MétaCan
Menu
Back to cohort

Learning to Slide: Cross-Size Graph Neural Heuristics for Optimal Puzzle Solving

2025· article· W4416363507 on OpenAlex
Keyin Liu

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueTheoretical and Natural Science · 2025
Typearticle
Language
FieldEngineering
Topic3D Shape Modeling and Analysis
Canadian institutionsUniversity of Toronto
Fundersnot available
KeywordsHeuristicsArtificial neural networkHeuristicGraphInferenceRangingScalabilityEmbeddingDPLL algorithm

Abstract

fetched live from OpenAlex

Heuristic techniques such as A* and IDA* with Manhattan distance or linear conflict as heuristics fall short for larger sliding-tile puzzles. This is quite unfortunate as the sliding-tile puzzle is often used as a heuristic search benchmark. We introduce PuzzleGNN, a size-adaptive graph neural network that learns cross-size heuristics for puzzles ranging from 3× 3 to 7 × 7. By encapsulating tiles and adjacencies as graph nodes and edges and embedding the board size into the model, PuzzleGNN functions as a predictor of optimal step counts for puzzles. After being trained on solutions generated by IDA*, PuzzleGNN achieved R2 ≥ 0.85 within its trained range, performing 10 to 30 times faster in inference compared to A*, and excelling on mid-sized boards with a mean absolute error (MAE) of 0.62 on 6 × 6. Nonetheless, while generalizing PuzzleGNN to unseen configurations remains challenging, a promising approach is to fuse neural and admissible heuristics as a means to achieving optimal, scalable search in combinatorial domains.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.003
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Science and technology studies
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.534
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.003
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.002
Science and technology studies0.0010.002
Scholarly communication0.0010.000
Open science0.0010.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.005
GPT teacher head0.270
Teacher spread0.265 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it