{"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10747654,0.003495861,0.87149024,0.00073485816,0.0003736606,0.00052806776,0.0032788145,0.0019252981,0.010696642],"genre_scores_gemma":[0.19234328,0.0019915057,0.7953666,0.0001878141,0.0001206755,0.0002477057,0.006198232,0.00035580402,0.003188408],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9973924,0.0008701538,0.0004804314,0.0005695848,0.00061995175,0.000067411354],"domain_scores_gemma":[0.99150497,0.004706785,0.0010305393,0.0012395896,0.0013823644,0.0001357828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016925136,0.00078318163,0.00093841687,0.0060366997,0.0007368438,0.0018837175,0.0011625272,0.00070961326,0.0038418083],"category_scores_gemma":[0.014098249,0.00053539895,0.00079328596,0.005171304,0.0007602481,0.00480203,0.0021987276,0.0008128908,0.0022626885],"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":[0.00015084239,0.0001751619,0.010100598,0.0032937033,0.00022938484,0.0015297537,0.0026251406,0.004501699,0.03878283,0.0500707,0.010372473,0.87816775],"study_design_scores_gemma":[0.00019635251,0.00066030776,0.02486468,0.0014767309,0.0004524961,0.011682722,0.0077560274,0.17757018,0.17285423,0.15925564,0.44291523,0.00031545636],"about_ca_topic_score_codex":0.00046020062,"about_ca_topic_score_gemma":0.0011191617,"teacher_disagreement_score":0.0060366997,"about_ca_system_score_codex":0.00042102108,"about_ca_system_score_gemma":0.000975082,"threshold_uncertainty_score":0.012852132},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06801297,0.020627018,0.75269884,0.017691584,0.0018069282,0.00024666957,0.0009060086,0.0013089532,0.13670105],"genre_scores_gemma":[0.63319135,0.011159034,0.33170703,0.0018407069,0.0012054872,0.000493242,0.0015581347,0.000853185,0.017991913],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9975777,0.001327453,0.0001388153,0.00036275422,0.00045501246,0.00013834877],"domain_scores_gemma":[0.99524045,0.0027100628,0.00040815005,0.0007413118,0.00062303507,0.00027706506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040845457,0.00093786314,0.001074031,0.006172776,0.0027389769,0.00705978,0.0017056843,0.0020728824,0.007441776],"category_scores_gemma":[0.013165693,0.0004061795,0.0008318539,0.007909585,0.006519688,0.025694797,0.004417378,0.002568766,0.0015059478],"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":[0.00006908691,0.00003065193,0.0008566981,0.00015221308,0.000031071475,0.000118277385,0.00057711813,0.0020039044,0.00046289366,0.94830066,0.002657265,0.04474027],"study_design_scores_gemma":[0.0000077768345,0.000041243045,0.00060823513,0.00011883793,0.000018158615,0.00027794184,0.00057991315,0.01628547,0.0009659378,0.94824064,0.032833543,0.000022307062],"about_ca_topic_score_codex":0.0018134157,"about_ca_topic_score_gemma":0.0026929842,"teacher_disagreement_score":0.007441776,"about_ca_system_score_codex":0.002088344,"about_ca_system_score_gemma":0.001249616,"threshold_uncertainty_score":0.02489525},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9604774,0.0010957258,0.011660655,0.003910153,0.00020825719,0.00025393176,0.015401359,0.00022920639,0.0067633046],"genre_scores_gemma":[0.95482016,0.0009794009,0.021093963,0.0004560307,0.00031326155,0.00025550576,0.017886292,0.000059349248,0.0041360725],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992021,0.00016885388,0.00014055707,0.00016653037,0.00022074235,0.00010125375],"domain_scores_gemma":[0.99644595,0.001938569,0.00083362905,0.00022442534,0.00038828177,0.00016917975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00081719935,0.00041699962,0.00033988972,0.0046494817,0.0008643738,0.0011501614,0.00044037995,0.00091890164,0.0013592442],"category_scores_gemma":[0.006165479,0.0002469923,0.00051