.2024.102600","title":"Incomplete label distribution learning via label correlation decomposition","year":2024,"lang":"en","type":"article","venue":"Information Fusion","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Computer science; Decomposition; Distribution (mathematics); Correlation; Multi-label classification; Artificial intelligence; Mathematics; Chemistry","score_opus":0.012884044777630204,"score_gpt":0.26547569615949135,"score_spread":0.2525916513818611,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401009136","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":[0.013873005,0.000082863175,0.97932553,0.001992545,0.0006435861,0.0001819724,0.000007655496,0.002074521,0.0018182917],"genre_scores_gemma":[0.9906048,0.00005665342,0.008214017,0.00012217373,0.000032349864,0.000030352041,0.0007714658,0.000004699929,0.00016344615],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896276,0.000038062124,0.00036722724,0.00016099667,0.00030646432,0.00016448804],"domain_scores_gemma":[0.9994074,0.00007067211,0.00013452183,0.00022904435,0.000118798554,0.00003954207],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00027613947,0.00011782784,0.00008342833,0.00023831916,0.00030395202,0.0006185393,0.00029569832,0.00011592856,0.00004206542],"category_scores_gemma":[0.000056954766,0.000110096116,0.00003291546,0.00068325613,0.000027465958,0.00491583,0.00017381221,0.00022660226,0.0013399583],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000061261603,0.00001885542,0.00015874591,0.000037368398,0.0000063011307,0.0000010175077,0.0005012822,0.0004301538,0.0030102024,0.19007128,0.0034781555,0.8022805],"study_design_scores_gemma":[0.00024281575,0.00007544677,0.0018052391,0.00005252858,0.0000048809575,0.000013699776,0.000041439554,0.87762177,0.00146047,0.006679599,0.11185387,0.00014822872],"about_ca_topic_score_codex":0.000012736789,"about_ca_topic_score_gemma":0.0000011753631,"teacher_disagreement_score":0.97673184,"about_ca_system_score_codex":0.00015749547,"about_ca_system_score_gemma":0.000033295593,"threshold_uncertainty_score":0.99943763},"labels":[],"label_agreement":null},{"id":"W4401508264","doi":"10.1109/dcoss-iot61029.2024.00037","title":"Privacy-Preserving Multi-Party Keyword-Based Classification of Unstructured Text Data","year":2024,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"Queen's University","funders":"","keywords":"Computer science; Information retrieval; Unstructured data; Keyword search; Natural language processing; World Wide Web; Data mining; Big data","score_opus":0.10229281079065004,"score_gpt":0.3338654759186699,"score_spread":0.23157266512801983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401508264","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":[0.0032738177,0.00036572537,0.9822898,0.00980992,0.00035227695,0.00020355968,0.000015977232,0.0016252984,0.00206365],"genre_scores_gemma":[0.79571944,0.000013683224,0.2034389,0.00006741397,0.000015116302,0.000011798972,0.00004285954,0.000007983608,0.0006828009],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855924,0.000038818976,0.00033451698,0.0006100985,0.00027200236,0.0001853319],"domain_scores_gemma":[0.99661994,0.0001933676,0.000097076525,0.0029802388,0.00006797959,0.000041422478],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027640027,0.00013080797,0.00013716743,0.00023333094,0.00006438228,0.00028103872,0.0040019797,0.0000979549,0.00011915703],"category_scores_gemma":[0.00029603826,0.00010269731,0.000043138127,0.00079908717,0.00009496926,0.001073667,0.0011802502,0.00014019251,0.000069620975],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000062851777,0.00012129238,0.002280293,0.0001871233,0.00004501767,0.000004387643,0.00026897018,0.000060037164,0.05810684,0.553587,0.0454325,0.33990026],"study_design_scores_gemma":[0.00019096292,0.000019889121,0.010604061,0.000041405827,0.000007988056,0.0000014737057,0.000068660374,0.9129182,0.031179035,0.0063598556,0.03845095,0.00015752616],"about_ca_topic_score_codex":0.000028695778,"about_ca_topic_score_gemma":0.000018923098,"teacher_disagreement_score":0.9128581,"about_ca_system_score_codex":0.00003337015,"about_ca_system_score_gemma":0.00013649417,"threshold_uncertainty_score":0.7436741},"labels":[],"label_agreement":null},{"id":"W4402670684","doi":"10.18653/v1/2024.findings-acl.151","title":"Accurate and Nuanced Open-QA Evaluation Through Textual Entailment","year":2024,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Textual entailment; Computer science; Natural language processing; Logical consequence; Artificial intelligence; Information retrieval","score_opus":0.0861146672899413,"score_gpt":0.3814566730101803,"score_spread":0.29534200572023905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402670684","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":[0.015387202,0.0015913246,0.89045745,0.026877176,0.0005417303,0.0008544943,0.00000212246,0.001527107,0.06276137],"genre_scores_gemma":[0.9749982,0.00009961072,0.022357656,0.00028457365,0.00001358016,0.0001016418,0.0000034825184,0.0000035981686,0.0021376873],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991311,0.00002811165,0.00014089703,0.00035683202,0.00022143463,0.00012164763],"domain_scores_gemma":[0.99952525,0.000050929575,0.000027222166,0.00033639855,0.000039437837,0.000020790856],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00030828916,0.00008073535,0.000070294824,0.000050129525,0.000065818385,0.0011364566,0.0006634387,0.000038278,0.00016967129],"category_scores_gemma":[0.00002859314,0.000060963368,0.000015333766,0.0002845807,0.000039304243,0.0017228934,0.0005555901,0.00006182037,0.00015960867],"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":[0.000001000464,0.000013177503,0.000019600346,0.0000048737493,0.000007809864,9.845701e-7,0.00027818847,0.000006688353,0.0009505695,0.7346714,0.00974935,0.25429633],"study_design_scores_gemma":[0.0008574668,0.00020840834,0.002377952,0.0000690888,0.00002476077,0.000015849191,0.001457307,0.3705481,0.05267909,0.34542593,0.2258703,0.0004657472],"about_ca_topic_score_codex":0.000021767491,"about_ca_topic_score_gemma":0.0000060214725,"teacher_disagreement_score":0.959611,"about_ca_system_score_codex":0.000050935443,"about_ca_system_score_gemma":0.000063692256,"threshold_uncertainty_score":0.99990046},"labels":[],"label_agreement":null},{"id":"W4402671274","doi":"10.18653/v1/2024.acl-long.808","title":"Tree-Averaging Algorithms for Ensemble-Based Unsupervised Discontinuous Constituency Parsing","year":2024,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer 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":"Alliance de recherche numérique du Canada; Alberta Innovates; DeepMind; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Parsing; Computer science; Tree (set theory); Ensemble learning; Artificial intelligence; Algorithm; Machine learning; Mathematics","score_opus":0.03995286326179818,"score_gpt":0.2922784025302487,"score_spread":0.2523255392684505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402671274","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":[0.0009916015,0.00046429527,0.9799111,0.009349567,0.0006941318,0.00029475483,0.000003790512,0.0025020665,0.005788699],"genre_scores_gemma":[0.77163184,0.000010071993,0.22660129,0.00026332508,0.000040585877,0.00008757296,0.00000785336,0.000010795534,0.0013466536],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988397,0.000016224587,0.00022820772,0.00046526882,0.00016109095,0.00028954135],"domain_scores_gemma":[0.9992039,0.00022813861,0.000030382009,0.00043939386,0.000048721253,0.00004943074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018277921,0.00014576517,0.00014122737,0.0002127389,0.0001484748,0.0006788558,0.0005821745,0.000063438005,0.000032080236],"category_scores_gemma":[0.000040776074,0.00011848914,0.00010204473,0.00042552955,0.00007720679,0.0005753505,0.000077177756,0.00008988026,0.000056576293],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019868924,0.000023081726,0.000059468763,0.00003139838,0.000011320089,0.000008679811,0.00009270318,0.000014323057,0.0030331311,0.38996303,0.0030683975,0.6036925],"study_design_scores_gemma":[0.00064076524,0.000093730494,0.00010251789,0.0001180896,0.00001744675,0.000009471501,0.00021341162,0.8556584,0.055404764,0.035157386,0.052190945,0.0003930613],"about_ca_topic_score_codex":0.000012654495,"about_ca_topic_score_gemma":0.0000059754034,"teacher_disagreement_score":0.8556441,"about_ca_system_score_codex":0.00004209922,"about_ca_system_score_gemma":0.00013202241,"threshold_uncertainty_score":0.6546222},"labels":[],"label_agreement":null},{"id":"W4402812082","doi":"10.1109/iccc62479.2024.10681804","title":"DCML: Boosting Applying Experience of NILM with Dilated Convolution and Multi-Task Learning","year":2024,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"University of Waterloo; University of Calgary","funders":"Research and Development; Central South University; National Natural Science Foundation of China","keywords":"Boosting (machine learning); Computer science; Convolution (computer science); Task (project management); Artificial intelligence; Engineering","score_opus":0.020856789116897853,"score_gpt":0.261504320181814,"score_spread":0.24064753106491615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402812082","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":[0.14920156,0.0004919083,0.84812635,0.00020476968,0.000048313406,0.00011696966,1.5679261e-7,0.0010429394,0.0007670461],"genre_scores_gemma":[0.9555447,0.000026215186,0.043846928,0.00001124266,0.000003376,0.00003004248,6.827288e-7,0.0000040526697,0.00053272466],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99936545,0.000013535457,0.00013306914,0.00025411937,0.00011530087,0.00011851309],"domain_scores_gemma":[0.9996746,0.00006881322,0.000047677204,0.00015414094,0.00003307198,0.000021664797],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010070079,0.00007150432,0.00007648165,0.00009776244,0.0000886731,0.00014153244,0.00019460214,0.000036521258,0.0000063358784],"category_scores_gemma":[0.000042550106,0.00005331807,0.00001163799,0.00035471426,0.00009990564,0.0004984661,0.00013054244,0.00010254799,0.000006032852],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008961087,0.000046389476,0.038358517,0.00014808397,0.00003565777,0.000017189208,0.009033595,0.00031433546,0.15660878,0.24944213,0.00010186405,0.5458845],"study_design_scores_gemma":[0.00026077934,0.00012075901,0.0067190286,0.0001597196,0.000006044634,0.00002228286,0.0025861014,0.9333462,0.053087875,0.00055180327,0.0029161593,0.0002232619],"about_ca_topic_score_codex":0.000032876353,"about_ca_topic_score_gemma":0.000002776498,"teacher_disagreement_score":0.93303186,"about_ca_system_score_codex":0.0000142042745,"about_ca_system_score_gemma":0.000019390993,"threshold_uncertainty_score":0.21742477},"labels":[],"label_agreement":null},{"id":"W4403724357","doi":"10.1109/dsaa61799.2024.10722777","title":"Multi-View Relational Evidential C-Medoid Clustering with Adaptive Weighted","year":2024,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"Simon Fraser University","funders":"","keywords":"Medoid; Cluster analysis; Computer science; Data mining; Artificial intelligence; Pattern recognition (psychology)","score_opus":0.04369156456313723,"score_gpt":0.27403866543081806,"score_spread":0.23034710086768084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403724357","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":[0.0006245684,0.00079528673,0.9912678,0.0030919372,0.00024537623,0.0001279183,8.269048e-7,0.0015905558,0.002255749],"genre_scores_gemma":[0.5780963,0.000051517014,0.41712973,0.000080939186,0.000030547657,0.000033721237,0.0000026156451,0.0000072925595,0.004567361],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991424,0.000018095614,0.0001477986,0.0003309219,0.00021994856,0.00014082354],"domain_scores_gemma":[0.9995409,0.00006750571,0.000029234792,0.00028450094,0.000045188648,0.00003261771],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000102056096,0.000098782504,0.00007869487,0.00013893016,0.00007997225,0.00026502897,0.00039905228,0.000049441864,0.00011894091],"category_scores_gemma":[0.000009548939,0.00006862671,0.000033766406,0.00044710693,0.000051946463,0.0009529588,0.000189779,0.00012074827,0.00034731676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008933778,0.000040705236,0.0002727201,0.000026477084,0.00006882358,0.000029819232,0.00032027808,0.00008366772,0.00072424696,0.86156195,0.0028376132,0.13402475],"study_design_scores_gemma":[0.00027590722,0.00010415264,0.003955189,0.00012590141,0.000011777359,0.000031304455,0.00008380706,0.9514947,0.001622399,0.0031929608,0.03884707,0.00025481588],"about_ca_topic_score_codex":0.000012504195,"about_ca_topic_score_gemma":0.000029366027,"teacher_disagreement_score":0.95141107,"about_ca_system_score_codex":0.000045173736,"about_ca_system_score_gemma":0.0000623883,"threshold_uncertainty_score":0.446417},"labels":[],"label_agreement":null},{"id":"W4403839440","doi":"10.1080/10618600.2024.2421248","title":"Multi-label Random Subspace Ensemble Classification","year":2024,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University; National Institute on Aging; National Institutes of Health; National Science Foundation","keywords":"Random forest; Random subspace method; Computer science; Classifier (UML); Subspace topology; Artificial intelligence; Ensemble learning; Linear subspace; Machine learning; Pattern recognition (psychology); Multinomial distribution; Multi-label classification; Data mining; Algorithm; Mathematics; Statistics","score_opus":0.03378278262940175,"score_gpt":0.30295361300985085,"score_spread":0.2691708303804491,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403839440","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":[0.00512162,0.0012152175,0.9874786,0.0056802747,0.00030704212,0.000058108853,0.000013582037,0.00008575278,0.000039776267],"genre_scores_gemma":[0.5323154,0.00022358648,0.4672695,0.00008036882,0.000032985277,0.0000018014601,0.000004557845,0.0000040910563,0.00006769946],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890023,0.000050004095,0.0004056515,0.00016328486,0.00036371095,0.00011714298],"domain_scores_gemma":[0.99867505,0.0007051973,0.00016375806,0.00009006824,0.00027780503,0.00008813359],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032272754,0.000100213234,0.00016210928,0.0002643539,0.00009640433,0.00032466245,0.0002666808,0.000063402644,0.0000060565703],"category_scores_gemma":[0.00013527767,0.00007672436,0.00004682037,0.00041547578,0.00012056275,0.00037298384,0.00004913654,0.00023342128,0.000009321779],"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":[0.000016072587,0.0000750331,0.00022809264,0.000027330809,0.00003990757,0.000030476966,0.000112099355,0.00013534253,0.00044529102,0.8312623,0.0042330986,0.16339496],"study_design_scores_gemma":[0.00068461784,0.000111830275,0.012875379,0.000030654097,0.000016044709,0.00009960852,0.000027105529,0.57111645,0.000040264713,0.41180608,0.0031000413,0.000091963935],"about_ca_topic_score_codex":0.0000011984044,"about_ca_topic_score_gemma":0.0000011701061,"teacher_disagreement_score":0.5709811,"about_ca_system_score_codex":0.000020999309,"about_ca_system_score_gemma":0.00009066636,"threshold_uncertainty_score":0.31307274},"labels":[],"label_agreement":null},{"id":"W4404037418","doi":"10.1109/mlsp58920.2024.10734736","title":"Self Supervised Dictionary Learning Using Kernel Matching","year":2024,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"McGill University","funders":"","keywords":"Computer science; Artificial intelligence; Kernel (algebra); Dictionary learning; Pattern recognition (psychology); Matching (statistics); Machine learning; Semi-supervised learning; Mathematics; Sparse approximation; Statistics","score_opus":0.02366937728997995,"score_gpt":0.2678861414947453,"score_spread":0.24421676420476537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404037418","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":[0.03755946,0.00041230128,0.94683814,0.001761095,0.00036099725,0.00005714173,1.7131076e-7,0.006230301,0.0067804037],"genre_scores_gemma":[0.83674985,0.00003842926,0.16142464,0.00006271775,0.00003356797,0.00000516929,0.0000010585411,0.0000071320487,0.0016774606],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992957,0.000020579839,0.0001226178,0.00026594504,0.0001509382,0.00014418176],"domain_scores_gemma":[0.9996638,0.000059824626,0.000015684565,0.00021679608,0.00001781764,0.000026091227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012972402,0.00007771457,0.000059614198,0.00014977784,0.00015226219,0.0004362999,0.00038398948,0.00004757355,0.000062129875],"category_scores_gemma":[0.000009333527,0.00006582423,0.000041372772,0.0003952358,0.000015966907,0.0008344725,0.0002137204,0.00016332752,0.00018137485],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.1972204e-7,0.000027616306,0.0008325769,0.000044899007,0.000029304601,0.000021194737,0.0013229783,0.000561128,0.007484671,0.88669896,0.0006982704,0.10227766],"study_design_scores_gemma":[0.000051605886,0.000016118387,0.0003212784,0.000021975773,0.000004103264,0.000022793782,0.00030776023,0.9544553,0.0016700577,0.020854028,0.022146204,0.00012878237],"about_ca_topic_score_codex":0.000014948414,"about_ca_topic_score_gemma":4.054394e-7,"teacher_disagreement_score":0.95389414,"about_ca_system_score_codex":0.000052894662,"about_ca_system_score_gemma":0.000041738294,"threshold_uncertainty_score":0.420725},"labels":[],"label_agreement":null},{"id":"W4404200925","doi":"10.1007/978-3-031-71452-8_12","title":"What Constitutes a Sufficiently Adequate Binary Classification System?","year":2024,"lang":"en","type":"book-chapter","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jewish General Hospital","funders":"","keywords":"Binary number; Computer science; Mathematics; Arithmetic","score_opus":0.039512616332957815,"score_gpt":0.25775004462695994,"score_spread":0.2182374282940021,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404200925","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000053537337,0.0067207986,0.054721706,0.0054383613,0.0049182936,0.00053768896,0.000010425244,0.005357497,0.92228985],"genre_scores_gemma":[0.032490756,0.0009252369,0.0022439861,0.00013017868,0.0000969672,0.00009054022,0.000044369015,0.00003952184,0.9639384],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975964,0.000010873072,0.00056172564,0.001039662,0.0004947581,0.00029661352],"domain_scores_gemma":[0.99780905,0.00009861788,0.00028525147,0.001568622,0.00014973179,0.000088700544],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00021110465,0.000426011,0.00035543574,0.00064448063,0.000145284,0.0016739683,0.0015766161,0.0004751167,0.00017630542],"category_scores_gemma":[0.000010477335,0.00035871312,0.00019605337,0.00018317049,0.0002807441,0.0012416841,0.0005865047,0.000428655,0.007237831],"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":[0.000001377316,0.000014348562,6.5628785e-7,0.00011429823,0.000046894984,0.00003255309,0.00006457994,0.0000017458322,0.000059969352,0.96864146,0.014064127,0.016958004],"study_design_scores_gemma":[0.00016008515,0.00012402433,0.000013392441,0.0013654131,0.000086117725,0.0000667197,0.0012743073,0.014738992,0.00034408257,0.101725794,0.87916905,0.00093201036],"about_ca_topic_score_codex":0.0000035657088,"about_ca_topic_score_gemma":0.0000020980724,"teacher_disagreement_score":0.86691564,"about_ca_system_score_codex":0.00026499244,"about_ca_system_score_gemma":0.00016649892,"threshold_uncertainty_score":0.9998865},"labels":[],"label_agreement":null},{"id":"W4404387399","doi":"10.18280/ts.410509","title":"Enhanced