51b88fd3e9e24edcdce1dd145a4fca2dcd12911407f00b06dfa6ff600f9733c1  LICENSE
20b06ac10cfeb804445eff339b4aa450e8462bcb42a93ef23eeeb9e09c469634  REDACTIONS.txt
2f16c4734716e30195694d2ea18ea2eceec6c53aac3edaa8adc5ebf203910247  codex-results.json
102027d3d929cc8e5cf4a44bfb8de8d4f421762e8d42093f63e9e35f97ee484f  freeze-first.json
0eb3b1f030f4bd0303b0c07e926472a42ac7b274be161b515199ca722ac127c8  freeze.json
e32a726c42a4146f6f84562b8e46e1b11033a07f5a251da361bdbf0396ffc2aa  initial-source/omnisim/ops_bench/agents.py
67253981140af0abe5b42aa2089870d3348e264017346f1be28890ed19d34842  initial-source/omnisim/ops_bench/cli.py
746c7167540b3ab214900c112fb0184d11d656d4c04ed897d7c0da885168098a  initial-source/omnisim/ops_bench/codex_agent.py
af9aa1a0451983383fb13908800e811bb87445a96300e7abf4c236162deb36dc  initial-source/omnisim/ops_bench/runner.py
e0fa3c22808799ecc122ac9f8c6fb27e3e665febb8844bd82c700cb96bd9d04d  initial-source/omnisim/ops_bench/session.py
c0490fd9c674665deea825a4f754a476fe3055a1ca94466d14526fdcaee6922e  initial-source/omnisim/ops_bench/suite.py
345af7d8706876165885f73fdd4d6e0e42cfc742b834223b955f8890f91d089d  initial-source/tests/benchmarks/robot_ops/shift/CODEX_EXTENSION.md
0770cc0771a4a6d8db38823ba6282d65f5a1bf589f045a1f35fc42a1203e7094  initial-source/tests/benchmarks/robot_ops/suites/shift_holdout_v1.json
9261bf74d8039fbab6e769433e8c94b18359602c8c074b18b80f974fd9a9ed23  machine.txt
1d895dda7a82faa54dd61fb52cd719e8a5f297267312eb2b1dfca5cbb569b0aa  omnisim/control_bench/engine.py
8cccaabc7bd2b7179023e8d1d5dd5df396b796b881549fc1f5f8125f2999cf75  omnisim/ops_bench/__init__.py
e32a726c42a4146f6f84562b8e46e1b11033a07f5a251da361bdbf0396ffc2aa  omnisim/ops_bench/agents.py
67253981140af0abe5b42aa2089870d3348e264017346f1be28890ed19d34842  omnisim/ops_bench/cli.py
c64f26998f2984cf406e0b3902c2be1110fbaf24bfe3e45b8ede13b92f10ed14  omnisim/ops_bench/codex_agent.py
b4622807786be2a8b2e2e315ca7851e14386343bfb43f95e81bc9b9a11eaf1ec  omnisim/ops_bench/competitors.py
af9aa1a0451983383fb13908800e811bb87445a96300e7abf4c236162deb36dc  omnisim/ops_bench/runner.py
e0fa3c22808799ecc122ac9f8c6fb27e3e665febb8844bd82c700cb96bd9d04d  omnisim/ops_bench/session.py
c0490fd9c674665deea825a4f754a476fe3055a1ca94466d14526fdcaee6922e  omnisim/ops_bench/suite.py
dc5a0003444c7085c890cdb4cc276fbe43537a37095583fb928c35bd85616652  omnisim/paths.py
c8a4edaa423646ba6c74f525779ccb47f4d84a2346c6332a042af0a4f0680758  tests/benchmarks/robot_ops/analyze_holdout.py
c621c550e63edbe8addeb13a4719fa3dc76626fa0d126b21692886ec6d70c4ef  tests/benchmarks/robot_ops/analyze_shift.py
05c78a1071415d15b266f99cd4a28ac1978b3ccdaa6c968c1b27686991ec914e  tests/benchmarks/robot_ops/evidence/codex-shift-v1-20260930-corrected-r0/episodes/0000_codex_full_shift_holdout_v1/codex-config.json
63005b3ecd28e696505447f270eec3ad34eed2c46f3c8cbce8fdaa1ef8c990da  tests/benchmarks/robot_ops/evidence/codex-shift-v1-20260930-corrected-r0/episodes/0000_codex_full_shift_holdout_v1/codex-events.jsonl
fa05dd3c47719dc7fde2d6daf4645fab3cfa8f340a63f21cdc39dbf96534494f  tests/benchmarks/robot_ops/evidence/codex-shift-v1-20260930-corrected-r0/episodes/0000_codex_full_shift_holdout_v1/engine.log.newton.json
