vodorod/Dorod-Sky
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Webvoyager dataset modification (#1570)

Browse Source
This commit is contained in:
Shuchang Zheng
2025-01-15 15:02:56 -08:00
committed by GitHub
parent 9fc4ee6b2e
commit 5687fa4e52
3 changed files with 69 additions and 69 deletions
Download Patch File Download Diff File Expand all files Collapse all files

80
evaluation/datasets/webvoyager_reference_answer.json
View File

@@ -35,7 +35,7 @@
{
"id": 6,
"type": "possible",
"ans": "'Spinach Lasagna', 4.7-star, 501 reviews"
"ans": "'<recipe name>', 4.0+ star, 500+ reviews"
},
{
"id": 7,
@@ -90,12 +90,12 @@
{
"id": 17,
"type": "golden",
"ans": "Easy to make and very delicious"
"ans": "<review content>"
},
{
"id": 18,
"type": "possible",
"ans": "'Eggplant Lasagna', 4.7-star, 305 reviews"
"ans": "'<recipe name>', 4.5+ star, 300+ reviews"
},
{
"id": 19,
@@ -285,7 +285,7 @@
{
"id": 10,
"type": "possible",
"ans": "Sony Playstation PS4 1TB Black Console; 2-Year Protection for $30.99"
"ans": "Sony Playstation PS4; 2-Year Protection for $20 to $40"
},
{
"id": 11,
@@ -295,7 +295,7 @@
{
"id": 12,
"type": "possible",
"ans": "Worth every penny"
"ans": "<review content>"
},
{
"id": 13,
@@ -455,7 +455,7 @@
{
"id": 2,
"type": "possible",
"ans": "14 Pro: Available at authorized resellers, A16 Bionic chip, 6-core CPU, 5-core GPU, 16-core Neural Engine; 15 Pro: Starting at $999, A17 Pro chip, 6-core CPU, 6-core GPU, 16-core Neural Engine"
"ans": "16 Pro:<price>, <chip information>; 16: <price>, <chip information>"
},
{
"id": 3,
@@ -470,7 +470,7 @@
{
"id": 5,
"type": "possible",
"ans": "iPhone 15 ($799) or pro ($999) or pro Max ($1199); September 22, 2023"
"ans": "<iPhone model>, <price>"
},
{
"id": 6,
@@ -500,7 +500,7 @@
{
"id": 11,
"type": "possible",
"ans": "sixth-generation iPad Pro 11\u2011inch, iPad Pro 12.9\u2011inch; release date: October 26, 2022; base storage capacity 128 GB, starting price $799"
"ans": "<iPad model>, <starting price>, <base storage capacity>"
},
{
"id": 12,
@@ -525,7 +525,7 @@
{
"id": 16,
"type": "possible",
"ans": "2 types, price difference $10"
"ans": "2 types, price difference $50"
},
{
"id": 17,
@@ -540,7 +540,7 @@
{
"id": 19,
"type": "golden",
"ans": "If you can dream it, Mac can do it; Mind-blowing. Head-turning"
"ans": "<Mac slogan>; <Macbook pro slogan>"
},
{
"id": 20,
@@ -550,17 +550,17 @@
{
"id": 21,
"type": "possible",
"ans": "128GB, 256GB, 512GB, 1TB, and 2TB"
"ans": "256GB, 512GB, 1TB, and 2TB"
},
{
"id": 22,
"type": "possible",
"ans": "iPhone 13 Pro Max, Up to $500"
"ans": "iPhone 13 Pro Max, $3000 to $500"
},
{
"id": 23,
"type": "possible",
"ans": "Apple Watch SE From $249, Apple Watch Series 9 From $399"
"ans": "Apple Watch SE From $249, Apple Watch Series 10 From $399"
},
{
"id": 24,
@@ -575,12 +575,12 @@
{
"id": 26,
"type": "possible",
"ans": "4K video recording at 24 fps, 25 fps, 30 fps, or 60 fps"
"ans": "4K video recording at 60 fps"
},
{
"id": 27,
"type": "possible",
"ans": "Available in multiple colors: Space Gray, Blue, Yellow, White, and Orange."
"ans": "Available in multiple colors: Midnight, Blue, Yellow, White, and Orange."
},
{
"id": 28,
@@ -595,7 +595,7 @@
{
"id": 30,
"type": "possible",
"ans": "11-inch, 128GB from $799, 256GB from $899, 512GB from $1099, 1TB from $1499, and 2TB from $1899."
"ans": "11-inch, 256GB from <price>, 512GB from <price>, 1TB from <price>, and 2TB from <price>"
},
{
"id": 31,
@@ -725,7 +725,7 @@
{
"id": 12,
"type": "golden",
"ans": "3"
"ans": "3 to 5"
},
{
"id": 13,
@@ -735,7 +735,7 @@
{
"id": 14,
"type": "golden",
"ans": "3"
"ans": "4"
},
{
"id": 15,
@@ -810,7 +810,7 @@
{
"id": 29,
"type": "possible",
"ans": "240+ (search by title)"
"ans": "212 (search by title)"
},
{
"id": 30,
@@ -820,7 +820,7 @@
{
