{"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/mis-fitting-a-survey-of-scaling-laws","title":"(Mis)Fitting: A Survey of Scaling Laws","arxiv_id":"2502.18969","date":"2025-02-26","proceeding":null,"authors":["Margaret Li","Sneha Kudugunta","Luke Zettlemoyer"],"abstract":"Modern foundation models rely heavily on using scaling laws to guide crucial training decisions. Researchers often extrapolate the optimal architecture and hyper parameters settings from smaller training runs by describing the relationship between, loss, or task performance, and scale. All components of this process vary, from the specific equation being fit, to the training setup, to the optimization method. Each of these factors may affect the fitted law, and therefore, the conclusions of a given study. We discuss discrepancies in the conclusions that several prior works reach, on questions such as the optimal token to parameter ratio. We augment this discussion with our own analysis of the critical impact that changes in specific details may effect in a scaling study, and the resulting altered conclusions. Additionally, we survey over 50 papers that study scaling trends: while 45 of these papers quantify these trends using a power law, most under-report crucial details needed to reproduce their findings. To mitigate this, we we propose a checklist for authors to consider while contributing to scaling law research.","url_abs":"https://arxiv.org/abs/2502.18969v1","url_pdf":"https://arxiv.org/pdf/2502.18969v1.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":"mis-fitting-a-survey-of-scaling-laws","repo_url":"https://github.com/hadasah/scaling_laws","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"survey","task_name":"Survey"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2502.18969","atlas_url":"https://app.syntology.ai/?focus=2502.18969","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.18969"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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":"deterministic:regex_extraction","url":"https://github.com/hadasah/scaling_laws","reach":null}],"summary":{"ran_draft_wrong":9,"ran_violates":3,"ran_honours":2,"unverified":4},"by_repo_kind":{"official":{"samples":18,"ran":14,"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":18,"samples":[{"code_sha256_prefix":"ba7a1602469aeabd","entry":"adapt_df_for_isoflop","repo":"hadasah/scaling_laws","repo_kind":"official","path":"paper_analysis_and_plots.py","file_url":"https://github.com/hadasah/scaling_laws/blob/HEAD/paper_analysis_and_plots.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ba7a1602469aeabd"}},{"code_sha256_prefix":"c10f725822634149","entry":"apply_smoothing_filter","repo":"hadasah/scaling_laws","repo_kind":"official","path":"paper_analysis_and_plots.py","file_url":"https://github.com/hadasah/scaling_laws/blob/HEAD/paper_analysis_and_plots.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c10f725822634149"}},{"code_sha256_prefix":"0e3ad85778a00e72","entry":"custom_huber_loss","repo":"hadasah/scaling_laws","repo_kind":"official","path":"paper_analysis_and_plots.py","file_url":"https://github.com/hadasah/scaling_laws/blob/HEAD/paper_analysis_and_plots.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0e3ad85778a00e72"}},{"code_sha256_prefix":"394938c35cfc309b","entry":"fetch_flop","repo":"hadasah/scaling_laws","repo_kind":"official","path":"paper_analysis_and_plots.py","file_url":"https://github.com/hadasah/scaling_laws/blob/HEAD/paper_analysis_and_plots.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"394938c35cfc309b"}},{"code_sha256_prefix":"a37acb41a719d908","entry":"fit_loss_with_saturation","repo":"hadasah/scaling_laws","repo_kind":"official","path":"paper_analysis_and_plots.py","file_url":"https://github.com/hadasah/scaling_laws/blob/HEAD/paper_analysis_and_plots.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a37acb41a719d908"}},{"code_sha256_prefix":"8d1a5df6af7bf845","entry":"get_color","repo":"hadasah/scaling_laws","repo_kind":"official","path":"paper_analysis_and_plots.py","file_url":"https://github.com/hadasah/scaling_laws/blob/HEAD/paper_analysis_and_plots.