9428c4363a32e2fffb8d414d19c0f787d8080a5b493b9b5307ce28eb629a5b64  docs/AUTHOR_BRIEF.md
c1e00ee1b23c3deaa19e447e89ee61f7ff4640d85c32eb47b3d93c50faae4409  docs/CALIBRATION_FEEDBACK_01.txt
c12c1a8e9f7853b23aab973505f460b365c76b85124a7c3f58cd4cf8195c50e3  docs/CALIBRATION_FEEDBACK_02.txt
880c6eb8a85e6ddc5156ee6210f1caaeb8d2a6cdbd7e6b7e053726039c63149b  docs/CALIBRATION_FEEDBACK_03.txt
4ef5beabab1c1bb964d1847f799b02e152ec9ae7c84e2600741af7bc8a89b263  docs/CALIBRATION_FEEDBACK_04.txt
3f84ae14f477be01ed8bcc2df794d15b6f883714f6e356c8109e1fc0af907be7  docs/FREEZE.md
6e0d859649082b2b8e21ccbb47091c40e179bc6ec39589ae534efddc5ecf51f7  docs/FREEZE_AMENDMENT_01.md
45ce2fdd79980599ee168f63453f5f1db71eaa41327aeea2845d3a7709e559a7  docs/PREREGISTRATION.md
ea421f571f9519a2281923296e1a7b37c680b1250aa9ab8f12f3f50fc94430db  docs/REPRODUCE.md
1d2f3858cc366dc183f12967b256cf59579886c88f4e8472e7c626aff4d5daa7  docs/SHIFT_V1_RESULTS.md
c0490fd9c674665deea825a4f754a476fe3055a1ca94466d14526fdcaee6922e  grader/suite.py
cb353a8b293da235bec672535d8b6cee8b5f4c2ec39c1c66d32a21174021d5f0  REDACTIONS.txt
8856569ca73955fa5ddbe360d3adf288d9685691996f712cc8543d4431a1caf7  results.json
fa05dd3c47719dc7fde2d6daf4645fab3cfa8f340a63f21cdc39dbf96534494f  runs/shift-holdout-v1-rerun/episodes/0000_plain_full_shift_holdout_v1/engine.log.newton.json
978a35ce34a1813679f9f6e4b8ece96b9bb77885ec8c61c3626d0dd3dbf0887e  runs/shift-holdout-v1-rerun/episodes/0000_plain_full_shift_holdout_v1/stdout.log
0466d0f0f72d7d8fd9b5afbf3ef6379d9a7631d56d15743140bf028bb5fbf431  runs/shift-holdout-v1-rerun/episodes/0000_plain_full_shift_holdout_v1/trace.json.gz
fa05dd3c47719dc7fde2d6daf4645fab3cfa8f340a63f21cdc39dbf96534494f  runs/shift-holdout-v1-rerun/episodes/0001_langgraph_full_shift_holdout_v1/engine.log.newton.json
88671524fbb2bf56f55675a6552d240630ba12c43cdc16c118515c0458a6ca99  runs/shift-holdout-v1-rerun/episodes/0001_langgraph_full_shift_holdout_v1/stdout.log
f9c5d4312d74f8d7f75bebe3b20c2ceb35f9b77c713c6366f9bb5a6ac1d1342d  runs/shift-holdout-v1-rerun/episodes/0001_langgraph_full_shift_holdout_v1/trace.json.gz
fa05dd3c47719dc7fde2d6daf4645fab3cfa8f340a63f21cdc39dbf96534494f  runs/shift-holdout-v1-rerun/episodes/0002_lobster_full_shift_holdout_v1/engine.log.newton.json
b589f1439f1e6263d0a759a6994973fe0b219e12f7b8aee074097b5d1c01410a  runs/shift-holdout-v1-rerun/episodes/0002_lobster_full_shift_holdout_v1/stdout.log
365afc9e3d8516a8bfdac7b6853cfeebe364b63b157aeb543a5117ad034e3f6e  runs/shift-holdout-v1-rerun/episodes/0002_lobster_full_shift_holdout_v1/trace.json.gz
fa05dd3c47719dc7fde2d6daf4645fab3cfa8f340a63f21cdc39dbf96534494f  runs/shift-holdout-v1-rerun/episodes/0003_lobster_full_shift_holdout_v1/engine.log.newton.json
