Papers › Emergent Representations of Program Semantics in Language Models Trained on Programs

Emergent Representations of Program Semantics in Language Models Trained on Programs

18 May 2023arXiv:2305.11169archive 2025-07-28

Charles Jin, Martin Rinard

We present evidence that language models (LMs) of code can learn to represent the formal semantics of programs, despite being trained only to perform next-token prediction. Specifically, we train a Transformer model on a synthetic corpus of programs written in a domain-specific language for navigating 2D grid world environments. Each program in the corpus is preceded by a (partial) specification in the form of several input-output grid world states. Despite providing no further inductive biases, we find that a probing classifier is able to extract increasingly accurate representations of the unobserved, intermediate grid world states from the LM hidden states over the course of training, suggesting the LM acquires an emergent ability to interpret programs in the formal sense. We also develop a novel interventional baseline that enables us to disambiguate what is represented by the LM as opposed to learned by the probe. We anticipate that this technique may be generally applicable to a broad range of semantic probing experiments. In summary, this paper does not propose any new techniques for training LMs of code, but develops an experimental framework for and provides insights into the acquisition and representation of formal semantics in statistical models of code. Our code is available at https://github.com/charlesjin/emergent-semantics.

PaperPDFCodeCode 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 13 code samples harvested from 1 repository linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 12 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 12 where our contract draft was wrong; failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 12 ran (0 with no instrument failure; 12 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 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

charlesjin/emergent-semantics officialmentioned in papermentioned on GitHubpytorchSyntology: 13 samples, 12 ran (12 instrument-failed) · 1 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

13 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 12 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Every run on this page is a failure 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.

12ran · our draft was wrong
1unverified

Licence: 13 of the 13 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 charlesjin/emergent-semantics. “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.

charlesjin/emergent-semantics official repository 13 samples, 12 ran (12 instrument-failed) · 1 unverified
opposite1 probe/alt.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 19289791bccfe4aa · report fixture: signature prog:str/0/str · returned str · level recorded 2026-09-22
perm1 probe/alt.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 06ef4785e27794a2 · report fixture: signature prog:str/0/str · returned str · level recorded 2026-09-22
perm_nomarks_1 probe/alt.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 9c15d06bd3b8286a · report fixture: signature prog:str/0/str · returned str · level recorded 2026-09-22
perm_nomarks_2 probe/alt.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 57fa76126e713940 · report fixture: signature prog:str/0/str · returned str · level recorded 2026-09-22
perm_nomarks_3 probe/alt.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 45f490a781f1c4b4 · report fixture: signature prog:str/0/str · returned str · level recorded 2026-09-22
perm_nomarks_4 probe/alt.py ran · our draft was wrong fingerprinted no licence file found · pointer only · e5a9b785d18c1264 · report fixture: signature prog:str/0/str · returned str · level recorded 2026-09-22
perm_nomarks_5 probe/alt.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 017dd7ef99ca3626 · report fixture: signature prog:str/0/str · returned str · level recorded 2026-09-22
random1 probe/alt.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 55d8912d375aaabb · report fixture: signature prog:str/0/str · returned str · level recorded 2026-09-22
unsemantic1 probe/alt.py ran · our draft was wrong fingerprinted no licence file found · pointer only · c785730b24eadf32 · report fixture: signature prog:str/0/str · returned str · level recorded 2026-09-22
unsemantic2 probe/alt.py ran · our draft was wrong fingerprinted no licence file found · pointer only · a54437cd7c70b3e9 · report fixture: signature prog:str/0/str · returned str · level recorded 2026-09-22
unsemantic3 probe/alt.py ran · our draft was wrong fingerprinted no licence file found · pointer only · c860b95cbf28a9cc · report fixture: signature prog:str/0/str · returned str · level recorded 2026-09-22
unsemantic4 probe/alt.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 46316ec582bba1bf · report fixture: signature prog:str/0/str · returned str · level recorded 2026-09-22
semantics_transformer probe/alt.py unverified no licence file found · pointer only · de1956b9f51d4ea7 · 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 interventional baseline (graph method: interventional baseline). 13 bricks; individually on a fixture: 12 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 12 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

  1. semantics_transformer entry · level 0 · unverified · de1956b9f51d4ea7
  2. opposite1 data_transform · level 1 · ran · our draft was wrong · 19289791bccfe4aa
  3. perm1 data_transform · level 1 · ran · our draft was wrong · 06ef4785e27794a2
  4. perm_nomarks_1 data_transform · level 1 · ran · our draft was wrong · 9c15d06bd3b8286a
  5. perm_nomarks_2 data_transform · level 1 · ran · our draft was wrong · 57fa76126e713940
  6. perm_nomarks_3 data_transform · level 1 · ran · our draft was wrong · 45f490a781f1c4b4
  7. perm_nomarks_4 data_transform · level 1 · ran · our draft was wrong · e5a9b785d18c1264
  8. perm_nomarks_5 data_transform · level 1 · ran · our draft was wrong · 017dd7ef99ca3626
  9. random1 data_transform · level 1 · ran · our draft was wrong · 55d8912d375aaabb
  10. unsemantic1 data_transform · level 1 · ran · our draft was wrong · c785730b24eadf32
  11. unsemantic2 data_transform · level 1 · ran · our draft was wrong · a54437cd7c70b3e9
  12. unsemantic3 data_transform · level 1 · ran · our draft was wrong · c860b95cbf28a9cc
  13. unsemantic4 data_transform · level 1 · ran · our draft was wrong · 46316ec582bba1bf

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="2305.11169") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Inductive BiasLanguage ModellingProgram Synthesis

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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