From 937232e6afa48655d9cf2b84dcfc1149932c6366 Mon Sep 17 00:00:00 2001 From: Dhruv Ahuja Date: Thu, 19 Dec 2024 23:20:19 -0800 Subject: [PATCH] more garbage cleanup --- data/dom_tasks.jsonl | 126 ----------------------------------- data/evaluation_output.jsonl | 5 -- 2 files changed, 131 deletions(-) delete mode 100644 data/dom_tasks.jsonl delete mode 100644 data/evaluation_output.jsonl diff --git a/data/dom_tasks.jsonl b/data/dom_tasks.jsonl deleted file mode 100644 index c5263e6..0000000 --- a/data/dom_tasks.jsonl +++ /dev/null @@ -1,126 +0,0 @@ -{"web_name": "TripAdvisor", "id": "tripadvisor_search_101", "task": "Type 'Paris hotels' in the search box and press search", "web": "https://www.tripadvisor.com", "element_type": "input", "interaction": "type_submit", "target_element": {"type": "id", "value": "mainSearch"}, "input_text": "Paris hotels", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_101_gt.png", "description": "Paris hotels has been entered and search initiated"}} -{"web_name": "IMDB", "id": "imdb_search_102", "task": "Click the search box and type 'Inception'", "web": "https://www.imdb.com", "element_type": "input", "interaction": "type", "target_element": {"type": "id", "value": "suggestion-search"}, "input_text": "Inception", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_102_gt.png", "description": "The word 'Inception' has been entered in the search box"}} -{"web_name": "Stack Overflow", "id": "stackoverflow_nav_104", "task": "Click the Questions link in the navigation", "web": "https://stackoverflow.com", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "nav-questions"}, "target_html": "Questions", "ground_truth": {"screenshot": "evaluation/ground_truth/task_104_gt.png", "description": "The Questions navigation link has been clicked"}} -{"web_name": "NPR", "id": "npr_menu_105", "task": "Click the Culture button in the navigation menu", "web": "https://www.npr.org", "element_type": "button", "interaction": "click", "target_element": {"type": "id", "value": "menu-button"}, "target_html": "Culture", "ground_truth": {"screenshot": "evaluation/ground_truth/task_105_gt.png", "description": "The Culture button has been clicked"}} -{"web_name": "NASA", "id": "nasa_search_106", "task": "Type 'space station' in the search box and press search", "web": "https://www.nasa.gov", "element_type": "input", "interaction": "type_submit", "target_element": {"type": "id", "value": "nasa-search"}, "input_text": "space station", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_106_gt.png", "description": "The phrase 'space station' has been entered and search initiated"}} -{"web_name": "NASA", "id": "nasa_nav_107", "task": "Click the Missions link", "web": "https://www.nasa.gov", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "nav-missions"}, "target_html": "Missions", "ground_truth": {"screenshot": "evaluation/ground_truth/task_107_gt.png", "description": "The Missions link has been clicked"}} -{"web_name": "IMDB", "id": "imdb_nav_109", "task": "Click the Sign In button", "web": "https://www.imdb.com", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "signin-button"}, "target_html": "Sign In", "ground_truth": {"screenshot": "evaluation/ground_truth/task_109_gt.png", "description": "The Sign In button has been clicked"}} -{"web_name": "Project Gutenberg", "id": "gutenberg_search_111", "task": "Type 'Shakespeare' in the search box", "web": "https://www.gutenberg.org", "element_type": "input", "interaction": "type", "target_element": {"type": "id", "value": "mainsearch"}, "input_text": "Shakespeare", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_111_gt.png", "description": "The word 'Shakespeare' has been entered in the search box"}} -{"web_name": "NPR", "id": "npr_podcasts_112", "task": "Click the Podcasts link", "web": "https://www.npr.org", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "podcasts-link"}, "target_html": "Podcasts & Shows", "ground_truth": {"screenshot": "evaluation/ground_truth/task_112_gt.png", "description": "The Podcasts link has been clicked"}} -{"web_name": "NASA", "id": "nasa_images_114", "task": "Click the Multimedia link", "web": "https://www.nasa.gov", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "images-link"}, "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_114_gt.png", "description": "The Multimedia link has been clicked"}} -{"web_name": "Project Gutenberg", "id": "gutenberg_browse_115", "task": "Click the Browse Catalog link", "web": "https://www.gutenberg.org", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "browse-catalog"}, "target_html": "Search and Browse▾", "ground_truth": {"screenshot": "evaluation/ground_truth/task_115_gt.png", "description": "The Browse Catalog link has been clicked"}} -{"web_name": "IMDB", "id": "imdb_top_116", "task": "Click the Menu link", "web": "https://www.imdb.com", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "top-250-link"}, "target_html": "Menu", "ground_truth": {"screenshot": "evaluation/ground_truth/task_116_gt.png", "description": "The Top 250 link has been clicked"}} -{"web_name": "Soundcloud", "id": "soundcloud_legal_118", "task": "Click the Legal link in the footer", "web": "https://soundcloud.com", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "legal-link"}, "target_html": "Legal", "ground_truth": {"screenshot": "evaluation/ground_truth/task_118_gt.png", "description": "The Legal link has been clicked"}} -{"web_name": "NPR", "id": "npr_stations_119", "task": "Click the newsletter button and enter johndoe@email.com", "web": "https://www.npr.org", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "stations-link"}, "target_html": "Newsletters ", "ground_truth": {"screenshot": "evaluation/ground_truth/task_119_gt.png", "description": "The email has been entered on the newsletter page"}} -{"web_name": "Soundcloud", "id": "soundcloud_upload_120", "task": "Click the Upload button", "web": "https://soundcloud.com", "element_type": "button", "interaction": "click", "target_element": {"type": "id", "value": "upload-button"}, "target_html": "Upload your own", "ground_truth": {"screenshot": "evaluation/ground_truth/task_120_gt.png", "description": "The Upload button has been clicked"}} -{"web_name": "NASA", "id": "nasa_astronomy_121", "task": "Click the Nasa youtube channel button", "web": "https://www.nasa.gov", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "astronomy-link"}, "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_121_gt.png", "description": "The