Improved Proportionate Set-Membership Fast NLMS Using the ℓ0 Norm","year":2024,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Norm (philosophy); Mathematics; Set (abstract data type); Computer science; Political science; Programming language","score_opus":0.03695893696391265,"score_gpt":0.27848977989132734,"score_spread":0.2415308429274147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404387399","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":[0.056409236,0.00022901886,0.93436354,0.005607408,0.0004753196,0.00047422692,0.0000056861018,0.0011449934,0.001290555],"genre_scores_gemma":[0.99417114,0.000009729726,0.004823271,0.00018984944,0.00009537386,0.00007599779,0.000006400758,0.000010973121,0.0006172591],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864924,0.00003589058,0.00030825604,0.00041378167,0.00029665924,0.0002961522],"domain_scores_gemma":[0.99935436,0.000065350665,0.000090730275,0.00038458884,0.00005970243,0.000045263903],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037800663,0.00016547546,0.00010956908,0.000118942015,0.00021681593,0.000547877,0.0008336054,0.00006063509,0.00025788718],"category_scores_gemma":[0.000012387027,0.00010966318,0.00008594156,0.0004932463,0.00010771856,0.0006132519,0.00016996768,0.00018101925,0.000071437826],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017046572,0.00010922887,0.0000707087,0.00009415102,0.00011437152,0.000020491498,0.0028438517,0.0003793633,0.29484385,0.41617998,0.001999772,0.2833272],"study_design_scores_gemma":[0.0004985009,0.00019775837,0.00075939693,0.00009092636,0.000041868338,0.000022359014,0.0010196109,0.73606986,0.22610058,0.021732846,0.012939946,0.0005263764],"about_ca_topic_score_codex":0.000016033731,"about_ca_topic_score_gemma":0.0000071992613,"teacher_disagreement_score":0.9377619,"about_ca_system_score_codex":0.0000995054,"about_ca_system_score_gemma":0.00010848352,"threshold_uncertainty_score":0.52831906},"labels":[],"label_agreement":null},{"id":"W4404682082","doi":"10.54254/2755-2721/97/20241397","title":"Review on Application of Chi-square Statistic in Text Classification in Recent Five Years","year":2024,"lang":"en","type":"article","venue":"Applied and Computational Engineering","topic":"Text and Document Classification Technologies","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":"McMaster University","funders":"","keywords":"Feature selection; Statistic; Chi-square test; Computer science; Feature (linguistics); Selection (genetic algorithm); Test (biology); Natural language processing; Artificial intelligence; Information retrieval; Statistics; Mathematics; Linguistics","score_opus":0.012529627397966573,"score_gpt":0.2512400210169778,"score_spread":0.23871039361901122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404682082","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":[0.009232354,0.0046823337,0.9836602,0.0012717665,0.00006677015,0.00044599304,0.0000057970583,0.00023923129,0.00039552368],"genre_scores_gemma":[0.98669475,0.0013724476,0.011754523,0.00007530696,0.0000062771733,0.00006244405,0.00002425858,0.000005559088,0.0000044487083],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993276,0.00000665186,0.00023351217,0.0002292877,0.00012090312,0.000082020575],"domain_scores_gemma":[0.9996813,0.00012547281,0.000038290305,0.00012212672,0.000016540029,0.00001625475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012884078,0.000074221956,0.00010878756,0.00023411284,0.000008982805,0.00002883132,0.0001426737,0.000031766205,0.0000022882125],"category_scores_gemma":[0.000018026336,0.00007696576,0.000011449312,0.00059346686,0.000013916226,0.00008585915,0.000033232387,0.00010147747,0.000011656348],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013012984,0.000018485056,0.00003086195,0.00025545157,0.0000027299084,8.09134e-7,0.00009904629,0.025098048,0.00020227453,0.69407284,0.00006789729,0.28015026],"study_design_scores_gemma":[0.00015795758,0.000021097563,0.05105744,0.00059651013,0.0000025434013,0.0000017091556,0.00003186229,0.9249608,0.00008280116,0.019688189,0.003274437,0.00012464904],"about_ca_topic_score_codex":0.0000046843534,"about_ca_topic_score_gemma":0.0000012341181,"teacher_disagreement_score":0.97746235,"about_ca_system_score_codex":0.000050943545,"about_ca_system_score_gemma":0.00002411845,"threshold_uncertainty_score":0.31385726},"labels":[],"label_agreement":null},{"id":"W4404781466","doi":"10.18653/v1/2024.findings-emnlp.257","title":"Graph-tree Fusion Model with Bidirectional Information Propagation for Long Document Classification","year":2024,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer 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":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Artificial intelligence; Graph; Document classification; Tree (set theory); Fusion; Information retrieval; Data mining; Theoretical computer science; Mathematics","score_opus":0.02160782277492738,"score_gpt":0.2581732532938748,"score_spread":0.23656543051894743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404781466","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":[0.0025175973,0.000046253437,0.9847754,0.0071203965,0.00019538018,0.000576516,0.0000024048754,0.0016894187,0.0030766008],"genre_scores_gemma":[0.88334745,0.000040911655,0.114251785,0.00011518147,0.000025803056,0.0004959922,0.00007493761,0.0000073386095,0.0016405837],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99900365,0.000010540938,0.0002497271,0.0002708427,0.0003108633,0.00015436391],"domain_scores_gemma":[0.9993619,0.000047573463,0.00008020051,0.00030997844,0.00016667468,0.00003369093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022067623,0.000118865515,0.00007370069,0.00037537928,0.00015893948,0.00061546906,0.00030840162,0.00007305412,0.000010084106],"category_scores_gemma":[0.000019483372,0.000085721964,0.00004636924,0.0005915738,0.000037093196,0.0035486938,0.00005590318,0.00007644696,0.000057434958],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010660847,0.000016790293,0.00008799208,0.00004187776,0.000010828054,1.5321423e-7,0.00014035031,0.0006570071,0.00080106634,0.7369603,0.003120055,0.2581529],"study_design_scores_gemma":[0.00021565035,0.00010693931,0.0019705102,0.000034118504,0.000009247487,0.0000056754907,0.00007596514,0.929543,0.008580094,0.051974162,0.007314123,0.00017050988],"about_ca_topic_score_codex":0.0000045406723,"about_ca_topic_score_gemma":0.000012241706,"teacher_disagreement_score":0.928886,"about_ca_system_score_codex":0.00010686781,"about_ca_system_score_gemma":0.000114252245,"threshold_uncertainty_score":0.59349823},"labels":[],"label_agreement":null},{"id":"W4404799249","doi":"10.1007/s11517-024-03247-0","title":"CorLabelNet: a comprehensive framework for multi-label chest X-ray image classification with correlation guided discriminant feature learning and oversampling","year":2024,"lang":"en","type":"article","venue":"Medical & Biological Engineering & Computing","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Oversampling; Discriminative model; Artificial intelligence; Feature (linguistics); Computer science; Pattern recognition (psychology); Machine learning; Correlation; Multi-label classification; Discriminant; Class (philosophy); Mathematics","score_opus":0.060818128199565454,"score_gpt":0.3265953085034993,"score_spread":0.2657771803039339,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404799249","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":[0.02233642,0.0010889284,0.9722262,0.0022518756,0.00036620526,0.00033027245,0.0000020666357,0.0013768681,0.000021160819],"genre_scores_gemma":[0.5254693,0.00006265975,0.47424883,0.00006235253,0.000073655,0.000024735848,0.000019880665,0.000013620846,0.000024957486],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99823886,0.000049400358,0.0003245096,0.0006953475,0.00028791666,0.0004039845],"domain_scores_gemma":[0.9980241,0.0014141331,0.0001059635,0.00021373024,0.00009485782,0.00014718143],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045441056,0.00026842774,0.00029095128,0.00013308963,0.0002322586,0.0003221926,0.00042213796,0.00035955923,0.000009038558],"category_scores_gemma":[0.0013593744,0.00018724878,0.000054757278,0.00046030388,0.00015719651,0.00020384988,0.00027204788,0.0008065185,0.000011393851],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036507983,0.00018514805,0.005411878,0.00057340105,0.0001350969,0.00006159982,0.0011545892,0.00405749,0.019392692,0.41993496,0.0004865817,0.54857004],"study_design_scores_gemma":[0.0003575354,0.00017172593,0.013174272,0.00049064716,0.000012902055,0.000028494695,0.00016894766,0.9806912,0.00009995646,0.00045598307,0.004075228,0.00027312915],"about_ca_topic_score_codex":0.0000036881256,"about_ca_topic_score_gemma":2.818956e-7,"teacher_disagreement_score":0.97663367,"about_ca_system_score_codex":0.00006242776,"about_ca_system_score_gemma":0.0000446196,"threshold_uncertainty_score":0.76357836},"labels":[],"label_agreement":null},{"id":"W4404984454","doi":"10.2139/ssrn.5031329","title":"Research on Multi-Dimensional Feature Multi-Label Decision Models for Traditional Medicine Based on Deep Learning","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Artificial intelligence; Feature (linguistics); Computer science; Machine learning; Deep learning","score_opus":0.15229368374303165,"score_gpt":0.38134160667929157,"score_spread":0.22904792293625992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404984454","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":[0.0016701721,0.004469795,0.9698625,0.021519281,0.0011385704,0.0006486754,0.000013608047,0.00043356657,0.00024383701],"genre_scores_gemma":[0.8291288,0.0016917974,0.16225517,0.00041151533,0.00078837626,0.00032442142,0.00013586953,0.00010603301,0.0051580244],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9940025,0.0002940467,0.0005401883,0.0011777862,0.0018423308,0.0021431108],"domain_scores_gemma":[0.996728,0.0014679097,0.0003033977,0.00076015136,0.00058047386,0.00016003838],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.005714732,0.00046119414,0.00043999022,0.001630485,0.0008068106,0.00038714884,0.0021624437,0.0006426733,0.00001762668],"category_scores_gemma":[0.00058234914,0.00035387962,0.0002625233,0.00061766536,0.00018901905,0.0002108653,0.00062081584,0.014678103,0.00006298837],"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":[0.00020168169,0.0004191272,0.0000039928423,0.000040164072,0.00011330312,0.0000133833955,0.0001030823,0.0875981,0.00019122011,0.72577196,0.0031090428,0.18243496],"study_design_scores_gemma":[0.0011945829,0.00084417,0.000022056645,0.00038469434,0.000013466358,0.000029081832,0.00013136938,0.529593,0.00007055744,0.46721676,0.0003130274,0.0001872551],"about_ca_topic_score_codex":0.000009227847,"about_ca_topic_score_gemma":0.000055158074,"teacher_disagreement_score":0.8274586,"about_ca_system_score_codex":0.0023363968,"about_ca_system_score_gemma":0.0030110665,"threshold_uncertainty_score":0.99989134},"labels":[],"label_agreement":null},{"id":"W4405496143","doi":"10.1007/978-3-031-61503-0_23","title":"Automated Classification of Construction Claim Documents Using Text Mining","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in civil engineering","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Information retrieval; Natural language processing; Data science; Artificial intelligence","score_opus":0.01905286285939375,"score_gpt":0.2504813625161217,"score_spread":0.23142849965672793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405496143","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":[0.0009492515,0.0017955712,0.9756999,0.00032039415,0.0014244871,0.0003322774,0.000009789246,0.0028325445,0.016635805],"genre_scores_gemma":[0.91476953,0.00011693651,0.083770685,0.000016033464,0.00009063126,0.000017890397,0.000022035214,0.000075938166,0.0011202999],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99833834,0.0000069235016,0.0005606419,0.00053970935,0.00030799885,0.00024640118],"domain_scores_gemma":[0.99885094,0.00016982581,0.00026755015,0.00060974114,0.00006657782,0.00003535191],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00014038918,0.00035039618,0.0003712979,0.0009136514,0.000035478235,0.00012928456,0.0005692805,0.0005240861,0.000035123245],"category_scores_gemma":[0.00009617935,0.00036320896,0.00010341835,0.00034132748,0.000069880625,0.00027721553,0.00020203445,0.00049258117,0.00001690715],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006788265,0.00002356255,0.00022070971,0.00079507305,0.00018927357,0.00003187619,0.00063960516,0.0931942,0.02631402,0.78134805,0.0001250481,0.097111784],"study_design_scores_gemma":[0.00017696065,0.000033911572,0.00015765782,0.0012069661,0.0000393247,0.000036195976,0.0000072590005,0.9512616,0.004203384,0.0375984,0.0047642686,0.0005140835],"about_ca_topic_score_codex":0.000007538073,"about_ca_topic_score_gemma":0.000021147425,"teacher_disagreement_score":0.91382027,"about_ca_system_score_codex":0.00029073487,"about_ca_system_score_gemma":0.00007067363,"threshold_uncertainty_score":0.999882},"labels":[],"label_agreement":null},{"id":"W4405786055","doi":"10.1109/iros58592.2024.10802538","title":"Contextual Emotion Recognition using Large Vision Language Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Artificial intelligence; Natural language processing; Emotion recognition; Human–computer interaction; Speech recognition; Computer vision","score_opus":0.05055027205860438,"score_gpt":0.31501068606604454,"score_spread":0.26446041400744014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405786055","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":[0.0516114,0.00032536936,0.94096965,0.0008528754,0.0002560023,0.00008612812,0.000003566612,0.0017688748,0.0041261245],"genre_scores_gemma":[0.968309,0.000019125508,0.030942867,0.00011358076,0.000026852096,0.0000045466463,0.000010254198,0.000005235581,0.00056856085],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993242,0.000020636937,0.000125931,0.0002520256,0.00013901283,0.00013817693],"domain_scores_gemma":[0.9996592,0.000031044565,0.00002187461,0.00023410418,0.000031378273,0.000022402053],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017094843,0.00007030765,0.0000590362,0.00015476882,0.000069424306,0.0003370073,0.00023147586,0.00006191192,0.00007900133],"category_scores_gemma":[0.000013849324,0.000057884827,0.000037591657,0.00030480852,0.0000159029,0.00146641,0.0001178846,0.00007873953,0.00023094118],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014062036,0.00003747232,0.000005144399,0.000016492171,0.000007222848,0.000009583199,0.0009529263,0.000031914224,0.009121182,0.3874817,0.0019537227,0.60038126],"study_design_scores_gemma":[0.0001008612,0.00003137244,0.000027493023,0.000041084135,0.0000033117337,0.000008399551,0.0005801488,0.9446103,0.007978682,0.045262367,0.0012506604,0.00010534152],"about_ca_topic_score_codex":0.000016689042,"about_ca_topic_score_gemma":0.000004295762,"teacher_disagreement_score":0.94457835,"about_ca_system_score_codex":0.00004153967,"about_ca_system_score_gemma":0.000020563966,"threshold_uncertainty_score":0.32497692},"labels":[],"label_agreement":null},{"id":"W4406553888","doi":"10.1016/j.asoc.2025.112757","title":"Three-way multi-label classification: A review, a framework, and new challenges","year":2025,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Computer science; Multi-label classification; Artificial intelligence; Machine learning","score_opus":0.09022495306802511,"score_gpt":0.32144610589805883,"score_spread":0.23122115283003372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406553888","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021101635,0.029862551,0.9423569,0.023151081,0.0001594456,0.00038285129,2.2637674e-7,0.0010673673,0.0028085834],"genre_scores_gemma":[0.23562862,0.0049744966,0.75649446,0.0025782657,0.000053618016,0.000047086134,0.000002052784,0.000012809255,0.00020859846],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984988,0.00001888958,0.0003624999,0.00065189763,0.00018215162,0.00028578643],"domain_scores_gemma":[0.9984781,0.00036210904,0.00018096344,0.00085003854,0.00005681148,0.00007196646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035705057,0.00020015205,0.00027612303,0.00014115259,0.00023124606,0.00017005087,0.0009564593,0.00015050036,0.000004072497],"category_scores_gemma":[0.0001738913,0.00019086563,0.000035878496,0.0006004851,0.00008783784,0.00014528721,0.0006373546,0.00030630748,0.000043524495],"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":[7.250535e-7,0.000023568371,0.00008498315,0.00008931044,0.000009860321,3.3936092e-7,0.00010970366,7.260129e-7,0.000100945785,0.4741022,0.0014771083,0.5240005],"study_design_scores_gemma":[0.0020856354,0.00007759408,0.028162725,0.0030770751,0.00007352299,0.000013521436,0.00063287816,0.39331514,0.0006927316,0.508987,0.06165777,0.0012243625],"about_ca_topic_score_codex":0.00000681905,"about_ca_topic_score_gemma":0.000007967715,"teacher_disagreement_score":0.5227761,"about_ca_system_score_codex":0.00003764049,"about_ca_system_score_gemma":0.00007935727,"threshold_uncertainty_score":0.77832747},"labels":[],"label_agreement":null},{"id":"W4407264831","doi":"10.29173/cais1978","title":"Exploring a Machine-Generated Concept Hierarchy Through the Lens of \"Naive\" Classification","year":2025,"lang":"en","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Hierarchy; Computer science; Lens (geology); Artificial intelligence; Machine learning; Physics; Political science; Optics","score_opus":0.08693258341529242,"score_gpt":0.27825960745357914,"score_spread":0.19132702403828672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407264831","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":[0.9475926,0.00054803264,0.009464203,0.02770334,0.00036637273,0.00067661656,0.00007484752,0.00026612784,0.013307833],"genre_scores_gemma":[0.99683535,0.00031731065,0.0021058442,0.00019293562,0.000020670146,0.00008334258,0.0000028606023,0.000008930283,0.000432769],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982915,0.00003810417,0.0006079591,0.0003672739,0.00040212285,0.0002930695],"domain_scores_gemma":[0.98269516,0.00020037386,0.00083680585,0.00046774067,0.015769485,0.000030453257],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00040347443,0.00022277416,0.00037045477,0.00018687961,0.00019537682,0.001092882,0.0037206719,0.00011439113,0.0000060821544],"category_scores_gemma":[0.005301646,0.00014703281,0.00014736892,0.0012080068,0.0007497462,0.009830556,0.0009146654,0.00028729677,0.0000014024145],"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":[0.00003774303,0.0001080331,0.00932316,0.00012346354,0.00008758245,1.5151431e-7,0.022974838,0.000010160565,0.07483464,0.86988425,0.0018717541,0.020744227],"study_design_scores_gemma":[0.0008292686,0.00027166202,0.081186675,0.00042347683,0.000090116744,0.000006396438,0.008216805,0.0053195935,0.7869781,0.053598784,0.062673256,0.00040581942],"about_ca_topic_score_codex":0.00013303252,"about_ca_topic_score_gemma":0.0000042238066,"teacher_disagreement_score":0.8162855,"about_ca_system_score_codex":0.00005249758,"about_ca_system_score_gemma":0.0002443661,"threshold_uncertainty_score":0.9999441},"labels":[],"label_agreement":null},{"id":"W4407870825","doi":"10.1016/j.ress.2025.110971","title":"Creating