SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1809.07412 · 2018

Learning, Planning, and Control in a Monolithic Neural Event Inference Architecture

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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; 1 failure 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/1809.07412.json · badge: /api/ran/1809.07412.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
CognitiveModeling/reprise reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
ai_loss Ran
ran; our contract draft was wrong, not the code
CognitiveModeling/reprise/tests/test_reprise.py
code served (permissive licence) · get_code("b02fa5240a54dd91")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned Tensor, ndim 0, dtype family float, shape () 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 concatenates outputs along dim=0, then does cumsum along dim=0
# outputs is a list of tensors
# After concatenation, it compares with targets using MSELoss

# Let's say we have 3 output tensors, each of shape (2, 4)
# After concatenation: (6, 4)
# After cumsum: (6, 4)
# So targets should be (6, 4)

outputs = [
    torch.randn(2, 4),
    torch.randn(2, 4),
    torch.randn(2, 4)
]

# targets should match the shape after concatenation: (6, 4)
targets = torch.randn(6, 4)

ARGS = {
    'outputs': outputs,
    'targets': targets
}
Setup block drafted by
a language model, Claude Sonnet 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 Tensor, ndim 0, dtype family float, shape () — shape () 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
ci_loss Ran
ran, honoured the contract we drafted
CognitiveModeling/reprise/tests/test_reprise.py
code served (permissive licence) · get_code("b42c9f05becd0e3a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned Tensor, ndim 0, dtype family float, shape () 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 expects outputs and targets to be lists of tensors
# that can be concatenated along dim=0

# Create a list of output tensors (e.g., from multiple batches or models)
outputs = [
    torch.randn(2, 4),  # batch_size=2, feature_dim=4
    torch.randn(3, 4),  # batch_size=3, feature_dim=4
]

# Create a list of target tensors with matching shapes
targets = [
    torch.randn(2, 4),  # batch_size=2, feature_dim=4
    torch.randn(3, 4),  # batch_size=3, feature_dim=4
]

ARGS = {
    'outputs': outputs,
    'targets': targets
}
Setup block drafted by
a language model, Claude Sonnet 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 Tensor, ndim 0, dtype family float, shape () — shape () 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

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 2 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 2026-11-22.

Repositories linked to this paper

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

Abstract

We introduce REPRISE, a REtrospective and PRospective Inference SchEme, which learns temporal event-predictive models of dynamical systems. REPRISE infers the unobservable contextual event state and accompanying temporal predictive models that best explain the recently encountered sensorimotor experiences retrospectively. Meanwhile, it optimizes upcoming motor activities prospectively in a goal-directed manner. Here, REPRISE is implemented by a recurrent neural network (RNN), which learns temporal forward models of the sensorimotor contingencies generated by different simulated dynamic vehicles. The RNN is augmented with contextual neurons, which enable the encoding of distinct, but related, sensorimotor dynamics as compact event codes. We show that REPRISE concurrently learns to separate and approximate the encountered sensorimotor dynamics: it analyzes sensorimotor error signals adapting both internal contextual neural activities and connection weight values. Moreover, we show that REPRISE can exploit the learned model to induce goal-directed, model-predictive control, that is, approximate active inference: Given a goal state, the system imagines a motor command sequence optimizing it with the prospective objective to minimize the distance to the goal. The RNN activities thus continuously imagine the upcoming future and reflect on the recent past, optimizing the predictive model, the hidden neural state activities, and the upcoming motor activities. As a result, event-predictive neural encodings develop, which allow the invocation of highly effective and adaptive goal-directed sensorimotor control.

For agents

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

get_harvested_code_for_paper("1809.07412")
get_code_for_paper("1809.07412")
have("1809.07412")

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

curl https://syntology.ai/api/ran/1809.07412.json

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

[![Syntology run record](https://syntology.ai/api/ran/1809.07412.svg)](https://syntology.ai/paper/1809.07412)

Connect an agent — have() is free.