"id": 31,
"type": "golden",
"ans": "7 papers"
"ans": "2 papers"
},
{
"id": 32,
@@ -895,7 +895,7 @@
{
"id": 2,
"type": "possible",
"ans": "<article> (within the last 2 days)"
"ans": "<article> (within the last 2 months)"
},
{
"id": 3,
@@ -945,7 +945,7 @@
{
"id": 12,
"type": "possible",
"ans": "ramen, Tokyo"
"ans": "<food>, <region>"
},
{
"id": 13,
@@ -1630,7 +1630,7 @@
{
"id": 17,
"type": "possible",
"ans": "23"
"ans": "30 to 50"
},
{
"id": 18,
@@ -1690,7 +1690,7 @@
{
"id": 29,
"type": "possible",
"ans": "$399/year, discount: 59 / month * 12 - 399 = 309; Google, IBM, and Imperial College London ..."
"ans": "<price>; Google, Microsoft, and IBM..."
},
{
"id": 30,
@@ -1700,7 +1700,7 @@
{
"id": 31,
"type": "possible",
"ans": "52.6%"
"ans": "56.81%"
},
{
"id": 32,
@@ -1805,7 +1805,7 @@
{
"id": 9,
"type": "golden",
"ans": "10 teams have Los Angeles in their name; 2 teams are NBA"
"ans": "9 teams have Los Angeles in their name; 1 teams are NBA"
},
{
"id": 10,
@@ -1845,7 +1845,7 @@
{
"id": 17,
"type": "golden",
"ans": "Boston Celtics; San Antonio Spurs"
"ans": "<team 1>; <team 2>"
},
{
"id": 18,
@@ -1855,7 +1855,7 @@
{
"id": 19,
"type": "golden",
"ans": "Jrue Holiday"
"ans": "Jaylen Brown"
},
{
"id": 20,
@@ -1895,7 +1895,7 @@
{
"id": 27,
"type": "golden",
"ans": "30 teams in search results, 1 team Vegas Golden Knights (NHL)"
"ans": "31 teams in search results, 1 team Vegas Golden Knights (NHL)"
},
{
"id": 28,
@@ -1915,7 +1915,7 @@
{
"id": 31,
"type": "golden",
"ans": "Carlos Rodon, 255 lbs"
"ans": "Paul Goldschmidt, 225 lbs"
},
{
"id": 32,
@@ -1945,7 +1945,7 @@
{
"id": 37,
"type": "possible",
"ans": "1471"
"ans": "1471 or more"
},
{
"id": 38,
@@ -1975,7 +1975,7 @@
{
"id": 43,
"type": "possible",
"ans": "espnW Rankings Class of 2023, Judea Watkins from USC, Mikaylah Williams from LSU, Jadyn Donovan from Duke"
"ans": "espnW Rankings Class of 2025, Aaliyah Chavez, Sienna Betts from UCLA, Jasmine Davidson from USC"
}
]
},
@@ -2055,7 +2055,7 @@
{
"id": 14,
"type": "possible",
"ans": "bpasero; jrieken; mjbvz"
"ans": "bpasero; jrieken; Tyriar"
},
{
"id": 15,
@@ -2150,7 +2150,7 @@
{
"id": 33,
"type": "possible",
"ans": "Philips builds and deploys digital health technology faster with innersource on GitHub. Shopify keeps pushing eCommerce forward with help from GitHub tools."
"ans": "Duolingo boosts developer speed by 25% with GitHub Copilot. "
},
{
"id": 34,
@@ -2175,7 +2175,7 @@
{
"id": 38,
"type": "golden",
"ans": "WerWolv/ImHex"
"ans": "sherlock-project/sherlock"
},
{
"id": 39,
@@ -2685,7 +2685,7 @@
{
"id": 13,
"type": "possible",
"ans": "Strange Planet, 2023"
"ans": "iCarly Reboot"
},
{
"id": 14,
@@ -2750,7 +2750,7 @@
{
"id": 26,
"type": "possible",
"ans": "RAM 8 GB; Processor: Multicore Intel\u00ae or Apple Silicon processor (2 GHz or faster processor with SSE 4.2 or later) with 64-bit support; Operating system, macOS Big Sur (version 11.0) or later; Graphics card, GPU with Metal support, 1.5 GB of GPU memory ..."
"ans": "<hardware information> (Mac) ..."
},
{
"id": 27,
@@ -2780,7 +2780,7 @@
{
"id": 32,
"type": "possible",
"ans": "Manchester City Football Club; June 10, 2023; Atat\u00fcrk Olympic Stadium, Istanbul, Turkey"
"ans": "The final was held in London on June 1, 2024, and the winner was Real Madrid."
},
{
"id": 33,
@@ -2810,7 +2810,7 @@
{
"id": 38,
"type": "possible",
"ans": "next: April 8, 2024. The one after that will take place on August 23, 2044."
"ans": "next: August 23, 2044. The one after that will take place on August 12, 2045."
},
{
"id": 39,
@@ -2970,7 +2970,7 @@
{
"id": 26,
"type": "possible",
"ans": "PhilipTheGreat/DiabloGPT-small-Traveller, GPT2LMHeadModel, 510 MB"
"ans": "<model> (generating travel chats), <model name>, <model size>, <model trainning framework>"
},
{
"id": 27,