{"id":3252,"date":"2023-05-01T04:33:00","date_gmt":"2023-04-30T19:33:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=3252"},"modified":"2023-05-01T04:33:00","modified_gmt":"2023-04-30T19:33:00","slug":"gpt-%e9%96%a2%e9%80%a3","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=3252","title":{"rendered":"GPT-#\u95a2\u9023"},"content":{"rendered":"\n<p>\u6bce\u9031GPT-X\u306b\u95a2\u3059\u308b\u8ad6\u6587\u306f\u591a\u3044\u3002\u30aa\u30fc\u30d7\u30f3\u306a\u52d5\u304d\u5171\u306b\u8981\u30c1\u30a7\u30c3\u30af\u3002<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Evaluation of GPT-3.5 and GPT-4 for supporting real-world information needs in healthcare delivery&nbsp;<\/strong>[17.5]<br>\u672c\u7814\u7a76\u306e\u76ee\u7684\u306f, 2\u3064\u306e\u5927\u898f\u6a21\u8a00\u8a9e\u30e2\u30c7\u30eb (LLM) \u304c, \u533b\u5e2b\u304c\u63d0\u4f9b\u3057\u305f\u60c5\u5831\u30cb\u30fc\u30ba\u3092, \u5b89\u5168\u304b\u3064\u4e00\u81f4\u3057\u305f\u65b9\u6cd5\u3067\u60c5\u5831\u76f8\u8ac7\u30b5\u30fc\u30d3\u30b9\u306b\u63d0\u4f9b\u3067\u304d\u308b\u304b\u3069\u3046\u304b\u3092\u5224\u65ad\u3059\u308b\u3053\u3068\u3067\u3042\u3063\u305f\u3002 GPT-3.5\u3067\u306f,8\u8cea\u554f\u306b\u5bfe\u3059\u308b\u56de\u7b54\u306f\u30a4\u30f3\u30d5\u30a9\u30de\u30c6\u30a3\u30af\u30b9\u30fb\u30b3\u30f3\u30b5\u30eb\u30c6\u30a3\u30f3\u30b0\u30fb\u30ec\u30dd\u30fc\u30c8\u3068\u4e00\u81f4\u3057,20\u554f,9\u554f\u306f\u8a55\u4fa1\u3067\u304d\u306a\u304b\u3063\u305f\u3002 \u56de\u7b54\u306e20%\u672a\u6e80\u306f\u3001\u60c5\u5831\u76f8\u8ac7\u30b5\u30fc\u30d3\u30b9\u304b\u3089\u306e\u56de\u7b54\u3068\u4e00\u81f4\u3057\u3001\u56de\u7b54\u306b\u306f\u5e7b\u899a\u7684\u57fa\u6e96\u304c\u542b\u307e\u308c\u3066\u304a\u308a\u3001\u533b\u5e2b\u306f\u88ab\u5bb3\u3092\u69cb\u6210\u3059\u308b\u3082\u306e\u306b\u3064\u3044\u3066\u5206\u5272\u3055\u308c\u305f\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2304.13714v1\">\u8ad6\u6587<\/a>&nbsp;&nbsp;<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2304.13714v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>&nbsp; &nbsp;(Wed, 26 Apr 2023 17:54:28 GMT)<\/li>\n\n\n\n<li>\u533b\u7642\u5206\u91ce\u306b\u304a\u3051\u308bGPT-3.5\u3001GPT-4\u306e\u5229\u7528\u304c\u53ef\u80fd\u304b\u306b\u95a2\u3059\u308b\u5831\u544a<\/li>\n\n\n\n<li>\u300cThese results suggest that while general purpose LLMs are able to provide safe and credible responses, they often do not fully meet the specific information need of a given question.\u300d\u3068\u306e\u3053\u3068\u3067\u30ea\u30b9\u30af\u306e\u9ad8\u3044\u56de\u7b54\u3092\u907f\u3051\u3066\u3044\u308b\uff08\u3086\u3048\u306b\u60c5\u5831\u30cb\u30fc\u30ba\u306b\u5408\u3063\u3066\u3044\u306a\u3044\uff09\u3068\u3044\u3046\u7d50\u679c\u306e\u3088\u3046<\/li>\n<\/ul>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Differentiate ChatGPT-generated and Human-written Medical Texts&nbsp;<\/strong>[8.5]<br>\u3053\u306e\u7814\u7a76\u306f\u3001\u533b\u5b66\u306b\u304a\u3051\u308b\u8cac\u4efb\u3068\u502b\u7406\u7684AIGC(Artificial