713735,0.004687574,0.00042169305,0.0024135686,0.00081257493,0.00059755205,0.00094572944],"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":[0.00084166066,0.00053218106,0.7151824,0.001243806,0.0003599966,0.0029095986,0.007953608,0.0050801053,0.018305501,0.0047349324,0.027826888,0.2150293],"study_design_scores_gemma":[0.00006181645,0.00031993876,0.7398688,0.0004049175,0.00039505053,0.0031633968,0.024619102,0.11166785,0.0125840055,0.013403835,0.093344115,0.00016717604],"about_ca_topic_score_codex":0.006841688,"about_ca_topic_score_gemma":0.016394133,"teacher_disagreement_score":0.006841688,"about_ca_system_score_codex":0.00054111856,"about_ca_system_score_gemma":0.0005099008,"threshold_uncertainty_score":0.013603747},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98849726,0.0006226515,0.0055244993,0.0001291813,0.00004199674,0.000022701977,0.00048692105,0.0000385008,0.00463629],"genre_scores_gemma":[0.9935666,0.00026286457,0.004369452,0.000028075812,0.000018238294,0.000023347564,0.0009976354,0.00002248431,0.00071141095],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992299,0.000353111,0.0001000767,0.00013761138,0.000106876265,0.00007245471],"domain_scores_gemma":[0.9986802,0.0006906112,0.00028072158,0.00006836435,0.00023983537,0.000040162045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066390703,0.00025627823,0.00025974872,0.0018293512,0.0003848037,0.0007631287,0.00017386596,0.00019977675,0.0011370796],"category_scores_gemma":[0.0029668375,0.00009151538,0.00038069027,0.0013053206,0.0004854683,0.00096366764,0.0005085873,0.0004229713,0.00042266233],"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":[0.0020205274,0.00029220685,0.42950547,0.0011481195,0.0003041065,0.0016353526,0.020790452,0.005994046,0.099381365,0.01742468,0.00438354,0.41712013],"study_design_scores_gemma":[0.00007304696,0.00069856824,0.8651155,0.00030006663,0.00020168202,0.0035816974,0.020539518,0.047418293,0.021388585,0.008212774,0.03235018,0.000120096425],"about_ca_topic_score_codex":0.0014250475,"about_ca_topic_score_gemma":0.0009235585,"teacher_disagreement_score":0.0018293512,"about_ca_system_score_codex":0.0003515631,"about_ca_system_score_gemma":0.00018064203,"threshold_uncertainty_score":0.0038039088},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9383897,0.0050681587,0.011333013,0.008086378,0.00070938445,0.00010754278,0.0034980755,0.00026533607,0.032542303],"genre_scores_gemma":[0.98995715,0.0012830772,0.004389472,0.00058095227,0.00058612996,0.000039114577,0.0008744371,0.00006927392,0.0022203068],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987036,0.000565619,0.00010687744,0.00015155012,0.00033948384,0.00013293832],"domain_scores_gemma":[0.98837364,0.006431619,0.0029271515,0.0003026506,0.0014353709,0.00052953284],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002326291,0.00027669818,0.00028166888,0.0032003422,0.0006244402,0.0016975768,0.00012788728,0.00041086224,0.0033651679],"category_scores_gemma":[0.013619452,0.00014467395,0.00025973708,0.00135986,0.00047167117,0.002073872,0.0006217672,0.0003348061,0.00084802986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011339667,0.00022999008,0.47192508,0.001890041,0.00039596445,0.0014865096,0.024829648,0.00068017264,0.039733883,0.007558876,0.027730357,0.4224055],"study_design_scores_gemma":[0.00006920555,0.00048500087,0.81420213,0.0014243084,0.00038902886,0.0031860566,0.023558695,0.009420719,0.010132159,0.016875163,0.12008475,0.00017284606],"about_ca_topic_score_codex":0.00047758766,"about_ca_topic_score_gemma":0.0008732674,"teacher_disagreement_score":0.0033651679,"about_ca_system_score_codex":0.00033096576,"about_ca_system_score_gemma":0.00022096779,"threshold_uncertainty_score":0.012302756},