Download eval_diagnostic.json from knpatil/laya-browser-agent: direct link, hf CLI and curl.
- Browser
- Download file 36 kB
-
https://huggingface.co/knpatil/laya-browser-agent/resolve/main/eval_diagnostic.json
- Command line
-
hf download hf://knpatil/laya-browser-agent/eval_diagnostic.json
-
curl -L -o eval_diagnostic.json https://huggingface.co/knpatil/laya-browser-agent/resolve/main/eval_diagnostic.json
36 kB
| { | |
| "summary": { | |
| "total_decisions": 244, | |
| "jev_failures_count": 22, | |
| "laya_failures_count": 44, | |
| "laya_better_count": 13, | |
| "jev_better_count": 35 | |
| }, | |
| "laya_better_than_jev": [ | |
| { | |
| "case_idx": 2, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "operation", | |
| "qtype": "choice", | |
| "instructions": "Advance goal 'Find one-way flights from Sydney to Melbourne on Nov 5' using one immediate operation.", | |
| "gold": "TYPE_TEXT", | |
| "laya_pred": "TYPE_TEXT", | |
| "laya_conf": 0.873, | |
| "laya_correct": true, | |
| "jev_pred": "CLICK", | |
| "jev_conf": 0.84, | |
| "jev_correct": false | |
| }, | |
| { | |
| "case_idx": 6, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "operation", | |
| "qtype": "choice", | |
| "instructions": "Advance goal 'Find one-way flights from Sydney to Melbourne on Dec 22' using one immediate operation.", | |
| "gold": "TYPE_TEXT", | |
| "laya_pred": "TYPE_TEXT", | |
| "laya_conf": 0.874, | |
| "laya_correct": true, | |
| "jev_pred": "CLICK", | |
| "jev_conf": 0.83, | |
| "jev_correct": false | |
| }, | |
| { | |
| "case_idx": 10, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "operation", | |
| "qtype": "choice", | |
| "instructions": "Advance goal 'Find one-way flights from New York to Boston on Jan 15' using one immediate operation.", | |
| "gold": "TYPE_TEXT", | |
| "laya_pred": "TYPE_TEXT", | |
| "laya_conf": 0.873, | |
| "laya_correct": true, | |
| "jev_pred": "CLICK", | |
| "jev_conf": 0.78, | |
| "jev_correct": false | |
| }, | |
| { | |
| "case_idx": 11, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "operation", | |
| "qtype": "choice", | |
| "instructions": "Advance goal 'Find one-way flights from Sydney to Melbourne on Oct 12' using one immediate operation.", | |
| "gold": "TYPE_TEXT", | |
| "laya_pred": "TYPE_TEXT", | |
| "laya_conf": 0.874, | |
| "laya_correct": true, | |
| "jev_pred": "CLICK", | |
| "jev_conf": 0.84, | |
| "jev_correct": false | |
| }, | |
| { | |
| "case_idx": 14, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "operation", | |
| "qtype": "choice", | |
| "instructions": "Advance goal 'Find one-way flights from Sydney to Melbourne on Jan 15' using one immediate operation.", | |
| "gold": "TYPE_TEXT", | |
| "laya_pred": "TYPE_TEXT", | |
| "laya_conf": 0.873, | |
| "laya_correct": true, | |
| "jev_pred": "CLICK", | |
| "jev_conf": 0.8, | |
| "jev_correct": false | |
| }, | |
| { | |
| "case_idx": 24, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "operation", | |
| "qtype": "choice", | |
| "instructions": "Advance goal 'Find one-way flights from Berlin to Madrid on Oct 12' using one immediate operation.", | |
| "gold": "TYPE_TEXT", | |
| "laya_pred": "TYPE_TEXT", | |
| "laya_conf": 0.874, | |
| "laya_correct": true, | |
| "jev_pred": "CLICK", | |
| "jev_conf": 0.85, | |
| "jev_correct": false | |
| }, | |
| { | |
| "case_idx": 44, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "operation", | |
| "qtype": "choice", | |
| "instructions": "Advance goal 'Find one-way flights from Tokyo to Kyoto on Feb 28' using one immediate operation.", | |
| "gold": "TYPE_TEXT", | |
| "laya_pred": "TYPE_TEXT", | |
| "laya_conf": 0.873, | |
| "laya_correct": true, | |
| "jev_pred": "CLICK", | |
| "jev_conf": 0.76, | |
| "jev_correct": false | |
| }, | |
| { | |
| "case_idx": 45, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "operation", | |
| "qtype": "choice", | |
| "instructions": "Advance goal 'Find one-way flights from Berlin to Madrid on Jan 15' using one immediate operation.", | |
