Papers › Maia-2: A Unified Model for Human-AI Alignment in Chess

Maia-2: A Unified Model for Human-AI Alignment in Chess

30 Sep 2024arXiv:2409.20553archive 2025-07-28

Zhenwei Tang, Difan Jiao, Reid McIlroy-Young, Jon Kleinberg, Siddhartha Sen, Ashton Anderson

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.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 18 code samples harvested from 2 repositories linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 10 unverified. Where Syntology's instrument failed: 7 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 7 samples from 1 repository, 4 ran (0 with no instrument failure; 4 where Syntology's instrument failed); community (archive-listed): 11 samples from 1 repository, 4 ran (1 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

csslab/maia2 officialmentioned in papermentioned on GitHubpytorchMITSyntology: 7 samples, 4 ran (4 instrument-failed) · 3 unverified report
CSSLab/maia-chess mentioned on GitHubpytorchGPL-3.0Syntology: 11 samples, 4 ran (3 instrument-failed) · 7 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

18 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 10 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

7ran · our draft was wrong
1ran
10unverified

Licence: 11 of the 18 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

csslab/maia2 official repository 7 samples, 4 ran (4 instrument-failed) · 3 unverified
load_example_train_dataset maia2/dataset.py ran · our draft was wrong MIT (permissive) · 6008bedc62663800 · report fixture: returned str · level recorded 2026-09-24
parse_args in 355 papers maia2/utils.py ran · our draft was wrong MIT (permissive) · 2e197fc204c4df1b · report fixture: signature cfg_file_path:str/0/str · returned Config · level recorded 2026-09-24
readable_num maia2/utils.py ran · our draft was wrong fingerprinted MIT (permissive) · 3d01121e567b461a · report fixture: signature num:float/0/float · returned str · level recorded 2026-09-24
readable_time maia2/utils.py ran · our draft was wrong fingerprinted MIT (permissive) · 1b31d7f15a7a7f53 · report fixture: signature elapsed_time:float/0/float · returned str · level recorded 2026-09-24
from_pretrained maia2/model.py unverified MIT (permissive) · f2060b9a8207669c · report
get_preds in 18 papers maia2/inference.py unverified MIT (permissive) · 56ee634d6f4bdab3 · report
load_example_test_dataset maia2/dataset.py unverified MIT (permissive) · be0a07c0bc229683 · report
CSSLab/maia-chess community (archive-listed) 11 samples, 4 ran (3 instrument-failed) · 7 unverified
loadbzJson blunder_prediction/maia_chess_backend/boardTrees.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · 17ce924b3e8437ff · report fixture: signature filename:str/0/str · returned dict · level recorded 2026-09-24
nodeFromSeq blunder_prediction/maia_chess_backend/boardTrees.py ran GPL-3.0 (copyleft) · pointer only · 40c224517343d54a · report fixture: signature root:dict/0/?, seq:list/1/int · returned str · level recorded 2026-09-24
toBin blunder_prediction/maia_chess_backend/fen_to_vec.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · 88734a70ea400df9 · report fixture: signature c:str/0/str · returned bytes · level recorded 2026-09-24
toByteBuff blunder_prediction/maia_chess_backend/fen_to_vec.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · 326edeccdebb5bd9 · report fixture: signature l:list/1/bool · returned bytes · level recorded 2026-09-24
binarizeFiles blunder_prediction/maia_chess_backend/data_prep.py unverified GPL-3.0 (copyleft) · pointer only · af21b1c2558b6b63 · report
cleanFile blunder_prediction/maia_chess_backend/data_prep.py unverified GPL-3.0 (copyleft) · pointer only · f17b236a2f6e490c · report
genSeqs blunder_prediction/maia_chess_backend/boardTrees.py unverified GPL-3.0 (copyleft) · pointer only · eb4d1418a63392a6 · report
getBoardMoveMap blunder_prediction/maia_chess_backend/games.py unverified GPL-3.0 (copyleft) · pointer only · b821c7c8c900be7e · report
lczeroFile blunder_prediction/maia_chess_backend/data_prep.py unverified GPL-3.0 (copyleft) · pointer only · ada9bf8c1a4d8a69 · report
load_model_config in 8 papers blunder_prediction/maia_chess_backend/model_loader.py unverified GPL-3.0 (copyleft) · pointer only · 09eda5e6f21ccdab · report
move_to_index blunder_prediction/maia_chess_backend/fen_to_vec.py unverified GPL-3.0 (copyleft) · pointer only · 1dffeee3d0d0b59c · report

Tasks

Decision Making

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AlphaZeroAttentionSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections