Papers › No True State-of-the-Art? OOD Detection Methods are Inconsistent across Datasets

No True State-of-the-Art? OOD Detection Methods are Inconsistent across Datasets

12 Sep 2021arXiv:2109.05554archive 2025-07-28

Fahim Tajwar, Ananya Kumar, Sang Michael Xie, Percy Liang

Out-of-distribution detection is an important component of reliable ML systems. Prior literature has proposed various methods (e.g., MSP (Hendrycks & Gimpel, 2017), ODIN (Liang et al., 2018), Mahalanobis (Lee et al., 2018)), claiming they are state-of-the-art by showing they outperform previous methods on a selected set of in-distribution (ID) and out-of-distribution (OOD) datasets. In this work, we show that none of these methods are inherently better at OOD detection than others on a standardized set of 16 (ID, OOD) pairs. We give possible explanations for these inconsistencies with simple toy datasets where whether one method outperforms another depends on the structure of the ID and OOD datasets in question. Finally, we show that a method outperforming another on a certain (ID, OOD) pair may not do so in a low-data regime. In the low-data regime, we propose a distance-based method, Pairwise OOD detection (POD), which is based on Siamese networks and improves over Mahalanobis by sidestepping the expensive covariance estimation step. Our results suggest that the OOD detection problem may be too broad, and we should consider more specific structures for leverage.

PaperPDFCodeCode Syntology ranMethod as code

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 25 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 14 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 25 samples from 1 repository, 11 ran (7 with no instrument failure; 4 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.

tajwarfahim/ood_detection_inconsistency officialmentioned in paperpytorchSyntology: 25 samples, 11 ran (4 instrument-failed) · 14 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

25 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 14 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.

4ran · our draft was wrong
7ran
14unverified

Licence: 25 of the 25 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 tajwarfahim/ood_detection_inconsistency. “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.

tajwarfahim/ood_detection_inconsistency official repository 25 samples, 11 ran (4 instrument-failed) · 14 unverified
LinearCritic utils/siamese_network.py ran no licence file found · pointer only · a04706445c3a44b5 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
ResNet in 139 papers utils/siamese_network.py ran · metamorphic tier: invariant no licence file found · pointer only · 0f5c726e9580ca0a · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
ResNet18 in 174 papers utils/siamese_network.py ran · our draft was wrong no licence file found · pointer only · 7ca36149b988c54e · report fixture: signature contains_last_layer:bool/0/bool, num_input_channels:int/0/int, num_classes:int/0/int · returned ResNet · level recorded 2026-09-22
ResNet34 in 91 papers utils/siamese_network.py ran · our draft was wrong no licence file found · pointer only · 9d4e412922385a20 · report fixture: signature contains_last_layer:bool/0/bool, num_input_channels:int/0/int, num_classes:int/0/int · returned ResNet · level recorded 2026-09-22
ResNet50 in 83 papers utils/siamese_network.py ran · our draft was wrong no licence file found · pointer only · caa63b6cbc7fd52e · report fixture: signature contains_last_layer:bool/0/bool, num_input_channels:int/0/int, num_classes:int/0/int · returned ResNet · level recorded 2026-09-22
ResNetWithoutLastLayer utils/siamese_network.py ran · metamorphic tier: invariant no licence file found · pointer only · a1333c964477658d · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
SiameseNetworkVersion1 utils/siamese_network.py ran no licence file found · pointer only · ef84d9b3e36ef6bb · report fixture: signature x1:Tensor/2/float, x2:Tensor/2/float · returned Tensor · level recorded 2026-09-24
SiameseNetworkVersion2 utils/siamese_network.py ran no licence file found · pointer only · 091727a59cfe18c5 · report fixture: signature x1:Tensor/2/float, x2:Tensor/2/float · returned Tensor · level recorded 2026-09-24
SiameseNetworkVersion3 utils/siamese_network.py ran no licence file found · pointer only · bb726f48afa2bf1e · report fixture: signature x1:Tensor/2/float, x2:Tensor/2/float · returned Tensor · level recorded 2026-09-24
SiameseNetworkVersion5 utils/siamese_network.py ran fingerprinted no licence file found · pointer only · b655b80a757b91a5 · report fixture: signature x1:Tensor/2/float, x2:Tensor/2/float · returned Tensor · level recorded 2026-09-24
process_shared_model_name_wide_resnet utils/siamese_network.py ran · our draft was wrong no licence file found · pointer only · a8193ab021196916 · report fixture: signature shared_model_name:str/0/str · returned dict · level recorded 2026-09-22
SiameseNetworkSkeleton utils/siamese_network.py unverified no licence file found · pointer only · e113c4f6c24ebbd1 · report
SiameseNetworkVersion4 utils/siamese_network.py unverified no licence file found · pointer only · 0b7f4ef94c512dfd · report
WideResNet in 13 papers utils/siamese_network.py unverified no licence file found · pointer only · e005fe22e69cd426 · report
WideResNetWithoutLastLayer utils/siamese_network.py unverified no licence file found · pointer only · c175203550f4dcb0 · report
createSiameseNetwork utils/siamese_network.py unverified no licence file found · pointer only · 84ab954d28da2dfd · report
create_resnet utils/siamese_network.py unverified no licence file found · pointer only · 31f08a3d3a6f84f3 · report
create_resnet utils/siamese_network.py unverified no licence file found · pointer only · e893a80255c1f421 · report
create_resnet_based_shared_model utils/siamese_network.py unverified no licence file found · pointer only · 1bf44f5fcc3432c6 · report
create_siamese_network_wrapper utils/siamese_network.py unverified no licence file found · pointer only · 1655bbb2f181e73d · report
create_wide_resnet utils/siamese_network.py unverified no licence file found · pointer only · cfd72ce7f48cf580 · report
create_wide_resnet_based_shared_model utils/siamese_network.py unverified no licence file found · pointer only · 3d3f74f6425de128 · report
create_wide_resnet_based_shared_model utils/siamese_network.py unverified no licence file found · pointer only · adefa2d05ffc3cb9 · report
print_message utils/siamese_network.py unverified no licence file found · pointer only · 623dbfda864bfef7 · report
process_shared_model_name_wide_resnet utils/siamese_network.py unverified no licence file found · pointer only · 39a439e6c10d840b · 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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Pairwise OOD detection (POD) (graph method: Pairwise OOD detection (POD)). 25 bricks; individually on a fixture: 14 ran (of which 3 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 11 unverified. The assembly has not been run end-to-end.

