{"id":"W2145410165","doi":"10.1145/2600428.2609534","title":"The effect of expanding relevance judgements with duplicates","year":2014,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Automatic summarization; Computer science; Relevance (law); Context (archaeology); Set (abstract data type); Natural language processing; Reusability; Information retrieval; Artificial intelligence; Test set; Sentence; Data mining; Programming language; Software","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0003576095,0.00004871076,0.00006658124,0.00001239902,0.00007402852,0.00003846514,0.0004627928,0.000009779312,0.000001472747],"category_scores_gemma":[0.00005123292,0.00002326297,0.00001386968,0.00007875211,0.00002027789,0.00009905734,0.0001013721,0.00003212697,0.000009345054],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006184856,"about_ca_system_score_gemma":0.000003534984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001045394,"about_ca_topic_score_gemma":0.000003584686,"domain_scores_codex":[0.9994975,0.00003521419,0.00008488457,0.0001407311,0.0001288912,0.0001127391],"domain_scores_gemma":[0.9991383,0.0003573188,0.00004225503,0.00042687,0.00001652489,0.00001873899],"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":[0.00003448985,0.00001527464,0.04907019,0.00006700837,0.00004345876,0.000001084958,0.0003495409,0.00253315,0.006822835,0.243858,0.0007067572,0.6964982],"study_design_scores_gemma":[0.0009511624,0.0007634942,0.003317302,0.00007344082,0.000008915484,0.00000493153,0.00001207819,0.7529527,0.2305074,0.003799909,0.007397802,0.0002108881],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1639453,0.00002525419,0.8309484,0.0002874451,0.00006217445,0.00007369477,1.905129e-8,0.00004613061,0.004611601],"genre_scores_gemma":[0.9815921,0.000003635233,0.01795384,0.00003806821,0.00001561291,0.000009686874,4.293495e-8,0.000002475349,0.0003845321],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8176467,"threshold_uncertainty_score":0.09486364,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006888291307441076,"score_gpt":0.2347738308926272,"score_spread":0.2278855395851861,"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."}}