{"paper_id":"2309.13246","title":"Can I Trust the Explanations? Investigating Explainable Machine Learning Methods for Monotonic Models","authors":["Dangxing Chen"],"paper_date":"2023-09-23","paper_type":"theoretical","paper_url":"https://arxiv.org/pdf/2309.13246v1","page_url":"https://thequant.space/flowcharts/can-i-trust-the-explanations-investigating-explainable-mach/","scores":{"empirical_rigor":2,"math_complexity":8.5,"quadrant":"Lab Rats"},"proposes":{"status":"available","statement":"The paper proposes three new axioms for average preservation of three types of monotonicity and analyzes which attribution methods satisfy them.","quote":"We propose three new axioms concerning the average preservation of three types of monotonicity.","summary":"In recent years, explainable machine learning methods have been very successful. Despite their success, most explainable machine learning methods are applied to black-box models without any domain knowledge. By incorporating domain knowledge, science-informed machine learning models have…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"A zero baseline (x′ = 0) is used for attribution methods.","type":"model","stated":"explicit","quote":"For simplicity, we consider the zero baseline as x′ = 0."},{"assumption":"Missing variables are removed and past dues greater than four times are truncated in the credit dataset.","type":"data","stated":"explicit","quote":"For simplicity, data with missing variables are removed. Past dues greater than four times are truncated."},{"assumption":"The dataset is randomly partitioned into 75% training and 25% test sets.","type":"data","stated":"explicit","quote":"The dataset is randomly partitioned into 75% training and 25% test sets."},{"assumption":"Features x1‑x3 are grouped together and monotonicity is only imposed on these features.","type":"model","stated":"explicit","quote":"All functions are approximated by neural networks with one hidden layer and two neurons. For"}]},"datasets":{"status":"available","items":[{"name":"Kaggle credit score dataset","provider":"Kaggle","kind":"alternative","access":"public","period":null,"universe":null,"quote":"We use the Kaggle credit score dataset 2.","known_id":"kaggle"}],"known":[{"id":"kaggle","name":"Kaggle","provider":"Kaggle","kind":"other","access":"public","quote":"4 EMPIRICAL EXAMPLES 4.1 Data description We use the Kaggle credit score dataset 2.","mentions":1,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"unclear"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"unclear","findings":[{"finding":"Baseline Shapley (BShap) provides satisfactory explanations when only individual monotonicity is involved.","kind":"theoretical","quote":"BShap provides satisfactory explanations when only individual monotonicity is involved"},{"finding":"Integrated Gradients (IG) provides reasonable explanations when strong pairwise monotonicity is involved.","kind":"theoretical","quote":"IG provides reasonable explanations when strong pairwise monotonicity is involved"},{"finding":"Both the black‑box FCNN and the transparent monotonic neural additive model achieve an AUC of approximately 80%.","kind":"performance","quote":"Both models have an AUC of approximately 80%."}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":22,"citations":{"cited_by_in_corpus":3,"by_independent_authors":2,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":2,"unclassified":1},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T18:21:40Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}