156 commits

Author	SHA1	Message	Date
Andreas Köpf	5d7fbac0ad	Minor question template & score_answer improvements (#261) ... * math prompt improvements * ignore brackets in complex_arithmetic results * improve additional instruction in prompt of polynomial_equations * more strict tests for score_answer in polynomial_equations * simplify special reward handling * fix test_intermediate_integration * fix sokoban dataset * add common dataset score_answer consistency test	2025-03-04 21:55:09 +01:00
Andreas Köpf	c0cf237474	Reduce precision from 28 to 6 in DecimalArithmeticDataset (#256)	2025-03-03 21:57:08 +01:00
Zafir Stojanovski	01e1c8f9af	fix: Unify Prompts (#254) ... * remove cot * fix prompt template * fix pool matrix * spiral matrix fixed	2025-03-03 21:55:53 +01:00
Andreas Köpf	24828e1889	Remove strip from ProceduralDataset::core score_answer() (#250) ... * remove strip from ProceduralDataset::core score_answer(), strip in extract answer (optional, default=True) * test: Move test_extract_answer() from test_dataset.py to test_utils.py * refactor: Improve decimal reward computation with more flexible comparison * fix: Implement rounding for format_number when round_if_needed is True * test: Add test case for compute_decimal_reward with sign and zeros	2025-03-02 08:46:36 +01:00
Rich Jones	253e49aecf	sm fixes	2025-02-27 11:54:04 +01:00
vncntt	5f01049607	Add KnightsKnavesDataset (knights_knaves) ... Adapted code from https://github.com/AlphaPav/mem-kk-logic/blob/main/data_prep/lib_kk.py --------- Co-authored-by: Andreas Koepf (aider) <andreas.koepf@provisio.com>	2025-02-25 20:15:38 +01:00
Andreas Koepf	eeb9fa31d5	more native type hints	2025-02-21 21:23:14 +01:00
Andreas Köpf	1c6359f1f3	Merge pull request #181 from open-thought/rich/bitwise ... Add Bitwise Arithmetic	2025-02-21 17:27:45 +01:00
Andreas Koepf (aider)	bae97aa795	docs: Add comment explaining automatic base detection in int() conversion	2025-02-21 17:16:11 +01:00
Andreas Koepf (aider)	5ff957a766	docs: Add detailed comments for BitwiseArithmeticConfig and BitwiseArithmeticDataset	2025-02-21 17:14:00 +01:00
Andreas Koepf	44f4cc08eb	refactor: Update type hints and remove unused imports in bitwise_arithmetic.py	2025-02-21 17:13:36 +01:00
Andreas Koepf (aider)	c91d13bd08	feat: Add typing hints and improve difficulty parameter documentation in bitwise_arithmetic.py	2025-02-21 17:11:40 +01:00
Rich Jones	1cf6821f17	lint	2025-02-21 17:09:19 +01:00
Rich Jones	c1b26cf184	ensure arbitrary bit depth and signed values	2025-02-21 16:52:26 +01:00
Andreas Koepf	acde58a200	use Decimal class for numeric comparison e.g. +0123.100 == 123.1	2025-02-21 15:36:06 +01:00
Andreas Koepf	3e7ff3b084	use native types List->list, Dict->dict, Set->set, Tuple->tuple	2025-02-21 15:15:38 +01:00
AhmedSaif2	5d02064b5a	add a helper function to handle redundant code	2025-02-21 15:54:00 +02:00
Rich Jones	b6c7ceabb2	clean up comments	2025-02-21 12:17:21 +01:00
Rich Jones	ee9202d63d	add to init	2025-02-21 12:07:17 +01:00
Rich Jones	17088e9b42	add bitwise arithmetic	2025-02-21 12:02:41 +01:00
AhmedSaif2	73dfaa7f58	remove added instructions	2025-02-20 21:29:01 +02:00
AhmedSaif2	dcdef3f9ec	Add score answer to support comma format	2025-02-20 20:52:31 +02:00
Andreas Köpf	e25973b118	Merge pull request #158 from open-thought/rich/decimalmath ... Decimal Arithmetic	2025-02-20 12:35:41 +01:00
Rich Jones	2eaffb9837	lint	2025-02-20 12:29:12 +01:00
Rich Jones	0b7c221cb6	type hints ... blind roboting	2025-02-20 12:10:28 +01:00
ahmedsaif	14b2f1f99d	Add allow-negation in products dataset	2025-02-20 12:01:09 +02:00
Rich Jones	da9b215278	add to init	2025-02-20 10:51:00 +01:00
Rich Jones	0f965c157f	Merge branch 'rich/decimalmath' of github.com:open-thought/reasoning-gym into rich/decimalmath	2025-02-20 10:46:13 +01:00
Rich Jones	556860d5b1	add random paren grouping	2025-02-20 10:46:01 +01:00
Rich Jones	edba52d2a2	Merge branch 'main' into rich/decimalmath	2025-02-20 10:07:28 +01:00
vncntt	992896af29	Merge branch 'open-thought:main' into decimal_chain_sum	2025-02-19 15:31:20 -08:00
vncntt	cdcd79ae2b	register decimal_chain_sum	2025-02-19 15:30:30 -08:00
Andreas Köpf	1cf44267f3	Merge pull request #164 from vncntt/decimal_chain_sum ... decimal_chain_sum	2025-02-20 00:14:23 +01:00
vncntt	83e5e92126	decimal refactor	2025-02-19 14:46:27 -08:00
Rich Jones	17ba950c1a	implement decimal precision	2025-02-19 12:30:07 +01:00
Zafir Stojanovski	f9a3fd4ddf	number format	2025-02-19 11:41:06 +01:00
vncntt	60cedc62dd	decimal_chain_sum	2025-02-19 01:51:10 -08:00
Andreas Koepf	667d088f55	remove redundant assert in ChainSumConfig.validate()	2025-02-19 09:42:32 +01:00
Rich Jones	59229bd2d2	Merge branch 'rich/decimalmath' of github.com:open-thought/reasoning-gym into rich/decimalmath	2025-02-19 03:34:57 +01:00
Rich Jones	19b697c89a	[wip] more flexible api	2025-02-19 03:29:40 +01:00
Rich Jones	2532cdce8e	Merge branch 'main' into rich/decimalmath	2025-02-18 20:53:36 +01:00
Rich Jones	46cdfc71cf	lint	2025-02-18 19:22:03 +01:00
Rich Jones	80d8dbcc36	decimal math	2025-02-18 19:20:33 +01:00
Andreas Koepf	203394314e	minor formatting changes	2025-02-17 18:20:18 +01:00
abdulhakeem	15140d06e7	Tweaked some question templates	2025-02-17 02:58:42 -06:00
Andreas Koepf	2cbaab2918	fix question templates	2025-02-16 23:04:24 +01:00
joesharratt1229	95f179f34e	Merge pull request #144 from joesharratt1229/fix/arithmetic ... Added fixes for arithmetic environments	2025-02-16 16:34:09 +00:00
joesharratt1229	6b82654074	adjusted gsm symbolic question template	2025-02-16 15:28:44 +00:00
joesharratt1229	44bc04c00b	changed products question template	2025-02-16 15:18:41 +00:00
Andreas Koepf	44f8d7b6af	formatting	2025-02-16 16:18:39 +01:00