  1. create_siamese_network_wrapper entry · level 0 · unverified · 1655bbb2f181e73d
  2. createSiameseNetwork helper · level 0 · unverified · 84ab954d28da2dfd
  3. create_resnet_based_shared_model model · level 0 · unverified · 1bf44f5fcc3432c6
  4. create_wide_resnet_based_shared_model model · level 0 · unverified · adefa2d05ffc3cb9
  5. SiameseNetworkVersion1 helper · level 1 · ran · ef84d9b3e36ef6bb
  6. SiameseNetworkVersion2 helper · level 1 · ran · 091727a59cfe18c5
  7. SiameseNetworkVersion3 helper · level 1 · ran · bb726f48afa2bf1e
  8. SiameseNetworkVersion4 helper · level 0 · unverified · 0b7f4ef94c512dfd
  9. SiameseNetworkVersion5 helper · level 1 · ran · b655b80a757b91a5
  10. print_message helper · level 0 · unverified · 623dbfda864bfef7
  11. create_resnet model · level 0 · unverified · e893a80255c1f421
  12. create_wide_resnet helper · level 0 · unverified · cfd72ce7f48cf580
  13. process_shared_model_name_wide_resnet helper · level 1 · ran · our draft was wrong · a8193ab021196916
  14. SiameseNetworkSkeleton helper · level 0 · unverified · e113c4f6c24ebbd1
  15. LinearCritic helper · level 1 · ran · a04706445c3a44b5
  16. ResNet18 helper · level 1 · ran · our draft was wrong · 7ca36149b988c54e
  17. ResNet34 helper · level 1 · ran · our draft was wrong · 9d4e412922385a20
  18. ResNet50 helper · level 1 · ran · our draft was wrong · caa63b6cbc7fd52e
  19. WideResNet helper · level 0 · unverified · e005fe22e69cd426
  20. WideResNetWithoutLastLayer helper · level 0 · unverified · c175203550f4dcb0
  21. BasicBlock helper · level 1 · ran · e33f907725fe74f0
  22. ResNet helper · level 1 · ran · 0f5c726e9580ca0a
  23. ResNetWithoutLastLayer helper · level 1 · ran · a1333c964477658d
  24. Bottleneck helper · level 1 · ran · a89b8862957e5753
  25. NetworkBlock helper · level 1 · ran · dc96cf9441e16644

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="2109.05554") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Out of Distribution (OOD) DetectionOut-of-Distribution Detection

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