{"id":15906702,"url":"https://github.com/csinva/csinva","last_synced_at":"2026-03-18T17:11:37.130Z","repository":{"id":97069762,"uuid":"306536713","full_name":"csinva/csinva","owner":"csinva","description":"readme","archived":false,"fork":false,"pushed_at":"2025-06-02T20:04:23.000Z","size":96,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-06-03T09:49:47.319Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/csinva.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2020-10-23T05:21:22.000Z","updated_at":"2025-06-02T20:04:27.000Z","dependencies_parsed_at":"2023-11-12T02:23:39.346Z","dependency_job_id":"9da4ab68-ae10-4736-9695-4365e7be7b10","html_url":"https://github.com/csinva/csinva","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/csinva/csinva","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/csinva%2Fcsinva","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/csinva%2Fcsinva/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/csinva%2Fcsinva/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/csinva%2Fcsinva/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/csinva","download_url":"https://codeload.github.com/csinva/csinva/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/csinva%2Fcsinva/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":274415664,"owners_count":25280799,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-09-10T02:00:12.551Z","response_time":83,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-10-06T13:41:24.775Z","updated_at":"2026-02-13T02:42:50.682Z","avatar_url":"https://github.com/csinva.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cp\u003e\n  \u003cpre align=\"center\"\u003e\nHi there 👋 I'm Chandan, a Senior Researcher at Microsoft Research working on interpretable machine learning.\n\u003ca href=\"https://csinva.io/\"\u003eHomepage\u003c/a\u003e / \u003ca href=\"https://twitter.com/csinva\"\u003eTwitter\u003c/a\u003e / \u003ca href=\"https://scholar.google.com/citations?hl=en\u0026user=vPYz4QwAAAAJ\"\u003eGoogle Scholar\u003c/a\u003e / \u003ca href=\"https://www.linkedin.com/in/csinva/\"\u003eLinkedIn\u003c/a\u003e \u003c/pre\u003e\n\u003c/p\u003e\n\n## 🌳 Interpretable models / dataset explanations\n\n\u003ca href=\"https://github.com/csinva/imodels\"\u003e\u003cimg align=\"center\" style=\"height:30px;\" src=\"https://csinva.io/imodels/img/imodels_logo.svg?sanitize=True\"\u003e \u003c/img\u003e\u003c/a\u003e **![](https://img.shields.io/github/stars/csinva/imodels?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE)** Interpretable and accurate predictive modeling, sklearn-compatible ([JOSS 2021](https://joss.theoj.org/papers/10.21105/joss.03192)). Contains FIGS ([PNAS 2022](https://arxiv.org/abs/2201.11931)) and HSTree ([ICML 2022](https://arxiv.org/abs/2202.00858))\n\n\u003ca href=\"https://github.com/csinva/imodelsX\"\u003e\u003cimg align=\"center\" style=\"height:35px;\" src=\"https://csinva.io/imodelsX/imodelsx_logo.svg?sanitize=True\"\u003e \u003c/img\u003e\u003c/a\u003e **![](https://img.shields.io/github/stars/csinva/imodelsX?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE)** Interpretability for text. Contains Aug-imodels ([Nature Communications 2023](https://arxiv.org/abs/2209.11799)) ![](https://img.shields.io/github/stars/microsoft/augmented-interpretable-models?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE), Tree-Prompt ([EMNLP 2023](https://arxiv.org/abs/2310.14034)) ![](https://img.shields.io/github/stars/csinva/tree-prompt?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE), iPrompt ([ICLR workshop 2023](https://arxiv.org/abs/2210.01848)) ![](https://img.shields.io/github/stars/csinva/interpretable-autoprompting?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE), SASC ([NeurIPS workshop 2023](https://arxiv.org/abs/2305.09863)) ![](https://img.shields.io/github/stars/microsoft/automated-explanations?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE), and QA-Embs ([NeurIPS 2024](https://arxiv.org/abs/2405.16714)) ![](https://img.shields.io/github/stars/csinva/interpretable-embeddings?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE)\n\n**[adaptive-wavelets](https://github.com/Yu-Group/adaptive-wavelet-distillation) ![](https://img.shields.io/github/stars/Yu-Group/adaptive-wavelet-distillation?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE)** Adaptive, interpretable wavelets ([NeurIPS 2021](https://arxiv.org/abs/2107.09145))\n\n## 🤖 General-purpose AI packages and cheatsheets\n\n\u003ca href=\"https://github.com/csinva/csinva.github.io\"\u003e\u003cimg align=\"center\" style=\"height:30px;\" src=\"https://csinva.io/blog/compiled_notes/_build/html//_static/logo.png\"\u003e \u003c/img\u003e\u003c/a\u003e **![](https://img.shields.io/github/stars/csinva/csinva.github.io?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE)** Notes and resources on AI\n\n\u003ca href=\"https://github.com/Yu-Group/veridical-flow\"\u003e\u003cimg align=\"center\" style=\"height:30px;\" src=\"https://yu-group.github.io/veridical-flow/logo_vflow_straight.png\"\u003e \u003c/img\u003e\u003c/a\u003e **![](https://img.shields.io/github/stars/Yu-Group/pcs-pipeline?