{"id":"W3099434687","doi":"10.18653/v1/2020.conll-1.26","title":"“LazImpa”: Lazy and Impatient neural agents learn to communicate efficiently","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Language and cultural evolution","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Agence Nationale de la Recherche; Canadian Institute for Advanced Research; Microsoft Research","keywords":"Zipf's law; Computer science; Channel (broadcasting); Artificial neural network; Natural (archaeology); Artificial intelligence; Theoretical computer science; Computer network; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001185808,0.000359629,0.0004541334,0.0003468126,0.0007599844,0.001373966,0.001214183,0.001206805,0.002643158],"category_scores_gemma":[0.009188214,0.0003105181,0.0003593387,0.0002082175,0.002274288,0.002905114,0.001892917,0.001674835,0.0005376967],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006556482,"about_ca_system_score_gemma":0.0006997622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001253658,"about_ca_topic_score_gemma":0.001359101,"domain_scores_codex":[0.9994708,0.0002297159,0.00002538705,0.0001290129,0.00008027694,0.00006486231],"domain_scores_gemma":[0.9964055,0.001760818,0.0005457578,0.0006487237,0.0002838267,0.0003552787],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005128943,0.00023603,0.01089968,0.0002785329,0.0002529952,0.0007268501,0.002945516,0.3321352,0.05381734,0.503498,0.007753286,0.08694378],"study_design_scores_gemma":[0.00004202855,0.00006881572,0.0007125498,0.00001136438,0.00002039492,0.0001055273,0.0001408607,0.788361,0.004016471,0.2043488,0.002142067,0.00003018546],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4911106,0.0002308666,0.4888305,0.002715769,0.00007857269,0.00006434941,0.0001274083,0.001236406,0.01560543],"genre_scores_gemma":[0.9544962,0.00006249144,0.0407876,0.0002652999,0.00003317041,0.00005790558,0.0000593109,0.00009488635,0.004142999],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002643158,"threshold_uncertainty_score":0.008842289,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07412707764797923,"score_gpt":0.3617043061144944,"score_spread":0.2875772284665152,"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."}}