{"meta":{"query_hash":"a6c2b8c45c44","filters":{"venue":"Information Retrieval"},"cohort_total":26,"direct_labels_cover":0,"predictions_cover":26,"exported":26,"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/a6c2b8c45c44","api":"https://metacan.xera.ac/api/v1/cohort?venue=Information+Retrieval"},"results":[{"id":"W1503824486","doi":"10.1023/a:1023936321956","title":"Query Expansion with Long-Span Collocates","year":2003,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Microsoft Research","keywords":"Collocation (remote sensing); Computer science; Window (computing); Information retrieval; Mathematics; Machine learning","score_opus":0.009880289279499396,"score_gpt":0.22393088713362766,"score_spread":0.21405059785412828,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1503824486","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":[0.1789887,0.000024417384,0.80165005,0.00038411643,0.000410167,0.0005313431,0.000007018786,0.00039951538,0.017604683],"genre_scores_gemma":[0.99139386,0.000012063171,0.0071415696,0.0008805265,0.00001788861,0.000011986782,0.00003398614,0.000006365418,0.00050177745],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981608,0.000060133025,0.00046030115,0.00013240863,0.0008290841,0.0003572848],"domain_scores_gemma":[0.99864423,0.00006251842,0.00019203892,0.00043321634,0.00049348135,0.00017451352],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005693992,0.00017143677,0.00015391369,0.00028434684,0.00026266088,0.0004917196,0.00044834547,0.00009944453,0.00010073149],"category_scores_gemma":[0.0001565168,0.00013115199,0.000054505635,0.0011326743,0.00006208379,0.0061698044,0.00006504168,0.0001985593,0.00073885213],"study_design_candidate":"theoretical_or_conceptual","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":[0.0011858868,0.0005615865,0.028544195,0.00054108136,0.0001848769,0.00010466821,0.031032339,0.0074504116,0.0010136606,0.68451965,0.012750444,0.2321112],"study_design_scores_gemma":[0.011295913,0.003960942,0.075718455,0.00030096062,0.000073887444,0.0012054939,0.0034312664,0.1154809,0.2728475,0.0022781459,0.5098674,0.0035391138],"about_ca_topic_score_codex":0.000009464384,"about_ca_topic_score_gemma":0.0000018594682,"teacher_disagreement_score":0.8124051,"about_ca_system_score_codex":0.0000921547,"about_ca_system_score_gemma":0.0003377448,"threshold_uncertainty_score":0.94966954},"labels":[],"label_agreement":null},{"id":"W1685426458","doi":"10.1007/s10791-011-9162-z","title":"Efficient and effective spam filtering and re-ranking for large web datasets","year":2011,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":277,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Institute of Standards and Technology","keywords":"Computer science; Information retrieval; Ranking (information retrieval); Relevance feedback; Relevance (law); Search engine; Learning to rank; Set (abstract data type); Honeypot; Web page; Rank (graph theory); Data mining; World Wide Web; Artificial intelligence; Image retrieval; Mathematics","score_opus":0.015493414875478324,"score_gpt":0.23253805024293472,"score_spread":0.2170446353674564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1685426458","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":[0.42199194,0.00003651646,0.57614124,0.00004541995,0.00047042815,0.0004515708,0.00008880603,0.00011934908,0.0006547185],"genre_scores_gemma":[0.99360675,0.0000036834394,0.0061793425,0.00014497191,0.000027474267,0.000008883775,0.000024124347,0.0000025115305,0.0000022611127],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994586,0.00001779028,0.00015177623,0.00010982983,0.000121654055,0.00014034074],"domain_scores_gemma":[0.9995837,0.00008314152,0.000085681866,0.00015346357,0.000045871566,0.000048100697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050930184,0.00007316475,0.00007389486,0.000105394734,0.00017139167,0.00016659178,0.000118322365,0.00004672012,0.0000047388207],"category_scores_gemma":[0.00012776376,0.000068584966,0.0000168802,0.00014548261,0.000013836603,0.0008896849,0.00012232011,0.00006469617,0.000008373953],"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":[0.0024777474,0.000299279,0.0101946965,0.0019104452,0.00027488792,0.000014880769,0.15294665,0.0008314913,0.0094218645,0.14688078,0.0065558404,0.66819143],"study_design_scores_gemma":[0.0019720246,0.00048481696,0.022287667,0.00006992311,0.000016911878,0.000035488087,0.00016515265,0.9368455,0.013307071,0.00067962083,0.02383004,0.000305803],"about_ca_topic_score_codex":0.000007726608,"about_ca_topic_score_gemma":0.000002083803,"teacher_disagreement_score":0.936014,"about_ca_system_score_codex":0.000018630653,"about_ca_system_score_gemma":0.000011861228,"threshold_uncertainty_score":0.27968138},"labels":[],"label_agreement":null},{"id":"W2000952055","doi":"10.1007/s10791-006-9397-2","title":"Introduction to the special issue on the 27th European Conference on Information Retrieval Research","year":2006,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Waterloo","keywords":"Information retrieval; Political science; Library science; Data science; Computer science","score_opus":0.03850458048473922,"score_gpt":0.29410519826420334,"score_spread":0.25560061777946413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000952055","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":[0.067109875,0.000007129245,0.05775145,0.27475345,0.0072728954,0.0049376218,0.00014623722,0.00079294725,0.58722836],"genre_scores_gemma":[0.9448259,0.00003299089,0.001164397,0.016943542,0.02966301,0.00006288366,0.00051833544,0.00003723094,0.0067517445],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.994451,0.0006231013,0.0010321707,0.00024550964,0.0029584705,0.0006897327],"domain_scores_gemma":[0.99628127,0.00034863537,0.00033383115,0.001203275,0.0016684126,0.00016455913],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006372033,0.00027943932,0.00018516867,0.0007383103,0.0014135211,0.002414212,0.0019340256,0.00012371228,0.00060595974],"category_scores_gemma":[0.0013999371,0.00017006198,0.00011000423,0.0028745942,0.00017988383,0.0054046256,0.0004121944,0.0010759442,0.027158905],"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":[0.00054961984,0.000053210035,0.000011047004,0.000016713291,0.000009044934,0.0000018979266,0.0048003425,0.0014694268,0.00006672664,0.36915544,0.57046074,0.053405788],"study_design_scores_gemma":[0.00045943802,0.000684443,0.0042202827,0.00002570261,0.000004086228,0.000014692642,0.00068055,0.0079790335,0.0043257335,0.0006853837,0.9806615,0.00025912153],"about_ca_topic_score_codex":0.000041727322,"about_ca_topic_score_gemma":0.0000045641073,"teacher_disagreement_score":0.877716,"about_ca_system_score_codex":0.00033257896,"about_ca_system_score_gemma":0.00023008337,"threshold_uncertainty_score":0.9998865},"labels":[],"label_agreement":null},{"id":"W2008283248","doi":"10.1007/s10791-013-9220-9","title":"Latent word context model for information retrieval","year":2013,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Topic Modeling","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Ministry of Education, Culture, Sports, Science and Technology","keywords":"Computer science; Latent Dirichlet allocation; Word (group theory); Context (archaeology); Information