{"meta":{"query_hash":"57531d6a651c","filters":{"venue":"The COCOON platform (University of Paris)"},"cohort_total":59,"direct_labels_cover":0,"predictions_cover":59,"exported":59,"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/57531d6a651c","api":"https://metacan.xera.ac/api/v1/cohort?venue=The+COCOON+platform+%28University+of+Paris%29"},"results":[{"id":"W2224144213","doi":"","title":"Diachronic change in procedural semantic content","year":2015,"lang":"fr","type":"article","venue":"The COCOON platform (University of Paris)","topic":"Linguistics and Discourse Analysis","field":"Arts and Humanities","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trinity Western University","funders":"","keywords":"Grammaticalization; Procedural memory; Computer science; Inference; Linguistics; Natural language processing; Semantics (computer science); Procedural knowledge; Cognitive psychology; Artificial intelligence; Psychology; Cognition; Knowledge base; Programming language; Philosophy","score_opus":0.16975009993385642,"score_gpt":0.2646538416475659,"score_spread":0.09490374171370947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2224144213","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":[0.84096897,0.021577474,0.00007558893,0.014625653,0.001359539,0.00078240834,0.00014243806,0.00003836039,0.12042955],"genre_scores_gemma":[0.9688168,0.0011658154,0.000016477943,0.00013919023,0.00064663915,8.75618e-7,0.000026478117,0.000010865503,0.029176816],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99900424,0.000034521483,0.00018474966,0.00018095467,0.0002582713,0.0003372469],"domain_scores_gemma":[0.9990694,0.000058892492,0.00020704156,0.00025361447,0.000286252,0.00012482837],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003999599,0.0001658412,0.00034825664,0.00013371174,0.00029840722,0.00005808724,0.00034183392,0.00008602346,0.0010406824],"category_scores_gemma":[0.00003720797,0.00014713935,0.00014229366,0.00013084972,0.0006215419,0.00037116336,0.00015975999,0.00021871194,0.000260457],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019259375,0.00041977086,0.0033891967,0.00031139515,0.00027842654,0.00008286911,0.13251612,0.00011207798,0.0000041368735,0.8462753,0.013702435,0.0027156165],"study_design_scores_gemma":[0.0042226813,0.00063762383,0.0092964275,0.0009204619,0.0015758561,0.000012374318,0.34115672,0.039024346,0.00002098771,0.011091216,0.5912069,0.00083436776],"about_ca_topic_score_codex":0.060396377,"about_ca_topic_score_gemma":0.043067843,"teacher_disagreement_score":0.83518416,"about_ca_system_score_codex":0.00015621171,"about_ca_system_score_gemma":0.00016190672,"threshold_uncertainty_score":0.9998725},"labels":[],"label_agreement":null},{"id":"W2239197541","doi":"","title":"Beautiful words: Enriching language revitalization through understandings of linguistic structure","year":2015,"lang":"en","type":"article","venue":"The COCOON platform (University of Paris)","topic":"Discourse Analysis in Language Studies","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Linguistics; Meaning (existential); Morpheme; Literal and figurative language; Sociology; Psychology; Philosophy","score_opus":0.04612649789817787,"score_gpt":0.25108835665032275,"score_spread":0.2049618587521449,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2239197541","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":[0.74781954,0.0032167137,0.0067074765,0.00043652861,0.00046331907,0.00034998453,0.00011824898,0.000092215,0.24079598],"genre_scores_gemma":[0.9966316,0.00006176004,0.00020311952,0.000034235116,0.0001113753,9.054779e-8,0.0000344009,0.000008389862,0.002915024],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9993113,0.000024268424,0.0001424894,0.00012206016,0.00026478045,0.00013506223],"domain_scores_gemma":[0.99919766,0.00007037,0.00027034318,0.00023336006,0.00019887721,0.000029403644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020767908,0.00011037367,0.00025935468,0.00007469732,0.0002813066,0.00002922551,0.00028211958,0.000036604637,0.00052443985],"category_scores_gemma":[0.0000940594,0.00008835615,0.00008162366,0.00012622045,0.0005453578,0.0003124786,0.00011892853,0.000108780936,0.0000083848445],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041943946,0.000023404615,0.00012391193,0.000065018765,0.0001974651,0.0000072171483,0.61662567,0.000082951236,0.000049459148,0.37963295,0.002861332,0.0002886987],"study_design_scores_gemma":[0.0005861555,0.0000913392,0.000056947243,0.00015968987,0.00051897817,0.0000018612119,0.95746166,0.00066636293,0.000116685405,0.026690444,0.013440412,0.00020949075],"about_ca_topic_score_codex":0.0018778084,"about_ca_topic_score_gemma":0.0035596206,"teacher_disagreement_score":0.3529425,"about_ca_system_score_codex":0.000055143897,"about_ca_system_score_gemma":0.000036640376,"threshold_uncertainty_score":0.5742248},"labels":[],"label_agreement":null},{"id":"W2726154201","doi":"","title":"Giving back to the language community: lessons from the Kiowa and Ojibwe peoples","year":2017,"lang":"en","type":"article","venue":"The COCOON platform (University of Paris)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Commit; Tribe; Linguistics; History; Computer science; Sociology; Anthropology; Philosophy","score_opus":0.033979421795715836,"score_gpt":0.269982291153701,"score_spread":0.23600286935798515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2726154201","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":[0.8219788,0.0019377185,0.11845385,0.054037303,0.00015172632,0.0005292957,0.00004626176,0.00022146168,0.0026435868],"genre_scores_gemma":[0.9784165,0.000091811,0.020409705,0.00043211607,0.000030328496,4.797488e-7,0.000002892438,0.0000056431177,0.00061054557],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99927855,0.00009748413,0.00007639615,0.00015991552,0.00020102666,0.00018663364],"domain_scores_gemma":[0.9973256,0.00069238886,0.00019673065,0.0016684434,0.00006566879,0.000051183757],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00074356224,0.00011577786,0.00015477854,0.000031358722,0.002703009,0.00031641248,0.004701423,0.000060616352,0.000025507085],"category_scores_gemma":[0.00015753003,0.000067481196,0.00004757048,0.00013711337,0.00030147098,0.0006810781,0.002706722,0.00044944754,0.00003130676],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014532743,0.00013910815,0.0064225853,0.00014769055,0.00024988776,0.00005569513,0.5006143,0.000023406337,0.008094291,0.12477003,0.047941465,0.31139624],"study_design_scores_gemma":[0.003595684,0.0006920339,0.3927721,0.0023618578,0.000487078,0.00014352206,0.31359857,0.038439542,0.019537041,0.1382386,0.08744205,0.00269192],"about_ca_topic_score_codex":0.0134200035,"about_ca_topic_score_gemma":0.013257415,"teacher_disagreement_score":0.3863495,"about_ca_system_score_codex":0.000024453868,"about_ca_system_score_gemma":0.000045205597,"threshold_uncertainty_score":0.99859536},"labels":[],"label_agreement":null},{"id":"W2735679914","doi":"","title":"From Archives to Augmented Realities: Feeling, Seeing, and Hearing the Language on Screen","year":2017,"lang":"en","type":"article","venue":"The COCOON platform (University of Paris)","topic":"Multilingual Education and Policy","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Documentation; Context (archaeology); Globalization; Indigenous; Sociology; Media studies; Digitization; Indigenous language; Thriving; World Wide Web; Public relations; Political science; Social science; History; Computer science; Law","score_opus":0.09300980796362546,"score_gpt":0.3872068443309521,"score_spread":0.29419703636732664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2735679914","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":[0.9115389,0.000039698087,0.0000611081,0.0073363422,0.00008191692,0.00018610175,0.000023089417,0.000021741991,0.08071109],"genre_scores_gemma":[0.98810136,0.00010386789,0.00014224747,0.00033668012,0.0001461596,2.5809564e-7,0.000005042494,0.000003535219,0.011160823],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99948186,0.000049495655,0.00005625858,0.00011072573,0.0001517626,0.00014991556],"domain_scores_gemma":[0.999191,0.00025188836,0.00010926385,0.0003349701,0.00002194641,0.000090942776],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00032903362,0.000059541635,0.00009276747,0.000038436316,0.0019676506,0.0000798125,0.00053388305,0.00003502793,0.00014855979],"category_scores_gemma":[0.00014557801,0.000045703222,0.000032104872,0.00004541661,0.00039831718,0.00012947198,0.00014132731,0.000116465184,0.000026597902],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014616484,0.00002677945,0.0017824388,0.0000072900425,0.000040833675,0.0000020345665,0.93605894,0.000016605469,0.00017402244,0.022507934,0.003969973,0.035266995],"study_design_scores_gemma":[0.00054525986,0.000057589594,0.091499195,0.00013504708,0.00004025591,3.409793e-7,0.6797986,0.0007008173,0.0001762134,0.0016748338,0.22519626,0.00017556461],"about_ca_topic_score_codex":0.19765349,"about_ca_topic_score_gemma":0.016329426,"teacher_disagreement_score":0.2562603,"about_ca_system_score_codex":0.000021151203,"about_ca_system_score_gemma":0.0000763521,"threshold_uncertainty_score":0.99933165},"labels":[],"label_agreement":null},{"id":"W2735947388","doi":"","title":"Mentor-Apprentice Programs: Effects on Mentors & Apprentices’ wellbeing","year":2017,"lang":"en","type":"article","venue":"The COCOON platform (University of Paris)","topic":"Indigenous Health, Education, and Rights","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Apprenticeship; Indigenous; Thematic analysis; Indigenous language; Psychology; Exploratory research; Pedagogy; Sociology; Qualitative research; Geography; Social science","score_opus":0.02125505077756707,"score_gpt":0.27364112289632625,"score_spread":0.2523860721187592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2735947388","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":[0.76866335,0.000054247783,0.00008575151,0.0005243406,0.0008037821,0.0008986787,0.0000015226872,0.00005228105,0.22891603],"genre_scores_gemma":[0.97543937,0.0013547031,0.00014917183,0.000014574614,0.00021972072,5.0654717e-7,0.000009078841,0.000008228531,0.022804642],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.99866045,0.00011380221,0.000113608534,0.00021337457,0.0004658052,0.00043297122],"domain_scores_gemma":[0.9986308,0.00016878519,0.00040440136,0.00051737594,0.00012295543,0.00015567917],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00102792,0.00012025542,0.00018534568,0.00007060499,0.015060998,0.00012833513,0.0010172382,0.00012054865,0.00008599411],"category_scores_gemma":[0.000009956062,0.00009999089,0.00008997159,0.00012227858,0.00053433503,0.0006154406,0.000014484846,0.00017801541,0.00011380046],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013384869,0.00037436615,0.0035578208,0.00022413547,0.00012878937,0.0000072300063,0.7244038,0.000003901821,0.000013718713,0.25939035,0.00085175456,0.0109102875],"study_design_scores_gemma":[0.0008771288,0.00023825793,0.008775067,0.00026272653,0.00019180396,6.3180477e-7,0.056224443,0.00009734498,0.00035528236,0.0025096554,0.93017334,0.00029433152],"about_ca_topic_score_codex":0.077707164,"about_ca_topic_score_gemma":0.22258161,"teacher_disagreement_score":0.9293216,"about_ca_system_score_codex":0.00017084055,"about_ca_system_score_gemma":0.0010954444,"threshold_uncertainty_score":0.98622125},"labels":[],"label_agreement":null},{"id":"W2736098086","doi":"","title":"Community-based corpus-building: Three case studies","year":2017,"lang":"en","type":"article","venue":"The COCOON platform (University of Paris)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Lemmatisation; Linguistics; Corpus linguistics; Annotation; Focus (optics); Ethos; Narrative; Documentation; Artificial intelligence; Natural language processing","score_opus":0.07443160432197264,"score_gpt":0.3087848184024849,"score_spread":0.23435321408051224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2736098086","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":[0.47276258,0.0013859583,0.5206815,0.0031048951,0.00020902493,0.00036194865,0.000008627827,0.00051575765,0.00096973573],"genre_scores_gemma":[0.88064843,0.000027320484,0.11906308,0.0001072903,0.000011730658,4.182457e-7,0.000001294618,0.000005448208,0.00013500695],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99925154,0.000055036984,0.000104250365,0.00016773408,0.0002134734,0.00020793689],"domain_scores_gemma":[0.99742293,0.0002456174,0.0003844185,0.0016458472,0.00024619946,0.00005499604],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0008351031,0.00013809494,0.00023922125,0.00009041883,0.0030174435,0.00012588705,0.0034168148,0.0000801934,0.0000052171154],"category_scores_gemma":[0.00011012451,0.0001140284,0.00007857718,0.0001553951,0.00058924675,0.0010106759,0.001546129,0.00047189672,0.000008803985],"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":[0.00042407255,0.0005769171,0.005235475,0.0010527262,0.0006965355,0.0069448394,0.035328496,0.00015274774,0.0067307088,0.6428419,0.019810956,0.28020468],"study_design_scores_gemma":[0.006084818,0.0015139704,0.004308649,0.0014842821,0.0005202856,0.0024669012,0.013632587,0.14274515,0.050020114,0.75902724,0.015701964,0.0024940267],"about_ca_topic_score_codex":0.0015749275,"about_ca_topic_score_gemma":0.0012183235,"teacher_disagreement_score":0.40788585,"about_ca_system_score_codex":0.000060734314,"about_ca_system_score_gemma":0.00006643491,"threshold_uncertainty_score":0.99828047},"labels":[],"label_agreement":null},{"id":"W2773922654","doi":"","title":"Seeing Speech: A Pronunciation Toolkit for Indigenous Language Teaching and Learning","year":2017,"lang":"en","type":"article","venue":"The COCOON platform (University of Paris)","topic":"Subtitles and Audiovisual Media","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Pronunciation; Indigenous; Linguistics; Context (archaeology); First language; Indigenous language; Computer science; Psychology; History","score_opus":0.035544309952787324,"score_gpt":0.24024908111457746,"score_spread":0.20470477116179014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2773922654","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":[0.9836829,0.00010577843,0.00023839842,0.00016460729,0.00009010838,0.0002442852,0.000008837334,0.000026059917,0.015439055],"genre_scores_gemma":[0.9901712,0.000020146133,0.00027235228,0.00002099348,0.00014113491,4.780966e-7,0.000009292858,0.0000064803985,0.009357957],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9996292,0.000015415959,0.00005446302,0.00008837794,0.000088025285,0.00012453528],"domain_scores_gemma":[0.9995097,0.00011508725,0.00017891046,0.00013326362,0.00003801832,0.000025022975],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00042836787,0.00006244724,0.000112400165,0.00003312268,0.0025590924,0.00010696176,0.00018227691,0.000030168796,0.00010119731],"category_scores_gemma":[0.000102887505,0.000052869967,0.00003815932,0.000005940588,0.000128942,0.00035543856,0.0000802364,0.00019242639,0.000010377074],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001145642,0.00003863468,0.0018022764,0.0001353856,0.00008289163,0.000009972093,0.75691104,0.000009770356,0.0005376942,0.025266487,0.0006387516,0.21445252],"study_design_scores_gemma":[0.0024627529,0.00061748875,0.013003796,0.00029645883,0.0002814092,0.000010777073,0.65582925,0.0057218117,0.00039805,0.002384928,0.318438,0.00055530854],"about_ca_topic_score_codex":0.0020933526,"about_ca_topic_score_gemma":0.0021074768,"teacher_disagreement_score":0.31779924,"about_ca_system_score_codex":0.00001949962,"about_ca_system_score_gemma":0.00001819175,"threshold_uncertainty_score":0.9987394},"labels":[],"label_agreement":null},{"id":"W6890004888","doi":"10.34847/cocoon.e1084e8c-f2d6-4ddf-884e-8cf2d61ddfca","title":"Liste