{"id":13584849,"url":"https://github.com/chiphuyen/sotawhat","last_synced_at":"2025-04-08T09:08:24.253Z","repository":{"id":42041108,"uuid":"151323163","full_name":"chiphuyen/sotawhat","owner":"chiphuyen","description":"Returns latest research results by crawling arxiv papers and summarizing abstracts. Helps you stay afloat with so many new papers everyday.","archived":false,"fork":false,"pushed_at":"2024-02-02T04:30:15.000Z","size":27,"stargazers_count":1360,"open_issues_count":18,"forks_count":181,"subscribers_count":58,"default_branch":"master","last_synced_at":"2025-04-01T07:51:14.266Z","etag":null,"topics":["arxiv","python","research-tool","script","summarization"],"latest_commit_sha":null,"homepage":"https://huyenchip.com/2018/10/04/sotawhat.html","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/chiphuyen.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2018-10-02T21:03:28.000Z","updated_at":"2025-03-15T15:38:21.000Z","dependencies_parsed_at":"2022-08-02T16:15:07.711Z","dependency_job_id":"e74e774a-99bd-4e48-a308-3c1f0ff804ae","html_url":"https://github.com/chiphuyen/sotawhat","commit_stats":{"total_commits":21,"total_committers":10,"mean_commits":2.1,"dds":0.6190476190476191,"last_synced_commit":"b7f27b468c6dc0f9995d4a1c6e7f3fede12c7d79"},"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chiphuyen%2Fsotawhat","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chiphuyen%2Fsotawhat/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chiphuyen%2Fsotawhat/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chiphuyen%2Fsotawhat/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/chiphuyen","download_url":"https://codeload.github.com/chiphuyen/sotawhat/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247809962,"owners_count":20999816,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["arxiv","python","research-tool","script","summarization"],"created_at":"2024-08-01T15:04:33.805Z","updated_at":"2025-04-08T09:08:24.221Z","avatar_url":"https://github.com/chiphuyen.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# sotawhat\n\n[![License](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)\n\nRead more about SOTAWHAT [here](https://huyenchip.com/2018/10/04/sotawhat.html).\n\nYou can use sotawhat through a web interface [here](https://sotawhat.herokuapp.com/#/). Thanks hmchuong!\n\nThis script runs using Python 3. It requires ``nltk``, ``six``, and ``pyspellchecker``. To install it as a Python package, follow the following steps:\n\n\nStep 1: clone this repo, and go inside that repo:\n```bash\n$ git clone [HTTPS or SSH linnk to this repo]\n$ cd sotawhat\n```\nStep 2: install using pip\n\n```bash\n$ pip3 install .\n```\n\nOn Windows, due to encoding errors, the script may cause issues when run on the command line. It is\nrecommended to use `pip install win-unicode-console --upgrade` prior to launching the script. If you get\nUnicodeEncodingError, you *must* install the above.\n\nIn MacOS, you can get the SSL error\n\n```\n[nltk_data] Error loading punkt: \u003curlopen error [SSL:\n[nltk_data]     CERTIFICATE_VERIFY_FAILED] certificate verify failed:\n[nltk_data]     unable to get local issuer certificate (_ssl.c:1045)\u003e\n```\n\nthis will be fixed by reinstalling certificates\n```shell\n$ /Applications/Python\\ 3.x/Install\\ Certificates.command\n```\n\n# Usage\nThis project adds the `sotawhat` script for you to run globally on Terminal or commandline.\n\nTo query for a certain keyword, run:\n\n```bash\n$ sotawhat [keyword] [number of results]\n```\n\nFor example:\n\n```bash\n$ sotawhat perplexity 10\n```\n\nor \n\n```bash\n$ sotawhat language model 10\n```\n\nIf you don't specify the number of results, by default, the script returns 5 results. Each result contains the title of the paper with author and published date, a summary of the abstract, and link to the paper.\n\nWe've found that this script works well with keywords that are:\n+ a model (e.g. transformer, wavenet, ...)\n+ a dataset (e.g. wikitext, imagenet, ...)\n+ a task (e.g. language model, machine translation, fuzzing, ...)\n+ a metric (e.g. BLEU, perplexity, ...)\n+ random stuff\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fchiphuyen%2Fsotawhat","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fchiphuyen%2Fsotawhat","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fchiphuyen%2Fsotawhat/lists"}