retrieval; Natural language processing; Latent semantic analysis; Search engine indexing; Topic model; Relevance (law); Artificial intelligence; Probabilistic latent semantic analysis; Linguistics","score_opus":0.02483661079381079,"score_gpt":0.23769802741019738,"score_spread":0.21286141661638658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2008283248","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03142921,0.000013921807,0.9636255,0.001416529,0.00056131894,0.0009803092,0.000015042886,0.00029062785,0.00166753],"genre_scores_gemma":[0.94534683,0.0000070210917,0.051180743,0.0029898055,0.00006534528,0.00003491534,0.00007345893,0.0000062313575,0.00029567082],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99810624,0.000018095065,0.0008292467,0.00013513971,0.00054741587,0.0003638866],"domain_scores_gemma":[0.99818265,0.00008106513,0.00034145816,0.0005047977,0.0007487138,0.00014128925],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004929929,0.00017418929,0.00018058436,0.00026038758,0.00017661022,0.00076071755,0.00065631716,0.00015448578,0.0000315356],"category_scores_gemma":[0.00033030982,0.00016359171,0.000104570274,0.00038273184,0.000026179174,0.014874013,0.00016822192,0.00016793767,0.0008800389],"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":[0.00026350337,0.000045911955,0.00018306448,0.00023655163,0.00006164689,3.6857642e-7,0.017543223,0.076280825,0.00021130273,0.23325875,0.017146265,0.6547686],"study_design_scores_gemma":[0.00085634406,0.00005526953,0.0002700482,0.000015291042,0.0000044744847,0.0000049254736,0.00010341315,0.98154086,0.00065100496,0.0038830293,0.01240925,0.00020608868],"about_ca_topic_score_codex":0.000024406992,"about_ca_topic_score_gemma":8.8998655e-7,"teacher_disagreement_score":0.9139176,"about_ca_system_score_codex":0.00013768396,"about_ca_system_score_gemma":0.00016516019,"threshold_uncertainty_score":0.9998979},"labels":[],"label_agreement":null},{"id":"W2032328503","doi":"10.1007/s10791-009-9108-x","title":"Document clustering of scientific texts using citation contexts","year":2009,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Cluster analysis; Information retrieval; Computer science; Document clustering; Citation; Vocabulary; Context (archaeology); Similarity (geometry); Representation (politics); Document retrieval; Natural language processing; Artificial intelligence; World Wide Web; Linguistics","score_opus":0.016025685924846902,"score_gpt":0.2950436954188471,"score_spread":0.27901800949400024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032328503","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07608683,0.000021043123,0.922473,0.000101745376,0.00013843851,0.00015264824,0.0000011538779,0.00014536605,0.00087975606],"genre_scores_gemma":[0.8730282,0.0000017921966,0.12679331,0.00012733469,0.000009851551,6.3575385e-7,0.0000081043145,0.0000015262516,0.000029232839],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873674,0.000023851091,0.0004896937,0.0001185582,0.00047968785,0.00015145414],"domain_scores_gemma":[0.9988553,0.000027921944,0.00036414934,0.0003516878,0.00035639273,0.000044568318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004991781,0.000087954206,0.00013130238,0.00045049714,0.00012522656,0.00029144232,0.00038742763,0.000044833167,0.000008330959],"category_scores_gemma":[0.00011209011,0.00008700669,0.00005907105,0.0010127735,0.000042933214,0.0049297926,0.000076947246,0.00006564358,0.000018396873],"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":[0.000068013214,0.00006210744,0.00017887336,0.000058573954,0.00003056094,0.000002354211,0.0052327854,0.015389724,0.04377983,0.081656314,0.00030506754,0.8532358],"study_design_scores_gemma":[0.0007095921,0.00027348706,0.0042520007,0.00010702849,0.000018363162,0.000017211005,0.000086201384,0.7957874,0.16236202,0.032525443,0.0034892815,0.00037195513],"about_ca_topic_score_codex":0.0000032243572,"about_ca_topic_score_gemma":8.041845e-7,"teacher_disagreement_score":0.85286385,"about_ca_system_score_codex":0.00010212303,"about_ca_system_score_gemma":0.000056798282,"threshold_uncertainty_score":0.35739806},"labels":[],"label_agreement":null},{"id":"W2033681837","doi":"10.1007/s10791-011-9163-y","title":"Improving document clustering using Okapi BM25 feature weighting","year":2011,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Weighting; Cluster analysis; Computer science; Artificial intelligence; Data mining; Feature (linguistics); Document clustering; Pattern recognition (psychology); Term (time)","score_opus":0.024820470294881734,"score_gpt":0.24203731868756767,"score_spread":0.21721684839268593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2033681837","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047458806,0.000036196223,0.9876043,0.00013783645,0.0003831296,0.00023643585,0.000001983369,0.00053587137,0.0063183266],"genre_scores_gemma":[0.6141777,0.000014456936,0.38478976,0.00061248156,0.00010295864,0.0000064942437,0.0000103999355,0.00001218457,0.0002735689],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986537,0.000036133246,0.00042941002,0.00017724653,0.0004096886,0.00029378748],"domain_scores_gemma":[0.9988438,0.000024557412,0.00036331668,0.00042753146,0.0002471335,0.00009369713],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005130527,0.00016111991,0.00013671325,0.00022240433,0.000243293,0.00037480152,0.00061486004,0.00012245782,0.000046762092],"category_scores_gemma":[0.000104571525,0.00014616354,0.00007572631,0.00059352105,0.000034023586,0.0049798265,0.00030021527,0.00021610642,0.00008917789],"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":[0.00027383326,0.000118250035,0.00082925335,0.0005347833,0.00009868265,0.000026129193,0.022047913,0.000057216253,0.05010868,0.06460754,0.0010229646,0.86027473],"study_design_scores_gemma":[0.0007008398,0.00020747876,0.0015223258,0.00010400152,0.000020657864,0.00012540554,0.0004016093,0.54323286,0.43789497,0.0021188792,0.012960604,0.0007104031],"about_ca_topic_score_codex":0.000027204565,"about_ca_topic_score_gemma":4.7179992e-7,"teacher_disagreement_score":0.85956436,"about_ca_system_score_codex":0.00015286947,"about_ca_system_score_gemma":0.000095378404,"threshold_uncertainty_score":0.59603757},"labels":[],"label_agreement":null},{"id":"W2056081579","doi":"10.1007/s10791-007-9042-8","title":"Hybrid index maintenance for contiguous inverted lists","year":2008,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"University of Waterloo","keywords":"Merge (version control); Computer science; Inverted index; Information retrieval; Data mining; Search engine