SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.10211 · 2024

Hierarchical State Space Models for Continuous Sequence-to-Sequence Modeling

arXiv · PDF · Open in the Atlas

Code that ran

5 of 6 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; 1 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2402.10211.json · badge: /api/ran/2402.10211.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
raunaqbhirangi/hiss canonical (classifier label)
classifier basis: census
5 ran · 1 no recorded run
FunctionStatusWhere it lives
get_num_params Ran
ran, honoured the contract we drafted
raunaqbhirangi/hiss/hiss/utils/train_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from fortuinlab/spam-pruning, is pointer only (licence: NONE) · get_code("b81882decca625ee")
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 fortuinlab/spam-pruning, 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.

aggregate_list_of_dicts Ran
ran; our contract draft was wrong, not the code
raunaqbhirangi/hiss/hiss/utils/data_utils.py
code served (permissive licence) · get_code("17f4101e6a3c928f")
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 dict. 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 numpy as np

# Test case 1: Simple list of dicts with scalar values
list_of_dicts_simple = [
    {'a': 1, 'b': 2},
    {'a': 3, 'b': 4},
    {'a': 5, 'b': 6}
]

# Test case 2: List of dicts with numpy arrays
list_of_dicts_arrays = [
    {'x': np.array([1, 2, 3]), 'y': np.array([4, 5, 6])},
    {'x': np.array([7, 8, 9]), 'y': np.array([10, 11, 12])}
]

# Test case 3: List of dicts with mixed types
list_of_dicts_mixed = [
    {'scalar': 10, 'array': np.array([1, 2])},
    {'scalar': 20, 'array': np.array([3, 4])}
]

# Test case 4: Nested list of dicts
list_of_dicts_nested = [
    [{'a': 1, 'b': 2}, {'a': 3, 'b': 4}],
    [{'a': 5, 'b': 6}, {'a': 7, 'b': 8}]
]

# Test case 5: Empty list
list_of_dicts_empty = []

ARGS = {
    'list_of_dicts': list_of_dicts_simple
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
cauchy_naive Ran
ran; our contract draft was wrong, not the code
raunaqbhirangi/hiss/hiss/s4.py
code served (permissive licence) · get_code("b7d9d94554e93b1b")
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 Tensor, ndim 2, dtype family float, shape (2, 3) 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)

# v: (..., N) - shape (batch, N)
# z: (..., L) - shape (batch, L)
# w: (..., N) - shape (batch, N)

batch_size = 2
N = 4
L = 3

v = torch.randn(batch_size, N)
z = torch.randn(batch_size, L)
w = torch.randn(batch_size, N)

ARGS = {
    "v": v,
    "z": z,
    "w": w,
}
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 Tensor, ndim 2, dtype family float, shape (2, 3) — shape (2, 3) 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
change_cf Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
raunaqbhirangi/hiss/hiss/tasks/ronin_task.py
code served (permissive licence) · get_code("29211975823f3158")
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 Tensor, ndim 2, dtype family float, shape (2, 3) 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 numpy as np
import torch

torch.manual_seed(0)

# Construct ori: quaternion [n]x4
# Can be either 1D (shape [4]) or 2D (shape [n, 4])
ori = torch.tensor([[0.8, 0.2, 0.3, 0.5], [0.7, 0.1, 0.4, 0.6]], dtype=torch.float32)

# Construct vectors: nx3
vectors = torch.tensor([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]], dtype=torch.float32)

ARGS = {
    "ori": ori,
    "vectors": vectors,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 3) — shape (2, 3) 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
log_vandermonde_naive Ran
ran; our contract draft was wrong, not the code
raunaqbhirangi/hiss/hiss/s4.py
code served (permissive licence) · get_code("e25911109ba29783")
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 Tensor, ndim 2, dtype family float, shape (2, 3) 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)

# Create small tensors with distinct dimensions
batch_size = 2
N = 4
L = 3

# v: (..., N) - shape (2, 4)
v = torch.randn(batch_size, N)

# x: (..., N) - shape (2, 4)
x = torch.randn(batch_size, N)

ARGS = {
    "v": v,
    "x": x,
    "L": L,
    "conj": True,
}
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 Tensor, ndim 2, dtype family float, shape (2, 3) — shape (2, 3) 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
log_vandermonde_transpose_naive Not yet run
unverified (harvested, no recorded run)
raunaqbhirangi/hiss/hiss/s4.py
code served (permissive licence) · get_code("7cfca855faa8e8dc")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 1 the same month, 3 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.

FunctionAlso present inEarliest-datedOthers named
cauchy_naive 6 other papers
3 dated earlier, 3 later · 1 only as an assembly brick
1612.00796 (2016-12)
Overcoming catastrophic forgetting in neural networks
2111.00396 (2021-11)
Efficiently Modeling Long Sequences with Structured State Spaces
2312.00752 (2023-12)
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
and 3 more not named here
log_vandermonde_naive 6 other papers
3 dated earlier, 3 later · 1 only as an assembly brick
1612.00796 (2016-12)
Overcoming catastrophic forgetting in neural networks
2111.00396 (2021-11)
Efficiently Modeling Long Sequences with Structured State Spaces
2312.00752 (2023-12)
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
and 3 more not named here
log_vandermonde_transpose_naive 4 other papers
3 dated earlier, 1 later · 2 only as an assembly brick
1612.00796 (2016-12)
Overcoming catastrophic forgetting in neural networks
2111.00396 (2021-11)
Efficiently Modeling Long Sequences with Structured State Spaces
2312.00752 (2023-12)
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
and 1 more not named here
get_num_params 2 other papers
1 dated earlier, 1 the same month
2306.05651 (2023-06)
Differentially Private Sharpness-Aware Training
2402.15978 (2024-02)
Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks using the Marginal Likelihood

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

Reasoning from sequences of raw sensory data is a ubiquitous problem across fields ranging from medical devices to robotics. These problems often involve using long sequences of raw sensor data (e.g. magnetometers, piezoresistors) to predict sequences of desirable physical quantities (e.g. force, inertial measurements). While classical approaches are powerful for locally-linear prediction problems, they often fall short when using real-world sensors. These sensors are typically non-linear, are affected by extraneous variables (e.g. vibration), and exhibit data-dependent drift. For many problems, the prediction task is exacerbated by small labeled datasets since obtaining ground-truth labels requires expensive equipment. In this work, we present Hierarchical State-Space Models (HiSS), a conceptually simple, new technique for continuous sequential prediction. HiSS stacks structured state-space models on top of each other to create a temporal hierarchy. Across six real-world sensor datasets, from tactile-based state prediction to accelerometer-based inertial measurement, HiSS outperforms state-of-the-art sequence models such as causal Transformers, LSTMs, S4, and Mamba by at least 23% on MSE. Our experiments further indicate that HiSS demonstrates efficient scaling to smaller datasets and is compatible with existing data-filtering techniques. Code, datasets and videos can be found on https://hiss-csp.github.io.

For agents

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

get_harvested_code_for_paper("2402.10211")
get_code_for_paper("2402.10211")
have("2402.10211")

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

curl https://syntology.ai/api/ran/2402.10211.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.10211.svg)](https://syntology.ai/paper/2402.10211)

Connect an agent — have() is free.