an incident investigation framework for a complex socio-technical system: Application of multi-label text classification and Bayesian network structure learning","year":2025,"lang":"en","type":"article","venue":"Reliability Engineering & System Safety","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; AltaLink; Alberta Electric System Operator","keywords":"Bayesian network; Computer science; Artificial intelligence; Bayesian probability; Machine learning; Data mining","score_opus":0.016915216967306333,"score_gpt":0.26893714021609716,"score_spread":0.2520219232487908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407870825","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":[0.026595907,0.000109495544,0.97024614,0.0003681822,0.00014941994,0.0011215127,0.000008737969,0.0013778853,0.000022711025],"genre_scores_gemma":[0.63486326,0.0000038533944,0.36490363,0.000006028196,0.000030655345,0.0001495541,0.000027850907,0.000010649735,0.0000045400798],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997932,0.00013137134,0.00082638883,0.0006252616,0.00022262782,0.00026235782],"domain_scores_gemma":[0.9978691,0.0005684811,0.0004242716,0.00083678815,0.0002251465,0.00007624953],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010689063,0.0002225949,0.00039465382,0.00014166535,0.0003146042,0.00011237838,0.00054741453,0.00034271958,3.9107005e-7],"category_scores_gemma":[0.0005426078,0.00022280526,0.00006015791,0.000654964,0.00008438537,0.0003266073,0.00013551213,0.0003032511,6.5966236e-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":[0.000015314752,0.0000327441,0.018928701,0.0019182432,0.000022801576,1.0845159e-7,0.00035054245,0.033603985,0.021530425,0.9100166,0.000011261651,0.013569262],"study_design_scores_gemma":[0.00028042024,0.000047654587,0.09810984,0.00040385997,0.000023256749,0.0000029074554,0.00046320335,0.898077,0.00040546275,0.0019106907,0.000108154745,0.00016751728],"about_ca_topic_score_codex":0.000037961567,"about_ca_topic_score_gemma":0.0000057059206,"teacher_disagreement_score":0.9081059,"about_ca_system_score_codex":0.00055061316,"about_ca_system_score_gemma":0.00006990997,"threshold_uncertainty_score":0.90857345},"labels":[],"label_agreement":null},{"id":"W4408010102","doi":"10.1016/j.knosys.2025.113210","title":"Fine-grained local label correlation for multi-label classification","year":2025,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Multi-label classification; Correlation; Off-label use; Computer science; Pattern recognition (psychology); Statistics; Artificial intelligence; Mathematics; Medicine; Internal medicine; Geometry","score_opus":0.07526925042946161,"score_gpt":0.3345912497241709,"score_spread":0.25932199929470934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408010102","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":[0.00053260394,0.0011048974,0.99036634,0.0017376796,0.0019555008,0.0011228273,0.000012053535,0.0012204624,0.0019476584],"genre_scores_gemma":[0.9470995,0.0000035220014,0.042372618,0.00006616995,0.00005895579,0.0009503115,0.000066845234,0.000016844828,0.00936521],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99821717,0.00011887441,0.00056288467,0.0005976175,0.00018091434,0.0003225162],"domain_scores_gemma":[0.9979205,0.00038716628,0.00024835108,0.000903839,0.0004783055,0.00006185207],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005600012,0.00022933877,0.00027724667,0.0004580099,0.00029753865,0.0002686136,0.0009347181,0.0002550314,0.000002775966],"category_scores_gemma":[0.000282048,0.0002147265,0.00008095125,0.0010437922,0.00011719721,0.00032195027,0.000090538844,0.00015027956,0.00016348451],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030997475,0.0006037296,0.0012938116,0.00030873815,0.0000386213,6.1089827e-7,0.00016162558,0.0002766756,0.0042144586,0.7596793,0.02167702,0.21171439],"study_design_scores_gemma":[0.0024490864,0.00008384498,0.0008974397,0.00012921228,0.000017120065,5.8088506e-7,0.00013102409,0.96779376,0.0022993747,0.000977582,0.02500166,0.00021929617],"about_ca_topic_score_codex":0.000015972757,"about_ca_topic_score_gemma":0.000048299782,"teacher_disagreement_score":0.9675171,"about_ca_system_score_codex":0.00027618185,"about_ca_system_score_gemma":0.000323358,"threshold_uncertainty_score":0.87562925},"labels":[],"label_agreement":null},{"id":"W4408100472","doi":"10.1109/rws62086.2025.10904839","title":"UNet-Based Deep Learning Pathloss Estimator with Boundary Condition Input","year":2025,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"École de Technologie Supérieure","funders":"","keywords":"Estimator; Computer science; Artificial intelligence; Statistics; Mathematics","score_opus":0.006467127590436183,"score_gpt":0.247263460090543,"score_spread":0.24079633250010682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408100472","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":[0.00912502,0.00007707806,0.97558993,0.004124049,0.00008354447,0.00010814833,3.8327326e-7,0.0015113482,0.009380482],"genre_scores_gemma":[0.91452706,0.000003291247,0.08325828,0.00046667657,0.0000043062914,0.000037506856,0.0000104826695,0.0000037005345,0.0016886881],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99928087,0.000025075982,0.0001292764,0.0002641631,0.00014475822,0.00015583886],"domain_scores_gemma":[0.9994222,0.0000764484,0.00006118498,0.00035494944,0.000059770588,0.000025442843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009565817,0.00009531527,0.0000916123,0.00016881671,0.00024072528,0.0002906762,0.00044320547,0.00005687316,0.000039822575],"category_scores_gemma":[0.00004536176,0.00007436645,0.000022417753,0.0005108723,0.000107660046,0.00034968095,0.000090019894,0.0001337316,0.000059673966],"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":[0.000011532963,0.00007184428,0.010792222,0.00003157915,0.000019091112,0.000010346049,0.00006560931,0.0012366442,0.0007548903,0.7968642,0.0020565311,0.18808551],"study_design_scores_gemma":[0.0023992825,0.00053882,0.03168446,0.00017612374,0.000026955815,0.000008705395,0.0005617974,0.63911647,0.06304123,0.061244812,0.20042758,0.000773767],"about_ca_topic_score_codex":0.000008021616,"about_ca_topic_score_gemma":0.000008301007,"teacher_disagreement_score":0.90540206,"about_ca_system_score_codex":0.000044252723,"about_ca_system_score_gemma":0.000115065646,"threshold_uncertainty_score":0.30325758},"labels":[],"label_agreement":null},{"id":"W4408897052","doi":"10.1109/icmlc63072.2024.10935045","title":"Text Classification Method Based on Gating Mechanism and Graph Convolutional Networks","year":2024,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"University of Toronto","funders":"","keywords":"Computer science; Gating; Mechanism (biology); Graph; Convolutional neural network; Artificial intelligence; Theoretical computer science; Physics; Neuroscience","score_opus":0.025615101472069732,"score_gpt":0.28803812802383805,"score_spread":0.2624230265517683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408897052","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":[0.00022312888,0.00015587141,0.98613554,0.007434222,0.00024759313,0.00011531543,9.190186e-7,0.0013158805,0.0043715434],"genre_scores_gemma":[0.7795999,0.000020237989,0.21948923,0.0004195553,0.00002511931,0.000038087805,0.000004673879,0.000005725133,0.00039746286],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99900955,0.00005225007,0.00016733083,0.00042066933,0.00019266848,0.00015751591],"domain_scores_gemma":[0.9992119,0.00034373355,0.000040815634,0.0003270137,0.000035518835,0.000041013023],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040361323,0.0001071888,0.00008154961,0.00021568642,0.0001320791,0.00034690768,0.0003072614,0.00009097027,0.000042544933],"category_scores_gemma":[0.000038628637,0.00008757992,0.000039128354,0.00049179426,0.00004468566,0.00029864057,0.000076447555,0.00015264172,0.000034777215],"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":[9.78881e-7,0.000010469732,0.000029537827,0.0000058861547,0.000004434372,8.842241e-7,0.000016672177,0.00025763296,0.00070540915,0.90869474,0.0009781729,0.0892952],"study_design_scores_gemma":[0.00007210148,0.000037628324,0.00095766364,0.00002011367,0.0000031783775,0.000002740949,0.000039591803,0.8654721,0.0011701224,0.13053368,0.0015930352,0.000098084354],"about_ca_topic_score_codex":0.000004321919,"about_ca_topic_score_gemma":0.0000010972792,"teacher_disagreement_score":0.8652144,"about_ca_system_score_codex":0.00003490399,"about_ca_system_score_gemma":0.000037756407,"threshold_uncertainty_score":0.35714054},"labels":[],"label_agreement":null},{"id":"W4409576551","doi":"10.61091/jcmcc127a-134","title":"Research on Multi-Label Legal Text Categorization Methods Based on Large Predicate Models","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Predicate (mathematical logic); Categorization; Natural language processing; Computer science; Text categorization; Artificial intelligence; Information retrieval; Programming language","score_opus":0.07133117302106569,"score_gpt":0.391292831074241,"score_spread":0.31996165805317534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409576551","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":[0.009835144,0.0001256714,0.97619,0.0015674161,0.008694282,0.000369427,0.0000013208727,0.00016518366,0.0030515706],"genre_scores_gemma":[0.87979263,0.000023830618,0.11979296,0.0000938101,0.00022168296,0.0000075980593,0.0000011400083,0.00001879567,0.000047527275],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964669,0.0005093813,0.0010634975,0.000410171,0.0010665206,0.0004835599],"domain_scores_gemma":[0.99548465,0.0020019363,0.00074682327,0.0006602094,0.0009659956,0.00014039756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0059799696,0.00028709703,0.00059324055,0.0010472045,0.00061515224,0.0006977131,0.0014552667,0.00026805044,0.0000022765942],"category_scores_gemma":[0.00101931,0.00024442226,0.00012457011,0.0013723631,0.00011803305,0.00049680076,0.0004982346,0.0010302147,0.000004295582],"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":[0.000058988582,0.0013908537,0.000016046488,0.000077540586,0.000039806917,0.0000073305696,0.00020997097,0.00046335993,0.00023200695,0.98399687,0.00061293016,0.012894271],"study_design_scores_gemma":[0.003185518,0.0006292307,0.000024024836,0.00023761965,0.00001530465,0.0000029223684,0.000121478704,0.51712304,0.001768753,0.47599992,0.0007555152,0.00013664922],"about_ca_topic_score_codex":0.0000055400483,"about_ca_topic_score_gemma":1.8044989e-7,"teacher_disagreement_score":0.8699575,"about_ca_system_score_codex":0.00020438555,"about_ca_system_score_gemma":0.00037570435,"threshold_uncertainty_score":0.996725},"labels":[],"label_agreement":null},{"id":"W4410109448","doi":"10.1016/j.nlp.2025.100152","title":"Bayesian Q-learning in multi-objective reward model for homophobic and transphobic text classification in low-resource languages: A hypothesis testing framework in multi-objective setting","year":2025,"lang":"en","type":"article","venue":"Natural Language Processing Journal","topic":"Text and Document Classification Technologies","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":"University of Calgary","funders":"Science Foundation Ireland","keywords":"Bayesian probability; Computer science; Resource (disambiguation); Machine learning; Artificial intelligence; Natural language processing; Psychology","score_opus":0.02416340836884429,"score_gpt":0.3046702726710389,"score_spread":0.2805068643021946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410109448","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":[0.17828058,0.008541961,0.8112101,0.001038583,0.00005660518,0.00050887803,0.000002291735,0.00027669128,0.00008432966],"genre_scores_gemma":[0.70045334,0.000023247492,0.29920223,0.00012656036,0.000014729403,0.00006362823,0.0000014505995,0.000015872638,0.00009893471],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978722,0.00017402714,0.0006044363,0.0006094393,0.00022312786,0.00051681494],"domain_scores_gemma":[0.99830776,0.00092772226,0.00035983013,0.00021072134,0.0001386433,0.000055310004],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009662623,0.00027490343,0.00034675866,0.0011271508,0.00031958378,0.00046952374,0.000615445,0.00028518715,9.842504e-7],"category_scores_gemma":[0.0033818546,0.00025392097,0.0000659918,0.0017586075,0.00008805827,0.0008337285,0.00009846876,0.0017106861,6.535298e-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":[0.00008540437,0.0002057403,0.023302726,0.00028220945,0.000015562746,0.000054970176,0.04143179,0.005699682,0.0123637235,0.00026208122,0.0000057266748,0.9162904],"study_design_scores_gemma":[0.0014132565,0.000029460494,0.031789992,0.0017161003,0.000008936712,0.00002625731,0.0155745875,0.94588107,0.001526324,0.0017511917,0.0000034089103,0.0002794345],"about_ca_topic_score_codex":0.000048362337,"about_ca_topic_score_gemma":0.0002902494,"teacher_disagreement_score":0.9401814,"about_ca_system_score_codex":0.00043569415,"about_ca_system_score_gemma":0.00027402575,"threshold_uncertainty_score":0.9999913},"labels":[],"label_agreement":null},{"id":"W4410546712","doi":"10.18280/isi.300408","title":"An Accurate Model for Text Document Classification Using Machine Learning Techniques","year":2025,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Document classification; Natural language processing; Information retrieval","score_opus":0.035065862375805834,"score_gpt":0.30417657013829197,"score_spread":0.26911070776248613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410546712","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":[0.011089425,0.000059039117,0.9850415,0.00035285088,0.000117145304,0.0006037768,0.0000062092463,0.0014254873,0.0013045431],"genre_scores_gemma":[0.7931931,0.00003421165,0.20614645,0.00015752838,0.000010554091,0.00022234856,0.000069425034,0.0000059949857,0.00016038831],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987155,0.000045382,0.0005788843,0.00022117877,0.00018030577,0.0002587217],"domain_scores_gemma":[0.99869454,0.000055759298,0.0003871276,0.0005108027,0.00031125653,0.000040537834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052622997,0.00017621033,0.00016698171,0.0005220123,0.0005160309,0.0008280893,0.0007225668,0.00014550984,0.0000030643307],"category_scores_gemma":[0.00018529828,0.00016980838,0.000059800455,0.00057904306,0.00008107002,0.007213258,0.00012752123,0.00013817308,0.000009058124],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024719164,0.000034945577,0.000569278,0.0001762378,0.000022898752,1.1442109e-7,0.002289186,0.0066020675,0.009157762,0.49871793,0.00016451514,0.48224035],"study_design_scores_gemma":[0.00018195667,0.000058281457,0.00031134303,0.00005804616,0.000009197482,0.000001923347,0.00036028435,0.9241878,0.020624707,0.05079708,0.00323671,0.0001726981],"about_ca_topic_score_codex":0.00002946723,"about_ca_topic_score_gemma":0.000005092054,"teacher_disagreement_score":0.91758573,"about_ca_system_score_codex":0.00037362712,"about_ca_system_score_gemma":0.00013936161,"threshold_uncertainty_score":0.79852843},"labels":[],"label_agreement":null},{"id":"W4410863961","doi":"10.1007/978-3-031-84756-1_3","title":"An Introduction to ML Through PCG","year":2025,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on games and computational intelligence","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Sudbury; University of Alberta","funders":"","keywords":"Computer science; History","score_opus":0.020586847759865076,"score_gpt":0.28160711620189516,"score_spread":0.2610202684420301,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410863961","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":[0.0000146401635,0.00052460824,0.94437134,0.019582879,0.00038152572,0.00029664912,0.00001769488,0.00046444513,0.034346245],"genre_scores_gemma":[0.40327746,0.0017142935,0.37998578,0.01182523,0.0016041867,0.0003857067,0.00013135643,0.00013429717,0.2009417],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99797356,0.000034069984,0.000374404,0.0010157813,0.00039017494,0.00021203683],"domain_scores_gemma":[0.9982994,0.00053232163,0.00017060738,0.000731181,0.00018864653,0.00007779915],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001372165,0.00036919548,0.00032428815,0.00038265536,0.00019476231,0.0003644544,0.0009946601,0.00024465,0.00014396985],"category_scores_gemma":[0.00015973164,0.00033337346,0.0000946602,0.00015363806,0.00013503378,0.00026304423,0.00018926071,0.00030080692,0.00010040801],"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":[0.000009908266,0.000017904142,6.5546294e-7,0.0000127618405,0.000025781195,0.0000014019723,0.00009474293,0.006239511,0.000009113528,0.63244563,0.005803806,0.35533878],"study_design_scores_gemma":[0.000020063902,0.00021632815,0.00004888725,0.0001137372,0.000019984722,0.000008847393,0.000027843636,0.008631523,0.003756237,0.7643231,0.22240375,0.0004296867],"about_ca_topic_score_codex":0.000007202306,"about_ca_topic_score_gemma":0.0000053140557,"teacher_disagreement_score":0.56438553,"about_ca_system_score_codex":0.00008367861,"about_ca_system_score_gemma":0.000098638695,"threshold_uncertainty_score":0.99991184},"labels":[],"label_agreement":null},{"id":"W4411799602","doi":"10.1109/lsp.2025.3584670","title":"A Novel Evaluation Criterion for Density Clustering via Circular Information Granules","year":2025,"lang":"en","type":"article","venue":"IEEE Signal Processing Letters","topic":"Text and Document Classification Technologies","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 Alberta","funders":"","keywords":"Cluster analysis; Mathematics; Computer science; Pattern recognition (psychology); Probability density function; Data mining; Artificial