f63c4ba6c5d514fa987d6bc4e6dcbbd93809fc7c828252e67cd2ff4a547c02a7  runs/shift-holdout-v1-rerun/episodes/0003_lobster_full_shift_holdout_v1/stdout.log
83bde09b50b09daed3325c665a80cf45e1f486878ed7807dcb19293aa7e897f2  runs/shift-holdout-v1-rerun/episodes/0003_lobster_full_shift_holdout_v1/trace.json.gz
fa05dd3c47719dc7fde2d6daf4645fab3cfa8f340a63f21cdc39dbf96534494f  runs/shift-holdout-v1-rerun/episodes/0004_plain_basic_shift_holdout_v1/engine.log.newton.json
e29b0371fa2c8bd02258d480750183124d39d3894206b52cef2f5287e4089377  runs/shift-holdout-v1-rerun/episodes/0004_plain_basic_shift_holdout_v1/stdout.log
b3cc7dcc21bbe308a85045a9d1fc7142383c118ef9b553e65cf6dd3cf4c22eb9  runs/shift-holdout-v1-rerun/episodes/0004_plain_basic_shift_holdout_v1/trace.json.gz
fa05dd3c47719dc7fde2d6daf4645fab3cfa8f340a63f21cdc39dbf96534494f  runs/shift-holdout-v1-rerun/episodes/0005_langgraph_basic_shift_holdout_v1/engine.log.newton.json
24deb4e68b3e6f834b8935813440e4e6493b0d78a194c35ba9542b95665df1f1  runs/shift-holdout-v1-rerun/episodes/0005_langgraph_basic_shift_holdout_v1/stdout.log
d989e8deb431ec2407d5025300046ee6a8846d096a06b19de272f326c86d26bf  runs/shift-holdout-v1-rerun/episodes/0005_langgraph_basic_shift_holdout_v1/trace.json.gz
fa05dd3c47719dc7fde2d6daf4645fab3cfa8f340a63f21cdc39dbf96534494f  runs/shift-holdout-v1-rerun/episodes/0006_lobster_basic_shift_holdout_v1/engine.log.newton.json
a9d1b967b572528c2c8db3fc3fc2f65f777f3e6a123e9f4d49b0a7a7cb5ec5fe  runs/shift-holdout-v1-rerun/episodes/0006_lobster_basic_shift_holdout_v1/stdout.log
d9824280681b57569e215d3fd52159db2ba2b1e5f8dca8d9d29b25678f9ee73f  runs/shift-holdout-v1-rerun/episodes/0006_lobster_basic_shift_holdout_v1/trace.json.gz
6be35ba5ef4bfcee275cda619ae852912e85bbcb9c8ad31ede133d18827e5bbb  runs/shift-holdout-v1-rerun/health.jsonl
bae9da1e7fb4b855d95a85b1fc06638155eb0cc918f38149edf610903723ba80  runs/shift-holdout-v1-rerun/manifest.json
100764410d6fe9e58d08d12073bdb4df9acc71acd89d6fa79d24648870900da0  runs/shift-holdout-v1-rerun/rows.jsonl
fa05dd3c47719dc7fde2d6daf4645fab3cfa8f340a63f21cdc39dbf96534494f  runs/shift-holdout-v1-wave0/episodes/0000_omnilink_shift_holdout_v1/engine.log.newton.json
ce347105582c253cdf2d2209b2eb24500c29bf698e123a174a1dc5aad1a45948  runs/shift-holdout-v1-wave0/episodes/0000_omnilink_shift_holdout_v1/relay_trace.jsonl
c934758a5450ab6e2f03299a2f0845c5edea95a49ff2ad48cafcb233e6427359  runs/shift-holdout-v1-wave0/episodes/0000_omnilink_shift_holdout_v1/stdout.log
a647da12e01812c9412fa67e59bde86dc68cb60c03425cc3b48bf4c8625021a5  runs/shift-holdout-v1-wave0/episodes/0000_omnilink_shift_holdout_v1/trace.json.gz
