joesharratt1229
a28f78812b
Curriculum/cognition ( #314 )
...
* added rectangle count curriculum
* added number sequences
* registered curriculum
2025-03-11 00:10:28 +01:00
Rich Jones
46013e4640
BF Curricula and More ( #309 )
...
* bf curricula
* modulo grid curricula
* minor changes to how difficulty is stored
---------
Co-authored-by: Andreas Koepf <andreas.koepf@provisio.com>
2025-03-09 18:22:22 +01:00
Rich Jones
34889d0517
Add Modulo Grid Task ( #273 )
...
* add modulo_grid dataset
* ensure the pattern is mathematical, not just spatial
---------
Co-authored-by: Andreas Koepf <andreas.koepf@provisio.com>
2025-03-07 11:11:41 +01:00
Andreas Köpf
b2904ccab9
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
Zafir Stojanovski
2f9d94c1e7
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
ed90fff3fa
Merge pull request #220 from open-thought/rich/cubeinstructions
...
Make Rubiks Cube Output Format More Explicit
2025-02-27 12:16:09 +01:00
Rich Jones
a1b1272e8d
sm fixes
2025-02-27 11:54:04 +01:00
Rich Jones
9daaccc208
expand more
2025-02-27 10:41:30 +01:00
Rich Jones
214e9d4957
support expanded notation anyway
2025-02-26 13:17:03 +01:00
Rich Jones
b252937f99
rubiks cube instructions
2025-02-26 13:07:17 +01:00
Rich Jones
f2479fcacc
fix CCC scoring
2025-02-26 12:54:40 +01:00
Andreas Koepf
74f590e24f
more native type hints
2025-02-21 21:23:14 +01:00
Andreas Köpf
1e0f67f7a2
Merge pull request #175 from AhmedSaif2/fix-format
...
Add score_answer function to handle comma-formatted numbers
2025-02-21 15:36:21 +01:00
Andreas Koepf
ff5b210106
use native types List->list, Dict->dict, Set->set, Tuple->tuple
2025-02-21 15:15:38 +01:00
Andreas Köpf
5440649720
Merge pull request #170 from open-thought/rich/needle
...
Adds Needle in a Haystack problems
2025-02-20 22:12:47 +01:00
Rich Jones
af5bb57218
wiggle imports
2025-02-20 16:23:40 +01:00
Rich Jones
9322d83358
move assert to config
2025-02-20 12:45:09 +01:00
Rich Jones
c3ced61c6e
adds Needle in a Haystack problems
2025-02-20 12:28:30 +01:00
Rich Jones
da0b882b87
rc gallery format
2025-02-20 11:26:05 +01:00
joesharratt1229
1a27d9b0a4
added colour cube score answer impl
2025-02-19 18:12:31 +00:00
Zafir Stojanovski
1c75f7cfd2
fix prompt
2025-02-17 16:12:50 +01:00
Andreas Koepf
92ffda4b8b
lazy import of wordle_words
2025-02-14 12:06:44 +01:00
Rich Jones
2fa1ea106d
add rectangle count dataset
2025-02-11 13:56:27 +01:00
Andreas Koepf
2ad0965fdc
move arc_1d into from cognition into arc folder
2025-02-08 19:37:26 +01:00
Andreas Köpf
a607db79f7
Add Coaching & ScoreBoard class (result tracking) ( #72 )
...
* feat: Add Coach and ScoreBoard classes for performance tracking and difficulty adjustment
* feat: Add GroupedScores class to wrap aggregated scores
* refactor: Create ScoreStats class with tuple-based score statistics
* feat: Add unit test for Coach with CompositeDataset and multiple datasets
* fix: Add difficulty metadata to leg counting dataset
* feat: Add clear() method to ScoreBoard to reset all stored data
* feat: Add __len__ method to ScoreBoard to return number of scores
* feat: Add update_dataset_config method to CompositeDataset
* cleanup __init__ & imports
2025-02-06 23:15:28 +01:00
Andreas Koepf
8dc496bc35
add attribution for arc-1d and unit tests
2025-02-02 23:45:25 +01:00
Andreas Koepf (aider)
2b978de850
feat: Add mirrored and inverse task variations to ARC_1D_TASKS
2025-02-02 23:21:46 +01:00
Andreas Koepf
f8c7807892
add arc_1d dataset
2025-02-02 23:03:56 +01:00
Andreas Koepf (aider)
52c86ed327
fix: Resolve undefined task function references in arc_1d.py
2025-02-02 22:49:28 +01:00
Andreas Koepf (aider)
67027b828f
feat: Add Arc1D dataset with comprehensive task generation and configuration
2025-02-02 22:49:00 +01:00
Andreas Koepf (aider)
017148d78d
feat: Add task augmentation functions mirror, inverse, and identity to arc_1d.py
2025-02-02 22:42:21 +01:00
Andreas Koepf
604db012c3
change parameter order for basic arc tasks
2025-02-02 17:25:37 +01:00
Andreas Koepf (aider)
845a80711f
feat: Add five new 1D ARC task generation functions
2025-02-02 16:38:14 +01:00
Andreas Koepf (aider)
e55266c5e6
feat: Add five new 1D ARC task generation functions
2025-02-02 16:37:14 +01:00
Andreas Koepf (aider)
5b4998049a
feat: Add new 1D ARC task generation functions for block manipulation
2025-02-02 16:36:19 +01:00
Andreas Koepf (aider)
c3a527aed3
feat: Add new 1D ARC task generation functions
2025-02-02 16:34:52 +01:00
Andreas Koepf (aider)
185c5d7504
feat: Add new 1D task generation functions to arc_1d.py
2025-02-02 16:33:02 +01:00
Andreas Koepf
8a153d9857
feat: Add arc_1d.py module for one-dimensional abstract reasoning challenges
2025-02-02 16:33:01 +01:00
Andreas Koepf
25540b6634
lint
2025-01-30 22:55:04 +01:00
Rich Jones
645aa13a15
init definitions
2025-01-30 17:15:48 +01:00
Andreas Koepf
d90548658e
fix chain_sum unit test
2025-01-30 10:57:55 +01:00
Andreas Koepf
f75cc3e17e
catch exception in RubiksCube score_answer
2025-01-30 10:25:04 +01:00
Andreas Koepf
87bf5d6f9a
rename static.py -> wordle_words.py
2025-01-30 01:06:52 +01:00
Andreas Koepf
9450768aad
lint, seed & size for figlet
2025-01-30 00:58:34 +01:00
Andreas Koepf
9e0a59f847
add seed & size params to RubicsCubeConfig
2025-01-30 00:49:41 +01:00
Andreas Koepf
f1e554beb8
make sure rubiks cube is scrambled deterministically based on seed+idx
2025-01-30 00:36:34 +01:00
Andreas Köpf
4b02834aa0
Merge branch 'main' into miserlou/figlet
2025-01-29 23:59:27 +01:00
Rich Jones
75fba9d864
optional space letters, default true since it seems to perform slightly better
2025-01-29 21:38:54 +01:00
Rich Jones
d6bab78fa1
figlet fonts
2025-01-29 20:38:38 +01:00
Rich Jones
9c4e820fc4
lint
2025-01-29 16:09:39 +01:00
