{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":10,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":10,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"f55b3b497170","filters":{"venue":"Recent Advances in Natural Language Processing"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","authors":[{"name":"Monika Zaśko-Zielińska","is_ca":false},{"name":"Maciej Piasecki","is_ca":false},{"name":"Stan Śzpakowicz","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01883846270494322,"gpt":0.3323440766371095,"spread":0.3135056139321662,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005147075,0.0001813756,0.0002396271,0.0002337012,0.0001009892,0.000235191,0.0004893398,0.00005185303,0.00001205222],"category_scores_gemma":[0.0001318827,0.0001544886,0.00007745258,0.0007789965,0.00002125461,0.001203511,0.0001101816,0.0001553078,0.000006711605],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001502602,"about_ca_system_score_gemma":0.0001455757,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003517819,"about_ca_topic_score_gemma":0.00004338455,"domain_scores_codex":[0.9983435,0.0000491694,0.0003183668,0.0004475222,0.0003688614,0.0004725737],"domain_scores_gemma":[0.9992576,0.0000617785,0.0001894074,0.0002358879,0.0001485,0.0001067801],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007012387,0.0001807237,0.001532066,0.0001142421,0.00001338375,0.00001844057,0.003899892,0.001254394,0.000385963,0.002444746,0.0003571378,0.9897289],"study_design_scores_gemma":[0.002728916,0.00006822743,0.00006185973,0.0003015939,0.00001544514,0.000004098805,0.001994413,0.8844492,0.006766349,0.001116315,0.1020138,0.00047981],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01256788,0.3834949,0.5974522,0.002070579,0.001690938,0.0006208438,0.000007134788,0.0003187104,0.001776929],"genre_scores_gemma":[0.8701668,0.0002296525,0.1281422,0.0007839777,0.0002178079,0.00004399234,0.0000657507,0.00001859798,0.0003311626],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9892491,"threshold_uncertainty_score":0.629986,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Marina Sokolova","is_ca":true},{"name":"Victoria Bobicev","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01053726599896035,"gpt":0.3149843429458523,"spread":0.3044470769468919,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003363823,0.0001807181,0.0002508406,0.0002768135,0.00008097555,0.0005589785,0.0006819074,0.00007916299,0.000175675],"category_scores_gemma":[0.0001182116,0.0001486101,0.00004418806,0.001227715,0.00004237019,0.004360563,0.0002430597,0.000327182,0.00001554075],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001338345,"about_ca_system_score_gemma":0.00007627654,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005184137,"about_ca_topic_score_gemma":0.0005095619,"domain_scores_codex":[0.9978985,0.00006664478,0.0004133195,0.0004630192,0.0006730016,0.000485573],"domain_scores_gemma":[0.9993733,0.0000721015,0.0001483645,0.0002205601,0.00008159225,0.0001041207],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002970854,0.00004892091,0.003370834,0.00003598122,0.00000479908,0.00004008582,0.002077711,0.00008182589,0.0001178341,0.0001177216,0.00003514865,0.9940662],"study_design_scores_gemma":[0.002481994,0.00005024419,0.004015288,0.00263883,0.00001143318,0.00004552774,0.00970835,0.9593293,0.00267064,0.00172991,0.01627651,0.001041987],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.2967023,0.6732064,0.01017434,0.01329338,0.003835108,0.0007735296,7.676845e-7,0.0002473796,0.001766733],"genre_scores_gemma":[0.9825791,0.005792053,0.009740201,0.001384176,0.0001024722,0.0000304656,0.00001920825,0.00001277079,0.0003395884],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9930242,"threshold_uncertainty_score":0.6060143,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Marek Maziarz","is_ca":false},{"name":"Maciej Piasecki","is_ca":false},{"name":"Ewa Rudnicka","is_ca":false},{"name":"Stan