{"meta":{"query_hash":"f55b3b497170","filters":{"venue":"Recent Advances in Natural Language Processing"},"cohort_total":10,"direct_labels_cover":0,"predictions_cover":10,"exported":10,"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/f55b3b497170","api":"https://metacan.xera.ac/api/v1/cohort?venue=Recent+Advances+in+Natural+Language+Processing"},"results":[{"id":"W14107570","doi":"","title":"Extracting Synonyms from Dictionary Definitions","year":2009,"lang":"en","type":"article","venue":"Recent Advances in Natural Language Processing","topic":"Natural Language Processing Techniques","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":"Computer science; Natural language processing; Synonym (taxonomy); Artificial intelligence; Lexicon; Bilingual dictionary; Lemmatisation; Information retrieval","score_opus":0.013372814188784323,"score_gpt":0.2994146677861813,"score_spread":0.286041853597397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W14107570","genre_codex":"review","genre_gemma":"empirical","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":[0.004198855,0.80909956,0.17994007,0.0018938136,0.0005180131,0.00023466254,0.000006987914,0.0014830548,0.0026249615],"genre_scores_gemma":[0.6232747,0.0029297224,0.37292486,0.0006284238,0.0001475991,0.000011946865,0.000032570482,0.000012220511,0.00003797449],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978722,0.00007496239,0.0004382514,0.0006681053,0.00044061232,0.00050591957],"domain_scores_gemma":[0.9989592,0.00018173183,0.0002608396,0.00038226682,0.00013011716,0.00008587803],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00023520907,0.0002896176,0.00027727714,0.00029204486,0.00025500444,0.00030803817,0.00094932446,0.0001301406,0.00002431883],"category_scores_gemma":[0.00033745426,0.0002571397,0.0000644168,0.0011997551,0.000040392297,0.0042798673,0.00014081737,0.0007929863,0.000010970747],"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":[0.000014367847,0.000069929236,0.00012433672,0.000020912019,0.0000023279517,0.000116955176,0.00089652697,0.000023796023,0.004587837,0.0019954396,0.00002328068,0.9921243],"study_design_scores_gemma":[0.0034418523,0.00041011136,0.00355306,0.0059408545,0.00007914138,0.00075142895,0.002809618,0.23043774,0.10325943,0.6130426,0.03124671,0.0050274907],"about_ca_topic_score_codex":0.0000183126,"about_ca_topic_score_gemma":0.000037429978,"teacher_disagreement_score":0.9870968,"about_ca_system_score_codex":0.00027174765,"about_ca_system_score_gemma":0.00008543213,"threshold_uncertainty_score":0.9999881},"labels":[],"label_agreement":null},{"id":"W2120344709","doi":"","title":"Beyond the Transfer-and-Merge Wordnet Construction: plWordNet and a Comparison with WordNet","year":2013,"lang":"en","type":"article","venue":"Recent Advances in Natural Language Processing","topic":"Natural Language Processing Techniques","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 Ottawa","funders":"","keywords":"WordNet; Computer science; Merge (version control); Natural language processing; Artificial intelligence; Perspective (graphical); Information retrieval","score_opus":0.005192038935594544,"score_gpt":0.2609067758639921,"score_spread":0.2557147369283975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120344709","genre_codex":"review","genre_gemma":"empirical","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":[0.05205707,0.8773407,0.06447274,0.003642431,0.00033848843,0.00084092305,0.000003100962,0.00059459277,0.0007099718],"genre_scores_gemma":[0.77469903,0.0026585255,0.22189564,0.0005202146,0.0000737622,0.00006884098,0.000007218628,0.000020149339,0.000056609817],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979862,0.000102320075,0.00039182595,0.0006332976,0.00038669258,0.00049967377],"domain_scores_gemma":[0.9991494,0.00014079174,0.0001462481,0.00032248275,0.00013453804,0.00010657975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026072166,0.00034340