| "gold": "TYPE_TEXT", | |
| "laya_pred": "TYPE_TEXT", | |
| "laya_conf": 0.873, | |
| "laya_correct": true, | |
| "jev_pred": "CLICK", | |
| "jev_conf": 0.82, | |
| "jev_correct": false | |
| }, | |
| { | |
| "case_idx": 54, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "operation", | |
| "qtype": "choice", | |
| "instructions": "Advance goal 'Find one-way flights from New York to Boston on Oct 12' using one immediate operation.", | |
| "gold": "TYPE_TEXT", | |
| "laya_pred": "TYPE_TEXT", | |
| "laya_conf": 0.874, | |
| "laya_correct": true, | |
| "jev_pred": "CLICK", | |
| "jev_conf": 0.76, | |
| "jev_correct": false | |
| }, | |
| { | |
| "case_idx": 56, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "operation", | |
| "qtype": "choice", | |
| "instructions": "Advance goal 'Find one-way flights from New York to Boston on Feb 28' using one immediate operation.", | |
| "gold": "TYPE_TEXT", | |
| "laya_pred": "TYPE_TEXT", | |
| "laya_conf": 0.874, | |
| "laya_correct": true, | |
| "jev_pred": "CLICK", | |
| "jev_conf": 0.73, | |
| "jev_correct": false | |
| }, | |
| { | |
| "case_idx": 57, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "operation", | |
| "qtype": "choice", | |
| "instructions": "Advance goal 'Find one-way flights from Sydney to Melbourne on Jan 15' using one immediate operation.", | |
| "gold": "TYPE_TEXT", | |
| "laya_pred": "TYPE_TEXT", | |
| "laya_conf": 0.873, | |
| "laya_correct": true, | |
| "jev_pred": "CLICK", | |
| "jev_conf": 0.8, | |
| "jev_correct": false | |
| }, | |
| { | |
| "case_idx": 64, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "operation", | |
| "qtype": "choice", | |
| "instructions": "Advance goal 'Find one-way flights from Sydney to Melbourne on Nov 5' using one immediate operation.", | |
| "gold": "TYPE_TEXT", | |
| "laya_pred": "TYPE_TEXT", | |
| "laya_conf": 0.873, | |
| "laya_correct": true, | |
| "jev_pred": "CLICK", | |
| "jev_conf": 0.8, | |
| "jev_correct": false | |
| }, | |
| { | |
| "case_idx": 68, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "operation", | |
| "qtype": "choice", | |
| "instructions": "Advance goal 'Find one-way flights from New York to Boston on Oct 12' using one immediate operation.", | |
| "gold": "TYPE_TEXT", | |
| "laya_pred": "TYPE_TEXT", | |
| "laya_conf": 0.874, | |
| "laya_correct": true, | |
| "jev_pred": "CLICK", | |
| "jev_conf": 0.78, | |
| "jev_correct": false | |
| } | |
| ], | |
| "jev_better_than_laya": [ | |
| { | |
| "case_idx": 1, | |
| "url": "https://en.wikipedia.org/wiki/Main_Page", | |
| "title": "Wikipedia, the free encyclopedia", | |
| "qid": "click_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is CLICK for goal 'Lookup G\u00f6del's incompleteness theorems on Wikipedia'.", | |
| "gold": "1", | |
| "laya_pred": "3", | |
| "laya_conf": 0.334, | |
| "laya_correct": false, | |
| "jev_pred": "1", | |
| "jev_conf": 0.34, | |
| "jev_correct": true | |
| }, | |
| { | |
| "case_idx": 2, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "click_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is CLICK for goal 'Find one-way flights from Sydney to Melbourne on Nov 5'.", | |
| "gold": "1", | |
| "laya_pred": "5", | |
| "laya_conf": 0.201, | |
| "laya_correct": false, | |
| "jev_pred": "1", | |
| "jev_conf": 0.94, | |
| "jev_correct": true | |
| }, | |
| { | |
| "case_idx": 3, | |
| "url": "https://en.wikipedia.org/wiki/Main_Page", | |
| "title": "Wikipedia, the free encyclopedia", | |
| "qid": "click_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is CLICK for goal 'Lookup G\u00f6del's incompleteness theorems on Wikipedia'.", | |
| "gold": "1", | |
| "laya_pred": "3", | |
| "laya_conf": 0.334, | |
| "laya_correct": false, | |
| "jev_pred": "1", | |
| "jev_conf": 0.42, | |
| "jev_correct": true | |
| }, | |
| { | |
| "case_idx": 6, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "click_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is CLICK for goal 'Find one-way flights from Sydney to Melbourne on Dec 22'.", | |
