Papers › Uncertainty Sets for Image Classifiers using Conformal Prediction
Uncertainty Sets for Image Classifiers using Conformal Prediction
Anastasios Angelopoulos, Stephen Bates, Jitendra Malik, Michael. I. Jordan
Convolutional image classifiers can achieve high predictive accuracy, but quantifying their uncertainty remains an unresolved challenge, hindering their deployment in consequential settings. Existing uncertainty quantification techniques, such as Platt scaling, attempt to calibrate the network's probability estimates, but they do not have formal guarantees. We present an algorithm that modifies any classifier to output a predictive set containing the true label with a user-specified probability, such as 90%. The algorithm is simple and fast like Platt scaling, but provides a formal finite-sample coverage guarantee for every model and dataset. Our method modifies an existing conformal prediction algorithm to give more stable predictive sets by regularizing the small scores of unlikely classes after Platt scaling. In experiments on both Imagenet and Imagenet-V2 with ResNet-152 and other classifiers, our scheme outperforms existing approaches, achieving coverage with sets that are often factors of 5 to 10 smaller than a stand-alone Platt scaling baseline.
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):
get_harvested_code_for_paper(arxiv_id="2009.14193")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2009.14193", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2009.14193")
Code
Syntology 63 code samples harvested from 5 repositories linked to this paper: 26 ran (of which 1 constructed an object rather than computing a result; 13 with no instrument failure: 4 honoured, 0 violated, 9 with no contract checked; 13 where Syntology's instrument failed) · 37 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 9 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: official repository: 21 samples from 2 repositories, 6 ran (5 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 42 samples from 3 repositories, 20 ran (8 with no instrument failure; 12 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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.
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
63 samples harvested: 26 ran (of which 1 constructed an object rather than computing a result; 13 with no instrument failure: 4 honoured, 0 violated, 9 with no contract checked; 13 where Syntology's instrument failed) · 37 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.
Licence: 19 of the 63 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 5 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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.
bd14e9d95bb7ddfc · report
fixture: returned tuple · level recorded 2026-09-22 af6e06025c2d3e9e · report
fixture: signature df_big:DataFrame/0/? · returned str · level recorded 2026-09-25 b8814251e2dc9f83 · report
fixture: signature df_big:DataFrame/0/? · returned str · level recorded 2026-09-25 8ce51944e3958c60 · report
fixture: signature df:DataFrame/0/?, alpha:float/0/float · returned str · level recorded 2026-09-25 837d496b65e5409a · report
fixture: signature df:DataFrame/0/? · returned str · level recorded 2026-09-25 3e5323ecb83f4191 · report
fixture: signature df:DataFrame/0/?, alpha:float/0/float · returned str · level recorded 2026-09-25 dd37044d7fcf6f2e · report
8609f9ffa4a463bb · report
153f3eb42aa57f6e · report
31ac51fceb1bed9c · report
fixture: returned tuple · level recorded 2026-09-22 233fd8c72fe7bee3 · report
fixture: returned AverageMeterNamed · level recorded 2026-09-22 ad9b2ac4522ac726 · report
fixture: signature output:Tensor/2/float, target:Tensor/1/int, topk:tuple/1/int · returned list · level recorded 2026-09-22 f246b8eb9dcd2a55 · report
fixture: signature S:list/1/Tensor, targets:Tensor/1/int · returned tuple · level recorded 2026-09-25 91bbe02deed691ad · report
fixture: signature scores:ndarray/2/float, tau:float/0/float, I:ndarray/2/int, ordered:ndarray/2/float, cumsum:ndarray/2/float, penalties:ndarray/2/float, randomized:bool/0/bool, allow_zero_sets:bool/0/bool · returned list · level recorded 2026-09-22 3a9dae3b91f61830 · report
fixture: signature model:callable/0/?, loader:DataLoader/0/? · returned TensorDataset · level recorded 2026-09-25 ffb82a3e85bf0356 · report
fixture: signature score:ndarray/1/float, target:int/0/int, I:ndarray/2/int, ordered:ndarray/2/float, cumsum:ndarray/2/float, penalty:ndarray/1/float, randomized:bool/0/bool, allow_zero_sets:bool/0/bool · returned ndarray · level recorded 2026-09-22 27301ab04f721d1b · report
fixture: returned Parameter · level recorded 2026-09-22 ce9cdd0a73c5e072 · report
fixture: signature scores:ndarray/2/float · returned tuple · level recorded 2026-09-22 cf250d297edd395d · report