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE)** Utilities for trustworthy data-science ([JOSS 2021](https://joss.theoj.org/papers/10.21105/joss.03895))\n\n## 🧠 Interpreting neural networks\n\n**[deep-explanation-penalization](https://github.com/laura-rieger/deep-explanation-penalization) ![](https://img.shields.io/github/stars/laura-rieger/deep-explanation-penalization?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE)** Penalizing neural-network explanations ([ICML 2020](https://arxiv.org/abs/1909.13584))\n\n**[hierarchical-dnn-interpretations](https://github.com/csinva/hierarchical-dnn-interpretations) ![](https://img.shields.io/github/stars/csinva/hierarchical-dnn-interpretations?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE)** Hierarchical interpretations for neural network predictions ([ICLR 2019](https://arxiv.org/abs/1806.05337))\n\n**[transformation-importance](https://github.com/csinva/transformation-importance) ![](https://img.shields.io/github/stars/csinva/transformation-importance?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE)** Feature importance for transformations ([ICLR Workshop 2020](https://arxiv.org/abs/2003.01926))\n\n\n## 📊 Data-science problems\n\n**[automated-brain-explanations](https://github.com/microsoft/automated-brain-explanations) ![](https://img.shields.io/github/stars/microsoft/automated-brain-explanations?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE)** Building natural-language explanations for the brain. Contains GCT ([arxiv 2024](https://arxiv.org/abs/2410.00812))\n\n**[clinical-rule-development](https://github.com/csinva/clinical-rule-development) ![](https://img.shields.io/github/stars/csinva/clinical-rule-development?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE)** Building and vetting clinical decision rules, including vetting an intraabdominal rule ([PLOS DH, 2022](https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0000076)), analyzing patient perspectives for approving rules (\u003ca href=\"https://www.nature.com/articles/s41598-025-89996-w\"\u003eNature SR, 2025\u003c/a\u003e), or analyzing bias across CDIs (\u003ca href=\"https://www.medrxiv.org/content/10.1101/2025.02.12.25320965v1\"\u003emedRxiv, 2025\u003c/a\u003e). See also general PECARN data preprocessing ([clinical-rule-vetting](https://github.com/Yu-Group/rule-stress-testing) ![](https://img.shields.io/github/stars/Yu-Group/rule-stress-testing?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE)) and ([clinical-self-verification](https://github.com/microsoft/clinical-self-verification) ![](https://img.shields.io/github/stars/microsoft/clinical-self-verification?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE)). Also working on an LLM/EHR pipeline for this culminating in [HACHI](https://github.com/jjfenglab/HACHI), and previously [BC-LLM](https://github.com/jjfeng/bc-llm).\n\n**[covid19-severity-prediction](https://github.com/Yu-Group/covid19-severity-prediction) ![](https://img.shields.io/github/stars/Yu-Group/covid19-severity-prediction?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE)** Extensive COVID-19 data + forecasting for counties and hospitals ([HDSR 2021](https://hdsr.mitpress.mit.edu/pub/p6isyf0g/release/4))\n\n**[molecular-partner-prediction](https://github.com/Yu-Group/molecular-partner-prediction) ![](https://img.shields.io/github/stars/csinva/auxilin-prediction?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE)** Predicting successful CME events using only clathrin markers\n\n\n## Various aspects of deep learning and machine learning\n\n**[gan-vae-pretrained-pytorch](https://github.com/csinva/gan-vae-pretrained-pytorch) ![](https://img.shields.io/github/stars/csinva/gan-vae-pretrained-pytorch?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE)** Pretrained GANs + VAEs + classifiers for MNIST/CIFAR in pytorch\n\n**[gpt-paper-title-generator](https://github.com/csinva/gpt-paper-title-generator) ![](https://img.shields.io/github/stars/csinva/gpt2-paper-title-generator?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE)** Generating paper titles with GPT-2\n\n**[disentangled-attribution-curves](https://github.com/csinva/disentangled-attribution-curves) ![](https://img.shields.io/github/stars/csinva/disentangled-attribution-curves?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE)** Attribution curves for interpreting tree ensembles trees ([arxiv 2019](https://arxiv.org/abs/1905.07631))\n\n**[matching-with-gans](https://github.com/csinva/matching-with-gans) ![](https://img.shields.io/github/stars/csinva/matching-with-gans?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE)** Matching in GAN latent space for better bias benchmarking. ([CVPR workshop 2021](https://arxiv.org/abs/2103.13455))\n\n**[data-viz-utils](https://github.com/csinva/data-viz-utils) ![](https://img.shields.io/github/stars/csinva/data-viz-utils?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE)** Functions for easily making publication-quality figures with matplotlib\n\n**[mdl-complexity](https://github.com/csinva/mdl-complexity) ![](https://img.shields.io/github/stars/csinva/mdl-complexity?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE)** Revisiting complexity and the bias-variance tradeoff ([JMLR 2021](https://arxiv.org/abs/2006.10189))\n\n## Projects advised\n\n**[pasta](https://github.com/QingruZhang/PASTA) ![](https://img.shields.io/github/stars/QingruZhang/PASTA?