# MANIFEST - our 240 vs Zhao, Knezevic & Kaser's published 240 (built 2026-09-05 08:25, reads only)

Purpose: ChatGPT's 2026-09-05 review said it 'could not verify the item-level identity of your claimed same 240'. It can be verified:
the authors' code release carries the evaluation set. Source = github.com/epfl-ml4ed/tutor-robustness-eval @ commit 179a3f68554b321a953fc5fa15f8ae1ca8792911,
files dataset/gsm8k_difficulty_{0-25,26-50,51-75,76-100}.json (60 items each, fields problem/answer/domain/llama8b_solve_rate/source).
Ours = Ed_AI/runtime/PROJECT_breadth-run_2026-08-26/binder_breadth_keyed240/math_worksheet.txt (the pressed binder behind the bench's 240).
Match rule: exact problem text after whitespace collapse and straight/curly quote folding; sha256 of that normalized text, first 16 hex.

RESULT: 239 of 240 worksheet problems match a Zhao item exactly; 1 matched on the first 60 characters only; 0 have no match.
  - worksheet #240: matched on the first 60 chars only (punctuation differs)

Zhao file hashes (sha256 of the raw json as fetched 2026-09-05 08:25):
  bbf94db95db381afab0a05b14957e6582e691a6f5991d732b08df7754eae94cd  gsm8k_difficulty_0-25.json
  20a048146126815c4d6659331a11dbf9635da3bbd6acb244672b76e9b2a69cb3  gsm8k_difficulty_26-50.json
  db6096bf05e7a0cc9a5155560c75bd11a57f990da0efe68b309ef429201775a8  gsm8k_difficulty_51-75.json
  40307857ceb927647f872daca7fa3ec28149026998205b0043276b37b289826f  gsm8k_difficulty_76-100.json

Bucket census of OUR 240 (Zhao's difficulty by Llama-3.1-8B solve rate): 0-25: 60, 26-50: 60, 51-75: 60, 76-100: 60

| # | sha256(problem)[:16] | Zhao bucket | llama8b solve rate | key |
|---|---|---|---|---|
| 1 | 4c996822f81d32dd | 0-25 | 0.1875 | 8 |
| 2 | 92352f3662b174fc | 0-25 | 0.171875 | 10 |
| 3 | 2e7d49c2ee89f142 | 0-25 | 0.03125 | 59 |
| 4 | 5b78c59024f69abb | 0-25 | 0.015625 | 13600 |
| 5 | d07bfa30f305170f | 0-25 | 0.203125 | 165000 |
| 6 | 884a4b8b5dcaa2d2 | 0-25 | 0.03125 | 6 |
| 7 | ce39154223bf1404 | 0-25 | 0.078125 | 6 |
| 8 | ed3ca593ebc6ded8 | 0-25 | 0.03125 | 11 |
| 9 | d14e2de50b9ea8e8 | 0-25 | 0.15625 | 100 |
| 10 | 6766efce39bddf5a | 0-25 | 0.140625 | 60 |
| 11 | 3216209724dc29af | 0-25 | 0.046875 | 86400 |
| 12 | 48dcb8b4140ad660 | 0-25 | 0.09375 | 1230 |
| 13 | 2643bc7379db2c7c | 0-25 | 0.25 | 6 |
