Papers › Conformal prediction under ambiguous ground truth

Conformal prediction under ambiguous ground truth

18 Jul 2023arXiv:2307.09302archive 2025-07-28

David Stutz, Abhijit Guha Roy, Tatiana Matejovicova, Patricia Strachan, Ali Taylan Cemgil, Arnaud Doucet

Conformal Prediction (CP) allows to perform rigorous uncertainty quantification by constructing a prediction set C(X) satisfying ℙ(Y ∈C(X))≥1-α for a user-chosen α∈[0,1] by relying on calibration data (X₁,Y₁),...,(Xₙ,Yₙ) from ℙ=ℙ^X ⊗ℙ^(Y|X). It is typically implicitly assumed that ℙ^(Y|X) is the "true" posterior label distribution. However, in many real-world scenarios, the labels Y₁,...,Yₙ are obtained by aggregating expert opinions using a voting procedure, resulting in a one-hot distribution ℙᵥₒₜₑ^(Y|X). For such ``voted'' labels, CP guarantees are thus w.r.t. ℙᵥₒₜₑ=ℙ^X ⊗ℙᵥₒₜₑ^(Y|X) rather than the true distribution ℙ. In cases with unambiguous ground truth labels, the distinction between ℙᵥₒₜₑ and ℙ is irrelevant. However, when experts do not agree because of ambiguous labels, approximating ℙ^(Y|X) with a one-hot distribution ℙᵥₒₜₑ^(Y|X) ignores this uncertainty. In this paper, we propose to leverage expert opinions to approximate ℙ^(Y|X) using a non-degenerate distribution ℙ_(agg)^(Y|X). We develop Monte Carlo CP procedures which provide guarantees w.r.t. ℙ_(agg)=ℙ^X ⊗ℙ_(agg)^(Y|X) by sampling multiple synthetic pseudo-labels from ℙ_(agg)^(Y|X) for each calibration example X₁,...,Xₙ. In a case study of skin condition classification with significant disagreement among expert annotators, we show that applying CP w.r.t. ℙᵥₒₜₑ under-covers expert annotations: calibrated for 72% coverage, it falls short by on average 10%; our Monte Carlo CP closes this gap both empirically and theoretically.

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 2 repositories linked to this paper: 15 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 6 samples from 1 repository, 6 ran (1 with no instrument failure; 5 where Syntology's instrument failed); community (archive-listed): 13 samples from 1 repository, 9 ran (9 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 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

google-deepmind/uncertain_ground_truth officialmentioned on GitHubjaxSyntology: 6 samples, 6 ran (5 instrument-failed) · 0 unverified report
alaalab/webcp mentioned on GitHubpytorchMITSyntology: 13 samples, 9 ran (0 instrument-failed) · 4 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: 15 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 5 where Syntology's instrument failed) · 4 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.

1ran · honoured contract
2ran · our draft was wrong
3ran; the contract check could not run
9ran
4unverified

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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

