{"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/fidelity-isn-t-accuracy-when-linearly","title":"Fidelity Isn't Accuracy: When Linearly Decodable Functions Fail to Match the Ground Truth","arxiv_id":"2506.12176","date":"2025-06-13","proceeding":null,"authors":["Jackson Eshbaugh"],"abstract":"Neural networks excel as function approximators, but their complexity often obscures the nature of the functions they learn. In this work, we propose the linearity score $\\lambda(f)$, a simple and interpretable diagnostic that quantifies how well a regression network's output can be mimicked by a linear model. Defined as the $R^2$ between the network's predictions and those of a trained linear surrogate, $\\lambda(f)$ offers insight into the linear decodability of the learned function. We evaluate this framework on both synthetic ($y = x \\sin(x) + \\epsilon$) and real-world datasets (Medical Insurance, Concrete, California Housing), using dataset-specific networks and surrogates. Our findings show that while high $\\lambda(f)$ scores indicate strong linear alignment, they do not necessarily imply predictive accuracy with respect to the ground truth. This underscores both the promise and the limitations of using linear surrogates to understand nonlinear model behavior, particularly in high-stakes regression tasks.","url_abs":"https://arxiv.org/abs/2506.12176v1","url_pdf":"https://arxiv.org/pdf/2506.12176v1.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":"fidelity-isn-t-accuracy-when-linearly","repo_url":"https://github.com/jacksoneshbaugh/lambda-linearity-score","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"diagnostic","task_name":"Diagnostic"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/regression-on-california-housing-prices","task":"regression","dataset":"California Housing Prices","model":"Neural Network","rank_in_archive_order":1,"of":3,"metrics":{"R2 Score":"0.7908","lambda":"0.6968"},"uses_additional_data":false},{"leaderboard":"/sota/regression-on-california-housing-prices","task":"regression","dataset":"California Housing Prices","model":"Baseline Regression","rank_in_archive_order":2,"of":3,"metrics":{"R2 Score":"0.5758"},"uses_additional_data":false},{"leaderboard":"/sota/regression-on-california-housing-prices","task":"regression","dataset":"California Housing Prices","model":"Mimic / Surrogate","rank_in_archive_order":3,"of":3,"metrics":{"R2 Score":"0.5658"},"uses_additional_data":false},{"leaderboard":"/sota/regression-on-concrete-compressive-strength","task":"regression","dataset":"Concrete Compressive Strength","model":"Neural Network","rank_in_archive_order":1,"of":3,"metrics":{"R2 Score":"0.8588","lambda":"0.6659"},"uses_additional_data":false},{"leaderboard":"/sota/regression-on-concrete-compressive-strength","task":"regression","dataset":"Concrete Compressive Strength","model":"Baseline Regression","rank_in_archive_order":2,"of":3,"metrics":{"R2 Score":"0.5944"},"uses_additional_data":false},{"leaderboard":"/sota/regression-on-concrete-compressive-strength","task":"regression","dataset":"Concrete Compressive Strength","model":"Mimic / Surrogate","rank_in_archive_order":3,"of":3,"metrics":{"R2 Score":"0.5821"},"uses_additional_data":false},{"leaderboard":"/sota/regression-on-medical-cost-personal-dataset","task":"regression","dataset":"Medical Cost Personal Dataset","model":"Neural Network","rank_in_archive_order":1,"of":3,"metrics":{"R2 Score":"0.8673","lambda":"0.9186"},"uses_additional_data":false},{"leaderboard":"/sota/regression-on-medical-cost-personal-dataset","task":"regression","dataset":"Medical Cost Personal Dataset","model":"Baseline Regression","rank_in_archive_order":2,"of":3,"metrics":{"R2 Score":"0.7836"},"uses_additional_data":false},{"leaderboard":"/sota/regression-on-medical-cost-personal-dataset","task":"regression","dataset":"Medical Cost Personal Dataset","model":"Mimic / Surrogate","rank_in_archive_order":3,"of":3,"metrics":{"R2 Score":"0.7835"},"uses_additional_data":false},{"leaderboard":"/sota/regression-on-synthetic-y-x-sin-x","task":"regression","dataset":"Synthetic: y = x * sin x","model":"Neural Network","rank_in_archive_order":1,"of":3,"metrics":{"R2 Score":"0.9755","lambda":"-0.0105"},"uses_additional_data":false},{"leaderboard":"/sota/regression-on-synthetic-y-x-sin-x","task":"regression","dataset":"Synthetic: y = x * sin x","model":"Baseline Regression","rank_in_archive_order":2,"of":3,"metrics":{"R2 Score":"-0.0080"},"uses_additional_data":false},{"leaderboard":"/sota/regression-on-synthetic-y-x-sin-x","task":"regression","dataset":"Synthetic: y = x * sin x","model":"Mimic / Surrogate","rank_in_archive_order":3,"of":3,"metrics":{"R2 Score":"-0.0137"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2506.12176","atlas_url":"https://app.syntology.ai/?focus=2506.12176","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":"2506.12176"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2506.12176\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2506.12176"},"call":"get_concepts_for_paper(arxiv_id=\"2506.12176\")"}],"by_repo":[{"repo":"jacksoneshbaugh/lambda-linearity-score","kind":"official","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":"2792abd6bbffe796d168e5fa72a200e4202ea4bb07abbee9166d2108c43fdb32","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}