| "gold": "1", | |
| "laya_pred": "5", | |
| "laya_conf": 0.201, | |
| "laya_correct": false, | |
| "jev_pred": "1", | |
| "jev_conf": 0.92, | |
| "jev_correct": true | |
| }, | |
| { | |
| "case_idx": 7, | |
| "url": "https://www.google.com/travel/flights/search?q=zurich+to+london", | |
| "title": "Flights from Zurich to London from $129", | |
| "qid": "click_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is CLICK for goal 'Find flight ticket price from Zurich to London'.", | |
| "gold": "1", | |
| "laya_pred": "3", | |
| "laya_conf": 0.335, | |
| "laya_correct": false, | |
| "jev_pred": "1", | |
| "jev_conf": 0.95, | |
| "jev_correct": true | |
| }, | |
| { | |
| "case_idx": 8, | |
| "url": "https://en.wikipedia.org/wiki/Main_Page", | |
| "title": "Wikipedia, the free encyclopedia", | |
| "qid": "click_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is CLICK for goal 'Lookup G\u00f6del's incompleteness theorems on Wikipedia'.", | |
| "gold": "1", | |
| "laya_pred": "3", | |
| "laya_conf": 0.334, | |
| "laya_correct": false, | |
| "jev_pred": "1", | |
| "jev_conf": 0.46, | |
| "jev_correct": true | |
| }, | |
| { | |
| "case_idx": 9, | |
| "url": "https://en.wikipedia.org/wiki/Main_Page", | |
| "title": "Wikipedia, the free encyclopedia", | |
| "qid": "click_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is CLICK for goal 'Lookup G\u00f6del's incompleteness theorems on Wikipedia'.", | |
| "gold": "1", | |
| "laya_pred": "3", | |
| "laya_conf": 0.334, | |
| "laya_correct": false, | |
| "jev_pred": "1", | |
| "jev_conf": 0.33, | |
| "jev_correct": true | |
| }, | |
| { | |
| "case_idx": 10, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "click_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is CLICK for goal 'Find one-way flights from New York to Boston on Jan 15'.", | |
| "gold": "1", | |
| "laya_pred": "5", | |
| "laya_conf": 0.202, | |
| "laya_correct": false, | |
| "jev_pred": "1", | |
| "jev_conf": 0.91, | |
| "jev_correct": true | |
| }, | |
| { | |
| "case_idx": 11, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "click_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is CLICK for goal 'Find one-way flights from Sydney to Melbourne on Oct 12'.", | |
| "gold": "1", | |
| "laya_pred": "5", | |
| "laya_conf": 0.201, | |
| "laya_correct": false, | |
| "jev_pred": "1", | |
| "jev_conf": 0.9, | |
| "jev_correct": true | |
| }, | |
| { | |
| "case_idx": 13, | |
| "url": "https://en.wikipedia.org/wiki/Main_Page", | |
| "title": "Wikipedia, the free encyclopedia", | |
| "qid": "click_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is CLICK for goal 'Lookup G\u00f6del's incompleteness theorems on Wikipedia'.", | |
| "gold": "1", | |
| "laya_pred": "3", | |
| "laya_conf": 0.334, | |
| "laya_correct": false, | |
| "jev_pred": "1", | |
| "jev_conf": 0.39, | |
| "jev_correct": true | |
| }, | |
| { | |
| "case_idx": 14, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "click_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is CLICK for goal 'Find one-way flights from Sydney to Melbourne on Jan 15'.", | |
| "gold": "1", | |
| "laya_pred": "5", | |
| "laya_conf": 0.201, | |
| "laya_correct": false, | |
| "jev_pred": "1", | |
| "jev_conf": 0.93, | |
| "jev_correct": true | |
| }, | |
| { | |
| "case_idx": 17, | |
| "url": "https://www.google.com/travel/flights/search?q=zurich+to+london", | |
| "title": "Flights from Zurich to London from $129", | |
| "qid": "click_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is CLICK for goal 'Find flight ticket price from Zurich to London'.", | |
| "gold": "1", | |
| "laya_pred": "3", | |
| "laya_conf": 0.335, | |
| "laya_correct": false, | |
| "jev_pred": "1", | |
| "jev_conf": 0.94, | |
| "jev_correct": true | |
| }, | |
| { | |
| "case_idx": 24, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "click_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is CLICK for goal 'Find one-way flights from Berlin to Madrid on Oct 12'.", | |