fa05dd3c47719dc7fde2d6daf4645fab3cfa8f340a63f21cdc39dbf96534494f  runs/shift-holdout-v1-wave0/episodes/0001_plain_basic_shift_holdout_v1/engine.log.newton.json
190b3c019d83a5a4a9aa6ff42cc0920bd5f5cca69dbbab0dd8db0fd88c78e7df  runs/shift-holdout-v1-wave0/episodes/0001_plain_basic_shift_holdout_v1/stdout.log
f40c8094077319396762a979366dc0d3de00968160c3d478fbf93e1f0c4092be  runs/shift-holdout-v1-wave0/episodes/0001_plain_basic_shift_holdout_v1/trace.json.gz
fa05dd3c47719dc7fde2d6daf4645fab3cfa8f340a63f21cdc39dbf96534494f  runs/shift-holdout-v1-wave0/episodes/0002_langgraph_basic_shift_holdout_v1/engine.log.newton.json
c1777602a73c338fb75cb3e0bf4cf1a668f8323b02251eb60e45c1a168e732e8  runs/shift-holdout-v1-wave0/episodes/0002_langgraph_basic_shift_holdout_v1/stdout.log
1d8b9b5985f3a17d7bb570e6185ffd1814f4b524b554e005008acf1353b42f63  runs/shift-holdout-v1-wave0/episodes/0002_langgraph_basic_shift_holdout_v1/trace.json.gz
fa05dd3c47719dc7fde2d6daf4645fab3cfa8f340a63f21cdc39dbf96534494f  runs/shift-holdout-v1-wave0/episodes/0003_lobster_basic_shift_holdout_v1/engine.log.newton.json
491e8fb84e7031f475caa1a22f2c74e291381bf0f108883f1f600c9b5f527ed6  runs/shift-holdout-v1-wave0/episodes/0003_lobster_basic_shift_holdout_v1/stdout.log
b40f83dc4eacfeeae54a977a01ed82e397152e0c176085088e87e0dbb5d30cba  runs/shift-holdout-v1-wave0/episodes/0003_lobster_basic_shift_holdout_v1/trace.json.gz
fa05dd3c47719dc7fde2d6daf4645fab3cfa8f340a63f21cdc39dbf96534494f  runs/shift-holdout-v1-wave0/episodes/0004_plain_full_shift_holdout_v1/engine.log.newton.json
20f53148c9fdb0e5beaced84dd3370a0a913228d289e7e79c9671f40d92a66a3  runs/shift-holdout-v1-wave0/episodes/0004_plain_full_shift_holdout_v1/stdout.log
51be61f3b9719a8169d5d908a4b237495e266ff2c8188d00724f0d25f8a8dd89  runs/shift-holdout-v1-wave0/episodes/0004_plain_full_shift_holdout_v1/trace.json.gz
fa05dd3c47719dc7fde2d6daf4645fab3cfa8f340a63f21cdc39dbf96534494f  runs/shift-holdout-v1-wave0/episodes/0005_langgraph_full_shift_holdout_v1/engine.log.newton.json
c57ab9e405b84332f56f5e77b75a73e24e7a7adfc2bacae020053307a40836ea  runs/shift-holdout-v1-wave0/episodes/0005_langgraph_full_shift_holdout_v1/stdout.log
46c71dacc209e9a126f1500ed4391897c5133edecc8b0cabc13e89690645fb34  runs/shift-holdout-v1-wave0/episodes/0005_langgraph_full_shift_holdout_v1/trace.json.gz
fa05dd3c47719dc7fde2d6daf4645fab3cfa8f340a63f21cdc39dbf96534494f  runs/shift-holdout-v1-wave0/episodes/0006_lobster_full_shift_holdout_v1/engine.log.newton.json
4b124f22402382231edbc5c59a5d7d28a60fb95d363cbcbd62ce2a30ef501301  runs/shift-holdout-v1-wave0/episodes/0006_lobster_full_shift_holdout_v1/stdout.log