34d5c79066ecf967c492f4efe5a8a82228e7ca92c3fabb9384e806d4b97a4b66  tests/benchmarks/robot_ops/evidence/codex-shift-v1-20260930-corrected-r0/episodes/0000_codex_full_shift_holdout_v1/trace.json.gz
3a34401925d2a0bb88ad3296901e8b3b85eeaccca8ecafacdb9b8ada6505d4a4  tests/benchmarks/robot_ops/evidence/codex-shift-v1-20260930-corrected-r0/manifest.json
824812d5aebd60032a8c52637d402df7c750dd7362d06982eae0e6d108e02415  tests/benchmarks/robot_ops/evidence/codex-shift-v1-20260930-corrected-r0/rows.jsonl
cf3e977a781a4d41bf81f59fb22cf0bbb2831142a60dc8dff131fc9d5d1e329b  tests/benchmarks/robot_ops/evidence/codex-shift-v1-20260930-corrected-r1/episodes/0000_codex_full_shift_holdout_v1/codex-config.json
ed961ebb55a91545b018fc2b69856f1c51d7006ccfdb40ea9e4aa4934611d6a3  tests/benchmarks/robot_ops/evidence/codex-shift-v1-20260930-corrected-r1/episodes/0000_codex_full_shift_holdout_v1/codex-events.jsonl
fa05dd3c47719dc7fde2d6daf4645fab3cfa8f340a63f21cdc39dbf96534494f  tests/benchmarks/robot_ops/evidence/codex-shift-v1-20260930-corrected-r1/episodes/0000_codex_full_shift_holdout_v1/engine.log.newton.json
61022e34eb884b2fa4fc504674aca6db4354a407a42364fc121553013072d995  tests/benchmarks/robot_ops/evidence/codex-shift-v1-20260930-corrected-r1/episodes/0000_codex_full_shift_holdout_v1/trace.json.gz
c694b8dbc3dfe07b2f6bdbcf340d1a19f70a995ba74a32aa663a7a94c9047591  tests/benchmarks/robot_ops/evidence/codex-shift-v1-20260930-corrected-r1/manifest.json
3b0210d0f3cceb9301fb2a185671ee96f8eb3b9a75d732a5eb100c98ccfcdbec  tests/benchmarks/robot_ops/evidence/codex-shift-v1-20260930-corrected-r1/rows.jsonl
1dc278c898a76ebc7e8177c94c537329d8dc74f10fd42a97c4501386dc42e625  tests/benchmarks/robot_ops/evidence/codex-shift-v1-20260930-corrected-r2/episodes/0000_codex_full_shift_holdout_v1/codex-config.json
67bd29c298847153c16f586dd387e0ee1161537127494c510ec84187842a46aa  tests/benchmarks/robot_ops/evidence/codex-shift-v1-20260930-corrected-r2/episodes/0000_codex_full_shift_holdout_v1/codex-events.jsonl
fa05dd3c47719dc7fde2d6daf4645fab3cfa8f340a63f21cdc39dbf96534494f  tests/benchmarks/robot_ops/evidence/codex-shift-v1-20260930-corrected-r2/episodes/0000_codex_full_shift_holdout_v1/engine.log.newton.json
4b27791387988bab2e5c9086092f186a2f284ff7c916c390d47c30e0c93b6f66  tests/benchmarks/robot_ops/evidence/codex-shift-v1-20260930-corrected-r2/episodes/0000_codex_full_shift_holdout_v1/trace.json.gz
1a76fd0d35b62d329cf17588236619ed5de9873918702735eba649d6a93f3b29  tests/benchmarks/robot_ops/evidence/codex-shift-v1-20260930-corrected-r2/manifest.json
e61159fef44401f7645a019861bec7671f255634137e4e07e3d8d21205655a0a  tests/benchmarks/robot_ops/evidence/codex-shift-v1-20260930-corrected-r2/rows.jsonl
ecb7b1af4c4b1ddc6fab127037d432a6543cc999214d7ef18883a2eefa83112a  tests/benchmarks/robot_ops/evidence/codex-shift-v1-20260930-r0/episodes/0000_codex_full_shift_holdout_v1/codex-config.json
223ffbada2808fbe135a90559ecba119abbf6d3ea5d0df64af02c51604df3d53  tests/benchmarks/robot_ops/evidence/codex-shift-v1-20260930-r0/episodes/0000_codex_full_shift_holdout_v1/codex-events.jsonl