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE)** Post-hoc Attention Steering for LLMs ([ICLR 2024](https://arxiv.org/abs/2311.02262)), led by [Qingru Zhang](https://github.com/QingruZhang)\n\n**[meta-tree](https://github.com/EvanZhuang/MetaTree) ![](https://img.shields.io/github/stars/EvanZhuang/MetaTree?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE)** Learning a Decision Tree Algorithm with Transformers ([TMLR 2024](https://arxiv.org/abs/2402.03774)), led by [Yufan Zhuang](https://github.com/EvanZhuang)\n\n**[sim-dino](https://github.com/RobinWu218/SimDINO) ![](https://img.shields.io/github/stars/RobinWu218/SimDINO?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE)** Simplifying DINO via coding rate regularization ([ICML 2025](https://arxiv.org/abs/2502.10385)), led by [Ziyang Wu](https://github.com/RobinWu218)\n\n**[explanation-consistency-finetuning](https://github.com/yandachen/explanation-consistency-finetuning) ![](https://img.shields.io/github/stars/yandachen/explanation-consistency-finetuning?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE)**  Consistent Natural-Language Explanations ([COLING 2025](https://arxiv.org/abs/2401.13986)), led by [Yanda Chen](https://github.com/yandachen)\n\n**[induction-gram](https://github.com/ejkim47/induction-gram) ![](https://img.shields.io/github/stars/ejkim47/induction-gram?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE)**  Interpretable Language Modeling via Induction-head Ngram Models ([arXiv 2024](https://arxiv.org/abs/2401.13986)), led by [Eunji Kim](https://github.com/ejkim47) \u0026 [Sriya Mantena](https://github.com/SriyaM)\n\n\n## Open-source contributions\n\nMajor: **[autogluon](https://github.com/awslabs/autogluon) ![](https://img.shields.io/github/stars/awslabs/autogluon?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE), [big-bench](https://github.com/google/BIG-bench) ![](https://img.shields.io/github/stars/google/BIG-bench?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE), [nl-augmenter](https://github.com/GEM-benchmark/NL-Augmenter) ![](https://img.shields.io/github/stars/GEM-benchmark/NL-Augmenter?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE)**\n\nMinor: **[conference-acceptance-rates](https://github.com/lixin4ever/Conference-Acceptance-Rate) ![](https://img.shields.io/github/stars/lixin4ever/Conference-Acceptance-Rate?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE), [iterative-random-forest](https://github.com/Yu-Group/iterative-Random-Forest) ![](https://img.shields.io/github/stars/Yu-Group/iterative-Random-Forest?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE), [interpretable-ml-book](https://github.com/christophM/interpretable-ml-book) ![](https://img.shields.io/github/stars/christophM/interpretable-ml-book?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE), [awesome-interpretable-machine-learning](https://github.com/lopusz/awesome-interpretable-machine-learning) ![](https://img.shields.io/github/stars/lopusz/awesome-interpretable-machine-learning?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE), [awesome-machine-learning-interpretability](https://github.com/jphall663/awesome-machine-learning-interpretability) ![](https://img.shields.io/github/stars/jphall663/awesome-machine-learning-interpretability?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE), [awesome-llm-interpretability](https://github.com/JShollaj/awesome-llm-interpretability) ![](https://img.shields.io/github/stars/JShollaj/awesome-llm-interpretability?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE), [executable-books](https://github.com/executablebooks/meta) ![](https://img.shields.io/github/stars/executablebooks/meta?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE), [deep-fMRI-dataset](https://github.com/HuthLab/deep-fMRI-dataset) ![](https://img.shields.io/github/stars/HuthLab/deep-fMRI-dataset?color=%23EEE\u0026style=flat-square\u0026label=%E2%AD%90\u0026labelColor=%23EEE)**\n\n## Mini-projects\n\n**[hummingbird-tracking](https://github.com/csinva/hummingbird-tracking), [imodels-experiments](https://github.com/Yu-Group/imodels-experiments), [cookiecutter-ml-research](https://github.com/csinva/cookiecutter-ml-research), [nano-descriptions](https://github.com/csinva/nano-descriptions), [news-title-bias](https://github.com/csinva/news-title-bias), [java-mini-games](https://github.com/csinva/mini-games), [imodels-data](https://github.com/csinva/imodels-data), [news-balancer](https://github.com/csinva/news-balancer), [arxiv-copier](https://github.com/csinva/arxiv-copier), [dnn-experiments](https://github.com/csinva/dnn-experiments), [max-activation-interpretation-pytorch](https://github.com/csinva/max-activation-interpretation-pytorch), [acronym-generator](https://github.com/csinva/acronym-generator), [hpa-interp](https://github.com/csinva/hpa-interp), [sensible-local-interpretations](https://github.com/csinva/sensible-local-interpretations), [global-sports-analysis](https://github.com/csinva/global-sports-analysis), [mouse-brain-decoding](https://github.com/csinva/mouse-brain-decoding),  ...**\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcsinva%2Fcsinva","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcsinva%2Fcsinva","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcsinva%2Fcsinva/lists"}