9c571399116a23d65fb2c40bff2c3d8445c70ee14d75bb21f838c68776d8091c  runs/shift-holdout-v1-wave0/episodes/0006_lobster_full_shift_holdout_v1/trace.json.gz
8b118261ec3dc2e13b6f308cb16596e922c40cac58af957df6843ce76360ead6  runs/shift-holdout-v1-wave0/health.jsonl
20c552e25d1b696146b1977b54167581db1cd419a4113b355e294dd0e4e47ffb  runs/shift-holdout-v1-wave0/manifest.json
895d8df76a625ead9c32f6b065b91a0dfcd6bc071d4f6ae109e2ac68b5368fa7  runs/shift-holdout-v1-wave0/rows.jsonl
fa05dd3c47719dc7fde2d6daf4645fab3cfa8f340a63f21cdc39dbf96534494f  runs/shift-holdout-v1-wave1/episodes/0000_plain_basic_shift_holdout_v1/engine.log.newton.json
35d070c9633b89fde8b757ce9c97876c6e7d62c0a8f6e9d192da8b8793323aa7  runs/shift-holdout-v1-wave1/episodes/0000_plain_basic_shift_holdout_v1/stdout.log
10e6e64cba96fc446b099d9fc968d05385bde94223d421423e7472ae656e96a9  runs/shift-holdout-v1-wave1/episodes/0000_plain_basic_shift_holdout_v1/trace.json.gz
fa05dd3c47719dc7fde2d6daf4645fab3cfa8f340a63f21cdc39dbf96534494f  runs/shift-holdout-v1-wave1/episodes/0001_langgraph_basic_shift_holdout_v1/engine.log.newton.json
06878d6a0c4d764e589c77e78ac0feb4093c844b86dc9db0c1bdf221fbe2ae47  runs/shift-holdout-v1-wave1/episodes/0001_langgraph_basic_shift_holdout_v1/stdout.log
ae947acd9d099186282de5d4d07b4b066e1feae46cb638695d261240e2c29db6  runs/shift-holdout-v1-wave1/episodes/0001_langgraph_basic_shift_holdout_v1/trace.json.gz
fa05dd3c47719dc7fde2d6daf4645fab3cfa8f340a63f21cdc39dbf96534494f  runs/shift-holdout-v1-wave1/episodes/0002_lobster_basic_shift_holdout_v1/engine.log.newton.json
d70fdc4a56b7a6ea31e083bb64b556f9af19fde3709c04c6274fb4b598a6a69b  runs/shift-holdout-v1-wave1/episodes/0002_lobster_basic_shift_holdout_v1/stdout.log
dc079605df0246f672311e6a72a5b5021a81614ffe0323c43b49442216fe58a3  runs/shift-holdout-v1-wave1/episodes/0002_lobster_basic_shift_holdout_v1/trace.json.gz
fa05dd3c47719dc7fde2d6daf4645fab3cfa8f340a63f21cdc39dbf96534494f  runs/shift-holdout-v1-wave1/episodes/0003_plain_full_shift_holdout_v1/engine.log.newton.json
5cc0b0911c781e8af0d7dd93f0411bfe1e9dc4b458e61dfec0d82937c7ffc741  runs/shift-holdout-v1-wave1/episodes/0003_plain_full_shift_holdout_v1/stdout.log
7c060e26ca87cdebd3655eb3fb8115aa863be61a4c544c77f63b936398765a5e  runs/shift-holdout-v1-wave1/episodes/0003_plain_full_shift_holdout_v1/trace.json.gz
fa05dd3c47719dc7fde2d6daf4645fab3cfa8f340a63f21cdc39dbf96534494f  runs/shift-holdout-v1-wave1/episodes/0004_langgraph_full_shift_holdout_v1/engine.log.newton.json
a8dddb0081a60db81a2042581d78a945195e6d1ead13f0321dd336feac4cf018  runs/shift-holdout-v1-wave1/episodes/0004_langgraph_full_shift_holdout_v1/stdout.log
fd6ec27d1ff61623cde919a8d7ea5506735ae9b0fb56784bf739825bc2561b2c  runs/shift-holdout-v1-wave1/episodes/0004_langgraph_full_shift_holdout_v1/trace.json.gz