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030804338,0.00057517656,0.94333273,0.00029422817,0.00015757987,0.00022220523,0.0004929796,0.020503594,0.0036170997],"genre_scores_gemma":[0.15866129,0.00026640255,0.8334328,0.00029828073,0.00011748061,0.00023872702,0.0016088007,0.00033146143,0.005044699],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993771,0.00014400527,0.00009140412,0.00019086497,0.00016124395,0.00003550105],"domain_scores_gemma":[0.999201,0.00017127345,0.000049977265,0.00010094896,0.0004360989,0.000040642975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010120074,0.0007286949,0.0008844508,0.0010317911,0.00062961754,0.0014411316,0.0008685353,0.0009949697,0.0024578646],"category_scores_gemma":[0.0013021365,0.0003812601,0.0006612215,0.00075597485,0.00036247825,0.0009271137,0.00068029884,0.00065768906,0.0036968146],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037588403,0.0003149104,0.0029539242,0.00033163233,0.00028211108,0.0011027467,0.0002447088,0.044646848,0.2002144,0.009609201,0.011496195,0.72842747],"study_design_scores_gemma":[0.00007764564,0.00028947133,0.002161464,0.00004480887,0.00022093717,0.00096409686,0.00009473598,0.8816633,0.083215095,0.0052043535,0.025986187,0.00007785668],"about_ca_topic_score_codex":0.003873786,"about_ca_topic_score_gemma":0.0035653168,"teacher_disagreement_score":0.003873786,"about_ca_system_score_codex":0.00040287754,"about_ca_system_score_gemma":0.0009951224,"threshold_uncertainty_score":0.008222342},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93485725,0.002347174,0.035323624,0.0005831309,0.00015521515,0.00021482557,0.0030686932,0.00043207937,0.02301795],"genre_scores_gemma":[0.952366,0.0013366468,0.03926075,0.000098647964,0.00011261396,0.00013875168,0.0043372125,0.00019209956,0.0021572427],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987985,0.0005737917,0.00014511267,0.00009573012,0.00030346675,0.000083291314],"domain_scores_gemma":[0.9922071,0.004871798,0.00038190963,0.00023977576,0.0020859863,0.00021344775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016946574,0.00028041942,0.000308197,0.004585302,0.0008016652,0.0017828625,0.00022628739,0.00030093436,0.003053707],"category_scores_gemma":[0.008923487,0.00013297751,0.00061963696,0.0038617328,0.00049820956,0.0021931932,0.00053072395,0.00039353952,0.0009299678],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005585454,0.000885453,0.16430928,0.0035556355,0.00073659304,0.0008629082,0.009145123,0.0021197994,0.15972207,0.0184591,0.012286818,0.62233174],"study_design_scores_gemma":[0.0005082184,0.003310381,0.6336344,0.0011532098,0.0025581531,0.0039087795,0.038193136,0.11788017,0.099661544,0.022231825,0.076522276,0.0004380277],"about_ca_topic_score_codex":0.0017458735,"about_ca_topic_score_gemma":0.0031336646,"teacher_disagreement_score":0.004585302,"about_ca_system_score_codex":0.0005578285,"about_ca_system_score_gemma":0.00049964886,"threshold_uncertainty_score":0.01021564},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0044724387,0.0005816506,0.9712195,0.0018947044,0.00055519486,0.00026778068,0.00053983444,0.000489648,0.019979201],"genre_scores_gemma":[0.14609542,0.00044653934,0.8411563,0.0015084049,0.00037649012,0.0013564993,0.0007008374,0.000602998,0.007756425],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9949673,0.0021247808,0.00070715236,0.001212503,0.0007601455,0.00022814369],"domain_scores_gemma":[0.99357903,0.0025062286,0.0006357891,0.001791612,0.0012529601,0.00023433975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049678446,0.0009005097,0.00082938524,0.002809675,0.0027613607,0.0061667617,0.0031491076,0.0021170639,0.010086911],"category_scores_gemma":[0.016169272,0.00081609393,0.001000706,0.003047774,