Papers › Break-It-Fix-It: Unsupervised Learning for Program Repair

Break-It-Fix-It: Unsupervised Learning for Program Repair

11 Jun 2021arXiv:2106.06600archive 2025-07-28

Michihiro Yasunaga, Percy Liang

We consider repair tasks: given a critic (e.g., compiler) that assesses the quality of an input, the goal is to train a fixer that converts a bad example (e.g., code with syntax errors) into a good one (e.g., code with no syntax errors). Existing works create training data consisting of (bad, good) pairs by corrupting good examples using heuristics (e.g., dropping tokens). However, fixers trained on this synthetically-generated data do not extrapolate well to the real distribution of bad inputs. To bridge this gap, we propose a new training approach, Break-It-Fix-It (BIFI), which has two key ideas: (i) we use the critic to check a fixer's output on real bad inputs and add good (fixed) outputs to the training data, and (ii) we train a breaker to generate realistic bad code from good code. Based on these ideas, we iteratively update the breaker and the fixer while using them in conjunction to generate more paired data. We evaluate BIFI on two code repair datasets: GitHub-Python, a new dataset we introduce where the goal is to repair Python code with AST parse errors; and DeepFix, where the goal is to repair C code with compiler errors. BIFI outperforms existing methods, obtaining 90.5% repair accuracy on GitHub-Python (+28.5%) and 71.7% on DeepFix (+5.6%). Notably, BIFI does not require any labeled data; we hope it will be a strong starting point for unsupervised learning of various repair tasks.

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 6 code samples harvested from 1 repository linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 6 samples from 1 repository, 6 ran (6 with no instrument failure; 0 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 2026-09-25 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

michiyasunaga/bifi officialmentioned in papermentioned on GitHubpytorchMITSyntology: 6 samples, 6 ran (0 instrument-failed) · 0 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

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

6ran

Licence: 0 of the 6 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 michiyasunaga/bifi. “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.

michiyasunaga/bifi official repository 6 samples, 6 ran (0 instrument-failed) · 0 unverified
check_ast_error utils/code_error_checker.py ran fingerprinted MIT (permissive) · 7956f0c3ad623dc9 · report fixture: signature codeString:str/0/str · returned dict · level recorded 2026-09-25
code_toks_to_code_string utils/code_utils.py ran MIT (permissive) · d31293eebb3f2fbb · report fixture: signature code_toks_joined:str/0/str, anonymize_dict:dict/0/? · returned str · level recorded 2026-09-25
detect_encoding utils/code_tokenizer.py ran MIT (permissive) · 4e338ff6454175b7 · report fixture: signature readline:callable/0/? · returned tuple · level recorded 2026-09-25
fairseq_generate utils/fairseq_utils.py ran MIT (permissive) · 24311a36d4c36789 · report fixture: signature GPUs:str/0/str, preprocess_dir:str/0/str, checkpoint_path:str/0/str, results_path:str/0/str, src:str/0/str, tgt:str/0/str, gen_subset:str/0/str, beam:int/0/int, nbest:int/0/int, max_len_a:int/0/int, max_len_b:int/0/int, remove_bpe:str/0/str, user_dir:NoneType/0/?, use_Popen:bool/0/bool · returned Popen · level recorded 2026-09-25
parse_fairseq_preds utils/fairseq_utils.py ran MIT (permissive) · 0b5ffc297fbdf5da · report fixture: signature pred_path:str/0/str · returned list · level recorded 2026-09-25
toks2lines utils/code_utils.py ran fingerprinted MIT (permissive) · 1661aeef734f01a4 · report fixture: signature code_toks_raw:list/1/str · returned list · level recorded 2026-09-26

Tasks

C++ codeCode RepairData AugmentationDomain AdaptationProgram RepairStyle TransferUnsupervised Machine Translation

Datasets

Introduced by this paper, per the archive.

GitHub-Python

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Program Repair DeepFix DrRepair + BIFI Average Success Rate 71.7 #1 of 4 Archive leaderboard report
Program Repair GitHub-Python Transformer + BIFI Accuracy (%) 90.5 #1 of 2 Archive leaderboard report
Program Repair GitHub-Python Transformer Accuracy (%) 62.0 #2 of 2 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

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