fa05dd3c47719dc7fde2d6daf4645fab3cfa8f340a63f21cdc39dbf96534494f  tests/benchmarks/robot_ops/evidence/codex-shift-v1-20260930-r0/episodes/0000_codex_full_shift_holdout_v1/engine.log.newton.json
5e126c8dca33e287189a46564a29f0a63f635e5d132715cecb70852e9c36ac90  tests/benchmarks/robot_ops/evidence/codex-shift-v1-20260930-r0/episodes/0000_codex_full_shift_holdout_v1/trace.json.gz
ef8bb6bf704898586abc5ef2ff56216bf4b822bd795022c932bfd9c36f1a7a5a  tests/benchmarks/robot_ops/evidence/codex-shift-v1-20260930-r0/manifest.json
cde9e593e7ebd8a08ded8b468e3885bf7fd824fa0139fbc2d6aa530c49abe199  tests/benchmarks/robot_ops/evidence/codex-shift-v1-20260930-r0/rows.jsonl
c907274763c4e6adb769002255053066b1ac4e5fa738fac6d57a8efd7af099ea  tests/benchmarks/robot_ops/evidence/codex-shift-v1-20260930-r1/episodes/0000_codex_full_shift_holdout_v1/codex-config.json
974d380a7556b4e923b1b11ec23715ba8d7dcf430c3fe888e631c64a7d8673a3  tests/benchmarks/robot_ops/evidence/codex-shift-v1-20260930-r1/episodes/0000_codex_full_shift_holdout_v1/codex-events.jsonl
fa05dd3c47719dc7fde2d6daf4645fab3cfa8f340a63f21cdc39dbf96534494f  tests/benchmarks/robot_ops/evidence/codex-shift-v1-20260930-r1/episodes/0000_codex_full_shift_holdout_v1/engine.log.newton.json
a3862d2a084a9e091903a351de306cce8fb3c8defee08a8567bc52698e126784  tests/benchmarks/robot_ops/evidence/codex-shift-v1-20260930-r1/episodes/0000_codex_full_shift_holdout_v1/trace.json.gz
a0d3b2fbff4b9499b3292a672ab452edae2a19c06ee6012aa735b0b02f51f795  tests/benchmarks/robot_ops/evidence/codex-shift-v1-20260930-r1/manifest.json
e54354417fe178aa9b4876b1b2497e11d7b84f21679dfee744c9089eb09b2e55  tests/benchmarks/robot_ops/evidence/codex-shift-v1-20260930-r1/rows.jsonl
88c35f82a52bd17210a5124597f368657ccf26cf110544a9ab99e894cba4b59d  tests/benchmarks/robot_ops/evidence/codex-shift-v1-20260930-r2/episodes/0000_codex_full_shift_holdout_v1/codex-config.json
b11f9ae971ac91282d59374f3529148df9244c0d98ae7be4e6c3977cde332ed9  tests/benchmarks/robot_ops/evidence/codex-shift-v1-20260930-r2/episodes/0000_codex_full_shift_holdout_v1/codex-events.jsonl
fa05dd3c47719dc7fde2d6daf4645fab3cfa8f340a63f21cdc39dbf96534494f  tests/benchmarks/robot_ops/evidence/codex-shift-v1-20260930-r2/episodes/0000_codex_full_shift_holdout_v1/engine.log.newton.json
ab9b571daa7e363bf5493cc0debed607ba6618c0a26e599551c64de1b45cbb52  tests/benchmarks/robot_ops/evidence/codex-shift-v1-20260930-r2/episodes/0000_codex_full_shift_holdout_v1/trace.json.gz
fd3e0b44331bbc9a24e6f900246364dc41df5f8668731365b992a4b79383f48e  tests/benchmarks/robot_ops/evidence/codex-shift-v1-20260930-r2/manifest.json
9ad67a370693853cd3cecc505eff18ff808d6fc5d732bf768fec5fc6aa2bf06b  tests/benchmarks/robot_ops/evidence/codex-shift-v1-20260930-r2/rows.jsonl
da8cc71906eab75bcf646b2eeb71d43c3446d8a32b05754816e88304e97164b3  tests/benchmarks/robot_ops/shift/CODEX_EXTENSION.md
0770cc0771a4a6d8db38823ba6282d65f5a1bf589f045a1f35fc42a1203e7094  tests/benchmarks/robot_ops/suites/shift_holdout_v1.json
436fa5a37733fa9028cf30eeb7497c5de2d7f3b63fb7ecefae875d3f6b7985cb  verify_codex.py
