SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1908.02899 · 2019

Do Neural Language Representations Learn Physical Commonsense?

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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; 3 failures of our instrument; 0 no recorded run), measured 2026-11-21; 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/1908.02899.json · badge: /api/ran/1908.02899.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
mbforbes/physical-commonsense canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
make_batcher Ran
ran; our contract draft was wrong, not the code
mbforbes/physical-commonsense/pc/models.py
code served (permissive licence) · get_code("06342cf241b8b64a")
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) and returned function. 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 torch

torch.manual_seed(0)

# Create small tensors for x and y
# x: 8 samples, 4 features
# y: 8 samples, 3 targets
x = torch.randn(8, 4)
y = torch.randn(8, 3)

# batch_size
batch_size = 2

ARGS = {
    "x": x,
    "y": y,
    "batch_size": batch_size,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
mlp Ran
ran; our contract draft was wrong, not the code
mbforbes/physical-commonsense/pc/models.py
code served (permissive licence) · get_code("040799bb98fb58f2")
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) and returned Sequential. 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 torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "d_in": 4,
    "input_dropout": 0.1,
    "h": 8,
    "activation": nn.ReLU,
    "inner_dropout": 0.2,
    "d_out": 2,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 and dtype family float describe that coercion, not the output, and are not 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
train Ran
ran; our contract draft was wrong, not the code
mbforbes/physical-commonsense/pc/models.py
code served (permissive licence) · get_code("bbc487522630ed47")
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) and returned tuple, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 torch
import numpy as np
from torch import nn

torch.manual_seed(0)

# Create a simple model
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 8)
        self.linear2 = nn.Linear(8, 3)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

# Create small dummy data
x_np = np.random.randn(2, 4).astype(np.float32)
y_np = np.random.randn(2, 3).astype(np.float32)

# Create config dict with all required keys
config = {
    'lr': 0.01,
    'l2': 0.001,
    'decay_epochs': 5,
    'decay_scale': 0.1,
    'center': True,
    'batch_size': 2,
    'epochs': 2,
    'report_every': 1
}

# Create model instance
model = SimpleModel()

ARGS = {
    'model': model,
    'x_np': x_np,
    'y_np': y_np,
    'config': config
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, 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

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 3 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.

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 2026-11-21.

Repositories linked to this paper

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

Abstract

Humans understand language based on the rich background knowledge about how the physical world works, which in turn allows us to reason about the physical world through language. In addition to the properties of objects (e.g., boats require fuel) and their affordances, i.e., the actions that are applicable to them (e.g., boats can be driven), we can also reason about if-then inferences between what properties of objects imply the kind of actions that are applicable to them (e.g., that if we can drive something then it likely requires fuel). In this paper, we investigate the extent to which state-of-the-art neural language representations, trained on a vast amount of natural language text, demonstrate physical commonsense reasoning. While recent advancements of neural language models have demonstrated strong performance on various types of natural language inference tasks, our study based on a dataset of over 200k newly collected annotations suggests that neural language representations still only learn associations that are explicitly written down.

For agents

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

get_harvested_code_for_paper("1908.02899")
get_code_for_paper("1908.02899")
have("1908.02899")

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

curl https://syntology.ai/api/ran/1908.02899.json

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

[![Syntology run record](https://syntology.ai/api/ran/1908.02899.svg)](https://syntology.ai/paper/1908.02899)

Connect an agent — have() is free.