NASA YouTube channel button has been clicked"}} -{"web_name": "PubMed", "id": "pubmed_search_122", "task": "Type 'cancer research' in the search box and press search", "web": "https://pubmed.ncbi.nlm.nih.gov", "element_type": "input", "interaction": "type_submit", "target_element": {"type": "id", "value": "id-term"}, "input_text": "cancer research", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_122_gt.png", "description": "The phrase 'cancer research' has been entered and search initiated"}} -{"web_name": "IMDB", "id": "imdb_trailers_123", "task": "Click the trailers link", "web": "https://www.imdb.com", "element_type": "link", "interaction": "click", "target_element": {"type": "class", "value": "sc-5d356059-6"}, "target_html": "Browse trailers", "ground_truth": {"screenshot": "evaluation/ground_truth/task_123_gt.png", "description": "The trailers page is open"}} -{"web_name": "Project Gutenberg", "id": "gutenberg_popular_125", "task": "Click the ibiblio button", "web": "https://www.gutenberg.org", "element_type": "link", "interaction": "click", "target_element": {"type": "text", "value": "Popular"}, "target_html": "\"iBiblio\"", "ground_truth": {"screenshot": "evaluation/ground_truth/task_125_gt.png", "description": "The ibiblio page is open"}} -{"web_name": "NPR", "id": "npr_support_126", "task": "Click the Support radio button", "web": "https://www.npr.org", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "support-link"}, "target_html": "Support Public Radio", "ground_truth": {"screenshot": "evaluation/ground_truth/task_126_gt.png", "description": "The support radio page is open"}} -{"web_name": "SoundCloud", "id": "soundcloud_search_127", "task": "Type Nav in the search bar and execute search", "web": "https://www.soundcloud.com", "element_type": "link", "interaction": "type_submit", "target_element": {"type": "id", "value": "search-bar"}, "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_127_gt.png", "description": "Nav has been searched"}} -{"web_name": "NASA", "id": "nasa_earth_128", "task": "Click the Earth link", "web": "https://www.nasa.gov", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "earth-link"}, "target_html": "Earth & Climate", "ground_truth": {"screenshot": "evaluation/ground_truth/task_128_gt.png", "description": "The Earth link has been clicked"}} -{"web_name": "SoundCloud", "id": "soundcloud_search_129", "task": "Go to the other slide in the carousel", "web": "https://www.soundcloud.com", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "carousel"}, "target_html": "
", "ground_truth": {"screenshot": "evaluation/ground_truth/task_129_gt.png", "description": "The carousel slide has been switched"}} -{"web_name": "IMDB", "id": "imdb_watchlist_130", "task": "Click the Watchlist link", "web": "https://www.imdb.com", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "watchlist-button"}, "target_html": "Watchlist", "ground_truth": {"screenshot": "evaluation/ground_truth/task_130_gt.png", "description": "The Watchlist link has been clicked"}} -{"web_name": "Weather.com", "id": "weather_alerts_131", "task": "Open the menu and click the Hourly button", "web": "https://weather.com", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "alerts-link"}, "target_html": " Hourly", "ground_truth": {"screenshot": "evaluation/ground_truth/task_131_gt.png", "description": "The hourly forecast has been opened"}} -{"web_name": "Project Gutenberg", "id": "gutenberg_policy_132", "task": "Find the 11th section in the privacy policy", "web": "https://www.gutenberg.org/policy/permission.html", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "eleventh-item"}, "target_html": "
  • US only
    • ", "ground_truth": {"screenshot": "evaluation/ground_truth/task_132_gt.png", "description": "The 11th section from the privacy policy has been opened"}} -{"web_name": "NPR", "id": "npr_about_133", "task": "Click search and type in uc berkeley", "web": "https://www.npr.org", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "about-link"}, "target_html": "Search ", "ground_truth": {"screenshot": "evaluation/ground_truth/task_133_gt.png", "description": "The search bar has uc berkeley type in"}} -{"web_name": "CNN", "id": "cnn_politics_134", "task": "Click the Politics link", "web": "https://www.cnn.com", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "politics-nav"}, "target_html": "Politics", "ground_truth": {"screenshot": "evaluation/ground_truth/task_134_gt.png", "description": "The Politics link has been clicked"}} -{"web_name": "NASA", "id": "nasa_search_135", "task": "Type 'mars rover' in the search box", "web": "https://www.nasa.gov", "element_type": "input", "interaction": "type", "target_element": {"type": "id", "value": "search-box"}, "input_text": "mars rover", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_135_gt.png", "description": "The phrase 'mars rover' has been entered in the search box"}} -{"web_name": "IMDB", "id": "imdb_awards_137", "task": "Click the Awards & Events link", "web": "https://www.imdb.com", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "awards-link"}, "target_html": "Awards & Events", "ground_truth": {"screenshot": "evaluation/ground_truth/task_137_gt.png", "description": "The Awards & Events link has been clicked"}} -{"web_name": "Weather.com", "id": "weather_maps_138", "task": "Type in johndoe@email.com in the email signup for mornin brief", "web": "https://weather.com", "element_type": "link", "interaction": "type", "target_element": {"type": "id", "value": "maps-link"}, "input_text": "johndoe@email.com", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_138_gt.png", "description": "The email has been entered"}} -{"web_name": "Sound Cloud", "id": "soundcloud_keyboard_139", "task": "Click the three buttons and then click the key board short cuts", "web": "https://soundcloud.com/discover", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "nav-jobs"}, "target_html": "Settings and more Keyboard shortcuts", "ground_truth": {"screenshot": "evaluation/ground_truth/task_139_gt.png", "description": "The keyboard short cuts show up"}} -{"web_name": "NPR", "id": "npr_music_140", "task": "Click the Music link", "web": "https://www.npr.org", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "music-link"}, "target_html": "Music", "ground_truth": {"screenshot": "evaluation/ground_truth/task_140_gt.png", "description": "The