indexing","score_opus":0.01558255272543664,"score_gpt":0.22993730688226618,"score_spread":0.21435475415682953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056081579","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016905269,0.0000205521,0.9805768,0.00026267633,0.0005469847,0.00027920245,0.00004310091,0.00018646501,0.0011789544],"genre_scores_gemma":[0.9693955,0.000030123669,0.027936874,0.001981889,0.000095389194,0.000015331869,0.00014539211,0.0000061963347,0.00039329976],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901175,0.000013299918,0.00032211744,0.00012586554,0.00030378948,0.00022319671],"domain_scores_gemma":[0.99903566,0.000054068434,0.00016662855,0.00036881556,0.00028711028,0.00008769828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017823734,0.000103068414,0.00012495235,0.000107662934,0.0002164107,0.000121224984,0.0005385965,0.000049557293,0.000010564285],"category_scores_gemma":[0.00018281826,0.00008869423,0.0000540481,0.00020740001,0.000043674925,0.003224666,0.00015522982,0.000093303905,0.000105427476],"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":[0.000638112,0.000150992,0.0015871824,0.00015007785,0.00006786099,0.00005423145,0.0038724719,0.0008092258,0.0003005463,0.058894787,0.5312862,0.40218836],"study_design_scores_gemma":[0.00137802,0.00011531303,0.005220438,0.00002183824,0.0000018141853,0.00013069196,0.000013164071,0.7236498,0.0018727195,0.0012821179,0.2661092,0.00020486813],"about_ca_topic_score_codex":0.00002036115,"about_ca_topic_score_gemma":3.3296706e-7,"teacher_disagreement_score":0.95263994,"about_ca_system_score_codex":0.000043097476,"about_ca_system_score_gemma":0.00010659689,"threshold_uncertainty_score":0.36168456},"labels":[],"label_agreement":null},{"id":"W2062626555","doi":"10.1007/s10791-009-9105-0","title":"Swapping documents and terms","year":2009,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Agricultural Research Development Agency","keywords":"Relevance feedback; Computer science; Information retrieval; Relevance (law); Query expansion; Data mining; Artificial intelligence; Image retrieval","score_opus":0.009581800700385145,"score_gpt":0.25307819252788394,"score_spread":0.2434963918274988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062626555","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":[0.34459913,0.000063021376,0.54404706,0.0054527135,0.0008328023,0.0009229107,0.000012507023,0.0009065008,0.1031634],"genre_scores_gemma":[0.9906166,0.000023155937,0.0059119835,0.0030491704,0.000029721568,0.0000018187461,0.00001671843,0.0000016989181,0.00034908752],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988753,0.000016115791,0.00035150535,0.000085162465,0.00044460897,0.00022729399],"domain_scores_gemma":[0.9994001,0.000020953936,0.00011492081,0.00022080337,0.00012214843,0.00012106789],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032669416,0.000100471974,0.00009594345,0.00020602832,0.00017176865,0.00058039796,0.00033074355,0.000060899125,0.000034806366],"category_scores_gemma":[0.000071884606,0.000086789354,0.000032603486,0.00041898608,0.00002384374,0.0070542474,0.00008570192,0.00012633568,0.00035402813],"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":[0.000050364022,0.000027586673,0.0003807906,0.00002176549,0.000008630208,0.000004383724,0.0038867125,0.00001423846,0.00046009864,0.10391242,0.0020260839,0.88920695],"study_design_scores_gemma":[0.006019909,0.001964118,0.37201267,0.00014027399,0.000025488156,0.00037519826,0.00051295984,0.12871447,0.02334466,0.022001106,0.44307575,0.001813409],"about_ca_topic_score_codex":0.000003828765,"about_ca_topic_score_gemma":8.5977945e-8,"teacher_disagreement_score":0.88739353,"about_ca_system_score_codex":0.00003918214,"about_ca_system_score_gemma":0.000037479014,"threshold_uncertainty_score":0.5596791},"labels":[],"label_agreement":null},{"id":"W2069744915","doi":"10.1007/s10791-012-9192-1","title":"Extended structural relevance framework: a framework for evaluating structured document retrieval","year":2012,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Relevance (law); Information retrieval; Redundancy (engineering); Probabilistic logic; Task (project management); Tree (set theory); Data mining; Range (aeronautics); Artificial intelligence; Mathematics","score_opus":0.03216634289591799,"score_gpt":0.3490464434591703,"score_spread":0.31688010056325233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069744915","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12293362,0.00015038977,0.87067884,0.00067144004,0.0030955188,0.0015565784,0.0000651526,0.00046420988,0.00038422976],"genre_scores_gemma":[0.65441763,0.000013833991,0.34384346,0.0011481514,0.0003648122,0.000032908956,0.000075717544,0.000017710929,0.000085734384],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9950216,0.00013753636,0.0013512395,0.0003063147,0.0019147767,0.001268535],"domain_scores_gemma":[0.99579626,0.0009475234,0.00078944716,0.00095950876,0.0010240244,0.00048323264],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0022303432,0.000434599,0.00041589775,0.00038530186,0.0007229766,0.0009118169,0.0012578027,0.00047214355,0.00028225948],"category_scores_gemma":[0.0052556437,0.00038386983,0.00026865583,0.0013843168,0.000105850864,0.011237001,0.00036472862,0.0008066576,0.0002679526],"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":[0.0010034326,0.00003879215,0.00046224022,0.00020725936,0.00007269971,0.0000011004114,0.011515227,0.00026961963,0.00044829378,0.8474795,0.0005248997,0.13797691],"study_design_scores_gemma":[0.008313396,0.0034797145,0.06419552,0.0006424112,0.00023371402,0.00035192742,0.0025575464,0.27206472,0.09141935,0.49138987,0.060724374,0.004627453],"about_ca_topic_score_codex":0.000004061358,"about_ca_topic_score_gemma":1.4466227e-7,"teacher_disagreement_score":0.53148407,"about_ca_system_score_codex":0.00038943757,"about_ca_system_score_gemma":0.00029577597,"threshold_uncertainty_score":0.9998613},"labels":[],"label_agreement":null},{"id":"W2074280490","doi":"10.1007/s10791-011-9168-6","title":"A study of the integration of passage-, document-, and cluster-based information for re-ranking search results","year":2011,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Israel Science Foundation; McGill University","keywords":"Ranking (information retrieval); Computer science; Information retrieval; Context (archaeology); Representation (politics); Query expansion; Task (project management); Cluster (spacecraft); Document retrieval; Data mining; Information integration; Geography","score_opus":0.05817615587411926,"score_gpt":0.29534894858965705,"score_spread":0.2371727927155378,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074280490","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":[0.69806117,0.0000029160906,0.29696327,0.00027591526,0.00027804018,0.002272602,0.000043517135,0.00005881267,0.0020437164],"genre_scores_gemma":[0.99479467,0.0000016733227,0.0049580387,0.00016267998,0.000008283591,0.000022269316,0.000033029366,0.0000026259606,0.00001670363],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99763066,0.00011021584,0.0011640849,0.00008942556,0.00081151316,0.00019408712],"domain_scores_gemma":[0.9976883,0.00017432636,0.0006812881,0.0004503651,0.0009500984,0.000055626104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018070437,0.00012836122,0.00018012975,0.0003734755,0.00018730441,0.00014847406,0.00056675216,0.00008700838,0.0000057199545],"category_scores_gemma":[0.00048088422,0.00009047459,0.000076201315,0.0007912647,0.000074220705,0.0056082574,0.00018696123,0.00015657037,0.000005988559],"study_design_candidate":"qualitative","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":[0.00754975,0.00081100716,0.006681907,0.0011137654,0.00014746544,7.999395e-7,0.60644495,0.0027720768,0.0008060521,0.070191436,0.0010723909,0.3024084],"study_design_scores_gemma":[0.033038747,0.010504572,0.17950541,0.0005112298,0.00015427919,0.000020507054,0.045894977,0.45656666,0.26639962,0.0024098682,0.0038534054,0.0011407225],"about_ca_topic_score_codex":0.00008231913,"about_ca_topic_score_gemma":0.000010290072,"teacher_disagreement_score":0.56055,"about_ca_system_score_codex":0.000050998944,"about_ca_system_score_gemma":0.00015640895,"threshold_uncertainty_score":0.4065851},"labels":[],"label_agreement":null},{"id":"W2082055394","doi":"10.1007/s10791-012-9218-8","title":"Increasing