fixture: returned tuple · level recorded 2026-09-22 d70924ef3a0c1d8c · report
b1c2b43f4d3b155b · report
2faec253bfdad8a3 · report
a1271a87af4e4175 · report
28513efa13e9bf63 · report
925e3a758022b8dc · report
b2728fc9fde250ba · report
cc2739d79cf32721 · report
1ce010bfb1ac1994 · report
f43467eedb43283d · report
2df4a9fc1d319ad7 · report
fixture: signature pred_set:Tensor/2/float, targets:Tensor/1/int · returned NoneType · level recorded 2026-09-24 d540f5e805ba1e82 · report
fixture: signature paramtune_logits:DataLoader/0/?, alpha:float/0/float · returned int · level recorded 2026-09-22 9f1c82f5fda99c76 · report
fixture: signature scores:Tensor/2/float, tau:Tensor/0/float, sorted_score_indices:Tensor/2/int, ordered:Tensor/2/float, cumsum:Tensor/2/float, penalties:Tensor/2/float, randomized:bool/0/bool, allow_zero_sets:bool/0/bool · returned list · level recorded 2026-09-24 355136b6943fb837 · report
fixture: signature targets:Tensor/1/int, sorted_score_indices:Tensor/2/int, ordered:Tensor/2/float, cumsum:Tensor/2/float, penalties:Tensor/2/float, randomized:bool/0/bool, allow_zero_sets:bool/0/bool · returned Tensor · level recorded 2026-09-22 f43a6e1abc3d5ba6 · report
fixture: signature cmodel:callable/0/?, loader_paramtune:DataLoader/0/?, strata:list/1/list, alpha:float/0/float · returned float64 · level recorded 2026-09-24 census: 11 implementations from 39 papers, 3 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32 lightning_uq_box/uq_methods/raps.py ran · honoured contract fingerprinted Apache-2.0 (permissive) ·
9adf3e5a14a94f24 · report
fixture: signature x:Tensor/2/float, dim:NoneType/0/? · returned Tensor · level recorded 2026-09-22 162981b9545d9250 · report
fixture: signature logits:Tensor/3/float, aggregate_fn:callable/0/?, eps:float/0/float, task:str/0/str · returned dict · level recorded 2026-09-22 334697eb3983e90d · report
fixture: signature logits:Tensor/2/float, labels:Tensor/1/int, criterion:callable/0/?, temperature:Tensor/2/float, optimizer:callable/0/?, max_iter:int/0/int · returned Parameter · level recorded 2026-09-22 0915e08c6d516b48 · report
fixture: signature scores:Tensor/2/float · returned tuple · level recorded 2026-09-22 6fd34088368dcdbf · report
fixture: signature logits:Tensor/2/float, temperature:Tensor/2/float · returned Tensor · level recorded 2026-09-22 466b72a3e0124a34 · report
b55f91e7bf34638e · report
99e14fdcc6ff711f · report
ed0742b3cda42dbb · report
e151158cfc4459c8 · report
8ad44ec25960a4a2 · report
b21986df9d596afb · report
0e425cc3cb76f358 · report
5002e7982e88d68b · report
8834b23ad655655f · report
75313f9955e8f579 · 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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.
4 assemblies on this paper: 4 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).
4 sibling assemblies for conformal prediction algorithm modification (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.
harvested Assembly for conformal prediction algorithm modification (graph method: conformal prediction algorithm modification). 19 bricks; individually on a fixture: 9 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 10 unverified. The assembly has not been run end-to-end.
one of 4 siblings
- ConformalModel entry · level 0 · unverified ·
d70924ef3a0c1d8c - conformal_calibration_logits helper · level 0 · unverified ·
2faec253bfdad8a3 - gcq helper · level 1 · ran; the contract check could not run (RAISES) ·
91bbe02deed691ad - pick_parameters helper · level 0 · unverified ·
1ce010bfb1ac1994 - platt helper · level 0 · unverified ·
f43467eedb43283d - sort_sum helper · level 1 · ran · honoured contract ·
ce9cdd0a73c5e072 - giq helper · level 0 · unverified ·
28513efa13e9bf63 - pick_kreg helper · level 0 · unverified ·
925e3a758022b8dc - pick_lamda_adaptiveness helper · level 0 · unverified ·
b2728fc9fde250ba - pick_lamda_size helper · level 0 · unverified ·
cc2739d79cf32721 - get_logits_targets helper · level 1 · ran ·
3a9dae3b91f61830 - platt_logits helper · level 1 · ran; the contract check could not run (RAISES) ·
27301ab04f721d1b - get_tau helper · level 1 · ran; the contract check could not run (RAISES) ·
ffb82a3e85bf0356 - ConformalModelLogits helper · level 0 · unverified ·
b1c2b43f4d3b155b - get_violation helper · level 0 · unverified ·
a1271a87af4e4175 - validate helper · level 1 · ran; the contract check could not run (RAISES) ·
cf250d297edd395d - AverageMeterNamed helper · level 1 · ran ·
233fd8c72fe7bee3 - accuracy_RAPS helper · level 1 · ran; the contract check could not run (RAISES) ·
ad9b2ac4522ac726 - coverage_size helper · level 1 · ran ·
f246b8eb9dcd2a55
harvested Assembly for conformal prediction algorithm modification (graph method: conformal prediction algorithm modification). 2 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.