Music link has been clicked"}} -{"web_name": "CNN", "id": "cnn_business_141", "task": "Click the Business link", "web": "https://www.cnn.com", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "business-nav"}, "target_html": "Business", "ground_truth": {"screenshot": "evaluation/ground_truth/task_141_gt.png", "description": "The Business link has been clicked"}} -{"web_name": "NASA", "id": "nasa_solar_142", "task": "Click the Solar System link", "web": "https://www.nasa.gov", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "solar-system-link"}, "target_html": "The Solar System", "ground_truth": {"screenshot": "evaluation/ground_truth/task_142_gt.png", "description": "The Solar System link has been clicked"}} -{"web_name": "Gutenberg", "id": "gutenberg_books_143", "task": "Click the random books link", "web": "https://www.gutenberg.org/ebooks/", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "nav-books-link"}, "target_html": "RandomRandom books.", "ground_truth": {"screenshot": "evaluation/ground_truth/task_143_gt.png", "description": "The random books link has been clicked"}} -{"web_name": "Gutenberg", "id": "gutenberg_books_144", "task": "Click the ways to donate button", "web": "https://www.gutenberg.org", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "donate-button"}, "target_html": "Ways to donate", "ground_truth": {"screenshot": "evaluation/ground_truth/task_143_gt.png", "description": "The random books link has been clicked"}} -{"web_name": "PubMed", "id": "pubmed_search_146", "task": "Click the FAQs & User Guide link", "web": "https://pubmed.ncbi.nlm.nih.gov", "element_type": "input", "interaction": "click", "target_element": {"type": "id", "value": "id-term"}, "target_html": "FAQs & User Guide", "ground_truth": {"screenshot": "evaluation/ground_truth/task_146_gt.png", "description": "The faqs and user guide page shows up"}} -{"web_name": "PubMed", "id": "pubmed_search_147", "task": "Click X (Twitter) icon", "web": "https://pubmed.ncbi.nlm.nih.gov", "element_type": "input", "interaction": "click", "target_element": {"type": "id", "value": "x-button"}, "target_html": "Twitter", "ground_truth": {"screenshot": "evaluation/ground_truth/task_147_gt.png", "description": "The PubMed X (Twitter) account shows up"}} -{"web_name": "PubMed", "id": "pubmed_search_148", "task": "Click usa.gov link", "web": "https://pubmed.ncbi.nlm.nih.gov", "element_type": "input", "interaction": "click", "target_element": {"type": "id", "value": "usa-gov-link"}, "target_html": "USA.gov", "ground_truth": {"screenshot": "evaluation/ground_truth/task_147_gt.png", "description": "The usa.gov page opens"}} -{"web_name": "PubMed", "id": "pubmed_search_149", "task": "Click see tending articles and search uc berkeley", "web": "https://pubmed.ncbi.nlm.nih.gov", "element_type": "input", "interaction": "click", "target_element": {"type": "id", "value": "usa-gov-link"}, "target_html": "See more trending articles ", "ground_truth": {"screenshot": "evaluation/ground_truth/task_149_gt.png", "description": "The trending articles open and uc berkeley is typed in"}} -{"web_name": "PubMed", "id": "pubmed_search_149", "task": "Click see trending articles and search uc berkeley", "web": "https://pubmed.ncbi.nlm.nih.gov", "element_type": "input", "interaction": "click", "target_element": {"type": "data-ga-action", "value": "trending"}, "target_html": "See more trending articles", "ground_truth": {"screenshot": "evaluation/ground_truth/task_149_gt.png", "description": "The trending articles page opens"}} -{"web_name": "PubMed", "id": "pubmed_clinical_150", "task": "Click the Clinical Queries link and change the study category to prognosis", "web": "https://pubmed.ncbi.nlm.nih.gov", "element_type": "link", "interaction": "click", "target_element": {"type": "data-ga-label", "value": "clinical_query"}, "target_html": "Clinical Queries
    ", "ground_truth": {"screenshot": "evaluation/ground_truth/task_150_gt.png", "description": "The clinical queries page is shown with prognosis as the study type"}} -{"web_name": "Cambridge Dictionary", "id": "cambridge_lookup_1", "task": "Click the search box and type 'hello'", "web": "https://dictionary.cambridge.org/", "element_type": "input", "interaction": "type", "target_element": {"type": "id", "value": "searchword"}, "input_text": "hello", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_1_gt.png", "description": "The word 'hello' has been entered in the search box"}} -{"web_name": "Amazon", "id": "amazon_cart_1", "task": "Click the Cart button", "web": "https://www.amazon.com", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "nav-cart"}, "target_html": "
    Cart
    ", "ground_truth": {"screenshot": "evaluation/ground_truth/task_2_gt.png", "description": "The Cart button has been clicked"}} -{"web_name": "Google Maps", "id": "maps_search_1", "task": "Type 'San Francisco' into the search box and press search", "web": "https://www.google.com/maps", "element_type": "input", "interaction": "type_submit", "target_element": {"type": "id", "value": "searchboxinput"}, "input_text": "San Francisco", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_3_gt.png", "description": "San Francisco has been entered and search initiated"}} -{"web_name": "YouTube", "id": "youtube_logo_1", "task": "Hover over the YouTube logo in the top left", "web": "https://www.youtube.com", "element_type": "link", "interaction": "hover", "target_element": {"type": "id", "value": "logo"}, "target_html": "
