{"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/2305-15017","title":"Calc-X and Calcformers: Empowering Arithmetical Chain-of-Thought through Interaction with Symbolic Systems","arxiv_id":"2305.15017","date":"2023-05-24","proceeding":null,"authors":["Marek Kadlčík","Michal Štefánik","Ondřej Sotolář","Vlastimil Martinek"],"abstract":"Despite outstanding performance in many tasks, language models are notoriously inclined to make factual errors in tasks requiring arithmetic computation. We address this deficiency by creating Calc-X, a collection of datasets that demonstrates the appropriate use of a calculator in reasoning chains. Calc-X is suitable for teaching language models to offload computations to a symbolic system. We survey and unify several existing chain-of-thought datasets into a proposed format, resulting in a standard collection of over 300,000 samples requiring arithmetic reasoning. Finally, we use the new Calc-X collection to train open-source calculator-using models we call Calcformers and show that these models approximately double the accuracy of generating correct results compared to vanilla language model baselines. We make all Calc-X datasets, source code and Calcformers models publicly available.","url_abs":"https://arxiv.org/abs/2305.15017v2","url_pdf":"https://arxiv.org/pdf/2305.15017v2.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":"2305-15017","repo_url":"https://github.com/prompteus/calc-x","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"arithmetic-reasoning","task_name":"Arithmetic Reasoning"},{"task_slug":"gsm8k","task_name":"GSM8K"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.15017","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.15017"}},"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":"deterministic:regex_extraction","url":"https://github.com/prompteus/calc-x","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"ran":0,"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":"423e450729e9b679","entry":"add_missing_dots","repo":"prompteus/calc-x","repo_kind":"official","path":"gadgets/gsm8k.py","file_url":"https://github.com/prompteus/calc-x/blob/HEAD/gadgets/gsm8k.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":"423e450729e9b679"}},{"code_sha256_prefix":"3c5177e2659c2456","entry":"get_result_from_output_fallback","repo":"prompteus/calc-x","repo_kind":"official","path":"gadgets/markup.py","file_url":"https://github.com/prompteus/calc-x/blob/HEAD/gadgets/markup.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":"3c5177e2659c2456"}},{"code_sha256_prefix":"2f993de9d45872dc","entry":"is_option_result","repo":"prompteus/calc-x","repo_kind":"official","path":"gadgets/metrics.py","file_url":"https://github.com/prompteus/calc-x/blob/HEAD/gadgets/metrics.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":"2f993de9d45872dc"}},{"code_sha256_prefix":"7e7f46fbad321925","entry":"normalize_option","repo":"prompteus/calc-x","repo_kind":"official","path":"gadgets/metrics.py","file_url":"https://github.com/prompteus/calc-x/blob/HEAD/gadgets/metrics.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":"7e7f46fbad321925"}},{"code_sha256_prefix":"6172fbccc8c70d90","entry":"replace_unicode","repo":"prompteus/calc-x","repo_kind":"official","path":"gadgets/gsm8k.py","file_url":"https://github.com/prompteus/calc-x/blob/HEAD/gadgets/gsm8k.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":"6172fbccc8c70d90"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}