WangNet – 1.8 MB, zero-dependency Numberwang adjudication in 11 languages
Recorded: Sept. 15, 2026, 8:08 p.m.
| Original | Summarized |
GitHub - GraafHenk/numberwang: A small neural network that decides whether a number is Numberwang. · GitHub Skip to content Navigation MenuSign inAppearance settingsPlatformAI CODE CREATIONGitHub CopilotWrite better code with AIGitHub Copilot appDirect agents from issue to mergeMCP RegistryIntegrate external toolsDEVELOPER WORKFLOWSActionsAutomate any workflowCodespacesInstant dev environmentsIssuesPlan and track workCode ReviewManage code changesCode QualityEnforce quality at mergeAPPLICATION SECURITYGitHub Advanced SecurityFind and fix vulnerabilitiesCode securitySecure your code as you buildSecret protectionStop leaks before they startEXPLOREWhy GitHubDocumentationBlogChangelogMarketplaceView all featuresSolutionsBY COMPANY SIZEEnterprisesSmall and medium teamsStartupsNonprofitsBY USE CASEApp ModernizationDevSecOpsDevOpsCI/CDView all use casesBY INDUSTRYHealthcareFinancial servicesManufacturingGovernmentView all industriesView all solutionsResourcesEXPLORE BY TOPICAISoftware DevelopmentDevOpsSecurityView all topicsEXPLORE BY TYPECustomer storiesEvents & webinarsEbooks & reportsBusiness insightsGitHub SkillsSUPPORT & SERVICESDocumentationCustomer supportCommunity forumTrust centerPartnersView all resourcesOpen SourceCOMMUNITYGitHub SponsorsFund open source developersPROGRAMSSecurity LabMaintainer CommunityGitHub StarsArchive ProgramREPOSITORIESTopicsTrendingCollectionsEnterpriseENTERPRISE SOLUTIONSEnterprise platformAI-powered developer platformAVAILABLE ADD-ONSGitHub Advanced SecurityEnterprise-grade security featuresCopilot for BusinessEnterprise-grade AI featuresPremium SupportEnterprise-grade 24/7 supportPricingSearch/Sign inSign upAppearance settings You signed in with another tab or window. Reload to refresh your session. Dismiss alert GraafHenk numberwang Public
Notifications
Fork
Star Code Issues Pull requests Actions Projects Security and quality Insights
Additional navigation options
Code Issues Pull requests Actions Projects Security and quality Insights
mainBranchesTagsGo to fileCodeOpen more actions menuLatest commit History5 Commits5 CommitsFolders and filesNameNameLast commit messageLast commit dateLICENSELICENSE README.mdREADME.md app.pyapp.py model.jsonmodel.json numberwang.pynumberwang.py requirements.txtrequirements.txt View all filesRepository files navigationREADMELicenseMore itemsNumberwang $ python3 numberwang.py "45 - 44" $ python3 numberwang.py "hello how are you" model = load_model("model.json") verdict = max(range(4), key=probs.__getitem__) id 0 1 2 3 What it accepts input 42, sixty-six, 12345 zweiundzwanzig, veintidós, tweeëntwintig 5*2, 96 divided by 2, twelve plus four 45 - 44, double four, eins -7, 4.5, £5, 50%, 9:30 XLIV, twenty-third, 22nd fortnight, vierendelen, september achtneming, often, money shinty-six, twentington bonjour, hello how are you A number's wangness is a property of the number, not the language it 80,804 parameters. The network reads characters directly — there is no class not Numberwang Numberwang not a number Wangernumb Arithmetic on unseen operands is the weak spot, at 44–72%. The Footer © 2026 GitHub, Inc. Footer navigation Terms Privacy Security Status Community Docs Contact Manage cookies Do not share my personal information You can’t perform that action at this time. |
A small neural network has been developed that functions to determine whether a given number is classified as Numberwang. The entire model is encapsulated within a 1.8 megabyte JSON file, and the inference process is implemented using pure Python standard library functions, requiring no external machine learning frameworks like PyTorch or NumPy for execution. This approach allows for direct cloning and running of the model. The system is designed to handle a broad and complex range of input behaviors. It accepts inputs ranging from simple integers and digits to complex linguistic expressions, including words from up to eleven languages with optional accents, Roman numerals, and multi-operand arithmetic calculations. For example, it can evaluate expressions like 45 minus 44, or handle linguistic inputs such as "zweiundzwanzig," while explicitly rejecting inputs that contain no numeric content, such as conversational phrases like "hello how are you." The core principle established is that the wangness of a number is an intrinsic property, independent of the language used to express it. The architecture of the network processes character inputs through an embedded layer followed by one or more one-dimensional convolutional layers with a kernel size of three and ReLU activation functions. This is followed by global max pooling and linear layers, culminating in four final output nodes activated by a softmax function to produce the required verdicts. The entire structure contains 80,804 parameters, with the weights for digits, operators, canonical verdicts, and the eleven languages intrinsically encoded within the model weights and the model file. The network's operational capacity is demonstrated by its classification system, which provides four distinct verdicts: That's not Numberwang, THAT'S NUMBERWANG, That's not even a number, and That's Wangernumb. Performance evaluation on 486 held-out adjudications indicates an overall accuracy of 88.9 percent, corresponding to a macro-F1 score of 0.896, against a theoretical ceiling of approximately 98 percent, with a notable observation that about two percent of the training labels were inverted, reflecting established adjudication practices. The model exhibits performance differentials across the classes. For instance, the recall for identifying "Numberwang" is 0.900, and the precision is 0.919. The network shows a particularly high degree of certainty in classifying inputs as "not a number," achieving a recall of 0.830. A known limitation identified is the handling of arithmetic operations on operands that were not present in the training set, where uncertainty arises for calculations involving numbers between 44 and 72 percent. This suggests that while the network excels at pattern recognition based on linguistic and numerical forms, its capacity for computing unseen arithmetic relies more on memorization than true computation. The system is provided with specific guidance regarding this limitation, advising users to evaluate and provide the result for expressions if arithmetic correctness is paramount. The repository is licensed under the MIT License, and the developer explicitly disclaims any warranty regarding the absolute veracity of any single number's classification. |