{"id":"W4313680212","doi":"10.48550/arxiv.2301.01913","title":"Learning a Generic Value-Selection Heuristic Inside a Constraint Programming Solver","year":2023,"lang":"en","type":"preprint","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Constraint Satisfaction and Optimization","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Centre interuniversitaire de recherche sur les reseaux d'entreprise, la logistique et le transport","keywords":"Heuristics; Solver; Computer science; Heuristic; Mathematical optimization; Artificial intelligence; Graph; Constraint satisfaction problem; Machine learning; Theoretical computer science; Mathematics; Programming language","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001074868,0.0006619364,0.0006158644,0.001127827,0.0005384161,0.001183724,0.00100877,0.0007376054,0.00003157152],"category_scores_gemma":[0.0006016484,0.000758861,0.0003723199,0.001241188,0.0001506338,0.0004260801,0.001437645,0.001986285,0.00006170627],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001035284,"about_ca_system_score_gemma":0.001140552,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005379956,"about_ca_topic_score_gemma":0.002167098,"domain_scores_codex":[0.9957303,0.0004037028,0.0008780797,0.001311933,0.0006802442,0.0009957623],"domain_scores_gemma":[0.9974036,0.0002138717,0.0006929635,0.0009985642,0.0003024284,0.0003885218],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002614946,0.0001618562,0.01384333,0.0001990712,0.000186163,0.0001689109,0.0009809269,0.5926001,0.001787741,0.03603126,0.000916661,0.3530978],"study_design_scores_gemma":[0.0003170843,0.0001313513,0.01449008,0.0001980044,0.00005530569,0.0002288721,0.0000881045,0.9764342,0.0006512827,0.004824984,0.001781368,0.0007993454],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007299562,0.0002516879,0.9820794,0.002576616,0.00080382,0.001341189,0.00001388574,0.005356125,0.0002777127],"genre_scores_gemma":[0.4717972,0.0003113997,0.525042,0.0006574097,0.0002208557,0.0009765077,0.00008808013,0.0001119231,0.0007946407],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4644976,"threshold_uncertainty_score":0.9998531,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01976041773586389,"score_gpt":0.2445285228191116,"score_spread":0.2247681050832477,"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."}}