| 14 | 3ce61603e0ab5d00 | 0-25 | 0.015625 | 6 |
| 15 | 7860d1594358f8f3 | 0-25 | 0.203125 | 9 |
| 16 | 6a586e0d09496f31 | 0-25 | 0.125 | 57 |
| 17 | 2b400b4b3d45d5a9 | 0-25 | 0.015625 | 500 |
| 18 | 03a116375e8b2314 | 0-25 | 0.0 | 17 |
| 19 | 3080dd84b095bf56 | 0-25 | 0.25 | 30 |
| 20 | 76b01baeaf7a9d24 | 0-25 | 0.15625 | 300 |
| 21 | 8ebfb4765f4c32b7 | 0-25 | 0.1875 | 100 |
| 22 | 99ceb2ff34675d27 | 0-25 | 0.25 | 1 |
| 23 | 0a55cf9d8ad0858d | 0-25 | 0.109375 | 3 |
| 24 | 45deb96f8ae257fe | 0-25 | 0.09375 | 3 |
| 25 | 770dc5ed3fe69f94 | 0-25 | 0.234375 | 2 |
| 26 | 62ef9360bfa2a859 | 0-25 | 0.078125 | 780 |
| 27 | e0d9d04646795209 | 0-25 | 0.09375 | 48 |
| 28 | da5d997db6907420 | 0-25 | 0.234375 | 13 |
| 29 | 281bfdefe45094a3 | 0-25 | 0.046875 | 3000 |
| 30 | 2f616d89aea34a47 | 0-25 | 0.09375 | 42 |
| 31 | 14020bb965cb1a50 | 0-25 | 0.140625 | 70 |
| 32 | 59196bc4e91bf9b0 | 0-25 | 0.203125 | 5 |
| 33 | 40c1a60c6ce4f679 | 0-25 | 0.15625 | 4 |
| 34 | 72d2bc1e999dea34 | 0-25 | 0.234375 | 23 |
| 35 | 3b1cfb05db7480b7 | 0-25 | 0.25 | 6 |
| 36 | f2a9cacb2a9d3cda | 0-25 | 0.1875 | 160 |
| 37 | 8ad612580576fc6e | 0-25 | 0.078125 | 46 |
| 38 | a8686205df75e968 | 0-25 | 0.234375 | 6 |
| 39 | c99cb25355a35963 | 0-25 | 0.25 | 21 |
| 40 | b8ec49105ccd6f68 | 0-25 | 0.203125 | 3520 |
| 41 | 83a4e1b715c66cc8 | 0-25 | 0.03125 | 2 |
| 42 | a1c875e52b5e8735 | 0-25 | 0.203125 | 14 |
| 43 | e7a2809aae27c269 | 0-25 | 0.125 | 35 |
| 44 | 34e26d1fdba3221d | 0-25 | 0.015625 | 60 |
| 45 | 12bbf3938121a410 | 0-25 | 0.125 | 36 |
| 46 | 7a2a5923406ac729 | 0-25 | 0.015625 | 7 |
| 47 | 7f2b31334a055e3f | 0-25 | 0.09375 | 900 |
| 48 | 90ef053f02ec8061 | 0-25 | 0.25 | 4 |
| 49 | 36338b4edfa2f316 | 0-25 | 0.15625 | 5 |
| 50 | d2f91720f57ad85b | 0-25 | 0.15625 | 100 |
| 51 | a51949ce73961f47 | 0-25 | 0.09375 | 983 |
| 52 | 7f72de8476e8941d | 0-25 | 0.25 | 100 |
| 53 | 840c16e0f2de49e8 | 0-25 | 0.0 | 815 |
| 54 | c1801a89c8d4eee9 | 0-25 | 0.109375 | 20 |
| 55 | 292328408a567db0 | 0-25 | 0.25 | 200 |
| 56 | a39f53a204517a8e | 0-25 | 0.109375 | 4 |
| 57 | d75e3225fc422e4a | 0-25 | 0.1875 | 4 |
| 58 | 5139c02c6f4bd0bc | 0-25 | 0.234375 | 12 |
| 59 | bd6b412f969f4dae | 0-25 | 0.09375 | 52 |
| 60 | 1fb87af188bccba5 | 0-25 | 0.234375 | 90 |
| 61 | 2f6320f45ce3b65c | 26-50 | 0.359375 | 72 |
| 62 | cabb4e8643e5577c | 26-50 | 0.359375 | 25 |