Śzpakowicz","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.005192038935594544,"gpt":0.2609067758639921,"spread":0.2557147369283975,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002607217,0.0003434056,0.000367741,0.0001776623,0.0002856199,0.0005839042,0.0006645595,0.0001068673,0.00002201861],"category_scores_gemma":[0.00006331612,0.0002097691,0.0000256277,0.001004944,0.0003777478,0.002613897,0.0001995373,0.0007634799,0.000002273563],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006102074,"about_ca_system_score_gemma":0.00006022997,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003656886,"about_ca_topic_score_gemma":0.0001848647,"domain_scores_codex":[0.9979862,0.0001023201,0.0003918259,0.0006332976,0.0003866926,0.0004996738],"domain_scores_gemma":[0.9991494,0.0001407917,0.0001462481,0.0003224828,0.000134538,0.0001065797],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000286854,0.00002333951,0.001635147,0.0001178448,0.000007212617,0.00001584164,0.002960786,0.000008297933,0.0004256864,0.002525884,0.00004215746,0.9922091],"study_design_scores_gemma":[0.0149252,0.002040061,0.01001884,0.009008773,0.0003623342,0.007052996,0.0367626,0.5745879,0.05928475,0.1932095,0.0811522,0.01159478],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.05205707,0.8773407,0.06447274,0.003642431,0.0003384884,0.0008409231,0.000003100962,0.0005945928,0.0007099718],"genre_scores_gemma":[0.774699,0.002658525,0.2218956,0.0005202146,0.0000737622,0.00006884098,0.000007218628,0.00002014934,0.00005660982],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.9806144,"threshold_uncertainty_score":0.8554136,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Marina Sokolova","is_ca":true},{"name":"Victoria Bobicev","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.008528628059636015,"gpt":0.3052329617792707,"spread":0.2967043337196347,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002050052,0.0000922157,0.0001572794,0.0002659803,0.00003285949,0.00006297891,0.0001954158,0.00003835896,0.000004377735],"category_scores_gemma":[0.00003979927,0.00007900685,0.00001939058,0.0007615648,0.00001968804,0.0009952956,0.00003025869,0.0001284161,5.493139e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004235575,"about_ca_system_score_gemma":0.0000149758,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004889715,"about_ca_topic_score_gemma":0.0000575097,"domain_scores_codex":[0.9991284,0.00004032274,0.0002569601,0.0002493362,0.0001673661,0.0001576199],"domain_scores_gemma":[0.9996568,0.00002233848,0.0001531243,0.0001232601,0.0000207376,0.00002372623],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005791657,0.00003029466,0.006589384,0.00002439526,9.677008e-7,0.000005549758,0.002713477,0.00004603838,0.002425937,0.001466779,6.502901e-7,0.9866908],"study_design_scores_gemma":[0.001237039,0.00009765736,0.4602914,0.00113699,0.00001057343,0.00001439955,0.00704298,0.5211802,0.00599227,0.00174686,0.0007379997,0.0005116214],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7190125,0.2647759,0.01127175,0.001404461,0.0001627334,0.0001786813,5.533365e-7,0.00007812459,0.00311529],"genre_scores_gemma":[0.9842877,0.001553225,0.0140373,0.00005490582,0.00002852795,0.000001381277,0.000007113769,0.000002958992,0.00002682035],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9861791,"threshold_uncertainty_score":0.3221806,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Marina Sokolova","is_ca":true},{"name":"Stan Matwin","is_ca":true},{"name":"Yasser Jafer","is_ca":true},{"name":"David Schramm","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06336643424205922,"gpt":0.4017052128905336,"spread":0.3383387786484743,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001735812,0.0001712714,0.000309654,0.0002752988,0.0002550913,0.0008821737,0.0002725445,0.00004102422,0.0000271111],"category_scores_gemma":[0.0009508833,0.0001140833,0.00003585548,0.0004135398,0.00006165789,0.004157146,0.00009845287,0.0001890518,0.00001024595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001192011,"about_ca_system_score_gemma":0.00006683783,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002796896,"about_ca_topic_score_gemma":0.0001273266,"domain_scores_codex":[0.9979951,0.0001255873,0.0005330321,0.0003404223,0.0005920284,0.0004138769],"domain_scores_gemma":[0.9987092,0.0003879252,0.0005001129,0.0001547928,0.0001449582,0.0001029966],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003243392,0.0000161524,0.0001305994,0.0001982371,0.000002236499,3.22489e-7,0.01779276,0.000007324417,0.000006070286,0.00005438141,0.002273769,0.9794857],"study_design_scores_gemma":[0.001531285,0.0003173013,0.003142123,0.0008952974,0.000003335194,0.000009508195,0.1289005,0.0317594,0.0001187514,0.002140239,0.8307087,0.0004734997],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.319914,0.4678303,0.03053282,0.1726304,0.002264407,0.004524616,0.0002345318,0.0002456961,0.001823219],"genre_scores_gemma":[0.9751705,0.002709754,0.008029607,0.01315012,0.000141287,0.00007683662,0.0001572705,0.00001114005,0.0005534829],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9790122,"threshold_uncertainty_score":0.8506821,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Tong