Papers › AI Feynman 2.0: Pareto-optimal symbolic regression exploiting graph modularity

AI Feynman 2.0: Pareto-optimal symbolic regression exploiting graph modularity

18 Jun 2020NeurIPS 2020 12arXiv:2006.10782archive 2025-07-28

Silviu-Marian Udrescu, Andrew Tan, Jiahai Feng, Orisvaldo Neto, Tailin Wu, Max Tegmark

We present an improved method for symbolic regression that seeks to fit data to formulas that are Pareto-optimal, in the sense of having the best accuracy for a given complexity. It improves on the previous state-of-the-art by typically being orders of magnitude more robust toward noise and bad data, and also by discovering many formulas that stumped previous methods. We develop a method for discovering generalized symmetries (arbitrary modularity in the computational graph of a formula) from gradient properties of a neural network fit. We use normalizing flows to generalize our symbolic regression method to probability distributions from which we only have samples, and employ statistical hypothesis testing to accelerate robust brute-force search.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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 20 code samples harvested from 2 repositories linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 20 samples from 2 repositories, 12 ran (8 with no instrument failure; 4 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 between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

SJ001/AI-Feynman mentioned on GitHubpytorchMITSyntology: 13 samples, 7 ran (0 instrument-failed) · 6 unverified report
zykhoo/ai-feynman mentioned on GitHubpytorchSyntology: 7 samples, 5 ran (4 instrument-failed) · 2 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

20 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
4ran · our draft was wrong
7ran
8unverified

Licence: 0 of the 20 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.

SJ001/AI-Feynman community (archive-listed) 13 samples, 7 ran (0 instrument-failed) · 6 unverified
NN_eval aifeynman/S_NN_eval.py ran fingerprinted MIT (permissive) · 4a9e454bb7c407bf · report fixture: signature pathdir:str/0/str, filename:str/0/str · returned tuple · level recorded 2026-09-25
RPN_to_eq aifeynman/RPN_to_eq.py ran fingerprinted MIT (permissive) · 7c2df61572f9e3c0 · report fixture: signature expr:str/0/str · returned str_ · level recorded 2026-09-25
add_bf_on_numbers_on_pareto aifeynman/S_add_bf_on_numbers_on_pareto.py ran MIT (permissive) · aefecb64907f3e4f · report fixture: returned MockPareto · level recorded 2026-09-25
add_snap_expr_on_pareto aifeynman/S_add_snap_expr_on_pareto.py ran MIT (permissive) · 799d88fb2639c6a0 · report fixture: signature pathdir:str/0/str, filename:str/0/str, math_expr:str/0/str, PA:ndarray/2/float, DR_file:str/0/str · returned ndarray · level recorded 2026-09-25
evaluate_derivatives aifeynman/S_NN_get_gradients.py ran MIT (permissive) · 6fc741317fe3c443 · report fixture: signature pathdir:str/0/str, filename:str/0/str, model:callable/0/? · returned int · level recorded 2026-09-25
intify aifeynman/S_add_snap_expr_on_pareto.py ran MIT (permissive) · a081d0e97957a1f7 · report fixture: signature expr:Add/0/? · returned Add · level recorded 2026-09-25
rmse_loss aifeynman/S_NN_eval.py ran fingerprinted MIT (permissive) · f194288004a3dba8 · report fixture: signature pred:Tensor/2/float, targ:Tensor/2/float · returned Tensor · level recorded 2026-09-25
NN_train aifeynman/S_NN_train.py unverified MIT (permissive) · 1f12c200481a3f18 · report
RPN_to_pytorch aifeynman/RPN_to_pytorch.py unverified MIT (permissive) · f71b2f2208f359cc · report
add_sym_on_pareto aifeynman/S_add_sym_on_pareto.py unverified MIT (permissive) · 9198af899b3208cb · report
brute_force_comp aifeynman/S_brute_force_comp.py unverified MIT (permissive) · 5139d3e67c91cdd3 · report
brute_force_gen_sym aifeynman/S_brute_force_gen_sym.py unverified MIT (permissive) · 947b21e6e1a2cb74 · report
brute_force_number aifeynman/S_brute_force_number.py unverified MIT (permissive) · c8434b02a9ba199f · report
zykhoo/ai-feynman community (archive-listed) 7 samples, 5 ran (4 instrument-failed) · 2 unverified
draw_samples aifeynman/S_gradient_decomposition.py ran · our draft was wrong MIT (permissive) · 45e77154a33a4ee2 · report fixture: signature X:Tensor/2/float, y:Tensor/1/float, model:callable/0/?, s:list/1/int, NUM_SAMPLES:int/0/int, point:NoneType/0/? · returned Tensor · level recorded 2026-09-22
filter_decompositions_relative_scoring aifeynman/S_gradient_decomposition.py ran · our draft was wrong MIT (permissive) · 3f393d2c3c8a8dd6 · report fixture: signature X:Tensor/2/float, y:Tensor/2/float, model:callable/0/?, max_subset_size:int/0/int, visualize:bool/0/bool · returned list · level recorded 2026-09-22
powerset_atleast_2 aifeynman/S_gradient_decomposition.py ran · our draft was wrong MIT (permissive) · 252c1aad46c908fa · report fixture: signature iterable:list/1/int, max_subset_size:int/0/int · returned chain · level recorded 2026-09-22
score_consistency aifeynman/S_gradient_decomposition.py ran · our draft was wrong fingerprinted MIT (permissive) · 96167167f766b306 · report fixture: signature grads_tensor:Tensor/2/float · returned tuple · level recorded 2026-09-22
signal_to_noise aifeynman/S_gradient_decomposition.py ran · violated contract fingerprinted MIT (permissive) · ec79e09961e5f71d · report fixture: signature high:list/1/float, low:list/1/float · returned int · level recorded 2026-09-22
evaluate_derivatives_andrew aifeynman/S_gradient_decomposition.py unverified MIT (permissive) · 05a477901acb3736 · report
visualize_distribution aifeynman/S_gradient_decomposition.py unverified MIT (permissive) · 21905df6db18ffa8 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for AI Feynman 2.0 (graph method: AI Feynman 2.0). 7 bricks; individually on a fixture: 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

  1. filter_decompositions_relative_scoring entry · level 1 · ran · our draft was wrong · 3f393d2c3c8a8dd6
  2. draw_samples helper · level 1 · ran · our draft was wrong · 45e77154a33a4ee2
  3. evaluate_derivatives_andrew helper · level 0 · unverified · 05a477901acb3736
  4. powerset_atleast_2 helper · level 1 · ran · our draft was wrong · 252c1aad46c908fa
  5. score_consistency metric · level 1 · ran · our draft was wrong · 96167167f766b306
  6. signal_to_noise helper · level 1 · ran · violated contract · ec79e09961e5f71d
  7. visualize_distribution helper · level 0 · unverified · 21905df6db18ffa8

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2006.10782") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Symbolic RegressionTwo-sample testingregression

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Normalizing Flows

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