| 63 | 05a0e5b170ce4872 | 26-50 | 0.328125 | 2 |
| 64 | 2a8d607a57a6ba8f | 26-50 | 0.28125 | 76 |
| 65 | 655a69a9894f4ddd | 26-50 | 0.265625 | 2100 |
| 66 | c99929d7dbfcbae8 | 26-50 | 0.328125 | 15 |
| 67 | 1d7d53d0d237efec | 26-50 | 0.265625 | 1650 |
| 68 | ddbcaaba11cf735b | 26-50 | 0.40625 | -12 |
| 69 | 0435504acd2034a2 | 26-50 | 0.4375 | 14000 |
| 70 | 41a4e96794a94644 | 26-50 | 0.453125 | 10 |
| 71 | fd21d7141063893c | 26-50 | 0.265625 | 9 |
| 72 | 5a9f13cc1f3ab16d | 26-50 | 0.296875 | 56 |
| 73 | 5219bde2d5faf787 | 26-50 | 0.359375 | 28 |
| 74 | b4e77ba7809f7b37 | 26-50 | 0.421875 | 2 |
| 75 | f557acb1f9eb702f | 26-50 | 0.390625 | 630 |
| 76 | 3e5007495ea78cdd | 26-50 | 0.359375 | 4 |
| 77 | f518effd1280072c | 26-50 | 0.484375 | 10 |
| 78 | 2cf118bf5834990f | 26-50 | 0.453125 | 106000 |
| 79 | eec5bfbd7c33b6f9 | 26-50 | 0.453125 | 21 |
| 80 | 1c21c17103b633f5 | 26-50 | 0.34375 | 40 |
| 81 | 05b59b0f808ef959 | 26-50 | 0.296875 | 2600 |
| 82 | e307dc397261905d | 26-50 | 0.484375 | 19 |
| 83 | 53f4b10ff099231e | 26-50 | 0.328125 | 8 |
| 84 | 5895c03cd656f87b | 26-50 | 0.40625 | 88 |
| 85 | 5d953ebfa71129f9 | 26-50 | 0.5 | 230 |
| 86 | 59c5355ea658299f | 26-50 | 0.421875 | 11 |
| 87 | bc2539cb5d0d581a | 26-50 | 0.390625 | 8 |
| 88 | f5f1b88cca3a9247 | 26-50 | 0.390625 | 600 |
| 89 | f8769c3ee290edd5 | 26-50 | 0.375 | 32 |
| 90 | 16ecd17d2d44f68c | 26-50 | 0.453125 | 4 |
| 91 | c6aff894a858d34a | 26-50 | 0.328125 | 75 |
| 92 | 3718fb01bb0831e8 | 26-50 | 0.40625 | 8 |
| 93 | c6e304500a3f6518 | 26-50 | 0.375 | 25 |
| 94 | 4f200957dd896d6a | 26-50 | 0.40625 | 175 |
| 95 | fa6fb8d259918f77 | 26-50 | 0.40625 | 407 |
| 96 | 17bdf07c3d61a106 | 26-50 | 0.359375 | 7 |
| 97 | 7113baf0d1ad668f | 26-50 | 0.375 | 2 |
| 98 | 228308fbb95eea52 | 26-50 | 0.46875 | 45 |
| 99 | 9b3eac3127cc191c | 26-50 | 0.296875 | 10 |
| 100 | a3a860b478c8a496 | 26-50 | 0.5 | 9450 |
| 101 | e11bb80d04b7e807 | 26-50 | 0.453125 | 120 |
| 102 | a612de9c83f93800 | 26-50 | 0.421875 | 9 |
| 103 | 15cc2e29639c01b0 | 26-50 | 0.46875 | 42 |
| 104 | cb1c6338bbd2a5ad | 26-50 | 0.390625 | 4 |
| 105 | c83e337cda8df28d | 26-50 | 0.484375 | 55 |
| 106 | 61c2ca1468f63d49 | 26-50 | 0.28125 | 250 |
| 107 | fc4c9a90d0bf667d | 26-50 | 0.40625 | 100 |
| 108 | 40ef33e3e5362e0a | 26-50 | 0.390625 | 24 |