de mots en rục lue par une locutrice née à Mò O Ồ Ồ en 1975","year":2021,"lang":"fr","type":"article","venue":"The COCOON platform (University of Paris)","topic":"Linguistic and Sociocultural Studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Voice; Frame (networking); Southeast asia; Sound (geography); Feature (linguistics)","score_opus":0.022226765460886203,"score_gpt":0.2515337499289934,"score_spread":0.2293069844681072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6890004888","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":[0.7955906,0.010550889,0.00067871273,0.02905433,0.0013377182,0.00039534204,0.00009503584,0.000073766976,0.16222362],"genre_scores_gemma":[0.8818999,0.0126666,0.000692379,0.00022505493,0.0005322666,4.5987636e-7,0.00002031278,0.000010255457,0.103952795],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.99823636,0.00028418654,0.00019051653,0.0002883204,0.00045062447,0.00055001944],"domain_scores_gemma":[0.9981288,0.0008114408,0.00023072548,0.00025591452,0.00039068187,0.0001824566],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00085932703,0.00020860427,0.00042459476,0.000031204625,0.0018761354,0.000043648728,0.00064781774,0.00031912894,0.0008212472],"category_scores_gemma":[0.00034570106,0.00019715638,0.00023077895,0.0008952864,0.00124143,0.0003116251,0.00041970628,0.00043330475,0.00020625378],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001500579,0.00037300744,0.011381641,0.000310407,0.0010176833,0.0004872433,0.6000246,0.00020199486,0.00017947074,0.29361457,0.0782364,0.014022942],"study_design_scores_gemma":[0.0008868971,0.00009410869,0.025180127,0.00019762966,0.0006208183,0.00001236008,0.27980438,0.0005294614,0.00012230853,0.009121544,0.6829799,0.00045051522],"about_ca_topic_score_codex":0.03748611,"about_ca_topic_score_gemma":0.009307098,"teacher_disagreement_score":0.6047435,"about_ca_system_score_codex":0.0003622587,"about_ca_system_score_gemma":0.00035322364,"threshold_uncertainty_score":0.99942327},"labels":[],"label_agreement":null},{"id":"W6890102774","doi":"10.34847/cocoon.f0bb34d8-96e7-4ad1-bb34-d896e74ad16b","title":"Liste de mots en rục lue par une locutrice née à Mò O Ồ Ồ en 1950","year":2021,"lang":"fr","type":"article","venue":"The COCOON platform (University of Paris)","topic":"Linguistic and Sociocultural Studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Voice; Frame (networking); Southeast asia; Sound (geography); Feature (linguistics)","score_opus":0.02128200222381275,"score_gpt":0.25053009812899923,"score_spread":0.2292480959051865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6890102774","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":[0.81075084,0.009641955,0.000678956,0.036166888,0.0013020982,0.00038328534,0.00009127304,0.000071435104,0.14091328],"genre_scores_gemma":[0.90822566,0.012096386,0.00067215797,0.00021677982,0.00051440584,4.4098584e-7,0.000019442376,0.00000996676,0.07824477],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.99822927,0.00028969403,0.00019100975,0.00028846718,0.00045112456,0.0005504207],"domain_scores_gemma":[0.99811965,0.0008191363,0.00023082245,0.0002559373,0.00039183913,0.00018260998],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0008627492,0.00020825784,0.00042486106,0.000031071773,0.0018771756,0.0000437679,0.00064881437,0.00032017642,0.0008264174],"category_scores_gemma":[0.0003680855,0.00019688616,0.0002308006,0.00089002855,0.0012458299,0.00031206245,0.00041984927,0.00043403544,0.0002093722],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013706062,0.00034267426,0.011308139,0.0002851832,0.0009067865,0.00044156483,0.6660116,0.00017674401,0.00017042988,0.23942915,0.06717072,0.013620003],"study_design_scores_gemma":[0.0009314651,0.00009802619,0.032042157,0.00020651272,0.00065410626,0.000012698107,0.3339632,0.0005456879,0.0001270725,0.011308066,0.61963576,0.00047527402],"about_ca_topic_score_codex":0.03793416,"about_ca_topic_score_gemma":0.010325582,"teacher_disagreement_score":0.552465,"about_ca_system_score_codex":0.00042852052,"about_ca_system_score_gemma":0.0003565794,"threshold_uncertainty_score":0.99942225},"labels":[],"label_agreement":null},{"id":"W6890132586","doi":"10.34847/cocoon.36811c5c-df25-4eb3-811c-5cdf25deb3b6","title":"Liste de mots en rục lue par une locutrice née à Mò O Ồ Ồ en 1994","year":2021,"lang":"fr","type":"article","venue":"The COCOON platform (University of Paris)","topic":"Linguistic and Sociocultural Studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Voice; Frame (networking); Southeast asia; Sound (geography); Feature (linguistics)","score_opus":0.02106789753836426,"score_gpt":0.2501383177524582,"score_spread":0.22907042021409393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6890132586","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":[0.8142171,0.010561949,0.00068357884,0.027358944,0.0013203409,0.00039229635,0.00010007794,0.000073577474,0.14529213],"genre_scores_gemma":[0.9054974,0.01254688,0.0006826508,0.0002186268,0.00051781314,4.4794106e-7,0.00002152171,0.0000101122205,0.08050458],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.99824625,0.00028202546,0.00019024726,0.0002864363,0.0004479796,0.00054703385],"domain_scores_gemma":[0.9982443,0.0008157478,0.00022940773,0.0002533421,0.00027611636,0.0001810859],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00084458594,0.00020744803,0.00042195036,0.000031015123,0.0018737311,0.00004317215,0.0006455665,0.0003193569,0.00078289915],"category_scores_gemma":[0.00029953674,0.00019623317,0.00023059738,0.0008808158,0.0012422625,0.00031002582,0.0004184311,0.00043157733,0.00015998584],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013977548,0.00034968765,0.010735802,0.00028960418,0.0009531465,0.00045698302,0.6367516,0.00019534171,0.00016620688,0.2600891,0.07643076,0.013442008],"study_design_scores_gemma":[0.00089312484,0.00009441589,0.022473065,0.00019892692,0.00062841404,0.000012534712,0.3209221,0.0005593957,0.00011549097,0.010917077,0.64272994,0.00045551336],"about_ca_topic_score_codex":0.04348983,"about_ca_topic_score_gemma":0.009980836,"teacher_disagreement_score":0.5662992,"about_ca_system_score_codex":0.00043025252,"about_ca_system_score_gemma":0.00033811448,"threshold_uncertainty_score":0.9994257},"labels":[],"label_agreement":null},{"id":"W6890152255","doi":"10.34847/cocoon.fb4681f3-bf08-421a-8681-f3bf08321a6a","title":"Liste de mots en rục lue par un locuteur né à Mò O Ồ Ồ en 1994","year":2019,"lang":"fr","type":"other","venue":"The COCOON platform (University of Paris)","topic":"Linguistic and Sociocultural Studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Voice; Frame (networking); Acoustic phonetics; Feature (linguistics); Southeast asia","score_opus":0.014842162244551597,"score_gpt":0.22796207280684264,"score_spread":0.21311991056229104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6890152255","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11357776,0.0025470478,0.00045005622,0.0030416304,0.0013481145,0.00096078357,0.00012704183,0.00010358714,0.877844],"genre_scores_gemma":[0.31237516,0.0059309397,0.00047025835,0.00014790814,0.0006928564,7.380519e-7,0.00002023363,0.000043918055,0.680318],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979055,0.00028021127,0.00022433458,0.00040041553,0.00054237084,0.00064715726],"domain_scores_gemma":[0.99810416,0.0006887168,0.0004965661,0.0003855772,0.00014281829,0.0001821746],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008732916,0.0003875063,0.00072697515,0.00006783288,0.0013945275,0.00004006909,0.0013204778,0.00071626453,0.003355057],"category_scores_gemma":[0.0001700482,0.00033264872,0.000337164,0.00037225708,0.0014456455,0.00018761044,0.0005058494,0.00061868754,0.0013830789],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002311281,0.00024948484,0.011741285,0.00046397594,0.002084089,0.00011781179,0.4891545,0.00010241036,0.00003953898,0.34580326,0.13087362,0.01913893],"study_design_scores_gemma":[0.00065632485,0.00011848583,0.007232014,0.00024537247,0.000534286,0.000002941295,0.06870447,0.00019892605,0.000008573543,0.0023253902,0.9194848,0.00048840296],"about_ca_topic_score_codex":0.028734772,"about_ca_topic_score_gemma":0.0061145644,"teacher_disagreement_score":0.7886112,"about_ca_system_score_codex":0.00038879472,"about_ca_system_score_gemma":0.0002569182,"threshold_uncertainty_score":0.99991256},"labels":[],"label_agreement":null},{"id":"W6908804101","doi":"10.34847/cocoon.2df0cf9a-7c79-48cd-b0cf-9a7c7938cd56","title":"Liste de mots en rục lue par un locuteur né à Mò O Ồ Ồ en 1983","year":2021,"lang":"fr","type":"article","venue":"The COCOON platform (University of Paris)","topic":"Linguistic and Sociocultural Studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Voice; Frame (networking); Acoustic phonetics; Feature (linguistics)","score_opus":0.02019916591291063,"score_gpt":0.24195411729649702,"score_spread":0.2217549513835864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6908804101","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":[0.86906594,0.0073335255,0.0006549974,0.017375218,0.0012499803,0.00032063253,0.000088721485,0.00007485284,0.103836134],"genre_scores_gemma":[0.9133617,0.009719896,0.0008125563,0.00023370875,0.00048871536,4.0085982e-7,0.000014871336,0.000010740414,0.07535741],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982354,0.00031859387,0.00018420894,0.000287237,0.00042960586,0.00054496573],"domain_scores_gemma":[0.9983671,0.00063957484,0.00021135822,0.0002594755,0.00034006595,0.00018246581],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0008697231,0.00020936562,0.00040915966,0.000026015978,0.0018438661,0.000044138927,0.0006537591,0.000314761,0.00088595186],"category_scores_gemma":[0.00033876815,0.00019752818,0.00023935147,0.0005182644,0.0011897926,0.00029710127,0.0004611728,0.000423167,0.00025806148],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011344577,0.00029895268,0.01713249,0.00021249954,0.0010369127,0.00046849903,0.6014785,0.000119616896,0.00014019871,0.32525393,0.03393271,0.019812204],"study_design_scores_gemma":[0.00093928835,0.00010942303,0.033137772,0.00019855083,0.00065757066,0.000015194719,0.31044492,0.0005041869,0.00021179768,0.012108202,0.6411742,0.0004988703],"about_ca_topic_score_codex":0.015786363,"about_ca_topic_score_gemma":0.0050121075,"teacher_disagreement_score":0.6072415,"about_ca_system_score_codex":0.0002704426,"about_ca_system_score_gemma":0.00030513224,"threshold_uncertainty_score":0.9994556},"labels":[],"label_agreement":null},{"id":"W6908820524","doi":"10.34847/cocoon.74b07a67-2c2b-4aa3-b07a-672c2bcaa387","title":"Liste de mots en rục lue par un locuteur né à Mò O Ồ Ồ en 1970","year":2019,"lang":"fr","type":"other","venue":"The COCOON platform (University of Paris)","topic":"Linguistic and Sociocultural Studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Voice; Frame (networking); Acoustic phonetics; Feature (linguistics); Southeast asia","score_opus":0.015828342111831185,"score_gpt":0.23000237044546623,"score_spread":0.21417402833363505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6908820524","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12134355,0.0024954865,0.0004492129,0.003703838,0.0013435247,0.0009524921,0.00011921096,0.000102159654,0.8694905],"genre_scores_gemma":[0.3162593,0.005784515,0.00045419447,0.00014396507,0.0006792469,7.228761e-7,0.000018221386,0.000042493877,0.6766173],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978854,0.00028806418,0.00022524239,0.00040349583,0.00054643274,0.00065138773],"domain_scores_gemma":[0.9980275,0.00069630466,0.0004997164,0.00038983364,0.000203037,0.00018357855],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008915454,0.00039005777,0.0007324183,0.00006802571,0.0013986307,0.000040612773,0.0013275178,0.00071849895,0.0035256778],"category_scores_gemma":[0.0002071308,0.0003345096,0.0003399988,0.0003765799,0.0014482393,0.00018874537,0.0005074378,0.0006227705,0.0017846369],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002304133,0.00024779563,0.010821788,0.00046299017,0.0020900122,0.0001170871,0.5078093,0.00009835679,0.000040678904,0.33364102,0.122971244,0.021469345],"study_design_scores_gemma":[0.0006656402,0.0001206302,0.008741612,0.000249088,0.0005432408,0.000002962268,0.06874093,0.00018713914,0.000009325376,0.0022703502,0.9179752,0.00049386965],"about_ca_topic_score_codex":0.0261975,"about_ca_topic_score_gemma":0.00599301,"teacher_disagreement_score":0.79500395,"about_ca_system_score_codex":0.0003822728,"about_ca_system_score_gemma":0.00026998852,"threshold_uncertainty_score":0.9999107},"labels":[],"label_agreement":null},{"id":"W6908827332","doi":"10.34847/cocoon.a718c6e5-304d-4eef-98c6-e5304ddeefba","title":"Liste de mots en rục lue par un locuteur né à Mò O Ồ Ồ en 1973","year":2021,"lang":"fr","type":"article","venue":"The COCOON platform (University of Paris)","topic":"Historical and Scientific Studies","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Voice; Frame (networking); Acoustic phonetics; Southeast asia; Feature (linguistics)","score_opus":0.02162544927005672,"score_gpt":0.216265472263239,"score_spread":0.19464002299318228,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6908827332","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":[0.84802836,0.030111386,0.0042242794,0.02269417,0.0046217307,0.0006045071,0.00019978549,0.00011146367,0.08940431],"genre_scores_gemma":[0.6909333,0.0054210476,0.0011948763,0.00031264205,0.0004401941,6.099316e-7,0.000038641352,0.000019974816,0.3016387],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981623,0.0001588256,0.00023309179,0.0003904583,0.00046256182,0.00059274986],"domain_scores_gemma":[0.9981607,0.00054457434,0.00016611781,0.0005604429,0.00027176208,0.00029638756],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00085967564,0.0002314177,0.0005570809,0.00008856019,0.000725383,0.000018588413,0.00047332208,0.00025586065,0.0020004536],"category_scores_gemma":[0.00024122733,0.00021576109,0.00025303196,0.00073503586,0.0006284933,0.0002167986,0.00047465082,0.00053780427,0.0007744108],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012191159,0.0016681413,0.016262516,0.0016659795,0.002335314,0.0047447635,0.16320735,0.00024063264,0.010173666,0.030876135,0.6598133,0.10779309],"study_design_scores_gemma":[0.0020079259,0.0002883799,0.02983604,0.000462493,0.0010723436,0.0001417023,0.025037993,0.00268421,0.0017343549,0.0010113075,0.9353558,0.00036749034],"about_ca_topic_score_codex":0.0015250818,"about_ca_topic_score_gemma":0.0006533495,"teacher_disagreement_score":0.27554247,"about_ca_system_score_codex":0.00036987837,"about_ca_system_score_gemma":0.0003443754,"threshold_uncertainty_score":0.99891186},"labels":[],"label_agreement":null},{"id":"W6908969753","doi":"10.34847/cocoon.4b524174-b6ff-4b9d-9241-74b6ffdb9d4b","title":"Liste de mots en rục lue par un locuteur né à Mò O Ồ Ồ en 1981","year":2021,"lang":"fr","type":"article","venue":"The COCOON platform (University of Paris)","topic":"Linguistic and Sociocultural Studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Voice; Frame (networking); Acoustic phonetics; Feature (linguistics); Southeast