Intelligence Generated Content)\u306b\u95a2\u3059\u308b\u6700\u521d\u306e\u7814\u7a76\u3067\u3042\u308b\u3002 \u672c\u7a3f\u3067\u306f,ChatGPT\u306b\u3088\u308b\u4eba\u7684\u5c02\u9580\u5bb6\u306b\u3088\u308b\u533b\u7642\u7528\u30c6\u30ad\u30b9\u30c8\u306e\u5dee\u7570\u306e\u5206\u6790\u306b\u7126\u70b9\u3092\u3042\u3066\u308b\u3002 \u6b21\u306e\u30b9\u30c6\u30c3\u30d7\u3067\u306f\u3001\u3053\u308c\u3089\u306e2\u7a2e\u985e\u306e\u5185\u5bb9\u306e\u8a00\u8a9e\u7684\u7279\u5fb4\u3092\u5206\u6790\u3057\u3001\u8a9e\u5f59\u3001\u90e8\u5206\u97f3\u58f0\u3001\u4f9d\u5b58\u6027\u3001\u611f\u60c5\u3001\u96e3\u6613\u5ea6\u306a\u3069\u306e\u9055\u3044\u3092\u660e\u3089\u304b\u306b\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2304.11567v1\">\u8ad6\u6587<\/a>&nbsp;&nbsp;<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2304.11567v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>&nbsp; &nbsp;(Sun, 23 Apr 2023 07:38:07 GMT)<\/li>\n\n\n\n<li>ChatGPT\u306b\u3088\u3063\u3066\u751f\u6210\u3055\u308c\u305f\u533b\u7642\u7528\u30c6\u30ad\u30b9\u30c8\u3068\u4eba\u9593\u306e\u5c02\u9580\u5bb6\u304c\u66f8\u3044\u305f\u30c6\u30ad\u30b9\u30c8\u306e\u5dee\u7570\u3092\u691c\u8a3c\u3057\u305f\u5831\u544a<\/li>\n\n\n\n<li>\u300cMedical texts written by humans are more concrete, more diverse, and typically contain more useful information, while medical texts generated by ChatGPT pay more attention to \ufb02uency and logic, and usually express general terminologies rather than e\ufb00ective information speci\ufb01c to the context of the problem.\u300d\u3068\u3044\u3046\u7d50\u679c\u306f\u4e00\u3064\u4e0a\u306e\u8ad6\u6587\u3068\u6574\u5408\u7684\u306b\u601d\u3048\u308b\u3002<\/li>\n<\/ul>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Boosting Theory-of-Mind Performance in Large Language Models via Prompting&nbsp;<\/strong>[2.5]<br>\u672c\u7814\u7a76\u306f,GPT-4\u304a\u3088\u30733\u7a2e\u985e\u306eGPT-3.5\u306eToM\u7279\u6027\u3092\u6e2c\u5b9a\u3059\u308b\u3002 ToM\u7406\u89e3\u306e\u6539\u5584\u306b\u304a\u3051\u308b\u6587\u8108\u5185\u5b66\u7fd2\u306e\u6709\u52b9\u6027\u3092\u691c\u8a0e\u3057\u305f\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2304.11490v3\">\u8ad6\u6587<\/a>&nbsp;&nbsp;<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2304.11490v3\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>&nbsp; &nbsp;(Wed, 26 Apr 2023 04:02:04 GMT)<\/li>\n\n\n\n<li>ToM\u7279\u6027\u306e\u6e2c\u5b9a\u3068in-context learning\u306e\u6709\u52b9\u6027\u306b\u95a2\u3059\u308b\u5831\u544a<\/li>\n\n\n\n<li>chain-of-thought reasoning\u3084step-by-step thinking\u306f\u3068\u3082\u304b\u304f\u3068\u3057\u3066few shot\u3067\u306e\uff08\u8fd1\u3044\u4f8b\u984c\u3092\u53c2\u7167\u3057\u3064\u3064\uff09ToM\u6e2c\u308b\u3068\u3044\u3046\u306e\u306f\u305d\u3082\u305d\u3082\u3042\u308a\u306a\u3093\u3060\u308d\u3046\u304b\uff1f\u3068\u601d\u3044\u3064\u3064GPT-4\u306e\u6709\u7528\u6027\u306f\u8868\u308c\u3066\u3044\u308b\u3088\u3046\u306b\u601d\u3046<\/li>\n<\/ul>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>AI-assisted