| "gold": "1", | |
| "laya_pred": "5", | |
| "laya_conf": 0.201, | |
| "laya_correct": false, | |
| "jev_pred": "1", | |
| "jev_conf": 0.87, | |
| "jev_correct": true | |
| }, | |
| { | |
| "case_idx": 25, | |
| "url": "https://www.google.com/travel/flights/search?q=zurich+to+london", | |
| "title": "Flights from Zurich to London from $129", | |
| "qid": "click_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is CLICK for goal 'Find flight ticket price from Zurich to London'.", | |
| "gold": "1", | |
| "laya_pred": "3", | |
| "laya_conf": 0.335, | |
| "laya_correct": false, | |
| "jev_pred": "1", | |
| "jev_conf": 0.94, | |
| "jev_correct": true | |
| }, | |
| { | |
| "case_idx": 26, | |
| "url": "https://www.google.com/travel/flights/search?q=zurich+to+london", | |
| "title": "Flights from Zurich to London from $129", | |
| "qid": "click_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is CLICK for goal 'Find flight ticket price from Zurich to London'.", | |
| "gold": "1", | |
| "laya_pred": "3", | |
| "laya_conf": 0.335, | |
| "laya_correct": false, | |
| "jev_pred": "1", | |
| "jev_conf": 0.93, | |
| "jev_correct": true | |
| }, | |
| { | |
| "case_idx": 27, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Form Filled", | |
| "qid": "type_text_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is TYPE_TEXT for goal 'Find one-way flights from Tokyo to Kyoto on Dec 22'.", | |
| "gold": "1", | |
| "laya_pred": "3", | |
| "laya_conf": 0.335, | |
| "laya_correct": false, | |
| "jev_pred": "1", | |
| "jev_conf": 0.25, | |
| "jev_correct": true | |
| }, | |
| { | |
| "case_idx": 31, | |
| "url": "https://www.google.com/travel/flights/search?q=zurich+to+london", | |
| "title": "Flights from Zurich to London from $129", | |
| "qid": "click_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is CLICK for goal 'Find flight ticket price from Zurich to London'.", | |
| "gold": "1", | |
| "laya_pred": "3", | |
| "laya_conf": 0.335, | |
| "laya_correct": false, | |
| "jev_pred": "1", | |
| "jev_conf": 0.94, | |
| "jev_correct": true | |
| }, | |
| { | |
| "case_idx": 36, | |
| "url": "https://www.google.com/travel/flights/search?q=zurich+to+london", | |
| "title": "Flights from Zurich to London from $129", | |
| "qid": "click_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is CLICK for goal 'Find flight ticket price from Zurich to London'.", | |
| "gold": "1", | |
| "laya_pred": "3", | |
| "laya_conf": 0.335, | |
| "laya_correct": false, | |
| "jev_pred": "1", | |
| "jev_conf": 0.94, | |
| "jev_correct": true | |
| }, | |
| { | |
| "case_idx": 38, | |
| "url": "https://en.wikipedia.org/wiki/Main_Page", | |
| "title": "Wikipedia, the free encyclopedia", | |
| "qid": "click_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is CLICK for goal 'Lookup G\u00f6del's incompleteness theorems on Wikipedia'.", | |
| "gold": "1", | |
| "laya_pred": "3", | |
| "laya_conf": 0.334, | |
| "laya_correct": false, | |
| "jev_pred": "1", | |
| "jev_conf": 0.32, | |
| "jev_correct": true | |
| }, | |
| { | |
| "case_idx": 39, | |
| "url": "https://www.google.com/travel/flights/search?q=zurich+to+london", | |
| "title": "Flights from Zurich to London from $129", | |
| "qid": "click_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is CLICK for goal 'Find flight ticket price from Zurich to London'.", | |
| "gold": "1", | |
| "laya_pred": "3", | |
| "laya_conf": 0.335, | |
| "laya_correct": false, | |
| "jev_pred": "1", | |
| "jev_conf": 0.95, | |
| "jev_correct": true | |
| }, | |
| { | |
| "case_idx": 42, | |
| "url": "https://en.wikipedia.org/wiki/Main_Page", | |
| "title": "Wikipedia, the free encyclopedia", | |
| "qid": "click_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is CLICK for goal 'Lookup G\u00f6del's incompleteness theorems on Wikipedia'.", | |
| "gold": "1", | |
| "laya_pred": "3", | |
| "laya_conf": 0.334, | |
| "laya_correct": false, | |
| "jev_pred": "1", | |
| "jev_conf": 0.45, | |
| "jev_correct": true | |