asia","score_opus":0.020242175318857535,"score_gpt":0.24196217947969242,"score_spread":0.2217200041608349,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6908969753","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":[0.8663712,0.007944538,0.0006994982,0.02104849,0.0013091078,0.000339157,0.00009346931,0.00007716387,0.102117375],"genre_scores_gemma":[0.89866734,0.00984364,0.00082217465,0.00023904572,0.00049237796,4.1336958e-7,0.00001527692,0.0000106729985,0.08990909],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.99823296,0.00031909868,0.00018445229,0.00028738438,0.00043022932,0.0005458944],"domain_scores_gemma":[0.99836105,0.00064404844,0.0002119329,0.00025968516,0.0003405147,0.00018276763],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00087021507,0.00020947521,0.00040967937,0.0000260279,0.0018734891,0.000044272914,0.0006557521,0.00031520994,0.0008541503],"category_scores_gemma":[0.00034018315,0.00019760194,0.00023948231,0.0005200792,0.0011960734,0.00029759263,0.00046176105,0.00042386784,0.00025301543],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001393471,0.00030136373,0.012873091,0.00021684551,0.001051081,0.00048420177,0.5719245,0.000127155,0.00014166565,0.3530132,0.038275413,0.021452157],"study_design_scores_gemma":[0.000974935,0.00012368186,0.02720204,0.00020332746,0.0006719363,0.000015750013,0.29329887,0.0005912669,0.00021646914,0.013377092,0.66281253,0.00051211746],"about_ca_topic_score_codex":0.014912125,"about_ca_topic_score_gemma":0.005521456,"teacher_disagreement_score":0.6245371,"about_ca_system_score_codex":0.00027800215,"about_ca_system_score_gemma":0.0003289489,"threshold_uncertainty_score":0.99942595},"labels":[],"label_agreement":null},{"id":"W6909134167","doi":"10.34847/cocoon.30fef00d-bf8f-497a-bef0-0dbf8f097a64","title":"Liste de mots en arem lue par un locuteur né à Tân Trạch en 1966","year":2021,"lang":"fr","type":"article","venue":"The COCOON platform (University of Paris)","topic":"Southeast Asian Sociopolitical Studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Voice; Frame (networking); Acoustic phonetics; Voice-onset time; Deixis; Discourse analysis","score_opus":0.018761476089080353,"score_gpt":0.24345251939264365,"score_spread":0.2246910433035633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6909134167","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":[0.83291566,0.004603136,0.001012954,0.035410915,0.0007971962,0.0004359647,0.00015031503,0.00010690477,0.12456694],"genre_scores_gemma":[0.9662307,0.0016595831,0.0009197314,0.0002827151,0.00037975857,8.414624e-7,0.000011372869,0.000021739044,0.030493565],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9971973,0.0005918742,0.00024706492,0.0004073125,0.0006263772,0.0009300887],"domain_scores_gemma":[0.99768525,0.0010149915,0.00021551136,0.00044453455,0.00028910843,0.00035058917],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011343724,0.00028123002,0.00055145205,0.00005215786,0.0016001933,0.000053339612,0.00091083033,0.00042719432,0.0016432997],"category_scores_gemma":[0.00027014056,0.0003003697,0.00033386235,0.0008735276,0.0021574022,0.00042705468,0.00059350807,0.0006062083,0.00064635876],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020391363,0.0005032862,0.018719384,0.00025664852,0.001028834,0.00046497653,0.5482918,0.000042689844,0.00010431326,0.38825575,0.012302267,0.029826129],"study_design_scores_gemma":[0.0014375763,0.00016149873,0.048008926,0.0002630303,0.0007851397,0.00003151406,0.6647051,0.0006736306,0.0003066734,0.027827533,0.25514174,0.00065762183],"about_ca_topic_score_codex":0.00672773,"about_ca_topic_score_gemma":0.0033458616,"teacher_disagreement_score":0.3604282,"about_ca_system_score_codex":0.00046998129,"about_ca_system_score_gemma":0.0004850473,"threshold_uncertainty_score":0.99994487},"labels":[],"label_agreement":null},{"id":"W6927447310","doi":"10.34847/cocoon.1053604e-8a08-4e29-9360-4e8a087e292e","title":"Liste de mots en rục lue par une locutrice née à Mò O Ồ Ồ en 1976","year":2019,"lang":"fr","type":"other","venue":"The COCOON platform (University of Paris)","topic":"Infections and bacterial resistance","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Voice; Frame (networking); Southeast asia; Sound (geography); Feature (linguistics)","score_opus":0.004474927201305694,"score_gpt":0.19071780828802976,"score_spread":0.18624288108672407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6927447310","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":[0.6092421,0.002412057,0.005389548,0.0010347371,0.0009756942,0.0009898795,0.00034423385,0.000030187526,0.37958157],"genre_scores_gemma":[0.55347055,0.0059309136,0.00054229895,0.00010018022,0.000472634,0.0000013005038,0.00023914794,0.00007755676,0.43916538],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986326,0.00012494283,0.00019669707,0.00042421746,0.0001725144,0.00044902708],"domain_scores_gemma":[0.9985426,0.000096879005,0.00039505315,0.0007177857,0.0001320244,0.0001156588],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00036305422,0.00034841325,0.00045143403,0.000101727084,0.00029355584,0.000029879553,0.0007167155,0.00086431974,0.0016561568],"category_scores_gemma":[0.000047664907,0.0003434798,0.00026753254,0.0002832664,0.000333121,0.000019401195,0.00034709883,0.0003736524,0.00036393845],"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":[0.004236708,0.0012737823,0.006232944,0.0029898481,0.003965289,0.00019727135,0.006983445,0.0011123499,0.5779185,0.029866884,0.32170874,0.043514185],"study_design_scores_gemma":[0.0010301253,0.0003284582,0.0065991874,0.00021664373,0.0003089479,0.00002691435,0.0008080542,0.00018736064,0.0055202856,0.00011337721,0.9844017,0.00045892174],"about_ca_topic_score_codex":0.0027683517,"about_ca_topic_score_gemma":0.002177948,"teacher_disagreement_score":0.66269296,"about_ca_system_score_codex":0.00016259354,"about_ca_system_score_gemma":0.00033553684,"threshold_uncertainty_score":0.9999017},"labels":[],"label_agreement":null},{"id":"W6927473562","doi":"10.34847/cocoon.f0b5fafc-3f0e-40d2-b5fa-fc3f0ec0d2d8","title":"Liste de mots en arem lue par un locuteur né à Thượng Trạch en 1956","year":2019,"lang":"fr","type":"other","venue":"The COCOON platform (University of Paris)","topic":"Seaweed-derived Bioactive Compounds","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Voice; Frame (networking); Acoustic phonetics; Voice-onset time; Deixis; Term (time)","score_opus":0.013716399104476926,"score_gpt":0.1874594793501322,"score_spread":0.1737430802456553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6927473562","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":[0.78993803,0.0013109428,0.00022364268,0.0050681448,0.0007229117,0.0011996096,0.00024760113,0.00013255558,0.20115657],"genre_scores_gemma":[0.6592842,0.0015422836,0.00043069117,0.00027049365,0.0005408905,0.0000012840163,0.0001246278,0.00002249197,0.33778307],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973832,0.0003457403,0.00027828306,0.0007039012,0.000498143,0.0007907597],"domain_scores_gemma":[0.99758655,0.0009709553,0.00061086775,0.000398291,0.00017818603,0.00025516446],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00067744753,0.00058072445,0.0008120928,0.0000846519,0.00062107027,0.000079678444,0.002149611,0.0009191662,0.009888657],"category_scores_gemma":[0.000054778397,0.00031380856,0.0004504563,0.0006391389,0.0007292833,0.00034928907,0.0008057504,0.0008267872,0.0017730246],"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":[0.0038613116,0.0022916251,0.0630042,0.0011928026,0.0047884956,0.0005788259,0.035654865,0.00045517294,0.22187854,0.049436312,0.1758648,0.44099304],"study_design_scores_gemma":[0.0011988087,0.0009537185,0.23161268,0.00049060624,0.00053571846,0.00006133551,0.015129495,0.0013213358,0.0017238387,0.001435075,0.7443596,0.0011777724],"about_ca_topic_score_codex":0.005931025,"about_ca_topic_score_gemma":0.0030321514,"teacher_disagreement_score":0.5684948,"about_ca_system_score_codex":0.0002996036,"about_ca_system_score_gemma":0.0001129882,"threshold_uncertainty_score":0.9999314},"labels":[],"label_agreement":null},{"id":"W6927634163","doi":"10.34847/cocoon.f0aa897e-9c3f-4a5f-aa89-7e9c3f3a5f78","title":"Liste de mots en rục lue par un locuteur né à Mò O Ồ Ồ en 1955","year":2021,"lang":"fr","type":"article","venue":"The COCOON platform (University of Paris)","topic":"Physiological and biochemical adaptations","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Voice; Frame (networking); Acoustic phonetics; Feature (linguistics); Southeast asia","score_opus":0.013382143121653492,"score_gpt":0.1917929774724121,"score_spread":0.1784108343507586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6927634163","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":[0.98036176,0.0006195492,0.0014678489,0.006809588,0.00012370948,0.00016149106,0.00011295754,0.000028994917,0.01031412],"genre_scores_gemma":[0.98368186,0.0013332617,0.0020096914,0.00031447737,0.00005901482,3.9514032e-7,0.000040349096,0.000006550169,0.012554395],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9987604,0.00012443322,0.00014667555,0.00031591862,0.00025253967,0.00040000718],"domain_scores_gemma":[0.99901813,0.00031484527,0.000120817545,0.00031729773,0.000030918072,0.00019797473],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00025110744,0.00017222937,0.0002447171,0.000016731605,0.00039682558,0.000018013448,0.00062046666,0.000226024,0.0052452707],"category_scores_gemma":[0.00005753644,0.00015207406,0.00016700712,0.00041342826,0.00069045654,0.0003102049,0.0007210563,0.00036486398,0.0010501362],"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":[0.00035693916,0.0013473657,0.0059825224,0.00017623321,0.00031467635,0.00035453256,0.009588759,0.0033432092,0.87411827,0.016780306,0.028844178,0.058792982],"study_design_scores_gemma":[0.0021637557,0.00062098517,0.56742674,0.00029299405,0.0006424933,0.00011503769,0.013007398,0.023277273,0.1231611,0.046530843,0.22155233,0.0012090794],"about_ca_topic_score_codex":0.0018518025,"about_ca_topic_score_gemma":0.0004121586,"teacher_disagreement_score":0.7509572,"about_ca_system_score_codex":0.00014870815,"about_ca_system_score_gemma":0.00006474368,"threshold_uncertainty_score":0.99972767},"labels":[],"label_agreement":null},{"id":"W6927730959","doi":"10.34847/cocoon.ba6897ff-55ff-45df-a897-ff55ffb5df96","title":"Liste de mots en rục lue par un locuteur né à Mò O Ồ Ồ en 1970","year":2021,"lang":"fr","type":"article","venue":"The COCOON platform (University of Paris)","topic":"Viral Infectious Diseases and Gene Expression in Insects","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Voice; Frame (networking); Acoustic phonetics; Feature (linguistics); Southeast asia","score_opus":0.007464323765896978,"score_gpt":0.214153415032339,"score_spread":0.20668909126644203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6927730959","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":[0.97271335,0.01215368,0.0032165872,0.0021144068,0.00070514623,0.00024533673,0.00021606238,0.000024771784,0.008610639],"genre_scores_gemma":[0.971316,0.0084308535,0.00056174945,0.00039487222,0.00031351994,0.0000011102946,0.00015871396,0.000024970777,0.018798234],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99849194,0.00023323711,0.00019730434,0.0004187847,0.00019968905,0.00045905673],"domain_scores_gemma":[0.9986041,0.000087568464,0.00020445859,0.0006565878,0.00021379828,0.00023348618],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003123848,0.0002580066,0.00029724103,0.00004319161,0.00046673507,0.000037649057,0.00051247707,0.00046478282,0.0008453381],"category_scores_gemma":[0.00008211007,0.0002716982,0.0003243041,0.00024403559,0.00030353552,0.00003334594,0.00064118573,0.0003212929,0.00010093745],"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":[0.0021685967,0.0021667767,0.016789025,0.0012580268,0.0026943379,0.0010833176,0.010196584,0.004821415,0.5453645,0.01005482,0.35259396,0.050808657],"study_design_scores_gemma":[0.0032093164,0.0010842058,0.017710838,0.00039926573,0.0008363077,0.00030498364,0.0067303255,0.002380059,0.21654496,0.0024550096,0.7473372,0.0010074952],"about_ca_topic_score_codex":0.00078069285,"about_ca_topic_score_gemma":0.00042863973,"teacher_disagreement_score":0.3947433,"about_ca_system_score_codex":0.000060310387,"about_ca_system_score_gemma":0.00038316203,"threshold_uncertainty_score":0.99997354},"labels":[],"label_agreement":null},{"id":"W6927745965","doi":"10.34847/cocoon.b92c32f7-d461-44af-ac32-f7d461a4aff4","title":"Liste de mots en rục lue par un locuteur né à Mò O Ồ Ồ en 1994","year":2021,"lang":"fr","type":"article","venue":"The COCOON platform (University of Paris)","topic":"Linguistic and Sociocultural Studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Voice; Frame (networking); Acoustic phonetics; Feature (linguistics); Southeast asia","score_opus":0.02004277265409535,"score_gpt":0.24166779597834626,"score_spread":0.2216250233242509,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6927745965","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":[0.8761696,0.008112823,0.0006698844,0.016034234,0.0012988814,0.0003342806,0.00009687285,0.0000769295,0.09720649],"genre_scores_gemma":[0.90644544,0.0100514665,0.00083440123,0.00023845675,0.0004952538,4.135061e-7,0.000016441674,0.000010689311,0.08190745],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.99825054,0.0003103215,0.00018374162,0.000285467,0.00042731373,0.000542589],"domain_scores_gemma":[0.9984742,0.00063701405,0.00021067171,0.00025709375,0.00023979227,0.00018122898],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0008538724,0.00020817491,0.00040671258,0.000026020742,0.001870554,0.000043767952,0.0006523931,0.00031406686,0.0008756782],"category_scores_gemma":[0.00027710563,0.00019657325,0.00023920403,0.000515562,0.0011927718,0.00029585764,0.00046068017,0.00042092707,0.00019676803],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014326381,0.00031381968,0.013506527,0.00022205285,0.0010813972,0.0004974136,0.5956759,0.00013051006,0.0001441687,0.32412505,0.04201816,0.02214174],"study_design_scores_gemma":[0.0009362189,0.00012050119,0.022388386,0.0001985232,0.0006521999,0.000015269605,0.27650356,0.0005693301,0.00020272343,0.012381756,0.68553555,0.0004960017],"about_ca_topic_score_codex":0.016116181,"about_ca_topic_score_gemma":0.005617527,"teacher_disagreement_score":0.6435174,"about_ca_system_score_codex":0.0002712923,"about_ca_system_score_gemma":0.00029615578,"threshold_uncertainty_score":0.99942887},"labels":[],"label_agreement":null},{"id":"W6927747205","doi":"10.34847/cocoon.5ff0cff5-8296-4756-b0cf-f58296d756e3","title":"Liste de mots en rục lue par une locutrice née à Mò O Ồ Ồ en 1999","year":2019,"lang":"fr","type":"other","venue":"The COCOON platform (University of Paris)","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Voice; Frame (networking); Southeast asia; Sound (geography); Feature (linguistics)","score_opus":0.007633742997781248,"score_gpt":0.20766165502389428,"score_spread":0.20002791202611303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6927747205","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2784901,0.01487635,0.020856945,0.007335247,0.0016459431,0.0023449454,0.00038584997,0.00007346022,0.67399114],"genre_scores_gemma":[0.51751506,0.008804732,0.0005742373,0.0002064122,0.0003263048,0.0000022867318,0.00032772802,0.00008056469,0.47216266],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99849534,0.00015462111,0.00020779837,0.0005072815,0.00024317876,0.0003917785],"domain_scores_gemma":[0.99826515,0.00007042873,0.00048182838,0.000908826,0.000121156096,0.0001525842],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003536733,0.00033964435,0.0004025424,0.00012464184,0.00021369176,0.00002215317,0.0009895586,0.0008889331,0.001562681],"category_scores_gemma":[0.00003236622,0.00033276438,0.00023635906,0.00030852944,0.00028026165,0.000016531245,0.0003756935,0.00039124957,0.0003913845],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001115068,0.00042337467,0.0025978552,0.000915854,0.0009860306,0.000028978415,0.0059830975,0.0007804757,0.32730916,0.0057155634,0.62030673,0.033837803],"study_design_scores_gemma":[0.0011454494,0.00020663523,0.006175414,0.0002013838,0.00024517803,0.000014206705,0.0029122506,0.0006646529,0.0092643825,0.000115134004,0.97863984,0.00041545957],"about_ca_topic_score_codex":0.001408954,"about_ca_topic_score_gemma":0.00049326156,"teacher_disagreement_score":0.3583331,"about_ca_system_score_codex":0.00015013406,"about_ca_system_score_gemma":0.0003830362,"threshold_uncertainty_score":0.99991244},"labels":[],"label_agreement":null},{"id":"W6927799586","doi":"10.34847/cocoon.40484fab-4665-431f-884f-ab4665831fbc","title":"Liste