coding: Experiments with GPT-4&nbsp;<\/strong>[0.2]<br>GPT-4\u306f\u3001\u304b\u306a\u308a\u306e\u30ab\u30d0\u30ec\u30c3\u30b8\u3067\u30c6\u30b9\u30c8\u3092\u751f\u6210\u3059\u308b\u3053\u3068\u304c\u3067\u304d\u308b\u304c\u3001\u307b\u3068\u3093\u3069\u306e\u30c6\u30b9\u30c8\u306f\u95a2\u9023\u3059\u308b\u30b3\u30fc\u30c9\u306b\u9069\u7528\u3055\u308c\u306a\u3044\u3002 \u3053\u308c\u3089\u306e\u7d50\u679c\u306f\u3001AI\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u30c4\u30fc\u30eb\u306f\u975e\u5e38\u306b\u5f37\u529b\u3067\u3042\u308b\u304c\u3001\u7d50\u679c\u306e\u59a5\u5f53\u6027\u3068\u6b63\u78ba\u6027\u3092\u4fdd\u8a3c\u3059\u308b\u305f\u3081\u306b\u306f\u3001\u307e\u3060\u4eba\u9593\u3092\u5fc5\u8981\u3068\u3059\u308b\u3053\u3068\u3092\u793a\u5506\u3057\u3066\u3044\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2304.13187v1\">\u8ad6\u6587<\/a>&nbsp;&nbsp;<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2304.13187v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>&nbsp; &nbsp;(Tue, 25 Apr 2023 22:59:01 GMT)<\/li>\n\n\n\n<li>GPT-4\u306e\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u652f\u63f4\u306b\u95a2\u3059\u308b\u5831\u544a<\/li>\n\n\n\n<li>\u300cIt should be emphasized that these results do not assess the accuracy of the code; rather, they suggest that GPT-4 can help programmers achieve code that is cleaner and potentially more maintainable than the original.\u300d\u3068\u3044\u3046\u6307\u6458\u306f\u8208\u5473\u6df1\u3044\u3002GPT-4\u306e\u652f\u63f4\u3067\u30e1\u30f3\u30c6\u30ca\u30f3\u30b9\u6027\u304c\u4e0a\u304c\u308b\u306e\u3067\u3042\u308c\u3070\u3068\u3063\u3066\u3082\u3042\u308a\u304c\u305f\u3044<\/li>\n<\/ul>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Can GPT-4 Perform Neural Architecture Search?&nbsp;<\/strong>[57.0]<br>\u30cb\u30e5\u30fc\u30e9\u30eb\u30a2\u30fc\u30ad\u30c6\u30af\u30c1\u30e3\u30b5\u30fc\u30c1(NAS)\u306b\u304a\u3051\u308bGPT-4\u306e\u53ef\u80fd\u6027\u306b\u3064\u3044\u3066\u691c\u8a0e\u3059\u308b\u3002 \u63d0\u6848\u624b\u6cd5\u3067\u3042\u308b GPT-4 Enhanced Neural archItectUre Search (GENIUS)\u306f\u3001\u3044\u304f\u3064\u304b\u306e\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3067\u8a55\u4fa1\u3001\u65e2\u5b58\u306eNAS\u6280\u8853\u3068\u6bd4\u8f03\u3057\u3001\u305d\u306e\u52b9\u679c\u3092\u5b9f\u8a3c\u3057\u305f\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2304.10970v2\">\u8ad6\u6587<\/a>&nbsp;&nbsp;<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2304.10970v2\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>&nbsp; &nbsp;(Mon, 24 Apr 2023 14:56:54 