evaluation sensitivity to diversity","year":2013,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Science Foundation","keywords":"Computer science; Diversity (politics); Context (archaeology); Information retrieval; Discriminative model; Measure (data warehouse); Data science; Data mining; Artificial intelligence; Geography","score_opus":0.023805444270144614,"score_gpt":0.25938339518383075,"score_spread":0.23557795091368613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082055394","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":[0.7435578,0.0000018179082,0.24813715,0.0011354169,0.00032138053,0.000871696,0.0000060477564,0.00021024725,0.005758462],"genre_scores_gemma":[0.98943746,7.8957936e-7,0.00860889,0.0018364352,0.000031549705,0.000011036344,0.00002732648,0.0000022896643,0.000044209108],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99774176,0.00017899019,0.00036741167,0.00012469394,0.0012889619,0.00029817593],"domain_scores_gemma":[0.99784434,0.00011466689,0.00013375137,0.0003573127,0.0013134582,0.0002364445],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0023912948,0.00012360894,0.000119485245,0.00033009058,0.0004872083,0.0005975086,0.00037855585,0.00007857154,0.00022318392],"category_scores_gemma":[0.0008201572,0.00011610174,0.000058220117,0.0009015072,0.000024005645,0.0097672995,0.0007756918,0.00014665033,0.004764339],"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":[0.00017205864,0.00009907965,0.014631912,0.000060309492,0.000038559723,0.000004711017,0.019488547,0.0021418603,0.0034660986,0.02143931,0.010123594,0.92833394],"study_design_scores_gemma":[0.0011977104,0.00023373724,0.42640117,0.000027469458,0.000017511025,0.00008361277,0.00044744049,0.55469143,0.0064035887,0.001120199,0.008793486,0.0005826814],"about_ca_topic_score_codex":0.00034875382,"about_ca_topic_score_gemma":0.00000251352,"teacher_disagreement_score":0.9277513,"about_ca_system_score_codex":0.00021958491,"about_ca_system_score_gemma":0.00012796813,"threshold_uncertainty_score":0.99601054},"labels":[],"label_agreement":null},{"id":"W2084946528","doi":"10.1007/s10791-006-9020-6","title":"Knowledge-based query expansion to support scenario-specific retrieval of medical free text","year":2007,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":79,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institutes of Health; McMaster University","keywords":"Computer science; Query expansion; Unified Medical Language System; Information retrieval; Query language; Testbed; Query optimization; Precision and recall; Exploit; Recall; Data mining; World Wide Web","score_opus":0.020538311628058734,"score_gpt":0.3008048304354492,"score_spread":0.28026651880739045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084946528","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":[0.9056827,0.00038496585,0.08600736,0.0012604828,0.00096719904,0.00031414512,0.00005889535,0.00008189082,0.005242387],"genre_scores_gemma":[0.9953862,0.000051668983,0.0028190257,0.0009773894,0.0002808393,0.000001818663,0.00028009375,0.000012809585,0.00019015989],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978587,0.000041122352,0.0007223381,0.00019376192,0.00083949615,0.0003445969],"domain_scores_gemma":[0.9986301,0.00008460508,0.00017728299,0.0004913068,0.0003062735,0.0003104459],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018459265,0.00016840477,0.00022001374,0.00022041232,0.00007492588,0.000028268369,0.0005355745,0.00057894323,0.00023201967],"category_scores_gemma":[0.0019109503,0.00014808372,0.00011497981,0.00044957252,0.00021481502,0.000016097336,0.00021791876,0.00020574345,0.00013466524],"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":[0.008290402,0.00052362884,0.0029851971,0.0003633372,0.00011469481,0.000030798103,0.002048903,0.000059619262,0.13851188,0.0009191257,0.23044108,0.61571133],"study_design_scores_gemma":[0.0019228744,0.0015743277,0.005775819,0.00007648967,0.000009799421,0.000022342896,0.00042932632,0.00017165708,0.34062633,0.00002546106,0.6490836,0.00028198582],"about_ca_topic_score_codex":0.00001004627,"about_ca_topic_score_gemma":0.000014640663,"teacher_disagreement_score":0.61542934,"about_ca_system_score_codex":0.000039521965,"about_ca_system_score_gemma":0.00043239357,"threshold_uncertainty_score":0.60386795},"labels":[],"label_agreement":null},{"id":"W2121315872","doi":"10.1007/s10791-013-9230-7","title":"Discover hidden web properties by random walk on bipartite graph","year":2013,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada; State Key Laboratory of Novel Software Technology; Nanjing University","keywords":"Zipf's law; Crawling; Simple random sample; Random walk; Sampling (signal processing); Bipartite graph; Statistics; Computer science; Sample size determination; Sample (material); Bernoulli's principle; Population; Mathematics; Graph; Theoretical computer science","score_opus":0.008604713258223986,"score_gpt":0.18922231192531797,"score_spread":0.18061759866709398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121315872","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":[0.91324395,0.00010352544,0.06682483,0.0032901044,0.0018456285,0.00085063383,0.000013308996,0.00060338277,0.013224608],"genre_scores_gemma":[0.99815404,0.000014870451,0.00027439953,0.0010257247,0.00005567139,0.000019721563,0.000012042815,0.0000040394275,0.00043948297],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99898136,0.000038155405,0.00027931063,0.00011082424,0.0004044168,0.00018591306],"domain_scores_gemma":[0.9993744,0.000038806105,0.00011893135,0.00028675224,0.000109498185,0.000071642215],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00021676479,0.000111514004,0.000102570695,0.00014835673,0.00014474709,0.0007285004,0.0003425946,0.000069229725,0.000070607464],"category_scores_gemma":[0.00010318424,0.00008251806,0.00005745373,0.000405515,0.000031329568,0.005295907,0.000059700797,0.00012989662,0.0017369519],"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":[0.0013063365,0.00025869368,0.0020554396,0.00021546496,0.00017740497,0.000002748483,0.015908955,0.001100304,0.039703418,0.021974191,0.5408679,0.3764291],"study_design_scores_gemma":[0.0098995445,0.0015878791,0.00938682,0.00021560771,0.000030842362,0.000041127983,0.00028401514,0.34209916,0.2272429,0.008431642,0.39916337,0.0016170965],"about_ca_topic_score_codex":0.000070508104,"about_ca_topic_score_gemma":0.0000011748716,"teacher_disagreement_score":0.374812,"about_ca_system_score_codex":0.00003806556,"about_ca_system_score_gemma":0.000040391795,"threshold_uncertainty_score":0.9990403},"labels":[],"label_agreement":null},{"id":"W2141520705","doi":"10.1023/a:1026028229881","title":"Applying Machine Learning to Text Segmentation for Information