de mots en rục lue par une locutrice née à Mò O Ồ Ồ en 1950","year":2019,"lang":"fr","type":"other","venue":"The COCOON platform (University of Paris)","topic":"Linguistic and Sociocultural Studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Voice; Frame (networking); Southeast asia; Sound (geography); Feature (linguistics)","score_opus":0.015578177229586923,"score_gpt":0.23550865974525823,"score_spread":0.2199304825156713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6927799586","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08067485,0.0026002338,0.00039156264,0.0059776544,0.0011580794,0.00094435376,0.00010249285,0.000082552215,0.90806824],"genre_scores_gemma":[0.31500852,0.0072041927,0.00038240847,0.00013577481,0.00072463386,7.944453e-7,0.000024099265,0.000041162955,0.6764784],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.99787265,0.00026155365,0.00023315017,0.00040421746,0.0005722863,0.0006561433],"domain_scores_gemma":[0.9977695,0.0008870993,0.0005427837,0.00038335327,0.00023371183,0.00018357627],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008823666,0.00038689468,0.00075816497,0.000080842474,0.0014009465,0.00004007534,0.0013108085,0.0007277205,0.0031512238],"category_scores_gemma":[0.00022655858,0.00033260195,0.00032486688,0.00064447103,0.0015075944,0.00019812152,0.0004612568,0.0006372215,0.0014660176],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021338748,0.00026322415,0.009494225,0.00057424884,0.0016824403,0.00010121115,0.5318693,0.00013449916,0.000045418365,0.24605301,0.19821587,0.011353153],"study_design_scores_gemma":[0.0006831119,0.00010084833,0.010904206,0.00026622912,0.0005602164,0.0000025586787,0.08937408,0.00020085755,0.000005675525,0.0022220418,0.8951915,0.0004887144],"about_ca_topic_score_codex":0.066409804,"about_ca_topic_score_gemma":0.011229385,"teacher_disagreement_score":0.6969756,"about_ca_system_score_codex":0.000614061,"about_ca_system_score_gemma":0.00030921042,"threshold_uncertainty_score":0.9999126},"labels":[],"label_agreement":null},{"id":"W6927800290","doi":"10.34847/cocoon.6618b16f-c757-4ed2-98b1-6fc757fed262","title":"Liste de mots en rục lue par une locutrice née à Mò O Ồ Ồ en 1949","year":2019,"lang":"fr","type":"other","venue":"The COCOON platform (University of Paris)","topic":"Linguistic and Sociocultural Studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Voice; Frame (networking); Southeast asia; Sound (geography); Feature (linguistics)","score_opus":0.015502951404262666,"score_gpt":0.23538196934389477,"score_spread":0.2198790179396321,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6927800290","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0708902,0.0024774547,0.00040005674,0.005758313,0.0011440963,0.00091153703,0.00010163522,0.000079707024,0.918237],"genre_scores_gemma":[0.303189,0.0066665486,0.000380048,0.00013110113,0.00070398225,7.946641e-7,0.000023774832,0.000040743544,0.688864],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978615,0.00026672482,0.00023288475,0.00040351565,0.0005783759,0.0006569674],"domain_scores_gemma":[0.9977335,0.00091586047,0.0005503164,0.0003819088,0.00023535469,0.00018307171],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00089377165,0.00038692224,0.00075976126,0.00008046319,0.0014081034,0.00004084349,0.0013062719,0.0007340991,0.0030426756],"category_scores_gemma":[0.00023035241,0.000332554,0.0003253153,0.00064050674,0.0014826756,0.00020005602,0.0004597478,0.0006415106,0.0014320946],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020796836,0.0002674671,0.009385769,0.00056340126,0.001784893,0.000102813014,0.47005484,0.00013935509,0.000045217672,0.28537166,0.2213651,0.010711494],"study_design_scores_gemma":[0.00068291405,0.000100604164,0.011591078,0.00026090734,0.0005674545,0.0000025380398,0.085674055,0.00021105386,0.000005580133,0.0021741022,0.8982437,0.0004859628],"about_ca_topic_score_codex":0.075791016,"about_ca_topic_score_gemma":0.012156613,"teacher_disagreement_score":0.67687863,"about_ca_system_score_codex":0.0006435141,"about_ca_system_score_gemma":0.0003380197,"threshold_uncertainty_score":0.9999127},"labels":[],"label_agreement":null},{"id":"W6946263776","doi":"10.34847/cocoon.5517406a-df58-4c98-9740-6adf585c9815","title":"Liste de mots en arem lue par un locuteur né à Thượng Trạch en 1944","year":2021,"lang":"fr","type":"article","venue":"The COCOON platform (University of Paris)","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Voice; Frame (networking); Acoustic phonetics; Voice-onset time; Deixis; Discourse analysis","score_opus":0.018147029979594193,"score_gpt":0.20640765202157682,"score_spread":0.18826062204198263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6946263776","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":[0.9368831,0.001521547,0.0010395771,0.008852887,0.0004033581,0.00025017915,0.00039689775,0.00004901391,0.050603434],"genre_scores_gemma":[0.9693166,0.005495789,0.0002939992,0.00036809954,0.000066953864,6.4746007e-7,0.00013624421,0.000017089951,0.024304597],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982808,0.00016537284,0.00018945655,0.00036751808,0.00041680885,0.0005800105],"domain_scores_gemma":[0.99882424,0.00017789839,0.00018967432,0.0005194306,0.000051020867,0.00023775628],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005340409,0.00023390274,0.0003124168,0.0000348728,0.0005942545,0.000049052673,0.00073267124,0.0002717225,0.07952565],"category_scores_gemma":[0.00005128622,0.00025161778,0.00020518657,0.00055710145,0.00062051415,0.000499309,0.0007447094,0.00039867457,0.0027248287],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014735251,0.003461827,0.11510283,0.0011164687,0.0011307107,0.003015236,0.12190714,0.0022828842,0.066123515,0.12586226,0.43404976,0.124473855],"study_design_scores_gemma":[0.0018591345,0.00019401374,0.39108548,0.00016400723,0.00038198233,0.00017503249,0.09263219,0.0033476443,0.008986885,0.0010155606,0.4995148,0.0006433007],"about_ca_topic_score_codex":0.0027952679,"about_ca_topic_score_gemma":0.003736614,"teacher_disagreement_score":0.27598265,"about_ca_system_score_codex":0.00083255407,"about_ca_system_score_gemma":0.00008459817,"threshold_uncertainty_score":0.9999936},"labels":[],"label_agreement":null},{"id":"W6946420245","doi":"10.34847/cocoon.67b28b30-7381-41c2-b28b-30738111c294","title":"Liste de mots en rục lue par un locuteur né à Mò O Ồ Ồ en 1983","year":2019,"lang":"fr","type":"other","venue":"The COCOON platform (University of Paris)","topic":"Linguistic and Sociocultural Studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Voice; Frame (networking); Acoustic phonetics; Feature (linguistics)","score_opus":0.014960001384470172,"score_gpt":0.22823794204664877,"score_spread":0.2132779406621786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6946420245","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11676492,0.0022943036,0.00043869085,0.0032899238,0.0012932152,0.00091858365,0.0001159577,0.000100472185,0.87478393],"genre_scores_gemma":[0.33782893,0.0057301195,0.0004575775,0.00014484944,0.00068319525,7.14882e-7,0.000018281029,0.00004409725,0.65509224],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.99788916,0.00028770388,0.00022491353,0.00040291445,0.00054530153,0.00065001805],"domain_scores_gemma":[0.99803495,0.0006915281,0.00049822376,0.00038918504,0.00020268264,0.00018343447],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008895397,0.0003897281,0.0007313601,0.00006782171,0.0013746339,0.000040410192,0.0013232599,0.00071785384,0.003394521],"category_scores_gemma":[0.00020796385,0.00033426954,0.0003373736,0.0003742178,0.0014420504,0.00018840157,0.0005063909,0.0006219885,0.0018139947],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018609669,0.00024166012,0.015147952,0.00045147812,0.002031989,0.00011282333,0.5035746,0.00009542808,0.000039101367,0.35294265,0.10776334,0.017412877],"study_design_scores_gemma":[0.00066318957,0.000108362015,0.010810275,0.00024716093,0.0005425509,0.0000029478124,0.07855764,0.00017740959,0.000009023015,0.002289991,0.9060967,0.0004947458],"about_ca_topic_score_codex":0.028143695,"about_ca_topic_score_gemma":0.0054550543,"teacher_disagreement_score":0.79833335,"about_ca_system_score_codex":0.00038757312,"about_ca_system_score_gemma":0.00026474695,"threshold_uncertainty_score":0.99992543},"labels":[],"label_agreement":null},{"id":"W6946435629","doi":"10.34847/cocoon.e1aff026-4847-4779-aff0-2648470779e7","title":"Liste de mots en arem lue par un locuteur né à Tân Trạch en 1966","year":2019,"lang":"fr","type":"other","venue":"The COCOON platform (University of Paris)","topic":"Southeast Asian Sociopolitical Studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Voice; Frame (networking); Acoustic phonetics; Voice-onset time; Deixis; Discourse analysis","score_opus":0.013717779601040411,"score_gpt":0.2286677750205319,"score_spread":0.2149499954194915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6946435629","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12214675,0.0014745158,0.0006881212,0.00695976,0.0008284728,0.0012354092,0.0001975979,0.00014382457,0.86632556],"genre_scores_gemma":[0.5339009,0.0010890353,0.0005812302,0.00019604448,0.0005870108,0.0000016637721,0.000015524267,0.00009765681,0.46353093],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.99667007,0.0005406345,0.00030325327,0.0005729365,0.00079791463,0.0011151803],"domain_scores_gemma":[0.9971916,0.0011034615,0.0005055675,0.000668835,0.00017496603,0.00035556892],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0011683904,0.0005232574,0.0009847637,0.00013556164,0.0012021683,0.00004929354,0.0018373871,0.0009712919,0.0062140785],"category_scores_gemma":[0.00016795454,0.0005090896,0.00047214422,0.00063897966,0.0026285097,0.0002746447,0.0006544077,0.00089322164,0.0044382983],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034628087,0.00042610135,0.01717024,0.0005620265,0.0020790515,0.0001192312,0.47497475,0.000035380737,0.000030805477,0.4366452,0.040304784,0.027306143],"study_design_scores_gemma":[0.0012516752,0.00019591763,0.01943004,0.0004010752,0.000796696,0.000007760177,0.23429155,0.00029270718,0.000016778336,0.0066427984,0.735872,0.0008010443],"about_ca_topic_score_codex":0.011963291,"about_ca_topic_score_gemma":0.003636765,"teacher_disagreement_score":0.6955672,"about_ca_system_score_codex":0.0006749382,"about_ca_system_score_gemma":0.000425978,"threshold_uncertainty_score":0.9997361},"labels":[],"label_agreement":null},{"id":"W6946687541","doi":"10.34847/cocoon.82f8e556-e153-4a8b-b8e5-56e1535a8b20","title":"Liste de mots en rục lue par une locutrice née à Mò O Ồ Ồ en 1966","year":2021,"lang":"fr","type":"article","venue":"The COCOON platform (University of Paris)","topic":"Linguistic and Sociocultural Studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Voice; Frame (networking); Southeast asia; Sound (geography); Feature (linguistics)","score_opus":0.02125692665164756,"score_gpt":0.2503602603888745,"score_spread":0.22910333373722694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6946687541","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":[0.79960406,0.01004641,0.0006823292,0.0327294,0.0013047272,0.00038609008,0.00009311577,0.00007067641,0.15508321],"genre_scores_gemma":[0.89431286,0.012065004,0.00067237567,0.00021738229,0.0005153652,4.4599844e-7,0.00001936016,0.000010082745,0.09218711],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982288,0.00028955468,0.00019105451,0.00028865325,0.00045132005,0.0005506003],"domain_scores_gemma":[0.9981146,0.0008240462,0.00023084946,0.0002561399,0.00039167656,0.00018269503],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0008559444,0.00020881408,0.00042512233,0.000031026084,0.0018787271,0.000043784683,0.0006491068,0.00031998206,0.00081672997],"category_scores_gemma":[0.00036568474,0.00019732457,0.00023089355,0.0008880113,0.00124469,0.000305143,0.00040824854,0.00043397615,0.00020620963],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001379771,0.0003450295,0.010610744,0.00028716328,0.00094052416,0.00045603595,0.62828165,0.00018306452,0.0001665605,0.27691597,0.06846925,0.013206029],"study_design_scores_gemma":[0.0008996121,0.000094333154,0.027146056,0.00019870143,0.0006297566,0.000012711547,0.3188353,0.00054407824,0.00012332688,0.010406888,0.64065176,0.00045747633],"about_ca_topic_score_codex":0.038644277,"about_ca_topic_score_gemma":0.0092962785,"teacher_disagreement_score":0.57218254,"about_ca_system_score_codex":0.00043395697,"about_ca_system_score_gemma":0.0003686339,"threshold_uncertainty_score":0.9994207},"labels":[],"label_agreement":null},{"id":"W6964701780","doi":"10.34847/cocoon.bdc392b1-5203-4690-8392-b152033690f9","title":"Liste de mots en arem lue par un locuteur né à Tân Trạch en 1981","year":2021,"lang":"fr","type":"article","venue":"The COCOON platform (University of Paris)","topic":"Tree-ring climate responses","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Voice; Frame (networking); Acoustic phonetics; Voice-onset time; Deixis; Discourse analysis","score_opus":0.01958253954880425,"score_gpt":0.20292293052664814,"score_spread":0.18334039097784388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6964701780","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":[0.9761684,0.006227233,0.00042562085,0.005045961,0.0005568666,0.00025011742,0.0004369212,0.000071837145,0.010817035],"genre_scores_gemma":[0.97012323,0.005954313,0.0018712874,0.00016344165,0.00013334287,1.3428338e-7,0.00013838957,0.000013497728,0.021602377],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9976814,0.00045213854,0.00024957524,0.00042770957,0.00044815036,0.000741059],"domain_scores_gemma":[0.9972372,0.001477964,0.00023970043,0.0006071706,0.00013039853,0.00030758927],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0010195125,0.00029808335,0.0004664873,0.00012834935,0.0006600898,0.00008209311,0.00091303245,0.00033113267,0.004851955],"category_scores_gemma":[0.00013446002,0.00030282015,0.00022151363,0.0006723842,0.00046751482,0.00066662254,0.00023322718,0.00056208554,0.0010895046],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0044059837,0.00077581505,0.5136623,0.001604981,0.0016742789,0.0068076067,0.06750546,0.015562031,0.0023218777,0.0062993756,0.034942675,0.34443763],"study_design_scores_gemma":[0.0016668151,0.00044162426,0.71562374,0.00040714102,0.00054502074,0.00048489042,0.017548062,0.022772638,0.0016717982,0.0010396416,0.2371051,0.00069353246],"about_ca_topic_score_codex":0.008919288,"about_ca_topic_score_gemma":0.015099735,"teacher_disagreement_score":0.3437441,"about_ca_system_score_codex":0.000059693277,"about_ca_system_score_gemma":0.0004884038,"threshold_uncertainty_score":0.99994236},"labels":[],"label_agreement":null},{"id":"W6965350154","doi":"10.34847/cocoon.8249ba44-9e6e-4b11-89ba-449e6e8b116c","title":"Liste