| }, | |
| { | |
| "case_idx": 44, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "click_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is CLICK for goal 'Find one-way flights from Tokyo to Kyoto on Feb 28'.", | |
| "gold": "1", | |
| "laya_pred": "5", | |
| "laya_conf": 0.201, | |
| "laya_correct": false, | |
| "jev_pred": "1", | |
| "jev_conf": 0.91, | |
| "jev_correct": true | |
| }, | |
| { | |
| "case_idx": 45, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "click_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is CLICK for goal 'Find one-way flights from Berlin to Madrid on Jan 15'.", | |
| "gold": "1", | |
| "laya_pred": "5", | |
| "laya_conf": 0.201, | |
| "laya_correct": false, | |
| "jev_pred": "1", | |
| "jev_conf": 0.88, | |
| "jev_correct": true | |
| }, | |
| { | |
| "case_idx": 49, | |
| "url": "https://www.google.com/travel/flights/search?q=zurich+to+london", | |
| "title": "Flights from Zurich to London from $129", | |
| "qid": "click_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is CLICK for goal 'Find flight ticket price from Zurich to London'.", | |
| "gold": "1", | |
| "laya_pred": "3", | |
| "laya_conf": 0.335, | |
| "laya_correct": false, | |
| "jev_pred": "1", | |
| "jev_conf": 0.94, | |
| "jev_correct": true | |
| }, | |
| { | |
| "case_idx": 50, | |
| "url": "https://en.wikipedia.org/wiki/Main_Page", | |
| "title": "Wikipedia, the free encyclopedia", | |
| "qid": "click_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is CLICK for goal 'Lookup G\u00f6del's incompleteness theorems on Wikipedia'.", | |
| "gold": "1", | |
| "laya_pred": "3", | |
| "laya_conf": 0.334, | |
| "laya_correct": false, | |
| "jev_pred": "1", | |
| "jev_conf": 0.48, | |
| "jev_correct": true | |
| }, | |
| { | |
| "case_idx": 51, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Form Filled", | |
| "qid": "type_text_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is TYPE_TEXT for goal 'Find one-way flights from Tokyo to Kyoto on Jan 15'.", | |
| "gold": "1", | |
| "laya_pred": "3", | |
| "laya_conf": 0.334, | |
| "laya_correct": false, | |
| "jev_pred": "1", | |
| "jev_conf": 0.25, | |
| "jev_correct": true | |
| }, | |
| { | |
| "case_idx": 54, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "click_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is CLICK for goal 'Find one-way flights from New York to Boston on Oct 12'.", | |
| "gold": "1", | |
| "laya_pred": "5", | |
| "laya_conf": 0.201, | |
| "laya_correct": false, | |
| "jev_pred": "1", | |
| "jev_conf": 0.89, | |
| "jev_correct": true | |
| }, | |
| { | |
| "case_idx": 55, | |
| "url": "https://en.wikipedia.org/wiki/Main_Page", | |
| "title": "Wikipedia, the free encyclopedia", | |
| "qid": "click_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is CLICK for goal 'Lookup G\u00f6del's incompleteness theorems on Wikipedia'.", | |
| "gold": "1", | |
| "laya_pred": "3", | |
| "laya_conf": 0.334, | |
| "laya_correct": false, | |
| "jev_pred": "1", | |
| "jev_conf": 0.37, | |
| "jev_correct": true | |
| }, | |
| { | |
| "case_idx": 56, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "click_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is CLICK for goal 'Find one-way flights from New York to Boston on Feb 28'.", | |
| "gold": "1", | |
| "laya_pred": "5", | |
| "laya_conf": 0.202, | |
| "laya_correct": false, | |
| "jev_pred": "1", | |
| "jev_conf": 0.89, | |
| "jev_correct": true | |
| }, | |
| { | |
| "case_idx": 57, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "click_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is CLICK for goal 'Find one-way flights from Sydney to Melbourne on Jan 15'.", | |
| "gold": "1", | |
| "laya_pred": "5", | |
| "laya_conf": 0.201, | |
| "laya_correct": false, | |
| "jev_pred": "1", | |
| "jev_conf": 0.93, | |
| "jev_correct": true | |
| }, | |
| { | |
| "case_idx": 58, | |
| "url": "https://www.google.com/travel/flights/search?q=zurich+to+london", | |