558,0.00036774098,0.00017766232,0.0002856199,0.0005839042,0.00066455954,0.00010686727,0.000022018612],"category_scores_gemma":[0.00006331612,0.00020976909,0.000025627704,0.0010049439,0.0003777478,0.002613897,0.00019953727,0.0007634799,0.000002273563],"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":[0.000028685403,0.00002333951,0.0016351471,0.000117844815,0.0000072126168,0.000015841642,0.002960786,0.000008297933,0.00042568645,0.0025258842,0.00004215746,0.99220914],"study_design_scores_gemma":[0.014925201,0.0020400612,0.010018844,0.009008773,0.0003623342,0.0070529957,0.0367626,0.5745879,0.059284747,0.19320954,0.0811522,0.011594781],"about_ca_topic_score_codex":0.000036568865,"about_ca_topic_score_gemma":0.00018486468,"teacher_disagreement_score":0.98061436,"about_ca_system_score_codex":0.00006102074,"about_ca_system_score_gemma":0.000060229966,"threshold_uncertainty_score":0.85541356},"labels":[],"label_agreement":null},{"id":"W2250240387","doi":"","title":"How Joe and Jane Tweet about Their Health: Mining for Personal Health Information on Twitter","year":2013,"lang":"en","type":"article","venue":"Recent Advances in Natural Language Processing","topic":"Data Quality and Management","field":"Decision Sciences","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":"Dalhousie University; University of Ottawa","funders":"","keywords":"WordNet; Computer science; Social media; World Wide Web; Ontology; The Internet; Personally identifiable information; Information retrieval; Internet privacy; Information extraction; Health information; Data science; Health care; Computer security","score_opus":0.06336643424205922,"score_gpt":0.40170521289053357,"score_spread":0.33833877864847434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2250240387","genre_codex":"review","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":[0.319914,0.4678303,0.03053282,0.1726304,0.002264407,0.004524616,0.0002345318,0.00024569614,0.0018232194],"genre_scores_gemma":[0.9751705,0.0027097543,0.008029607,0.01315012,0.00014128698,0.000076836615,0.00015727054,0.000011140055,0.00055348285],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979951,0.00012558729,0.00053303206,0.0003404223,0.0005920284,0.00041387693],"domain_scores_gemma":[0.9987092,0.0003879252,0.00050011295,0.0001547928,0.00014495819,0.00010299659],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017358116,0.00017127136,0.00030965396,0.00027529884,0.00025509132,0.0008821737,0.0002725445,0.00004102422,0.000027111104],"category_scores_gemma":[0.0009508833,0.0001140833,0.000035855475,0.00041353985,0.00006165789,0.0041571455,0.00009845287,0.00018905183,0.000010245951],"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":[0.000032433916,0.000016152402,0.00013059944,0.00019823715,0.000002236499,3.2248903e-7,0.017792758,0.000007324417,0.0000060702864,0.00005438141,0.0022737687,0.9794857],"study_design_scores_gemma":[0.0015312849,0.00031730134,0.0031421229,0.00089529745,0.0000033351942,0.000009508195,0.12890053,0.031759404,0.000118751406,0.0021402393,0.83070874,0.0004734997],"about_ca_topic_score_codex":0.000027968958,"about_ca_topic_score_gemma":0.00012732655,"teacher_disagreement_score":0.9790122,"about_ca_system_score_codex":0.00011920111,"about_ca_system_score_gemma":0.00006683783,"threshold_uncertainty_score":0.85068214},"labels":[],"label_agreement":null},{"id":"W2250988804","doi":"","title":"Classification of Emotion Words in Russian and Romanian Languages","year":2009,"lang":"en","type":"article","venue":"Recent Advances in Natural Language Processing","topic":"Sentiment Analysis and Opinion Mining","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":"Children's Hospital of Eastern Ontario","funders":"","keywords":"Surprise; Sadness; Anger; WordNet; Disgust; Root (linguistics); Spelling; Computer science; Natural language processing; Artificial intelligence; Emotion classification; Word (group