SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2009.02623 · 2020

Information Theoretic Counterfactual Learning from Missing-Not-At-Random Feedback

arXiv · PDF · Open in the Atlas

Code that ran

5 of 7 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; 1 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 3 failures of our instrument; 2 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/2009.02623.json · badge: /api/ran/2009.02623.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
RyanWangZf/CVIB-Rec canonical (classifier label)
classifier basis: census
5 ran · 2 no recorded run
FunctionStatusWhere it lives
generate_total_sample Ran
ran, honoured the contract we drafted
RyanWangZf/CVIB-Rec/matrix_factorization.py
pointer only (licence: MIT); the stored copy get_code serves, from haoxuanli-pku/iclr24-kernel-balancing, is pointer only (licence: NONE) · get_code("ae360e2dd0114535")
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 haoxuanli-pku/iclr24-kernel-balancing, and GitHub detected no licence in that repository when it was checked. 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.

gini_index Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
RyanWangZf/CVIB-Rec/utils.py
code served (permissive licence) · get_code("615fa676468d85d9")
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 tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 numpy as np

# The function takes user_utility as input
# It expects an array-like of numeric values representing utilities for each user
# The function computes: cumulative sum, total sum, length, and uses them for Gini calculation

# Create a simple user_utility array with distinct values
user_utility = np.array([1.5, 2.3, 0.8, 3.2, 1.9, 2.1])

ARGS = {
    'user_utility': user_utility
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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
one_hot Ran
ran; our contract draft was wrong, not the code
RyanWangZf/CVIB-Rec/matrix_factorization.py
code served (permissive licence) · get_code("4fe5b26db1726dd8")
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 3, dtype family float, shape (2, 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 one_hot takes a single parameter x
# Looking at the body: x is used with torch.unsqueeze and 1 - x
# So x should be a tensor that supports arithmetic operations
# Based on the logic, x appears to be binary values (0s and 1s) or floats in [0, 1]
# The function creates a one-hot like output by stacking (1-x) and x

# Create a small tensor with shape (2, 4) - batch size 2, feature dim 4
x = torch.tensor([[0.0, 1.0, 0.5, 0.2],
                   [1.0, 0.0, 0.8, 0.3]], dtype=torch.float32)

ARGS = {
    "x": x
}
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 3, dtype family float, shape (2, 2, 4) — shape (2, 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
rating_mat_to_sample Ran
ran; our contract draft was wrong, not the code
RyanWangZf/CVIB-Rec/dataset.py
code served (permissive licence) · get_code("926bdb90da334126")
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 tuple. The image it ran in was not recorded. If your copy returns the same type 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 numpy as np

# Create a small rating matrix with some non-zero entries
# Using a 4x3 matrix (distinct dimensions) with a few ratings
mat = np.array([
    [5.0, 0.0, 3.0],
    [0.0, 4.0, 0.0],
    [2.0, 0.0, 0.0],
    [0.0, 1.0, 5.0]
], dtype=np.float32)

ARGS = {
    "mat": mat
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
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
sigmoid Ran
ran, violated the contract we drafted
RyanWangZf/CVIB-Rec/matrix_factorization.py
pointer only (licence: MIT); the stored copy get_code serves, from baharanm/craig, is pointer only (licence: NONE) · get_code("b30dd0f0a1d1fde8")
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 baharanm/craig, and GitHub detected no licence in that repository when it was checked. 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.

load_data Not yet run
unverified (harvested, no recorded run)
RyanWangZf/CVIB-Rec/dataset.py
code served (permissive licence) · get_code("bde459e5e57b9c6d")
How it ran

no invocation recorded.

simulate_click_or_not Not yet run
unverified (harvested, no recorded run)
RyanWangZf/CVIB-Rec/utils.py
code served (permissive licence) · get_code("6a729d144afe99a2")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 7 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 7 later) and 0 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
sigmoid 6 other papers
2 dated earlier, 4 later
1905.03381 (2019-05)
AutoAssist: A Framework to Accelerate Training of Deep Neural Networks
1906.01827 (2019-06)
Coresets for Data-efficient Training of Machine Learning Models
2404.19596 (2024-04)
Debiased Collaborative Filtering with Kernel-Based Causal Balancing
and 3 more not named here
generate_total_sample 2 other papers
2 later
2404.19596 (2024-04)
Debiased Collaborative Filtering with Kernel-Based Causal Balancing
2404.19620 (2024-04)
Be Aware of the Neighborhood Effect: Modeling Selection Bias under Interference
gini_index 2 other papers
2 later
2404.19596 (2024-04)
Debiased Collaborative Filtering with Kernel-Based Causal Balancing
2404.19620 (2024-04)
Be Aware of the Neighborhood Effect: Modeling Selection Bias under Interference
load_data 2 other papers
2 later
2404.19596 (2024-04)
Debiased Collaborative Filtering with Kernel-Based Causal Balancing
2404.19620 (2024-04)
Be Aware of the Neighborhood Effect: Modeling Selection Bias under Interference
one_hot 2 other papers
2 later
2404.19596 (2024-04)
Debiased Collaborative Filtering with Kernel-Based Causal Balancing
2404.19620 (2024-04)
Be Aware of the Neighborhood Effect: Modeling Selection Bias under Interference
rating_mat_to_sample 2 other papers
2 later
2404.19596 (2024-04)
Debiased Collaborative Filtering with Kernel-Based Causal Balancing
2404.19620 (2024-04)
Be Aware of the Neighborhood Effect: Modeling Selection Bias under Interference
simulate_click_or_not 2 other papers
2 later
2404.19596 (2024-04)
Debiased Collaborative Filtering with Kernel-Based Causal Balancing
2404.19620 (2024-04)
Be Aware of the Neighborhood Effect: Modeling Selection Bias under Interference

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

Counterfactual learning for dealing with missing-not-at-random data (MNAR) is an intriguing topic in the recommendation literature since MNAR data are ubiquitous in modern recommender systems. Missing-at-random (MAR) data, namely randomized controlled trials (RCTs), are usually required by most previous counterfactual learning methods for debiasing learning. However, the execution of RCTs is extraordinarily expensive in practice. To circumvent the use of RCTs, we build an information-theoretic counterfactual variational information bottleneck (CVIB), as an alternative for debiasing learning without RCTs. By separating the task-aware mutual information term in the original information bottleneck Lagrangian into factual and counterfactual parts, we derive a contrastive information loss and an additional output confidence penalty, which facilitates balanced learning between the factual and counterfactual domains. Empirical evaluation on real-world datasets shows that our CVIB significantly enhances both shallow and deep models, which sheds light on counterfactual learning in recommendation that goes beyond RCTs.

For agents

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

get_harvested_code_for_paper("2009.02623")
get_code_for_paper("2009.02623")
have("2009.02623")

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

curl https://syntology.ai/api/ran/2009.02623.json

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

[![Syntology run record](https://syntology.ai/api/ran/2009.02623.svg)](https://syntology.ai/paper/2009.02623)

Connect an agent — have() is free.