{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/understanding-learned-models-by-identifying","title":"Understanding Learned Models by Identifying Important Features at the Right Resolution","arxiv_id":"1811.07279","date":"2018-11-18","proceeding":null,"authors":["Kyubin Lee","Akshay Sood","Mark Craven"],"abstract":"In many application domains, it is important to characterize how complex\nlearned models make their decisions across the distribution of instances. One\nway to do this is to identify the features and interactions among them that\ncontribute to a model's predictive accuracy. We present a model-agnostic\napproach to this task that makes the following specific contributions. Our\napproach (i) tests feature groups, in addition to base features, and tries to\ndetermine the level of resolution at which important features can be\ndetermined, (ii) uses hypothesis testing to rigorously assess the effect of\neach feature on the model's loss, (iii) employs a hierarchical approach to\ncontrol the false discovery rate when testing feature groups and individual\nbase features for importance, and (iv) uses hypothesis testing to identify\nimportant interactions among features and feature groups. We evaluate our\napproach by analyzing random forest and LSTM neural network models learned in\ntwo challenging biomedical applications.","url_abs":"http://arxiv.org/abs/1811.07279v2","url_pdf":"http://arxiv.org/pdf/1811.07279v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"understanding-learned-models-by-identifying","repo_url":"https://github.com/Craven-Biostat-Lab/mihifepe","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"hypothesis-testing","task_name":"Two-sample testing"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1811.07279","atlas_url":"https://app.syntology.ai/?focus=1811.07279","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1811.07279"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1811.07279\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1811.07279"},"call":"get_concepts_for_paper(arxiv_id=\"1811.07279\")"}],"by_repo":[{"repo":"Craven-Biostat-Lab/mihifepe","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"ba2ba9b85038302d8244dc6f3d9b7f1908ba4a20bb4f02817f6ded8749fbada4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}