Batch 26 commit 7f99538 measured 1 HARD (FreeRTOS loopback and mDNS state, where Qwen ran out of context in all three attempts), 3 MEDIUM (canmatrix JSON round trip, Zephyr byte-value formatting, Contiki event timer sleep) and 4 ROUTINE; two tasks still need more valid attempts. From batch 27 the lazy integer expression task becomes MEDIUM once its top-up attempts are added. Each task comes from the commit Qwen measured, its digest matches, and it is still present at the batch branch head. Attempts made while /home was below the 20 GiB sampling floor are recorded as disk_low and left out. Batches 26, 28 and 29 are stopped: after a login refresh on 11-03 the Codex account no longer offers the sol models they use. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
32 lines
768 B
JSON
32 lines
768 B
JSON
{
|
|
"id": "config-lazy-integer-expression",
|
|
"version": "1",
|
|
"family": "config-calibration",
|
|
"source": "original/config-lazy-integer-expression",
|
|
"language": "python",
|
|
"template": "template",
|
|
"verifier": "verify.py",
|
|
"candidate_files": [
|
|
"lazy_integer.py"
|
|
],
|
|
"grader_files": [
|
|
"check.py"
|
|
],
|
|
"timeout_seconds": 60,
|
|
"fixtures": {
|
|
"gold": "PASS",
|
|
"template": "FAIL",
|
|
"noop": "FAIL",
|
|
"cheat": "FAIL",
|
|
"cheat_read_grader": "FAIL",
|
|
"near_upper_endpoint": "FAIL",
|
|
"near_floor_division": "FAIL",
|
|
"near_right_first": "FAIL",
|
|
"valid_stack": "PASS",
|
|
"valid_subclasses": "PASS",
|
|
"cheat_mutate_input": "FAIL",
|
|
"cheat_named_error": "FAIL"
|
|
},
|
|
"split_group": "bounded-lazy-infix-integer-expression"
|
|
}
|