Retrieval","year":2003,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Topic Modeling","field":"Computer Science","cited_by":76,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Segmentation; Computer science; Text segmentation; Artificial intelligence; Pattern recognition (psychology); Natural language processing; Word (group theory); Mathematics","score_opus":0.016645412208762866,"score_gpt":0.25568494074736936,"score_spread":0.2390395285386065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141520705","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013145828,0.000014916606,0.98080134,0.0002860309,0.00058100437,0.001337618,0.00000948932,0.00026627906,0.0035574909],"genre_scores_gemma":[0.73996913,0.000009288218,0.25644788,0.002910964,0.00008605512,0.00012793673,0.00020223408,0.000013224993,0.0002332498],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982131,0.000054767395,0.00069648214,0.00014890144,0.0005632973,0.0003234305],"domain_scores_gemma":[0.9987821,0.0001184678,0.00030350228,0.00030270047,0.00036046572,0.00013276139],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010913797,0.00016411339,0.00015319453,0.00039728018,0.0003189477,0.00056286907,0.00036516887,0.00010262099,0.000022806034],"category_scores_gemma":[0.0011348297,0.00017024741,0.00006952147,0.0007744515,0.0000103703715,0.00702247,0.0000847463,0.00019098044,0.00033101375],"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":[0.0004527553,0.000045205004,0.0009856811,0.0003584147,0.000064169064,9.814225e-7,0.023964575,0.12270166,0.003111723,0.2245377,0.0012385389,0.6225386],"study_design_scores_gemma":[0.001439928,0.0002376027,0.00016680188,0.000026778194,0.000009425885,0.000018093671,0.0005584903,0.586629,0.014444729,0.0007945496,0.39530465,0.0003699399],"about_ca_topic_score_codex":0.000009044008,"about_ca_topic_score_gemma":7.178546e-7,"teacher_disagreement_score":0.72682333,"about_ca_system_score_codex":0.00018157878,"about_ca_system_score_gemma":0.00011393139,"threshold_uncertainty_score":0.6942488},"labels":[],"label_agreement":null},{"id":"W2151752770","doi":"10.1023/b:inrt.0000011209.19643.e2","title":"Augmenting Naive Bayes Classifiers with Statistical Language Models","year":2004,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Topic Modeling","field":"Computer Science","cited_by":247,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Naive Bayes classifier; Artificial intelligence; Computer science; Machine learning; Bayes error rate; Bayes classifier; Bayes' theorem; Classifier (UML); Conditional independence; Bayesian programming; Natural language processing; Pattern recognition (psychology); Bayes factor; Bayesian probability; Support vector machine","score_opus":0.013246135569706644,"score_gpt":0.23719751641258194,"score_spread":0.2239513808428753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151752770","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0353856,0.000009743699,0.9577029,0.00029309618,0.00011287783,0.000116915624,0.0000063739985,0.00016635569,0.006206165],"genre_scores_gemma":[0.80691046,0.0000011619221,0.19264907,0.00037025893,0.000023839555,0.0000022959912,0.000012724578,0.0000031166692,0.000027087694],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990052,0.0000133083095,0.0002491017,0.000117579155,0.0004055533,0.00020924697],"domain_scores_gemma":[0.99945194,0.000036425397,0.000099631914,0.00024781702,0.000086437336,0.00007773283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019260233,0.00009013081,0.00008838175,0.00009451572,0.000099209705,0.00023176914,0.00028488002,0.00004685853,0.000011959108],"category_scores_gemma":[0.0000530533,0.0000753612,0.00001898191,0.00022356104,0.000029844556,0.0028536632,0.00008076937,0.00012865641,0.00006952407],"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":[0.000050041595,0.000020740697,0.00007901485,0.000044875247,0.000026417561,0.000020976431,0.016849527,0.106592245,0.0000888289,0.8306463,0.00009249901,0.045488525],"study_design_scores_gemma":[0.0011933706,0.00012276406,0.00027080934,0.00004549321,0.0000070517845,0.00003632784,0.0010929676,0.98353076,0.0016095177,0.01132223,0.000528303,0.00024042602],"about_ca_topic_score_codex":0.000034223434,"about_ca_topic_score_gemma":0.0000020268442,"teacher_disagreement_score":0.87693846,"about_ca_system_score_codex":0.00009778347,"about_ca_system_score_gemma":0.00013470225,"threshold_uncertainty_score":0.30731404},"labels":[],"label_agreement":null},{"id":"W2556771250","doi":"10.1007/s10791-016-9290-6","title":"Efficient distributed selective search","year":2016,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Directorate for Computer and Information Science and Engineering; Australian Research Council; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Ranking (information retrieval); Resource (disambiguation); Index (typography); Mirroring; Data mining; Selection (genetic algorithm); Web search query; Query expansion; Search engine; Information retrieval; Distributed computing; Machine learning; Computer network; World Wide Web","score_opus":0.013532769585453928,"score_gpt":0.25299165861495426,"score_spread":0.23945888902950033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2556771250","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":[0.121592246,0.0000045393704,0.87197095,0.0015733396,0.0003030552,0.0003331726,0.000079458056,0.00034598834,0.0037972291],"genre_scores_gemma":[0.99756324,0.0000034753082,0.0018702897,0.00030209197,0.000032325006,0.000006946047,0.000025600093,0.0000035534197,0.00019245883],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980074,0.000057739282,0.00046317227,0.00013624167,0.00090950617,0.00042593354],"domain_scores_gemma":[0.9984536,0.00013150589,0.00012178879,0.00037537678,0.0007326341,0.00018507567],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006541641,0.00013749606,0.00012779776,0.00027878457,0.00021886929,0.0002628319,0.00064104854,0.000092357135,0.000096975564],"category_scores_gemma":[0.00027919008,0.00008811807,0.00007879559,0.0011349312,0.00007072811,0.0020813844,0.0002172076,0.00014357675,0.0023374083],"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":[0.0006422705,0.0002565342,0.0026746492,0.00009638011,0.000090234695,0.000018425215,0.009266807,0.0031884715,0.006046324,0.38083425,0.010860685,0.58602494],"study_design_scores_gemma":[0.009521821,0.0016442976,0.114979446,0.00018268733,0.00002747513,0.00022571711,0.0006049169,0.4565658,0.25318015,0.0019199922,0.15902816,0.002119535],"about_ca_topic_score_codex":0.000005918697,"about_ca_topic_score_gemma":1.7727879e-7,"teacher_disagreement_score":0.875971,"about_ca_system_score_codex":0.000237895,"about_ca_system_score_gemma":0.00022413634,"threshold_uncertainty_score":0.9984394},"labels":[],"label_agreement":null},{"id":"W2576646839","doi":"10.1007/s10791-016-9292-4","title":"Enhancing click models with mouse movement information","year":2017,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Relevance (law); Computer science; Information retrieval; Search engine; Process (computing); Movement (music); Artificial intelligence; World Wide Web; Human–computer interaction; Programming