Papers › SemCoder: Training Code Language Models with Comprehensive Semantics Reasoning

SemCoder: Training Code Language Models with Comprehensive Semantics Reasoning

3 Jun 2024arXiv:2406.01006archive 2025-07-28

Yangruibo Ding, Jinjun Peng, Marcus J. Min, Gail Kaiser, Junfeng Yang, Baishakhi Ray

Code Large Language Models (Code LLMs) have excelled at tasks like code completion but often miss deeper semantics such as execution effects and dynamic states. This paper aims to bridge the gap between Code LLMs' reliance on static text data and the need for semantic understanding for complex tasks like debugging and program repair. We introduce a novel strategy, monologue reasoning, to train Code LLMs to reason comprehensive semantics, encompassing high-level functional descriptions, local execution effects of individual statements, and overall input/output behavior, thereby linking static code text with dynamic execution states. We begin by collecting PyX, a clean Python corpus of fully executable code samples with functional descriptions and test cases. We propose training Code LLMs not only to write code but also to understand code semantics by reasoning about key properties, constraints, and execution behaviors using natural language, mimicking human verbal debugging, i.e., rubber-duck debugging. This approach led to the development of SemCoder, a Code LLM with only 6.7B parameters, which shows competitive performance with GPT-3.5-turbo on code generation and execution reasoning tasks. SemCoder achieves 79.3% on HumanEval (GPT-3.5-turbo: 76.8%), 63.6% on CRUXEval-I (GPT-3.5-turbo: 50.3%), and 63.9% on CRUXEval-O (GPT-3.5-turbo: 59.0%). We also study the effectiveness of SemCoder's monologue-style execution reasoning compared to concrete scratchpad reasoning, showing that our approach integrates semantics from multiple dimensions more smoothly. Finally, we demonstrate the potential of applying learned semantics to improve Code LLMs' debugging and self-refining capabilities. Our data, code, and models are available at: https://github.com/ARiSE-Lab/SemCoder.

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 15 code samples harvested from 1 repository linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 12 ran (6 with no instrument failure; 6 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 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

arise-lab/semcoder officialmentioned in papermentioned on GitHubpytorchMITSyntology: 15 samples, 12 ran (6 instrument-failed) · 3 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

15 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 3 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.

1ran · honoured contract
6ran · our draft was wrong
5ran
3unverified

Licence: 0 of the 15 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 arise-lab/semcoder. “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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

arise-lab/semcoder official repository 15 samples, 12 ran (6 instrument-failed) · 3 unverified
attach_execution_exception experiments/build_self_refine_input.py ran fingerprinted MIT (permissive) · 23ef3078d45c966b · report fixture: signature traced_program:str/0/str, trace:str/0/str · returned str · level recorded 2026-09-24
chunked in 5 papers src/utils.py ran · our draft was wrong MIT (permissive) · 8fbbf1d9e53be9ec · report fixture: signature seq:list/1/int, n:int/0/int · returned generator · level recorded 2026-09-24
complete_code in 7 papers experiments/cruxeval_utils.py ran MIT (permissive) · b9090aa3af341871 · report fixture: signature task:Task/0/?, model:callable/0/?, sampling_params:SamplingParams/0/?, dataloader:Dataloader/0/?, batch_size:int/0/int, n_tasks:int/0/int, log_path:str/0/str, prefix:str/0/str, postprocess:bool/0/bool · returned tuple · level recorded 2026-09-24
concise_spad experiments/construct_trace.py ran · our draft was wrong fingerprinted MIT (permissive) · 7e638715779072af · report fixture: signature line:str/0/str · returned str · level recorded 2026-09-22
convertv2s experiments/construct_trace.py ran · our draft was wrong MIT (permissive) · 5c7a36496bbe50b3 · report fixture: signature obj:dict/0/?, output:bool/0/bool · returned str · level recorded 2026-09-22
extract_failed_test experiments/build_self_refine_input.py ran fingerprinted MIT (permissive) · 660d74f09a475daa · report fixture: signature traced_program:str/0/str, funcname:str/0/str · returned str · level recorded 2026-09-24
extract_trace experiments/build_self_refine_input.py ran fingerprinted MIT (permissive) · 7e07a365b5619a81 · report fixture: signature trace:str/0/str, inference:bool/0/bool · returned str · level recorded 2026-09-24
handle_value experiments/construct_trace.py ran · honoured contract fingerprinted MIT (permissive) · 6834377c553301df · report fixture: signature var_value:str/0/str · returned list · level recorded 2026-09-22
make_cot_output_prompt experiments/cruxeval_prompts.py ran · our draft was wrong fingerprinted MIT (permissive) · b4a6d7a477e69976 · report fixture: signature s:tuple/1/str · returned str · level recorded 2026-09-24
make_direct_output_prompt experiments/cruxeval_prompts.py ran · our draft was wrong fingerprinted MIT (permissive) · 7ff4e308c6863412 · report fixture: signature s:tuple/1/str · returned str · level recorded 2026-09-24
make_forward_monologue_output_prompt experiments/cruxeval_prompts.py ran · our draft was wrong MIT (permissive) · 1c29bebc3b2830c3 · report fixture: signature s:tuple/1/str · returned str · level recorded 2026-09-24
pad_sequences in 19 papers src/wrapper.py ran MIT (permissive) · 7b178c461482e3f6 · report fixture: signature sequences:list/1/list, pad_value:int/0/int, padding_side:str/0/str, dtype:dtype/0/?, padding_length:NoneType/0/? · returned Tensor · level recorded 2026-09-26
attach_trace_to_code experiments/construct_trace.py unverified MIT (permissive) · 926bd7fef63dd64e · report
get_model_context src/wrapper.py unverified MIT (permissive) · da99ae3e6a8eb89e · report
get_task in 28 papers experiments/cruxeval_utils.py unverified MIT (permissive) · 0ea1d7ce8d9d3e2a · 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 SEMCODER (graph method: SEMCODER). 4 bricks; individually on a fixture: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

  1. attach_trace_to_code entry · level 0 · unverified · 926bd7fef63dd64e
  2. concise_spad helper · level 1 · ran · our draft was wrong · 7e638715779072af
  3. convertv2s helper · level 1 · ran · our draft was wrong · 5c7a36496bbe50b3
  4. handle_value helper · level 1 · ran · honoured contract · 6834377c553301df

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="2406.01006") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Code CompletionCode GenerationHumanEvalProgram Repair

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamAttentionAttention DropoutBPECosine AnnealingDense ConnectionsDropoutGPT-3Layer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMulti-Head AttentionResidual ConnectionSoftmaxWeight Decay

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