{"meta":{"query_hash":"918e7084900e","filters":{"venue":"Natural language processing"},"cohort_total":2,"direct_labels_cover":0,"predictions_cover":2,"exported":2,"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/918e7084900e","api":"https://metacan.xera.ac/api/v1/cohort?venue=Natural+language+processing"},"results":[{"id":"W2475426007","doi":"10.1075/nlp.9.05hab","title":"Arabic preprocessing for Statistical Machine Translation","year":2012,"lang":"en","type":"book-chapter","venue":"Natural language processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Arabic; Preprocessor; Computer science; Natural language processing; Translation (biology); Machine translation; Artificial intelligence; Linguistics; Philosophy; Chemistry","score_opus":0.01989698859571343,"score_gpt":0.29778559573148655,"score_spread":0.2778886071357731,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2475426007","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000010469635,0.44711912,0.542789,0.00019732458,0.00026301065,0.0005337868,0.00006194871,0.0010997037,0.007935077],"genre_scores_gemma":[0.12922226,0.00008761324,0.8228327,0.00046682355,0.0007937274,0.00007406979,0.00048071131,0.00018855164,0.045853548],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964447,0.00003454072,0.00073903316,0.0011788632,0.0007807054,0.0008221557],"domain_scores_gemma":[0.9977037,0.00030336034,0.0006764146,0.00070631027,0.000395898,0.0002143479],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006014216,0.00081144896,0.0007410979,0.00040151784,0.00042838795,0.0006888921,0.0014064995,0.0007106921,0.000072195035],"category_scores_gemma":[0.00018899793,0.00070150616,0.00023508922,0.0001659782,0.00014508648,0.0017253864,0.0002443358,0.0013381167,0.000027112996],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003695383,0.000021007114,0.0000015490424,0.001052808,0.000029277966,0.000027414359,0.0011126257,7.270449e-7,0.0006530696,0.0168817,0.00024895434,0.9799339],"study_design_scores_gemma":[0.0034681985,0.0004783465,0.00001702122,0.0075591104,0.0010968646,0.0010467232,0.00011686833,0.6232317,0.012340512,0.16869275,0.17320356,0.008748299],"about_ca_topic_score_codex":0.00001418323,"about_ca_topic_score_gemma":0.000018616654,"teacher_disagreement_score":0.9711856,"about_ca_system_score_codex":0.00022881237,"about_ca_system_score_gemma":0.00027481417,"threshold_uncertainty_score":0.9995436},"labels":[],"label_agreement":null},{"id":"W2548230849","doi":"10.1075/nlp.2.15mey","title":"Extracting knowledge-rich contexts for terminography","year":2001,"lang":"en","type":"book-chapter","venue":"Natural language processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":215,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Construct (python library); Computer science; Paralanguage; Domain knowledge; Domain (mathematical analysis); Knowledge extraction; Field (mathematics); Context (archaeology); Knowledge management; Natural language processing; Data science; Artificial intelligence; Psychology; Communication; Geography; Mathematics","score_opus":0.015630032468229135,"score_gpt":0.30286852901542444,"score_spread":0.2872384965471953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2548230849","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000021197147,0.69579774,0.120593354,0.0002826504,0.00095427147,0.0010858396,0.000026106107,0.0028221111,0.17841671],"genre_scores_gemma":[0.18433394,0.0001739035,0.467833,0.0008167608,0.0017074809,0.00013550131,0.00015825618,0.00030259744,0.34453857],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.996295,0.00003278453,0.0007794738,0.0014143613,0.0005919903,0.0008863951],"domain_scores_gemma":[0.99688524,0.0003504634,0.00093783555,0.0008897218,0.00074691937,0.0001898201],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00053062575,0.0009565764,0.00086286414,0.00080967246,0.0005663479,0.0009534777,0.0023336334,0.0008533777,0.000038227136],"category_scores_gemma":[0.00025278353,0.0008446428,0.00044771054,0.00034922682,0.00015300061,0.0014229055,0.00053997,0.0016802042,0.000032809938],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021406004,0.000027216942,0.000003450084,0.00060228386,0.000044926423,0.00015595407,0.0015387787,1.6784365e-7,0.00063458615,0.013223382,0.0014643497,0.9822835],"study_design_scores_gemma":[0.0047440105,0.00084126525,0.000021280071,0.018516978,0.0009517972,0.0033117756,0.00054179557,0.068818435,0.021718903,0.1768467,0.6901055,0.0135815535],"about_ca_topic_score_codex":0.00000832424,"about_ca_topic_score_gemma":0.000028625145,"teacher_disagreement_score":0.96870196,"about_ca_system_score_codex":0.00022191547,"about_ca_system_score_gemma":0.00031376962,"threshold_uncertainty_score":0.99940044},"labels":[],"label_agreement":null}]}