SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2601.07576 · 2026

A Multimodal Dataset of Student Oral Presentations with Sensors and Evaluation Data

Roberto Daza, Alvaro Becerra, Ruth Cobos

arXiv · PDF · Open in the Atlas

Code that ran

14 of 21 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; 3 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 10 failures of our instrument; 7 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/2601.07576.json · badge: /api/ran/2601.07576.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
Ascend-Research/HeadPoseEstimation-WHENet canonical (classifier label)
classifier basis: census
7 ran · 1 no recorded run
deepinsight/insightface canonical (classifier label)
classifier basis: census
6 ran · 6 no recorded run
rafabs97/headpose_final community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
data_file Ran
ran; our contract draft was wrong, not the code
Ascend-Research/HeadPoseEstimation-WHENet/yolo_v3/yolo_postprocess.py
code served (permissive licence) · get_code("ff61dcb093415fdd")
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 str. 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 os

def data_file(filename):
    """Prepend the path to the data subdirectory to filename"""
    return os.path.join(os.path.dirname(__file__), 'data', filename)

ARGS = {
    'filename': 'test_data.csv'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
draw_axis Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Ascend-Research/HeadPoseEstimation-WHENet/utils.py
code served (permissive licence) · get_code("794df55d93a10c3b")
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 ndarray, ndim 3, dtype family int, shape (480, 640, 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 cv2

# Create a small test image (BGR format, typical for cv2)
img = np.zeros((480, 640, 3), dtype=np.uint8)

# Define arguments for draw_axis function
ARGS = {
    "img": img,
    "yaw": 15.0,
    "pitch": 10.0,
    "roll": 5.0,
    "tdx": 320.0,
    "tdy": 240.0,
    "size": 100
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (480, 640, 3) — shape (480, 640, 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
find_onnx_file Ran
ran; our contract draft was wrong, not the code
deepinsight/insightface/python-package/insightface/model_zoo/model_zoo.py
pointer only (licence: NONE) · get_code("8a967699bfeec4fc")
How it ran

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

find_params_file Ran
ran; our contract draft was wrong, not the code
deepinsight/insightface/python-package/insightface/model_zoo/model_store.py
pointer only (licence: NONE) · get_code("3dd6e87e7b70bf2b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, deepinsight/insightface 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_pose Ran
ran; our contract draft was wrong, not the code
rafabs97/headpose_final/pose_estimator_utils.py
pointer only (licence: GPL-3.0) · get_code("c8b27fc58789d71f")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, rafabs97/headpose_final, is not in the permissive set Syntology serves inline. 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_random_data Ran
ran; our contract draft was wrong, not the code
Ascend-Research/HeadPoseEstimation-WHENet/yolo_v3/utils.py
code served (permissive licence) · get_code("2d6f15893e2ed21a")
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 tuple. 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
from PIL import Image
import tempfile
import os

# Create a temporary directory for test images
temp_dir = tempfile.mkdtemp()

# Create a small test image and save it
test_image = Image.new('RGB', (100, 80), color=(73, 109, 137))
image_path = os.path.join(temp_dir, 'test_image.jpg')
test_image.save(image_path)

# Create annotation line with image path and bounding boxes
# Format: image_path box1 box2 ... where each box is x1,y1,x2,y2,class_id
annotation_line = f"{image_path} 10,20,50,60,0 55,25,80,70,1"

ARGS = {
    'annotation_line': annotation_line,
    'input_shape': (224, 224),
    'random': True,
    'max_boxes': 20,
    'jitter': 0.3,
    'hue': 0.1,
    'sat': 1.5,
    'val': 1.5,
    'proc_img': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, matplotlib, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
has_model_package_manifest Ran
ran, violated the contract we drafted
deepinsight/insightface/python-package/insightface/model_zoo/package_manifest.py
pointer only (licence: NONE) · get_code("578b5e6a424a1ab0")
How it ran

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

last_8chars Ran
ran; our contract draft was wrong, not the code
Ascend-Research/HeadPoseEstimation-WHENet/prepare_images.py
code served (permissive licence) · get_code("581670870bb3e20a")
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 str. 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

def last_8chars(x):
    x = x[-12:]
    x = x.split('.')[0]
    return x

# The function takes a string parameter 'x'
# It slices the last 12 characters, then splits by '.' and takes the first part
# We need to provide a string that will work with these operations

ARGS = {
    'x': 'some.string.example.txt'
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
letterbox_image Ran
ran; our contract draft was wrong, not the code
Ascend-Research/HeadPoseEstimation-WHENet/yolo_v3/utils.py
code served (permissive licence) · get_code("fe7e8a0ae28d05e2")
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 Image. 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.

from PIL import Image

# Create a small test image
image = Image.new('RGB', (100, 80), color=(200, 100, 50))

# Define target size for letterboxing
size = (128, 128)

ARGS = {
    'image': image,
    'size': size,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
model_package_manifest_version Ran
ran, honoured the contract we drafted
deepinsight/insightface/python-package/insightface/model_zoo/package_manifest.py
pointer only (licence: NONE) · get_code("d07f2a42c18c7056")
How it ran

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

normalize_preprocessing Ran
ran; our contract draft was wrong, not the code
deepinsight/insightface/python-package/insightface/model_zoo/package_manifest.py
pointer only (licence: NONE) · get_code("fc9f491186bd066b")
How it ran

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

rand Ran
ran, honoured the contract we drafted
Ascend-Research/HeadPoseEstimation-WHENet/yolo_v3/utils.py
code served (permissive licence) · get_code("cdf3547dcf481932")
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 float, 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 numpy as np

