SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2311.04449 · NeurIPS · 2023

Recursion in Recursion: Two-Level Nested Recursion for Length Generalization with Scalability

Jishnu Chowdhury, Cornelia Caragea

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 1 no recorded run), measured 2026-11-22; 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/2311.04449.json · badge: /api/ran/2311.04449.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
JRC1995/BeamRecursionFamily community
Papers with Code archive
1 ran · 1 no recorded run
FunctionStatusWhere it lives
CellLayer Ran
ran on a synthesized input · constructed an object; no result was computed
JRC1995/BeamRecursionFamily/models/encoders/BT_GRC.py
code served (permissive licence) · get_code("323d7a2a1d72ca39")
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 an instance of its own class, CellLayer: the run constructed the object and did not call it, so no result was computed. 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
from torch import nn

torch.manual_seed(0)

# CellLayer expects:
# - hidden_dim: int
# - cell_hidden_dim: int
# - dropout: float

ARGS = {
    "hidden_dim": 4,
    "cell_hidden_dim": 8,
    "dropout": 0.1,
}
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 CellLayer — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a CellLayer 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
BT_GRC Not yet run
unverified (harvested, no recorded run)
JRC1995/BeamRecursionFamily/models/encoders/BT_GRC.py
code served (permissive licence) · get_code("61476c3692537186")
How it ran

no invocation recorded.

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, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 1 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
CellLayer
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2305.19999 (2023-05)
Beam Tree Recursive Cells

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

Binary Balanced Tree Recursive Neural Networks (BBT-RvNNs) enforce sequence composition according to a preset balanced binary tree structure. Thus, their nonlinear recursion depth (which is the tree depth) is just log 2 n (n being the sequence length). Such logarithmic scaling makes BBT-RvNNs efficient and scalable on long sequence tasks such as Long Range Arena (LRA). However, such computational efficiency comes at a cost because BBT-RvNNs cannot solve simple arithmetic tasks like ListOps. On the flip side, RvNN models (e.g., Beam Tree RvNN) that do succeed on ListOps (and other structure-sensitive tasks like formal logical inference) are generally several times more expensive (in time and space) than even Recurrent Neural Networks. In this paper, we introduce a novel framework -Recursion in Recursion (RIR) to strike a balance between the two sides -getting some of the benefits from both worlds. In RIR, we use a form of two-level nested recursion -where the outer recursion is a k-ary balanced tree model with another recursive model (inner recursion) implementing its cell function. For the inner recursion, we choose Beam Tree RvNNs. To adjust Beam Tree RvNNs within RIR we also propose a novel strategy of beam alignment. Overall, this entails that the total recursive depth in RIR is upper-bounded by k log k n. Our best RIR-based model is the first model that demonstrates high (≥ 90%) length-generalization performance on ListOps while at the same time being scalable enough to be trainable on long sequence inputs from LRA (it can reduce the memory usage of the original Beam Tree RvNN by hundreds of times). Moreover, in terms of accuracy in the LRA language tasks, it performs competitively with Structured State Space Models (SSMs) without any special initialization -outperforming Transformers by a large margin. On the other hand, while SSMs can marginally outperform RIR on LRA, they (SSMs) fail to length-generalize on ListOps. Our code is available at: https://github.com/JRC1995/BeamRecursionFamily/. 37th Conference on Neural Information Processing Systems (NeurIPS 2023).

For agents

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

get_harvested_code_for_paper("2311.04449")
get_code_for_paper("2311.04449")
have("2311.04449")

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

curl https://syntology.ai/api/ran/2311.04449.json

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

[![Syntology run record](https://syntology.ai/api/ran/2311.04449.svg)](https://syntology.ai/paper/2311.04449)

Connect an agent — have() is free.