GMT)<\/li>\n\n\n\n<li>GPT-4\u3092\u7528\u3044\u305fNAS\u3001\u52b9\u679c\u304c\u3042\u308b\u3068\u3044\u3046\u306e\u306f\u9762\u767d\u304f\u610f\u5916\u306a\u7d50\u679c\u3002Kaggle\u306e\u76f8\u8ac7\u5f79\u3068\u3057\u3066\u3082\u6709\u52b9\u3068\u304b\u3044\u3046\u8a71\u3082\u3042\u308a\u3001\u30c1\u30e5\u30fc\u30cb\u30f3\u30b0\u30c6\u30af\u30cb\u30c3\u30af\u306e\u60c5\u5831\u3092\u4f55\u3089\u304b\u306e\u5f62\u3067\u6301\u3063\u3066\u3044\u308b\u304b\u3089\u306a\u3093\u3060\u308d\u3046\u304b\u3002\uff08\u305d\u308c\u3067\u3082\u3044\u308d\u3044\u308d\u306a\u5f62\u3067\u60c5\u5831\u304c\u5165\u3063\u3066\u3044\u308b\u306f\u305a\u306e\u65e2\u5b58\u624b\u6cd5\u3068\u6bd4\u3079\u3066\u4e00\u5b9a\u306e\u512a\u4f4d\u6027\u304c\u3042\u308b\u306e\u304c\u610f\u5916\u3067\u306f\u3042\u308b\u304c\uff09<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/mingkai-zheng\/GENIUS\">GitHub &#8211; mingkai-zheng\/GENIUS<\/a><\/li>\n<\/ul>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>ChatGPT vs State-of-the-Art Models: A Benchmarking Study in Keyphrase Generation Task\u00a0<\/strong>[0.0]<br>ChatGPT\u3092\u542b\u3080\u30c8\u30e9\u30f3\u30b9\u30d5\u30a9\u30fc\u30de\u30fc\u30d9\u30fc\u30b9\u306e\u8a00\u8a9e\u30e2\u30c7\u30eb\u306f\u3001\u69d8\u3005\u306a\u81ea\u7136\u8a00\u8a9e\u751f\u6210\u30bf\u30b9\u30af\u306b\u304a\u3044\u3066\u4f8b\u5916\u7684\u306a\u6027\u80fd\u3092\u793a\u3057\u305f\u3002 \u672c\u7814\u7a76\u306f\u3001ChatGPT\u306e\u30ad\u30fc\u30d5\u30ec\u30fc\u30ba\u751f\u6210\u6027\u80fd\u3068\u6700\u5148\u7aef\u30e2\u30c7\u30eb\u3092\u6bd4\u8f03\u3057\u3001\u3053\u306e\u5206\u91ce\u306b\u304a\u3051\u308b2\u3064\u306e\u91cd\u8981\u306a\u8ab2\u984c\u306b\u5bfe\u3059\u308b\u89e3\u6c7a\u7b56\u3068\u3057\u3066\u306e\u53ef\u80fd\u6027\u3092\u30c6\u30b9\u30c8\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2304.14177v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2304.14177v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Thu, 27 Apr 2023 13:25:43 GMT)<\/li>\n\n\n\n<li>\u30ad\u30fc\u30d5\u30ec\u30fc\u30ba\u751f\u6210\u306b\u304a\u3051\u308b\u6bd4\u8f03<\/li>\n\n\n\n<li>KeyBART\u3092\u8d85\u3048\u308b\u6027\u80fd\u3067\u3053\u306e\u624b\u306e\u30bf\u30b9\u30af\u306e\u76f8\u6027\u306f\u3055\u3059\u304c<\/li>\n<\/ul>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Is ChatGPT a Good NLG Evaluator? A Preliminary Study\u00a0<\/strong>[53.1]<br>NLG\u6e2c\u5b9a\u5024\u3068\u3057\u3066\u4fe1\u983c\u6027\u3092\u793a\u3059\u305f\u3081,ChatGPT\u306e\u30e1\u30bf\u8a55\u4fa1\u3092\u884c\u3063\u305f\u3002 \u5b9f\u9a13\u306e\u7d50\u679c,ChatGPT\u306f\u5f93\u6765\u306e\u81ea\u52d5\u6e2c\u5b9a\u5024\u3068\u6bd4\u8f03\u3057\u3066,\u4eba\u9593\u306e\u5224\u65ad\u3068\u6700\u5148\u7aef\u3042\u308b\u3044\u306f\u7af6\u5408\u7684\u306a\u76f8\u95a2\u3092\u9054\u6210\u3067\u304d\u305f\u3002 \u6211\u3005\u306e\u4e88\u5099\u7814\u7a76\u306f\u3001\u6c4e\u7528\u7684\u306a\u4fe1\u983c\u6027\u306e\u3042\u308bNLG\u30e1\u30c8\u30ea\u30c3\u30af\u306e\u51fa\u73fe\u3092\u4fc3\u3059\u3053\u3068\u3092\u9858\u3063\u3066\u3044\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2303.04048v2\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2303.04048v2\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Tue, 25 Apr 2023 16:15:20 