{"id":"W3217492267","doi":"10.1007/978-3-030-99739-7_18","title":"Less is Less: When are Snippets Insufficient for Human vs Machine Relevance Estimation?","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Microsoft (Canada)","funders":"","keywords":"Snippet; Computer science; Information retrieval; Relevance (law); Ranking (information retrieval); Search engine; Document retrieval; Query expansion; Language model; Range (aeronautics); Artificial intelligence; Natural language processing","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001095477,0.0006384559,0.0007051326,0.0007979711,0.0009164667,0.0006245655,0.005097104,0.0002436866,0.00007641259],"category_scores_gemma":[0.0001342604,0.0006387907,0.0002007972,0.0004551055,0.0003780299,0.0006957978,0.002465509,0.0009798793,0.00001067139],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006044118,"about_ca_system_score_gemma":0.0004340953,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008093895,"about_ca_topic_score_gemma":0.0001868751,"domain_scores_codex":[0.9945462,0.00004499027,0.0007932704,0.002345424,0.001455156,0.0008149571],"domain_scores_gemma":[0.9961931,0.0005307152,0.0006203821,0.00219201,0.0002867575,0.0001770553],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009064251,0.00007149073,0.00007662932,0.0001522767,0.00001428975,0.00005065172,0.002137242,0.2625728,0.00003862313,0.0790121,0.0001058345,0.655759],"study_design_scores_gemma":[0.0003271805,0.000170377,0.00004147035,0.0003206872,0.000008558974,0.00003629767,8.597503e-7,0.8146643,0.0002738206,0.1784778,0.005053484,0.0006251282],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005880048,0.0006934094,0.9916288,0.003202636,0.002027456,0.0008484514,0.00004593522,0.0002481897,0.0007171485],"genre_scores_gemma":[0.2152736,0.00003883551,0.7785984,0.004627961,0.0004325238,0.00009385867,0.00002711456,0.00007765,0.0008300091],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6551339,"threshold_uncertainty_score":0.9996063,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03607754583885837,"score_gpt":0.2760300977723595,"score_spread":0.2399525519335012,"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."}}