| "title": "Flights from Zurich to London from $129", | |
| "qid": "click_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is CLICK for goal 'Find flight ticket price from Zurich to London'.", | |
| "gold": "1", | |
| "laya_pred": "3", | |
| "laya_conf": 0.335, | |
| "laya_correct": false, | |
| "jev_pred": "1", | |
| "jev_conf": 0.95, | |
| "jev_correct": true | |
| }, | |
| { | |
| "case_idx": 60, | |
| "url": "https://www.google.com/travel/flights/search?q=zurich+to+london", | |
| "title": "Flights from Zurich to London from $129", | |
| "qid": "click_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is CLICK for goal 'Find flight ticket price from Zurich to London'.", | |
| "gold": "1", | |
| "laya_pred": "3", | |
| "laya_conf": 0.335, | |
| "laya_correct": false, | |
| "jev_pred": "1", | |
| "jev_conf": 0.95, | |
| "jev_correct": true | |
| }, | |
| { | |
| "case_idx": 64, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "click_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is CLICK for goal 'Find one-way flights from Sydney to Melbourne on Nov 5'.", | |
| "gold": "1", | |
| "laya_pred": "5", | |
| "laya_conf": 0.201, | |
| "laya_correct": false, | |
| "jev_pred": "1", | |
| "jev_conf": 0.93, | |
| "jev_correct": true | |
| }, | |
| { | |
| "case_idx": 67, | |
| "url": "https://www.google.com/travel/flights/search?q=zurich+to+london", | |
| "title": "Flights from Zurich to London from $129", | |
| "qid": "click_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is CLICK for goal 'Find flight ticket price from Zurich to London'.", | |
| "gold": "1", | |
| "laya_pred": "3", | |
| "laya_conf": 0.335, | |
| "laya_correct": false, | |
| "jev_pred": "1", | |
| "jev_conf": 0.95, | |
| "jev_correct": true | |
| }, | |
| { | |
| "case_idx": 68, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "click_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is CLICK for goal 'Find one-way flights from New York to Boston on Oct 12'.", | |
| "gold": "1", | |
| "laya_pred": "5", | |
| "laya_conf": 0.201, | |
| "laya_correct": false, | |
| "jev_pred": "1", | |
| "jev_conf": 0.91, | |
| "jev_correct": true | |
| } | |
| ], | |
| "jev_failures": [ | |
| { | |
| "case_idx": 2, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "operation", | |
| "qtype": "choice", | |
| "instructions": "Advance goal 'Find one-way flights from Sydney to Melbourne on Nov 5' using one immediate operation.", | |
| "gold": "TYPE_TEXT", | |
| "laya_pred": "TYPE_TEXT", | |
| "laya_conf": 0.873, | |
| "laya_correct": true, | |
| "jev_pred": "CLICK", | |
| "jev_conf": 0.84, | |
| "jev_correct": false | |
| }, | |
| { | |
| "case_idx": 6, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "operation", | |
| "qtype": "choice", | |
| "instructions": "Advance goal 'Find one-way flights from Sydney to Melbourne on Dec 22' using one immediate operation.", | |
| "gold": "TYPE_TEXT", | |
| "laya_pred": "TYPE_TEXT", | |
| "laya_conf": 0.874, | |
| "laya_correct": true, | |
| "jev_pred": "CLICK", | |
| "jev_conf": 0.83, | |
| "jev_correct": false | |
| }, | |
| { | |
| "case_idx": 10, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "operation", | |
| "qtype": "choice", | |
| "instructions": "Advance goal 'Find one-way flights from New York to Boston on Jan 15' using one immediate operation.", | |
| "gold": "TYPE_TEXT", | |
| "laya_pred": "TYPE_TEXT", | |
| "laya_conf": 0.873, | |
| "laya_correct": true, | |
| "jev_pred": "CLICK", | |
| "jev_conf": 0.78, | |
| "jev_correct": false | |
| }, | |
| { | |
| "case_idx": 11, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "operation", | |
| "qtype": "choice", | |
| "instructions": "Advance goal 'Find one-way flights from Sydney to Melbourne on Oct 12' using one immediate operation.", | |
| "gold": "TYPE_TEXT", | |
| "laya_pred": "TYPE_TEXT", | |
| "laya_conf": 0.874, | |
| "laya_correct": true, | |
| "jev_pred": "CLICK", | |
| "jev_conf": 0.84, | |
| "jev_correct": false | |
| }, | |
| { | |