theory); Romanian; Psychology; Linguistics; Communication; Social psychology","score_opus":0.008528628059636015,"score_gpt":0.30523296177927073,"score_spread":0.2967043337196347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2250988804","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":[0.7190125,0.26477587,0.011271754,0.0014044608,0.0001627334,0.00017868126,5.533365e-7,0.00007812459,0.0031152898],"genre_scores_gemma":[0.98428774,0.0015532251,0.014037299,0.00005490582,0.000028527948,0.0000013812773,0.0000071137692,0.000002958992,0.000026820351],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991284,0.00004032274,0.0002569601,0.00024933624,0.00016736609,0.00015761991],"domain_scores_gemma":[0.9996568,0.000022338478,0.00015312432,0.00012326008,0.0000207376,0.000023726232],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020500524,0.0000922157,0.00015727937,0.00026598026,0.000032859494,0.00006297891,0.00019541582,0.000038358965,0.0000043777345],"category_scores_gemma":[0.000039799274,0.00007900685,0.000019390578,0.00076156476,0.000019688037,0.0009952956,0.000030258689,0.00012841607,5.4931394e-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":[0.000005791657,0.000030294663,0.0065893843,0.000024395264,9.677008e-7,0.0000055497585,0.0027134768,0.000046038378,0.002425937,0.0014667792,6.5029013e-7,0.98669076],"study_design_scores_gemma":[0.0012370389,0.00009765736,0.46029142,0.0011369897,0.000010573426,0.000014399547,0.00704298,0.5211802,0.00599227,0.0017468598,0.00073799974,0.0005116214],"about_ca_topic_score_codex":0.000004889715,"about_ca_topic_score_gemma":0.000057509704,"teacher_disagreement_score":0.9861791,"about_ca_system_score_codex":0.000042355754,"about_ca_system_score_gemma":0.000014975803,"threshold_uncertainty_score":0.3221806},"labels":[],"label_agreement":null},{"id":"W2251088109","doi":"","title":"What Sentiments Can Be Found in Medical Forums","year":2013,"lang":"en","type":"article","venue":"Recent Advances in Natural Language Processing","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Sentiment analysis; Gratitude; Categorization; Computer science; Confusion; Class (philosophy); Natural language processing; Artificial intelligence; Information retrieval; Psychology; Social psychology","score_opus":0.010537265998960346,"score_gpt":0.31498434294585226,"score_spread":0.30444707694689194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2251088109","genre_codex":"review","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":[0.2967023,0.67320645,0.01017434,0.013293376,0.0038351077,0.0007735296,7.676845e-7,0.00024737956,0.0017667328],"genre_scores_gemma":[0.98257905,0.005792053,0.009740201,0.0013841762,0.000102472215,0.000030465595,0.000019208252,0.00001277079,0.0003395884],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99789846,0.00006664478,0.00041331953,0.00046301918,0.00067300163,0.00048557302],"domain_scores_gemma":[0.99937326,0.0000721015,0.00014836452,0.00022056013,0.000081592254,0.00010412072],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033638228,0.00018071807,0.00025084065,0.00027681346,0.00008097555,0.00055897847,0.0006819074,0.000079162994,0.00017567497],"category_scores_gemma":[0.00011821158,0.00014861007,0.000044188062,0.0012277149,0.000042370193,0.004360563,0.00024305967,0.00032718203,0.000015540752],"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":[0.000002970854,0.00004892091,0.003370834,0.00003598122,0.0000047990798,0.000040085823,0.002077711,0.00008182589,0.0001178341,0.00011772158,0.000035148652,0.9940662],"study_design_scores_gemma":[0.0024819945,0.000050244187,0.0040152883,0.0026388303,0.000011433181,0.000045527744,0.00970835,0.9593293,0.0026706404,0.0017299105,0.01627651,0.0010419866],"about_ca_topic_score_codex":0.00005184137,"about_ca_topic_score_gemma":0.00050956185,"teacher_disagreement_score":0.9930242,"about_ca_system_score_codex":0.0001338345,"about_ca_system_score_gemma":0.00007627654,"threshold_uncertainty_score":0.60601425},"labels":[],"label_agreement":null},{"id":"W2251989420","doi":"","title":"Towards