    ", "ground_truth": {"screenshot": "evaluation/ground_truth/task_4_gt.png", "description": "The YouTube logo is in hover state, showing a tooltip with 'YouTube Home'"}} -{"web_name": "React Documentation", "id": "react_search_1", "task": "Type 'hooks tutorial' in the search box", "web": "https://legacy.reactjs.org/", "element_type": "input", "interaction": "type", "target_element": {"type": "id", "value": "algolia-doc-search"}, "input_text": "hooks tutorial", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_54_gt.png", "description": "The phrase 'hooks tutorial' has been entered in the search box"}} -{"web_name": "Vue.js Documentation", "id": "vue_search_1", "task": "Type 'component props' into the search box and press search", "web": "https://vuejs.org/guide", "element_type": "input", "interaction": "type_submit", "target_element": {"type": "id", "value": "search-input"}, "input_text": "component props", "target_html": "Search", "ground_truth": {"screenshot": "evaluation/ground_truth/task_55_gt.png", "description": "The phrase 'component props' has been entered and search initiated"}} -{"web_name": "Django Documentation", "id": "django_search_1", "task": "Type 'model fields' in the search box and click search", "web": "https://docs.djangoproject.com", "element_type": "input", "interaction": "type_submit", "target_element": {"type": "id", "value": "search-input"}, "input_text": "model fields", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_56_gt.png", "description": "The phrase 'model fields' has been entered in the search box and search initiated"}} -{"web_name": "Flask Documentation", "id": "flask_search_1", "task": "Type 'route decorators' into the search box and press search", "web": "https://flask.palletsprojects.com", "element_type": "input", "interaction": "type_submit", "target_element": {"type": "id", "value": "searchbox"}, "input_text": "route decorators", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_57_gt.png", "description": "The phrase 'route decorators' has been entered and search initiated"}} -{"web_name": "MDN Web Docs", "id": "mdn_nav_1", "task": "Click the Guides link in the navigation", "web": "https://developer.mozilla.org", "element_type": "link", "interaction": "click", "target_element": {"type": "class", "value": "nav-guides"}, "target_html": "Guides", "ground_truth": {"screenshot": "evaluation/ground_truth/task_58_gt.png", "description": "The Guides link has been clicked"}} -{"web_name": "W3Schools", "id": "w3_tutorial_1", "task": "Click the HTML Tutorial link", "web": "https://www.w3schools.com", "element_type": "link", "interaction": "click", "target_element": {"type": "class", "value": "w3-bar-item"}, "target_html": "Tutorials", "ground_truth": {"screenshot": "evaluation/ground_truth/task_59_gt.png", "description": "The HTML Tutorial link has been clicked"}} -{"web_name": "Python Documentation", "id": "python_nav_1", "task": "Click the Library Reference link", "web": "https://docs.python.org", "element_type": "link", "interaction": "click", "target_element": {"type": "class", "value": "reference-nav"}, "target_html": "Language reference", "ground_truth": {"screenshot": "evaluation/ground_truth/task_60_gt.png", "description": "The Library Reference link has been clicked"}} -{"web_name": "Node.js Documentation", "id": "node_nav_1", "task": "Click the Docs link", "web": "https://nodejs.org/en", "element_type": "link", "interaction": "click", "target_element": {"type": "class", "value": "docs-link"}, "target_html": "Docs", "ground_truth": {"screenshot": "evaluation/ground_truth/task_61_gt.png", "description": "The docs link has been clicked"}} -{"web_name": "MySQL Documentation", "id": "mysql_search_2", "task": "Type 'stored procedures' in the search box", "web": "https://dev.mysql.com/doc", "element_type": "input", "interaction": "type", "target_element": {"type": "id", "value": "search-input"}, "input_text": "stored procedures", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_62_gt.png", "description": "The phrase 'stored procedures' has been entered in the search box"}} -{"web_name": "PostgreSQL Documentation", "id": "postgres_nav_1", "task": "Click the Developers link", "web": "https://www.postgresql.org/docs", "element_type": "link", "interaction": "click", "target_element": {"type": "class", "value": "dev-link"}, "target_html": "
  • Developers
    • ", "ground_truth": {"screenshot": "evaluation/ground_truth/task_63_gt.png", "description": "The Developers link has been clicked"}} -{"web_name": "MySQL Documentation", "id": "mysql_nav_1", "task": "Click the Reference Manual link", "web": "https://dev.mysql.com/doc", "element_type": "link", "interaction": "click", "target_element": {"type": "class", "value": "reference-link"}, "target_html": "
  • Reference Manual
    • ", "ground_truth": {"screenshot": "evaluation/ground_truth/task_64_gt.png", "description": "The Reference Manual link has been clicked"}} -{"web_name": "PHP Documentation", "id": "php_nav_1", "task": "Click the Get Involved link", "web": "https://www.php.net/docs.php", "element_type": "link", "interaction": "click", "target_element": {"type": "class", "value": "get_involved"}, "target_html": "Get Involved", "ground_truth": {"screenshot": "evaluation/ground_truth/task_65_gt.png", "description": "The Get Involved link has been clicked"}} -{"web_name": "React Get Started", "id": "react_nav_1", "task": "Click the Get Started link", "web": "https://legacy.reactjs.org", "element_type": "link", "interaction": "click", "target_element": {"type": "class", "value": "nav-tutorial"}, "target_html": "Get Started", "ground_truth": {"screenshot": "evaluation/ground_truth/task_66_gt.png", "description": "The Get Started link has been clicked"}} -{"web_name": "Django Community Link", "id": "django_nav_1", "task": "Click the Community link", "web": "https://docs.djangoproject.com", "element_type": "link", "interaction": "click", "target_element": {"type": "class", "value": "community-tutorial"}, "target_html": "Community", "ground_truth": {"screenshot": "evaluation/ground_truth/task_67_gt.png", "description": "The Community link has been clicked"}} -{"web_name": "Flask Documentation", "id": "flask_search_2", "task": "Type 'database' into the search box and press search", "web": "https://flask.palletsprojects.com", "element_type": "input", "interaction": "type_submit", "target_element": {"type": "id", "value": "searchbox"}, "input_text": "database", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_68_gt.png", "description": "The word 'database' has been entered and search initiated"}} -{"web_name": "PostgreSQL Documentation", "id": "postgres_search_1", "task": "Type 'indexes' in the search box", "web": "https://www.postgresql.org/docs", "element_type": "input", "interaction": "type", "target_element": {"type": "id", "value": "docSearch"}, "input_text": "indexes", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_69_gt.png", "description": "The word 'indexes' has been entered in the search box"}} -{"web_name": "MySQL Documentation", "id": "mysql_search_3", "task": "Type 'triggers' into the search box and press search", "web": "https://dev.mysql.com/doc", "element_type": "input", "interaction": "type_submit", "target_element": {"type": "id", "value": "search-input"}, "input_text": "triggers", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_70_gt.png", "description": "The