SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.20141 · ICLR · 2024

Contrastive Difference Predictive Coding

Ruslan Salakhutdinov, Benjamin Eysenbach, Chongyi Zheng

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 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, 0 violated it and 0 have no contract verdict; 4 failures of our instrument; 0 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/2310.20141.json · badge: /api/ran/2310.20141.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
chongyi-zheng/td_infonce canonical (classifier label)
classifier basis not recorded on the link
5 ran · 0 no recorded run
FunctionStatusWhere it lives
apply_policy_and_sample Ran
ran; our contract draft was wrong, not the code
chongyi-zheng/td_infonce/td_infonce/networks.py
pointer only (licence: MIT); the stored copy get_code serves, from mnm-anonymous/qmd, is pointer only (licence: NONE) · get_code("86b31cc8f58a61b4")
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 mnm-anonymous/qmd, 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.

get_reward Ran
ran, honoured the contract we drafted
chongyi-zheng/td_infonce/envs/fetch_envs.py
pointer only (licence: MIT); the stored copy get_code serves, from mnm-anonymous/qmd, is pointer only (licence: NONE) · get_code("35bd6ebd08652e20")
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 mnm-anonymous/qmd, 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.

make_offline_d4rl Ran
ran; our contract draft was wrong, not the code
chongyi-zheng/td_infonce/envs/offline_ant_envs.py
pointer only (licence: MIT); the stored copy get_code serves, from mnm-anonymous/qmd, is pointer only (licence: NONE) · get_code("aae1c7c736822527")
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 mnm-anonymous/qmd, 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.

obs_to_goal_1d Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
chongyi-zheng/td_infonce/td_infonce/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from mnm-anonymous/qmd, is pointer only (licence: NONE) · get_code("414dbeb2f8b06a40")
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 mnm-anonymous/qmd, 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.

obs_to_goal_2d Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
chongyi-zheng/td_infonce/td_infonce/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from mnm-anonymous/qmd, is pointer only (licence: NONE) · get_code("1896647d018339ef")
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 mnm-anonymous/qmd, 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.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 5 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 5 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
apply_policy_and_sample 1 other paper
1 later
2406.17098 (2024-06)
Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making
get_reward 1 other paper
1 later
2406.17098 (2024-06)
Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making
make_offline_d4rl 1 other paper
1 later
2406.17098 (2024-06)
Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making
obs_to_goal_1d 1 other paper
1 later
2406.17098 (2024-06)
Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making
obs_to_goal_2d 1 other paper
1 later
2406.17098 (2024-06)
Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making

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

Predicting and reasoning about the future lie at the heart of many time-series questions. For example, goal-conditioned reinforcement learning can be viewed as learning representations to predict which states are likely to be visited in the future. While prior methods have used contrastive predictive coding to model time series data, learning representations that encode long-term dependencies usually requires large amounts of data. In this paper, we introduce a temporal difference version of contrastive predictive coding that stitches together pieces of different time series data to decrease the amount of data required to learn predictions of future events. We apply this representation learning method to derive an off-policy algorithm for goal-conditioned RL. Experiments demonstrate that, compared with prior RL methods, ours achieves 2× median improvement in success rates and can better cope with stochastic environments. In tabular settings, we show that our method is about 20× more sample efficient than the successor representation and 1500× more sample efficient than the standard (Monte Carlo) version of contrastive predictive coding.

For agents

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

get_harvested_code_for_paper("2310.20141")
get_code_for_paper("2310.20141")
have("2310.20141")

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

curl https://syntology.ai/api/ran/2310.20141.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.20141.svg)](https://syntology.ai/paper/2310.20141)

Connect an agent — have() is free.