Papers › When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programming

When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programming

8 Jun 2023arXiv:2306.04930archive 2025-07-28

Hussein Mozannar, Gagan Bansal, Adam Fourney, Eric Horvitz

AI powered code-recommendation systems, such as Copilot and CodeWhisperer, provide code suggestions inside a programmer's environment (e.g., an IDE) with the aim of improving productivity. We pursue mechanisms for leveraging signals about programmers' acceptance and rejection of code suggestions to guide recommendations. We harness data drawn from interactions with GitHub Copilot, a system used by millions of programmers, to develop interventions that can save time for programmers. We introduce a utility-theoretic framework to drive decisions about suggestions to display versus withhold. The approach, conditional suggestion display from human feedback (CDHF), relies on a cascade of models that provide the likelihood that recommended code will be accepted. These likelihoods are used to selectively hide suggestions, reducing both latency and programmer verification time. Using data from 535 programmers, we perform a retrospective evaluation of CDHF and show that we can avoid displaying a significant fraction of suggestions that would have been rejected. We further demonstrate the importance of incorporating the programmer's latent unobserved state in decisions about when to display suggestions through an ablation study. Finally, we showcase how using suggestion acceptance as a reward signal for guiding the display of suggestions can lead to suggestions of reduced quality, indicating an unexpected pitfall.

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: 12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 19 samples from 1 repository, 12 ran (12 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 on 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

microsoft/coderec_programming_states officialmentioned in papermentioned on GitHubMITSyntology: 19 samples, 12 ran (0 instrument-failed) · 7 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: 12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 7 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.

12ran
7unverified

Licence: 0 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 microsoft/coderec_programming_states. “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.

microsoft/coderec_programming_states official repository 19 samples, 12 ran (0 instrument-failed) · 7 unverified
bootstrap_confidence_interval when_to_show/metrics_get.py ran MIT (permissive) · ed19bdc4230daed5 · report fixture: signature labels:list/1/int, prediction:list/1/float, metric_function:callable/0/?, num_samples:int/0/int, confidence_level:float/0/float · returned dict · level recorded 2026-09-26
crude_label when_to_show/get_code_label.py ran fingerprinted MIT (permissive) · 0490eac5bafb4137 · report fixture: signature prompt_token:str/0/str · returned str · level recorded 2026-09-26
entropy_single_probability when_to_show/cdhf.py ran fingerprinted MIT (permissive) · 5397058661fb4a5c · report fixture: signature prob:float/0/float · returned float · level recorded 2026-09-26
get_extended_states when_to_show/extended_logs/extended_logs_mass.py ran MIT (permissive) · 434292e5dfea98da · report fixture: signature df_logs:DataFrame/0/?, df_logs_restr:DataFrame/0/? · returned list · level recorded 2026-09-26
get_index in 27 papers between_the_lines/predict_cups/data_split.py ran fingerprinted MIT (permissive) · 53988409e494aa17 · report fixture: signature one_hot:list/1/int · returned int · level recorded 2026-09-26
local_entropy between_the_lines/user_study_analysis/entropy_utils.py ran fingerprinted MIT (permissive) · 73a8698bc54cc3fb · report fixture: signature P:ndarray/2/float · returned ndarray · level recorded 2026-09-26
retreive_logs when_to_show/extended_logs/extended_logs.py ran MIT (permissive) · 380ce40e3722bc67 · report fixture: signature logs_path:str/0/str, restricted_logs_path:str/0/str · returned tuple · level recorded 2026-09-26
stationary_distribution between_the_lines/user_study_analysis/entropy_utils.py ran fingerprinted MIT (permissive) · dfef76f9d70850bf · report fixture: signature P:ndarray/2/float · returned ndarray · level recorded 2026-09-26
text_features when_to_show/generate_features.py ran MIT (permissive) · 6545175d9ac9fa91 · report fixture: signature list_of_strs:list/1/str · returned list · level recorded 2026-09-26
tol_cset between_the_lines/user_study_analysis/colorblind_colors.py ran MIT (permissive) · 52fb834d8edc9f71 · report fixture: signature colorset:NoneType/0/? · returned tuple · level recorded 2026-09-26
trajectory_entropy between_the_lines/user_study_analysis/entropy_utils.py ran fingerprinted MIT (permissive) · 855f8589acc66aff · report fixture: signature P:ndarray/2/float · returned ndarray · level recorded 2026-09-26
traverse_tree when_to_show/get_code_label.py ran MIT (permissive) · cf65280e02f4e416 · report fixture: signature root:TreeNode/0/?, code_byte:bytes/0/? · returned tuple · level recorded 2026-09-26
discretemap between_the_lines/user_study_analysis/colorblind_colors.py unverified MIT (permissive) · 81dc0848a2719a79 · report
get_df_all when_to_show/extended_logs/extended_logs_mass.py unverified MIT (permissive) · 943614b7c2a70665 · report
get_embedding_list when_to_show/generate_features.py unverified MIT (permissive) · 213f0c818c404589 · report
get_features_labels when_to_show/data_split.py unverified MIT (permissive) · e57f8705e5725835 · report
get_features_labels_user_study when_to_show/data_split.py unverified MIT (permissive) · 1bfeef7a43e6e84b · report
process_data_user_study when_to_show/data_split.py unverified MIT (permissive) · 4b248dd17b83c8a3 · report
tol_cmap between_the_lines/user_study_analysis/colorblind_colors.py unverified MIT (permissive) · 9d13457c7a04bdb3 · report

Tasks

Recommendation Systems

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