52 Commits

Author	SHA1	Message	Date
Rowan Walshe	8f9cc4897a	Start adding HumanEval problems	2026-02-09 11:32:15 +00:00
Rowan Walshe	fd3e42bf1c	Remove the proof_steps metric	2026-01-28 10:32:37 +00:00
Rowan Walshe	891654ba98	Remove data/evalauted and data/generated	2026-01-28 10:32:12 +00:00
Rowan Walshe	80a1c293d1	Migrate dataset file contents to base64 encoding	2026-01-26 17:17:13 +00:00
Seb M'Caw	50de6e63b7	Update datasets to new EvaluationStats format	2025-10-16 13:48:46 +01:00
Seb M'Caw	3dbe2df1b3	Update datasets	2025-10-03 16:03:15 +01:00
Seb M'Caw	8d42535391	Run make pack-dataset	2025-10-02 10:17:21 +01:00
Seb M'Caw	8501aeb5c9	Add "required_checks" where appropriate	2025-09-26 17:36:25 +01:00
Seb M'Caw	4a9609b4d0	Remove redundant Loop_Invariant from char_count_2	2025-09-25 17:46:45 +01:00
Rowan Walshe	75fcb8902b	Add simple unit tests	2025-09-25 08:33:47 +01:00
Seb M'Caw	0786cba6e5	Also fix parameter order warning in base files of swap_depends	2025-09-08 12:33:32 +01:00
Seb M'Caw	b3028e3b8f	Update prompt for absolute_value to mention overflow warning	2025-09-08 12:26:08 +01:00
Seb M'Caw	9275c65f8f	Run make generate-dummy and make evaluate	2025-09-02 14:28:12 +01:00
Seb M'Caw	dc588f9d9f	Rename build stats attributes	2025-09-02 09:33:06 +01:00
Seb M'Caw	f0b5da214a	Cleaner fix for swap_depends compiler warning	2025-08-27 09:32:45 +01:00
Seb M'Caw	e6f71a156e	Reorder evals	2025-08-22 17:21:41 +01:00
Seb M'Caw	3f4e934b44	Fix serialisation of EvaluationStats.eval_name	2025-08-22 17:12:23 +01:00
Seb M'Caw	003e02d256	Shorten eval names	2025-08-22 16:15:00 +01:00
Seb M'Caw	b3a3e1bb89	Initial implementation of gprbuild eval	2025-08-22 13:29:46 +01:00
Seb M'Caw	817606e01f	Rerun dummy generation/evaluation	2025-08-20 10:46:13 +01:00
Seb M'Caw	d6c8fbc997	Detect missing subprograms explicitly	2025-08-07 12:39:14 +01:00
Seb M'Caw	c6bd319a6a	Restrict analysis with --limit-name	2025-08-07 11:42:31 +01:00
Seb M'Caw	4be79ccdb2	Fix absolute_value sample	2025-08-06 17:11:56 +01:00
Seb M'Caw	eb553d1042	Merge branch 'main' into mr/mcaw/implement-eval	2025-08-06 16:41:52 +01:00
Seb M'Caw	e7d2631607	Fix packing/unpacking with canonical_evaluation_results	2025-08-06 14:29:32 +01:00