Papers › Combining Induction and Transduction for Abstract Reasoning

Combining Induction and Transduction for Abstract Reasoning

4 Nov 2024arXiv:2411.02272archive 2025-07-28

Wen-Ding Li, Keya Hu, Carter Larsen, Yuqing Wu, Simon Alford, Caleb Woo, Spencer M. Dunn, Hao Tang, Michelangelo Naim, Dat Nguyen, Wei-Long Zheng, Zenna Tavares, Yewen Pu, Kevin Ellis

When learning an input-output mapping from very few examples, is it better to first infer a latent function that explains the examples, or is it better to directly predict new test outputs, e.g. using a neural network? We study this question on ARC by training neural models for induction (inferring latent functions) and transduction (directly predicting the test output for a given test input). We train on synthetically generated variations of Python programs that solve ARC training tasks. We find inductive and transductive models solve different kinds of test problems, despite having the same training problems and sharing the same neural architecture: Inductive program synthesis excels at precise computations, and at composing multiple concepts, while transduction succeeds on fuzzier perceptual concepts. Ensembling them approaches human-level performance on ARC.

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 19 code samples harvested from 1 repository linked to this paper: 17 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 3 honoured, 2 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 19 samples from 1 repository, 17 ran (12 with no instrument failure; 5 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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

xu3kev/barc officialmentioned in papermentioned on GitHubpytorchSyntology: 19 samples, 17 ran (5 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

19 samples harvested: 17 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 3 honoured, 2 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 2 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.

3ran · honoured contract
2ran · violated contract
4ran · our draft was wrong
1ran; the contract check could not run
7ran
2unverified

Licence: 19 of the 19 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 xu3kev/barc. “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.

xu3kev/barc official repository 19 samples, 17 ran (5 instrument-failed) · 2 unverified
check_grid generate_problems.py ran · violated contract fingerprinted no licence file found · pointer only · f60ed9b398bb02d7 · report fixture: signature grid:ndarray/2/int · returned bool · level recorded 2026-09-25
check_grids_all_equal generate_problems.py ran · violated contract no licence file found · pointer only · ce383926d54b465b · report fixture: signature grids:list/1/ndarray · returned bool · level recorded 2026-09-25
check_identity generate_problems.py ran; the contract check could not run (RAISES) no licence file found · pointer only · f2b5a5387a1e38f0 · report fixture: signature input_grid:ndarray/2/int, output_grid:ndarray/2/int · returned bool · level recorded 2026-09-25
color_deterministic color_variation.py ran fingerprinted no licence file found · pointer only · 05eb189e28232ffb · report fixture: signature problem_source_code:str/0/str, old_color:str/0/str, new_color:str/0/str · returned str · level recorded 2026-09-25
color_deterministic gen_aug_dataset.py ran fingerprinted no licence file found · pointer only · 86465f5ee4424776 · report fixture: signature problem_source_code:str/0/str, old_color:str/0/str, new_color:str/0/str · returned str · level recorded 2026-09-25
color_to_number evaluation.py ran · honoured contract no licence file found · pointer only · 715d8903f925b507 · report fixture: signature color:str/0/str · returned int · level recorded 2026-09-25
color_variation color_variation.py ran no licence file found · pointer only · 6c25536f44893fac · report fixture: signature problem_source_code:str/0/str, input_grids:list/1/list, output_grids:list/1/list · returned tuple · level recorded 2026-09-25
concepts_in_file concepts.py ran · our draft was wrong no licence file found · pointer only · e56a04784249e6b6 · report fixture: signature f:str/0/str · returned list · level recorded 2026-09-25
convert_color_name gen_aug_dataset.py ran · our draft was wrong no licence file found · pointer only · 74b9e46678c73f6d · report fixture: signature text:str/0/str, mapping:dict/0/? · returned str · level recorded 2026-09-25
description_in_file concepts.py ran · our draft was wrong no licence file found · pointer only · 236e88a71bbebcfd · report fixture: signature f:str/0/str · returned str · level recorded 2026-09-25
ensure_colors_exist generate_code.py ran · our draft was wrong fingerprinted no licence file found · pointer only · f216c58912a089d6 · report fixture: signature code:str/0/str · returned str · level recorded 2026-09-25
execute_transformation execution.py ran no licence file found · pointer only · e4aaf0dc18a08032 · report fixture: signature source:str/0/str, input_grid:list/1/list, timeout:int/0/int, function_name:str/0/str · returned str · level recorded 2026-09-25
grid_2d_to_tuple evaluation.py ran · honoured contract no licence file found · pointer only · 61fc7c63b253b738 · report fixture: signature grid:list/1/list · returned tuple · level recorded 2026-09-25
grid_to_input gen_aug_dataset.py ran no licence file found · pointer only · 0dfbc8b8fc6c38d1 · report fixture: signature grid:ndarray/2/int, transpose:bool/0/bool, color_mapping:dict/0/? · returned str · level recorded 2026-09-25
multi_process_execute_v2 execution.py ran no licence file found · pointer only · 464b726f85abe923 · report fixture: signature codes:list/1/str, return_var_name:str/0/str, timeout:int/0/int, num_workers:int/0/int · returned list · level recorded 2026-09-25
trace_calls eval_code_samples.py ran no licence file found · pointer only · dd3be7e32f87f0de · report fixture: signature frame:MockFrame/0/?, event:str/0/str, arg:str/0/str · returned function · level recorded 2026-09-25
tuple_to_grid_2d evaluation.py ran · honoured contract no licence file found · pointer only · c834c2c28315b0b0 · report fixture: signature t:tuple/1/tuple · returned list · level recorded 2026-09-25
compare_grids eval_code_samples.py unverified no licence file found · pointer only · 3b3fa833e3b26cd4 · report
multi_process_execute execution.py unverified no licence file found · pointer only · 01c435e68ef843e8 · report

Tasks

ARCProgram Synthesis

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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