google-deepmind/uncertain_ground_truth official repository 6 samples, 6 ran (5 instrument-failed) · 0 unverified
calibrate_mc_threshold monte_carlo.py ran · our draft was wrong Apache-2.0 (permissive) · 9454afd876c4a7c7 · report fixture: signature rng:ArrayImpl/1/int, conformity_scores:ArrayImpl/2/float, smooth_labels:ArrayImpl/2/float, alpha:float/0/float, num_samples:int/0/int · returned float · level recorded 2026-09-22
calibrate_threshold conformal_prediction.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant Apache-2.0 (permissive) · 9dbcb314e6aad51b · report fixture: signature conformity_scores:ArrayImpl/2/float, labels:ArrayImpl/1/int, alpha:float/0/float · returned float · level recorded 2026-09-22
conformal_quantile in 5 papers conformal_prediction.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · c293ce6b6a5d4d3d · report fixture: signature scores:ArrayImpl/1/float, alpha:float/0/float · returned float · level recorded 2026-09-22
mc_conformal_quantile monte_carlo.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 2436571bd53cdc72 · report fixture: signature scores:ArrayImpl/1/float, num_examples:int/0/int, num_samples:int/0/int, alpha:float/0/float · returned float · level recorded 2026-09-22
predict_threshold conformal_prediction.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 792f08759b26f4dc · report fixture: signature conformity_scores:ArrayImpl/2/float, threshold:float/0/float · returned ArrayImpl · level recorded 2026-09-22
sample_mc_labels monte_carlo.py ran · our draft was wrong Apache-2.0 (permissive) · 63fb282a3dc3fb0a · report fixture: signature rng:ArrayImpl/1/int, conformity_scores:ArrayImpl/2/float, smooth_labels:ArrayImpl/2/float, num_samples:int/0/int · returned tuple · level recorded 2026-09-22
alaalab/webcp community (archive-listed) 13 samples, 9 ran (0 instrument-failed) · 4 unverified
class_stratified_coverage ambiguous_cp/metrics.py ran MIT (permissive) · 981bb17491bde067 · report fixture: signature conformal_set_arr:ndarray/2/bool, true_class_arr:ndarray/2/bool · returned ndarray · level recorded 2026-09-24
compute_prediction_sets ambiguous_cp/conformal_risk_control.py ran MIT (permissive) · 3776f69137111df4 · report fixture: signature probability_arr:Tensor/2/float, threshold:float/0/float · returned Tensor · level recorded 2026-09-24
compute_prediction_sets_threshold ambiguous_cp/conformal_prediction_methods.py ran MIT (permissive) · d57df6bb388ac156 · report fixture: signature probability_arr:Tensor/2/float, threshold:float/0/float · returned Tensor · level recorded 2026-09-24
compute_simscores compute_alignments/generate_context_alignments.py ran MIT (permissive) · 1a976aa6e853fa6b · report fixture: signature context_encoder:callable/0/?, query_embedding_dict:dict/0/?, tokenized_context:dict/0/? · returned dict · level recorded 2026-09-24
compute_threshold ambiguous_cp/conformal_prediction_methods.py ran MIT (permissive) · 9b4f33f1fb0e29e7 · report fixture: signature alpha:float/0/float, probability_arr:ndarray/2/float, true_class_arr:ndarray/2/float · returned float · level recorded 2026-09-24
get_fileidx_list compute_alignments/generate_context_alignments.py ran MIT (permissive) · d9ea461f5d5de794 · report fixture: signature dataset_subfolder:PosixPath/0/? · returned list · level recorded 2026-09-24
openclip_process ambiguous_cp/plausibility_generation.py ran fingerprinted MIT (permissive) · 4692dedab0106411 · report fixture: signature image_logits:Tensor/2/float, text_logits:Tensor/2/float, temp:float/0/float · returned Tensor · level recorded 2026-09-24
overall_coverage ambiguous_cp/metrics.py ran MIT (permissive) · 829b99fa5448188b · report fixture: signature conformal_set_arr:ndarray/2/bool, true_class_arr:ndarray/2/bool · returned float64 · level recorded 2026-09-24
samplewise_loss ambiguous_cp/conformal_prediction_methods.py ran MIT (permissive) · 395fb2dace74ef7e · report fixture: signature conformal_set_arr:ndarray/2/bool, true_class_arr:ndarray/2/bool · returned ndarray · level recorded 2026-09-24
openclip_image_preprocess ambiguous_cp/experiment.py unverified MIT (permissive) · a3b4517e7249c4cf · report
openclip_process ambiguous_cp/experiment.py unverified MIT (permissive) · 33202b9bd3d95c68 · report
openclip_text_preprocess ambiguous_cp/experiment.py unverified MIT (permissive) · cc19e29ec50fcdf5 · report
performance_report ambiguous_cp/analysis.py unverified MIT (permissive) · ad14a67ac002ed26 · report

Tasks

Conformal PredictionPredictionUncertainty Quantification

Datasets

Introduced by this paper, per the archive.

Dermatology ddx dataset

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