intelligence; Statistics","score_opus":0.02650558789289352,"score_gpt":0.2806127953078521,"score_spread":0.25410720741495857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411799602","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":[0.018020581,0.000052355972,0.97443014,0.0063819806,0.0002712383,0.0003939105,0.0000011561375,0.00038596053,0.00006265076],"genre_scores_gemma":[0.9461767,0.0000010253041,0.051092636,0.002562795,0.000026128071,0.00012080792,0.000009442943,0.0000039095917,0.0000065319523],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989865,0.000021510788,0.00027651357,0.00023595351,0.0002855113,0.00019404375],"domain_scores_gemma":[0.99931955,0.000042596854,0.00015886739,0.00022534333,0.0002324989,0.000021122345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047808696,0.00012212686,0.00011294101,0.000283639,0.00029921273,0.0005014114,0.00044405332,0.0000693069,0.0000014084246],"category_scores_gemma":[0.000045090335,0.00012298964,0.00005339298,0.00037651922,0.000052207044,0.0019518386,0.00006133848,0.00008784825,0.00000573365],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011342001,0.000019532825,0.000045165478,0.00017166109,0.000009879662,1.9515109e-7,0.0002918941,0.0014048006,0.31641328,0.0008562005,0.00066378183,0.6801123],"study_design_scores_gemma":[0.00062271056,0.000018943538,0.0013466867,0.00010962753,0.000024381416,0.000004513353,0.00005000258,0.93421453,0.056209628,0.0060892534,0.0011195246,0.00019018103],"about_ca_topic_score_codex":0.000009232575,"about_ca_topic_score_gemma":0.0000015723277,"teacher_disagreement_score":0.93280977,"about_ca_system_score_codex":0.00012690185,"about_ca_system_score_gemma":0.00008104613,"threshold_uncertainty_score":0.5015372},"labels":[],"label_agreement":null},{"id":"W4412353994","doi":"10.2139/ssrn.5348737","title":"Land Cover Classification and Change Detection Using Large Language Models: A Novel Benchmark Study for Remote Sensing Applications","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Benchmark (surveying); Land cover; Cover (algebra); Change detection; Remote sensing; Computer science; Data mining; Natural language processing; Artificial intelligence; Land use; Geography; Cartography; Engineering","score_opus":0.05303684395705223,"score_gpt":0.31590635339267226,"score_spread":0.26286950943562004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412353994","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":[0.030326415,0.002088701,0.9648691,0.0005444962,0.00021089388,0.0016496913,0.000023810075,0.00022688093,0.00006002814],"genre_scores_gemma":[0.97299,0.0011113143,0.025294213,0.000058201327,0.00021134086,0.00006230889,0.000018942676,0.000017505454,0.00023621754],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976562,0.000069727146,0.0004032135,0.0006303262,0.00025114248,0.0009893803],"domain_scores_gemma":[0.99851424,0.00008029774,0.0004928615,0.0006614739,0.00020277505,0.0000483518],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014119829,0.00026112542,0.00027900666,0.0004435215,0.00051035226,0.00039185668,0.00063534616,0.00025653568,5.4482155e-7],"category_scores_gemma":[0.000046432157,0.00025858864,0.00010345961,0.00037312953,0.000030623825,0.00044707942,0.0005099188,0.0014849876,0.0000010080765],"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":[0.00005231748,0.00032582655,0.00036487426,0.00013910615,0.00038469388,0.0000011984556,0.0031341987,0.0005101375,0.002210592,0.10993973,0.000009272766,0.8829281],"study_design_scores_gemma":[0.0008330211,0.00011354321,0.00033869362,0.00006301967,0.00010329625,0.000056538767,0.0020779115,0.7811908,0.00009955775,0.21439874,0.0004322318,0.0002926245],"about_ca_topic_score_codex":0.00020182031,"about_ca_topic_score_gemma":0.0007751665,"teacher_disagreement_score":0.94266355,"about_ca_system_score_codex":0.0009197069,"about_ca_system_score_gemma":0.00080570043,"threshold_uncertainty_score":0.99998665},"labels":[],"label_agreement":null},{"id":"W4412512470","doi":"10.1007/978-981-96-6688-1_28","title":"A Simultaneous Hierarchical Count Data Clustering and Feature Selection Based on Multinomial Nested Dirichlet Mixture Using the Minorization-Maximization Framework","year":2025,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Multinomial distribution; Feature selection; Latent Dirichlet allocation; Selection (genetic algorithm); Hierarchical Dirichlet process; Dirichlet distribution; Cluster analysis; Maximization; Hierarchical clustering; Count data; Data mining; Artificial intelligence; Statistics; Topic model; Mathematics; Mathematical optimization","score_opus":0.034810372676734196,"score_gpt":0.3026684632058938,"score_spread":0.2678580905291596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412512470","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000036518904,0.00015306186,0.99032813,0.004952701,0.0002508422,0.0005408319,0.000028352888,0.00017910691,0.0035304765],"genre_scores_gemma":[0.17536975,0.0012202451,0.81903327,0.003120481,0.00008878454,0.000038818023,0.00038425127,0.000016589145,0.0007278294],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983697,0.00006312006,0.00047977985,0.0004527055,0.0004361421,0.00019856151],"domain_scores_gemma":[0.995524,0.001103335,0.0003654629,0.0026188293,0.00033482863,0.00005353286],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006655192,0.00024853906,0.00021044184,0.0008408862,0.0009953588,0.0011686073,0.0035973217,0.00028266845,0.0000022422494],"category_scores_gemma":[0.00044932854,0.00020607376,0.000023375034,0.0008814079,0.0006822341,0.0030125794,0.0026944408,0.0007538609,0.0000024379842],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022076392,0.000046338428,0.00025728624,0.00008161707,0.000013884483,6.972933e-7,0.0013770903,0.047149744,0.000012215977,0.48574382,0.0006323277,0.4646629],"study_design_scores_gemma":[0.00018512899,0.000031661137,0.0002831016,0.0002461017,0.000009719346,0.0000089515315,0.000018368508,0.9649313,0.000004723033,0.0021108834,0.031966936,0.00020312681],"about_ca_topic_score_codex":0.000009885718,"about_ca_topic_score_gemma":0.000015603497,"teacher_disagreement_score":0.91778153,"about_ca_system_score_codex":0.00017225041,"about_ca_system_score_gemma":0.00034777107,"threshold_uncertainty_score":0.9998683},"labels":[],"label_agreement":null},{"id":"W4412620322","doi":"10.1007/978-981-96-7423-7_9","title":"NLP Combined with Bi-LSTM Classifier Based Intent Detection Algorithm for Smart House Control Using WhatsApp Message","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Military College of Canada","funders":"","keywords":"Computer science; Classifier (UML); Artificial intelligence; Machine learning; Natural language processing","score_opus":0.01943103631634458,"score_gpt":0.24352514535941552,"score_spread":0.22409410904307095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412620322","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000029436374,0.00015831765,0.9943145,0.0013973579,0.0015956252,0.0013232538,0.000013538725,0.000911555,0.00025643228],"genre_scores_gemma":[0.17717592,0.000016702563,0.82019055,0.0018051548,0.000119311735,0.00013031505,0.0000070682268,0.000060842354,0.00049413735],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962382,0.000043385633,0.00058913033,0.0016487947,0.0007975933,0.00068292656],"domain_scores_gemma":[0.99666196,0.0006816615,0.00046965043,0.00155632,0.0005100946,0.00012031202],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007018566,0.00062999956,0.00066412037,0.0014026761,0.00045007424,0.0009296772,0.0026462805,0.00046051634,0.0000075083694],"category_scores_gemma":[0.00010486285,0.00052038196,0.00018157081,0.000939636,0.0007962214,0.000755357,0.00050694065,0.00068340864,0.0000064889964],"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":[0.00004324837,0.000054258828,0.000032150823,0.000046668934,0.000031899956,0.000014994884,0.000062725056,0.004930906,0.0004277981,0.006290936,0.00003112503,0.9880333],"study_design_scores_gemma":[0.0014296776,0.000590303,0.000047539143,0.000396553,0.000035182617,0.00001196803,9.150275e-7,0.95663714,0.009663994,0.028584475,0.001978889,0.0006233377],"about_ca_topic_score_codex":0.00002528657,"about_ca_topic_score_gemma":0.00009436482,"teacher_disagreement_score":0.98740995,"about_ca_system_score_codex":0.000558387,"about_ca_system_score_gemma":0.0007583361,"threshold_uncertainty_score":0.9997248},"labels":[],"label_agreement":null},{"id":"W4413679785","doi":"10.1109/compsac65507.2025.00049","title":"A Late Fusion Approach Using CSNNs for Multi-Modal Toxicity Detection in Online Media","year":2025,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"University of the Fraser Valley","funders":"","keywords":"Modal; Computer science; Fusion; Materials science; Linguistics; Composite material; Philosophy","score_opus":0.07134076682124128,"score_gpt":0.3228740942330066,"score_spread":0.2515333274117653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413679785","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":[0.21820354,0.000018853978,0.78060544,0.00041742675,0.00013690871,0.00021207455,0.0000014945917,0.00026986588,0.00013439033],"genre_scores_gemma":[0.68582714,0.000005278672,0.31383333,0.00007283235,0.0000076239776,0.000021531012,0.0000028444592,0.0000020702712,0.0002273758],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992834,0.00002170689,0.00018202266,0.00027866126,0.00008086385,0.00015338216],"domain_scores_gemma":[0.9995662,0.00006457602,0.00004631069,0.00026731574,0.000039000177,0.000016615746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019856734,0.00007930123,0.000100676036,0.00026664863,0.000079560974,0.000059584436,0.0003720663,0.00009494124,0.000001875985],"category_scores_gemma":[0.00012387765,0.00006830595,0.00003532623,0.00056913454,0.00002672438,0.00026488255,0.0001877477,0.000086456785,0.0000012851082],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003188896,0.0008475933,0.0026421312,0.00006109658,0.000014593408,9.525767e-7,0.00067191635,0.00092296867,0.2341911,0.086746514,0.00009028312,0.67377895],"study_design_scores_gemma":[0.00044467332,0.000014002436,0.00455028,0.0000086255895,0.000002079771,5.161273e-7,0.00014898958,0.93331516,0.057534836,0.0037192428,0.00018383503,0.00007778426],"about_ca_topic_score_codex":0.0000590892,"about_ca_topic_score_gemma":0.00028187508,"teacher_disagreement_score":0.9323922,"about_ca_system_score_codex":0.000079359765,"about_ca_system_score_gemma":0.000035062134,"threshold_uncertainty_score":0.27854356},"labels":[],"label_agreement":null},{"id":"W4413912352","doi":"10.5267/j.ijdns.2024.11.003","title":"Multi-label classification analysis with modified C-Tran on SCIN dataset ,","year":2025,"lang":"en","type":"article","venue":"International Journal of Data and Network Science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Business","score_opus":0.07758290269645432,"score_gpt":0.3729983239875304,"score_spread":0.2954154212910761,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413912352","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":[0.017224438,0.00014503588,0.97480345,0.0069653606,0.00043759937,0.00006366932,0.00010647443,0.000032736527,0.00022122974],"genre_scores_gemma":[0.89127034,0.00019529037,0.107935704,0.00042357575,0.000044550674,0.0000015157658,0.00008069466,0.0000015422567,0.000046762725],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99850476,0.000026960148,0.00030863198,0.0003755253,0.00063232216,0.00015177537],"domain_scores_gemma":[0.998448,0.00011717236,0.00030918693,0.0007602132,0.00030738662,0.00005801926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010361011,0.000087460445,0.00014081804,0.0007158116,0.00016999715,0.0005386308,0.0047401683,0.000028946879,0.00000303527],"category_scores_gemma":[0.000107308566,0.00006214419,0.000018837694,0.0018423576,0.00033040345,0.0021317538,0.00057156716,0.0001451713,0.000002202235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022970219,0.00058019673,0.028218184,0.000007222052,0.0008570876,0.000037460966,0.00016717485,0.004156596,0.0041398876,0.32704327,0.028690647,0.6058726],"study_design_scores_gemma":[0.0009820642,0.00011314695,0.074845046,0.00007946937,0.000090714035,0.000017810002,0.00007695623,0.9122349,0.0005091913,0.0023101992,0.00859208,0.0001484195],"about_ca_topic_score_codex":0.0000061564187,"about_ca_topic_score_gemma":0.000017820159,"teacher_disagreement_score":0.9080783,"about_ca_system_score_codex":0.00004947964,"about_ca_system_score_gemma":0.00018938174,"threshold_uncertainty_score":0.8808491},"labels":[],"label_agreement":null},{"id":"W4414059432","doi":"10.1007/s10032-025-00555-5","title":"Optimizing identity documents classification in online systems: A comparative analysis","year":2025,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"International Medias Data Services (Canada)","funders":"","keywords":"Convolutional neural network; Context (archaeology); Identity (music); Process (computing); A priori and a posteriori; Identity management; Strengths and weaknesses","score_opus":0.04133032381567437,"score_gpt":0.3529996195214886,"score_spread":0.31166929570581425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414059432","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":[0.3681466,0.0006720263,0.61945015,0.0074742823,0.0010663997,0.00031414497,0.000034027642,0.00016548963,0.0026768823],"genre_scores_gemma":[0.992269,0.0013036545,0.005081592,0.00038180273,0.00005509639,0.000036640675,0.00015575087,0.0000035493297,0.00071293017],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99721634,0.00022340279,0.0009704658,0.0005427836,0.00081540574,0.0002315897],"domain_scores_gemma":[0.9982194,0.00016495743,0.00064258213,0.00033115517,0.0005520002,0.00008996086],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00078910147,0.00023007551,0.00050715153,0.0051170555,0.00019849846,0.0019029364,0.0010123805,0.00011370922,0.00010852183],"category_scores_gemma":[0.000073135285,0.00020023396,0.00034864858,0.0038863758,0.0000696127,0.0019546023,0.00021137133,0.00036284697,0.000026773065],"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":[0.00047862952,0.0035826087,0.24218756,0.000058118374,0.05607975,0.00019592971,0.0033101835,0.027180657,0.0011387336,0.42086208,0.0028909384,0.24203481],"study_design_scores_gemma":[0.005146771,0.00030150547,0.5337169,0.00056096254,0.0053152437,0.00003257298,0.0064287023,0.35514057,0.001571392,0.0813398,0.009083667,0.0013618757],"about_ca_topic_score_codex":0.0001260417,"about_ca_topic_score_gemma":0.00024240765,"teacher_disagreement_score":0.6241224,"about_ca_system_score_codex":0.00041804987,"about_ca_system_score_gemma":0.0000615162,"threshold_uncertainty_score":0.99913317},"labels":[],"label_agreement":null},{"id":"W4414117165","doi":"10.1109/fuzz62266.2025.11152226","title":"Dynamic Recursive Fuzzy ART Multi-label Classifier","year":2025,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"University of Alberta","funders":"","keywords":"Classifier (UML); Fuzzy logic; Adaptive resonance theory; Pattern recognition (psychology); Incremental learning; Noisy data; Fuzzy classification; Fuzzy control system","score_opus":0.02345672928870909,"score_gpt":0.3015598249915767,"score_spread":0.2781030957028676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414117165","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00071780576,0.00012767177,0.8902923,0.017444631,0.00045857165,0.00015804263,8.437951e-7,0.0011768696,0.0896233],"genre_scores_gemma":[0.18642321,0.00010213555,0.53895664,0.001861755,0.0000058978476,0.0000793954,0.000005842119,0.0000074797827,0.27255762],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990827,0.000021440823,0.00018588689,0.0003704877,0.00012385496,0.00021564566],"domain_scores_gemma":[0.9990595,0.00006174067,0.00005476459,0.0007205358,0.00007177377,0.000031706306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000099984325,0.00011388968,0.00011360991,0.0002179991,0.00010730346,0.00015556089,0.0010056016,0.000101302445,0.000035897872],"category_scores_gemma":[0.000073470685,0.00009602848,0.000039716102,0.0006328503,0.00007994853,0.00038101064,0.00031461875,0.00013293682,0.0006606129],"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":[0.0000014308898,0.00007665621,0.00021067342,0.000004182464,0.0000121616295,0.0000015718399,0.000034502522,8.5654216e-7,0.0009204917,0.8106376,0.03939143,0.14870846],"study_design_scores_gemma":[0.0024288401,0.00014034979,0.016130457,0.0000768828,0.000021997443,0.00000616721,0.0006868952,0.2960366,0.013311007,0.36733338,0.30302837,0.00079904654],"about_ca_topic_score_codex":0.000003163641,"about_ca_topic_score_gemma":0.000019029989,"teacher_disagreement_score":0.44330418,"about_ca_system_score_codex":0.00007264416,"about_ca_system_score_gemma":0.00006413861,"threshold_uncertainty_score":0.84910625},"labels":[],"label_agreement":null},{"id":"W4414230855","doi":"10.1109/gem66882.2025.11155795","title":"LADDER: Level Analysis Dataset for Difficulty Evaluation and Ranking","year":2025,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"Université du Québec à Chicoutimi","funders":"","keywords":"Ranking (information retrieval); Bridge (graph theory); Limiting; Resource (disambiguation); Object (grammar); Focus (optics)","score_opus":0.07098476990132718,"score_gpt":0.3651269513298248,"score_spread":0.29414218142849763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414230855","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":[0.0031303412,0.00008813454,0.9916306,0.0042477176,0.000044391127,0.00020880462,0.00008021586,0.00013792093,0.0004318688],"genre_scores_gemma":[0.940552,0.000013757674,0.05793054,0.00028073386,0.00000423406,0.0000848569,0.00048055718,0.000001097054,0.00065224094],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99943286,0.000016648797,0.00011387531,0.00023786875,0.000116763054,0.000081957405],"domain_scores_gemma":[0.9994188,0.000096927244,0.00003735746,0.00036758566,0.00006845135,0.000010910205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032516004,0.00005147089,0.00008348141,0.000220012,0.00010606795,0.00015760663,0.00031374893,0.000032897897,0.000016179923],"category_scores_gemma":[0.000105343075,0.000040690178,0.0000287236,0.0006378747,0.000021819445,0.0002500984,0.00013667224,0.000023482671,0.0000023275034],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034437774,0.000034946388,0.0025551666,0.0000108442755,0.00020008844,8.1370516e-8,0.00007115741,0.00006868763,0.00071605836,0.44954106,0.052258484,0.49453998],"study_design_scores_gemma":[0.0009975262,0.000024477393,0.079634726,0.0000063847892,0.00038509455,3.0361156e-7,0.00017750099,0.8141659,0.005651773,0.049522884,0.04923816,0.0001952901],"about_ca_topic_score_codex":0.00001277054,"about_ca_topic_score_gemma":0.0000452057,"teacher_disagreement_score":0.9374216,"about_ca_system_score_codex":0.000017726474,"about_ca_system_score_gemma":0.000022992144,"threshold_uncertainty_score":0.16592973},"labels":[],"label_agreement":null},{"id":"W4414360013","doi":"10.18280/mmep.120835","title":"Enhanced Text Extraction: Combining Bacteria Foraging Optimization Algorithm-Optimized Scale-Invariant Feature Transform with Machine Learning for Robust Performance","year":2025,"lang":"en","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Pattern recognition (psychology); Feature (linguistics); Support vector machine; Feature selection; Foraging; Training