{"id":"W2073417241","doi":"10.1145/1979742.1979491","title":"RepliCHI - CHI should be replicating and validating results more","year":2011,"lang":"en","type":"preprint","venue":"","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":59,"is_retracted":false,"has_abstract":true,"ca_institutions":"Google (Canada)","funders":"","keywords":"Replication (statistics); Novelty; Cornerstone; Computer science; Value (mathematics); Psychology; Social psychology; Biology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.01982454,0.0004004006,0.0005965744,0.0004934762,0.000475235,0.002116593,0.002884043,0.0002350556,0.0002502614],"category_scores_gemma":[0.01574968,0.0002935168,0.000182736,0.0006624787,0.0002168789,0.0002150082,0.01320372,0.0006932782,0.0001234348],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003418639,"about_ca_system_score_gemma":0.00008077116,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001149285,"about_ca_topic_score_gemma":0.00006824224,"domain_scores_codex":[0.9912673,0.0002632844,0.001919153,0.004045145,0.002017745,0.0004874146],"domain_scores_gemma":[0.9889104,0.001283437,0.001211253,0.0079952,0.0003482481,0.0002514793],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007697753,0.0001290447,0.002928326,0.00008074362,0.0001001992,0.00002855504,0.00640927,0.0009471547,0.00008912652,0.01245703,0.5944248,0.3823287],"study_design_scores_gemma":[0.001841576,0.0001786441,0.03514599,0.0008957666,0.0002343321,0.00007960555,0.01209946,0.2454234,0.002409312,0.1809599,0.5173683,0.003363693],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.304,0.0003250663,0.03906485,0.01407961,0.004601958,0.001555708,0.0005014203,0.001094883,0.6347765],"genre_scores_gemma":[0.780875,0.00004080405,0.1482339,0.003387877,0.0007189369,0.00008010081,0.000458011,0.00007877972,0.0661266],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5686499,"threshold_uncertainty_score":0.9999517,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5117135165866231,"score_gpt":0.4653487608758974,"score_spread":0.04636475571072568,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}