Papers › Graph-based, Self-Supervised Program Repair from Diagnostic Feedback

Graph-based, Self-Supervised Program Repair from Diagnostic Feedback

20 May 2020ICML 2020 1arXiv:2005.10636archive 2025-07-28

Michihiro Yasunaga, Percy Liang

We consider the problem of learning to repair programs from diagnostic feedback (e.g., compiler error messages). Program repair is challenging for two reasons: First, it requires reasoning and tracking symbols across source code and diagnostic feedback. Second, labeled datasets available for program repair are relatively small. In this work, we propose novel solutions to these two challenges. First, we introduce a program-feedback graph, which connects symbols relevant to program repair in source code and diagnostic feedback, and then apply a graph neural network on top to model the reasoning process. Second, we present a self-supervised learning paradigm for program repair that leverages unlabeled programs available online to create a large amount of extra program repair examples, which we use to pre-train our models. We evaluate our proposed approach on two applications: correcting introductory programming assignments (DeepFix dataset) and correcting the outputs of program synthesis (SPoC dataset). Our final system, DrRepair, significantly outperforms prior work, achieving 68.2% full repair rate on DeepFix (+22.9% over the prior best), and 48.4% synthesis success rate on SPoC (+3.7% over the prior best).

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2005.10636")

Code

Syntology Ran 4 of 6 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · our draft was wrong; 2 ran with no contract checked.

By repository: official repository: 6 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

michiyasunaga/DrRepair officialmentioned in papermentioned on GitHubpytorch 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; 4 ran; 1 honoured the contract we drafted; 2 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
1ran · our draft was wrong
2ran
2unverified

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/DrRepair. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

MultiHeadedAttention michiyasunaga/DrRepair/model/repairer/model/attention_zoo.py official repository ran · metamorphic tier: deterministic MIT (permissive) · 995919c0e59b6ea0 · report
PositionwiseFeedForward michiyasunaga/DrRepair/model/repairer/model/attention_zoo.py official repository ran · metamorphic tier: deterministic MIT (permissive) · 675f1cb139ebf772 · report
generate_relative_positions_matrix michiyasunaga/DrRepair/model/repairer/model/attention_zoo.py official repository ran · honoured contract fingerprinted MIT (permissive) · 0732a6087209857f · report
prepare_lines_print michiyasunaga/DrRepair/evaluation/deepfix/test_deepfix.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 5829c26d2866a681 · report
GraphAttentionEncoderFlowLayer michiyasunaga/DrRepair/model/repairer/model/attention_zoo.py official repository unverified MIT (permissive) · 0839788f852dacce · report
relative_matmul michiyasunaga/DrRepair/model/repairer/model/attention_zoo.py official repository unverified MIT (permissive) · 2b837c9962d604d7 · report

Tasks

Code GenerationDiagnosticGraph LearningGraph Neural NetworkProgram RepairProgram SynthesisSelf-Supervised Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Program Repair DeepFix DrRepair Average Success Rate 68.2 #2 of 4 Archive leaderboard report
Program Synthesis SPoC TestP DrRepair Success rate @budget 100 38.5 #1 of 2 Archive leaderboard report
Program Synthesis SPoC TestW DrRepair Success rate @budget 100 57.0 #1 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 EncodingsGATGraph Neural NetworkLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerRepairTransformer

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