set","score_opus":0.013538007089078518,"score_gpt":0.21107193211330813,"score_spread":0.19753392502422962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414360013","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000937806,0.00013138709,0.9966506,0.0007429372,0.00007311183,0.00042992065,9.956798e-7,0.0007515462,0.00028173442],"genre_scores_gemma":[0.21756397,0.00012265344,0.78175074,0.000010829449,0.000009953207,0.00016818133,0.000010151887,0.000017499637,0.00034601067],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989295,0.000009401183,0.0002781176,0.00035520896,0.00013227318,0.00029549203],"domain_scores_gemma":[0.9994366,0.00014357702,0.00007750448,0.00021981997,0.00007018482,0.000052324962],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028576006,0.00021949003,0.00027557794,0.00016796203,0.00025132668,0.0002957958,0.00023776462,0.000119399876,0.0000035250894],"category_scores_gemma":[0.000018269486,0.00018082415,0.000042521802,0.00031050088,0.000029005314,0.0005014943,0.000044965975,0.00027751832,9.188806e-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":[0.000012371596,0.000029106173,0.0000015671117,0.00039354942,0.000023851402,2.4151157e-7,0.0003107949,0.9729754,0.0002422195,0.012496857,0.0000030659223,0.013511027],"study_design_scores_gemma":[0.00073542044,0.000084690066,0.0000019331137,0.00051716226,0.000024253832,0.0000097096745,0.00004093577,0.99438107,0.0023220605,0.0015118727,0.0001497289,0.00022113335],"about_ca_topic_score_codex":0.0000013858825,"about_ca_topic_score_gemma":1.5054948e-7,"teacher_disagreement_score":0.21662617,"about_ca_system_score_codex":0.000037913724,"about_ca_system_score_gemma":0.00002015494,"threshold_uncertainty_score":0.7373795},"labels":[],"label_agreement":null},{"id":"W4415185722","doi":"10.1016/j.prevetmed.2025.106723","title":"Automating classification of veterinary biosecurity recommendations using machine learning","year":2025,"lang":"en","type":"article","venue":"Preventive Veterinary Medicine","topic":"Text and Document Classification Technologies","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":true,"ca_institutions":"Association des Médecins Vétérinaires du Québec; University of Guelph; University of Calgary; Université de Montréal; Cegep de Saint Hyacinthe","funders":"Ville de Québec; Novalait; Université de Montréal; Dairy Farmers of Canada; Natural Sciences and Engineering Research Council of Canada; Ministère de l'Agriculture, des Pêcheries et de l'Alimentation","keywords":"Biosecurity; Random forest; Support vector machine; Naive Bayes classifier; Consistency (knowledge bases); Linear discriminant analysis; Bayes' theorem; Quality assurance","score_opus":0.09194989337965144,"score_gpt":0.3794110015846574,"score_spread":0.287461108205006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415185722","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":[0.5439494,0.00096366554,0.44626087,0.005762533,0.0005552084,0.00034656646,0.0000048188494,0.00059379,0.0015631358],"genre_scores_gemma":[0.9683763,0.00014297548,0.031028846,0.00004651222,0.000019953046,0.00003080591,0.000024502095,0.0000067958963,0.00032331722],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984321,0.00030226583,0.00052744296,0.0003671758,0.00018229795,0.00018869735],"domain_scores_gemma":[0.9987096,0.0002548245,0.0003833002,0.0004941371,0.00012315421,0.000034973327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064261025,0.00016045218,0.00026472227,0.00046997244,0.00021778012,0.000024597683,0.00064715656,0.00007581134,0.00005916575],"category_scores_gemma":[0.0003539669,0.00014684747,0.00005979031,0.0009160635,0.00018445394,0.00045461758,0.00047343128,0.00021644702,0.0000043421924],"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":[0.00004045148,0.0002622875,0.007842332,0.00029054578,0.000102775455,0.000009979629,0.0011591201,0.000010955858,0.68059874,0.07147564,0.00033110817,0.2378761],"study_design_scores_gemma":[0.0036527151,0.0054214164,0.26816413,0.003795125,0.0001880435,0.00015339715,0.0025156748,0.59545547,0.036954843,0.032837324,0.049826194,0.0010356676],"about_ca_topic_score_codex":0.000040638846,"about_ca_topic_score_gemma":0.0000010224165,"teacher_disagreement_score":0.64364386,"about_ca_system_score_codex":0.00008827638,"about_ca_system_score_gemma":0.000050645045,"threshold_uncertainty_score":0.5988266},"labels":[],"label_agreement":null},{"id":"W4415524230","doi":"10.1109/ubmk67458.2025.11206854","title":"Demographic-Aware Product Recommendation through Heterogeneous Graph Neural Networks","year":2025,"lang":"","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"Nexen (Canada)","funders":"","keywords":"Recommender system; Graph; Scalability; Collaborative filtering; Matrix decomposition; Artificial neural network; Product (mathematics); Convolution (computer science)","score_opus":0.024751924016009466,"score_gpt":0.2795145131428526,"score_spread":0.25476258912684313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415524230","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":[0.0016459856,0.0029892337,0.9376172,0.048062958,0.0038635759,0.0008875631,0.000004679825,0.0017166903,0.0032121544],"genre_scores_gemma":[0.9872542,0.0018120689,0.0061171106,0.0024511747,0.00010646544,0.00011509708,0.00003798816,0.000019503608,0.0020863863],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99612546,0.000226374,0.0009493124,0.0015631979,0.00029747622,0.0008381554],"domain_scores_gemma":[0.9972763,0.00015098373,0.00037066673,0.0018198298,0.00029759403,0.00008460249],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003712162,0.0005375305,0.00044196332,0.0005901523,0.0007704525,0.0010340152,0.002015717,0.00032425887,0.00033148978],"category_scores_gemma":[0.000079757934,0.00050791807,0.00032275592,0.0042178007,0.00038603425,0.001577052,0.0009901695,0.0005828836,0.00003491798],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026312395,0.00026198308,0.0039441045,0.000052422798,0.00014989238,0.0000053289873,0.000142972,0.0031213888,0.000032664368,0.13117506,0.02161646,0.8394714],"study_design_scores_gemma":[0.00076579687,0.0002591743,0.0025079434,0.00008381456,0.000091152884,0.000023718678,0.00021546714,0.90922534,0.0062914575,0.039608,0.040027905,0.000900217],"about_ca_topic_score_codex":0.00006714139,"about_ca_topic_score_gemma":0.000051348994,"teacher_disagreement_score":0.9856082,"about_ca_system_score_codex":0.00008851715,"about_ca_system_score_gemma":0.00009510772,"threshold_uncertainty_score":0.99973726},"labels":[],"label_agreement":null},{"id":"W4416109760","doi":"10.1093/comjnl/bxaf124","title":"CV content recognition using YOLOv8 and Tesseract-OCR deep learning","year":2025,"lang":"en","type":"article","venue":"The Computer Journal","topic":"Text and Document Classification Technologies","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":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Preprocessor; Consistency (knowledge bases); Sorting; Variety (cybernetics); Deep learning; Hyperparameter; Analytics; Precision and recall; Component (thermodynamics)","score_opus":0.06729306244984125,"score_gpt":0.276650143117134,"score_spread":0.20935708066729275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416109760","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":[0.11915086,0.0006195778,0.87172925,0.007574519,0.00051908864,0.0000661232,1.03202225e-7,0.00015051296,0.00018997301],"genre_scores_gemma":[0.9030192,0.00030911787,0.09552859,0.00081836473,0.00013529696,0.0000030846816,6.688492e-7,0.000005068252,0.00018063255],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921834,0.000112920665,0.00021494146,0.0001589413,0.00012542437,0.00016944062],"domain_scores_gemma":[0.99934715,0.00014953458,0.00015455218,0.00019967603,0.00011533937,0.00003377111],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040222952,0.000093090915,0.0001080092,0.00014757819,0.00052097684,0.00062482466,0.00056944793,0.000042700212,0.000007698448],"category_scores_gemma":[0.000040671217,0.00006330805,0.000040867875,0.0002381881,0.0000628835,0.00045234087,0.00032778998,0.0003972688,0.000011179618],"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":[0.00000519518,0.000020762087,0.0011057982,0.000004868774,0.000030935564,0.000006187068,0.00034747864,0.00021060686,0.0012919143,0.009431734,0.00041659933,0.9871279],"study_design_scores_gemma":[0.0010448497,0.0001680421,0.025467396,0.0002332875,0.000040875264,0.00073135004,0.0005808101,0.8363416,0.0032305957,0.12333284,0.00849969,0.00032866368],"about_ca_topic_score_codex":0.00000338956,"about_ca_topic_score_gemma":5.650838e-7,"teacher_disagreement_score":0.98679924,"about_ca_system_score_codex":0.000042254447,"about_ca_system_score_gemma":0.000030303954,"threshold_uncertainty_score":0.60251987},"labels":[],"label_agreement":null},{"id":"W4416136027","doi":"10.48550/arxiv.2506.05027","title":"Tuning the Right Foundation Models is What you Need for Partial Label Learning","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Ambiguity; Initialization; Foundation (evidence); Benchmark (surveying); Classifier (UML); Convolutional neural network; Model selection","score_opus":0.08464897028036827,"score_gpt":0.3101483991326191,"score_spread":0.22549942885225083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416136027","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":[0.037173096,0.000455437,0.93358105,0.02514486,0.0014592167,0.00061560073,0.0000043158852,0.00091465004,0.000651782],"genre_scores_gemma":[0.97456867,0.0006185288,0.014875839,0.0009397304,0.00017202024,0.000566361,0.0000833389,0.000018332092,0.0081571555],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99837255,0.0000750332,0.0003529935,0.00066634873,0.00023129968,0.00030178996],"domain_scores_gemma":[0.9981626,0.00022253445,0.00032899252,0.0010809337,0.0001724434,0.000032488584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043998085,0.00023741605,0.00023013394,0.00015415583,0.00050964166,0.0010124159,0.0017864576,0.00026190426,0.000020150776],"category_scores_gemma":[0.00013298301,0.00018591183,0.00012697301,0.0002882769,0.00008876281,0.0011843893,0.0014769625,0.0005840206,0.00005016685],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040036288,0.00017202401,0.00893602,0.00026092606,0.00030069175,0.000003084961,0.007975398,0.013004895,0.0010827688,0.49693897,0.007602456,0.4636827],"study_design_scores_gemma":[0.00046125217,0.000050787425,0.00058277434,0.00022997754,0.000052205985,8.2520097e-7,0.000688838,0.826615,0.0088686505,0.089952484,0.072067656,0.00042955225],"about_ca_topic_score_codex":0.000022539227,"about_ca_topic_score_gemma":0.000003930313,"teacher_disagreement_score":0.9373956,"about_ca_system_score_codex":0.00008633892,"about_ca_system_score_gemma":0.0001575863,"threshold_uncertainty_score":0.97627497},"labels":[],"label_agreement":null},{"id":"W4417112536","doi":"10.21203/rs.3.rs-7724663/v1","title":"Evolutionary Feature-wise Thresholding for Binary Representation of NLP Embeddings","year":2025,"lang":"","type":"preprint","venue":"Research Square","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University; Brock University","funders":"","keywords":"Binary number; Thresholding; Representation (politics); Embedding; Pattern recognition (psychology); Range (aeronautics); Key (lock)","score_opus":0.11120563944789606,"score_gpt":0.4393729790355389,"score_spread":0.3281673395876428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417112536","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":[0.070311755,0.03648536,0.71301347,0.108455576,0.0073348703,0.032014214,0.00240833,0.0032395206,0.026736895],"genre_scores_gemma":[0.90634733,0.0048840293,0.06342399,0.000049934333,0.00031572863,0.0026900077,0.00041725519,0.000051809246,0.021819927],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9916399,0.0006838011,0.0012138386,0.002419463,0.002685082,0.0013578779],"domain_scores_gemma":[0.9885889,0.0029006992,0.0007538032,0.0036450566,0.0038931035,0.00021840901],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0032817863,0.0005877143,0.0009411961,0.0030117135,0.0011594486,0.00063108525,0.004688184,0.0011462403,0.00011020206],"category_scores_gemma":[0.0036322086,0.00061561033,0.0007323139,0.0044029634,0.0010516278,0.0010838903,0.0073498767,0.002205446,0.000040926854],"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":[0.0008295212,0.001396178,0.010404827,0.009996279,0.00045475675,0.000029486357,0.0037718376,0.003999742,0.009473475,0.5648356,0.22844517,0.16636309],"study_design_scores_gemma":[0.0030390553,0.002197815,0.041501112,0.010062033,0.00014422422,0.000014276434,0.009149541,0.42522013,0.06724725,0.35831496,0.08117059,0.0019390022],"about_ca_topic_score_codex":0.0001600479,"about_ca_topic_score_gemma":0.0000066032553,"teacher_disagreement_score":0.83603555,"about_ca_system_score_codex":0.0008874981,"about_ca_system_score_gemma":0.0018604434,"threshold_uncertainty_score":0.9996295},"labels":[],"label_agreement":null},{"id":"W4417210052","doi":"10.1093/jssam/smaf023","title":"Analyzing List-Style Open-Ended Questions: Combining Texts from Individual Answer Boxes Improves Classification with Language Models","year":2025,"lang":"en","type":"article","venue":"Journal of Survey Statistics and Methodology","topic":"Text and Document Classification Technologies","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","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Classifier (UML); Factorial; Transformer; Language model; Encoder; Question answering","score_opus":0.1819431608627828,"score_gpt":0.3925421491784883,"score_spread":0.21059898831570548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417210052","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028986353,0.0010373758,0.9683693,0.000986509,0.00024772107,0.00010850333,0.0001076651,0.00003332702,0.00012322691],"genre_scores_gemma":[0.41714036,0.00024098517,0.58233887,0.00014093352,0.000011723355,0.000004721342,0.000022792063,0.000004357523,0.00009525599],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9978812,0.001024759,0.0005069541,0.00026048406,0.0001597999,0.00016680858],"domain_scores_gemma":[0.9954553,0.0032670803,0.0005708897,0.00030548597,0.00034188214,0.000059320522],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032654125,0.00013261137,0.00038049064,0.0003234078,0.0001477071,0.00039906835,0.0008296658,0.000104834595,0.0000042116117],"category_scores_gemma":[0.0014318957,0.00010294908,0.000022822214,0.0003660262,0.0001467327,0.0006122043,0.0002859642,0.00028002128,3.8542606e-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":[0.0002073606,0.00018849605,0.025679478,0.000028993769,0.00040728188,0.000029923824,0.0021538804,0.00007400652,0.011345072,0.51710755,0.0056039765,0.437174],"study_design_scores_gemma":[0.0018804123,0.00055324996,0.6383463,0.00012668656,0.00014435436,0.000029911029,0.0019472595,0.021807967,0.0020145494,0.33187434,0.0009336692,0.00034125702],"about_ca_topic_score_codex":0.0005419821,"about_ca_topic_score_gemma":0.00032187114,"teacher_disagreement_score":0.61266685,"about_ca_system_score_codex":0.000029935327,"about_ca_system_score_gemma":0.0001611205,"threshold_uncertainty_score":0.41981417},"labels":[],"label_agreement":null},{"id":"W4417471484","doi":"10.1109/iccvdm66874.2025.11290528","title":"Fusion of Local and Global Context in Large Language Models for Text Classification","year":2025,"lang":"","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Ambiguity; Language model; Context (archaeology); Pooling; Word embedding; Representation (politics); Encoder; Context model","score_opus":0.023662733678754096,"score_gpt":0.30029385108595696,"score_spread":0.27663111740720286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417471484","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":[0.022802206,0.0032154156,0.96132034,0.0051664975,0.00018916534,0.0006968868,0.000036870282,0.0001228382,0.0064497963],"genre_scores_gemma":[0.9927558,0.00024109968,0.0053852513,0.00026721988,0.0000051213933,0.00006096779,0.000007569054,0.0000038387193,0.0012731453],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99829274,0.000050286246,0.00060180336,0.0005646262,0.00017561912,0.00031493919],"domain_scores_gemma":[0.9988833,0.00014038148,0.00019283226,0.0005994549,0.00014296228,0.000041073497],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042566558,0.00018343456,0.000307694,0.00023979538,0.000095654774,0.00010960168,0.0006145421,0.00025048488,0.000023006574],"category_scores_gemma":[0.00007142999,0.00017213958,0.00006888667,0.0008834348,0.0002379475,0.0005509942,0.00042641038,0.000107060674,0.0000047828203],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029559236,0.00012900797,0.0009433063,0.00006440609,0.000006891323,2.6946347e-7,0.0003059134,0.000019411118,0.00038322993,0.58495355,0.00045547207,0.41270897],"study_design_scores_gemma":[0.0017245046,0.00011376109,0.012540403,0.00012839165,0.000013871225,7.5809777e-7,0.010423139,0.9038757,0.004282619,0.06560241,0.0011177178,0.00017672103],"about_ca_topic_score_codex":0.00013270318,"about_ca_topic_score_gemma":0.00036327762,"teacher_disagreement_score":0.9699536,"about_ca_system_score_codex":0.00013991333,"about_ca_system_score_gemma":0.00016094309,"threshold_uncertainty_score":0.70196486},"labels":[],"label_agreement":null},{"id":"W4417477703","doi":"10.1002/eng2.70555","title":"Advertisement Image Classification—Visual ( <scp>RESNET</scp> ) Versus Textual ( <scp>BERT</scp> ) Features: An Experimental Study","year":2025,"lang":"en","type":"article","venue":"Engineering Reports","topic":"Text and Document Classification Technologies","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":"Conestoga College","funders":"","keywords":"Newspaper; Set (abstract data type); Encoder; Transformer; The Internet; Contextual image classification","score_opus":0.014320708605344403,"score_gpt":0.2894027489401498,"score_spread":0.2750820403348054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417477703","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":[0.9101322,0.00091343885,0.07806005,0.00017344706,0.002442963,0.0010383202,0.0000032645573,0.0031153474,0.004120912],"genre_scores_gemma":[0.989423,0.000014020362,0.007492288,0.000040729294,0.00008654481,0.0003530755,0.000032337568,0.00003180106,0.0025262097],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99693716,0.000039395498,0.0007275002,0.001065801,0.0006505538,0.00057957135],"domain_scores_gemma":[0.99753654,0.00033246324,0.00027282492,0.0015693655,0.00011762931,0.00017116229],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00042807538,0.00041835965,0.00033661688,0.00048734367,0.00024614332,0.00052883365,0.00095197075,0.00017839656,0.000006602416],"category_scores_gemma":[0.0008474948,0.00042671745,0.00011710715,0.0008757086,0.000071676404,0.00097122503,0.00053312513,0.00036257665,0.000026666532],"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":[0.000037200844,0.015984176,0.037898477,0.00030994383,0.0015773722,0.0031709203,0.023770684,0.007530111,0.53443164,0.13505527,0.18605788,0.05417633],"study_design_scores_gemma":[0.004212343,0.00277723,0.3510385,0.00018123443,0.00015639185,0.0001801793,0.031570032,0.048435986,0.45228612,0.00058237294,0.10790909,0.0006705224],"about_ca_topic_score_codex":0.0000300587,"about_ca_topic_score_gemma":0.00000723345,"teacher_disagreement_score":0.31314,"about_ca_system_score_codex":0.00029122664,"about_ca_system_score_gemma":0.00013472646,"threshold_uncertainty_score":0.99981844},"labels":[],"label_agreement":null},{"id":"W49807964","doi":"","title":"A