Papers › Transferable Candidate Proposal with Bounded Uncertainty

Transferable Candidate Proposal with Bounded Uncertainty

7 Dec 2023arXiv:2312.04604archive 2025-07-28

Kyeongryeol Go, Kye-Hyeon Kim

From an empirical perspective, the subset chosen through active learning cannot guarantee an advantage over random sampling when transferred to another model. While it underscores the significance of verifying transferability, experimental design from previous works often neglected that the informativeness of a data subset can change over model configurations. To tackle this issue, we introduce a new experimental design, coined as Candidate Proposal, to find transferable data candidates from which active learning algorithms choose the informative subset. Correspondingly, a data selection algorithm is proposed, namely Transferable candidate proposal with Bounded Uncertainty (TBU), which constrains the pool of transferable data candidates by filtering out the presumably redundant data points based on uncertainty estimation. We verified the validity of TBU in image classification benchmarks, including CIFAR-10/100 and SVHN. When transferred to different model configurations, TBU consistency improves performance in existing active learning algorithms. Our code is available at https://github.com/gokyeongryeol/TBU.

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 21 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 10 unverified. Where Syntology's instrument failed: 3 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: 21 samples from 1 repository, 11 ran (5 with no instrument failure; 6 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 11 samples that ran have no recorded date.

gokyeongryeol/tbu officialmentioned in papermentioned on GitHubpytorchMITSyntology: 21 samples, 11 ran (6 instrument-failed) · 10 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

21 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 10 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · our draft was wrong
3ran; the contract check could not run
5ran
10unverified

Licence: 0 of the 21 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 gokyeongryeol/tbu. “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.

gokyeongryeol/tbu official repository 21 samples, 11 ran (6 instrument-failed) · 10 unverified
AutoContrast in 30 papers active/dataset/augment.py ran · our draft was wrong MIT (permissive) · 4d1221a0588c0703 · report fixture: signature img:Image/0/?, _:NoneType/0/? · returned Image · level recorded 2026-09-24
Brightness in 31 papers active/dataset/augment.py ran; the contract check could not run (RAISES) MIT (permissive) · c83f67dd85072e2d · report fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-24
Color in 29 papers active/dataset/augment.py ran; the contract check could not run (RAISES) MIT (permissive) · 8fa703bbf4bd406f · report fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-24
compute_metric in 18 papers active/models/train_utils.py ran · our draft was wrong MIT (permissive) · 92b61b67ddcc3a83 · report fixture: signature nLab:int/0/int, true:Tensor/1/int, prob:Tensor/2/float · returned tuple · level recorded, date not recorded
ema_thres_update active/models/train_utils.py ran MIT (permissive) · 0b9bab4e26b54ad4 · report fixture: signature thres:Tensor/1/float, thres_ema:Tensor/1/float, ema_m:float/0/float · returned Tensor · level recorded 2026-09-24
get_dataset_train active/dataset/data.py ran MIT (permissive) · 62292de77b72d38e · report fixture: signature data:MockData/0/?, args:MockArgs/0/? · returned tuple · level recorded 2026-09-24
get_dataset_valid active/dataset/data.py ran · our draft was wrong MIT (permissive) · 51d821f3a4dce07f · report fixture: signature data:MockData/0/? · returned list · level recorded 2026-09-24
hard_masking active/models/train_utils.py ran; the contract check could not run (RAISES) MIT (permissive) · 0a3b40f70517db28 · report fixture: returned Tensor · level recorded, date not recorded
init_centers in 8 papers active/selection/badge.py ran MIT (permissive) · 75953c142ae4e662 · report fixture: signature X:ndarray/2/float, K:int/0/int · returned list · level recorded 2026-09-24
make_loader in 12 papers active/models/trainer.py ran MIT (permissive) · 279d8d05cf132b12 · report fixture: signature dataset_lab:MinimalDataset/0/?, dataset_unlab:MinimalDataset/0/?, dataset_valid:MinimalDataset/0/?, args:Args/0/? · returned tuple · level recorded 2026-09-24
make_scheduler in 9 papers active/models/trainer.py ran MIT (permissive) · 28c0113be1ca01e1 · report fixture: signature optimizer:SGD/0/?, args:Args/0/? · returned LambdaLR · level recorded 2026-09-24
Architecture active/selection/strategy.py unverified MIT (permissive) · 9ee7db2b8fa19d16 · report
BaseModel in 92 papers active/selection/strategy.py unverified MIT (permissive) · d6be60152ea57197 · report
Laplace in 5 papers active/selection/strategy.py unverified MIT (permissive) · bf32d8572c0843cb · report
Strategy in 10 papers active/selection/strategy.py unverified MIT (permissive) · f71b931ef7fcb1e3 · report
ema_thres_update active/models/train_utils.py unverified MIT (permissive) · 7441d4dcb7a2f492 · report
get_transform in 75 papers active/dataset/data_utils.py unverified MIT (permissive) · 50d9500f54e43bd3 · report
make_ema_model active/models/model_factory.py unverified MIT (permissive) · f3b4f1ca365fd45e · report
make_model in 37 papers active/models/model_factory.py unverified MIT (permissive) · 181e3925fb15dca8 · report
prepare_data in 87 papers active/dataset/data.py unverified MIT (permissive) · d4ab69f9179216c0 · report
train_model in 103 papers active/models/trainer.py unverified MIT (permissive) · 10e0b8b620b79988 · 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 Transferable candidate proposal with Bounded Uncertainty (TBU) (graph method: Transferable candidate proposal with Bounded Uncertainty (TBU)). 4 bricks; individually on a fixture: 0 ran · 4 unverified. The assembly has not been run end-to-end.

  1. Strategy entry · level 0 · unverified · f71b931ef7fcb1e3
  2. Laplace helper · level 0 · unverified · bf32d8572c0843cb
  3. Architecture helper · level 0 · unverified · 9ee7db2b8fa19d16
  4. BaseModel helper · level 0 · unverified · d6be60152ea57197

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="2312.04604") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Active LearningExperimental DesignImage ClassificationInformativenessimage-classification

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