SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.06923 · ICML · 2026

From Kepler to Newton: Inductive Biases Guide Learned World Models in Transformers

Surya Ganguli, Andreas Tolias, Ziming Liu, Sophia Sanborn

arXiv · PDF · Open in the Atlas

Code that ran

14 of 15 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 6 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 8 failures of our instrument; 1 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2602.06923.json · badge: /api/ran/2602.06923.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
KindXiaoming/newton-kepler canonical (classifier label)
classifier basis: census
14 ran · 1 no recorded run
FunctionStatusWhere it lives
bin_trajectories Ran
ran; our contract draft was wrong, not the code
KindXiaoming/newton-kepler/generate_dataset.py
pointer only (licence: NONE) · get_code("1b8a43106c1a4c26")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KindXiaoming/newton-kepler when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

bin_trajectories Ran
ran; our contract draft was wrong, not the code
KindXiaoming/newton-kepler/sine.py
pointer only (licence: NONE) · get_code("17b190041a876f73")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KindXiaoming/newton-kepler when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

chop_trajectories_into_sequences Ran
ran; our contract draft was wrong, not the code
KindXiaoming/newton-kepler/kepler_cv_blocksize.py
pointer only (licence: NONE) · get_code("89a461bd7bbca0ec")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KindXiaoming/newton-kepler when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

compute_bins_and_tokenize Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
KindXiaoming/newton-kepler/kepler.py
pointer only (licence: NONE) · get_code("d20b160c467fd33e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KindXiaoming/newton-kepler when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

generate_data_inline Ran
ran, honoured the contract we drafted
KindXiaoming/newton-kepler/sine.py
pointer only (licence: NONE) · get_code("ce2e54426b296095")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KindXiaoming/newton-kepler when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

generate_kepler_trajectory Ran
ran, honoured the contract we drafted
KindXiaoming/newton-kepler/generate_kepler_cv.py
pointer only (licence: NONE) · get_code("fc8d22f673cacc8e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KindXiaoming/newton-kepler when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

generate_kepler_trajectory_euler Ran
ran, honoured the contract we drafted
KindXiaoming/newton-kepler/generate_kepler_cv.py
pointer only (licence: NONE) · get_code("2b6930bb8f77d523")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KindXiaoming/newton-kepler when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

generate_sine_wave_data Ran
ran; our contract draft was wrong, not the code
KindXiaoming/newton-kepler/generate_dataset.py
pointer only (licence: NONE) · get_code("e65dd229c75a7bbe")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KindXiaoming/newton-kepler when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_sequential_batch Ran
ran, honoured the contract we drafted
KindXiaoming/newton-kepler/fig2_vafa_spatial_map/train_utils.py
pointer only (licence: NONE) · get_code("980b906765e0aae2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KindXiaoming/newton-kepler when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

kepler_orbit Ran
ran; our contract draft was wrong, not the code
KindXiaoming/newton-kepler/generate_kepler_cv.py
pointer only (licence: NONE) · get_code("703cab57e803be11")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KindXiaoming/newton-kepler when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_trajectories Ran
ran, honoured the contract we drafted
KindXiaoming/newton-kepler/kepler.py
pointer only (licence: NONE) · get_code("e75836153ab7e442")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KindXiaoming/newton-kepler when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_trajectories Ran
ran, honoured the contract we drafted
KindXiaoming/newton-kepler/kepler_cv_blocksize.py
pointer only (licence: NONE) · get_code("f06d7888d73cea85")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KindXiaoming/newton-kepler when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

print_gpu_memory_stats Ran
ran; our contract draft was wrong, not the code
KindXiaoming/newton-kepler/kepler.py
pointer only (licence: NONE) · get_code("e3e2a1f1061a9341")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KindXiaoming/newton-kepler when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

setup_training_environment Ran
ran; our contract draft was wrong, not the code
KindXiaoming/newton-kepler/fig2_vafa_spatial_map/train_utils.py
pointer only (licence: NONE) · get_code("d51bf3b9c3bf2b15")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KindXiaoming/newton-kepler when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

add_common_args Not yet run
unverified (harvested, no recorded run)
KindXiaoming/newton-kepler/fig2_vafa_spatial_map/train_utils.py
pointer only (licence: NONE) · get_code("7aa5533e52e4ba12")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KindXiaoming/newton-kepler when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 15 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Can general-purpose AI architectures go beyond prediction to discover the physical laws governing the universe? True intelligence relies on "world models"-causal abstractions that allow an agent to not only predict future states but understand the underlying governing dynamics. While previous "AI Physicist" approaches have successfully recovered such laws, they typically rely on strong, domain-specific priors that effectively "bake in" the physics. Conversely, Vafa et al. ( 2025) recently showed that generic Transformers fail to acquire these world models, achieving high predictive accuracy without capturing the underlying physical laws. We bridge this gap by systematically introducing three minimal inductive biases. We show that ensuring spatial smoothness (by formulating prediction as continuous regression) and stability (by training with noisy contexts to mitigate error accumulation) enables generic Transformers to surpass prior failures and learn a coherent Keplerian world model, successfully fitting ellipses to planetary trajectories. However, true physical insight requires a third bias: temporal locality. By restricting the attention window to the immediate past-imposing the simple assumption that future states depend only on the local state rather than a complex history-we force the model to abandon curve-fitting and discover Newtonian force representations. Our results demonstrate that simple architectural choices determine whether an AI becomes a curve-fitter or a physicist, marking a critical step toward automated scientific discovery.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2602.06923")
get_code_for_paper("2602.06923")
have("2602.06923")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2602.06923.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2602.06923.svg)](https://syntology.ai/paper/2602.06923)

Connect an agent — have() is free.