language","score_opus":0.01890283138193856,"score_gpt":0.25183785941004816,"score_spread":0.23293502802810961,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2576646839","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":[0.074594736,0.000003416257,0.89941126,0.0008834596,0.00033452077,0.00063000387,0.0000282648,0.0003213146,0.023793044],"genre_scores_gemma":[0.9702352,0.000022589564,0.025888497,0.0030677768,0.00006222414,0.000033202254,0.00011632415,0.000008877815,0.0005652608],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99749047,0.000023834724,0.00076332013,0.00012024216,0.0011735273,0.000428634],"domain_scores_gemma":[0.9971603,0.00002952202,0.0007533819,0.001108001,0.00075059524,0.00019817293],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.00074582966,0.00021472496,0.00019205917,0.00031680072,0.00101654,0.0028612309,0.0013793274,0.00011770183,0.000038015824],"category_scores_gemma":[0.00016208921,0.00017306882,0.00007360365,0.0002505794,0.00008388788,0.049769036,0.00038182572,0.00025919505,0.0007804157],"study_design_candidate":"theoretical_or_conceptual","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":[0.0008530401,0.0001461092,0.0013585637,0.00038464775,0.00012486996,0.000010421782,0.02686745,0.010357189,0.0009824913,0.7371527,0.0029409765,0.21882156],"study_design_scores_gemma":[0.007303429,0.0013820683,0.014789671,0.00017608453,0.00003768646,0.000061102444,0.0015071632,0.7228205,0.16699618,0.0049036625,0.07814456,0.001877862],"about_ca_topic_score_codex":0.0000732414,"about_ca_topic_score_gemma":0.000006542178,"teacher_disagreement_score":0.8956405,"about_ca_system_score_codex":0.00015050804,"about_ca_system_score_gemma":0.00024040586,"threshold_uncertainty_score":0.9999976},"labels":[],"label_agreement":null},{"id":"W2584295907","doi":"10.1007/s10791-017-9294-x","title":"Constructing click models for search users","year":2017,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; World Wide Web; Information retrieval","score_opus":0.05359408056046548,"score_gpt":0.31268713016859917,"score_spread":0.2590930496081337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2584295907","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021890763,0.000006000443,0.9805351,0.0015249994,0.00025729835,0.00036002957,0.000016737262,0.0002699179,0.014840854],"genre_scores_gemma":[0.8895741,0.000013549419,0.10963373,0.0003460507,0.00006788102,0.000016047497,0.00002178638,0.0000061227192,0.00032069557],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989709,0.000016188344,0.00032800462,0.00013145432,0.00032556237,0.00022785555],"domain_scores_gemma":[0.99840707,0.00007325532,0.00028783936,0.00070090743,0.00045533167,0.0000756256],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006205535,0.00009512767,0.000114927374,0.000112688285,0.0006293505,0.0011723704,0.0010959519,0.000085869964,0.000006866044],"category_scores_gemma":[0.00031700465,0.00008933809,0.000075009724,0.00011729876,0.000103534134,0.006956673,0.00019388196,0.000115604904,0.000053244832],"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":[0.00004301227,0.000009681312,0.00023612403,0.00004906723,0.000012202409,4.0019071e-7,0.0006245333,0.00002188119,0.00021378041,0.6774265,0.00060163176,0.32076117],"study_design_scores_gemma":[0.0008813962,0.00012989723,0.00067988236,0.0000307584,0.0000064941028,0.000021174043,0.00034212542,0.84540033,0.11571808,0.01943032,0.017039202,0.00032032223],"about_ca_topic_score_codex":0.000012168763,"about_ca_topic_score_gemma":4.3678293e-7,"teacher_disagreement_score":0.8873851,"about_ca_system_score_codex":0.00007630504,"about_ca_system_score_gemma":0.00011792598,"threshold_uncertainty_score":0.9998645},"labels":[],"label_agreement":null},{"id":"W2803782109","doi":"10.1007/s10791-018-9332-3","title":"(CF)2 architecture: contextual collaborative filtering","year":2018,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Oakville-Trafalgar Memorial Hospital; Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Collaborative filtering; Computer science; Recommender system; Context (archaeology); Architecture; The Internet; Selection (genetic algorithm); Fraction (chemistry); Machine learning; Scale (ratio); Artificial intelligence; Contextual design; Filter (signal processing); Information retrieval; Data science; World Wide Web; Human–computer interaction","score_opus":0.011036141244884471,"score_gpt":0.24795552541158117,"score_spread":0.2369193841666967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2803782109","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0058195796,0.000012701291,0.9598922,0.0006531852,0.0006009172,0.00023533798,0.000008559334,0.00038600672,0.0323915],"genre_scores_gemma":[0.9643563,0.0000030700332,0.034359057,0.000993046,0.00016343998,0.00000846122,0.000007479706,0.0000038490675,0.000105296494],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.999128,0.00004046856,0.00031151294,0.00010324893,0.00024348851,0.00017331909],"domain_scores_gemma":[0.99913514,0.000042058935,0.000154798,0.00030258182,0.00030366355,0.000061784485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002917208,0.00010086744,0.000114618895,0.00014042438,0.00014226853,0.00034343754,0.00043180128,0.0000617633,0.000032991084],"category_scores_gemma":[0.00007161121,0.0000858862,0.000032601267,0.00050138496,0.00005006672,0.0017805841,0.000148298,0.00009592235,0.0002163107],"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":[0.00015401366,0.000043818764,0.0003142883,0.000075998054,0.000090184454,0.000005344052,0.035227522,0.00001831054,0.0027903626,0.2796016,0.056454618,0.62522393],"study_design_scores_gemma":[0.00066167925,0.000732184,0.00087124086,0.00004955779,0.0000029524508,0.000063455314,0.0003094287,0.009323559,0.10258636,0.00323473,0.88180184,0.00036300524],"about_ca_topic_score_codex":0.000012598806,"about_ca_topic_score_gemma":0.000004886374,"teacher_disagreement_score":0.95853674,"about_ca_system_score_codex":0.00004030928,"about_ca_system_score_gemma":0.00006809886,"threshold_uncertainty_score":0.35023373},"labels":[],"label_agreement":null},{"id":"W2850470857","doi":"10.1007/s10791-018-9337-y","title":"User interest prediction over future unobserved topics on social networks","year":2018,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Focus (optics); Work (physics); User modeling; Data science; Social network (sociolinguistics); World Wide Web; Social media; User