{"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/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":{"syntology_url":"https://syntology.ai/paper/2404.11534","atlas_url":"https://app.syntology.ai/?focus=2404.11534","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.11534"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2404.11534"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2404.11534"},"call":"get_harvested_code_for_paper(arxiv_id=\"2404.11534\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2404.11534"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2404.11534\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2404.11534"},"call":"get_concepts_for_paper(arxiv_id=\"2404.11534\")"}],"by_repo":[{"repo":"madrylab/modelcomponents","kind":"official","samples":11,"ran":3,"instrument":2,"unverified":8}],"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","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2404.11534.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2404.11534.svg"},"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":1,"ran_draft_wrong":2,"unverified":8},"n_samples":11,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":8,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":11,"ran":3,"n_ran_checked":1,"n_instrument":2,"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,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":3,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-24","last":"2026-09-24","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"68d226506d33fd8b","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,"signature":"input_dim:int/0/int, hidden_dim:int/0/int, output_dim:int/0/int, num_layers:int/0/int, use_kaiming_init:bool/0/bool, activation_func:callable/0/?, use_activation:bool/0/bool, use_batchnorm:bool/0/bool, dropout_prob:float/0/float","fixture_out_type":"Sequential","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"68d226506d33fd8b"}},{"code_sha256":"d0bd253702efa1a0","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_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"model:callable/0/?","fixture_out_type":"dict","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"d0bd253702efa1a0"}},{"code_sha256":"eab176d9494eef46","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_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"model:callable/0/?","fixture_out_type":"dict","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"eab176d9494eef46"}},{"code_sha256":"f2575fd3f27a7c1b","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,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f2575fd3f27a7c1b"}},{"code_sha256":"044b289cdfecfb33","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,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"044b289cdfecfb33"}},{"code_sha256":"0cc452e1fbb16c7e","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,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"0cc452e1fbb16c7e"}},{"code_sha256":"f33b5f3fc39b57ae","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,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f33b5f3fc39b57ae"}},{"code_sha256":"83b682ad1dd5d8df","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,"code_page":"/code/get-model","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"83b682ad1dd5d8df"}},{"code_sha256":"c9d51bd88f687663","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,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c9d51bd88f687663"}},{"code_sha256":"d795a49a09651847","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,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"d795a49a09651847"}},{"code_sha256":"95e672abb8e098da","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,"code_page":"/code/recursive-getattr","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"95e672abb8e098da"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"779b32d025adbb47795186f4075261ff654b0135b2391d488f8a4f93992c823d","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}