{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":6,"total_is_capped":false,"direct_labels_cover":1,"predictions_cover":6,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"cba7bb08c2d0","filters":{"venue":"25th International Conference on Software Engineering, 2003. Proceedings."}},"results":[{"id":"W4241947741","doi":"10.1109/icse.2003.1201219","title":"Hipikat: recommending pertinent software development artifacts","year":2003,"lang":"en","type":"article","venue":"25th International Conference on Software Engineering, 2003. Proceedings.","topic":"Software Engineering Research","field":"Computer Science","cited_by":173,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"U.S. Consumer Product Safety Commission","keywords":"Eclipse; Computer science; Task (project management); Context (archaeology); Open source; Open source software; Software; Software project management; Open-source software development; Software engineering; Software development; World Wide Web; Data science; Software construction; Engineering; Systems engineering; Programming language","authors":[{"name":"Davor Čubranić","is_ca":true},{"name":"Gail C. Murphy","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04131285254867295,"gpt":0.2738731626548143,"spread":0.2325603101061413,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003804005,0.001259243,0.0006703684,0.005039202,0.001179009,0.002569004,0.002227807,0.001740095,0.005219799],"category_scores_gemma":[0.02931864,0.000779541,0.0005792489,0.002375835,0.0004518373,0.003507836,0.00233165,0.0009718923,0.002398761],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006533288,"about_ca_system_score_gemma":0.002566259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00468533,"about_ca_topic_score_gemma":0.0175691,"domain_scores_codex":[0.9979973,0.0005966899,0.0001982212,0.0004392025,0.0006793251,0.00008924515],"domain_scores_gemma":[0.9868666,0.007464213,0.001309423,0.001879244,0.001740775,0.0007397554],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004843681,0.0007509786,0.02697704,0.002107012,0.0001863315,0.001249423,0.008646168,0.005883065,0.01735983,0.00300938,0.03743088,0.8959156],"study_design_scores_gemma":[0.0008710449,0.002942074,0.08657593,0.001990422,0.001353394,0.00600357,0.01910075,0.2592354,0.07066793,0.02892349,0.5213999,0.0009361308],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2522596,0.001673685,0.6737372,0.002776929,0.0003156584,0.003059874,0.003240101,0.04771532,0.01522165],"genre_scores_gemma":[0.15545,0.0005962084,0.8318896,0.0001993126,0.00006514585,0.0005442525,0.003267194,0.0006451583,0.007343072],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005219799,"threshold_uncertainty_score":0.0201177,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4229596932","doi":"10.1109/icse.2003.1201189","title":"Using benchmarking to advance research: a challenge to software engineering","year":2003,"lang":"en","type":"article","venue":"25th International Conference on Software Engineering, 2003. Proceedings.","topic":"Software Engineering Research","field":"Computer Science","cited_by":150,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Benchmarking; Benchmark (surveying); Computer science; Data science; Software engineering; Software; Academic community; Engineering management; Management science; Engineering","authors":[{"name":"S.E. Sim","is_ca":true},{"name":"Steve Easterbrook","is_ca":true},{"name":"Richard C. Holt","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1101268605763671,"gpt":0.3553565504832152,"spread":0.2452296899068481,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3067313,0.003312443,0.005469552,0.01250765,0.006122894,0.03085333,0.01107002,0.009709315,0.001905074],"category_scores_gemma":[0.5274109,0.001453562,0.0017279,0.01837414,0.02152988,0.05805392,0.02213132,0.01872171,0.002495675],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007025863,"about_ca_system_score_gemma":0.02400173,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002756448,"about_ca_topic_score_gemma":0.002514663,"domain_scores_codex":[0.6199469,0.2506683,0.02084692,0.01553928,0.08845881,0.004539864],"domain_scores_gemma":[0.2921697,0.4562198,0.02753133,0.1162977,0.09335408,0.01442746],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001250323,0.0003574165,0.00556878,0.00191922,0.0001852378,0.0001715079,0.004492269,0.009868663,0.001382212,0.4544932,0.03955973,0.4818767],"study_design_scores_gemma":[0.00008790466,0.0003992956,0.001505697,0.002298149,0.00004907482,0.0001694284,0.003333045,0.01498317,0.00163817,0.8636523,0.1116718,0.0002119368],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0188834,0.02802297,0.6365957,0.280543,0.004217784,0.0006292321,0.0003318153,0.003720886,0.02705528],"genre_scores_gemma":[0.207364,0.0152135,0.7508223,0.01493976,0.003533965,0.00204169,0.0007791676,0.002474252,0.002831387],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6932687,"threshold_uncertainty_score":0.8549237,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4238417811","doi":"10.1109/icse.2003.1201304","title":"FEAT