SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2405.04405 · ICML · 2024

Weakly-Supervised Residual Evidential Learning for Multi-Instance Uncertainty Estimation

Pei Liu, Luping Ji

arXiv · PDF · Open in the Atlas

Code that ran

6 of 11 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 6 failures of our instrument; 5 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2405.04405.json · badge: /api/ran/2405.04405.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
liupei101/MIREL canonical (classifier label)
classifier basis: census
6 ran · 4 no recorded run
liupei101/mirel canonical (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
FunctionStatusWhere it lives
aggregate_instance_evidence Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
liupei101/MIREL/loss/loss_edl.py
code served (permissive licence) · get_code("af34b926cbeb626c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# For 'mean' method: instance_evidence should be shape (batch_size, num_instances, num_classes)
# For 'max' method: same shape, accesses [:, :, [1]] and argmax on dim 1
# For 'diweight' method: weight must have shape[1] == instance_evidence.shape[1]

# Create instance_evidence tensor: (batch=2, instances=3, classes=4)
instance_evidence = torch.randn(2, 3, 4)

# Create weight tensor for 'diweight' method
# Must satisfy: weight.shape[1] == instance_evidence.shape[1] (which is 3)
# Shape: (batch=2, instances=3, classes=4)
weight = torch.randn(2, 3, 4)

ARGS = {
    'instance_evidence': instance_evidence,
    'method': 'mean',
    'weight': weight
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
exp_evidence Ran
ran; our contract draft was wrong, not the code
liupei101/MIREL/model/layer_utils.py
code served (permissive licence) · get_code("ddba7773fd3d51f7")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function exp_evidence takes a single parameter y and applies torch.exp and torch.clamp to it
# y should be a tensor
y = torch.randn(2, 4)

ARGS = {
    "y": y
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
kl_divergence Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
liupei101/MIREL/loss/loss_edl.py
code served (permissive licence) · get_code("b810113372d69a75")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 1) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Construct alpha tensor: batch_size=2, num_classes=4
# Alpha parameters must be positive (used in lgamma, digamma)
alpha = torch.ones(2, 4, dtype=torch.float32) + 1.0  # shape: (2, 4)

num_classes = 4

device = None  # Let the function determine device from alpha

ARGS = {
    "alpha": alpha,
    "num_classes": num_classes,
    "device": device,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 1) — shape (2, 1) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
loss_reg_l1 Ran
ran; our contract draft was wrong, not the code
liupei101/MIREL/loss/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from liupei101/VLSA, is pointer only (licence: NOASSERTION) · get_code("9e753dca3a11c335")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from liupei101/VLSA, and GitHub could not classify the licence of that repository (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

relu_evidence Ran
ran; our contract draft was wrong, not the code
liupei101/MIREL/model/layer_utils.py
code served (permissive licence) · get_code("efecc687b786a0cc")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn.functional as F

torch.manual_seed(0)

# relu_evidence takes a single parameter y and applies F.relu to it
# y should be a tensor
y = torch.randn(2, 4)

ARGS = {
    "y": y
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
softplus_evidence Ran
ran; our contract draft was wrong, not the code
liupei101/MIREL/model/layer_utils.py
code served (permissive licence) · get_code("f8059bd409d4bdf3")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn.functional as F

torch.manual_seed(0)

# The function softplus_evidence takes a single parameter y
# and applies F.softplus to it. y should be a tensor.
# Create a small tensor with distinct dimensions for probing
y = torch.randn(2, 4)

ARGS = {
    "y": y
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
ABMIL Not yet run
unverified (harvested, no recorded run)
liupei101/mirel/model/evmil.py
code served (permissive licence) · get_code("74911f7aa32bebb9")
How it ran

no invocation recorded.

Deep_ABMIL Not yet run
unverified (harvested, no recorded run)
liupei101/MIREL/model/model_utils.py
code served (permissive licence) · get_code("d257066e06719d0b")
How it ran

no invocation recorded.

Deep_MIL Not yet run
unverified (harvested, no recorded run)
liupei101/MIREL/model/model_utils.py
code served (permissive licence) · get_code("802a0dfcb54377e6")
How it ran

no invocation recorded.

load_loss Not yet run
unverified (harvested, no recorded run)
liupei101/MIREL/loss/utils.py
code served (permissive licence) · get_code("6ed66871680b63db")
How it ran

no invocation recorded.

load_model Not yet run
unverified (harvested, no recorded run)
liupei101/MIREL/model/model_utils.py
code served (permissive licence) · get_code("6640364ac6052908")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 4 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 3 later) and 7 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
exp_evidence 4 other papers
3 dated earlier, 1 later
1806.01768 (2018-06)
Evidential Deep Learning to Quantify Classification Uncertainty
136640190 (2022 (year only))
Dual-Evidential Learning for Weakly-supervised Temporal Action Localization
2309.02995 (2023-09)
Continual Evidential Deep Learning for Out-of-Distribution Detection
and 1 more not named here
relu_evidence 3 other papers
2 dated earlier, 1 later
1806.01768 (2018-06)
Evidential Deep Learning to Quantify Classification Uncertainty
136640190 (2022 (year only))
Dual-Evidential Learning for Weakly-supervised Temporal Action Localization
2406.07882 (2024-06)
Designing a Dashboard for Transparency and Control of Conversational AI
softplus_evidence 2 other papers
2 dated earlier
1806.01768 (2018-06)
Evidential Deep Learning to Quantify Classification Uncertainty
136640190 (2022 (year only))
Dual-Evidential Learning for Weakly-supervised Temporal Action Localization
loss_reg_l1 1 other paper
1 later
2409.09369 (2024-09)
Interpretable Vision-Language Survival Analysis with Ordinal Inductive Bias for Computational Pathology

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Uncertainty estimation (UE), as an effective means to quantify predictive uncertainty, is crucial for safe and reliable decision-making, especially in high-risk scenarios. Existing UE schemes usually assume that there are completely-labeled samples to support fully-supervised learning. In practice, however, many UE tasks often have no sufficiently-labeled data to use, such as the Multiple Instance Learning (MIL) with only weak instance annotations. To bridge this gap, this paper, for the first time, addresses the weakly-supervised issue of Multi-Instance UE (MIUE) and proposes a new baseline scheme, Multi-Instance Residual Evidential Learning (MIREL). Particularly, at the fine-grained instance UE with only weak supervision, we derive a multi-instance residual operator through the Fundamental Theorem of Symmetric Functions. On this operator derivation, we further propose MIREL to jointly model the high-order predictive distribution at bag and instance levels for MIUE. Extensive experiments empirically demonstrate that our MIREL not only could often make existing MIL networks perform better in MIUE, but also could surpass representative UE methods by large margins, especially in instancelevel UE tasks. Our source code is available at https://github.com/liupei101/MIREL.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2405.04405")
get_code_for_paper("2405.04405")
have("2405.04405")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2405.04405.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2405.04405.svg)](https://syntology.ai/paper/2405.04405)

Connect an agent — have() is free.