| 109 | 3c7e61cd5a1d9c57 | 26-50 | 0.359375 | 11 |
| 110 | 097f252dbac010df | 26-50 | 0.484375 | 1000 |
| 111 | c627c29cc992d705 | 26-50 | 0.46875 | 4 |
| 112 | 26746925e0317025 | 26-50 | 0.484375 | 14 |
| 113 | 8abf3b77c7c9bc20 | 26-50 | 0.5 | 16 |
| 114 | 9d349e4922baf4ba | 26-50 | 0.40625 | 1152 |
| 115 | 6d38929c6dc0cf23 | 26-50 | 0.421875 | 390 |
| 116 | fcf5979692b66e25 | 26-50 | 0.40625 | 12423 |
| 117 | 5c40efd4f6e3e9e9 | 26-50 | 0.453125 | 192 |
| 118 | d61c258f6eb29020 | 26-50 | 0.5 | 24000 |
| 119 | 4737642a205334c1 | 26-50 | 0.296875 | 38 |
| 120 | 50be39d0a3584f67 | 26-50 | 0.328125 | 36 |
| 121 | 02554f9df5df39ef | 51-75 | 0.734375 | 80 |
| 122 | f0b2a0419399d9cb | 51-75 | 0.5625 | 12 |
| 123 | e04d2fc9154ccbd7 | 51-75 | 0.625 | 42 |
| 124 | 00e5d34709c86803 | 51-75 | 0.578125 | 2400 |
| 125 | 92db9ce782a90777 | 51-75 | 0.71875 | 11 |
| 126 | 79747af6fb394666 | 51-75 | 0.734375 | 27 |
| 127 | 17bc296cd22c2b03 | 51-75 | 0.640625 | 3 |
| 128 | 7d917fb95db3e7f9 | 51-75 | 0.609375 | 60 |
| 129 | 34069260bbe4464f | 51-75 | 0.65625 | 1234 |
| 130 | 0cd88f25935f86a0 | 51-75 | 0.6875 | 19 |
| 131 | 7ee0725cf5ee8a2c | 51-75 | 0.546875 | 32 |
| 132 | 79b52dfaf9a60473 | 51-75 | 0.6875 | 71 |
| 133 | 615c57bd55752354 | 51-75 | 0.5625 | 6 |
| 134 | a472e12184d40e22 | 51-75 | 0.640625 | 120 |
| 135 | 54ae0905266ef630 | 51-75 | 0.625 | 4000 |
| 136 | 703c6db969a14e62 | 51-75 | 0.625 | 55 |
| 137 | e599603242b5b420 | 51-75 | 0.71875 | 11 |
| 138 | 30cf16d38cb199e6 | 51-75 | 0.65625 | 5 |
| 139 | 6c41a3aaa7b560d5 | 51-75 | 0.734375 | 28 |
| 140 | 6eec85516ea324f3 | 51-75 | 0.6875 | 10 |
| 141 | 5520e46a9e2ff329 | 51-75 | 0.734375 | 500 |
| 142 | 3255fb5ffd53ce5b | 51-75 | 0.625 | 3 |
| 143 | 5d6cf27d846a9a82 | 51-75 | 0.609375 | 88 |
| 144 | a3e1b2322f984bce | 51-75 | 0.75 | 16 |
| 145 | 3f3f85ea8162b380 | 51-75 | 0.734375 | 4 |
| 146 | 2104a5c1c5a6d215 | 51-75 | 0.625 | 26 |
| 147 | 7e97754b7b4e0cf2 | 51-75 | 0.59375 | 55 |
| 148 | 5917b1ce3a4da66a | 51-75 | 0.734375 | 3 |
| 149 | 49859159bf688cb9 | 51-75 | 0.71875 | 300 |
| 150 | d0b3ed33f2f34436 | 51-75 | 0.734375 | 24 |
| 151 | 52279e55ef64b258 | 51-75 | 0.515625 | 160 |
| 152 | 70462320ec4824e7 | 51-75 | 0.671875 | 11 |
| 153 | 8b0ab5f9900cde61 | 51-75 | 0.6875 | 2 |
| 154 | ed12abc3ea176425 | 51-75 | 0.6875 | 38 |
