{"meta":{"query_hash":"40ccdc7a803e","filters":{"venue":"NTCIR"},"cohort_total":4,"direct_labels_cover":0,"predictions_cover":4,"exported":4,"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/40ccdc7a803e","api":"https://metacan.xera.ac/api/v1/cohort?venue=NTCIR"},"results":[{"id":"W2157365731","doi":"","title":"Thomson Legal and Regulatory at NTCIR-4: Monolingual and Pivot-Language Retrieval Experiments","year":2004,"lang":"en","type":"article","venue":"NTCIR","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thomson Reuters (Canada)","funders":"","keywords":"Computer science; Task (project management); Natural language processing; Artificial intelligence; Information retrieval; Relevance (law); Quality (philosophy)","score_opus":0.013338833862058457,"score_gpt":0.2747150190288032,"score_spread":0.2613761851667447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157365731","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":[0.99535674,0.0005518708,0.0022930764,0.00023296977,0.00019030234,0.0001728291,0.000004596359,0.000120141005,0.0010774799],"genre_scores_gemma":[0.9957005,0.000023725197,0.0029543238,0.0002825939,0.00006286702,0.0000039203455,0.0000043911195,0.000008118078,0.00095955457],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99876475,0.000028154771,0.00021278998,0.00028470173,0.00040748573,0.00030213594],"domain_scores_gemma":[0.99935436,0.000021557504,0.00006418684,0.00031992907,0.000052966596,0.00018701074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002235967,0.00014417792,0.00014380961,0.000099543,0.00023499776,0.0002008759,0.00025973006,0.000089105546,0.000018780785],"category_scores_gemma":[0.000031301963,0.00012953089,0.0000340088,0.00018208861,0.00010237383,0.00075161917,0.00034908223,0.00014555317,0.00004324795],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009834555,0.0007501424,0.011009768,0.00032350366,0.00014965466,0.0015927505,0.20317288,0.00012211614,0.39086694,0.17585033,0.0022299998,0.21294846],"study_design_scores_gemma":[0.008093812,0.0009906252,0.22461113,0.00013876325,0.000033459117,0.00087215164,0.0018048566,0.005377635,0.73950016,0.0014481058,0.015600256,0.0015290164],"about_ca_topic_score_codex":0.000059938106,"about_ca_topic_score_gemma":0.000005248009,"teacher_disagreement_score":0.34863323,"about_ca_system_score_codex":0.00011068685,"about_ca_system_score_gemma":0.000080486556,"threshold_uncertainty_score":0.52821165},"labels":[],"label_agreement":null},{"id":"W2395937579","doi":"","title":"QA System Metis Based on Semantic Graph Matching at NTCIR 6.","year":2007,"lang":"en","type":"article","venue":"NTCIR","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"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":"Computer science; Metis; Artificial intelligence; Natural language processing; Graph; Matching (statistics); Information retrieval; World Wide Web; Theoretical computer science; Mathematics; Statistics","score_opus":0.015687917336282126,"score_gpt":0.2348742655769794,"score_spread":0.21918634824069727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2395937579","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":[0.15340328,0.00005257376,0.8355679,0.0003335225,0.0007704125,0.00016054341,0.0000010345267,0.00041119012,0.009299546],"genre_scores_gemma":[0.95951056,8.3799495e-7,0.039448977,0.0005934719,0.00012230477,0.0000066616017,0.0000013498684,0.000016240734,0.00029956902],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981848,0.000063772175,0.00030873346,0.0005027323,0.00049628754,0.00044369893],"domain_scores_gemma":[0.9986199,0.00018715143,0.00009770143,0.0009147623,0.00004347939,0.00013697274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00081254,0.00017293787,0.00020335098,0.00021882556,0.00019667154,0.00009586101,0.0007332339,0.0000869728,0.000015181837],"category_scores_gemma":[0.000019121353,0.00016108755,0.000107971544,0.0003466413,0.00001823936,0.00016965988,0.00017341669,0.00016612509,0.00022900866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015632578,0.0005502831,0.014324433,0.0017610023,0.00019103193,0.0032955883,0.008115301,0.13068412,0.020446386,0.5967511,0.0040100967,0.21971434],"study_design_scores_gemma":[0.0011895029,0.00013826069,0.015618062,0.0005512796,0.00002888647,0.00012482483,0.00018629876,0.96413773,0.010488711,0.0038964923,0.0027933833,0.00084656704],"about_ca_topic_score_codex":0.00012445252,"about_ca_topic_score_gemma":0.00005471745,"teacher_disagreement_score":0.8334536,"about_ca_system_score_codex":0.00019774663,"about_ca_system_score_gemma":0.0000324021,"threshold_uncertainty_score":0.656896},"labels":[],"label_agreement":null},{"id":"W2396216261","doi":"","title":"UQAM's