| "case_idx": 12, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Form Filled", | |
| "qid": "type_text_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is TYPE_TEXT for goal 'Find one-way flights from Berlin to Madrid on Feb 28'.", | |
| "gold": "1", | |
| "laya_pred": "3", | |
| "laya_conf": 0.335, | |
| "laya_correct": false, | |
| "jev_pred": "3", | |
| "jev_conf": 0.24, | |
| "jev_correct": false | |
| }, | |
| { | |
| "case_idx": 14, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "operation", | |
| "qtype": "choice", | |
| "instructions": "Advance goal 'Find one-way flights from Sydney to Melbourne on Jan 15' using one immediate operation.", | |
| "gold": "TYPE_TEXT", | |
| "laya_pred": "TYPE_TEXT", | |
| "laya_conf": 0.873, | |
| "laya_correct": true, | |
| "jev_pred": "CLICK", | |
| "jev_conf": 0.8, | |
| "jev_correct": false | |
| }, | |
| { | |
| "case_idx": 16, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Form Filled", | |
| "qid": "type_text_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is TYPE_TEXT for goal 'Find one-way flights from Sydney to Melbourne on Jan 15'.", | |
| "gold": "1", | |
| "laya_pred": "3", | |
| "laya_conf": 0.335, | |
| "laya_correct": false, | |
| "jev_pred": "3", | |
| "jev_conf": 0.32, | |
| "jev_correct": false | |
| }, | |
| { | |
| "case_idx": 23, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Form Filled", | |
| "qid": "type_text_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is TYPE_TEXT for goal 'Find one-way flights from Berlin to Madrid on Feb 28'.", | |
| "gold": "1", | |
| "laya_pred": "3", | |
| "laya_conf": 0.335, | |
| "laya_correct": false, | |
| "jev_pred": "3", | |
| "jev_conf": 0.31, | |
| "jev_correct": false | |
| }, | |
| { | |
| "case_idx": 24, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "operation", | |
| "qtype": "choice", | |
| "instructions": "Advance goal 'Find one-way flights from Berlin to Madrid on Oct 12' using one immediate operation.", | |
| "gold": "TYPE_TEXT", | |
| "laya_pred": "TYPE_TEXT", | |
| "laya_conf": 0.874, | |
| "laya_correct": true, | |
| "jev_pred": "CLICK", | |
| "jev_conf": 0.85, | |
| "jev_correct": false | |
| }, | |
| { | |
| "case_idx": 32, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Form Filled", | |
| "qid": "type_text_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is TYPE_TEXT for goal 'Find one-way flights from Berlin to Madrid on Dec 22'.", | |
| "gold": "1", | |
| "laya_pred": "3", | |
| "laya_conf": 0.335, | |
| "laya_correct": false, | |
| "jev_pred": "3", | |
| "jev_conf": 0.31, | |
| "jev_correct": false | |
| }, | |
| { | |
| "case_idx": 34, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Form Filled", | |
| "qid": "type_text_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is TYPE_TEXT for goal 'Find one-way flights from Tokyo to Kyoto on Feb 28'.", | |
| "gold": "1", | |
| "laya_pred": "3", | |
| "laya_conf": 0.334, | |
| "laya_correct": false, | |
| "jev_pred": "3", | |
| "jev_conf": 0.24, | |
| "jev_correct": false | |
| }, | |
| { | |
| "case_idx": 43, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Form Filled", | |
| "qid": "type_text_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is TYPE_TEXT for goal 'Find one-way flights from Sydney to Melbourne on Feb 28'.", | |
| "gold": "1", | |
| "laya_pred": "3", | |
| "laya_conf": 0.335, | |
| "laya_correct": false, | |
| "jev_pred": "3", | |
| "jev_conf": 0.32, | |
| "jev_correct": false | |
| }, | |
| { | |
| "case_idx": 44, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "operation", | |
| "qtype": "choice", | |
| "instructions": "Advance goal 'Find one-way flights from Tokyo to Kyoto on Feb 28' using one immediate operation.", | |
| "gold": "TYPE_TEXT", | |
| "laya_pred": "TYPE_TEXT", | |
| "laya_conf": 0.873, | |
| "laya_correct": true, | |
| "jev_pred": "CLICK", | |
| "jev_conf": 0.76, | |
| "jev_correct": false | |
| }, | |
| { | |
| "case_idx": 45, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "operation", | |