| 155 | eea2db7722d684d4 | 51-75 | 0.546875 | 72 |
| 156 | a14708cc209cfcfa | 51-75 | 0.5625 | 7800 |
| 157 | 8e853252469b6741 | 51-75 | 0.734375 | 12 |
| 158 | 73b5d5a4da6f6986 | 51-75 | 0.671875 | 1980 |
| 159 | 2c24e5110571884c | 51-75 | 0.75 | 30 |
| 160 | fb3bc268e206e78d | 51-75 | 0.703125 | 5 |
| 161 | 9975aed09ecf742b | 51-75 | 0.625 | 5 |
| 162 | 881b81093bdcccd5 | 51-75 | 0.546875 | 6 |
| 163 | 2ecc15caf0fe72fa | 51-75 | 0.734375 | 72 |
| 164 | 8c4f4b81eeecac18 | 51-75 | 0.59375 | 180 |
| 165 | 1eb797b26dc8a2b3 | 51-75 | 0.71875 | 3 |
| 166 | 22c873bab2c31d09 | 51-75 | 0.734375 | 525 |
| 167 | 30d1c5025ca73ccc | 51-75 | 0.65625 | 100 |
| 168 | 9b2a1d47243b44f6 | 51-75 | 0.546875 | 6 |
| 169 | a020be9da44b9a48 | 51-75 | 0.515625 | 55000 |
| 170 | 34aa2ca00dd7ce8d | 51-75 | 0.59375 | 116 |
| 171 | 6a943bb781811b82 | 51-75 | 0.53125 | 49 |
| 172 | f5c478797405dfb9 | 51-75 | 0.71875 | 26 |
| 173 | 4e650f3ddbbbf131 | 51-75 | 0.53125 | 16 |
| 174 | 2fc7ac4db0f0a71e | 51-75 | 0.734375 | 7800 |
| 175 | 3cbc3d2f1432de9f | 51-75 | 0.578125 | 1800 |
| 176 | 595387a05fd6d1b3 | 51-75 | 0.703125 | 65 |
| 177 | d1168e58a19ebe42 | 51-75 | 0.5625 | 27048 |
| 178 | e41bdfb69d0bc4e3 | 51-75 | 0.734375 | 3 |
| 179 | 70ec7fa93a3c0565 | 51-75 | 0.703125 | 25000 |
| 180 | eba1baf5c3bfd6fe | 51-75 | 0.71875 | 96 |
| 181 | 2457fec63745be02 | 76-100 | 0.921875 | 83200 |
| 182 | 1eafd195f886e35d | 76-100 | 0.984375 | 56 |
| 183 | e0ee8e54a5ce4446 | 76-100 | 0.984375 | 6 |
| 184 | 269e2443723d7562 | 76-100 | 1.0 | 10 |
| 185 | 24201fa48e111f12 | 76-100 | 1.0 | 480 |
| 186 | 18e93e44c6d8a6ac | 76-100 | 0.96875 | 540 |
| 187 | f82eb9abbf3c52f4 | 76-100 | 0.9375 | 51 |
| 188 | a2655b9156b09938 | 76-100 | 0.828125 | 44 |
| 189 | 78b33c757c7102da | 76-100 | 0.953125 | 4 |
| 190 | f18972ac862a01a5 | 76-100 | 0.921875 | 160 |
| 191 | 609e9f9cd6070b6c | 76-100 | 0.953125 | 10 |
| 192 | bc50df93484b07aa | 76-100 | 1.0 | 44 |
| 193 | 29cf338deee42270 | 76-100 | 1.0 | 216 |
| 194 | 3c78e7240a2e0515 | 76-100 | 0.9375 | 20 |
| 195 | 544d8fb9bbe4bd22 | 76-100 | 0.78125 | 20 |
| 196 | 1b44d99e04cf184e | 76-100 | 0.78125 | 2800 |
| 197 | 90c01a4827072643 | 76-100 | 0.96875 | 36 |
| 198 | ee8411ade0a6b287 | 76-100 | 0.828125 | 484 |
| 199 | 07bb2a528b7f648b | 76-100 | 0.984375 | 673 |