System Description for the NTCIR-10 Japanese and English PatentMT Evaluation Tasks.","year":2013,"lang":"en","type":"article","venue":"NTCIR","topic":"Natural Language Processing Techniques","field":"Computer Science","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":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Natural language processing; Machine translation; Artificial intelligence; Domain (mathematical analysis); Translation (biology); Linguistics","score_opus":0.025567362361244093,"score_gpt":0.2600134725910629,"score_spread":0.2344461102298188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2396216261","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":[0.1650192,0.020648288,0.7956986,0.003080101,0.0027130223,0.006817786,0.000015575408,0.003598051,0.0024093909],"genre_scores_gemma":[0.9545163,0.000007975013,0.04435799,0.00014091576,0.00016430144,0.00049730175,0.0000073427027,0.000010801571,0.00029710712],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99892193,0.000082027414,0.00017387574,0.00029976605,0.00031932164,0.00020306966],"domain_scores_gemma":[0.9986761,0.00013599698,0.0001071109,0.0004169861,0.00061488815,0.000048904098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007511355,0.000120131124,0.00011012427,0.000058222726,0.00020054684,0.0005047584,0.0005171585,0.000085482265,0.000018874884],"category_scores_gemma":[0.0002661721,0.00007889766,0.0000381778,0.0001755072,0.000037671558,0.0009146126,0.00012735666,0.00010002913,0.000020764717],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002311486,0.00007371742,0.00032982306,0.0004673019,0.000058422243,0.0000033016365,0.01348102,0.000024474193,0.01783545,0.031314593,0.035282128,0.90110666],"study_design_scores_gemma":[0.0013506699,0.0003066242,0.0040175985,0.00033016579,0.00010625555,0.00006464893,0.0020960073,0.94397724,0.0134375505,0.02593769,0.007630438,0.0007450987],"about_ca_topic_score_codex":0.00015429308,"about_ca_topic_score_gemma":0.000008576914,"teacher_disagreement_score":0.9439528,"about_ca_system_score_codex":0.00009306181,"about_ca_system_score_gemma":0.000032890166,"threshold_uncertainty_score":0.48673967},"labels":[],"label_agreement":null},{"id":"W2401796064","doi":"","title":"ClueWeb09 and TREC Diversity.","year":2010,"lang":"en","type":"article","venue":"NTCIR","topic":"Information Retrieval and Search Behavior","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; Information retrieval; Task (project management); World Wide Web; Set (abstract data type); Search engine; Web page","score_opus":0.010717057301256794,"score_gpt":0.2261840300999137,"score_spread":0.2154669727986569,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2401796064","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":[0.9762851,0.0000052981854,0.010186486,0.0008427649,0.0003657258,0.000060714312,0.0000015754119,0.00009149762,0.012160851],"genre_scores_gemma":[0.9946758,0.000002711716,0.0040942496,0.00027933295,0.000025590998,8.906317e-7,6.3248183e-7,9.560116e-7,0.0009197974],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99962866,0.0000061035694,0.00004948692,0.000076925324,0.00013890344,0.00009992267],"domain_scores_gemma":[0.9997182,0.000016462334,0.000014357951,0.0001461472,0.000036827612,0.00006801336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001077995,0.000034644647,0.00003680347,0.00004006912,0.0001743454,0.0000752519,0.00026117289,0.00003057346,0.000048707538],"category_scores_gemma":[0.000014872889,0.000028884206,0.000014452176,0.000097845084,0.00002930495,0.00040404272,0.00039602432,0.00011362598,0.00012012322],"study_design_candidate":"observational","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":[0.000009612855,0.00007094518,0.053668622,0.000016692793,0.000007883283,0.000026642427,0.006375083,0.0000011075039,0.007706651,0.24124156,0.005539469,0.68533576],"study_design_scores_gemma":[0.0012309953,0.0001969221,0.7455078,0.0000072286875,0.000008924043,0.00008632415,0.000113167116,0.018285807,0.011191969,0.0055172634,0.21737559,0.00047800966],"about_ca_topic_score_codex":0.000022209362,"about_ca_topic_score_gemma":0.000010359249,"teacher_disagreement_score":0.69183916,"about_ca_system_score_codex":0.0000037000527,"about_ca_system_score_gemma":0.000014530008,"threshold_uncertainty_score":0.15439811},"labels":[],"label_agreement":null}]}