de mots en rục lue par un locuteur né à Mò O Ồ Ồ en 1961","year":2021,"lang":"fr","type":"article","venue":"The COCOON platform (University of Paris)","topic":"Linguistic and Sociocultural Studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Voice; Frame (networking); Acoustic phonetics; Feature (linguistics)","score_opus":0.020706886656667572,"score_gpt":0.24255018979053714,"score_spread":0.22184330313386957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6965350154","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":[0.8770589,0.007465892,0.0007120077,0.01886345,0.0012614693,0.00035984186,0.00009353728,0.000075177006,0.09410973],"genre_scores_gemma":[0.90354913,0.009015863,0.00079712644,0.00023804259,0.00048893876,4.5346206e-7,0.0000144961095,0.000010638257,0.08588531],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982377,0.00031837635,0.0001842881,0.00028631443,0.00043032877,0.00054296566],"domain_scores_gemma":[0.99836653,0.0006403681,0.00021177036,0.00025915867,0.00034003562,0.00018213633],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00084881444,0.00020910097,0.00040787173,0.000025921745,0.0018839038,0.000044537166,0.000652716,0.000313947,0.00092842896],"category_scores_gemma":[0.00033867054,0.00019713923,0.00023846788,0.000510615,0.0011887948,0.00028932822,0.0004527773,0.0004221982,0.0002560896],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014449678,0.00031782506,0.013274513,0.00022749713,0.001090917,0.000501042,0.6195954,0.00012692178,0.00016216777,0.30416036,0.037800096,0.022598796],"study_design_scores_gemma":[0.001004871,0.00012636874,0.027270252,0.00020912258,0.0006881873,0.000016079555,0.28971568,0.00062502356,0.0002445766,0.011760709,0.6678186,0.0005205471],"about_ca_topic_score_codex":0.014142148,"about_ca_topic_score_gemma":0.005038368,"teacher_disagreement_score":0.6300185,"about_ca_system_score_codex":0.00027420468,"about_ca_system_score_gemma":0.00032904808,"threshold_uncertainty_score":0.99998486},"labels":[],"label_agreement":null},{"id":"W6965620854","doi":"10.34847/cocoon.780960ec-247d-4330-8960-ec247dc3303c","title":"Liste de mots en rục lue par une locutrice née à Mò O Ồ Ồ en 1999","year":2021,"lang":"fr","type":"article","venue":"The COCOON platform (University of Paris)","topic":"Linguistic and Sociocultural Studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Voice; Frame (networking); Southeast asia; Sound (geography); Feature (linguistics)","score_opus":0.02074028255919023,"score_gpt":0.24913377494679573,"score_spread":0.2283934923876055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6965620854","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":[0.8086936,0.014005588,0.00070498366,0.03361531,0.0013765153,0.0004101689,0.000102940525,0.00007672476,0.14101419],"genre_scores_gemma":[0.9067032,0.014460741,0.0006820527,0.0002199931,0.0005215635,4.52578e-7,0.000021472842,0.000010228094,0.07738032],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982363,0.0002873952,0.0001904891,0.00028763476,0.0004496474,0.0005485628],"domain_scores_gemma":[0.99814457,0.00082353665,0.00022985137,0.000254689,0.0003653999,0.00018193806],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0008572294,0.00020814544,0.000423397,0.00003108089,0.0018742445,0.000043238215,0.00064563996,0.00031968253,0.00076870027],"category_scores_gemma":[0.00035510567,0.00019663628,0.00023052827,0.00088933914,0.0012404743,0.00031093543,0.000418842,0.00043286866,0.00020158329],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014107578,0.00035258112,0.011007298,0.00029408417,0.00096153683,0.0004610979,0.63778156,0.00018777186,0.00016751421,0.2490947,0.08542034,0.014130417],"study_design_scores_gemma":[0.00085593184,0.000090321846,0.026243774,0.00019064592,0.0006016629,0.000011991963,0.30407354,0.0005241179,0.00011329752,0.009977421,0.6568808,0.00043648333],"about_ca_topic_score_codex":0.049088623,"about_ca_topic_score_gemma":0.010133564,"teacher_disagreement_score":0.5714605,"about_ca_system_score_codex":0.00042810684,"about_ca_system_score_gemma":0.00034502574,"threshold_uncertainty_score":0.9994252},"labels":[],"label_agreement":null},{"id":"W6980693507","doi":"","title":"Conservation²: The relationship between Kala language conservation and marine conservation in coastal Papua New Guinea","year":2015,"lang":"en","type":"other","venue":"The COCOON platform (University of Paris)","topic":"Consumer Behavior in Brand Consumption and Identification","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Fishing; Documentation; Sustainability; Pidgin; New guinea; Marine conservation","score_opus":0.0683268972693572,"score_gpt":0.24760561331283049,"score_spread":0.17927871604347329,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6980693507","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":[0.9031358,0.0005501861,0.0003602737,0.014170311,0.00042037384,0.0019367896,0.00013721272,0.0002887548,0.07900032],"genre_scores_gemma":[0.60960734,0.00015379224,0.00019041284,0.00089286413,0.00047761694,0.00000615361,0.00324563,0.00013679506,0.3852894],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99901503,0.000032565196,0.00027055305,0.00023631364,0.0002911953,0.0001543159],"domain_scores_gemma":[0.9985505,0.0002571669,0.00062194717,0.00038021652,0.0001673443,0.00002282428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060883746,0.00019742336,0.00027024464,0.00033365065,0.00022291108,0.00010761761,0.00033744617,0.00020219445,0.00082450925],"category_scores_gemma":[0.00017310954,0.00017192554,0.000047691898,0.00061887654,0.00025705877,0.00054212974,0.00022806232,0.00028193745,0.00016245995],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055281515,0.000019351923,0.5294875,0.00010295241,0.000028600205,0.0000021476199,0.00037374345,8.1707014e-7,0.000015539521,0.004030065,0.46073347,0.005150564],"study_design_scores_gemma":[0.0010321891,0.0000032224073,0.7098494,0.0001179672,0.00019092648,0.0000013046616,0.0017585235,0.00024367991,8.22259e-7,0.0011421324,0.2854844,0.00017543485],"about_ca_topic_score_codex":0.050809044,"about_ca_topic_score_gemma":0.06570235,"teacher_disagreement_score":0.3062891,"about_ca_system_score_codex":0.00003632507,"about_ca_system_score_gemma":0.00012194803,"threshold_uncertainty_score":0.9555117},"labels":[],"label_agreement":null},{"id":"W6991113458","doi":"","title":"Farming, food and yam: language and cultural practices among Ikaan speakers","year":2012,"lang":"en","type":"other","venue":"The COCOON platform (University of Paris)","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Documentation; Blessing; Variation (astronomy); Visual language; Principal (computer security); Quarter (Canadian coin)","score_opus":0.0332626246216759,"score_gpt":0.28692615549205935,"score_spread":0.25366353087038346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6991113458","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07731782,0.0010847992,0.00007254885,0.00053616916,0.00037784834,0.0003647792,0.000032254713,0.000080881226,0.9201329],"genre_scores_gemma":[0.58538765,0.0012449233,0.0004934651,0.00005179462,0.00034020483,3.3946338e-7,0.000023887716,0.000033690343,0.41242403],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.999395,0.00006146127,0.00006201729,0.0001429044,0.00015480876,0.00018382086],"domain_scores_gemma":[0.9991333,0.00009616425,0.0005128357,0.0001227872,0.00003835405,0.0000965415],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003723574,0.00010366646,0.00018408243,0.00007227952,0.00031706135,0.000027526348,0.00019657631,0.00021468186,0.0011418455],"category_scores_gemma":[0.00015927272,0.00008936801,0.000029838055,0.00008804255,0.00064715924,0.00016180304,0.000102419865,0.00016356893,0.000021437141],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009869319,0.000101632075,0.02603793,0.00020495163,0.0006083877,0.000039885785,0.5320275,2.8988381e-7,0.00006780125,0.14178991,0.2909231,0.008099949],"study_design_scores_gemma":[0.00043631377,0.000037211597,0.005546123,0.0000452896,0.00020662996,0.0000046245464,0.15516122,0.00001055687,0.0000024459048,0.00011288636,0.83825374,0.00018297585],"about_ca_topic_score_codex":0.029804267,"about_ca_topic_score_gemma":0.040323455,"teacher_disagreement_score":0.5473306,"about_ca_system_score_codex":0.000023217457,"about_ca_system_score_gemma":0.000048112557,"threshold_uncertainty_score":0.99977124},"labels":[],"label_agreement":null},{"id":"W6992928413","doi":"","title":"My Plains Cree (nêhiyawêwin) language classes","year":2015,"lang":"en","type":"other","venue":"The COCOON platform (University of Paris)","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Grammar; Sentence; Class (philosophy); Lexeme; Word (group theory); Certificate","score_opus":0.025481928825433483,"score_gpt":0.23612489978853013,"score_spread":0.21064297096309664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6992928413","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048317686,0.001680288,0.00016003862,0.00012463373,0.00026971614,0.0009048208,0.0018201374,0.0008088373,0.98939973],"genre_scores_gemma":[0.013389876,0.00025797207,0.00067011785,0.000060149763,0.00029717543,9.570522e-7,0.0007776029,0.0007960975,0.98375005],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99759865,0.000098151395,0.0002241314,0.0005323023,0.0009196089,0.00062715495],"domain_scores_gemma":[0.9970878,0.00015010801,0.00085462537,0.00144482,0.00018777474,0.00027491178],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00065551896,0.0005733809,0.00090090634,0.0006361044,0.0002546638,0.000036132747,0.001895543,0.00069023116,0.008821919],"category_scores_gemma":[0.000068120324,0.0005332838,0.0002503154,0.00082327344,0.00079488003,0.00033383636,0.00062854117,0.0007550617,0.0130356895],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023722893,0.000111678775,0.000076852986,0.00012994684,0.0004325724,0.00012280077,0.004361516,0.0000107680535,0.00018812163,0.0015955145,0.9921945,0.0005385114],"study_design_scores_gemma":[0.0016872288,0.00012239677,0.00020942872,0.00031670442,0.00046722652,0.000019768448,0.01978122,0.0001799966,0.000033627322,0.00020718576,0.9763328,0.0006424165],"about_ca_topic_score_codex":0.0070635085,"about_ca_topic_score_gemma":0.018641625,"teacher_disagreement_score":0.015861688,"about_ca_system_score_codex":0.00030729437,"about_ca_system_score_gemma":0.00050427404,"threshold_uncertainty_score":0.9997119},"labels":[],"label_agreement":null},{"id":"W7004539518","doi":"","title":"SD1-171","year":2015,"lang":"en","type":"other","venue":"The COCOON platform (University of Paris)","topic":"Nuclear Structure and Function","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Sitting; Active listening; Narrative; Clothing; Ask price; Quarter (Canadian coin)","score_opus":0.009868420482410866,"score_gpt":0.18976046380163417,"score_spread":0.1798920433192233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7004539518","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004565054,0.0011252454,0.00047886313,0.000091872535,0.0003717436,0.0002355872,0.00008454817,0.00003937976,0.9930077],"genre_scores_gemma":[0.015828429,0.0005720312,0.00034899113,0.00007999011,0.0003539745,1.5504905e-7,0.00039250494,0.00010656473,0.9823174],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995459,0.000012387056,0.000049890106,0.00016366494,0.000113993905,0.00011421689],"domain_scores_gemma":[0.99940854,0.000002955184,0.00013249298,0.00036050534,0.00004872092,0.000046774963],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000080802834,0.00012025983,0.00014874456,0.000046760044,0.00005757723,0.0000044780345,0.00026854442,0.00029652152,0.0008435364],"category_scores_gemma":[0.0000066104094,0.00010478523,0.000064992455,0.00007386522,0.00012298407,0.000002495655,0.0001344036,0.00011335262,0.00012748438],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000085045416,0.000009062227,0.000022157217,0.000020101914,0.00009589953,0.000002214245,0.00007742225,0.0000022045813,0.001597376,0.00016883605,0.99650866,0.0014110418],"study_design_scores_gemma":[0.00032152722,0.00010890863,0.000083531595,0.00001943866,0.000063759246,0.0000056301965,0.00041694666,0.000011377869,0.00013983953,0.000091713184,0.9986116,0.00012567652],"about_ca_topic_score_codex":0.00030085366,"about_ca_topic_score_gemma":0.000526413,"teacher_disagreement_score":0.011263375,"about_ca_system_score_codex":0.000010228429,"about_ca_system_score_gemma":0.00006211441,"threshold_uncertainty_score":0.92361325},"labels":[],"label_agreement":null},{"id":"W7005635526","doi":"","title":"Review of: A grammar of Sisaala-Pasaale, by Stuart McGill, Samuel Fembeti and Mike Toupin","year":2003,"lang":"en","type":"article","venue":"The COCOON platform (University of Paris)","topic":"Plant Taxonomy and Phylogenetics","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Grammar; English grammar","score_opus":0.023442853819054105,"score_gpt":0.1810264331288985,"score_spread":0.15758357930984437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7005635526","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":[0.9845631,0.010521786,0.000011147661,0.00030686933,0.000026463786,0.00028904073,0.00031280014,0.000008479074,0.0039603245],"genre_scores_gemma":[0.96982825,0.029473126,0.0002101093,0.00016119347,0.000006352881,3.724553e-7,0.00004155675,5.788057e-7,0.0002784548],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994203,0.000049092305,0.00014836964,0.00012677046,0.00012200815,0.00013347411],"domain_scores_gemma":[0.9993965,0.0001977881,0.00020871274,0.0000736997,0.00006712205,0.00005619045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030327737,0.00009363735,0.0002704607,0.00000871221,0.00014327004,0.0000024534472,0.0002377075,0.00006766892,0.00020412027],"category_scores_gemma":[0.000024025212,0.000043160657,0.0000758297,0.00022733837,0.00017764543,0.00006841349,0.000060738712,0.00007613229,0.000003944055],"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":[0.0007495525,0.0014186839,0.050242025,0.0066615194,0.0007047575,0.00001988383,0.0010975815,0.000015702404,0.38527006,0.030649867,0.18819821,0.33497217],"study_design_scores_gemma":[0.00052175566,0.0006405563,0.026196707,0.0011195469,0.00019556406,0.00001642692,0.00197675,0.000037267837,0.009450575,0.0010072762,0.95849705,0.0003405218],"about_ca_topic_score_codex":0.00035473396,"about_ca_topic_score_gemma":0.0002793502,"teacher_disagreement_score":0.77029884,"about_ca_system_score_codex":0.0000066813027,"about_ca_system_score_gemma":0.000008155309,"threshold_uncertainty_score":0.22349739},"labels":[],"label_agreement":null},{"id":"W7010663559","doi":"","title":"The KalaallisutâEnglish Dictionary Project","year":2013,"lang":"en","type":"other","venue":"The COCOON platform (University of Paris)","topic":"Medical History and Research","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Grammar; Set (abstract data type); Presentation (obstetrics); Bilingual dictionary; Language acquisition; Word (group theory); First language; Process (computing)","score_opus":0.03845799419900872,"score_gpt":0.21388864404321428,"score_spread":0.17543064984420556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7010663559","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013011848,0.0014546468,0.000019770925,0.0004520933,0.00069226784,0.00054179516,0.000052059717,0.0000928022,0.99656445],"genre_scores_gemma":[0.00079486024,0.0015722994,0.000010237705,0.000037039474,0.0006025718,0.0000022246447,0.000036737136,0.000056216373,0.9968878],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99903345,0.00005556512,0.00010207242,0.0001603062,0.00041108803,0.00023751013],"domain_scores_gemma":[0.99909407,0.0001939967,0.00018400152,0.00037507588,0.000091661845,0.0000612202],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00030826154,0.00014610648,0.00020892396,0.00011283492,0.0011791481,0.000043442597,0.00076205836,0.0001490209,0.024218272],"category_scores_gemma":[0.000020614087,0.000085031505,0.00011897512,0.000058185746,0.0019840912,0.00011501854,0.00016998584,0.00048623068,0.0007462586],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028669801,0.000028186958,0.0000017068986,0.00006361721,0.000099148565,0.0000054241473,0.006865385,1.4154999e-7,4.803954e-7,0.111367576,0.8791263,0.0024133702],"study_design_scores_gemma":[0.00019245797,0.000054518037,0.000007834744,0.00009849153,0.00004334537,0.0000010810961,0.013259709,0.0000732498,2.9508018e-7,0.00037605446,0.98578006,0.000112900634],"about_ca_topic_score_codex":0.003755468,"about_ca_topic_score_gemma":0.0030346436,"teacher_disagreement_score":0.11099152,"about_ca_system_score_codex":0.000041016312,"about_ca_system_score_gemma":0.00013294062,"threshold_uncertainty_score":0.9766737},"labels":[],"label_agreement":null},{"id":"W7014026024","doi":"","title":"SD1-048","year":2015,"lang":"en","type":"other","venue":"The COCOON platform (University of Paris)","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Session (web analytics); Period (music); Quarter (Canadian coin); Spike (software development)","score_opus":0.030803792732969803,"score_gpt":0.21785076280610371,"score_spread":0.18704697007313392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7014026024","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00051397434,0.0009198309,0.00011975811,0.00010147649,0.00025480016,0.0006437285,0.0007130337,0.00051763194,0.99621576],"genre_scores_gemma":[0.0031716046,0.00019544868,0.00042898156,0.000028425284,0.0001592778,3.5051485e-7,0.00031106407,0.0005692939,0.99513555],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99825644,0.00005727264,0.00015301142,0.0003814506,0.0007119063,0.00043989823],"domain_scores_gemma":[0.9977225,0.00006352359,0.00068797363,0.0011378448,0.00018109112,0.00020703397],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005841269,0.0003972044,0.0006716237,0.0004541942,0.00017604658,0.000017448718,0.0014874556,0.00052271795,0.011049555],"category_scores_gemma":[0.000028895292,0.00036853473,0.00018006463,0.0006758538,0.00063170824,0.00020685614,0.0004968152,0.0005330382,0.024499627],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014757695,0.000062775216,0.000039049548,0.00007267322,0.00028185532,0.00003282073,0.0011230388,0.0000059014696,0.000045462784,0.0023027817,0.9954275,0.0004586002],"study_design_scores_gemma":[0.0011013808,0.000071899965,0.000093363466,0.00020103753,0.00032392825,0.000010906376,0.0028712086,0.0001383338,0.0000075115363,0.00058795174,0.994173,0.0004195158],"about_ca_topic_score_codex":0.004618068,"about_ca_topic_score_gemma":0.0053245607,"teacher_disagreement_score":0.013450073,"about_ca_system_score_codex":0.00021678167,"about_ca_system_score_gemma":0.00035282227,"threshold_uncertainty_score":0.9998767},"labels":[],"label_agreement":null},{"id":"W7019583102","doi":"","title":"The Haíɫzaqv Language Mobilization Partnership: Collaboration & Mobilization on BC’s Central Coast","year":2017,"lang":"en","type":"article","venue":"The COCOON platform (University of Paris)","topic":"Multilingual Education and Policy","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"BELLA; Documentation; Language revitalization; Interpretation (philosophy); Curriculum; Written language; On Language","score_opus":0.0705340448402564,"score_gpt":0.3965605477537804,"score_spread":0.32602650291352403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7019583102","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":[0.9578216,0.00004469204,0.00030508693,0.0056669917,0.00036315204,0.00053928973,0.000012623636,0.000051349987,0.035195187],"genre_scores_gemma":[0.98541415,0.00023407015,0.0000313416,0.0000839699,0.00013351296,0.0000011492319,0.00003152342,0.000005159391,0.014065109],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990664,0.0001506279,0.00010939784,0.00013346215,0.00030680932,0.00023328839],"domain_scores_gemma":[0.9986511,0.00025127007,0.0003253876,0.0004491042,0.0002294826,0.000093692],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0008741574,0.00008377977,0.00009885496,0.000040199982,0.0038795562,0.00018004341,0.0005657632,0.00009435301,0.00018386249],"category_scores_gemma":[0.0005567123,0.000067469075,0.00004617215,0.00019208345,0.0005238009,0.0004292966,0.000051277064,0.00011278791,0.000079185804],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008568035,0.00025076664,0.01034232,0.00003593928,0.0000618285,0.0000016852915,0.65703595,0.0011390696,0.0006379133,0.26849934,0.03435307,0.026785322],"study_design_scores_gemma":[0.00089637074,0.000079049314,0.050119657,0.00004589326,0.000056334076,3.9484468e-7,0.3197058,0.0024034209,0.00033468768,0.0008763503,0.62524015,0.00024190379],"about_ca_topic_score_codex":0.01092254,"about_ca_topic_score_gemma":0.06947914,"teacher_disagreement_score":0.59088707,"about_ca_system_score_codex":0.00017207432,"about_ca_system_score_gemma":0.0003627412,"threshold_uncertainty_score":0.9974173},"labels":[],"label_agreement":null},{"id":"W7037437231","doi":"","title":"Documentation of Under-Represented Genres of Passamaquoddy-Maliseet Linguistic Practice","year":2007,"lang":"en","type":"other","venue":"The COCOON platform (University of Paris)","topic":"Diverse Musicological Studies","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Documentation; Period (music); Set (abstract data type); Spoken language; Data collection; Variety (cybernetics)","score_opus":0.08490079654670776,"score_gpt":0.26378368543960207,"score_spread":0.1788828888928943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7037437231","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022940794,0.00046315716,0.0002880009,0.00021102907,0.00033035086,0.00043450188,0.00017067794,0.000053967065,0.99575424],"genre_scores_gemma":[0.2453776,0.0009364381,0.00064056914,0.00017074283,0.00034888813,0.0000010102066,0.00012419723,0.00009328684,0.75230724],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.998984,0.00004815138,0.00022077553,0.00018185616,0.00039150091,0.00017372679],"domain_scores_gemma":[0.9978638,0.00050816016,0.0010029156,0.00025621415,0.00033328382,0.000035605986],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003063887,0.00017829586,0.00045507116,0.0002340814,0.000179076,0.000025597481,0.0003992013,0.00013037243,0.010372773],"category_scores_gemma":[0.00014636619,0.00014758485,0.00013448014,0.00010915822,0.0010169498,0.000142994,0.00025330175,0.00017011042,0.00007593452],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047283064,0.00033737553,0.00006694497,0.00036849803,0.0011582674,0.000023695016,0.022342876,0.000035129866,0.000036487687,0.5744983,0.39963967,0.001019954],"study_design_scores_gemma":[0.00062932965,0.00017785431,0.00011384332,0.00017303845,0.00057643035,7.398951e-7,0.06429236,0.000023719782,0.000023939812,0.0010328665,0.9327821,0.00017377747],"about_ca_topic_score_codex":0.0130207045,"about_ca_topic_score_gemma":0.0027703326,"teacher_disagreement_score":0.5734654,"about_ca_system_score_codex":0.000043995467,"about_ca_system_score_gemma":0.000036572437,"threshold_uncertainty_score":0.9935517},"labels":[],"label_agreement":null},{"id":"W7038219252","doi":"","title":"Gwichâin Caribou anatomy and verbal art","year":2015,"lang":"en","type":"other","venue":"The COCOON platform (University of Paris)","topic":"Subterranean biodiversity and taxonomy","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Metaphor; Literal and figurative language; Subsistence agriculture; Endangered species; Eagle; Ethnography","score_opus":0.027484990147887616,"score_gpt":0.17870650079524922,"score_spread":0.1512215106473616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7038219252","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008686632,0.0015455828,0.000049475595,0.00017410409,0.00026035943,0.0003088829,0.0009921893,0.00008392622,0.9878988],"genre_scores_gemma":[0.16437277,0.001571101,0.0008677975,0.00024293485,0.00027057595,1.0650186e-7,0.0023668627,0.00004682562,0.830261],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99919575,0.000030030347,0.00007542847,0.00023265187,0.0002462514,0.00021988922],"domain_scores_gemma":[0.99932224,0.000057502424,0.00017405099,0.00026230732,0.00003341491,0.00015051114],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00020056624,0.00018305703,0.00029812584,0.00014947531,0.00018851012,0.000021171705,0.00043720973,0.00023550329,0.013709171],"category_scores_gemma":[0.0000051386287,0.00016214701,0.000060993312,0.00019425908,0.00043342926,0.00016003213,0.000069091366,0.00022930681,0.000968716],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009170394,0.000009078608,0.01215245,0.00004458219,0.00011541967,0.00003829893,0.0008107067,0.0000070136853,1.5858151e-7,0.00006052449,0.98265886,0.0040112045],"study_design_scores_gemma":[0.00055662624,0.00007246589,0.0056584803,0.000046453915,0.00011623527,0.000012026954,0.002555106,0.000292546,6.871772e-7,0.0000981654,0.9903771,0.00021409456],"about_ca_topic_score_codex":0.013343897,"about_ca_topic_score_gemma":0.027105017,"teacher_disagreement_score":0.15763782,"about_ca_system_score_codex":0.000008400997,"about_ca_system_score_gemma":0.00009225799,"threshold_uncertainty_score":0.99980915},"labels":[],"label_agreement":null},{"id":"W7039790316","doi":"","title":"Na masu'u kia 'i Kwara'ae : tualaka 'i Solomon Islands fa'inia logo na ruÌ bulao kiÌ saena fanoa kia = Our forest of Kwara'ae : our life in Solomon Islands and the things growing in our home","year":2001,"lang":"en","type":"article","venue":"The COCOON platform (University of Paris)","topic":"New Zealand Economic and Social Studies","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Jungle; Metis; Ethnography; Folk song","score_opus":0.02280808329436275,"score_gpt":0.19894887481347562,"score_spread":0.17614079151911288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7039790316","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":[0.9848856,0.0013851541,0.0002740801,0.0032125919,0.0002802482,0.00046875427,0.000075338176,0.00003073728,0.009387507],"genre_scores_gemma":[0.9944152,0.0038863837,0.000052224226,0.00024244435,0.00008808433,0.0000039008373,0.000022347846,0.000025379431,0.0012639967],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99803543,0.000045884728,0.00072412926,0.00047471552,0.00010306718,0.00061678456],"domain_scores_gemma":[0.99859536,0.00012920261,0.000733987,0.0003832388,0.00004623831,0.000111993984],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015262567,0.00033327687,0.00121666,0.00036482562,0.00047021284,0.00005169447,0.0006702646,0.0002970758,0.000026185364],"category_scores_gemma":[0.00008120841,0.00030251907,0.00023636941,0.00045561037,0.00017232432,0.0008589765,0.00040721233,0.00052015384,0.000062936786],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013319306,0.0001884098,0.90435684,0.00013551148,0.0003779438,0.000039234757,0.07379708,0.00042125751,0.00002000926,0.015793283,0.0022852065,0.0012532824],"study_design_scores_gemma":[0.018149996,0.00050057325,0.6062492,0.00028257095,0.00015821854,0.00002629683,0.29804212,0.023737386,0.000020433685,0.04749826,0.003919838,0.0014151153],"about_ca_topic_score_codex":0.008735653,"about_ca_topic_score_gemma":0.004413676,"teacher_disagreement_score":0.29810765,"about_ca_system_score_codex":0.0001774962,"about_ca_system_score_gemma":0.000059067934,"threshold_uncertainty_score":0.9999427},"labels":[],"label_agreement":null},{"id":"W7045160596","doi":"","title":"Across mountain and sea: Bringing language to linguists","year":2015,"lang":"en","type":"other","venue":"The COCOON platform (University of Paris)","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Outreach; Parallels; Scope (computer science); Work (physics); Field (mathematics); Linguistic landscape; Speech community","score_opus":0.017952611474545264,"score_gpt":0.26459438914545313,"score_spread":0.24664177767090786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7045160596","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19645432,0.0033965735,0.00028907578,0.00019928464,0.00032825704,0.001678026,0.0023737266,0.00089264574,0.7943881],"genre_scores_gemma":[0.12259447,0.000104000035,0.0009032019,0.00007968499,0.0002932276,7.625984e-7,0.00023138424,0.00064352865,0.8751497],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984654,0.00003549816,0.00012477409,0.00040946144,0.00046446364,0.00050040125],"domain_scores_gemma":[0.9984627,0.000058582926,0.00032202245,0.0007055338,0.000131645,0.0003195606],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007664288,0.000338164,0.00051527313,0.00028284107,0.00022706944,0.000042239255,0.0007475135,0.0002498649,0.00053468853],"category_scores_gemma":[0.00008910208,0.00034182993,0.000074620046,0.000496712,0.00029916182,0.000116086565,0.0008016614,0.00038137124,0.0019209214],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028316656,0.00003888678,0.0006723763,0.00021554595,0.0002175145,0.0001788459,0.027908025,0.000035488494,0.0001742154,0.0004316628,0.968678,0.0011663021],"study_design_scores_gemma":[0.0011317981,0.00006211798,0.0011547996,0.0006021679,0.00016973609,0.0000162472,0.021791605,0.0005629759,0.000025753096,0.000102506565,0.9737762,0.00060405623],"about_ca_topic_score_codex":0.010938987,"about_ca_topic_score_gemma":0.013328487,"teacher_disagreement_score":0.08076165,"about_ca_system_score_codex":0.00021162821,"about_ca_system_score_gemma":0.00014201486,"threshold_uncertainty_score":0.9999034},"labels":[],"label_agreement":null},{"id":"W7071730253","doi":"","title":"Vadzaih Tthâan Oozhriâ and Gwichâin culture","year":2015,"lang":"en","type":"other","venue":"The COCOON platform (University of Paris)","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nothing; Butcher; Bit (key); Proper noun; Toponymy","score_opus":0.021233200307087467,"score_gpt":0.21183801831224677,"score_spread":0.1906048180051593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071730253","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020818424,0.0035288015,0.00007787618,0.00013329762,0.00019745562,0.00088042,0.0010520997,0.00047665669,0.99157155],"genre_scores_gemma":[0.00573434,0.0008357961,0.0006882035,0.000043244923,0.00017545688,5.2983046e-7,0.00039158395,0.00048920023,0.99164164],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982346,0.00006815043,0.00016166377,0.00047712738,0.0006180964,0.0004403573],"domain_scores_gemma":[0.99798363,0.000047266607,0.00063933094,0.0008805803,0.00018127488,0.00026794153],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00051124115,0.00048311474,0.00074508286,0.00036209566,0.0002442067,0.000031414806,0.0010058596,0.0006949996,0.0027310743],"category_scores_gemma":[0.000029213215,0.00041807658,0.00013317492,0.0005766368,0.0007729508,0.000268655,0.00052220904,0.0006580104,0.0033528914],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001759607,0.00005679798,0.000085907646,0.000118829776,0.00031954085,0.00003417337,0.00409864,0.000002828529,0.00009918525,0.0016612274,0.9926924,0.0006545262],"study_design_scores_gemma":[0.0015235763,0.000108648,0.00022569507,0.0002824093,0.00045446245,0.00002528714,0.0064242166,0.0001226095,0.000012129819,0.0007056922,0.9896027,0.00051261624],"about_ca_topic_score_codex":0.0028531097,"about_ca_topic_score_gemma":0.0051967837,"teacher_disagreement_score":0.0036524974,"about_ca_system_score_codex":0.00015353535,"about_ca_system_score_gemma":0.00021644738,"threshold_uncertainty_score":0.9998271},"labels":[],"label_agreement":null},{"id":"W7115211671","doi":"","title":"Word