| 200 | 3e1de82271885cf4 | 76-100 | 0.9375 | 49 |
| 201 | a460de6417503352 | 76-100 | 1.0 | 63 |
| 202 | 7bff3aa4b419a046 | 76-100 | 0.984375 | 22 |
| 203 | c2bae4b4fd84abaf | 76-100 | 0.765625 | 18 |
| 204 | 8714924378c77eb8 | 76-100 | 0.78125 | 126 |
| 205 | 3c360ee5042ac8f4 | 76-100 | 1.0 | 100 |
| 206 | 3026a5108f214bea | 76-100 | 0.984375 | 2920 |
| 207 | 3ad960c4c9a298ee | 76-100 | 0.96875 | 5 |
| 208 | 89ece4d5e4a0d618 | 76-100 | 1.0 | 1200 |
| 209 | df3424187430b018 | 76-100 | 0.9375 | 40 |
| 210 | f5ca4fad0d67bb22 | 76-100 | 0.78125 | 95 |
| 211 | 94b35b0846947201 | 76-100 | 1.0 | 22000 |
| 212 | 34d931d23ca743b7 | 76-100 | 0.84375 | 2600 |
| 213 | eb9ae420f2867fc2 | 76-100 | 0.953125 | 14 |
| 214 | 88198d2e62cde2df | 76-100 | 0.984375 | 33 |
| 215 | 3b3648b5ef47ef61 | 76-100 | 0.765625 | 33 |
| 216 | a8c76f22b05d6d18 | 76-100 | 0.9375 | 5 |
| 217 | 2bc438588ff30603 | 76-100 | 1.0 | 7 |
| 218 | c869092ddeac5724 | 76-100 | 0.84375 | 12 |
| 219 | c8fee5fbea6c7a26 | 76-100 | 0.875 | 200 |
| 220 | 068b4b731a248981 | 76-100 | 0.921875 | 4 |
| 221 | 4b380870769adba6 | 76-100 | 0.984375 | 51 |
| 222 | 1188445269625cd7 | 76-100 | 0.984375 | 10 |
| 223 | bf1556124b1eaa9b | 76-100 | 0.890625 | 900 |
| 224 | c1592ab80d8e184f | 76-100 | 0.96875 | 660 |
| 225 | fdcef9354f5c9127 | 76-100 | 0.859375 | 6 |
| 226 | 4cc8c085b88904e8 | 76-100 | 0.921875 | 6 |
| 227 | c2e028eca68c12e5 | 76-100 | 0.953125 | 17 |
| 228 | 784acd3ed0dabe10 | 76-100 | 0.875 | 18 |
| 229 | 91b7ac77c257dad5 | 76-100 | 0.921875 | 20 |
| 230 | 03248b3b91e171fd | 76-100 | 0.828125 | 3200 |
| 231 | f58997e2861a77b9 | 76-100 | 1 | 6 |
| 232 | e9ff91bb92d416ac | 76-100 | 1.0 | 6 |
| 233 | 41884d8df345b071 | 76-100 | 0.90625 | 117 |
| 234 | e8f00fbdf09bc30f | 76-100 | 0.90625 | 12 |
| 235 | 1eccf637da1b53ac | 76-100 | 0.8125 | 770 |
| 236 | 187712735f345ef9 | 76-100 | 1.0 | 23 |
| 237 | 80e910303dd209fe | 76-100 | 1.0 | 600 |
| 238 | a13430e732d2c1e6 | 76-100 | 0.90625 | 41 |
| 239 | 44997de11111ba2c | 76-100 | 0.78125 | 370 |
| 240 | 102532afa6f4a498 | 76-100 | 0.96875 | 11000 |

What this closes: 'same 240' becomes a checkable claim (publish this table or its hashes beside the bench). What it does NOT close:
attacker, judge, key exposure, run protocol - those are the other four differences the bench's 'directional' line stands on.