a Hybrid Rule-based and Statistical Arabic-French Machine Translation System","year":2013,"lang":"en","type":"article","venue":"Recent Advances in Natural Language Processing","topic":"Natural Language Processing Techniques","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 du Québec à Montréal","funders":"","keywords":"Machine translation; Computer science; Natural language processing; Artificial intelligence; Phrase; Arabic; Machine translation software usability; Example-based machine translation; Rule-based machine translation; Evaluation of machine translation; Transfer-based machine translation; Computer-assisted translation; Translation (biology); Synchronous context-free grammar; Scheme (mathematics); BLEU; Modern Standard Arabic; Quality (philosophy); Linguistics","score_opus":0.0067527020823977485,"score_gpt":0.2728687706527462,"score_spread":0.2661160685703484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2251989420","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":[0.0029200118,0.47270787,0.5222972,0.0005383185,0.00017339198,0.00039246178,0.00000846582,0.00064823334,0.00031404727],"genre_scores_gemma":[0.56916237,0.00030182672,0.43027505,0.0001297218,0.000035774596,0.000044554068,0.000025577729,0.000014477991,0.000010628679],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99783486,0.000119111224,0.0004477953,0.0006443922,0.00046547034,0.0004883799],"domain_scores_gemma":[0.9990893,0.00013754681,0.00019461034,0.00029043914,0.00016979189,0.00011829283],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00032484712,0.00031506125,0.0003452597,0.00027570405,0.00014631721,0.00043510355,0.0006131161,0.000090123634,0.000018811827],"category_scores_gemma":[0.00016456036,0.00024896278,0.00003495259,0.0006292065,0.00009623711,0.0024448317,0.00011472884,0.00052411784,0.000006385284],"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":[0.0000108872755,0.000027669112,0.00015393949,0.0004964671,0.00000238542,0.00005503149,0.0003764419,0.0000137204515,0.00064662297,0.0009497409,0.000009199497,0.9972579],"study_design_scores_gemma":[0.0011728588,0.000082072635,0.0005305472,0.0011592903,0.000016489377,0.00017424281,0.00017681242,0.97398376,0.011501682,0.009084284,0.0012954018,0.00082257955],"about_ca_topic_score_codex":0.000105915715,"about_ca_topic_score_gemma":0.00003794123,"teacher_disagreement_score":0.99643534,"about_ca_system_score_codex":0.00019216257,"about_ca_system_score_gemma":0.00010480943,"threshold_uncertainty_score":0.99999624},"labels":[],"label_agreement":null},{"id":"W2395936782","doi":"","title":"A Comparative Study of Different Sentiment Lexica for Sentiment Analysis of Tweets","year":2015,"lang":"en","type":"article","venue":"Recent Advances in Natural Language Processing","topic":"Sentiment Analysis and Opinion Mining","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":"Concordia University","funders":"","keywords":"Sentiment analysis; Computer science; Natural language processing; Artificial intelligence; Information retrieval","score_opus":0.03576092369102291,"score_gpt":0.3703291697388255,"score_spread":0.3345682460478026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2395936782","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":[0.92278314,0.04868452,0.027270135,0.00006996913,0.00029153575,0.00064077985,0.0000047140056,0.000036334044,0.00021888096],"genre_scores_gemma":[0.9913185,0.00010526399,0.008423876,0.000015698264,0.000022923534,0.000028677177,0.000025210598,0.0000057924235,0.000054064047],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979528,0.00010713602,0.00066721946,0.0004394108,0.0005767819,0.00025665574],"domain_scores_gemma":[0.99868685,0.00010600601,0.0005642933,0.00029358713,0.00027783506,0.00007141897],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037191593,0.