{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/decomposing-and-editing-predictions-by","title":"Decomposing and Editing Predictions by Modeling Model Computation","arxiv_id":"2404.11534","date":"2024-04-17","proceeding":null,"authors":["Harshay Shah","Andrew Ilyas","Aleksander Madry"],"abstract":"How does the internal computation of a machine learning model transform inputs into predictions? In this paper, we introduce a task called component modeling that aims to address this question. The goal of component modeling is to decompose an ML model's prediction in terms of its components -- simple functions (e.g., convolution filters, attention heads) that are the \"building blocks\" of model computation. We focus on a special case of this task, component attribution, where the goal is to estimate the counterfactual impact of individual components on a given prediction. We then present COAR, a scalable algorithm for estimating component attributions; we demonstrate its effectiveness across models, datasets, and modalities. Finally, we show that component attributions estimated with COAR directly enable model editing across five tasks, namely: fixing model errors, ``forgetting'' specific classes, boosting subpopulation robustness, localizing backdoor attacks, and improving robustness to typographic attacks. We provide code for COAR at https://github.com/MadryLab/modelcomponents .","url_abs":"https://arxiv.org/abs/2404.11534v1","url_pdf":"https://arxiv.org/pdf/2404.11534v1.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":"decomposing-and-editing-predictions-by","repo_url":"https://github.com/madrylab/modelcomponents","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"model-editing","task_name":"Model Editing"},{"task_slug":null,"task_name":"counterfactual"},{"task_slug":"model","task_name":"model"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.11534","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.11534"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/madrylab/modelcomponents","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"unverified":8},"by_repo_kind":{"official":{"samples":11,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"68d226506d33fd8b","entry":"get_fcn","repo":"madrylab/modelcomponents","repo_kind":"official","path":"coar/src/models/fcn.py","file_url":"https://github.com/madrylab/modelcomponents/blob/HEAD/coar/src/models/fcn.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"68d226506d33fd8b"}},{"code_sha256_prefix":"d0bd253702efa1a0","entry":"get_model_components","repo":"madrylab/modelcomponents","repo_kind":"official","path":"coar/estimate/imagenet_resnet/make_dataset.py","file_url":"https://github.com/madrylab/modelcomponents/blob/HEAD/coar/estimate/imagenet_resnet/make_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d0bd253702efa1a0"}},{"code_sha256_prefix":"eab176d9494eef46","entry":"get_resnet50_components","repo":"madrylab/modelcomponents","repo_kind":"official","path":"coar/edit/coar_edit.py","file_url":"https://github.com/madrylab/modelcomponents/blob/HEAD/coar/edit/coar_edit.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eab176d9494eef46"}},{"code_sha256_prefix":"f2575fd3f27a7c1b","entry":"ResNet9","repo":"madrylab/modelcomponents","repo_kind":"official","path":"coar/src/models/cifar_resnet.py","file_url":"https://github.com/madrylab/modelcomponents/blob/HEAD/coar/src/models/cifar_resnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f2575fd3f27a7c1b"}},{"code_sha256_prefix":"044b289cdfecfb33","entry":"ResNet9Narrow","repo":"madrylab/modelcomponents","repo_kind":"official","path":"coar/src/models/cifar_resnet.py","file_url":"https://github.com/madrylab/modelcomponents/blob/HEAD/coar/src/models/cifar_resnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"044b289cdfecfb33"}},{"code_sha256_prefix":"0cc452e1fbb16c7e","entry":"ResNet9Wide","repo":"madrylab/modelcomponents","repo_kind":"official","path":"coar/src/models/cifar_resnet.py","file_url":"https://github.com/madrylab/modelcomponents/blob/HEAD/coar/src/models/cifar_resnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0cc452e1fbb16c7e"}},{"code_sha256_prefix":"f33b5f3fc39b57ae","entry":"get_linear_model","repo":"madrylab/modelcomponents","repo_kind":"official","path":"coar/src/models/fcn.py","file_url":"https://github.com/madrylab/modelcomponents/blob/HEAD/coar/src/models/fcn.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f33b5f3fc39b57ae"}},{"code_sha256_prefix":"83b682ad1dd5d8df","entry":"get_model","repo":"madrylab/modelcomponents","repo_kind":"official","path":"coar/estimate/cifar_resnet/make_dataset.py","file_url":"https://github.com/madrylab/modelcomponents/blob/HEAD/coar/estimate/cifar_resnet/make_dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"83b682ad1dd5d8df"}},{"code_sha256_prefix":"c9d51bd88f687663","entry":"memmap_path","repo":"madrylab/modelcomponents","repo_kind":"official","path":"coar/estimate/initialize_store.py","file_url":"https://github.com/madrylab/modelcomponents/blob/HEAD/coar/estimate/initialize_store.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c9d51bd88f687663"}},{"code_sha256_prefix":"d795a49a09651847","entry":"preprocess_spec","repo":"madrylab/modelcomponents","repo_kind":"official","path":"coar/estimate/initialize_store.py","file_url":"https://github.com/madrylab/modelcomponents/blob/HEAD/coar/estimate/initialize_store.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d795a49a09651847"}},{"code_sha256_prefix":"95e672abb8e098da","entry":"recursive_getattr","repo":"madrylab/modelcomponents","repo_kind":"official","path":"coar/src/models/mini_resnet.py","file_url":"https://github.com/madrylab/modelcomponents/blob/HEAD/coar/src/models/mini_resnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"95e672abb8e098da"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}