39 Commits

Author	SHA1	Message	Date
Qi Liu	f4cc21cc96	Async: implemented; MiniF2F: fixed	2024-12-13 06:15:52 +00:00
Leni Aniva	ffacb67a03	fix: DSP output	2024-12-11 21:30:40 -08:00
Leni Aniva	56fc11f831	fix: Experiments with new `load_sorry`	2024-12-11 17:32:07 -08:00
Leni Aniva	8585e3dd9e	Merge pull request #24 from lenianiva/experiments/minif2f ... experiment: MiniF2F speedup	2024-10-13 19:21:16 -07:00
Leni Aniva	8196493258	feat: Handle exceptions in tactic generation	2024-10-11 22:51:20 -07:00
Leni Aniva	9fc035d466	fix: Filter invalid messages	2024-10-11 17:06:31 -07:00
Leni Aniva	cd05b67c10	fix: Filter out val/test data	2024-10-09 18:23:21 -07:00
Leni Aniva	ca66f52a1e	feat: o1-preview experiments	2024-10-08 21:44:14 -07:00
Leni Aniva	8c22ce09e7	feat: Plot generation for DSP	2024-10-08 19:20:57 -07:00
Leni Aniva	35f093821d	chore: Update upstream to fix bugs	2024-10-08 17:59:48 -07:00
Leni Aniva	76eb57b22e	fix: Prompt Lean code extraction	2024-10-07 18:58:35 -07:00
Leni Aniva	30cd3063f9	feat: Multiple sketches	2024-10-07 08:30:03 -07:00
Leni Aniva	789452f7b7	feat: Add stat function to show prove rate	2024-10-06 23:29:14 -07:00
Leni Aniva	a281557d0a	Merge branch 'misc/version' into experiments/dsp	2024-10-06 22:06:07 -07:00
Leni Aniva	034fd458e3	chore: Update Pantograph and Lean version to 4.12	2024-10-06 22:04:10 -07:00
Leni Aniva	7770c0fb59	feat: Error feedback in DSP	2024-10-06 19:14:38 -07:00
Leni Aniva	159da09c9d	Merge branch 'main' into experiments/minif2f	2024-10-05 22:31:22 -07:00
Leni Aniva	48f2f2cb5a	feat: Add handling for errors in compilation	2024-10-05 15:38:35 -07:00
Leni Aniva	104d2451b1	feat: Add more automation to `HammerAgent`	2024-10-05 01:26:19 -07:00
Leni Aniva	97f22ed67a	feat: Output experiment result into folder	2024-10-05 01:23:38 -07:00
Leni Aniva	0ab29e11cd	Merge branch 'experiments/dsp' into experiments/minif2f	2024-10-05 01:05:25 -07:00
Leni Aniva	1fde034dce	fix: Remove barrier that halts problem iter	2024-10-05 00:59:28 -07:00
Leni Aniva	3b76080495	feat: Search on minif2f	2024-10-04 21:55:47 -07:00
Leni Aniva	d94e3086c1	fix: Lean source project for DSP	2024-10-04 18:53:00 -07:00
Leni Aniva	82d9f9200e	refactor: Pass in `informal_{stmt,proof}` directly	2024-10-04 18:45:13 -07:00
Leni Aniva	9fd930380d	feat: Hammer agent for DSP, diagnostics	2024-10-04 18:36:52 -07:00
Leni Aniva	5b176795b2	doc: Diagnostics info at result	2024-10-04 18:04:10 -07:00
Leni Aniva	542784caa2	fix: Trailing comma in reply, remove simp fallback	2024-10-04 18:01:48 -07:00
Leni Aniva	2fae5e97f1	feat: Concise prompts and unhygienic mode	2024-10-04 17:55:32 -07:00
Leni Aniva	20f3011eb4	doc: Improve error message	2024-10-03 15:45:14 -07:00
Leni Aniva	b440363105	fix: Skip the commented out test cases	2024-10-03 12:58:39 -07:00
Leni Aniva	a30225069a	refactor: All MiniF2F into its own directory	2024-10-03 12:53:07 -07:00
Leni Aniva	80a356c75c	feat: Extract Lean code sections from sketches	2024-10-03 12:26:42 -07:00
Leni Aniva	f1e996baae	fix: Argument passing in dsp	2024-10-03 12:03:33 -07:00
Leni Aniva	3221cfb45b	refactor: Prompt debug printing into dsp main	2024-10-02 16:10:52 -07:00
Leni Aniva	ce2d689b03	refactor: Clarify code in dsp	2024-10-02 11:03:00 -07:00
Leni Aniva	e942359666	fix: Absolute directories in experiments ... doc: Add documentation about API key	2024-10-01 11:34:30 -07:00
Leni Aniva	95e90cc026	refactor: Experiments into their own folders	2024-10-01 11:06:01 -07:00
Leni Aniva	01ec8fa22a	refactor: Update the experiment repo Lean version, use new load_sorry API	2024-09-13 18:18:53 -07:00