interface; Engineering","score_opus":0.02993305481423278,"score_gpt":0.2657125739616944,"score_spread":0.23577951914746162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2850470857","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":[0.057244815,0.0000135595765,0.9171967,0.0032286828,0.0063234987,0.00042738626,0.000012877313,0.0009923772,0.014560085],"genre_scores_gemma":[0.9928478,0.0000081967655,0.0017758133,0.0019356227,0.003091968,0.000006827901,0.000030371966,0.000005805956,0.00029761982],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991594,0.00003760323,0.00032001617,0.000106612664,0.00021528432,0.00016111134],"domain_scores_gemma":[0.9993788,0.000013994493,0.00015911805,0.00025167383,0.0001538231,0.000042564378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025238615,0.00010264743,0.000099669414,0.00009391858,0.00018449697,0.00029597187,0.0003541292,0.00016356495,0.000031177584],"category_scores_gemma":[0.000015051504,0.00008801559,0.0000554335,0.00028902057,0.000023476632,0.0017487991,0.00010448655,0.00016559202,0.00005960936],"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":[0.00014061108,0.000060611415,0.0019748232,0.000042825814,0.000056056786,0.0000018677002,0.0043324614,0.000025392952,0.000029887386,0.33466592,0.36098418,0.29768535],"study_design_scores_gemma":[0.00048162305,0.00039730853,0.042231776,0.000031678213,0.0000037647662,0.000007133579,0.00008679782,0.050471973,0.0009123939,0.00050579564,0.90467817,0.00019159482],"about_ca_topic_score_codex":0.000009484728,"about_ca_topic_score_gemma":0.00000470562,"teacher_disagreement_score":0.93560296,"about_ca_system_score_codex":0.000073249765,"about_ca_system_score_gemma":0.000023343724,"threshold_uncertainty_score":0.35891718},"labels":[],"label_agreement":null},{"id":"W2967813257","doi":"10.1007/s10791-019-09361-0","title":"Evaluating sentence-level relevance feedback for high-recall information retrieval","year":2019,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Topic Modeling","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Relevance feedback; Relevance (law); Recall; Computer science; Sentence; Baseline (sea); Information retrieval; Precision and recall; Natural language processing; Artificial intelligence; Cognitive psychology; Psychology; Image retrieval","score_opus":0.046889037076321534,"score_gpt":0.292025163440755,"score_spread":0.2451361263644335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2967813257","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2182396,0.000016024203,0.77572924,0.00093111146,0.0019465592,0.0011457411,0.000042616735,0.00029213502,0.0016569571],"genre_scores_gemma":[0.7672732,0.000014935377,0.22958718,0.0021081946,0.00019051605,0.000020718922,0.0001948523,0.000013963115,0.0005964512],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99687326,0.000056119028,0.0011590549,0.0002631182,0.0011423145,0.00050615775],"domain_scores_gemma":[0.9969814,0.00035141956,0.0006795368,0.00081848627,0.0010387616,0.00013040485],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016578173,0.0002508897,0.0002852199,0.00029412174,0.0002080377,0.0006004287,0.0009571533,0.00020630515,0.000053029653],"category_scores_gemma":[0.001572526,0.00024816263,0.00011809158,0.00072862575,0.000030044108,0.0123847425,0.00026186585,0.0002828366,0.001411036],"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":[0.0015631478,0.00008240072,0.0010562608,0.0011581822,0.000130585,0.0000013752292,0.011845332,0.06378419,0.0036497493,0.2340185,0.0047643227,0.677946],"study_design_scores_gemma":[0.0026235513,0.00040659506,0.0018679746,0.00009905322,0.000012605132,0.000017403221,0.0002236504,0.9673481,0.0053612343,0.0036413579,0.017933413,0.00046508657],"about_ca_topic_score_codex":0.000022124355,"about_ca_topic_score_gemma":8.6951013e-7,"teacher_disagreement_score":0.9035639,"about_ca_system_score_codex":0.00025310353,"about_ca_system_score_gemma":0.0003034283,"threshold_uncertainty_score":0.9999971},"labels":[],"label_agreement":null},{"id":"W2976855657","doi":"10.1007/s10791-019-09364-x","title":"ReBoost: a retrieval-boosted sequence-to-sequence model for neural response generation","year":2019,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Topic Modeling","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Computer science; Benchmark (surveying); Conversation; Sequence (biology); Process (computing); Artificial intelligence; Natural language generation; Artificial neural network; Language model; Natural language processing; Recurrent neural network; Machine learning; Natural language; Programming language; Linguistics","score_opus":0.06926171490965688,"score_gpt":0.29959857846808324,"score_spread":0.23033686355842636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2976855657","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":[0.40818283,0.0000062756976,0.58837533,0.0015131133,0.00053363194,0.0009094819,0.000030324427,0.00019997731,0.00024905798],"genre_scores_gemma":[0.9350578,0.0000021223357,0.06088006,0.002997816,0.00009069626,0.000020059888,0.00005538219,0.00001238719,0.00088363636],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99767905,0.000092692484,0.00073708943,0.00036894815,0.0006877419,0.00043447534],"domain_scores_gemma":[0.9978774,0.00017365815,0.00027023847,0.00090754335,0.00058954593,0.00018158434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014507044,0.00021617029,0.00022166909,0.00035613895,0.00018148121,0.0004467911,0.0008575641,0.0001681538,0.000014667229],"category_scores_gemma":[0.00086240034,0.00021705354,0.00010178794,0.0007054896,0.000024184365,0.0040901327,0.000158905,0.00019117884,0.00035870925],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003132684,0.000030630734,0.00012636957,0.00011896733,0.000027850507,0.0000041785725,0.010979198,0.68053436,0.24611829,0.032734226,0.0015550157,0.024638196],"study_design_scores_gemma":[0.00079680333,0.00024183837,0.00005211249,0.000021199045,0.000004531062,0.000019686006,0.000029589304,0.9821163,0.013716036,0.00053965,0.0021882409,0.00027400683],"about_ca_topic_score_codex":0.0000067163414,"about_ca_topic_score_gemma":0.0000010079909,"teacher_disagreement_score":0.52749527,"about_ca_system_score_codex":0.00028532668,"about_ca_system_score_gemma":0.0003951143,"threshold_uncertainty_score":0.8851187},"labels":[],"label_agreement":null},{"id":"W3044191208","doi":"10.1007/s10791-020-09379-9","title":"Robust keyword search in large attributed graphs","year":2020,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada); Toronto Metropolitan University; University of Waterloo; Ontario Tech University","funders":"","keywords":"Scalability; Computer science; SPARK (programming language); Theoretical computer science; Set (abstract data type); Graph; Keyword search; Data mining; Information retrieval; Database","score_opus":0.0316519411098354,"score_gpt":0.26000995574858576,"score_spread":0.22835801463875036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3044191208","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":[0.6700756,0.000023736013,0.30580017,0.001735778,0.00007143352,0.00061277737,0.00016896734,0.00033222453,0.021179318],"genre_scores_gemma":[0.9984302,0.000001855208,0.000724249,0.00035250632,0.00006274371,0.000004680305,0.00039961928,0.000005377923,0.000018776982],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99899304,0.00004124949,0.00037852972,0.00009519957,0.00024692435,0.0002450823],"domain_scores_gemma":[0.999545,0.000032311575,0.00008597859,0.00013836566,0.00010949534,0.000088896064],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00028077708,0.00010246612,0.0001721506,0.00014606808,0.00006406277,0.00008397778,0.00017847012,0.000030567757,0.0009196281],"category_scores_gemma":[0.00001757921,0.000104563864,0.00009170584,0.001211732,0.000016888824,0.0006214853,0.00009380715,0.00023852763,0.00019610838],"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":[0.00051283726,0.0002535986,0.7076033,0.00008924984,0.00026956064,0.0000063423195,0.006181812,0.017368319,0.00024026903,0.17277454,0.037743744,0.056956433],"study_design_scores_gemma":[0.0042768675,0.0002875272,0.08356037,0.000064983506,0.000065143315,0.0000013971421,0.002301052,0.6729969,0.006315765,0.005333474,0.22376387,0.0010326556],"about_ca_topic_score_codex":0.00005231302,"about_ca_topic_score_gemma":0.000003286784,"teacher_disagreement_score":0.65562856,"about_ca_system_score_codex":0.000025835197,"about_ca_system_score_gemma":0.00003862363,"threshold_uncertainty_score":0.9999937},"labels":[],"label_agreement":null},{"id":"W3133365413","doi":"10.1007/s10791-021-09398-0","title":"Neural