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8d1a5df6af7bf845"}},{"code_sha256_prefix":"c2379e45b530b218","entry":"get_noise_for_loss","repo":"hadasah/scaling_laws","repo_kind":"official","path":"paper_analysis_and_plots.py","file_url":"https://github.com/hadasah/scaling_laws/blob/HEAD/paper_analysis_and_plots.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c2379e45b530b218"}},{"code_sha256_prefix":"a6d9e09c75556988","entry":"maybe_get_item","repo":"hadasah/scaling_laws","repo_kind":"official","path":"paper_analysis_and_plots.py","file_url":"https://github.com/hadasah/scaling_laws/blob/HEAD/paper_analysis_and_plots.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a6d9e09c75556988"}},{"code_sha256_prefix":"c569c60d28de0481","entry":"minimize_with_interp","repo":"hadasah/scaling_laws","repo_kind":"official","path":"paper_analysis_and_plots.py","file_url":"https://github.com/hadasah/scaling_laws/blob/HEAD/paper_analysis_and_plots.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c569c60d28de0481"}},{"code_sha256_prefix":"bf2301eb6d098001","entry":"power_law_fit","repo":"hadasah/scaling_laws","repo_kind":"official","path":"paper_analysis_and_plots.py","file_url":"https://github.com/hadasah/scaling_laws/blob/HEAD/paper_analysis_and_plots.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bf2301eb6d098001"}},{"code_sha256_prefix":"fc9bc7439b7fd07b","entry":"precise_flops_per_token_chinchilla","repo":"hadasah/scaling_laws","repo_kind":"official","path":"paper_analysis_and_plots.py","file_url":"https://github.com/hadasah/scaling_laws/blob/HEAD/paper_analysis_and_plots.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fc9bc7439b7fd07b"}},{"code_sha256_prefix":"e20ba47c892c9025","entry":"precise_param_count_open_lm","repo":"hadasah/scaling_laws","repo_kind":"official","path":"paper_analysis_and_plots.py","file_url":"https://github.com/hadasah/scaling_laws/blob/HEAD/paper_analysis_and_plots.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e20ba47c892c9025"}},{"code_sha256_prefix":"e21e1648a30e4bc5","entry":"proportional_sliding_window_filter","repo":"hadasah/scaling_laws","repo_kind":"official","path":"paper_analysis_and_plots.py","file_url":"https://github.com/hadasah/scaling_laws/blob/HEAD/paper_analysis_and_plots.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e21e1648a30e4bc5"}},{"code_sha256_prefix":"8d12b64a6baa8c66","entry":"vectorized_interp_with_seed_noise","repo":"hadasah/scaling_laws","repo_kind":"official","path":"paper_analysis_and_plots.py","file_url":"https://github.com/hadasah/scaling_laws/blob/HEAD/paper_analysis_and_plots.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8d12b64a6baa8c66"}},{"code_sha256_prefix":"0c16ea3bfb805dee","entry":"fit_compute_optimal_power_laws","repo":"hadasah/scaling_laws","repo_kind":"official","path":"paper_analysis_and_plots.py","file_url":"https://github.com/hadasah/scaling_laws/blob/HEAD/paper_analysis_and_plots.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0c16ea3bfb805dee"}},{"code_sha256_prefix":"6b4a2fc6a22b2143","entry":"fit_isoflop_power_law","repo":"hadasah/scaling_laws","repo_kind":"official","path":"paper_analysis_and_plots.py","file_url":"https://github.com/hadasah/scaling_laws/blob/HEAD/paper_analysis_and_plots.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6b4a2fc6a22b2143"}},{"code_sha256_prefix":"a4b194333547551a","entry":"interp_flop","repo":"hadasah/scaling_laws","repo_kind":"official","path":"paper_analysis_and_plots.py","file_url":"https://github.com/hadasah/scaling_laws/blob/HEAD/paper_analysis_and_plots.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a4b194333547551a"}},{"code_sha256_prefix":"910a5e11cfe206a8","entry":"interpolation","repo":"hadasah/scaling_laws","repo_kind":"official","path":"paper_analysis_and_plots.py","file_url":"https://github.com/hadasah/scaling_laws/blob/HEAD/paper_analysis_and_plots.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"910a5e11cfe206a8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}