Ashton Anderson, Jon Kleinberg, Siddhartha Sen, Reid Mcilroy-Young, Zhenwei Tang, Difan Jiao
We lifted 18 functions out of this paper's own repositories and ran 8 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| CSSLab/maia-chess | canonical | 4 of 11 |
| csslab/maia2 | canonical | 4 of 6 |
| CSSLab/maia2 | canonical | 0 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| load_example_train_dataset | Ran | csslab/maia2/maia2/dataset.py code served (permissive licence) · get_code("6008bedc62663800") |
| loadbzJson | Ran | CSSLab/maia-chess/blunder_prediction/maia_chess_backend/boardTrees.py pointer only (licence: GPL-3.0) · get_code("17ce924b3e8437ff") |
| nodeFromSeq | Ran | CSSLab/maia-chess/blunder_prediction/maia_chess_backend/boardTrees.py pointer only (licence: GPL-3.0) · get_code("40c224517343d54a") |
| parse_args | Ran | csslab/maia2/maia2/utils.py code served (permissive licence) · get_code("2e197fc204c4df1b") |
| readable_num | Ran | csslab/maia2/maia2/utils.py code served (permissive licence) · get_code("3d01121e567b461a") |
| readable_time | Ran | csslab/maia2/maia2/utils.py code served (permissive licence) · get_code("1b31d7f15a7a7f53") |
| toBin | Ran | CSSLab/maia-chess/blunder_prediction/maia_chess_backend/fen_to_vec.py pointer only (licence: GPL-3.0) · get_code("88734a70ea400df9") |
| toByteBuff | Ran | CSSLab/maia-chess/blunder_prediction/maia_chess_backend/fen_to_vec.py pointer only (licence: GPL-3.0) · get_code("326edeccdebb5bd9") |
| binarizeFiles | Not yet run | CSSLab/maia-chess/blunder_prediction/maia_chess_backend/data_prep.py pointer only (licence: GPL-3.0) · get_code("af21b1c2558b6b63") |
| cleanFile | Not yet run | CSSLab/maia-chess/blunder_prediction/maia_chess_backend/data_prep.py pointer only (licence: GPL-3.0) · get_code("f17b236a2f6e490c") |
| from_pretrained | Not yet run | csslab/maia2/maia2/model.py code served (permissive licence) · get_code("f2060b9a8207669c") |
| genSeqs | Not yet run | CSSLab/maia-chess/blunder_prediction/maia_chess_backend/boardTrees.py pointer only (licence: GPL-3.0) · get_code("eb4d1418a63392a6") |
| getBoardMoveMap | Not yet run | CSSLab/maia-chess/blunder_prediction/maia_chess_backend/games.py pointer only (licence: GPL-3.0) · get_code("b821c7c8c900be7e") |
| get_preds | Not yet run | CSSLab/maia2/maia2/inference.py code served (permissive licence) · get_code("56ee634d6f4bdab3") |
| lczeroFile | Not yet run | CSSLab/maia-chess/blunder_prediction/maia_chess_backend/data_prep.py pointer only (licence: GPL-3.0) · get_code("ada9bf8c1a4d8a69") |
| load_example_test_dataset | Not yet run | csslab/maia2/maia2/dataset.py code served (permissive licence) · get_code("be0a07c0bc229683") |
| load_model_config | Not yet run | CSSLab/maia-chess/blunder_prediction/maia_chess_backend/model_loader.py pointer only (licence: GPL-3.0) · get_code("09eda5e6f21ccdab") |
| move_to_index | Not yet run | CSSLab/maia-chess/blunder_prediction/maia_chess_backend/fen_to_vec.py pointer only (licence: GPL-3.0) · get_code("1dffeee3d0d0b59c") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
There are an increasing number of domains in which artificial intelligence (AI) systems both surpass human ability and accurately model human behavior. This introduces the possibility of algorithmically-informed teaching in these domains through more relatable AI partners and deeper insights into human decision-making. Critical to achieving this goal, however, is coherently modeling human behavior at various skill levels. Chess is an ideal model system for conducting research into this kind of human-AI alignment, with its rich history as a pivotal testbed for AI research, mature superhuman AI systems like AlphaZero, and precise measurements of skill via chess rating systems. Previous work in modeling human decision-making in chess uses completely independent models to capture human style at different skill levels, meaning they lack coherence in their ability to adapt to the full spectrum of human improvement and are ultimately limited in their effectiveness as AI partners and teaching tools. In this work, we propose a unified modeling approach for human-AI alignment in chess that coherently captures human style across different skill levels and directly captures how people improve. Recognizing the complex, non-linear nature of human learning, we introduce a skill-aware attention mechanism to dynamically integrate players' strengths with encoded chess positions, enabling our model to be sensitive to evolving player skill. Our experimental results demonstrate that this unified framework significantly enhances the alignment between AI and human players across a diverse range of expertise levels, paving the way for deeper insights into human decision-making and AI-guided teaching tools. Our implementation is available here.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2409.20553")
get_code_for_paper("2409.20553")
have("2409.20553")
Connect an agent — have() is free.