order in Nuuchahnulth","year":2004,"lang":"en","type":"other","venue":"The COCOON platform (University of Paris)","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Word (group theory); Word order; Order (exchange); Sound (geography)","score_opus":0.017002597066906513,"score_gpt":0.21387449305921408,"score_spread":0.19687189599230756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7115211671","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005580551,0.0008688852,0.00045497948,0.0002513796,0.0002274838,0.0013558727,0.00028509452,0.00044801342,0.99052775],"genre_scores_gemma":[0.025813464,0.00074478734,0.0016124067,0.00006035607,0.00012015374,0.0000012947926,0.00021762561,0.0008491015,0.9705808],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982243,0.000051054274,0.00020610416,0.00045227568,0.0005304568,0.00053576776],"domain_scores_gemma":[0.99818087,0.00007123897,0.0006144722,0.00092209055,0.000091800466,0.00011954946],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00041070214,0.00043076443,0.0007261487,0.0008343224,0.000136077,0.000015933623,0.0012684471,0.0005669786,0.009263976],"category_scores_gemma":[0.000026912017,0.00041837877,0.00015520789,0.0014937733,0.0005310383,0.00021342735,0.0003482912,0.000742629,0.007768661],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047594967,0.00035186554,0.00064988574,0.00028210098,0.00036258597,0.00017017158,0.00463392,0.00027217844,0.00008398544,0.008626397,0.9811988,0.0028921491],"study_design_scores_gemma":[0.003918815,0.000084323205,0.0020583381,0.0011540869,0.00022362536,0.000013651847,0.0055941166,0.00018703521,0.000016721257,0.0017785333,0.9841329,0.0008378583],"about_ca_topic_score_codex":0.017257452,"about_ca_topic_score_gemma":0.039197676,"teacher_disagreement_score":0.021940222,"about_ca_system_score_codex":0.00044604775,"about_ca_system_score_gemma":0.0004393746,"threshold_uncertainty_score":0.9998268},"labels":[],"label_agreement":null},{"id":"W7115212505","doi":"","title":"ENCHASQU_CD71_01","year":2010,"lang":"","type":"other","venue":"The COCOON platform (University of Paris)","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"","score_opus":0.016170870509461904,"score_gpt":0.20178812437956298,"score_spread":0.18561725387010108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7115212505","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031012373,0.0016174669,0.0012392348,0.00048602102,0.001817303,0.0031747562,0.0009735803,0.0004181048,0.9592612],"genre_scores_gemma":[0.14578123,0.0021906213,0.0014704156,0.00007825161,0.0005842311,0.0000015036204,0.00021936618,0.0010971073,0.84857726],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99455476,0.00020594391,0.0006621524,0.0013450858,0.0016878373,0.001544236],"domain_scores_gemma":[0.99161136,0.00050060125,0.0030211073,0.003627533,0.0006149326,0.0006244856],"candidate_categories":["metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","sts","research_integrity","insufficient_payload"],"category_scores_codex":[0.0018648027,0.0014102607,0.0020239425,0.0012178842,0.0014786783,0.000097003016,0.0053082597,0.0025442308,0.1395205],"category_scores_gemma":[0.000105525214,0.0014068924,0.0009945043,0.001991718,0.004255823,0.0008307837,0.0018394748,0.0039738184,0.06774073],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028214415,0.0016233018,0.00086678186,0.0011009437,0.004006056,0.00039088077,0.021852087,0.00009452899,0.012647292,0.032407943,0.8917392,0.03044958],"study_design_scores_gemma":[0.0034094716,0.00035499432,0.0016402128,0.00070562144,0.001859687,0.00006969673,0.010023143,0.0014245644,0.0002449389,0.0012200093,0.9774279,0.0016197382],"about_ca_topic_score_codex":0.0062376345,"about_ca_topic_score_gemma":0.012320282,"teacher_disagreement_score":0.114768855,"about_ca_system_score_codex":0.00040880727,"about_ca_system_score_gemma":0.0009531906,"threshold_uncertainty_score":0.99986476},"labels":[],"label_agreement":null},{"id":"W7115215606","doi":"","title":"Canadian Speaking English Speech Data by Mobile Phone - 207 Hours","year":2022,"lang":"en","type":"other","venue":"The COCOON platform (University of Paris)","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Phone; Mobile phone; Control (management); Transcription (linguistics); Domain (mathematical analysis); Mobile device","score_opus":0.021430881336535382,"score_gpt":0.21852250627570322,"score_spread":0.19709162493916782,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7115215606","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0059666773,0.002103627,0.00002938327,0.00008157221,0.0007892535,0.0017070175,0.030350996,0.00057111826,0.95840037],"genre_scores_gemma":[0.017954875,0.0011709342,0.0008401896,0.00015459402,0.00058121834,0.000004241122,0.023626415,0.0018398718,0.9538277],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99694,0.00010721302,0.00022884722,0.0008944876,0.00092171493,0.00090771855],"domain_scores_gemma":[0.9953033,0.00011646061,0.00080614974,0.0032016195,0.000117942465,0.00045457692],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0010147018,0.00055125676,0.00079008675,0.00086647185,0.00067351805,0.000058023197,0.005417809,0.00044692718,0.09753003],"category_scores_gemma":[0.000057997102,0.00062205206,0.0001550213,0.0011852331,0.0004328366,0.0005652291,0.0020346497,0.0011856488,0.003388261],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000070979746,0.00007319545,0.00031424352,0.000052617434,0.00040877305,0.00017606535,0.0024930583,0.000019585881,0.00003790726,0.00006330142,0.993928,0.0023622601],"study_design_scores_gemma":[0.000916642,0.000056577155,0.000060465492,0.000112883,0.0003836278,0.000015310634,0.0190535,0.00019767972,0.000012663052,0.000019297211,0.9785004,0.0006709147],"about_ca_topic_score_codex":0.7687765,"about_ca_topic_score_gemma":0.8312569,"teacher_disagreement_score":0.09414177,"about_ca_system_score_codex":0.0013408321,"about_ca_system_score_gemma":0.0010390823,"threshold_uncertainty_score":0.99996334},"labels":[],"label_agreement":null},{"id":"W7115271236","doi":"","title":"Optimizing translation training at Canada Institute of LInguistics","year":2013,"lang":"","type":"article","venue":"The COCOON platform (University of Paris)","topic":"Translation Studies and Practices","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Training (meteorology); Translation (biology); Computational linguistics; Translation studies","score_opus":0.08210391046825571,"score_gpt":0.22100942690737627,"score_spread":0.13890551643912055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7115271236","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42600542,0.011077282,0.0027470156,0.004969005,0.0042768097,0.0018278301,0.00054328016,0.00006624575,0.5484871],"genre_scores_gemma":[0.9953243,0.001669928,0.0008067139,0.00005046145,0.00016772516,4.126232e-7,0.000027939828,0.000011773672,0.00194074],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987607,0.000035702044,0.000368562,0.0001876044,0.00036653865,0.00028091736],"domain_scores_gemma":[0.9981883,0.00039725876,0.0006347475,0.00023874702,0.00046027123,0.0000806457],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00025859236,0.00020359858,0.0004217723,0.00007310071,0.0015230731,0.00004999519,0.00031761389,0.00008695505,0.0024960989],"category_scores_gemma":[0.000022821492,0.0001932735,0.0001268459,0.00012321933,0.0006498399,0.00058929244,0.000077062556,0.00024924424,0.000019861049],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009111028,0.00018882829,0.0005111434,0.0011015843,0.001825466,0.000021643118,0.69641626,0.010299844,0.00024515265,0.10948715,0.0188907,0.16010115],"study_design_scores_gemma":[0.0008377917,0.000092562936,0.00044248864,0.00014120438,0.00039464643,0.0000013011571,0.0858456,0.0072395494,0.000031684227,0.00029099683,0.9044394,0.00024280034],"about_ca_topic_score_codex":0.5657734,"about_ca_topic_score_gemma":0.80246884,"teacher_disagreement_score":0.88554865,"about_ca_system_score_codex":0.00008667836,"about_ca_system_score_gemma":0.00036410007,"threshold_uncertainty_score":0.9997768},"labels":[],"label_agreement":null},{"id":"W7115271798","doi":"","title":"Comparison of success factors of Canadian First Nations bilingual education and Chinese minorities bilingual education","year":2005,"lang":"","type":"article","venue":"The COCOON platform (University of Paris)","topic":"Multilingual Education and Policy","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Bilingual education; Neuroscience of multilingualism; Ethnic group; Higher education; Success factors","score_opus":0.051219997300355445,"score_gpt":0.3794956449031409,"score_spread":0.3282756476027855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7115271798","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":[0.9670165,0.0013619285,0.0000054234856,0.0020698782,0.0008274764,0.0005623351,0.00011194166,0.000012785135,0.028031738],"genre_scores_gemma":[0.9941268,0.0011401769,0.00025520095,0.0000354396,0.00027283857,6.5795865e-7,0.000070514696,0.000010697864,0.004087702],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9983426,0.00010785384,0.00052656414,0.00027067232,0.00041800062,0.00033434245],"domain_scores_gemma":[0.99682844,0.0007372062,0.0008495535,0.00033910386,0.00089372677,0.00035198705],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0005526219,0.00023438128,0.00048854965,0.001340441,0.0015181904,0.000041078194,0.00062992517,0.0002501366,0.0006845617],"category_scores_gemma":[0.0005550995,0.00023431782,0.0001340394,0.0020340658,0.0012478927,0.00064362824,0.000078664496,0.0002570496,0.000008465506],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056351066,0.0011686997,0.22368555,0.00040992838,0.00008668344,7.643726e-8,0.72206295,0.00019089616,0.00006485346,0.026566843,0.001247237,0.02445992],"study_design_scores_gemma":[0.00047446994,0.00013841911,0.1577726,0.00029417424,0.0002238054,0.0000014597714,0.7711121,0.001214036,0.0005736922,0.00031284086,0.06750215,0.00038024492],"about_ca_topic_score_codex":0.7323887,"about_ca_topic_score_gemma":0.92881423,"teacher_disagreement_score":0.19642557,"about_ca_system_score_codex":0.00028494207,"about_ca_system_score_gemma":0.011781421,"threshold_uncertainty_score":0.99978167},"labels":[],"label_agreement":null},{"id":"W7115274031","doi":"","title":"Bitext Lexical Dataset - Language Variants - French","year":2023,"lang":"fr","type":"article","venue":"The COCOON platform (University of Paris)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Complement (music); Vocabulary; Variation (astronomy); French; Lexical item; Component (thermodynamics)","score_opus":0.037266910510041856,"score_gpt":0.27085167011762323,"score_spread":0.23358475960758138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7115274031","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":[0.12927365,0.047681022,0.743975,0.05067752,0.004403052,0.0023102723,0.0074843056,0.0037053528,0.01048985],"genre_scores_gemma":[0.7876252,0.0021858774,0.14141886,0.0012045592,0.00047671993,0.0000023152706,0.0026054832,0.000074011616,0.064406954],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982611,0.00009143341,0.00019450542,0.0004397456,0.00047118723,0.00054205203],"domain_scores_gemma":[0.9981856,0.00028501407,0.00023773251,0.0010246702,0.00012025938,0.00014676615],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008695842,0.00022759399,0.00031760504,0.00022483342,0.0004953071,0.00012458133,0.0025071525,0.00025906455,0.0005350005],"category_scores_gemma":[0.000081923696,0.00021338747,0.0001036024,0.0018427488,0.0005296414,0.0015207978,0.0016731916,0.00057051034,0.00109765],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005684131,0.00016189303,0.00013502252,0.00032455695,0.00013445641,0.001140718,0.019359639,0.000032744734,0.0021037648,0.14433199,0.725095,0.10712339],"study_design_scores_gemma":[0.003516878,0.0009878846,0.009787998,0.0019719962,0.00064352376,0.000530622,0.012727183,0.30751634,0.0061456445,0.15897794,0.4945368,0.002657208],"about_ca_topic_score_codex":0.005784952,"about_ca_topic_score_gemma":0.00045378218,"teacher_disagreement_score":0.65835154,"about_ca_system_score_codex":0.00007626991,"about_ca_system_score_gemma":0.0001865118,"threshold_uncertainty_score":0.9996801},"labels":[],"label_agreement":null},{"id":"W7115327217","doi":"","title":"Dene Text Collection with a Special Focus on the Relationship between the Language and the Land","year":2007,"lang":"en","type":"other","venue":"The COCOON platform (University of Paris)","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Focus (optics); Data collection; Object (grammar); Natural language","score_opus":0.026763055473363634,"score_gpt":0.2246472662232538,"score_spread":0.19788421074989015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7115327217","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10966862,0.00058861886,0.0005425319,0.002683826,0.00012400482,0.0029298957,0.00031698472,0.0001812088,0.8829643],"genre_scores_gemma":[0.68107456,0.00010404573,0.00007860163,0.000076133256,0.0010028661,0.000003718203,0.000068227695,0.00028097577,0.3173109],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983711,0.00025423852,0.00015398342,0.0002892128,0.0006172208,0.00031419052],"domain_scores_gemma":[0.9956029,0.0028667618,0.00061425986,0.00079490035,0.000060418235,0.00006074003],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016317382,0.00032744493,0.00042052247,0.00032117876,0.001279079,0.000061613784,0.00081889686,0.0002985842,0.0010559008],"category_scores_gemma":[0.00011305862,0.00014882935,0.000118916505,0.0010584894,0.0014989978,0.0001042646,0.0001837903,0.0009273046,0.0006509508],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0050035804,0.00008206951,0.05505533,0.00006114667,0.0011056891,0.000035180405,0.02128104,0.000026209711,0.0000039970782,0.049440943,0.86549145,0.002413386],"study_design_scores_gemma":[0.016657826,0.0006926391,0.40111208,0.0011576575,0.0039225523,0.000107119355,0.06016248,0.00040632312,0.00004498309,0.008757668,0.5054801,0.0014985442],"about_ca_topic_score_codex":0.0056226957,"about_ca_topic_score_gemma":0.021490237,"teacher_disagreement_score":0.57140595,"about_ca_system_score_codex":0.00014900016,"about_ca_system_score_gemma":0.00012171477,"threshold_uncertainty_score":0.99985725},"labels":[],"label_agreement":null},{"id":"W7115353146","doi":"","title":"French Speech Data by Mobile Phone_Reading - 231 Hours","year":2022,"lang":"fr","type":"other","venue":"The COCOON platform (University of Paris)","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Noise (video); Sentence; Point (geometry); QUIET; Identifier; Background noise; Volume (thermodynamics)","score_opus":0.027635161354668723,"score_gpt":0.23218619830146286,"score_spread":0.20455103694679413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7115353146","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10175977,0.030181058,0.0011130502,0.0005274889,0.0020064912,0.0054978207,0.03665527,0.00071871706,0.82154036],"genre_scores_gemma":[0.022417456,0.0062048226,0.0018465804,0.0000649255,0.000342704,0.000005987148,0.011305611,0.001043029,0.9567689],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99469835,0.00033005167,0.000504061,0.0015682541,0.0015876825,0.0013115839],"domain_scores_gemma":[0.9921715,0.000585243,0.0017839395,0.0048648855,0.00017053784,0.0004238407],"candidate_categories":["metaepi_narrow","sts","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0016620563,0.0010257369,0.0015409857,0.0006968962,0.0014704595,0.00009422577,0.008475567,0.00077673193,0.27456906],"category_scores_gemma":[0.000077516626,0.0011511183,0.0003929789,0.0020617913,0.001607652,0.0012451829,0.006490558,0.0021839272,0.01785084],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019866506,0.0005887898,0.0013314872,0.00030766317,0.0013685152,0.00025374055,0.004482827,0.00020609736,0.0013634961,0.00046917345,0.9656316,0.023797937],"study_design_scores_gemma":[0.0019251172,0.00029092905,0.00052645797,0.00041002242,0.0015732978,0.00011028029,0.015924612,0.0036248867,0.000120930905,0.000121435136,0.9741485,0.001223515],"about_ca_topic_score_codex":0.02931377,"about_ca_topic_score_gemma":0.0072097722,"teacher_disagreement_score":0.25671822,"about_ca_system_score_codex":0.001547651,"about_ca_system_score_gemma":0.00069248676,"threshold_uncertainty_score":0.9998295},"labels":[],"label_agreement":null},{"id":"W7115402128","doi":"","title":"28th LACUS Forum, Université du Québec à Montréal, July 31-Aug. 4, 2001","year":2001,"lang":"","type":"article","venue":"The COCOON platform (University of Paris)","topic":"Intellectual Property Law","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Field (mathematics); Natural (archaeology); Exposition (narrative)","score_opus":0.02295548676933762,"score_gpt":0.20171733750572343,"score_spread":0.1787618507363858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7115402128","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40394837,0.0036130124,0.0016693282,0.03353019,0.00081718556,0.0017332602,0.0000693365,0.00033379064,0.5542855],"genre_scores_gemma":[0.908934,0.012034502,0.00010589214,0.000428075,0.00018700295,4.5492922e-7,0.0000095279165,0.000036150304,0.07826441],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99627656,0.0002382626,0.0004156341,0.0006572845,0.0010401775,0.0013720741],"domain_scores_gemma":[0.996753,0.0006424657,0.00061258517,0.0008428865,0.0006599679,0.00048912154],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["sts","insufficient_payload"],"category_scores_codex":[0.001201452,0.00051900966,0.00077017484,0.00026042873,0.004461978,0.00010689048,0.0025874313,0.00052413787,0.0071090884],"category_scores_gemma":[0.00019353478,0.00048554543,0.0005004958,0.0017725623,0.0027504105,0.0015644265,0.0009196382,0.00084862777,0.0032711732],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002306178,0.00050968124,0.0013105515,0.00005691608,0.00054729386,0.00028940392,0.123976946,0.00035216342,0.0001764729,0.009339746,0.8491737,0.011960911],"study_design_scores_gemma":[0.0015212732,0.00046827053,0.00060994824,0.00010878703,0.00040153405,0.000030028377,0.12941056,0.0068367408,0.000055171666,0.0005274699,0.85941315,0.00061702955],"about_ca_topic_score_codex":0.601351,"about_ca_topic_score_gemma":0.54166365,"teacher_disagreement_score":0.50498563,"about_ca_system_score_codex":0.0012756264,"about_ca_system_score_gemma":0.0019424343,"threshold_uncertainty_score":0.9999635},"labels":[],"label_agreement":null},{"id":"W7115406272","doi":"","title":"Nuu-chah-nulth (Ahousaht) language recordings","year":2002,"lang":"en","type":"other","venue":"The COCOON platform (University of Paris)","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Vowel; Pronunciation; Word (group theory); Diphthong; Natural language","score_opus":0.01715502655023602,"score_gpt":0.20491817813989208,"score_spread":0.18776315158965606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7115406272","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0065862355,0.0012950338,0.0002578683,0.00015281086,0.00032637763,0.0010063035,0.00069845485,0.00100828,0.9886686],"genre_scores_gemma":[0.01361845,0.0009399792,0.00088334345,0.00005961096,0.00023810998,8.83764e-7,0.00019411572,0.0008751922,0.9831903],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99770725,0.00007531406,0.00024405247,0.0006037283,0.0006982921,0.0006713805],"domain_scores_gemma":[0.9971615,0.00013308132,0.0010432637,0.0013517428,0.000101455276,0.00020897691],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00048540015,0.00058766286,0.00091032084,0.00067744654,0.00032068143,0.00003325934,0.0016837445,0.0006554602,0.031210335],"category_scores_gemma":[0.000040078718,0.00056335557,0.00035046137,0.00083106675,0.00057724386,0.00029338858,0.00047703084,0.0008294953,0.02102776],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013283342,0.0001081667,0.00008987743,0.0001532516,0.00031333545,0.00011218116,0.0048766495,0.000006813897,0.00020625658,0.00080067327,0.98959863,0.003601339],"study_design_scores_gemma":[0.0016430599,0.00012249095,0.00018119,0.0005316239,0.00047333288,0.00003144629,0.010937201,0.00047139375,0.00005243534,0.00013341151,0.9845993,0.00082311267],"about_ca_topic_score_codex":0.0116671175,"about_ca_topic_score_gemma":0.0039765094,"teacher_disagreement_score":0.010182574,"about_ca_system_score_codex":0.00028474553,"about_ca_system_score_gemma":0.00009610313,"threshold_uncertainty_score":0.9996818},"labels":[],"label_agreement":null},{"id":"W7115422580","doi":"","title":"Glottalization in Nuu-chah-nulth: Ahousaht and Ditidaht","year":2000,"lang":"en","type":"other","venue":"The COCOON platform (University of Paris)","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Field (mathematics); Lexical item; Word (group theory); Vocabulary","score_opus":0.011545890530136918,"score_gpt":0.1959299189167279,"score_spread":0.184384028386591,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7115422580","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031618092,0.0013507402,0.00024890734,0.00012622756,0.00014471868,0.0013219644,0.00075685687,0.00043804964,0.96399444],"genre_scores_gemma":[0.19243324,0.005975086,0.0006035323,0.00010109337,0.00023387815,0.0000028080485,0.0011684035,0.0012817278,0.79820025],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984789,0.00007043702,0.00020531731,0.00043937017,0.00041501797,0.00039094506],"domain_scores_gemma":[0.9987012,0.00008060847,0.00047536436,0.0005931445,0.000035610075,0.000114045826],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00027042907,0.00038117406,0.00060291943,0.0006796238,0.00016911054,0.000025058484,0.0006023298,0.00049402186,0.004655394],"category_scores_gemma":[0.000013181961,0.00038838718,0.000095039206,0.0007552322,0.00051210943,0.00029854002,0.00019995419,0.00039063732,0.0012789852],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048019743,0.00022115007,0.0024336474,0.000310799,0.0002501245,0.00009525877,0.004268093,0.00009189561,0.00016626426,0.0037494516,0.9835165,0.00441662],"study_design_scores_gemma":[0.0033538304,0.0001362993,0.009090644,0.0010041837,0.00032368954,0.000030156263,0.002994009,0.0015854986,0.000031217365,0.0009184756,0.9795958,0.0009361984],"about_ca_topic_score_codex":0.006548458,"about_ca_topic_score_gemma":0.013532973,"teacher_disagreement_score":0.16579421,"about_ca_system_score_codex":0.00012889993,"about_ca_system_score_gemma":0.00010420113,"threshold_uncertainty_score":0.9998568},"labels":[],"label_agreement":null},{"id":"W7115430260","doi":"","title":"The use of Low German by the Mennonites of Manitoba and dialect differences between the East and West Reserves","year":2005,"lang":"","type":"article","venue":"The COCOON platform (University of Paris)","topic":"Agriculture and Farm Safety","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"German; Ethnic group; Selection (genetic algorithm); Population","score_opus":0.04745165129654145,"score_gpt":0.20088621740127563,"score_spread":0.1534345661047342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7115430260","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":[0.9900221,0.0026502728,0.0000057702327,0.0063427147,0.000034520144,0.00048284043,0.00021084002,0.0000078927005,0.00024304658],"genre_scores_gemma":[0.9926398,0.0065580676,0.000011231314,0.000037802765,0.00011191917,6.2632654e-7,0.000017483964,0.0000014347032,0.000621652],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985802,0.00020342918,0.00030357207,0.00024022891,0.00035840215,0.00031412215],"domain_scores_gemma":[0.9969258,0.0020826927,0.0005507764,0.00020701117,0.00015168954,0.00008207375],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0006321304,0.00023268833,0.0003790039,0.000012919639,0.0018818143,0.00009360016,0.0010011937,0.00015102528,0.00005325518],"category_scores_gemma":[0.000017683562,0.0000630963,0.00013008494,0.00040454033,0.0023929165,0.00044715352,0.00053066504,0.00031562994,0.000003609113],"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":[0.0014475912,0.0005182796,0.562928,0.00022244867,0.0013207617,0.0000036873007,0.034435995,0.000024789477,0.027943775,0.007902047,0.013906036,0.3493466],"study_design_scores_gemma":[0.0002912684,0.00040057,0.9582499,0.000077287266,0.00024723707,0.0000047137637,0.025231639,0.00021904038,0.00023461581,0.00036370178,0.014495922,0.00018408654],"about_ca_topic_score_codex":0.0039503947,"about_ca_topic_score_gemma":0.015744582,"teacher_disagreement_score":0.39532194,"about_ca_system_score_codex":0.000015414975,"about_ca_system_score_gemma":0.000016089767,"threshold_uncertainty_score":0.9994176},"labels":[],"label_agreement":null},{"id":"W7134603109","doi":"","title":"SD1-171","year":2015,"lang":"","type":"other","venue":"The COCOON platform (University of Paris)","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Sitting; Active listening; Narrative; Clothing; Ask price; Quarter (Canadian coin)","score_opus":0.03376873557638114,"score_gpt":0.2174862249699892,"score_spread":0.18371748939360807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7134603109","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010178988,0.0035136577,0.00041520738,0.00036817807,0.0010112847,0.0025625995,0.0017115746,0.00038426745,0.9798542],"genre_scores_gemma":[0.0504841,0.001576696,0.0006804663,0.00006700736,0.0004219731,8.9231446e-7,0.00044635235,0.0009652795,0.94535726],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9943005,0.00028649444,0.00063040387,0.0012206562,0.0020939286,0.0014680172],"domain_scores_gemma":[0.9920106,0.00030987448,0.0026927174,0.0030867045,0.0010817075,0.00081838784],"candidate_categories":["metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","insufficient_payload"],"category_scores_codex":[0.0024517244,0.0013424202,0.0021220234,0.001102616,0.0009954164,0.00008415045,0.004626907,0.0016172576,0.058617946],"category_scores_gemma":[0.00011532722,0.0013482287,0.0006950577,0.002484806,0.0031720155,0.0009657777,0.001982891,0.0019223397,0.105004296],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015537298,0.00043516335,0.00017128175,0.0003286875,0.0015780058,0.00014889207,0.009198867,0.00012002787,0.00025945605,0.0036680808,0.97985065,0.002687129],"study_design_scores_gemma":[0.0041503385,0.00044279924,0.0005811018,0.00082426856,0.0019609474,0.000051725783,0.020701611,0.0018285459,0.000032918193,0.0013206393,0.96664983,0.0014552978],"about_ca_topic_score_codex":0.005087247,"about_ca_topic_score_gemma":0.0056417277,"teacher_disagreement_score":0.04638635,"about_ca_system_score_codex":0.0010528388,"about_ca_system_score_gemma":0.0017427199,"threshold_uncertainty_score":0.9999327},"labels":[],"label_agreement":null},{"id":"W7139539562","doi":"","title":"SD1-048","year":2015,"lang":"","type":"other","venue":"The COCOON platform (University of Paris)","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Session (web analytics); Period (music); Quarter (Canadian coin); Spike (software development)","score_opus":0.03390732825435375,"score_gpt":0.21738862733298045,"score_spread":0.1834812990786267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7139539562","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008182867,0.0033605192,0.00040159185,0.00036337393,0.0009831144,0.0024599466,0.0016017748,0.00037620123,0.9822706],"genre_scores_gemma":[0.05130262,0.0015475681,0.0006733848,0.00006662612,0.00041918366,8.8675455e-7,0.00045472386,0.0009625153,0.9445725],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99429893,0.00028853302,0.000630196,0.0012208311,0.0020951184,0.0014664122],"domain_scores_gemma":[0.99201816,0.00030722164,0.0026927618,0.003084667,0.0010784959,0.00081870006],"candidate_categories":["metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","insufficient_payload"],"category_scores_codex":[0.0024586136,0.0013417433,0.0021212269,0.0011021685,0.0009919824,0.00008436178,0.0046271216,0.0016149123,0.05760316],"category_scores_gemma":[0.0001129915,0.001347452,0.00070193945,0.0024338895,0.003160752,0.00096501975,0.0019830817,0.0019199013,0.10748216],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015304325,0.00043291523,0.00017100236,0.00033090735,0.0015640236,0.00014375277,0.009017204,0.00009388639,0.00025367615,0.004869717,0.9792183,0.0023742085],"study_design_scores_gemma":[0.004098421,0.0004384713,0.00057210977,0.00080920255,0.0019368111,0.00005111485,0.01972729,0.0016399648,0.000026786727,0.0012938131,0.9679692,0.0014368586],"about_ca_topic_score_codex":0.005096387,"about_ca_topic_score_gemma":0.005622747,"teacher_disagreement_score":0.049878992,"about_ca_system_score_codex":0.0010577554,"about_ca_system_score_gemma":0.0017254045,"threshold_uncertainty_score":0.99993336},"labels":[],"label_agreement":null},{"id":"W75573212","doi":"","title":"A report and comparative-historical look at the Cinta Larga, Suruí, Gavião and Zoró languages","year":2013,"lang":"en","type":"article","venue":"The COCOON platform (University of Paris)","topic":"Syntax, Semantics, Linguistic Variation","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Tree (set theory); Word (group theory); Linguistics; Genealogy; History; Mathematics; Philosophy; Combinatorics","score_opus":0.04464121881310591,"score_gpt":0.22577643255805993,"score_spread":0.181135213744954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W75573212","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":[0.9702072,0.00032135565,0.00015356063,0.00659736,0.00017529313,0.0003208429,0.000011910382,0.00003517396,0.02217727],"genre_scores_gemma":[0.9782725,0.000049876075,0.000091915565,0.000053911575,0.000116135125,6.8992415e-7,0.000014521594,0.000005367568,0.021395111],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9993862,0.00003060737,0.00012983824,0.00015543187,0.00016204202,0.00013590418],"domain_scores_gemma":[0.99913204,0.00024192687,0.00019547531,0.00023833029,0.00014631217,0.000045943325],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00027068224,0.00010389188,0.00020551053,0.0000408812,0.00067602884,0.000058166497,0.00014945885,0.000042090636,0.0009955277],"category_scores_gemma":[0.000048396105,0.00007331973,0.00003583698,0.000030345613,0.00038898378,0.00017919288,0.00017150809,0.00012075577,0.0000691435],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017547514,0.00015628053,0.015635317,0.00013538345,0.00035736497,0.00013402708,0.46622485,0.000008244266,0.00032051504,0.4499018,0.06498226,0.001968482],"study_design_scores_gemma":[0.00300522,0.00046299974,0.13518587,0.00017652646,0.0008500538,0.00038827184,0.5566486,0.005900495,0.0002586564,0.049757913,0.24632008,0.0010452903],"about_ca_topic_score_codex":0.017557574,"about_ca_topic_score_gemma":0.011003358,"teacher_disagreement_score":0.4001439,"about_ca_system_score_codex":0.00007896206,"about_ca_system_score_gemma":0.000019386393,"threshold_uncertainty_score":0.9999177},"labels":[],"label_agreement":null}]}