a tool for locating, describing, and analyzing concerns in source code","year":2003,"lang":"en","type":"article","venue":"25th International Conference on Software Engineering, 2003. Proceedings.","topic":"Software Engineering Research","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Source code; Task (project management); Code (set theory); Programming language; Software engineering; Code review; KPI-driven code analysis; Open source; Static program analysis; Software development; Software; Systems engineering; Engineering","authors":[{"name":"Martin P. Robillard","is_ca":true},{"name":"Gail C. Murphy","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05235386629265224,"gpt":0.2912926794672911,"spread":0.2389388131746389,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002989808,0.003206523,0.001049114,0.007514638,0.001905586,0.003243704,0.00297387,0.002854922,0.02030211],"category_scores_gemma":[0.01422138,0.002680452,0.00229287,0.002586378,0.001493242,0.007018638,0.003672202,0.003253773,0.01001387],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001169461,"about_ca_system_score_gemma":0.002325973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005821608,"about_ca_topic_score_gemma":0.008650236,"domain_scores_codex":[0.9981282,0.0003971429,0.0002470581,0.0003069327,0.0007771394,0.0001435455],"domain_scores_gemma":[0.9924248,0.004633057,0.0007637523,0.001254946,0.0007823501,0.0001409545],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007338863,0.0005725955,0.01593448,0.003366544,0.0005168541,0.002413125,0.004427725,0.01351066,0.03359163,0.0572394,0.3358353,0.5318578],"study_design_scores_gemma":[0.0004223207,0.0004626047,0.008530466,0.001237151,0.000367432,0.00507905,0.0009914377,0.1585298,0.05467959,0.05780772,0.7114027,0.0004897621],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00484201,0.0004867203,0.7262996,0.0002407706,0.0001298436,0.0004000089,0.004407807,0.2575556,0.005637577],"genre_scores_gemma":[0.04515002,0.0008788231,0.8784806,0.0003779311,0.0000923781,0.0009864848,0.02236527,0.03605144,0.01561711],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02030211,"threshold_uncertainty_score":0.06791735,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4239921431","doi":"10.1109/icse.2003.1201214","title":"Design pattern rationale graphs: linking design to source","year":2003,"lang":"en","type":"article","venue":"25th International Conference on Software Engineering, 2003. Proceedings.","topic":"Software Engineering Research","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Software design pattern; Computer science; Design pattern; Structural pattern; Flexibility (engineering); Pattern language (formal languages); Source code; TRACE (psycholinguistics); Code (set theory); Representation (politics); Software engineering; Human–computer interaction; Programming language; Software design; Software development; Software","authors":[{"name":"Elisa Baniassad","is_ca":true},{"name":"G.C. Murphy","is_ca":true},{"name":"C. Schwanninger","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05281837649059293,"gpt":0.2709705174956941,"spread":0.2181521410051012,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007895775,0.002258965,0.0007382983,0.00860691,0.001504263,0.004369649,0.002866488,0.002797218,0.009306025],"category_scores_gemma":[0.04476909,0.002085609,0.001869139,0.005917515,0.002114686,0.00749288,0.004954023,0.003089373,0.003393876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001529198,"about_ca_system_score_gemma":0.004018615,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007418426,"about_ca_topic_score_gemma":0.009502147,"domain_scores_codex":[0.9934676,0.002830352,0.0006144592,0.000679174,0.002198979,0.0002094344],"domain_scores_gemma":[0.9730483,0.01608979,0.002318519,0.005203233,0.002927991,0.0004120809],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001856561,0.0003985078,0.004328751,0.001933095,0.0001995434,0.001416501,0.00499782,0.02851656,0.008240688,0.231383,0.04905101,0.6693489],"study_design_scores_gemma":[0.0001728523,0.0001512034,0.001798076,0.001242427,0.0001768128,0.001100418,0.001085791,0.1581999,0.01710244,0.4169552,0.4017831,0.0002317346],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002142907,0.0001836315,0.9830722,0.0005967065,0.00006740093,0.0004029993,0.0008152386,0.008832308,0.00388674],"genre_scores_gemma":[0.02288585,0.0006895185,0.9661985,0.0003689141,0.00004722627,0.0007616135,0.003391821,0.002521135,0.003135498],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009306025,"threshold_uncertainty_score":0.0417574,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4237741047","doi":"10.1109/icse.2003.1201251","title":"Empowering