GMT)<\/li>\n\n\n\n<li>ChatGPT\u3092NLG\u306e\u8a55\u4fa1\u7528\u306b\u4f7f\u304a\u3046\u3068\u3044\u3046\u5831\u544a<\/li>\n\n\n\n<li>\u4eca\u307e\u3067\u3082\u304b\u306a\u308a\u6027\u80fd\u304c\u826f\u3044\u306e\u3067\u306f\uff1f\u3068\u3044\u3046\u8ad6\u6587\u304c\u591a\u304b\u3063\u305f\u304c\u3001\u57fa\u672c\u7684\u306b\u306f\u540c\u3058\u7d50\u8ad6<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/krystalan\/chatgpt_as_nlg_evaluator\">GitHub &#8211; krystalan\/chatgpt_as_nlg_evaluator: Technical Report: Is ChatGPT a Good NLG Evaluator? A Preliminary Study<\/a><\/li>\n<\/ul>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Evaluating ChatGPT&#8217;s Information Extraction Capabilities: An Assessment of Performance, Explainability, Calibration, and Faithfulness\u00a0<\/strong>[18.9]<br>7\u3064\u306e\u304d\u3081\u7d30\u304b\u3044\u60c5\u5831\u62bd\u51fa(IE)\u30bf\u30b9\u30af\u3092\u7528\u3044\u3066ChatGPT\u306e\u5168\u4f53\u7684\u306a\u80fd\u529b\u3092\u8a55\u4fa1\u3059\u308b\u3053\u3068\u306b\u96c6\u4e2d\u3059\u308b\u3002 \u6a19\u6e96IE\u8a2d\u5b9a\u3067\u306eChatGPT\u306e\u30d1\u30d5\u30a9\u30fc\u30de\u30f3\u30b9\u306f\u52a3\u3063\u3066\u3044\u308b\u304c\u3001OpenIE\u8a2d\u5b9a\u3067\u306f\u9a5a\u304f\u307b\u3069\u512a\u308c\u305f\u30d1\u30d5\u30a9\u30fc\u30de\u30f3\u30b9\u3092\u793a\u3057\u3066\u3044\u308b\u3002 ChatGPT\u306f\u3001\u305d\u306e\u6c7a\u5b9a\u306b\u5bfe\u3057\u3066\u9ad8\u54c1\u8cea\u3067\u4fe1\u983c\u3067\u304d\u308b\u8aac\u660e\u3092\u63d0\u4f9b\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2304.11633v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2304.11633v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Sun, 23 Apr 2023 12:33:18 GMT)<\/li>\n\n\n\n<li>\u60c5\u5831\u62bd\u51fa\u5206\u91ce\u3067\u306e\u6bd4\u8f03<\/li>\n\n\n\n<li>\u6a19\u6e96\u7684\u306a\u8a2d\u5b9a\u3067\u306fSoTA\u306a\u30e2\u30c7\u30eb\u306b\u306f\u53ca\u3070\u306a\u3044\u304c\u3001\u30aa\u30fc\u30d7\u30f3\u306a\u8a2d\u5b9a\u3067\u306f\u6975\u3081\u3066\u5f37\u529b<\/li>\n\n\n\n<li>\u7279\u5316\u578b\u30e2\u30c7\u30eb\u306b\u306f\u52dd\u3066\u306a\u3044\u3051\u3069\u57fa\u672c\u7684\u306b\u306f\u5f37\u529b\u3068\u3044\u3046\u7d50\u679c\u3067\u3053\u308c\u3082\u4ed6\u306e\u5831\u544a\u3068\u6574\u5408\u7684<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>\u6bce\u9031GPT-X\u306b\u95a2\u3059\u308b\u8ad6\u6587\u306f\u591a\u3044\u3002\u30aa\u30fc\u30d7\u30f3\u306a\u52d5\u304d\u5171\u306b\u8981\u30c1\u30a7\u30c3\u30af\u3002<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[63,173],"class_list":["post-3252","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-chatgpt","tag-gpt"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/3252","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=3252"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/3252\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=3252"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=3252"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=3252"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}