0.010144661,0.012842801,0.0038588706,0.0053085736,0.004493249],"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":[0.000027979584,0.000015739011,0.00024334798,0.0000934429,0.000009699956,0.000055652858,0.0010986617,0.00032465506,0.001842315,0.9720196,0.002738281,0.021530565],"study_design_scores_gemma":[0.000017327397,0.000055844674,0.0005041983,0.00018715177,0.000019165069,0.0004704044,0.0007104517,0.0062531824,0.0032658533,0.815102,0.17336805,0.00004634921],"about_ca_topic_score_codex":0.0007153494,"about_ca_topic_score_gemma":0.001068117,"teacher_disagreement_score":0.010086911,"about_ca_system_score_codex":0.0010390803,"about_ca_system_score_gemma":0.0015732604,"threshold_uncertainty_score":0.033744097},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10291558,0.001737843,0.44565478,0.0021291038,0.0010572575,0.0025149637,0.3082911,0.025386617,0.110312805],"genre_scores_gemma":[0.19034919,0.0016515412,0.32867277,0.0004432782,0.0001765566,0.0036718247,0.43577352,0.0058696154,0.03339174],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993412,0.00011650401,0.00018316403,0.00015753869,0.00016295112,0.000038500846],"domain_scores_gemma":[0.9986388,0.00032193682,0.00018805577,0.00019898103,0.0005523689,0.000099821395],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00093859166,0.0010211325,0.00050700334,0.0047492436,0.0009992822,0.0017615176,0.00061593985,0.0004694656,0.01625445],"category_scores_gemma":[0.0046711755,0.0007210153,0.0005030768,0.003779347,0.00046298385,0.004994878,0.0020771734,0.0009577815,0.014004831],"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":[0.0006322758,0.00019133915,0.008574314,0.004704412,0.00011661077,0.0015931835,0.006006107,0.0036609673,0.058364503,0.08089661,0.33407623,0.50118345],"study_design_scores_gemma":[0.00004967387,0.000064051506,0.009548044,0.0003744931,0.00006601266,0.00095379195,0.001067053,0.00856407,0.011507248,0.019286746,0.94846356,0.00005532633],"about_ca_topic_score_codex":0.0029819314,"about_ca_topic_score_gemma":0.005476093,"teacher_disagreement_score":0.01625445,"about_ca_system_score_codex":0.00085121795,"about_ca_system_score_gemma":0.0022378347,"threshold_uncertainty_score":0.054376543},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049894128,0.00018720141,0.94625837,0.00023617558,0.000033867535,0.00011482223,0.0006827622,0.00103252,0.0015601994],"genre_scores_gemma":[0.75218236,0.00046265114,0.2375225,0.0003341252,0.00020020257,0.0009045416,0.0032999814,0.0003433567,0.004750206],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99772996,0.0006042411,0.00014588468,0.0006109598,0.000779711,0.00012918786],"domain_scores_gemma":[0.9927382,0.0038325107,0.0011188142,0.0009972011,0.0011360688,0.0001772135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002785242,0.00079248054,0.0009879731,0.0044171326,0.00053166447,0.0013819173,0.0018104782,0.0015360424,0.0019057818],"category_scores_gemma":[0.014038479,0.00060548796,0.0013734272,0.002715086,0.0012698361,0.0037568714,0.00090857106,0.0015922383,0.002039571],"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":[0.0005636811,0.0008825797,0.04529995,0.00044389095,0.00065853127,0.0008334274,0.00072935736,0.5388482,0.045206774,0.12420349,0.007738075,0.23459198],"study_design_scores_gemma":[0.000010401392,0.00009926474,0.0056829634,0.000013793647,0.00004124791,0.00025432114,0.000033302458,0.95966125,0.0019512137,0.03100012,0.0012160118,0.000036057405],"about_ca_topic_score_codex":0.0035299337,"about_ca_topic_score_gemma":0.0031017074,"teacher_disagreement_score":0.0044171326,"about_ca_system_score_codex":0.0010925423,"about_ca_system_score_gemma":0.0012228696,"threshold_uncertainty_score":0.014729917},"labels":[],"label_agreement":null}]}