codex-benchmark / manifest.json
yzzhao's picture
Publish paired SIMPLE instruction revisions with preserved native evidence
efae0a1 verified
Raw History Blame Contribute Delete
3.48 kB
{
".gitattributes": "51dec59a208c8656ce7d6614b7b547022f7a4720b1cdad6a20aeeda717ec090b",
"DATA_FORMAT.md": "e2fd4f6b5c8be9d9e008db7d0c1f5d52b419d68328a1c86625c9f67c49b03403",
"README.md": "c2072205759773d80bbc173f03e69da48abec58ae20a218f87dda4c5d8777bc7",
"REPORT.md": "7717a341da6488a163b6982f14f8248186a78a62caf657b08cb010330d64d769",
"THIRD_PARTY_NOTICES.md": "8aa8e3db100d7a570931c5d87f44f78705b42cf17e8147016b35e9aeddb06bba",
"app.js": "872d57ccb8fab7c996443d78e5fcb757831bb8100ffd803109f55d4af4854177",
"attempt-history.json": "928e53e66edf104fa6d27ad7630aae102a25f33b5fe2841c70f1867f29e70bb8",
"catalog/task06/01-xmove-pick/task.yaml": "8a75a1ad3200a278b9159788433c0398ca16c4b01959086a651af325c2dc4c0c",
"catalog/task06/02-transfer-between-tables/task.yaml": "4d582260a03b2d6fc3d4516c488b580b8ff926f307968ca9d5a6b961c7a1729e",
"catalog/task06/03-bend-pick/task.yaml": "e99d597dee2a06a0afc889d230b5db050974f1a2bdfe764a881e895213731cab",
"catalog/task06/04-bend-pick-and-place/task.yaml": "9943d0d6f74996ead10611304620430c8f3fb3d1cfcd6e5da6a15eb4345f7ecb",
"catalog/task06/05-bend-handover/task.yaml": "ba55ca57801e786627a9b981db3ac4e007a0ddf64cbf3cccd0252ac9cba0b111",
"catalog/task06/06-handover/task.yaml": "2153c888b800f28c78afcfb05feccf37234ae88fae1bb305f45668ad9c0a2e00",
"catalog/task06/07-pick-and-place-and-hug-container/task.yaml": "30c3e4d743fb523ac8fd5f278b41c73c85cd08469bee4e4f0d2cf8db2dd4a6b0",
"catalog/task06/08-close-door/task.yaml": "a0256216150b375a5ba091179411e6a15ea3a455e50e793a5e479bb1355028b3",
"catalog/task06/09-open-oven/task.yaml": "f7126ed4aa03c922f3b7fbef567be75d9f5080b9219c673b941fa2d03cabb91e",
"catalog/task06/10-open-faucet/task.yaml": "dcdd2228bfd8de298da36798856f5ff59b523c7104118103530eb7a641b52197",
"catalog/task06/11-push-office-chair/task.yaml": "0e2de1c50619b0c58fd939f58362dfc0630f34d4e19587fe4927a2c4e5c1d785",
"catalog/task06/12-open-trash-can/task.yaml": "e02833927892caa9c40ed193348aab1858e6ae6208c4c04892dec8eae4ad45f0",
"comparison.json": "41ac8e73537d3866ad37188ed82e53dae6c51bb1d87414ee6406ee7479b2d777",
"data.json": "2283435d7f15c50d747eb5e231ede975757bfaa6cba15c6495aa7c1667cec9a6",
"episodes.csv": "f8262dfb6fc34aa549282d2e4983ffd3c97e3002a9259bff3d562010a2137a5f",
"episodes.json": "007cf098118cc2c2a111e0480db329d96fd91b23aed0099aae2737d7ba814e6e",
"failure-reviews.json": "c66a997c9ecd6f7f43f130a8a33cd64c7a5b2049033e9ccde653ee30e4796f23",
"favicon.svg": "46063791218655f70c828ef71a1232a34fd38181da938338badec929ad226819",
"index.html": "d29e3b0133b9af6378b8b3ab7a6bc04f8f985eff46a409078c4f8e6a521edfc2",
"licenses/LIBERO-LICENSE.txt": "e2885fd30a08381b799c4a33385522b23d637b4051b8f9a7f9f2519944b68ff6",
"licenses/RoboDojo-LICENSE.txt": "7794bb06af8fe5485ca912454ad1665ccd7846c45f9c2b1258658e480948cdbe",
"licenses/RoboTwin-LICENSE.txt": "c695d421718e54e6f3a60858f0c601125c3ecc60c199332c15947360561e2a9f",
"licenses/robocasa-LICENSE.txt": "5da18670b3f00c59847b1ded9c28dee59940d963b1e03b528b0108d9c5a09885",
"licenses/robosuite-LICENSE.txt": "177978cbece0a4c454c2aaec5b3f145b39270814874c43109da9e829c39d9cba",
"protocol.json": "8945b054460c822ed8e443487ec7f8d3ba65bf9c37242372f963d5f5865c6cea",
"style.css": "dd31b30951c220ebb82bc96224b5e640913945679e42b2e0a42e2c373a329e6c",
"summary.json": "3ffb3acaba725be116e5bf35c3240e100e8827029116d8c0ff73b9718f5500aa",
"task-index.json": "54f6e5004261b999d2823a2ac74e71ab913cb9766a52fbdc1703e0ecb6f2360d"
}