{"id":"W4286903770","doi":"10.48550/arxiv.2110.07752","title":"Hindsight: Posterior-guided training of retrievers for improved\\n open-ended generation","year":2021,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Hindsight bias; Computer science; Context (archaeology); Generator (circuit theory); Relevance (law); Labrador Retriever; Artificial intelligence; Natural language processing; Information retrieval; Psychology; Cognitive psychology; Medicine; Power (physics); Geography","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.00337232,0.002311344,0.00123914,0.0007408451,0.0006118258,0.001336284,0.003588617,0.002886076,0.01283831],"category_scores_gemma":[0.01025677,0.0009504338,0.001169132,0.0004679564,0.001298493,0.002391958,0.002977049,0.003747353,0.005480655],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000784857,"about_ca_system_score_gemma":0.0012552,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004599014,"about_ca_topic_score_gemma":0.008635299,"domain_scores_codex":[0.998473,0.0005185162,0.00008463687,0.0005723888,0.0001956261,0.0001558211],"domain_scores_gemma":[0.9952887,0.00334107,0.0001704929,0.0006155938,0.0004089608,0.0001751007],"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":[0.001534748,0.0006733983,0.004503513,0.000655142,0.0002514281,0.0006684771,0.0007080434,0.3508804,0.018955,0.00656953,0.03193069,0.5826696],"study_design_scores_gemma":[0.0001570957,0.0002458648,0.0004370859,0.00004049203,0.0000400461,0.0001479664,0.00006367479,0.980164,0.01046215,0.004446235,0.003768229,0.00002713052],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09677041,0.002081512,0.829077,0.0009902449,0.0004797649,0.0004540634,0.001102068,0.05854333,0.01050152],"genre_scores_gemma":[0.6117968,0.0003322705,0.3536959,0.002169631,0.0002522602,0.0007206462,0.006707341,0.003299398,0.02102576],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01283831,"threshold_uncertainty_score":0.04294842,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2562523096483355,"score_gpt":0.2391825804790763,"score_spread":0.01706972916925917,"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."}}