Wang","is_ca":true},{"name":"Graeme Hirst","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01337281418878432,"gpt":0.2994146677861813,"spread":0.286041853597397,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002352091,0.0002896176,0.0002772771,0.0002920449,0.0002550044,0.0003080382,0.0009493245,0.0001301406,0.00002431883],"category_scores_gemma":[0.0003374543,0.0002571397,0.0000644168,0.001199755,0.0000403923,0.004279867,0.0001408174,0.0007929863,0.00001097075],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002717476,"about_ca_system_score_gemma":0.00008543213,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000183126,"about_ca_topic_score_gemma":0.00003742998,"domain_scores_codex":[0.9978722,0.00007496239,0.0004382514,0.0006681053,0.0004406123,0.0005059196],"domain_scores_gemma":[0.9989592,0.0001817318,0.0002608396,0.0003822668,0.0001301172,0.00008587803],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001436785,0.00006992924,0.0001243367,0.00002091202,0.000002327952,0.0001169552,0.000896527,0.00002379602,0.004587837,0.00199544,0.00002328068,0.9921243],"study_design_scores_gemma":[0.003441852,0.0004101114,0.00355306,0.005940855,0.00007914138,0.0007514289,0.002809618,0.2304377,0.1032594,0.6130426,0.03124671,0.005027491],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.004198855,0.8090996,0.1799401,0.001893814,0.0005180131,0.0002346625,0.000006987914,0.001483055,0.002624962],"genre_scores_gemma":[0.6232747,0.002929722,0.3729249,0.0006284238,0.0001475991,0.00001194687,0.00003257048,0.00001222051,0.00003797449],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.9870968,"threshold_uncertainty_score":0.9999881,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; WordNet; Intuition; Artificial intelligence; Natural language processing; Decision tree; Machine learning","authors":[{"name":"Marek Maziarz","is_ca":false},{"name":"Stan Śzpakowicz","is_ca":true},{"name":"Maciej Piasecki","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03623442409141529,"gpt":0.3289595941006193,"spread":0.292725170009204,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004600501,0.0002775185,0.0003574443,0.0003363328,0.00007073573,0.0001206143,0.0009731798,0.0001393747,0.000003655554],"category_scores_gemma":[0.001105041,0.0002293172,0.00004225884,0.00219897,0.0001199032,0.00271945,0.0002852715,0.0005594852,0.000004148836],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001951417,"about_ca_system_score_gemma":0.0003270837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001425768,"about_ca_topic_score_gemma":0.00006877617,"domain_scores_codex":[0.997839,0.0001033188,0.0005143959,0.0005146854,0.0005545335,0.0004741055],"domain_scores_gemma":[0.9985509,0.00007072077,0.0003377952,0.0003147085,0.0005949316,0.0001309461],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006156546,0.0001060885,0.0002940295,0.0002558899,0.000003426134,0.00005682912,0.00308899,0.00002437791,0.001965499,0.003605753,0.00003086787,0.9905067],"study_design_scores_gemma":[0.01389665,0.001031911,0.0007487872,0.009619504,0.00009884024,0.001269508,0.01144612,0.4377393,0.3253914,0.1745674,0.01811138,0.006079225],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.01422789,0.8196678,0.1624133,0.0006625457,0.0005673078,0.0005065225,0.00000553168,0.0009608521,0.0009882735],"genre_scores_gemma":[0.5789875,0.0004634137,0.4202579,0.0001704918,0.00004643788,0.00001810968,0.00001405739,0.00001490016,0.00002726322],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.9844275,"threshold_uncertainty_score":0.9351283,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Sentiment analysis; Computer science; Natural language processing; Artificial intelligence; Information retrieval","authors":[{"name":"Canberk Özdemir","is_ca":false},{"name":"Sabine