SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2412.04671 · NeurIPS · 2024

Fully Distributed, Flexible Compositional Visual Representations via Soft Tensor Products

Yang Song, Maurice Pagnucco, Bethia Sun

arXiv · PDF · Open in the Atlas

Code that ran

11 of 12 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; 9 failures of our instrument; 1 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/2412.04671.json · badge: /api/ran/2412.04671.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
gomb0c/soft_tpr canonical (classifier label)
classifier basis: census
11 ran · 1 no recorded run
FunctionStatusWhere it lives
bce_recon_loss_fn Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
gomb0c/soft_tpr/src/repn_learners/soft_tpr_ae/optim/loss.py
pointer only (licence: NONE) · get_code("00ba486ea1f7537e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gomb0c/soft_tpr 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.

gaussian_kls Ran
ran; our contract draft was wrong, not the code
gomb0c/soft_tpr/src/repn_learners/soft_tpr_ae/utils.py
pointer only (licence: NONE) · get_code("406c6e802e6ba500")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gomb0c/soft_tpr 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_activation_name Ran
ran; our contract draft was wrong, not the code
gomb0c/soft_tpr/src/repn_learners/soft_tpr_ae/utils.py
pointer only (licence: NONE) · get_code("a9ef158cd6f83f6d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gomb0c/soft_tpr 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_most_recent_dir Ran
ran; our contract draft was wrong, not the code
gomb0c/soft_tpr/src/logger/load.py
pointer only (licence: NONE) · get_code("343bea31ec8dd2f5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gomb0c/soft_tpr 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_n_layers Ran
ran, honoured the contract we drafted
gomb0c/soft_tpr/src/repn_learners/soft_tpr_ae/utils.py
pointer only (licence: NONE) · get_code("0ed038365cbe2dc0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gomb0c/soft_tpr 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_result_from_summary_json Ran
ran; our contract draft was wrong, not the code
gomb0c/soft_tpr/src/vis_results/plot_results_final-tpr_comparison.py
pointer only (licence: NONE) · get_code("4217eff3614e5a21")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gomb0c/soft_tpr 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_save_path Ran
ran; our contract draft was wrong, not the code
gomb0c/soft_tpr/src/logger/load.py
pointer only (licence: NONE) · get_code("76111b30fc874b16")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gomb0c/soft_tpr 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.

is_incorrect_run Ran
ran, violated the contract we drafted
gomb0c/soft_tpr/src/vis_results/plot_results_final-tpr_comparison.py
pointer only (licence: NONE) · get_code("2445492633b2e3e7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gomb0c/soft_tpr 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.

mse_recon_loss_fn Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
gomb0c/soft_tpr/src/repn_learners/soft_tpr_ae/optim/loss.py
pointer only (licence: NONE) · get_code("58f2f3e8317316ec")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gomb0c/soft_tpr 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.

nearest_embed Ran
ran; our contract draft was wrong, not the code
gomb0c/soft_tpr/src/repn_learners/soft_tpr_ae/model/vq_vae.py
pointer only (licence: NONE) · get_code("34f0bd8890d57785")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gomb0c/soft_tpr 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.

nearest_embed Ran
ran; our contract draft was wrong, not the code
gomb0c/soft_tpr/src/repn_learners/soft_tpr_ae/model/nearest_embed.py
pointer only (licence: NONE) · get_code("663b284fc8ed7db2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gomb0c/soft_tpr 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.

parse_results_from_wandb_logs Not yet run
unverified (harvested, no recorded run)
gomb0c/soft_tpr/src/vis_results/plot_results_final-tpr_comparison.py
pointer only (licence: NONE) · get_code("b2d4cc7bb63548ca")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gomb0c/soft_tpr 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. No invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 0 later) and 8 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
nearest_embed 2 other papers
2 dated earlier
1711.00937 (2017-11)
Neural Discrete Representation Learning
2406.03234 (2024-06)
Fine-Grained Causal Dynamics Learning with Quantization for Improving Robustness in Reinforcement Learning
gaussian_kls 1 other paper
1 dated earlier
2106.03375 (2021-06)
Commutative Lie Group VAE for Disentanglement Learning
get_activation_name 1 other paper
1 dated earlier
2210.01796 (2022-10)
Multi-objective Deep Data Generation with Correlated Property Control

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

Since the inception of the classicalist vs. connectionist debate, it has been argued that the ability to systematically combine symbol-like entities into compositional representations is crucial for human intelligence. In connectionist systems, the field of disentanglement has gained prominence for its ability to produce explicitly compositional representations; however, it relies on a fundamentally symbolic, concatenative representation of compositional structure that clashes with the continuous, distributed foundations of deep learning. To resolve this tension, we extend Smolensky's Tensor Product Representation (TPR) and introduce Soft TPR, a representational form that encodes compositional structure in an inherently distributed, flexible manner, along with Soft TPR Autoencoder, a theoretically-principled architecture designed specifically to learn Soft TPRs. Comprehensive evaluations in the visual representation learning domain demonstrate that the Soft TPR framework consistently outperforms conventional disentanglement alternatives -achieving state-of-the-art disentanglement, boosting representation learner convergence, and delivering superior sample efficiency and low-sample regime performance in downstream tasks. These findings highlight the promise of a distributed and flexible approach to representing compositional structure by potentially enhancing alignment with the core principles of deep learning over the conventional symbolic approach.

For agents

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

get_harvested_code_for_paper("2412.04671")
get_code_for_paper("2412.04671")
have("2412.04671")

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

curl https://syntology.ai/api/ran/2412.04671.json

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

[![Syntology run record](https://syntology.ai/api/ran/2412.04671.svg)](https://syntology.ai/paper/2412.04671)

Connect an agent — have() is free.