word 'triggers' has been entered and search initiated"}} -{"web_name": "Node.js Documentation", "id": "node_search_1", "task": "Type 'events' into the search box and press search", "web": "https://nodejs.org/docs", "element_type": "input", "interaction": "type_submit", "target_element": {"type": "id", "value": "search"}, "input_text": "events", "target_html": "Start typing...", "ground_truth": {"screenshot": "evaluation/ground_truth/task_71_gt.png", "description": "The word 'events' has been entered and search initiated"}} -{"web_name": "React Documentation", "id": "react_search_2", "task": "Type 'context api' in the search box", "web": "https://react.dev/", "element_type": "input", "interaction": "type", "target_element": {"type": "id", "value": "algolia-doc-search"}, "input_text": "context api", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_72_gt.png", "description": "The phrase 'context api' has been entered in the search box"}} -{"web_name": "Vue.js Documentation", "id": "vue_nav_1", "task": "Click the API Reference link", "web": "https://vuejs.org/guide", "element_type": "link", "interaction": "click", "target_element": {"type": "class", "value": "nav-api"}, "target_html": "API", "ground_truth": {"screenshot": "evaluation/ground_truth/task_73_gt.png", "description": "The API Reference link has been clicked"}} -{"web_name": "Django Documentation", "id": "django_search_2", "task": "Type 'forms' into the search box and press search", "web": "https://docs.djangoproject.com", "element_type": "input", "interaction": "type_submit", "target_element": {"type": "id", "value": "search-input"}, "input_text": "forms", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_74_gt.png", "description": "The word 'forms' has been entered and search initiated"}} -{"web_name": "Flask Documentation", "id": "flask_nav_1", "task": "Click the API Reference link", "web": "https://flask.palletsprojects.com", "element_type": "link", "interaction": "click", "target_element": {"type": "class", "value": "nav-api"}, "target_html": "API Reference", "ground_truth": {"screenshot": "evaluation/ground_truth/task_75_gt.png", "description": "The API Reference link has been clicked"}} -{"web_name": "PostgreSQL Documentation", "id": "postgres_search_2", "task": "Type 'replication' in the search box", "web": "https://www.postgresql.org/docs", "element_type": "input", "interaction": "type", "target_element": {"type": "id", "value": "docSearch"}, "input_text": "replication", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_76_gt.png", "description": "The word 'replication' has been entered in the search box"}} -{"web_name": "MySQL Documentation", "id": "mysql_nav_2", "task": "Click the Release Notes link", "web": "https://dev.mysql.com/doc", "element_type": "link", "interaction": "click", "target_element": {"type": "class", "value": "release_notes"}, "target_html": "MySQL 8.4Release Notes", "ground_truth": {"screenshot": "evaluation/ground_truth/task_77_gt.png", "description": "The Release Notes link has been clicked"}} -{"web_name": "PHP Documentation", "id": "php_search_1", "task": "Type 'regex' into the search box and press search", "web": "https://www.php.net/docs.php", "element_type": "input", "interaction": "type_submit", "target_element": {"type": "id", "value": "search-text"}, "input_text": "regex", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_42_gt.png", "description": "The word 'regex' has been entered and search initiated"}} -{"web_name": "Node.js Documentation", "id": "node_nav_2", "task": "Click the Getting Started link", "web": "https://nodejs.org/en", "element_type": "link", "interaction": "click", "target_element": {"type": "class", "value": "nav-getting-started"}, "target_html": "Getting Started", "ground_truth": {"screenshot": "evaluation/ground_truth/task_78_gt.png", "description": "The Getting Started link has been clicked"}} -{"web_name": "Vue.js Documentation", "id": "vue_search_2", "task": "Type 'router' into the search box and press search", "web": "https://vuejs.org/guide", "element_type": "input", "interaction": "type_submit", "target_element": {"type": "id", "value": "search-input"}, "input_text": "router", "target_html": "Search", "ground_truth": {"screenshot": "evaluation/ground_truth/task_79_gt.png", "description": "The word 'router' has been entered and search initiated"}} -{"web_name": "Redis Documentation", "id": "redis_type_1", "task": "Type 'caching' into the search box", "web": "https://redis.io/docs/", "element_type": "input", "interaction": "type", "target_element": {"type": "id", "value": "docsearch"}, "input_text": "caching", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_80_gt.png", "description": "The word 'caching' has been typed in the search box"}} -{"web_name": "Python Documentation", "id": "python_type_2", "task": "Type 'list comprehension' into the search box", "web": "https://docs.python.org/3/", "element_type": "input", "interaction": "type", "target_element": {"type": "id", "value": "search-input"}, "input_text": "list comprehension", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_81_gt.png", "description": "The phrase 'list comprehension' has been typed in the search box"}} -{"web_name": "CPP Reference", "id": "cpp_type_1", "task": "Type 'vector' into the search box", "web": "https://en.cppreference.com/w/", "element_type": "input", "interaction": "type", "target_element": {"type": "id", "value": "searchbox"}, "input_text": "vector", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_82_gt.png", "description": "The word 'vector' has been typed in the search box"}} -{"web_name": "Java Documentation", "id": "java_type_1", "task": "Type 'collections' into the search box", "web": "https://docs.oracle.com/en/", "element_type": "input", "interaction": "type", "target_element": {"type": "id", "value": "search-input"}, "input_text": "collections", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_83_gt.png", "description": "The word 'collections' has been typed in the search box"}} -{"web_name": "PostgreSQL Documentation", "id": "postgres_type_1", "task": "Type 'joins' into the search box", "web": "https://www.postgresql.org/docs/", "element_type": "input", "interaction": "type", "target_element": {"type": "id", "value": "q"}, "input_text": "joins", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_84_gt.png", "description": "The word 