ranking models for document retrieval","year":2021,"lang":"en","type":"preprint","venue":"Information Retrieval","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Instituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de México; National Institute of Standards and Technology; Institute for Catastrophic Loss Reduction; National Science Foundation","keywords":"Ranking (information retrieval); Computer science; Artificial intelligence; Machine learning; Set (abstract data type); Variety (cybernetics); Information retrieval; Artificial neural network; Deep learning; Learning to rank; Data mining","score_opus":0.02256006568427007,"score_gpt":0.29165840351195466,"score_spread":0.2690983378276846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3133365413","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04124403,0.000113104295,0.951335,0.0025351665,0.0013943673,0.0014635592,0.000044837623,0.0005711074,0.0012987934],"genre_scores_gemma":[0.86149025,0.000020281153,0.13652611,0.00088946446,0.00019944494,0.000098002354,0.0006880732,0.000021633166,0.00006673157],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970396,0.00010415518,0.0010039641,0.0005231541,0.00088223896,0.00044686947],"domain_scores_gemma":[0.99659675,0.00027397845,0.0007667113,0.0013829722,0.00081933104,0.00016026023],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000976382,0.00037575487,0.0004195159,0.00032877488,0.00030860055,0.0018741086,0.0016955911,0.00039580135,0.00002584736],"category_scores_gemma":[0.00047302234,0.00040250932,0.00032725662,0.00055272394,0.000039755752,0.0029805733,0.0016800114,0.0009526065,0.000047810176],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018912969,0.00005924394,0.00007008817,0.00061685196,0.00013181324,0.000003048625,0.0065932767,0.86375654,0.00013147744,0.07432712,0.00065763557,0.053463805],"study_design_scores_gemma":[0.0007125494,0.000052188916,0.0005041033,0.00007367885,0.000025390507,0.000012825454,0.000048694892,0.9826886,0.0006501641,0.012329965,0.0024774263,0.00042441476],"about_ca_topic_score_codex":0.00010356543,"about_ca_topic_score_gemma":0.0000013685257,"teacher_disagreement_score":0.8202462,"about_ca_system_score_codex":0.000288609,"about_ca_system_score_gemma":0.0004656279,"threshold_uncertainty_score":0.9998427},"labels":[],"label_agreement":null},{"id":"W3196754070","doi":"10.1007/s10791-022-09411-0","title":"Shallow pooling for sparse labels","year":2022,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Ranking (information retrieval); Mean reciprocal rank; Information retrieval; Pooling; Computer science; Relevance (law); Set (abstract data type); Rank (graph theory); Learning to rank; Preference; Artificial intelligence; Statistics; Mathematics; Combinatorics","score_opus":0.023324810570541036,"score_gpt":0.2593679142488165,"score_spread":0.23604310367827547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196754070","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":[0.07467826,0.000034269942,0.90955186,0.0023939474,0.0019012669,0.001462768,0.00021307403,0.0006218875,0.009142665],"genre_scores_gemma":[0.9702983,0.0000048884003,0.023423452,0.004593429,0.00010128556,0.0001654993,0.0002870214,0.0000115953335,0.0011145377],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981591,0.000040890245,0.00052643067,0.00011936012,0.0008040195,0.000350185],"domain_scores_gemma":[0.9989461,0.00010081501,0.00021037542,0.00033126646,0.00030075054,0.00011071544],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010516762,0.0001191742,0.00013120439,0.00030098276,0.00071853335,0.00034768722,0.00084700546,0.000043363907,0.00021372864],"category_scores_gemma":[0.00017131362,0.00012068839,0.00010880024,0.0007920345,0.000021395117,0.0036854262,0.00039187315,0.00022563526,0.0001922615],"study_design_candidate":"theoretical_or_conceptual","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":[0.00064494496,0.00019257276,0.0006500225,0.00017518937,0.0000629955,0.000010056404,0.014522929,0.011451964,0.00076544925,0.73159003,0.017509187,0.22242467],"study_design_scores_gemma":[0.002012526,0.0006285805,0.001442775,0.000006472383,0.000010382867,0.00006582828,0.00060741015,0.318732,0.0029158813,0.0026736336,0.6704598,0.0004447014],"about_ca_topic_score_codex":0.0000061862816,"about_ca_topic_score_gemma":2.8319036e-7,"teacher_disagreement_score":0.89562005,"about_ca_system_score_codex":0.0001600988,"about_ca_system_score_gemma":0.00020508142,"threshold_uncertainty_score":0.552645},"labels":[],"label_agreement":null},{"id":"W4387453959","doi":"10.1007/s10791-023-09421-6","title":"Learning heterogeneous subgraph representations for team discovery","year":2023,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; York University; Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Overfitting; Ranking (information retrieval); Machine learning; Set (abstract data type); Graph; Task (project management); Artificial intelligence; Baseline (sea); Representation (politics); Data science; Artificial neural network; Theoretical computer science","score_opus":0.014467129190787973,"score_gpt":0.27384187858459824,"score_spread":0.2593747493938103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387453959","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":[0.11781285,0.000014962443,0.878769,0.0004765447,0.00070233323,0.00047144777,0.000013560189,0.0009456194,0.0007936924],"genre_scores_gemma":[0.9928805,0.000037953974,0.0058062314,0.0003788746,0.00008167373,0.000024642792,0.0001629406,0.000009801276,0.00061733375],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989251,0.000030572148,0.00032336477,0.00015681272,0.00027812438,0.00028601644],"domain_scores_gemma":[0.9990876,0.00026219827,0.00016135504,0.00030171184,0.00012484184,0.00006233488],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023699981,0.000102789934,0.0001011972,0.00027751294,0.00028634863,0.0003397961,0.00038532744,0.000056957808,0.0000021891647],"category_scores_gemma":[0.00027478155,0.00010083798,0.00011058575,0.0014606253,0.00003137578,0.004396531,0.00013819538,0.00013791537,0.000120010525],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015282634,0.000024779501,0.0024931366,0.000059791142,0.00006092834,0.00000802609,0.0035782913,0.8198736,0.0006554859,0.042812742,0.012396891,0.11788352],"study_design_scores_gemma":[0.0008326068,0.00030551577,0.0043461723,0.000019066354,0.0000078233315,0.000030610237,0.00021255646,0.9289084,0.0042346884,0.009526776,0.051218394,0.0003573806],"about_ca_topic_score_codex":0.000002065455,"about_ca_topic_score_gemma":6.8719885e-7,"teacher_disagreement_score":0.8750677,"about_ca_system_score_codex":0.000024828762,"about_ca_system_score_gemma":0.000029263996,"threshold_uncertainty_score":0.41120535},"labels":[],"label_agreement":null}]}