ARGS = {
    "a": 0,
    "b": 1
}
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 float, 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
short_hash Ran
ran; our contract draft was wrong, not the code
deepinsight/insightface/python-package/insightface/model_zoo/model_store.py
pointer only (licence: NONE) · get_code("48aa1fdc7e6172f9")
How it ran

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

softmax Ran
ran, honoured the contract we drafted
Ascend-Research/HeadPoseEstimation-WHENet/utils.py
code served (permissive licence) · get_code("1f4ad91cbcf8ec36")
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 ndarray, ndim 2, dtype family float, shape (2, 4) 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

# Create a small 2D numpy array (batch_size=2, features=4)
x = np.array([
    [1.0, 2.0, 3.0, 4.0],
    [5.0, 6.0, 7.0, 8.0]
], dtype=np.float32)

ARGS = {
    "x": x
}
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 ndarray, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
canonical_license_bytes Not yet run
unverified (harvested, no recorded run)
deepinsight/insightface/python-package/insightface/model_zoo/model_license.py
pointer only (licence: NONE) · get_code("ff65d95fb7b65509")
How it ran

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

copy_session_options Not yet run
unverified (harvested, no recorded run)
deepinsight/insightface/python-package/insightface/model_zoo/coreml_cache.py
pointer only (licence: NONE) · get_code("3cae2e779ae6b6ec")
How it ran

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

create_coreml_session Not yet run
unverified (harvested, no recorded run)
deepinsight/insightface/python-package/insightface/model_zoo/coreml_cache.py
pointer only (licence: NONE) · get_code("2549cd9faaa454ed")
How it ran

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

get_model_file Not yet run
unverified (harvested, no recorded run)
deepinsight/insightface/python-package/insightface/model_zoo/model_store.py
pointer only (licence: NONE) · get_code("b0a56313fb31fb43")
How it ran

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

inspect_model_package_license Not yet run
unverified (harvested, no recorded run)
deepinsight/insightface/python-package/insightface/model_zoo/model_license.py
pointer only (licence: NONE) · get_code("732a29683cd293c3")
How it ran

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

projectPoints Not yet run
unverified (harvested, no recorded run)
Ascend-Research/HeadPoseEstimation-WHENet/utils.py
code served (permissive licence) · get_code("11090652d9163fa8")
How it ran

no invocation recorded.

verify_model_license Not yet run
unverified (harvested, no recorded run)
deepinsight/insightface/python-package/insightface/model_zoo/model_license.py
pointer only (licence: NONE) · get_code("44abd83066eaf457")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, deepinsight/insightface 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 21 samples lifted from this paper's linked repositories, 21 carry a function identity and 0 do not. Of the 21 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 0 later) and 16 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
short_hash 11 other papers
11 dated earlier
1803.08904 (2018-03)
Context Encoding for Semantic Segmentation
1809.02983 (2018-09)
Dual Attention Network for Scene Segmentation
1905.00641 (2019-05)
RetinaFace: Single-stage Dense Face Localisation in the Wild
and 8 more not named here
letterbox_image 3 other papers
3 dated earlier
1804.02767 (2018-04)
YOLOv3: An Incremental Improvement
1905.05055 (2019-05)
Object Detection in 20 Years: A Survey
2003.08813 (2020-03)
Multi-task Collaborative Network for Joint Referring Expression Comprehension and Segmentation
rand 3 other papers
3 dated earlier
1804.02767 (2018-04)
YOLOv3: An Incremental Improvement
1905.05055 (2019-05)
Object Detection in 20 Years: A Survey
2003.08813 (2020-03)
Multi-task Collaborative Network for Joint Referring Expression Comprehension and Segmentation
get_model_file 2 other papers
2 dated earlier
1905.00641 (2019-05)
RetinaFace: Single-stage Dense Face Localisation in the Wild
2203.15565 (2022-03)
Killing Two Birds with One Stone: Efficient and Robust Training of Face Recognition CNNs by Partial FC
get_random_data 2 other papers
2 dated earlier
1804.02767 (2018-04)
YOLOv3: An Incremental Improvement
1905.05055 (2019-05)
Object Detection in 20 Years: A Survey

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

Oral presentation skills are a critical component of higher education, yet comprehensive datasets capturing real-world student performance across multiple modalities remain scarce. To address this gap, we present SOPHIAS (Student Oral Presentation monitoring for Holistic Insights & Analytics using Sensors), a 12-hour multimodal dataset containing recordings of 50 oral presentations (10-15-minute presentation followed by 5-15-minute Q&A) delivered by 65 undergraduate and master's students at the Universidad Autónoma de Madrid. SOPHIAS integrates eight synchronized sensor streams from high-definition webcams, ambient and webcam audio, eye-tracking glasses, smartwatch physiological sensors, and clicker, keyboard and mouse interactions. In addition, the dataset includes slides and rubric-based evaluations from teachers, peers, and self-assessments, along with timestamped contextual annotations. The dataset captures presentations conducted in real classroom settings, preserving authentic student behaviors, interactions, and physiological responses. SOPHIAS enables the exploration of relationships between multimodal behavioral and physiological signals and presentation performance, supports the study of peer-assessment and provides a benchmark for developing automated feedback and Multimodal Learning Analytics tools. The dataset is publicly available for research through GitHub and Science Data Bank.

For agents

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

get_harvested_code_for_paper("2601.07576")
get_code_for_paper("2601.07576")
have("2601.07576")

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

curl https://syntology.ai/api/ran/2601.07576.json

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

[![Syntology run record](https://syntology.ai/api/ran/2601.07576.svg)](https://syntology.ai/paper/2601.07576)

Connect an agent — have() is free.