Bergler","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03576092369102291,"gpt":0.3703291697388255,"spread":0.3345682460478026,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003719159,0.0001988265,0.000765913,0.0006078776,0.00005114312,0.00005476748,0.0004639162,0.00003281472,0.000008433146],"category_scores_gemma":[0.00003619632,0.0001534272,0.0001486825,0.001867893,0.00003606261,0.0005308392,0.0001777066,0.0001042984,4.495575e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001010164,"about_ca_system_score_gemma":0.00003869703,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001214638,"about_ca_topic_score_gemma":0.0001127532,"domain_scores_codex":[0.9979528,0.000107136,0.0006672195,0.0004394108,0.0005767819,0.0002566557],"domain_scores_gemma":[0.9986869,0.000106006,0.0005642933,0.0002935871,0.0002778351,0.00007141897],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005549055,0.006887149,0.1030045,0.0004359225,0.003024674,0.00002184918,0.1826612,0.03629602,0.006705286,0.0008072405,0.00008508964,0.6595162],"study_design_scores_gemma":[0.003338301,0.0005371374,0.005268458,0.0002350489,0.0007574874,9.984141e-7,0.03012868,0.9332064,0.02539492,0.0001826678,0.0004729143,0.0004769496],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9227831,0.04868452,0.02727013,0.00006996913,0.0002915357,0.0006407799,0.000004714006,0.00003633404,0.000218881],"genre_scores_gemma":[0.9913185,0.000105264,0.008423876,0.00001569826,0.00002292353,0.00002867718,0.0000252106,0.000005792424,0.00005406405],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8969104,"threshold_uncertainty_score":0.6256579,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Fatiha Sadat","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.006752702082397749,"gpt":0.2728687706527462,"spread":0.2661160685703484,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003248471,0.0003150612,0.0003452597,0.000275704,0.0001463172,0.0004351035,0.0006131161,0.00009012363,0.00001881183],"category_scores_gemma":[0.0001645604,0.0002489628,0.00003495259,0.0006292065,0.00009623711,0.002444832,0.0001147288,0.0005241178,0.000006385284],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001921626,"about_ca_system_score_gemma":0.0001048094,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001059157,"about_ca_topic_score_gemma":0.00003794123,"domain_scores_codex":[0.9978349,0.0001191112,0.0004477953,0.0006443922,0.0004654703,0.0004883799],"domain_scores_gemma":[0.9990893,0.0001375468,0.0001946103,0.0002904391,0.0001697919,0.0001182928],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001088728,0.00002766911,0.0001539395,0.0004964671,0.00000238542,0.00005503149,0.0003764419,0.00001372045,0.000646623,0.0009497409,0.000009199497,0.9972579],"study_design_scores_gemma":[0.001172859,0.00008207263,0.0005305472,0.00115929,0.00001648938,0.0001742428,0.0001768124,0.9739838,0.01150168,0.009084284,0.001295402,0.0008225795],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002920012,0.4727079,0.5222972,0.0005383185,0.000173392,0.0003924618,0.00000846582,0.0006482333,0.0003140473],"genre_scores_gemma":[0.5691624,0.0003018267,0.4302751,0.0001297218,0.0000357746,0.00004455407,0.00002557773,0.00001447799,0.00001062868],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9964353,"threshold_uncertainty_score":0.9999962,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Zhenisbek Assylbekov","is_ca":true},{"name":"Assulan Nurkas","is_ca":false},{"name":"Inês Russinho Mouga","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03928171059953837,"gpt":0.3505640517397068,"spread":0.3112823411401684,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007316886,0.000352984,0.0004514612,0.0002490874,0.0001764213,0.0003256652,0.001189473,0.0001583949,0.000002336149],"category_scores_gemma":[0.001160381,0.0002966516,0.00005848223,0.0006586929,0.0001007385,0.002891917,0.0003455554,0.000640359,0.000001481232],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003526289,"about_ca_system_score_gemma":0.0002663356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008345354,"about_ca_topic_score_gemma":0.00005534052,"domain_scores_codex":[0.9973401,0.0000868943,0.0004994692,0.0007464501,0.0006120742,0.0007149944],"domain_scores_gemma":[0.998624,0.0002110172,0.0002386282,0.0003631389,0.0003637637,0.0001994669],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005355318,0.00001944196,0.001011107,0.0002536596,0.000006176904,0.00002752576,0.002385884,0.0006280111,0.0002898454,0.002732604,0.00005419582,0.992538],"study_design_scores_gemma":[0.0009124437,0.00005342215,0.0000819079,0.0002529952,0.0000156672,0.00002360004,0.0002431011,0.9193919,0.004611324,0.07322766,0.0005789079,0.0006071197],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00307002,0.2195458,0.7755873,0.000401941,0.0002379502,0.0004008053,0.00002310989,0.0006076464,0.0001254508],"genre_scores_gemma":[0.5257224,0.0001053799,0.4738537,0.0001090471,0.0001061693,0.0000293722,0.0000264472,0.00001900534,0.00002846334],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9919309,"threshold_uncertainty_score":0.9999486,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}