{"meta":{"query_hash":"6a967eb56060","filters":{"venue":"Information Retrieval Research"},"cohort_total":2,"direct_labels_cover":0,"predictions_cover":2,"exported":2,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/6a967eb56060","api":"https://metacan.xera.ac/api/v1/cohort?venue=Information+Retrieval+Research"},"results":[{"id":"W4404401204","doi":"10.54195/irrj.19910","title":"Annotative Indexing","year":2025,"lang":"en","type":"preprint","venue":"Information Retrieval Research","topic":"Advanced Text Analysis 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":"University of Waterloo","funders":"Tsinghua University; University of Glasgow","keywords":"Search engine indexing; Computer science; Information retrieval","score_opus":0.08469652661856103,"score_gpt":0.4552504328181435,"score_spread":0.37055390619958245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404401204","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":[0.0005260865,0.000103695376,0.9291891,0.0011651751,0.00021989801,0.0006821418,0.000028593406,0.0005410636,0.06754427],"genre_scores_gemma":[0.49999458,0.0010656529,0.4861001,0.001586719,0.00031180988,0.00042157172,0.00048024234,0.000032035965,0.010007269],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99597454,0.0003386268,0.00069881295,0.00039535397,0.002059265,0.0005334219],"domain_scores_gemma":[0.9947589,0.0006633488,0.0002934341,0.001377565,0.0027850247,0.00012172086],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0035546923,0.00022223598,0.0003216785,0.0023111259,0.0003065796,0.0010250395,0.0029476935,0.00039748225,0.000022405788],"category_scores_gemma":[0.0026647192,0.00022078896,0.0001466131,0.0029223599,0.00014579874,0.0027377422,0.006042666,0.002444451,0.00021398503],"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":[0.00011613727,0.00007724597,0.00019137458,0.0007700101,0.00021311923,0.00001699317,0.010195987,0.0038050956,0.00011400067,0.5616689,0.020423902,0.40240723],"study_design_scores_gemma":[0.0004839082,0.00016717662,0.0007221558,0.00080851483,0.000015643842,0.000003983932,0.00043106155,0.35137397,0.031422187,0.4366107,0.17707989,0.0008808248],"about_ca_topic_score_codex":0.00005718113,"about_ca_topic_score_gemma":0.000002691161,"teacher_disagreement_score":0.4994685,"about_ca_system_score_codex":0.00059594476,"about_ca_system_score_gemma":0.0011588586,"threshold_uncertainty_score":0.99985695},"labels":[],"label_agreement":null},{"id":"W4415499254","doi":"10.54195/irrj.22626","title":"Effectiveness of In-Context Learning for Due Diligence","year":2025,"lang":"en","type":"article","venue":"Information Retrieval Research","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"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":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Universiteit van Amsterdam; Canadian Institute of Steel Construction","keywords":"Due diligence; Dependency (UML); Python (programming language); Diligence; Task (project management); Natural language","score_opus":0.048900071996636006,"score_gpt":0.38375496990580404,"score_spread":0.33485489790916806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415499254","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":[0.26754448,0.00005013155,0.7294726,0.00013352235,0.00011075901,0.0004537493,5.252512e-7,0.000022720964,0.0022115554],"genre_scores_gemma":[0.99832,0.00000866534,0.0015074235,0.000016974378,0.0000051205025,0.000026972759,0.0000021946496,0.0000014166627,0.00011126353],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99866337,0.00022441031,0.0003192432,0.000121149904,0.000429777,0.00024204212],"domain_scores_gemma":[0.99734706,0.0016834984,0.00005088863,0.00025295085,0.0006368335,0.000028748727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052079787,0.00005064908,0.00012346578,0.0005822935,0.000097338816,0.00009137415,0.0005610719,0.0000633058,0.000002456996],"category_scores_gemma":[0.0031815781,0.000049421833,0.000034651945,0.0012583525,0.000041308253,0.001050036,0.00023508126,0.0002673277,0.000014128544],"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":[0.00054245896,0.00004481068,0.008007292,0.0020187553,0.000019286947,0.0000016900948,0.0038244752,0.01681437,0.0029523124,0.584163,0.00006187101,0.38154966],"study_design_scores_gemma":[0.0011868955,0.00019634711,0.035849173,0.00049256795,0.0000013683813,0.0000013062325,0.00056103495,0.8431069,0.09826206,0.016751207,0.00346766,0.00012345606],"about_ca_topic_score_codex":0.00006318568,"about_ca_topic_score_gemma":0.0000036176446,"teacher_disagreement_score":0.8262926,"about_ca_system_score_codex":0.0001211663,"about_ca_system_score_gemma":0.0002923338,"threshold_uncertainty_score":0.3808876},"labels":[],"label_agreement":null}]}