fa05dd3c47719dc7fde2d6daf4645fab3cfa8f340a63f21cdc39dbf96534494f  runs/shift-holdout-v1-wave1/episodes/0005_lobster_full_shift_holdout_v1/engine.log.newton.json
67c003dee61ab0fabfe9dd565eb11314c72274a778c0455c66358da9936318d1  runs/shift-holdout-v1-wave1/episodes/0005_lobster_full_shift_holdout_v1/stdout.log
6069247ddef04df1264b585992c5b08fbce96b36592b923ddda972b0365d4bc2  runs/shift-holdout-v1-wave1/episodes/0005_lobster_full_shift_holdout_v1/trace.json.gz
fa05dd3c47719dc7fde2d6daf4645fab3cfa8f340a63f21cdc39dbf96534494f  runs/shift-holdout-v1-wave1/episodes/0006_omnilink_shift_holdout_v1/engine.log.newton.json
c26f2dfdeb59ce72c973f2577aed307ddeda1639a6299f86a8f7bbbc7f3ea889  runs/shift-holdout-v1-wave1/episodes/0006_omnilink_shift_holdout_v1/relay_trace.jsonl
24a81d902ac499e5692dfdc2ebb851d81b30d8720d268881088e46e242251f57  runs/shift-holdout-v1-wave1/episodes/0006_omnilink_shift_holdout_v1/stdout.log
1e6eddb2da14429964bcd652cc85df3fb45df13702c0a9386cb5cadf4ad5cdc4  runs/shift-holdout-v1-wave1/episodes/0006_omnilink_shift_holdout_v1/trace.json.gz
0cd48cde49b5943122a5fd291b88fc1e2eebff0542c25ac3301944289c7d4788  runs/shift-holdout-v1-wave1/health.jsonl
78b56b298243557a3ac88f31bba8f93ac15d5f3e95c11e36d3a0f9f9d54ff832  runs/shift-holdout-v1-wave1/manifest.json
68540f393232ccab483552bf7b4300781c74680c41d855a6bea93e71f0ebb68e  runs/shift-holdout-v1-wave1/rows.jsonl
fa05dd3c47719dc7fde2d6daf4645fab3cfa8f340a63f21cdc39dbf96534494f  runs/shift-holdout-v1-wave2/episodes/0000_langgraph_basic_shift_holdout_v1/engine.log.newton.json
ed98a183e1fe8b77e290fbde878eb4b053f21c3e5da04bda9ec57b0b406d247a  runs/shift-holdout-v1-wave2/episodes/0000_langgraph_basic_shift_holdout_v1/stdout.log
cc6a62e5d93c0734236c20ff98f22bf2bfbe36f0b5e547e7522d63a05f782974  runs/shift-holdout-v1-wave2/episodes/0000_langgraph_basic_shift_holdout_v1/trace.json.gz
fa05dd3c47719dc7fde2d6daf4645fab3cfa8f340a63f21cdc39dbf96534494f  runs/shift-holdout-v1-wave2/episodes/0001_lobster_basic_shift_holdout_v1/engine.log.newton.json
99ebef536d34a60f39490447b7ad371fe1f4c588ac3a914d8fd56aad65cc0d3f  runs/shift-holdout-v1-wave2/episodes/0001_lobster_basic_shift_holdout_v1/stdout.log
5b7a00781ffbfa935b57c00ffd3a83f8401c519ab5fe1bdb9caf7cd70850cf56  runs/shift-holdout-v1-wave2/episodes/0001_lobster_basic_shift_holdout_v1/trace.json.gz
fa05dd3c47719dc7fde2d6daf4645fab3cfa8f340a63f21cdc39dbf96534494f  runs/shift-holdout-v1-wave2/episodes/0002_plain_full_shift_holdout_v1/engine.log.newton.json
d38be94c997ab5cf20d9544e2ca0c2dd4a0c92600cbce1ad50d40f8594735437  runs/shift-holdout-v1-wave2/episodes/0002_plain_full_shift_holdout_v1/stdout.log