00019882646,0.000765913,0.00060787756,0.00005114312,0.00005476748,0.0004639162,0.000032814718,0.000008433146],"category_scores_gemma":[0.000036196318,0.00015342717,0.0001486825,0.0018678932,0.00003606261,0.0005308392,0.00017770658,0.00010429842,4.495575e-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":[0.0005549055,0.006887149,0.103004456,0.00043592247,0.0030246738,0.00002184918,0.18266118,0.036296025,0.0067052864,0.00080724055,0.00008508964,0.6595162],"study_design_scores_gemma":[0.003338301,0.0005371374,0.005268458,0.00023504885,0.00075748743,9.984141e-7,0.030128684,0.93320644,0.025394918,0.00018266785,0.0004729143,0.00047694956],"about_ca_topic_score_codex":0.000012146382,"about_ca_topic_score_gemma":0.00011275318,"teacher_disagreement_score":0.8969104,"about_ca_system_score_codex":0.00010101639,"about_ca_system_score_gemma":0.000038697028,"threshold_uncertainty_score":0.62565786},"labels":[],"label_agreement":null},{"id":"W2397481291","doi":"","title":"A Procedural Definition of Multi-word Lexical Units","year":2015,"lang":"en","type":"article","venue":"Recent Advances in Natural Language Processing","topic":"Natural Language Processing Techniques","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 Ottawa","funders":"","keywords":"Computer science; WordNet; Intuition; Artificial intelligence; Natural language processing; Decision tree; Machine learning","score_opus":0.036234424091415286,"score_gpt":0.3289595941006193,"score_spread":0.292725170009204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2397481291","genre_codex":"review","genre_gemma":"empirical","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":[0.014227893,0.8196678,0.16241327,0.00066254573,0.0005673078,0.00050652254,0.00000553168,0.0009608521,0.0009882735],"genre_scores_gemma":[0.5789875,0.00046341374,0.42025787,0.00017049182,0.000046437883,0.00001810968,0.000014057391,0.000014900161,0.00002726322],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997839,0.00010331883,0.0005143959,0.00051468535,0.0005545335,0.00047410547],"domain_scores_gemma":[0.9985509,0.000070720766,0.00033779515,0.00031470854,0.0005949316,0.00013094614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046005013,0.00027751847,0.00035744428,0.00033633277,0.00007073573,0.00012061435,0.0009731798,0.00013937466,0.0000036555537],"category_scores_gemma":[0.001105041,0.00022931717,0.000042258842,0.0021989704,0.00011990323,0.0027194496,0.00028527153,0.0005594852,0.000004148836],"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":[0.00006156546,0.00010608846,0.00029402945,0.00025588987,0.000003426134,0.000056829118,0.0030889898,0.000024377909,0.001965499,0.0036057527,0.00003086787,0.9905067],"study_design_scores_gemma":[0.01389665,0.0010319115,0.00074878725,0.009619504,0.00009884024,0.0012695078,0.01144612,0.43773925,0.32539144,0.17456737,0.018111384,0.0060792253],"about_ca_topic_score_codex":0.000014257685,"about_ca_topic_score_gemma":0.00006877617,"teacher_disagreement_score":0.98442745,"about_ca_system_score_codex":0.00019514174,"about_ca_system_score_gemma":0.00032708372,"threshold_uncertainty_score":0.9351283},"labels":[],"label_agreement":null},{"id":"W2402187144","doi":"","title":"A Large Wordnet-based Sentiment Lexicon for Polish.","year":2015,"lang":"en","type":"article","venue":"Recent Advances in Natural Language Processing","topic":"Sentiment Analysis and Opinion Mining","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 Ottawa","funders":"","keywords":"WordNet; Lexicon; Computer science; Sentiment analysis; Annotation; Natural language processing; Selection (genetic algorithm); Artificial intelligence; Resource (disambiguation); Process (computing); Information retrieval; Point (geometry)","score_opus":0.018838462704943215,"score_gpt":0.33234407663710946,"score_spread":0.31350561393216625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2402187144","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":[0.012567877,0.38349485,0.59745216,0.0020705792,0.0016909378,0.00062084384,0.000007134788,0.0003187104,0.0017769291],"genre_scores_gemma":[0.87016684,0.00022965252,0.12814222,0.00078397774,0.00021780789,0.000043992335,0.0000657507,0.000018597975,0.00033116262],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983435,0.000049169405,0.0003183668,0.00044752218,0.00036886142,0.00047257365],"domain_scores_gemma":[0.9992576,0.0000617785,0.0001894074,0.00023588793,0.00014850001,0.00010678009],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051470747,0.00018137562,0.00023962712,0.00023370124,0.000100989164,0.00023519096,0.00048933976,0.000051853032,0.0000120522245],"category_scores_gemma":[0.00013188271,0.00015448856,0.00007745258,0.0007789965,0.000021254606,0.0012035106,0.00011018163,0.00015530777,0.0000067116052],"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":[0.00007012387,0.00018072368,0.0015320659,0.00011424205,0.000013383753,0.000018440569,0.0038998916,0.0012543936,0.000385963,0.0024447455,0.00035713776,0.98972887],"study_design_scores_gemma":[0.0027289158,0.000068227426,0.000061859726,0.0003015939,0.00001544514,0.0000040988048,0.0019944126,0.88444924,0.0067663486,0.0011163151,0.10201375,0.00047980997],"about_ca_topic_score_codex":0.0000035178193,"about_ca_topic_score_gemma":0.000043384553,"teacher_disagreement_score":0.98924905,"about_ca_system_score_codex":0.00015026015,"about_ca_system_score_gemma":0.00014557569,"threshold_uncertainty_score":0.62998605},"labels":[],"label_agreement":null},{"id":"W2407195633","doi":"","title":"A Statistical Model for Measuring Structural Similarity between Webpages","year":2015,"lang":"en","type":"article","venue":"Recent Advances in Natural Language Processing","topic":"Natural Language Processing Techniques","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":"Toronto Metropolitan University","funders":"","keywords":"Similarity (geometry); Computer science; Web page; Statistical model; Task (project management); Measure (data warehouse); Artificial intelligence; Structural similarity; Information retrieval; Natural language processing; Data mining; Image (mathematics); World Wide Web","score_opus":0.039281710599538375,"score_gpt":0.3505640517397068,"score_spread":0.3112823411401684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2407195633","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":[0.0030700203,0.2195458,0.77558726,0.000401941,0.00023795015,0.00040080532,0.000023109893,0.00060764636,0.00012545077],"genre_scores_gemma":[0.52572244,0.00010537992,0.4738537,0.00010904712,0.00010616934,0.000029372204,0.000026447198,0.00001900534,0.00002846334],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99734014,0.000086894295,0.00049946917,0.0007464501,0.0006120742,0.0007149944],"domain_scores_gemma":[0.99862397,0.00021101716,0.00023862821,0.00036313885,0.0003637637,0.00019946694],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007316886,0.000352984,0.00045146124,0.0002490874,0.00017642128,0.00032566517,0.0011894734,0.00015839489,0.0000023361486],"category_scores_gemma":[0.0011603814,0.00029665165,0.000058482234,0.0006586929,0.000100738536,0.0028919175,0.00034555537,0.00064035895,0.0000014812318],"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":[0.000053553176,0.000019441963,0.0010111071,0.00025365956,0.0000061769038,0.000027525759,0.002385884,0.00062801107,0.0002898454,0.002732604,0.000054195818,0.992538],"study_design_scores_gemma":[0.0009124437,0.000053422154,0.0000819079,0.00025299523,0.000015667203,0.000023600043,0.0002431011,0.9193919,0.004611324,0.07322766,0.0005789079,0.0006071197],"about_ca_topic_score_codex":0.000008345354,"about_ca_topic_score_gemma":0.00005534052,"teacher_disagreement_score":0.9919309,"about_ca_system_score_codex":0.00035262894,"about_ca_system_score_gemma":0.00026633558,"threshold_uncertainty_score":0.99994856},"labels":[],"label_agreement":null}]}