'joins' has been typed in the search box"}} -{"web_name": "MySQL Documentation", "id": "mysql_type_1", "task": "Type 'indexes' into the search box", "web": "https://dev.mysql.com/doc/", "element_type": "input", "interaction": "type", "target_element": {"type": "id", "value": "search-input"}, "input_text": "indexes", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_85_gt.png", "description": "The word 'indexes' has been typed in the search box"}} -{"web_name": "Rust Documentation", "id": "rust_type_1", "task": "Type 'ownership' into the search box", "web": "https://doc.rust-lang.org/book/", "element_type": "input", "interaction": "type", "target_element": {"type": "id", "value": "search-input"}, "input_text": "ownership", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_86_gt.png", "description": "The word 'ownership' has been typed in the search box"}} -{"web_name": "TypeScript Documentation", "id": "typescript_type_1", "task": "Type 'interface' into the search box", "web": "https://www.typescriptlang.org/docs/", "element_type": "input", "interaction": "type", "target_element": {"type": "id", "value": "search"}, "input_text": "interface", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_87_gt.png", "description": "The word 'interface' has been typed in the search box"}} -{"web_name": "Scala Documentation", "id": "scala_type_1", "task": "Type 'traits' into the search box", "web": "https://docs.scala-lang.org", "element_type": "input", "interaction": "type", "target_element": {"type": "id", "value": "search-input"}, "input_text": "traits", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_88_gt.png", "description": "The word 'traits' has been typed in the search box"}} -{"web_name": "Swift Blog", "id": "swift_click_1", "task": "Click the Blog link", "web": "https://www.swift.org/documentation/", "element_type": "link", "interaction": "click", "target_element": {"type": "text", "value": "Blog"}, "target_html": "Blog", "ground_truth": {"screenshot": "evaluation/ground_truth/task_89_gt.png", "description": "The Blog link has been clicked"}} -{"web_name": "Python Documentation", "id": "python_click_1", "task": "Click the Modules link", "web": "https://docs.python.org/3/", "element_type": "link", "interaction": "click", "target_element": {"type": "text", "value": "Tutorial"}, "target_html": "modules", "ground_truth": {"screenshot": "evaluation/ground_truth/task_90_gt.png", "description": "The Modules link has been clicked"}} -{"web_name": "Go Documentation", "id": "go_click_1", "task": "Click the Installing Go link", "web": "https://golang.org/doc/", "element_type": "link", "interaction": "click", "target_element": {"type": "text", "value": "Installing Go"}, "target_html": "Installing Go", "ground_truth": {"screenshot": "evaluation/ground_truth/task_91_gt.png", "description": "The Installing Go link has been clicked"}} -{"web_name": "Rust Documentation", "id": "rust_click_1", "task": "Click the Playground link", "web": "https://www.rust-lang.org/learn", "element_type": "link", "interaction": "click", "target_element": {"type": "text", "value": "Playground"}, "target_html": "Playground", "ground_truth": {"screenshot": "evaluation/ground_truth/task_92_gt.png", "description": "The Playgrounf link has been clicked"}} -{"web_name": "TypeScript Documentation", "id": "typescript_click_1", "task": "Click the 'The Basics' link", "web": "https://www.typescriptlang.org/docs/", "element_type": "link", "interaction": "click", "target_element": {"type": "text", "value": "The_basics"}, "target_html": "The Basics", "ground_truth": {"screenshot": "evaluation/ground_truth/task_93_gt.png", "description": "The Basics link has been clicked"}} -{"web_name": "Scala Documentation", "id": "scala_click_1", "task": "Click the Learn link", "web": "https://www.scala-lang.org/", "element_type": "link", "interaction": "click", "target_element": {"type": "text", "value": "Learn"}, "target_html": "Learn", "ground_truth": {"screenshot": "evaluation/ground_truth/task_94_gt.png", "description": "The Learn link has been clicked"}} -{"web_name": "Python Documentation", "id": "python_submit_1", "task": "Type 'dictionary' into the search box and press search", "web": "https://docs.python.org/3/", "element_type": "input", "interaction": "type_submit", "target_element": {"type": "id", "value": "search-input"}, "input_text": "dictionary", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_95_gt.png", "description": "The word 'dictionary' has been entered and search initiated"}} -{"web_name": "Rust Documentation", "id": "rust_submit_1", "task": "Type 'traits' into the search box and press search", "web": "https://doc.rust-lang.org/book/", "element_type": "input", "interaction": "type_submit", "target_element": {"type": "id", "value": "search"}, "input_text": "traits", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_96_gt.png", "description": "The word 'traits' has been entered and search initiated"}} -{"web_name": "Go Documentation", "id": "go_submit_1", "task": "Click the Packages link", "web": "https://golang.org/doc/", "element_type": "link", "interaction": "click", "target_element": {"type": "text", "value": "Packages"}, "target_html": "Packages", "ground_truth": {"screenshot": "evaluation/ground_truth/task_97_gt.png", "description": "The Packages link has been clicked"}} -{"web_name": "TypeScript Documentation", "id": "typescript_submit_1", "task": "Type 'generics' into the search box", "web": "https://www.typescriptlang.org/docs/", "element_type": "input", "interaction": "type", "target_element": {"type": "id", "value": "search"}, "input_text": "generics", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_98_gt.png", "description": "The word 'generics' has been typed into the search box"}} -{"web_name": "Haskell Documentation", "id": "haskell_type_1", "task": "Type 'monads' into the search box", "web": "https://blog.haskell.org/", "element_type": "input", "interaction": "type", "target_element": {"type": "id", "value": "search-input"}, "input_text": "monads", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_99_gt.png", "description": "The word 'monads' has been typed in the search box"}} -{"web_name": "Elixir Documentation", "id": "elixir_type_1", "task": "Type 'phoenix' into the search box", "web": "https://elixir-lang.org/docs.html", "element_type": "input", "interaction": "type", "target_element": {"type": "id", "value": "search-input"}, "input_text": "phoenix", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_100_gt.png", "description": "The