one of 4 siblings
- ACP_D entry · level 1 · ran · our draft was wrong ·
31ac51fceb1bed9c - log_to_file helper · level 0 · unverified ·
69d3f5abde3456e2
harvested Assembly for conformal prediction algorithm modification (graph method: conformal prediction algorithm modification). 16 bricks; individually on a fixture: 8 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 8 unverified. The assembly has not been run end-to-end.
one of 4 siblings
- ConformalModelLogits entry · level 0 · unverified ·
47a75f97f3f91fb8 - conformal_calibration_logits model · level 0 · unverified ·
2faec253bfdad8a3 - gcq model · level 1 · ran; the contract check could not run (RAISES) ·
91bbe02deed691ad - pick_parameters helper · level 0 · unverified ·
4fcc55d02d28d664 - platt_logits update_rule · level 1 · ran; the contract check could not run (RAISES) ·
27301ab04f721d1b - sort_sum helper · level 1 · ran · honoured contract ·
ce9cdd0a73c5e072 - giq model · level 0 · unverified ·
28513efa13e9bf63 - pick_kreg helper · level 0 · unverified ·
925e3a758022b8dc - pick_lamda_adaptiveness helper · level 0 · unverified ·
d4fe06777aaee19f - pick_lamda_size helper · level 0 · unverified ·
417da00712c1c058 - get_tau helper · level 1 · ran; the contract check could not run (RAISES) ·
ffb82a3e85bf0356 - get_violation helper · level 0 · unverified ·
a1271a87af4e4175 - validate helper · level 1 · ran; the contract check could not run (RAISES) ·
bd14e9d95bb7ddfc - AverageMeter helper · level 1 · ran ·
52b386c85c15f1f1 - accuracy helper · level 1 · ran; the contract check could not run ·
ce4344448dda2040 - coverage_size helper · level 1 · ran ·
f246b8eb9dcd2a55
harvested Assembly for conformal prediction algorithm modification (graph method: conformal prediction algorithm modification). 25 bricks; individually on a fixture: 14 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 5 honoured, 0 violated, 1 with no contract checked; 8 where Syntology's instrument failed) · 11 unverified. The assembly has not been run end-to-end.
one of 4 siblings
- RAPS entry · level 0 · unverified ·
e151158cfc4459c8 - EmpiricalCoverage helper · level 0 · unverified ·
99e14fdcc6ff711f - PosthocBase helper · level 0 · unverified ·
ed0742b3cda42dbb - SetSize helper · level 0 · unverified ·
8ad44ec25960a4a2 - compute_q_hat helper · level 0 · unverified ·
b21986df9d596afb - find_kreg_param helper · level 1 · ran · honoured contract ·
d540f5e805ba1e82 - find_lamda_param_adaptiveness helper · level 0 · unverified ·
0e425cc3cb76f358 - find_lamda_param_size helper · level 0 · unverified ·
5002e7982e88d68b - gen_cond_quantile_function helper · level 1 · ran · our draft was wrong ·
9f1c82f5fda99c76 - identity helper · level 1 · ran · honoured contract ·
9adf3e5a14a94f24 - process_classification_prediction helper · level 1 · ran; the contract check could not run (RAISES) ·
162981b9545d9250 - run_temperature_optimization helper · level 1 · ran · our draft was wrong ·
334697eb3983e90d - save_classification_predictions helper · level 0 · unverified ·
75313f9955e8f579 - sort_sum helper · level 1 · ran · our draft was wrong ·
0915e08c6d516b48 - temp_scale_logits helper · level 1 · ran · honoured contract ·
6fd34088368dcdbf - EmpiricalCoverageBase helper · level 1 · ran ·
2df4a9fc1d319ad7 - BaseModule helper · level 0 · unverified ·
466b72a3e0124a34 - _get_num_inputs helper · level 1 · ran · honoured contract ·
916148f6022dcca9 - _get_num_outputs helper · level 1 · ran · honoured contract ·
ce7423706741a98c - gen_inverse_quantile_function helper · level 1 · ran; the contract check could not run (RAISES) ·
355136b6943fb837 - ConformalModelLogits helper · level 0 · unverified ·
b55f91e7bf34638e - get_violation helper · level 1 · ran; the contract check could not run (RAISES) ·
f43a6e1abc3d5ba6 - _get_input_layer_name_and_module helper · level 1 · ran · our draft was wrong ·
b5a8a70192307683 - _get_output_layer_name_and_module helper · level 1 · ran · our draft was wrong ·
1950974c63e5891e - get_single_tau helper · level 0 · unverified ·
8834b23ad655655f
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="2009.14193") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
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