simple feature selection method for text classification","year":2001,"lang":"en","type":"article","venue":"International Joint Conference on Artificial Intelligence","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Feature selection; Computer science; Information gain; Feature (linguistics); Simple (philosophy); Set (abstract data type); Artificial intelligence; Selection (genetic algorithm); Pattern recognition (psychology); Data mining; Feature extraction; Machine learning","score_opus":0.15109002272713962,"score_gpt":0.3835078255874474,"score_spread":0.23241780286030778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W49807964","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":[0.0009265626,0.000008568831,0.9591491,0.031551596,0.00069880916,0.0004118876,0.000010648868,0.00055733,0.0066854446],"genre_scores_gemma":[0.88985574,0.00006470622,0.107603684,0.00061597605,0.0001813968,0.0002411114,0.000034887238,0.000013623856,0.0013888587],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980019,0.00006280678,0.00047365576,0.0006989729,0.00044942248,0.0003132412],"domain_scores_gemma":[0.9982961,0.00020626643,0.00028495866,0.0004565737,0.00067544426,0.000080688966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004294358,0.00022435487,0.00018981552,0.00038905191,0.00021607046,0.0005579018,0.0012116655,0.00016628916,0.00025087938],"category_scores_gemma":[0.0004357975,0.00021307572,0.00013106807,0.00051856745,0.00007544675,0.000615337,0.000118989905,0.0002535256,0.00034962772],"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":[0.000031861502,0.00008534625,0.00005186684,0.0000020362638,0.000013373991,0.0000010705024,0.00007666352,0.00011686237,0.015769899,0.6268655,0.0011893922,0.3557961],"study_design_scores_gemma":[0.000046451183,0.00014925508,0.00076830946,0.000019488514,0.000004662375,0.000014132434,0.0002564202,0.54619604,0.06476967,0.36147606,0.026074676,0.0002247993],"about_ca_topic_score_codex":0.00003000382,"about_ca_topic_score_gemma":0.000058875423,"teacher_disagreement_score":0.8889292,"about_ca_system_score_codex":0.00017631352,"about_ca_system_score_gemma":0.00010817624,"threshold_uncertainty_score":0.86889756},"labels":[],"label_agreement":null},{"id":"W66763315","doi":"10.1007/978-3-642-30217-6_2","title":"Active Learning for Hierarchical Text Classification","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Oracle; Text categorization; Categorization; Machine learning; Active learning (machine learning); Artificial intelligence; Multi-label classification; Hierarchical database model; Relation (database); Data mining; Information retrieval","score_opus":0.034292010814983995,"score_gpt":0.2791535654519344,"score_spread":0.24486155463695042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W66763315","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":[0.000039602335,0.00032475175,0.9917894,0.0029438706,0.0008529788,0.0005579271,0.0000027733768,0.00051500794,0.00297371],"genre_scores_gemma":[0.54358447,0.00011887446,0.4537228,0.0005079936,0.00051498745,0.00009898123,0.000021130558,0.000044153676,0.0013866217],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969997,0.000029811885,0.00042932256,0.0012475025,0.00064131204,0.0006523825],"domain_scores_gemma":[0.997391,0.0007796852,0.00037231378,0.0010975463,0.00022818585,0.00013126676],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00067063054,0.00039961239,0.000377542,0.0008383607,0.0003854622,0.0004367229,0.0028415113,0.00043947063,0.000021259611],"category_scores_gemma":[0.00026483356,0.00036382937,0.0001354586,0.00047973107,0.00073620136,0.0008989555,0.00083910866,0.00097260176,0.00007228899],"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":[0.0000054182947,0.00001781104,0.0000331372,0.00001303848,0.0000053501685,0.0000010954648,0.00029215787,0.0005185644,0.0003458747,0.2007328,0.0000218944,0.79801285],"study_design_scores_gemma":[0.00045320037,0.00028897254,0.0012494203,0.00016453036,0.000014425728,0.000023146951,0.0000015102978,0.4115851,0.0058188695,0.5335995,0.04582787,0.0009734729],"about_ca_topic_score_codex":0.0000025460927,"about_ca_topic_score_gemma":0.0000059767517,"teacher_disagreement_score":0.7970394,"about_ca_system_score_codex":0.00035311608,"about_ca_system_score_gemma":0.00031693492,"threshold_uncertainty_score":0.9998814},"labels":[],"label_agreement":null},{"id":"W68431266","doi":"","title":"Model Based Document Classification and Clustering","year":2008,"lang":"en","type":"article","venue":"International journal of tomography and simulation","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Cluster analysis; Computer science; Weighting; Pattern recognition (psychology); Dimensionality reduction; Artificial intelligence; Naive Bayes classifier; Classifier (UML); Data mining; Document clustering; Document classification; Support vector machine","score_opus":0.03912766990925967,"score_gpt":0.292956668367835,"score_spread":0.2538289984585753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W68431266","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":[0.22123261,0.00014978932,0.77649987,0.0017821336,0.00014809461,0.00004052457,7.2261065e-7,0.000036695918,0.00010957317],"genre_scores_gemma":[0.9619962,0.00015225653,0.037675846,0.00012280077,0.000030966872,0.0000017466915,0.0000012413834,0.0000026424054,0.000016309443],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99920857,0.000019486311,0.0002810781,0.000119038836,0.00030719442,0.000064652355],"domain_scores_gemma":[0.9992702,0.000079746846,0.0002559999,0.00010133045,0.0002515472,0.00004115555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001697319,0.0000696985,0.000082582774,0.00040739964,0.000079151934,0.000104404106,0.00028365728,0.000044070388,0.000002542057],"category_scores_gemma":[0.000037322505,0.00006130176,0.000049420432,0.00012114788,0.00006160076,0.0008451464,0.00005582867,0.00007886389,4.3176414e-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":[0.00019612713,0.000215851,0.083422124,0.000022166,0.00018069897,0.000040611518,0.0017236612,0.5028161,0.0055227242,0.08025261,0.00027594256,0.32533142],"study_design_scores_gemma":[0.00044562086,0.00004753661,0.047102135,0.00001657904,0.000004369567,0.000031095624,0.000023221135,0.9430942,0.00029316437,0.008505279,0.00037106965,0.000065738976],"about_ca_topic_score_codex":0.0000014759943,"about_ca_topic_score_gemma":7.023175e-7,"teacher_disagreement_score":0.7407636,"about_ca_system_score_codex":0.000021990794,"about_ca_system_score_gemma":0.000026305706,"threshold_uncertainty_score":0.24998134},"labels":[],"label_agreement":null},{"id":"W6887713244","doi":"10.17600/18001062","title":"APPEAL ATL 19-2 cruise,Côtes De La Manche R/V","year":2019,"lang":"fr","type":"other","venue":"Institut Français de Recherche pour l'Exploitation de la Mer","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nova scotia; Appeal; Western europe; Settlement (finance)","score_opus":0.12242737919141,"score_gpt":0.36933885016424317,"score_spread":0.24691147097283317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6887713244","genre_codex":"methods","genre_gemma":"other","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":[0.0032477432,0.005187345,0.5322426,0.009596722,0.0007104509,0.0007282738,0.000020331094,0.0011215551,0.447145],"genre_scores_gemma":[0.08371703,0.0058257566,0.43887952,0.0023154875,0.0006740355,0.00066517625,0.000040111692,0.00035554572,0.46752733],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9918965,0.0043317163,0.00082458503,0.0011950101,0.0006420374,0.0011101229],"domain_scores_gemma":[0.99181336,0.0053856783,0.0006599447,0.0014786182,0.0002764707,0.0003858973],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity","insufficient_payload"],"category_scores_codex":[0.005975569,0.0008409822,0.00075350463,0.0007501134,0.00034516587,0.0010037937,0.0023410507,0.003897945,0.0021790848],"category_scores_gemma":[0.006068932,0.00088300003,0.0004031233,0.0011450113,0.0012265948,0.0009059698,0.00037637225,0.0029565394,0.005750594],"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":[0.000043539647,0.00047391286,0.010261262,0.00048624,0.0002996996,0.00011268383,0.015695252,0.0010683772,0.004544371,0.563793,0.069861285,0.33336034],"study_design_scores_gemma":[0.0013599516,0.000073741045,0.0069125816,0.00053882407,0.00013992847,0.0001476305,0.0011052866,0.007994183,0.0042257337,0.06200745,0.9144732,0.0010214909],"about_ca_topic_score_codex":0.0010653432,"about_ca_topic_score_gemma":0.00010765676,"teacher_disagreement_score":0.8446119,"about_ca_system_score_codex":0.0018747814,"about_ca_system_score_gemma":0.0029726091,"threshold_uncertainty_score":0.99936205},"labels":[],"label_agreement":null},{"id":"W6920345536","doi":"10.6068/dp14ba8daf1dc3","title":"Trend 1961 - 2013. Statistics Canada. CANSIM: Construction - Machinery and Equipment | Country: Canada | Table: Flows and stocks of fixed non-residential capital, by sector of North American Industry Classification System (NAICS) and asset | Variable: Hyperbolic (delayed) end-year net stock, Computers (x 1,000,000), Mining and oil and gas extraction, Current prices | Units: $CAD, 1961-2013. Data-Planet™ Statistical Ready Reference by Conquest Systems, Inc. Dataset-ID: 075-001-034.","year":2015,"lang":"en","type":"other","venue":"Data Planet","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Economic statistics; Census; Official statistics; Summary statistics; Index (typography); Stock (firearms); Descriptive statistics; Investment (military); Publication; Capital (architecture)","score_opus":0.020323707901361513,"score_gpt":0.24353244910684727,"score_spread":0.22320874120548576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920345536","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00065236713,0.0022677723,0.00047829875,0.000011086671,0.0004735811,0.00035523827,0.9956236,0.000075629025,0.00006244009],"genre_scores_gemma":[0.0026057265,0.0030546552,0.0020226291,0.000018685738,0.00006333563,0.000022519454,0.99209553,0.000050317652,0.000066594905],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969186,0.00020048916,0.00080123305,0.0010049627,0.00069242105,0.00038227267],"domain_scores_gemma":[0.9967062,0.0004195351,0.0013025258,0.0011453232,0.000095267904,0.00033115945],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00032494112,0.00049079634,0.00077354774,0.00018754233,0.00015493433,0.00031653108,0.0008061101,0.0002671738,0.000036148867],"category_scores_gemma":[0.000034199347,0.00047509716,2.6037992e-7,0.00030637428,0.0005124548,0.0004572927,0.0006434698,0.00052914984,2.9744777e-7],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034796387,0.00003281297,0.000751276,0.00068873266,0.00015165121,0.000012233919,0.0000115885505,0.000008730024,0.000021423,0.00026541098,0.98866963,0.009351719],"study_design_scores_gemma":[0.00063202775,0.00012576062,0.0003255665,0.000073915566,0.00019726707,0.00015039516,0.0006055479,0.0318174,2.5412697e-7,2.062479e-7,0.9656172,0.00045446816],"about_ca_topic_score_codex":0.9896452,"about_ca_topic_score_gemma":0.96254915,"teacher_disagreement_score":0.031808667,"about_ca_system_score_codex":0.00011955643,"about_ca_system_score_gemma":0.001992212,"threshold_uncertainty_score":0.99977005},"labels":[],"label_agreement":null},{"id":"W6925191551","doi":"10.17182/hepdata.26861.v1/t14","title":"\"Table 14\" of \"Backward pi- d Elastic Scattering from 496-MeV?c to 1050-MeV/c\"","year":2013,"lang":"en","type":"dataset","venue":"HEPData","topic":"Text and Document Classification Technologies","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":"McGill University","funders":"","keywords":"Scattering; Deformation (meteorology); Population; Elastic scattering; Elasticity (physics)","score_opus":0.03266979796748133,"score_gpt":0.26291160112065126,"score_spread":0.23024180315316994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6925191551","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00028119015,0.00032177614,0.036866818,0.0016436368,0.0011652318,0.0004675656,0.958675,0.00044183116,0.00013694799],"genre_scores_gemma":[0.0012336473,0.00036201018,0.027242918,0.0006221634,0.00019311735,0.00017192711,0.96925473,0.00003239187,0.0008871102],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972833,0.00005107471,0.0006182726,0.0010169749,0.0005404167,0.0004899836],"domain_scores_gemma":[0.99452764,0.00019970766,0.0003987237,0.004596278,0.00012535324,0.0001523254],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00018745645,0.00040054554,0.00056268263,0.00039627717,0.00010876445,0.00044618506,0.0061320974,0.00033676854,0.00081014703],"category_scores_gemma":[0.0002818555,0.00037735983,0.00008120609,0.0006471464,0.000115339426,0.0008077449,0.0036424096,0.00038305006,0.00503769],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030570764,0.000056197452,0.000027191298,0.00006329397,0.000032660584,0.000005199171,0.000021547941,0.000005192046,0.00055022014,0.00031025548,0.9931969,0.005728272],"study_design_scores_gemma":[0.00016992992,0.000070891794,0.00027220917,0.00017514706,0.00002825467,0.000002997695,0.00002704246,0.00020240864,0.0014679247,0.0010850573,0.9960761,0.0004220288],"about_ca_topic_score_codex":0.001489965,"about_ca_topic_score_gemma":0.00015157113,"teacher_disagreement_score":0.010579713,"about_ca_system_score_codex":0.00006320512,"about_ca_system_score_gemma":0.00013621713,"threshold_uncertainty_score":0.99986786},"labels":[],"label_agreement":null},{"id":"W6931862811","doi":"10.5683/sp3/1jyjiy","title":"Labour Force Survey, August 2019 [Canada] [Rebased 2025]","year":2023,"lang":"en","type":"dataset","venue":"Borealis","topic":"Text and Document Classification Technologies","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":true,"ca_institutions":"Statistics Canada","funders":"","keywords":"Unemployment; Current Population Survey; Government (linguistics); Population; Wage; Descriptive statistics; Minimum wage; Discouraged worker","score_opus":0.02842488221238821,"score_gpt":0.26997064311107544,"score_spread":0.24154576089868723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931862811","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000024731003,0.000121018056,0.0017059232,0.0019180649,0.00072912604,0.00023147782,0.9943746,0.00071809493,0.00019922097],"genre_scores_gemma":[0.00000864897,0.00036495802,0.00031530132,0.00053000276,0.00007789052,0.00005696774,0.9886627,0.000021330194,0.009962192],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99760175,0.00012493067,0.00040791303,0.0007094163,0.00067558076,0.00048041582],"domain_scores_gemma":[0.9965204,0.00037139034,0.0003168611,0.0025150003,0.00015912397,0.00011725287],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004936254,0.00034186392,0.0003752155,0.0002724497,0.00015113241,0.00032835963,0.0036746918,0.0003410941,0.000050320385],"category_scores_gemma":[0.00047404427,0.0003221873,0.000080127815,0.00084815704,0.00006825787,0.00023798057,0.0007771961,0.00037786562,0.00036873104],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002588779,0.00001707971,0.000026059559,0.000029464885,0.000027822114,0.000031136184,0.0000018180364,0.0000025369172,0.0000011500088,0.0025162285,0.9962088,0.0011353034],"study_design_scores_gemma":[0.00014650369,0.00002562846,0.014117257,0.00002319637,0.000009708869,0.000001623837,0.0000079877345,0.000046978155,0.00003901632,0.00066606473,0.98454785,0.00036818],"about_ca_topic_score_codex":0.9711613,"about_ca_topic_score_gemma":0.97129464,"teacher_disagreement_score":0.014091197,"about_ca_system_score_codex":0.0002006143,"about_ca_system_score_gemma":0.0009389353,"threshold_uncertainty_score":0.999923},"labels":[],"label_agreement":null},{"id":"W6957941294","doi":"10.6068/dp15df304bf0d75","title":"Trend 1980 - 2014. Energy Information Administration. International Energy Statistics: Liquid Petroleum Gases and Ethane | Country: Canada | Category: Production | Series: LPG Production (nonrefinery) | Units: Barrels Per Day, 1980-2014. Data-Planet™ Statistical Ready Reference by Conquest Systems, Inc. Dataset-ID: 004-015-004.","year":2017,"lang":"en","type":"other","venue":"Data Planet","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Production (economics); Petroleum; Energy (signal processing); Administration (probate law); Energy policy; Agency (philosophy); Liquefied petroleum gas; Environmental impact of the energy industry","score_opus":0.021915702606264645,"score_gpt":0.24903766311853273,"score_spread":0.22712196051226807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6957941294","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.4206583e-7,0.000875846,0.0028099811,0.00024182159,0.002579214,0.00027967143,0.99064666,0.00040318866,0.0021630554],"genre_scores_gemma":[0.00045015686,0.004794335,0.0008748997,0.00013735883,0.0005248929,0.000083191175,0.9863127,0.00007092254,0.006751539],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99607843,0.00024360331,0.00082380744,0.0013835722,0.0009920531,0.00047853208],"domain_scores_gemma":[0.994086,0.00018495484,0.0013616915,0.004047656,0.00010676183,0.00021289734],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000535862,0.0006290543,0.0005600676,0.0003352876,0.00027022444,0.0011178186,0.0033908552,0.00043422985,0.0006040117],"category_scores_gemma":[0.00021886219,0.0005950983,9.996081e-7,0.00008253655,0.00038970006,0.003402258,0.0010213151,0.00043825223,0.00013696734],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009585203,0.000049787475,0.000004193696,0.0001386643,0.00012870421,0.000027223612,0.0000052107125,0.000011663941,0.000022394554,0.04977327,0.94661635,0.003126665],"study_design_scores_gemma":[0.0002792322,0.00019584011,0.0000072901616,0.00003211713,0.00008670642,0.00022801185,0.00008106103,0.0016172752,0.00000795411,0.0000082960105,0.99680823,0.00064799405],"about_ca_topic_score_codex":0.80577904,"about_ca_topic_score_gemma":0.6117406,"teacher_disagreement_score":0.19403847,"about_ca_system_score_codex":0.00015774358,"about_ca_system_score_gemma":0.0016154065,"threshold_uncertainty_score":0.9999191},"labels":[],"label_agreement":null},{"id":"W6976673881","doi":"10.60692/hwq4j-m3d14","title":"Classifying Arabic Text Using KNN Classifier","year":2016,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Text and Document Classification Technologies","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":"University of New Brunswick","funders":"","keywords":"Classifier (UML); Search engine indexing; Pattern recognition (psychology); Feature selection; Word error rate; Term (time)","score_opus":0.07232163768643263,"score_gpt":0.23594012380209306,"score_spread":0.16361848611566043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6976673881","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":[0.088505276,0.0000030870249,0.903713,0.0006983272,0.0005779797,0.00022964478,0.000009535019,0.0014982302,0.004764902],"genre_scores_gemma":[0.9925575,2.5592797e-7,0.006782592,0.0001443985,0.000043404645,0.000041115356,0.0000010098944,0.0000075216003,0.00042215618],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9983545,0.00005123278,0.0006200527,0.00025430365,0.00037282257,0.0003470963],"domain_scores_gemma":[0.9984079,0.000017770422,0.00041375746,0.0008905849,0.00016364828,0.00010633307],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00030525288,0.00019845452,0.00019887723,0.0004470206,0.00022205274,0.00047910406,0.0008054721,0.0001588033,0.00002813282],"category_scores_gemma":[0.000052998148,0.00012473714,0.00008287105,0.0004600527,0.000064501546,0.0036178743,0.00023367925,0.00008189441,0.0018206168],"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":[0.000061700084,0.00001515032,0.2764176,0.000565761,0.0001768384,0.000016185359,0.048473623,0.000078368,0.0013760021,0.4405465,0.0028903875,0.22938186],"study_design_scores_gemma":[0.016013369,0.0005640947,0.40912792,0.0039307275,0.00017369495,0.00097089476,0.054274675,0.33749706,0.08860593,0.0014857008,0.080486335,0.006869595],"about_ca_topic_score_codex":0.0000018765484,"about_ca_topic_score_gemma":4.84818e-8,"teacher_disagreement_score":0.90405226,"about_ca_system_score_codex":0.0002607036,"about_ca_system_score_gemma":0.00007390509,"threshold_uncertainty_score":0.99895656},"labels":[],"label_agreement":null},{"id":"W6977231403","doi":"10.6084/m9.figshare.26569141","title":"Additional file 1 of Knowledge and appropriateness of care of family physicians and physiotherapists in the management of shoulder pain: a survey study in the province of Quebec, Canada","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Text and Document Classification Technologies","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":true,"ca_institutions":"Université Laval; Centre for Interdisciplinary Research in Rehabilitation; Université de Montréal; Hôpital Maisonneuve-Rosemont","funders":"","keywords":"Survey research; MEDLINE; Health services research; Survey data collection; Data collection; Primary care","score_opus":0.0298694448598964,"score_gpt":0.26385001193260077,"score_spread":0.23398056707270437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6977231403","genre_codex":"dataset","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":[0.018969197,0.0018531237,0.000035262605,0.00013235748,0.000016411916,0.0011032732,0.9775232,0.000018671486,0.00034850911],"genre_scores_gemma":[0.9906673,0.0000040539867,0.00007480054,0.000011015968,0.0000022321153,0.0002340512,0.008964344,0.0000029057007,0.000039283837],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9992783,0.00013657525,0.00018872973,0.00014120093,0.00019634819,0.00005882931],"domain_scores_gemma":[0.9988441,0.00070715684,0.00011329687,0.0002485778,0.00008294673,0.000003922355],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000115686125,0.000063536376,0.0001359783,0.000057639,0.000010960919,0.000011291587,0.0004526655,0.000019931489,0.002642355],"category_scores_gemma":[0.000061852676,0.000040851715,0.000016083179,0.00041283737,0.00002975221,0.00006908579,0.000115495444,0.000049960552,2.0348064e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000113698825,0.00039474946,0.0004710776,0.0047838204,0.000058725855,0.0000068173954,0.008042015,0.000020799522,0.00005168247,0.0005514982,0.8994604,0.08614709],"study_design_scores_gemma":[0.00023002164,0.00014165672,0.9739367,0.0037664261,0.000004110933,1.9133343e-7,0.01302436,0.0012752209,0.00035854086,0.00013473732,0.0070259147,0.0001021138],"about_ca_topic_score_codex":0.012000635,"about_ca_topic_score_gemma":0.24798244,"teacher_disagreement_score":0.9734656,"about_ca_system_score_codex":0.000016622724,"about_ca_system_score_gemma":0.00016122634,"threshold_uncertainty_score":0.9982694},"labels":[],"label_agreement":null},{"id":"W6992394548","doi":"","title":"Le Québec mis en caricatures. Humeurs et humours d'une société à travers le temps Quebec in caricature. Moods and humour of a society through time","year":2013,"lang":"fr","type":"other","venue":"OpenEdition (OpenEdition)","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Period (music); Theme (computing)","score_opus":0.013766931604180781,"score_gpt":0.24745574286617844,"score_spread":0.23368881126199767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6992394548","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028694475,0.009476823,0.039330754,0.50557494,0.002004482,0.0044201016,0.0007604225,0.001005429,0.4345576],"genre_scores_gemma":[0.36989832,0.003337806,0.030265523,0.016557056,0.0006094667,0.0015015496,0.0016371275,0.0003963554,0.5757968],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99508494,0.0005122697,0.0011718994,0.0015801088,0.0008625518,0.0007882011],"domain_scores_gemma":[0.996372,0.00048127116,0.001276359,0.0013236656,0.00033254147,0.00021416439],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006465452,0.00090815505,0.0012437222,0.00038630635,0.00049427483,0.0006771975,0.0019943852,0.0014278772,0.0024654926],"category_scores_gemma":[0.00017169084,0.000963966,0.0004715871,0.0012272112,0.0013231703,0.009341587,0.00058429595,0.0012415173,0.00055878103],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020089352,0.0006268801,0.00012674322,0.00020366062,0.00019258358,0.000011708848,0.003741896,0.000107691645,0.001739728,0.81926316,0.16301298,0.010952895],"study_design_scores_gemma":[0.004220929,0.00040029243,0.056026928,0.00094551145,0.00021354415,0.000059716633,0.008862569,0.0014316716,0.006634866,0.011596973,0.9073449,0.0022620994],"about_ca_topic_score_codex":0.18878905,"about_ca_topic_score_gemma":0.21011603,"teacher_disagreement_score":0.8076662,"about_ca_system_score_codex":0.0005754475,"about_ca_system_score_gemma":0.0026313902,"threshold_uncertainty_score":0.99986845},"labels":[],"label_agreement":null},{"id":"W7009548693","doi":"","title":"Enhancing Text Annotation with Few-shot and Active Learning: A Comprehensive Study and Tool Development","year":2023,"lang":"en","type":"dissertation","venue":"Spectrum Research Repository (Concordia University)","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Concordia University","keywords":"Process (computing); Task (project management); Field (mathematics); Feature (linguistics); Matching (statistics)","score_opus":0.04011149522743568,"score_gpt":0.29513010778234766,"score_spread":0.255018612554912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7009548693","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":[0.9941661,0.00006857481,0.0005536767,0.0001842951,0.00016615845,0.0008861782,8.0132554e-7,0.00047915924,0.0034950578],"genre_scores_gemma":[0.9698238,0.00012141695,0.00031797914,0.0000021145288,0.000027950504,0.000021915559,0.000028271463,0.000026308744,0.029630283],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99725187,0.00035126362,0.00023391389,0.0009787548,0.0007209927,0.000463233],"domain_scores_gemma":[0.99842703,0.00039616425,0.00023373318,0.00043306357,0.0003831257,0.0001268884],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00024919715,0.00028423686,0.0003281337,0.0014387409,0.0011901035,0.00049171434,0.0006414248,0.00019187511,0.00000294694],"category_scores_gemma":[0.00007381913,0.0002868127,0.000032876917,0.0014641307,0.00018964487,0.0006581364,0.00042208369,0.0009096107,0.000016649637],"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":[0.005275387,0.0018117969,0.22266953,0.0020876396,0.0037894254,0.0069251186,0.1907636,0.00008339923,0.09522487,0.049082667,0.0009957202,0.42129087],"study_design_scores_gemma":[0.0011955114,0.0014788529,0.83367157,0.00019945833,0.00004415259,0.000020151248,0.112111725,0.00018400428,0.0405334,0.0002244263,0.009686698,0.00065006997],"about_ca_topic_score_codex":0.0010642688,"about_ca_topic_score_gemma":0.006114407,"teacher_disagreement_score":0.611002,"about_ca_system_score_codex":0.00038933777,"about_ca_system_score_gemma":0.0007032749,"threshold_uncertainty_score":0.9999584},"labels":[],"label_agreement":null},{"id":"W7015701947","doi":"","title":"A text categorization approach for match-making in online business tendering","year":2005,"lang":"en","type":"article","venue":"NPARC","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Categorization; Ranking (information retrieval); Order (exchange); Training set; Procurement; Electronic business","score_opus":0.03290863753924243,"score_gpt":0.2748034285535879,"score_spread":0.24189479101434547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7015701947","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":[0.004585382,0.000021776383,0.987533,0.0045301593,0.000051298968,0.00019636269,0.0000012949712,0.00035261243,0.0027281188],"genre_scores_gemma":[0.60806113,0.000006316761,0.39164338,0.00007607671,0.000031709864,0.00004482929,0.000009035309,0.0000043426508,0.00012314165],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99929535,0.000008580686,0.00017071597,0.00024425276,0.00010591381,0.00017516129],"domain_scores_gemma":[0.99954635,0.000026706566,0.0000645018,0.00027679134,0.0000720679,0.000013602911],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000110760004,0.00007786364,0.000090105605,0.00016078808,0.00005584462,0.000096112664,0.00046334192,0.000058758716,0.000006357327],"category_scores_gemma":[0.0000699527,0.0000727696,0.00001629285,0.0006728493,0.000020521255,0.00046294407,0.00010665677,0.000065315704,0.0000052571927],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000054262196,0.0002062351,0.00079741917,0.000045244546,0.000004386497,6.3170734e-7,0.00055780803,0.003121502,0.013466959,0.37278113,0.0005005051,0.60851276],"study_design_scores_gemma":[0.0005357192,0.000020641253,0.008018595,0.00002223117,0.0000029213345,0.000005327012,0.00030111888,0.9424979,0.0045013246,0.034411423,0.009433804,0.00024899564],"about_ca_topic_score_codex":0.0000026077307,"about_ca_topic_score_gemma":0.0000086921855,"teacher_disagreement_score":0.9393764,"about_ca_system_score_codex":0.00006078747,"about_ca_system_score_gemma":0.00003347338,"threshold_uncertainty_score":0.2967458},"labels":[],"label_agreement":null},{"id":"W7020719597","doi":"","title":"$87.40 Million in Sales Expected for Vivint Solar Inc (NYSE:VSLR) This Quarter","year":2020,"lang":"en","type":"other","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Revenue; Work (physics)","score_opus":0.02115992947317765,"score_gpt":0.25607000225421295,"score_spread":0.2349100727810353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7020719597","genre_codex":"methods","genre_gemma":"other","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":[0.000022211067,0.0011943885,0.76317513,0.011643409,0.00075666193,0.0012731309,0.000028315759,0.0049465606,0.2169602],"genre_scores_gemma":[0.01587624,0.00073675584,0.24194707,0.0014815705,0.00037057095,0.00086282793,0.0001993805,0.00039309185,0.7381325],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984474,0.00003892657,0.0003245969,0.00067121274,0.00022891612,0.0002889394],"domain_scores_gemma":[0.99887204,0.00007734783,0.00019900475,0.0007687548,0.000029155697,0.00005369207],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00009392619,0.0002867123,0.0003478297,0.0005228614,0.000042296713,0.00015891777,0.0013099819,0.00039124567,0.00093185453],"category_scores_gemma":[0.000046085857,0.00023868946,0.00009817627,0.0004519201,0.00005985732,0.00017516082,0.0002699816,0.00020295753,0.0005584477],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000050837157,0.00004676394,0.000044834065,0.00004182666,0.000018868383,0.000003220628,0.0003346265,1.593734e-7,0.00035896682,0.027490024,0.9554794,0.016176257],"study_design_scores_gemma":[0.00040991767,0.000116414674,0.00012197433,0.00007394662,0.0000059748822,0.0000011385426,0.00023395153,0.002141759,0.0016469521,0.0033709647,0.9914607,0.00041631027],"about_ca_topic_score_codex":0.00012848571,"about_ca_topic_score_gemma":0.00034284784,"teacher_disagreement_score":0.521228,"about_ca_system_score_codex":0.000061063336,"about_ca_system_score_gemma":0.00005853701,"threshold_uncertainty_score":0.9999814},"labels":[],"label_agreement":null},{"id":"W7022485765","doi":"","title":"9780472902422.pdf","year":2021,"lang":"en","type":"other","venue":"OAPEN (The OAPEN Foundation)","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada; Jackman Humanities Institute, University of Toronto","keywords":"Eugenics; Context (archaeology); Population; Identity (music); Categorization; Indigenous; Perception; Embodied cognition","score_opus":0.019927424160352456,"score_gpt":0.2639188037139476,"score_spread":0.24399137955359515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7022485765","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000026032237,0.000019020808,0.05603125,0.0075091,0.0011656844,0.0004426227,6.200659e-9,0.0010389944,0.93379074],"genre_scores_gemma":[0.00055380404,0.0002909011,0.009447181,0.0006578907,0.000256751,0.00016534756,0.00021190342,0.00015053582,0.9882657],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978934,0.00011339852,0.00034820632,0.00075989985,0.000524946,0.00036018415],"domain_scores_gemma":[0.99711686,0.000121973266,0.0004398089,0.0021708352,0.000083330975,0.00006716132],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00025158253,0.00035925058,0.00033352204,0.00026088124,0.00025723682,0.0010016536,0.003053994,0.00025948728,0.7405394],"category_scores_gemma":[0.00009449317,0.00027926004,0.0001532631,0.0007717822,0.00018636281,0.0003371023,0.0008358982,0.00036243445,0.8293802],"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":[7.565054e-7,0.000032248725,0.000032975247,0.000017539029,0.000058346748,0.000005606034,0.000032620414,5.2343177e-7,0.00004578101,0.07664219,0.014255004,0.9088764],"study_design_scores_gemma":[0.00017534306,0.00001801946,0.00024304679,0.00007554824,0.000020760024,0.000013047324,0.0000481802,0.0001748458,0.00019340662,0.0050896476,0.9935954,0.00035271555],"about_ca_topic_score_codex":0.000086504224,"about_ca_topic_score_gemma":0.00008603613,"teacher_disagreement_score":0.97934043,"about_ca_system_score_codex":0.00009991249,"about_ca_system_score_gemma":0.00022536005,"threshold_uncertainty_score":0.99996597},"labels":[],"label_agreement":null},{"id":"W7030395727","doi":"","title":"Ne niin sanotut \"pestuumarkkinat\" : palkollisten pestuutapahtumat sanomalehdissä ja muistitiedossa vuosina 1880 - 1920","year":2018,"lang":"fi","type":"other","venue":"Jyväskylä University Digital Archive (University of Jyväskylä)","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Life style; Quarter (Canadian coin)","score_opus":0.0114479324778916,"score_gpt":0.18376768885274974,"score_spread":0.17231975637485814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7030395727","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012404467,0.00030202063,0.09574218,0.0017340932,0.0011712161,0.0016357626,0.0029343755,0.0015712848,0.8825046],"genre_scores_gemma":[0.16604127,0.001082227,0.013594996,0.00009139553,0.00028453997,0.0000010247032,0.00083990477,0.00023479837,0.81782985],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9926036,0.00042499442,0.0007853013,0.0029082184,0.001553791,0.0017240883],"domain_scores_gemma":[0.9927323,0.0006612064,0.0020872506,0.0030522519,0.0006258433,0.0008411444],"candidate_categories":["metaepi_narrow","sts","open_science","insufficient_payload"],"consensus_categories":["metaepi_narrow","sts","insufficient_payload"],"category_scores_codex":[0.00033398063,0.0016372367,0.0020880145,0.0024693448,0.0015788936,0.0006684395,0.0080417385,0.001127749,0.0056612664],"category_scores_gemma":[0.00023289541,0.0021449162,0.0013784919,0.002266748,0.005777641,0.0033138625,0.0056472067,0.0011274881,0.0054787095],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021547307,0.0034894082,0.01365915,0.001558469,0.002758732,0.0030728562,0.008578705,0.00003472648,0.00066727924,0.21344611,0.46667027,0.28390956],"study_design_scores_gemma":[0.0036242276,0.0011548977,0.019517204,0.0009211637,0.0004327254,0.00007534296,0.009986865,0.0012243697,0.000067091656,0.0046633324,0.95599985,0.002332902],"about_ca_topic_score_codex":0.0013113396,"about_ca_topic_score_gemma":0.001189004,"teacher_disagreement_score":0.4893296,"about_ca_system_score_codex":0.00085205166,"about_ca_system_score_gemma":0.0009434985,"threshold_uncertainty_score":0.99972093},"labels":[],"label_agreement":null},{"id":"W7066926928","doi":"","title":"102.7 KIIS FM Los Angeles Airchecks January 2025","year":2025,"lang":"en","type":"other","venue":"Internet Archive (Internet Archive)","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Thursday; Set (abstract data type); Collectable","score_opus":0.015821200614007283,"score_gpt":0.25682547217852564,"score_spread":0.24100427156451837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7066926928","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000015722522,0.0008083791,0.36265573,0.0005664303,0.0010388419,0.0006561557,0.00058575795,0.0019581115,0.6317149],"genre_scores_gemma":[0.002900743,0.00035809012,0.029194254,0.0006892677,0.00033092673,0.00017329826,0.00043045313,0.00024274984,0.96568024],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951129,0.00034046115,0.0009065083,0.0019935218,0.0006610416,0.0009855783],"domain_scores_gemma":[0.99611837,0.00051053095,0.0006692629,0.0023754886,0.00006391766,0.00026244586],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00022292175,0.0010664468,0.0009815589,0.0020113885,0.000060988346,0.0005223573,0.006550595,0.00043815392,0.0040896703],"category_scores_gemma":[0.00017704893,0.0009989099,0.0006014403,0.0004409998,0.0007004353,0.00029659108,0.0040651155,0.001290699,0.0023551565],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033963137,0.0001542423,0.00027261188,0.0001505659,0.000314272,0.00008511434,0.00042975336,0.0000013567326,0.0001238848,0.1280306,0.8554156,0.014988034],"study_design_scores_gemma":[0.00053813105,0.00019595197,0.00044068525,0.0011839255,0.000055741948,0.000020350302,0.000053260923,0.0034742663,0.0017598558,0.026548201,0.96478975,0.0009398745],"about_ca_topic_score_codex":0.005468148,"about_ca_topic_score_gemma":0.0074450695,"teacher_disagreement_score":0.33396536,"about_ca_system_score_codex":0.00010815807,"about_ca_system_score_gemma":0.00025512843,"threshold_uncertainty_score":0.9992461},"labels":[],"label_agreement":null},{"id":"W7069047744","doi":"","title":"Akron, Ohio","year":2009,"lang":"en","type":"other","venue":"OhioLink ETD Center (Ohio Library and Information Network)","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Watson; Booster (rocketry); Morning; Swift","score_opus":0.008611227068965154,"score_gpt":0.20176666614710442,"score_spread":0.19315543907813926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7069047744","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.0741334e-7,0.0011954482,0.034772165,0.0030002333,0.00074168894,0.00036831052,0.000030535346,0.0027549719,0.9571359],"genre_scores_gemma":[0.006544215,0.033572417,0.06874219,0.029280724,0.0028009142,0.00016892535,0.002930093,0.00038531978,0.8555752],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982591,0.00005661428,0.00057496596,0.00035756466,0.0002601731,0.000491528],"domain_scores_gemma":[0.99840385,0.00003418213,0.0005400718,0.00086070923,0.000014694004,0.0001464754],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00009524783,0.00041065886,0.00035938082,0.00044752713,0.0001466152,0.0007910075,0.001193112,0.0005113435,0.0008705732],"category_scores_gemma":[0.0000070024616,0.00036790565,0.00010385866,0.00053551147,0.000085681066,0.009969164,0.0004974779,0.00039684167,0.00037050122],"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":[0.0000031692462,0.000011781299,0.000014835753,0.000023862422,0.000012937743,7.9801686e-7,0.000026243511,0.0000052346113,1.2662105e-7,0.49520695,0.44605526,0.0586388],"study_design_scores_gemma":[0.00040965006,0.000058493075,0.0003643653,0.00020753128,0.0000069341368,0.00001026031,0.0000023924813,0.0014048455,0.000018061492,0.004604643,0.99250424,0.00040860692],"about_ca_topic_score_codex":5.1878303e-8,"about_ca_topic_score_gemma":4.0430027e-7,"teacher_disagreement_score":0.54644895,"about_ca_system_score_codex":0.000011732192,"about_ca_system_score_gemma":0.000056951558,"threshold_uncertainty_score":0.9998773},"labels":[],"label_agreement":null},{"id":"W7115013425","doi":"10.1007/s44443-025-00413-8","title":"A novel multi-label deep forest algorithm based on elite preservation strategy and multi-layer feature fusion","year":2025,"lang":"en","type":"article","venue":"Journal of King Saud University - Computer and Information Sciences","topic":"Text and Document Classification Technologies","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":"Artificial Intelligence in Medicine (Canada)","funders":"National Natural Science Foundation of China","keywords":"Feature (linguistics); Field (mathematics); Fusion; Stability (learning theory); Pattern recognition (psychology); Random forest; Layer (electronics); Statistical classification","score_opus":0.0334171096165064,"score_gpt":0.2660460454538522,"score_spread":0.23262893583734578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7115013425","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010761683,0.000046589554,0.9863896,0.002172878,0.0001783944,0.00008702034,0.000001881014,0.00004270744,0.00031929603],"genre_scores_gemma":[0.16247974,0.00013686027,0.83649737,0.00074281654,0.000016999411,2.346182e-7,0.0000021795677,0.0000010991351,0.00012271028],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999244,0.000027099071,0.0002107106,0.00012463274,0.00027681698,0.00011674255],"domain_scores_gemma":[0.9991877,0.00009078903,0.0003189863,0.00011431015,0.00024118925,0.00004702421],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004118954,0.000093431394,0.000116803356,0.0006962645,0.00039145543,0.0004863538,0.0005184123,0.000070801594,9.1115913e-7],"category_scores_gemma":[0.000031964995,0.000076059114,0.00002950771,0.00063471915,0.000121014884,0.0061002215,0.0001854841,0.00015113472,8.0676017e-7],"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":[0.000017076596,0.00008911187,0.003306704,0.000025527746,0.00001199204,0.0000018452678,0.0006242602,0.005140893,0.0001581456,0.02923048,0.00033269796,0.96106124],"study_design_scores_gemma":[0.001098915,0.00016044673,0.06306107,0.000082075225,0.0000053700924,0.000006761667,0.0002781485,0.9304382,0.000049976858,0.00016214572,0.0045799557,0.00007688729],"about_ca_topic_score_codex":0.000015392974,"about_ca_topic_score_gemma":0.000007722797,"teacher_disagreement_score":0.96098435,"about_ca_system_score_codex":0.00004276468,"about_ca_system_score_gemma":0.00008936065,"threshold_uncertainty_score":0.46899208},"labels":[],"label_agreement":null},{"id":"W7115168809","doi":"10.18280/isi.301001","title":"Text Augmentation Approaches to Enhance Traditional Machine Learning Performance for SDGs Classification of Indonesian News Articles","year":2025,"lang":"","type":"article","venue":"Ingénierie des systèmes d information","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Universitas Gadjah Mada","keywords":"Indonesian; Training set; Key (lock); Support vector machine","score_opus":0.07416843936564876,"score_gpt":0.2659454558059801,"score_spread":0.19177701644033135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7115168809","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":[0.25746477,0.00018344053,0.7355075,0.002347068,0.0004064453,0.0014143627,0.000043307246,0.00025769012,0.0023754388],"genre_scores_gemma":[0.9752736,0.00013323216,0.023002673,0.00017140011,0.000041961193,0.0007319382,0.00027678558,0.000013100835,0.0003552926],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99680007,0.0001214691,0.0016662878,0.00044137196,0.0005008787,0.0004699042],"domain_scores_gemma":[0.9974695,0.00025188838,0.0011373981,0.00057751726,0.00046531024,0.000098395765],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00086214725,0.00036434422,0.00042069363,0.0011738769,0.00074326707,0.0006355049,0.0008540387,0.00026253046,0.000024895813],"category_scores_gemma":[0.0005333191,0.00039035297,0.00014899272,0.0020402556,0.00031530196,0.006072504,0.00017569598,0.00026598753,0.00006012161],"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":[0.00017815043,0.0001260011,0.0047011864,0.0010940728,0.00006277849,6.361104e-8,0.006033868,0.0026941786,0.0027389098,0.13985534,0.00028617863,0.84222925],"study_design_scores_gemma":[0.0011414505,0.0008228274,0.1016713,0.0008361538,0.000082660816,0.0000056036956,0.0057925293,0.7518856,0.11602111,0.01564863,0.0054303766,0.0006617554],"about_ca_topic_score_codex":0.000044719003,"about_ca_topic_score_gemma":0.000018705452,"teacher_disagreement_score":0.8415675,"about_ca_system_score_codex":0.00053466746,"about_ca_system_score_gemma":0.00031850307,"threshold_uncertainty_score":0.99985486},"labels":[],"label_agreement":null},{"id":"W7116838783","doi":"10.1109/icsec67360.2025.11298043","title":"An Integration of Fine-Tuned RoBERTa, Support Vector Machine, and Differential Evolution in Enhancing Multi-Label Text Classification for Academic Publications","year":2025,"lang":"","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"Assumption University","funders":"","keywords":"Support vector machine; Feature selection; Benchmark (surveying); Classifier (UML); Differential evolution; Feature (linguistics); Class (philosophy)","score_opus":0.04325472606089602,"score_gpt":0.33758448402179303,"score_spread":0.294329757960897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7116838783","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":[0.07865401,0.00031351545,0.9120261,0.00659468,0.00043705266,0.0014307685,0.00003453795,0.00028632738,0.00022298332],"genre_scores_gemma":[0.9451489,0.0001624544,0.051429026,0.000053232656,0.000026130672,0.00045737394,0.0001585717,0.000015211036,0.0025491058],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966131,0.00014752142,0.0014553592,0.0010704132,0.00027744265,0.00043618053],"domain_scores_gemma":[0.9974492,0.00030874947,0.00064621057,0.0010181447,0.00048076763,0.00009692471],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006351676,0.00035804283,0.00044804128,0.0014188295,0.0002815449,0.0002871884,0.0010888412,0.00055957463,0.000081715276],"category_scores_gemma":[0.0007021885,0.00035078154,0.0000859456,0.0017287723,0.00025642768,0.0020151779,0.00022214392,0.00047504855,0.0000066571556],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043220785,0.00049916597,0.0058492175,0.00008323374,0.000018712954,4.444096e-8,0.00043773474,0.0000045967336,0.3374219,0.43839157,0.00016912329,0.21708149],"study_design_scores_gemma":[0.0014836162,0.00019943398,0.28837928,0.00009518928,0.000040913914,7.623757e-7,0.0004605482,0.66222304,0.042785242,0.004000119,0.00008429789,0.00024753794],"about_ca_topic_score_codex":0.00034590284,"about_ca_topic_score_gemma":0.002687513,"teacher_disagreement_score":0.8664949,"about_ca_system_score_codex":0.0003278791,"about_ca_system_score_gemma":0.0004376309,"threshold_uncertainty_score":0.99989444},"labels":[],"label_agreement":null},{"id":"W7117547339","doi":"10.18280/isi.301114","title":"SHADO: A Semantics-Preserving Hybrid Framework for Automatic Text Classification Using Domain Ontology","year":2025,"lang":"","type":"article","venue":"Ingénierie des systèmes d information","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Domain (mathematical analysis); Ontology; Feature (linguistics); Identification (biology); Pattern recognition (psychology)","score_opus":0.03452624255051188,"score_gpt":0.2994413137071079,"score_spread":0.264915071156596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117547339","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":[0.061152328,0.00062969554,0.9268136,0.003586181,0.0020893742,0.0020603996,0.000044041106,0.0010579894,0.002566395],"genre_scores_gemma":[0.7394071,0.00008068029,0.25941226,0.000462437,0.00006662817,0.00034734255,0.000065607775,0.00002001436,0.0001378939],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952619,0.00022943837,0.0023122784,0.0006569742,0.000529405,0.0010100254],"domain_scores_gemma":[0.9946495,0.0007868499,0.0017534556,0.001783577,0.00089791155,0.0001286971],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0013641604,0.0006066492,0.000757824,0.001494325,0.0015144394,0.00238441,0.0022179184,0.0006651393,0.00007039481],"category_scores_gemma":[0.0026246095,0.0006587208,0.00029466915,0.0019959665,0.0006122687,0.0074603194,0.0007776485,0.00051293673,0.000110118424],"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":[0.000040056384,0.000084533334,0.0009088272,0.0019797434,0.00012881651,0.0000013515395,0.0043800897,0.00028796957,0.00042527943,0.67909,0.0012732946,0.31140003],"study_design_scores_gemma":[0.0005643331,0.000103686034,0.0035443748,0.0012865913,0.000077216384,0.00002250606,0.002931056,0.6157586,0.0015805361,0.36808893,0.0055872896,0.0004548585],"about_ca_topic_score_codex":0.000056781482,"about_ca_topic_score_gemma":0.000012120111,"teacher_disagreement_score":0.6782548,"about_ca_system_score_codex":0.001345399,"about_ca_system_score_gemma":0.0007531813,"threshold_uncertainty_score":0.9997855},"labels":[],"label_agreement":null},{"id":"W7117575766","doi":"10.18280/isi.301102","title":"Indonesian Sports Text Classification Modeling Based on Few-Shot NER","year":2025,"lang":"","type":"article","venue":"Ingénierie des systèmes d information","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indonesian; Topic model; Feature (linguistics); Named-entity recognition; Acronym","score_opus":0.02922572258510529,"score_gpt":0.2616909532835031,"score_spread":0.23246523069839783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117575766","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":[0.027238326,0.00018427988,0.9086042,0.00295537,0.0015843187,0.0010697261,0.00001575421,0.0011211233,0.057226893],"genre_scores_gemma":[0.99198604,0.00011093582,0.0057046018,0.0013154956,0.000058044323,0.000240068,0.00013480915,0.000020300344,0.00042970307],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99546766,0.00015244585,0.0019481104,0.00065766723,0.0010137404,0.0007603786],"domain_scores_gemma":[0.9961217,0.00014722162,0.0010057327,0.0018250495,0.0007529895,0.00014730562],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0010897778,0.0006140598,0.0005188046,0.0021202536,0.0010741329,0.002070483,0.0015123278,0.0006358949,0.0000907809],"category_scores_gemma":[0.0005245104,0.00062854757,0.00022920675,0.0028960595,0.0003449584,0.0070754327,0.00028303228,0.00057655503,0.00031032215],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011129674,0.00016324063,0.0027892538,0.0004893644,0.000039121474,0.000002637958,0.0017470652,0.03845057,0.00012997336,0.2563088,0.0010706378,0.69869804],"study_design_scores_gemma":[0.00081173144,0.0001318599,0.0122828195,0.0008800867,0.000041524996,0.0000041024405,0.0015160874,0.96511054,0.0010630667,0.012015445,0.0055639436,0.00057877414],"about_ca_topic_score_codex":0.00005254749,"about_ca_topic_score_gemma":0.00000513289,"teacher_disagreement_score":0.9647477,"about_ca_system_score_codex":0.0010676305,"about_ca_system_score_gemma":0.0007924706,"threshold_uncertainty_score":0.99961656},"labels":[],"label_agreement":null},{"id":"W7124915570","doi":"10.1109/cloudcom67567.2025.11331420","title":"Enhancing Tail NFT Recommendation via Dependency-Aware Extreme Multi-Label Learning","year":2025,"lang":"","type":"article","venue":"","topic":"Text and Document Classification Technologies","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":"Simon Fraser University","funders":"","keywords":"Partition (number theory); Class (philosophy); Probabilistic logic; Multi-label classification; Set (abstract data type); Tree (set theory); Recommender system; Semantics (computer science)","score_opus":0.05599960013446609,"score_gpt":0.30490817461370134,"score_spread":0.24890857447923526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124915570","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":[0.0012748017,0.00046198355,0.9743953,0.012533656,0.0017223131,0.00050432474,0.0000016528734,0.0017743998,0.0073315827],"genre_scores_gemma":[0.83522207,0.00045708197,0.10800176,0.0005423943,0.000044671564,0.00007663354,0.000023093487,0.000022619402,0.055609647],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961115,0.00026281597,0.001098235,0.0013447533,0.00039305122,0.0007896055],"domain_scores_gemma":[0.9976555,0.00031666431,0.00049427955,0.0010310377,0.00038489728,0.00011763896],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00088820286,0.0004930466,0.00043483058,0.000751928,0.0010383893,0.00093036675,0.001712772,0.00045208764,0.0015172497],"category_scores_gemma":[0.000481718,0.0005097222,0.00014145079,0.0018647243,0.00014650113,0.0018806241,0.0013440378,0.00091829663,0.00072641857],"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":[0.000009209753,0.00027487485,0.0021454284,0.00007069576,0.00005427817,0.000003283584,0.00041776482,0.000025224423,0.012268887,0.019119574,0.0009021791,0.9647086],"study_design_scores_gemma":[0.0015062923,0.00016281263,0.0011166,0.00022227735,0.00004696342,0.0000051511147,0.0020526026,0.8946357,0.07795562,0.0052482346,0.01632812,0.0007196393],"about_ca_topic_score_codex":0.00015006338,"about_ca_topic_score_gemma":0.00033234674,"teacher_disagreement_score":0.96398896,"about_ca_system_score_codex":0.00035389955,"about_ca_system_score_gemma":0.0003340144,"threshold_uncertainty_score":0.9997354},"labels":[],"label_agreement":null},{"id":"W7132542374","doi":"","title":"Fast & confident probabilistic categorisation","year":2007,"lang":"en","type":"article","venue":"NPARC","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Probabilistic logic; Labelling; Set (abstract data type); Anomaly detection; Test (biology); Measure (data warehouse); Test set; Layer (electronics)","score_opus":0.017939049263417092,"score_gpt":0.2566820421824322,"score_spread":0.23874299291901507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132542374","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":[0.019892545,0.000014253918,0.93334454,0.0025221996,0.00023021657,0.00014090081,2.6849588e-7,0.0006410502,0.043214038],"genre_scores_gemma":[0.97886264,0.0000035451342,0.020280939,0.00008961772,0.00002362624,0.000010916521,0.0000015068537,0.0000026761875,0.00072451786],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993203,0.000009021841,0.00014970262,0.00018723388,0.00017198226,0.00016171852],"domain_scores_gemma":[0.99943686,0.000050243016,0.000058944846,0.00036577703,0.000053006912,0.000035165893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002686637,0.000059372855,0.000056257028,0.000081450824,0.0000628079,0.00008816094,0.00045340727,0.000042783795,0.000059084],"category_scores_gemma":[0.0000630424,0.00005267537,0.000020272933,0.00022051182,0.00004717448,0.00022334022,0.00008312134,0.000063933505,0.00016530573],"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":[0.0000011589142,0.000020780286,0.00033803255,0.0000030494873,0.0000018058781,0.0000018391939,0.000197313,0.0000032472099,0.009512566,0.8297563,0.0013933361,0.15877053],"study_design_scores_gemma":[0.00036251862,0.00010612467,0.033201803,0.000008863866,0.0000053205526,0.000012364217,0.00038771596,0.006792029,0.07575212,0.85189235,0.031179953,0.0002988544],"about_ca_topic_score_codex":0.000005459523,"about_ca_topic_score_gemma":0.000007602366,"teacher_disagreement_score":0.9589701,"about_ca_system_score_codex":0.00005182521,"about_ca_system_score_gemma":0.000024516863,"threshold_uncertainty_score":0.21480392},"labels":[],"label_agreement":null},{"id":"W8258861","doi":"10.7589/0090-3558-29.4.596","title":"Multi-class categorization based on cluster analysis and TFIDF","year":2008,"lang":"en","type":"article","venue":"Journal of Wildlife Diseases","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Categorization; tf–idf; Computer science; Class (philosophy); Artificial intelligence; Humanities; Information retrieval; Natural language processing; Philosophy; Physics","score_opus":0.018639204838426317,"score_gpt":0.25320885059448606,"score_spread":0.23456964575605974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W8258861","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":[0.18480009,0.00027520984,0.80457014,0.009914328,0.00017080539,0.00008805321,0.0000062891554,0.0001210632,0.00005399399],"genre_scores_gemma":[0.98851484,0.00010819455,0.009802012,0.0014466133,0.00003840095,0.0000025062714,0.0000030985082,0.0000041801577,0.0000801505],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99906975,0.00005158267,0.0002874613,0.00015540776,0.00032480666,0.000110982335],"domain_scores_gemma":[0.9990395,0.000110502166,0.00031341915,0.0002774435,0.00014635906,0.00011280115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000093191775,0.0000973797,0.00019067676,0.0005515973,0.00011913692,0.000086878186,0.00037149992,0.000041633826,0.000009224177],"category_scores_gemma":[0.00019288815,0.00007427427,0.00013590856,0.00068177644,0.000073003604,0.0004910155,0.000046644032,0.000083953826,0.0000050719113],"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":[0.00011765774,0.0010634576,0.94862634,0.000026483855,0.0003753787,0.000105943946,0.00033931635,0.011842385,0.00029831904,0.0028123541,0.020077763,0.014314627],"study_design_scores_gemma":[0.0010691724,0.00019041347,0.72445464,0.000016624927,0.00019054502,0.000015144244,0.000047237932,0.2708368,0.00033038677,0.00032878123,0.0023539122,0.00016632541],"about_ca_topic_score_codex":0.0000030017904,"about_ca_topic_score_gemma":0.0000011187601,"teacher_disagreement_score":0.80371475,"about_ca_system_score_codex":0.00003422143,"about_ca_system_score_gemma":0.000087379245,"threshold_uncertainty_score":0.3028817},"labels":[],"label_agreement":null}]}