word 'phoenix' has been typed in the search box"}} -{"web_name": "GitHub", "id": "github_search_1", "task": "Type 'tensorflow' in the search box", "web": "https://github.com", "element_type": "input", "interaction": "type", "target_element": {"type": "id", "value": "query-builder-test"}, "input_text": "tensorflow", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_151_gt.png", "description": "The word 'tensorflow' has been entered in the GitHub search box"}} -{"web_name": "ESPN", "id": "espn_nba_1", "task": "Click the NBA section", "web": "https://www.espn.com", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "global-nav-nba"}, "target_html": "NBA", "ground_truth": {"screenshot": "evaluation/ground_truth/task_152_gt.png", "description": "The NBA section has been clicked"}} -{"web_name": "Coursera", "id": "coursera_search_1", "task": "Search for 'machine learning' and press enter", "web": "https://www.coursera.org", "element_type": "input", "interaction": "type_submit", "target_element": {"type": "id", "value": "search-input"}, "input_text": "machine learning", "target_html": " \n ", "ground_truth": {"screenshot": "evaluation/ground_truth/task_153_gt.png", "description": "The search term 'machine learning' has been entered and search initiated"}} -{"web_name": "Google Flights", "id": "flights_dest_1", "task": "Type 'JFK' in the Where to field", "web": "https://www.google.com/flights", "element_type": "input", "interaction": "type", "target_element": {"type": "id", "value": "destination-input"}, "input_text": "JFK", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_154_gt.png", "description": "JFK has been entered in the Where to field"}} -{"web_name": "Google Search", "id": "google_search_1", "task": "Type 'weather today' and press enter", "web": "https://www.google.com", "element_type": "input", "interaction": "type_submit", "target_element": {"type": "id", "value": "APjFqb"}, "input_text": "weather today", "target_html": " \n ", "ground_truth": {"screenshot": "evaluation/ground_truth/task_155_gt.png", "description": "The search term 'weather today' has been entered and search initiated"}} -{"web_name": "Huggingface", "id": "hf_models_1", "task": "Click the Models tab", "web": "https://huggingface.co", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "models-tab"}, "target_html": " Models", "ground_truth": {"screenshot": "evaluation/ground_truth/task_156_gt.png", "description": "The Models tab has been clicked"}} -{"web_name": "Wolfram Alpha", "id": "wolfram_calc_1", "task": "Type '2+2' and press enter", "web": "https://www.wolframalpha.com", "element_type": "input", "interaction": "type_submit", "target_element": {"type": "id", "value": "query-input"}, "input_text": "2+2", "target_html": " \n ", "ground_truth": {"screenshot": "evaluation/ground_truth/task_157_gt.png", "description": "The calculation '2+2' has been entered and search initiated"}} -{"web_name": "GitHub", "id": "github_repo_1", "task": "Click the Pricing tab", "web": "https://github.com", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "pricing-requests-tab"}, "target_html": "Try GitHub Copilot", "ground_truth": {"screenshot": "evaluation/ground_truth/task_158_gt.png", "description": "The try github copilot button has been clicked"}} -{"web_name": "ESPN", "id": "espn_nfl_1", "task": "Click the NFL section", "web": "https://www.espn.com", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "global-nav-nfl"}, "target_html": "\n\t\t\t\t\t\t\n\t\t\t\t\t\t\tNFL\n\t\t\t\t\t\t\tNFL\n\t\t\t\t\t\t\n\t\t\t\t\t", "ground_truth": {"screenshot": "evaluation/ground_truth/task_159_gt.png", "description": "The NFL section has been clicked"}} -{"web_name": "Coursera", "id": "coursera_business_1", "task": "Click the For Business category", "web": "https://www.coursera.org", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "business-category"}, "target_html": "For Businesses", "ground_truth": {"screenshot": "evaluation/ground_truth/task_160_gt.png", "description": "The For Business category has been clicked"}} -{"web_name": "Google Flights", "id": "flights_origin_1", "task": "Type 'LAX' in the Where From", "web": "https://www.google.com/flights", "element_type": "input", "interaction": "type", "target_element": {"type": "id", "value": "origin-input"}, "input_text": "LAX", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_161_gt.png", "description": "LAX has been entered in the Where from"}} -{"web_name": "Huggingface", "id": "hf_datasets_1", "task": "Click the Datasets tab", "web": "https://huggingface.co", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "datasets-tab"}, "target_html": " Datasets", "ground_truth": {"screenshot": "evaluation/ground_truth/task_162_gt.png", "description": "The Datasets tab has been clicked"}} -{"web_name": "Wolfram Alpha", "id": "wolfram_integral_1", "task": "Type 'integrate x^2' and press enter", "web": "https://www.wolframalpha.com", "element_type": "input", "interaction": "type_submit", "target_element": {"type": "id", "value": "query-input"}, "input_text": "integrate x^2", "target_html": " \n \n ", "ground_truth": {"screenshot": "evaluation/ground_truth/task_163_gt.png", "description": "The query 'integrate x^2' has been entered and search initiated"}} -{"web_name": "Google Search", "id": "google_search_2", "task": "Search for 'news today' and press enter", "web": "https://www.google.com", "element_type": "input", "interaction": "type_submit", "target_element": {"type": "id", "value": "APjFqb"}, "input_text": "news today", "target_html": " \n ", "ground_truth": {"screenshot": "evaluation/ground_truth/task_164_gt.png", "description": "The search term 'news today' has been entered and search initiated"}} -{"web_name": "GitHub", "id": "github_issues_1", "task": "Click the Try Github Copilot button", "web": "https://github.com", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "github-copilot-tab"}, "target_html": "Try GitHub Copilot", "ground_truth": {"screenshot": "evaluation/ground_truth/task_165_gt.png", "description": "The try github copilot button has been clicked"}} -{"web_name": "ESPN", "id": "espn_mlb_1", "task": "Click the MLB section", "web": "https://www.espn.com", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "global-nav-mlb"}, "target_html": "MLB", "ground_truth": {"screenshot": "evaluation/ground_truth/task_166_gt.png", "description": "The MLB section has been clicked"}} -{"web_name": "Coursera", "id": "coursera_cs_1", "task": "Click the For University category", "web": "https://www.coursera.org", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "university-category"}, "target_html": "For Universities", "ground_truth": {"screenshot": "evaluation/ground_truth/task_167_gt.png", "description": "The For university category has been clicked"}} -{"web_name": "Google Flights", "id": "flights_roundtrip_1", "task": "Click the Round trip option", "web": "https://www.google.com/flights", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "roundtrip"}, "target_html": "