9f91cbe726b9e48010baa19739b1028745b2f51de4ec25517e000fdb78393549  runs/shift-holdout-v1-wave2/episodes/0002_plain_full_shift_holdout_v1/trace.json.gz
fa05dd3c47719dc7fde2d6daf4645fab3cfa8f340a63f21cdc39dbf96534494f  runs/shift-holdout-v1-wave2/episodes/0003_langgraph_full_shift_holdout_v1/engine.log.newton.json
60ea5ed0c727088cc85c0e7599a21f82dae448aef32d3842e9303f292b48bc87  runs/shift-holdout-v1-wave2/episodes/0003_langgraph_full_shift_holdout_v1/stdout.log
f5bf41cece3370bda52a0bdd668850d575f77b7e788611f5726bae58610979b8  runs/shift-holdout-v1-wave2/episodes/0003_langgraph_full_shift_holdout_v1/trace.json.gz
fa05dd3c47719dc7fde2d6daf4645fab3cfa8f340a63f21cdc39dbf96534494f  runs/shift-holdout-v1-wave2/episodes/0004_lobster_full_shift_holdout_v1/engine.log.newton.json
03076001170fd5e48190ad52f01323284bba58062a8d865169dd27bafa30b983  runs/shift-holdout-v1-wave2/episodes/0004_lobster_full_shift_holdout_v1/stdout.log
71b38c41767eb9184fe7f39a5fcbbe73f798019f6f1f5bcbabc4f75ef4524f08  runs/shift-holdout-v1-wave2/episodes/0004_lobster_full_shift_holdout_v1/trace.json.gz
fa05dd3c47719dc7fde2d6daf4645fab3cfa8f340a63f21cdc39dbf96534494f  runs/shift-holdout-v1-wave2/episodes/0005_omnilink_shift_holdout_v1/engine.log.newton.json
78537d50924556fc6e96d4996e6a8579c7cf9b79219d7e2416314903c4aea6d8  runs/shift-holdout-v1-wave2/episodes/0005_omnilink_shift_holdout_v1/relay_trace.jsonl
1e6880bc7c934aeeaf8d5b1361bd4c2d0247cbe7eadf29247d63db77108c0b13  runs/shift-holdout-v1-wave2/episodes/0005_omnilink_shift_holdout_v1/stdout.log
6badf1be0f9a56f501523fd17958a9ac015dd46bdded1e63534a3b0fdac4928b  runs/shift-holdout-v1-wave2/episodes/0005_omnilink_shift_holdout_v1/trace.json.gz
fa05dd3c47719dc7fde2d6daf4645fab3cfa8f340a63f21cdc39dbf96534494f  runs/shift-holdout-v1-wave2/episodes/0006_plain_basic_shift_holdout_v1/engine.log.newton.json
68a117a9bcca0a2432acea40e03a986b5eee419bade01785c73075506a057f2a  runs/shift-holdout-v1-wave2/episodes/0006_plain_basic_shift_holdout_v1/stdout.log
7d05a49ec574d2298859870f6732860d5b2b7e1299632596c33fdfb1bd19107b  runs/shift-holdout-v1-wave2/episodes/0006_plain_basic_shift_holdout_v1/trace.json.gz
b3c0b5b487c0fdd616678ff76c3e5c6c711df4fa4c1b016b87f6afc33a187f3c  runs/shift-holdout-v1-wave2/health.jsonl
5908772c2fc52d4b9e8b3ea1dc772aefbeb56b40b3e978291264cd6e5f86e173  runs/shift-holdout-v1-wave2/manifest.json
62297fe20acd83b9c7ebef0a066bfbe7140866ccc6d3d22802455d657717ed4a  runs/shift-holdout-v1-wave2/rows.jsonl
0770cc0771a4a6d8db38823ba6282d65f5a1bf589f045a1f35fc42a1203e7094  suites/shift_holdout_v1.json
4694aa995ea7d455b18eb1709714c7df7a5d895bdc67a0072060ccc6ff3d7765  verify_archive.py