| "qtype": "choice", | |
| "instructions": "Advance goal 'Find one-way flights from Berlin to Madrid on Jan 15' using one immediate operation.", | |
| "gold": "TYPE_TEXT", | |
| "laya_pred": "TYPE_TEXT", | |
| "laya_conf": 0.873, | |
| "laya_correct": true, | |
| "jev_pred": "CLICK", | |
| "jev_conf": 0.82, | |
| "jev_correct": false | |
| }, | |
| { | |
| "case_idx": 47, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Form Filled", | |
| "qid": "type_text_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is TYPE_TEXT for goal 'Find one-way flights from Sydney to Melbourne on Jan 15'.", | |
| "gold": "1", | |
| "laya_pred": "3", | |
| "laya_conf": 0.335, | |
| "laya_correct": false, | |
| "jev_pred": "3", | |
| "jev_conf": 0.35, | |
| "jev_correct": false | |
| }, | |
| { | |
| "case_idx": 54, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "operation", | |
| "qtype": "choice", | |
| "instructions": "Advance goal 'Find one-way flights from New York to Boston on Oct 12' using one immediate operation.", | |
| "gold": "TYPE_TEXT", | |
| "laya_pred": "TYPE_TEXT", | |
| "laya_conf": 0.874, | |
| "laya_correct": true, | |
| "jev_pred": "CLICK", | |
| "jev_conf": 0.76, | |
| "jev_correct": false | |
| }, | |
| { | |
| "case_idx": 56, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "operation", | |
| "qtype": "choice", | |
| "instructions": "Advance goal 'Find one-way flights from New York to Boston on Feb 28' using one immediate operation.", | |
| "gold": "TYPE_TEXT", | |
| "laya_pred": "TYPE_TEXT", | |
| "laya_conf": 0.874, | |
| "laya_correct": true, | |
| "jev_pred": "CLICK", | |
| "jev_conf": 0.73, | |
| "jev_correct": false | |
| }, | |
| { | |
| "case_idx": 57, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "operation", | |
| "qtype": "choice", | |
| "instructions": "Advance goal 'Find one-way flights from Sydney to Melbourne on Jan 15' using one immediate operation.", | |
| "gold": "TYPE_TEXT", | |
| "laya_pred": "TYPE_TEXT", | |
| "laya_conf": 0.873, | |
| "laya_correct": true, | |
| "jev_pred": "CLICK", | |
| "jev_conf": 0.8, | |
| "jev_correct": false | |
| }, | |
| { | |
| "case_idx": 61, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Form Filled", | |
| "qid": "type_text_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is TYPE_TEXT for goal 'Find one-way flights from Tokyo to Kyoto on Feb 28'.", | |
| "gold": "1", | |
| "laya_pred": "3", | |
| "laya_conf": 0.334, | |
| "laya_correct": false, | |
| "jev_pred": "3", | |
| "jev_conf": 0.3, | |
| "jev_correct": false | |
| }, | |
| { | |
| "case_idx": 62, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Form Filled", | |
| "qid": "type_text_target", | |
| "qtype": "choice", | |
| "instructions": "Choose element index if operation is TYPE_TEXT for goal 'Find one-way flights from Tokyo to Kyoto on Jan 15'.", | |
| "gold": "1", | |
| "laya_pred": "3", | |
| "laya_conf": 0.334, | |
| "laya_correct": false, | |
| "jev_pred": "3", | |
| "jev_conf": 0.25, | |
| "jev_correct": false | |
| }, | |
| { | |
| "case_idx": 64, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "operation", | |
| "qtype": "choice", | |
| "instructions": "Advance goal 'Find one-way flights from Sydney to Melbourne on Nov 5' using one immediate operation.", | |
| "gold": "TYPE_TEXT", | |
| "laya_pred": "TYPE_TEXT", | |
| "laya_conf": 0.873, | |
| "laya_correct": true, | |
| "jev_pred": "CLICK", | |
| "jev_conf": 0.8, | |
| "jev_correct": false | |
| }, | |
| { | |
| "case_idx": 68, | |
| "url": "https://www.google.com/travel/flights?hl=en", | |
| "title": "Google Flights - Search Flights", | |
| "qid": "operation", | |
| "qtype": "choice", | |
| "instructions": "Advance goal 'Find one-way flights from New York to Boston on Oct 12' using one immediate operation.", | |
| "gold": "TYPE_TEXT", | |
| "laya_pred": "TYPE_TEXT", | |
| "laya_conf": 0.874, | |
| "laya_correct": true, | |
| "jev_pred": "CLICK", | |
| "jev_conf": 0.78, | |
| "jev_correct": false | |
| } | |
| ] | |
| } |