    ", "ground_truth": {"screenshot": "evaluation/ground_truth/task_168_gt.png", "description": "The Round trip option has been clicked"}} -{"web_name": "Huggingface", "id": "hf_spaces_1", "task": "Click the Spaces tab", "web": "https://huggingface.co", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "spaces-tab"}, "target_html": " Spaces", "ground_truth": {"screenshot": "evaluation/ground_truth/task_169_gt.png", "description": "The Spaces tab has been clicked"}} -{"web_name": "Wolfram Alpha", "id": "wolfram_derivative_1", "task": "Type 'derivative of sin(x)' and press enter", "web": "https://www.wolframalpha.com", "element_type": "input", "interaction": "type_submit", "target_element": {"type": "id", "value": "query-input"}, "input_text": "derivative of sin(x)", "target_html": " \n \n ", "ground_truth": {"screenshot": "evaluation/ground_truth/task_170_gt.png", "description": "The query 'derivative of sin(x)' has been entered and search initiated"}} -{"web_name": "Google Search", "id": "google_search_3", "task": "Search for 'best schools in san francisco' and press enter", "web": "https://www.google.com", "element_type": "input", "interaction": "type_submit", "target_element": {"type": "id", "value": "APjFqb"}, "input_text": "best schools in san francisco", "target_html": "\n", "ground_truth": {"screenshot": "evaluation/ground_truth/task_171_gt.png", "description": "The search term 'best schools in san francisco' has been entered and search initiated"}} -{"web_name": "GitHub", "id": "github_marketplace_1", "task": "Click the sign up", "web": "https://github.com", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "sign-up-tab"}, "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_172_gt.png", "description": "The sign up tab has been clicked"}} -{"web_name": "ESPN", "id": "espn_nhl_1", "task": "Click the NHL section", "web": "https://www.espn.com", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "global-nav-nhl"}, "target_html": "NHL", "ground_truth": {"screenshot": "evaluation/ground_truth/task_173_gt.png", "description": "The NHL section has been clicked"}} -{"web_name": "Coursera", "id": "coursera_data_1", "task": "Click the online degrees category", "web": "https://www.coursera.org", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "online–degrees-category"}, "target_html": "Online Degrees", "ground_truth": {"screenshot": "evaluation/ground_truth/task_174_gt.png", "description": "The online degrees category has been clicked"}} -{"web_name": "Google Flights", "id": "flights_oneway_1", "task": "Click the economy option", "web": "https://www.google.com/flights", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "economy"}, "target_html": "
    ", "ground_truth": {"screenshot": "evaluation/ground_truth/task_175_gt.png", "description": "The economy option has been clicked"}} -{"web_name": "Huggingface", "id": "hf_search_1", "task": "Type 'bert' in the search box", "web": "https://huggingface.co", "element_type": "input", "interaction": "type", "target_element": {"type": "id", "value": "search-input"}, "input_text": "bert", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_176_gt.png", "description": "The word 'bert' has been entered in the search box"}} -{"web_name": "Wolfram Alpha", "id": "wolfram_plot_1", "task": "Type 'plot sin(x)' and press enter", "web": "https://www.wolframalpha.com", "element_type": "input", "interaction": "type_submit", "target_element": {"type": "id", "value": "query-input"}, "input_text": "plot sin(x)", "target_html": " \n ", "ground_truth": {"screenshot": "evaluation/ground_truth/task_177_gt.png", "description": "The query 'plot sin(x)' has been entered and search initiated"}} -{"web_name": "Google Search", "id": "google_search_4", "task": "Search for 'movies 2024' and press enter", "web": "https://www.google.com", "element_type": "input", "interaction": "type_submit", "target_element": {"type": "id", "value": "APjFqb"}, "input_text": "movies 2024", "target_html": " \n ", "ground_truth": {"screenshot": "evaluation/ground_truth/task_178_gt.png", "description": "The search term 'movies 2024' has been entered and search initiated"}} -{"web_name": "GitHub", "id": "github_explore_1", "task": "type 'example@test.com' in the enter your email box and click sign up for GitHub", "web": "https://github.com", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "sign-up-tab"}, "target_html": " \n ", "ground_truth": {"screenshot": "evaluation/ground_truth/task_179_gt.png", "description": "'example@test.com' has been entered and the button has been clicked"}} -{"web_name": "ESPN", "id": "espn_soccer_1", "task": "Click the Soccer section", "web": "https://www.espn.com", "element_type": "link", "interaction": "click", "target_element": {"type": "id", "value": "global-nav-soccer"}, "target_html": "SoccerSoccer", "ground_truth": {"screenshot": "evaluation/ground_truth/task_180_gt.png", "description": "The Soccer section has been clicked"}} -{"web_name": "GitHub", "id": "github_explore_1", "task": "type 'example@test.com' in the enter your email box and click sign up for GitHub", "web": "https://github.com", "element_type": "input", "interaction": "type", "target_element": {"type": "id", "value": "hero_user_email"}, "input_text": "example@test.com", "target_html": "", "ground_truth": {"screenshot": "evaluation/ground_truth/task_179_gt.png", "description": "'example@test.com' has been entered and the button has been clicked"}} \ No newline at end of file diff --git a/data/evaluation_output.jsonl b/data/evaluation_output.jsonl deleted file mode 100644 index de0aec7..0000000 --- a/data/evaluation_output.jsonl +++ /dev/null @@ -1,5 +0,0 @@ -{ - "total_tasks": 80, - "successful_tasks": 0, - "evaluations": [] -} \ No newline at end of file