software engineers in human-centered design","year":2003,"lang":"en","type":"article","venue":"25th International Conference on Software Engineering, 2003. Proceedings.","topic":"Usability and User Interface Design","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Usability; Computer science; Software engineering; Usability engineering; Social software engineering; Software development; Toolbox; Software construction; Human–computer interaction; Software; Programming language","authors":[{"name":"A. Seffah","is_ca":true},{"name":"A. Andreevskaia","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05692146588363678,"gpt":0.2961389041541138,"spread":0.239217438270477,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01473179,0.0006573225,0.0004388154,0.001638209,0.002179711,0.005686185,0.001085214,0.001906718,0.002058082],"category_scores_gemma":[0.02931597,0.0006605936,0.000449861,0.001117947,0.006644823,0.005249107,0.005375229,0.003017793,0.0009844899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001161913,"about_ca_system_score_gemma":0.004402115,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001129137,"about_ca_topic_score_gemma":0.001374863,"domain_scores_codex":[0.9838746,0.01143019,0.0005582529,0.0009015035,0.002689147,0.0005463058],"domain_scores_gemma":[0.9787339,0.01353087,0.0009540963,0.002884756,0.002647186,0.001249168],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.0001014957,0.0009207461,0.009840881,0.001053089,0.00006312605,0.0007005602,0.13689,0.0083375,0.01234374,0.3032603,0.01517734,0.5113114],"study_design_scores_gemma":[0.0002230799,0.0006810344,0.004770628,0.001517467,0.0000795118,0.001499491,0.02180975,0.02968884,0.009530321,0.5708585,0.3592029,0.000138331],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05980871,0.001593858,0.8869898,0.01213366,0.0002040062,0.0005566413,0.00002851043,0.001120128,0.03756469],"genre_scores_gemma":[0.4435472,0.00213241,0.5405033,0.002764151,0.000153114,0.0009288876,0.00009271966,0.0001890043,0.009689256],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01473179,"threshold_uncertainty_score":0.07791013,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4243475163","doi":"10.1109/icse.2003.1201295","title":"/spl chi/Chek: A model checker for multi-valued reasoning","year":2003,"lang":"en","type":"article","venue":"25th International Conference on Software Engineering, 2003. Proceedings.","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Model checking; Symbolic trajectory evaluation; Computer science; Computation tree logic; Generalization; Extension (predicate logic); Temporal logic; Theoretical computer science; Programming language; Linear temporal logic; Algorithm; Mathematics","authors":[{"name":"Steve Easterbrook","is_ca":true},{"name":"Marsha Chećhik","is_ca":true},{"name":"Benet Devereux","is_ca":true},{"name":"Arie Gurfinkel","is_ca":true},{"name":"Albert Lai","is_ca":true},{"name":"Victor Petrovykh","is_ca":true},{"name":"Anya Tafliovich","is_ca":true},{"name":"Chris Thompson-Walsh","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08485247251597294,"gpt":0.3296170011743911,"spread":0.2447645286584182,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003099305,0.001201607,0.001192611,0.001566034,0.0008812741,0.00248355,0.003995146,0.001646388,0.007160089],"category_scores_gemma":[0.009413043,0.001243223,0.002038342,0.001079852,0.002317003,0.005575691,0.003476123,0.005129006,0.001888943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001392373,"about_ca_system_score_gemma":0.002937815,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005380557,"about_ca_topic_score_gemma":0.007941934,"domain_scores_codex":[0.9962728,0.0009432839,0.0003532177,0.0004425069,0.001673019,0.0003152129],"domain_scores_gemma":[0.9936737,0.003152992,0.0003952547,0.001634615,0.0009401423,0.0002032898],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001094907,0.0006505024,0.005013171,0.001602511,0.0005817183,0.001191139,0.000605824,0.3168197,0.05029256,0.2842551,0.05304138,0.2848515],"study_design_scores_gemma":[0.0001857556,0.0000886535,0.0002487995,0.000098091,0.000124307,0.0002514854,0.00003063082,0.885756,0.04215201,0.04687605,0.02411998,0.00006819915],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004624398,0.0001311774,0.9715551,0.0002283613,0.0001186894,0.0001403093,0.0004569101,0.02076831,0.001976696],"genre_scores_gemma":[0.1256808,0.0003460225,0.8631982,0.0007421831,0.00008274405,0.0004196919,0.002265853,0.003162539,0.004101939],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007160089,"threshold_uncertainty_score":0.0239529,"prediction_status":"machine_predicted_unvalidated"},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"}]}