SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1810.03993 · 2018

Model Cards for Model Reporting

arXiv · PDF · Open in the Atlas

Code that ran

5 of 9 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 4 have no contract verdict; 1 failure of our instrument; 4 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/1810.03993.json · badge: /api/ran/1810.03993.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
tensorflow/model-card-toolkit community (classifier label)
classifier basis not recorded on the link
4 ran · 4 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
draw_histogram Ran
ran on a synthesized input
tensorflow/model-card-toolkit/model_card_toolkit/utils/graphics.py
code served (permissive licence) · get_code("6fd22617425986fe")
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 Graph. 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 matplotlib.pyplot as plt
import attr
from typing import Optional, Sequence, Union

_COLOR_PALETTE = {'material_cyan_700': '#129EAF', 'material_teal_700': '#00897B', 'material_indigo_400': '#5C6BC0', 'material_purple_500': '#A142F4'}

@attr.s(auto_attribs=True)
class Graph:
    """Model Card graph."""
    x: Optional[Sequence[Union[str, int, float]]] = None
    xerr: Optional[Sequence[Sequence[Union[int, float]]]] = None
    y: Optional[Sequence[Union[str, int, float]]] = None
    xlabel: Optional[str] = None
    ylabel: Optional[str] = None
    title: Optional[str] = None
    name: Optional[str] = None
    color: str = _COLOR_PALETTE['material_cyan_700']
    figure: Optional[plt.Figure] = None
    base64str: Optional[str] = None

# Create a valid Graph object with all required data for histogram plotting
graph = Graph(
    x=[0.5, 0.75, 0.95],
    y=['metric_a', 'metric_b', 'metric_c'],
    xlabel='Values',
    ylabel='Metrics',
    title='Performance Histogram',
    name='test_histogram',
    color=_COLOR_PALETTE['material_cyan_700']
)

ARGS = {
    'graph': graph
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
attr, matplotlib — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Graph — a Graph output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Graph 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
find_user_from_tags Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from jacopotagliabue/dag-card-is-the-new-model-card
pointer only · get_code("1de5cb6d09d27896")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

parse_proto_file Ran
ran on a synthesized input
tensorflow/model-card-toolkit/model_card_toolkit/utils/io_utils.py
code served (permissive licence) · get_code("7798a46fb3bac215")
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 FileDescriptorProto. 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
from pathlib import Path
import tempfile
from google.protobuf.message import Message
from google.protobuf import descriptor_pb2

# Create a temporary proto file with valid serialized proto content
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test.proto")

# Create a simple proto message and serialize it
proto_instance = descriptor_pb2.FileDescriptorProto()
proto_instance.name = "test.proto"
proto_instance.package = "test_package"

# Write the serialized proto to a file
with open(temp_file, 'wb') as f:
    f.write(proto_instance.SerializeToString())

# Create a new proto instance to parse into
proto_to_parse = descriptor_pb2.FileDescriptorProto()

ARGS = {
    'path': temp_file,
    'proto': proto_to_parse
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
google — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type FileDescriptorProto — a FileDescriptorProto output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a FileDescriptorProto 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
read_file Ran
ran on a synthesized input
tensorflow/model-card-toolkit/model_card_toolkit/utils/io_utils.py
code served (permissive licence) · get_code("71f79125049402a3")
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
from pathlib import Path
import tempfile

# Create a temporary file with test content
temp_dir = tempfile.mkdtemp()
test_file_path = os.path.join(temp_dir, "test.txt")
with open(test_file_path, 'w') as f:
    f.write("Hello, World!")

# Define arguments for read_file
ARGS = {
    'path': test_file_path,
    'mode': 'r'
}
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
suffix Ran
ran on a synthesized input
tensorflow/model-card-toolkit/model_card_toolkit/utils/io_utils.py
code served (permissive licence) · get_code("5f6caf0bd0169cd8")
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
from pathlib import Path

ARGS = {
    "path": "example_file.txt"
}
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
figure_to_base64str Not yet run
unverified (harvested, no recorded run)
tensorflow/model-card-toolkit/model_card_toolkit/utils/graphics.py
code served (permissive licence) · get_code("3ce49971c95d39c5")
How it ran

no invocation recorded.

stringify_slice_key Not yet run
unverified (harvested, no recorded run)
tensorflow/model-card-toolkit/model_card_toolkit/utils/graphics.py
code served (permissive licence) · get_code("ae38f009caac15cc")
How it ran

no invocation recorded.

update Not yet run
unverified (harvested, no recorded run)
tensorflow/model-card-toolkit/model_card_toolkit/utils/json_utils.py
code served (permissive licence) · get_code("201268fcbea40035")
How it ran

no invocation recorded.

validate_json_schema Not yet run
unverified (harvested, no recorded run)
tensorflow/model-card-toolkit/model_card_toolkit/utils/json_utils.py
code served (permissive licence) · get_code("df404bd1b3f804d3")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 8 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
find_user_from_tags 1 other paper
1 later
2110.13601 (2021-10)
DAG Card is the new Model Card

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

Trained machine learning models are increasingly used to perform high-impact tasks in areas such as law enforcement, medicine, education, and employment. In order to clarify the intended use cases of machine learning models and minimize their usage in contexts for which they are not well suited, we recommend that released models be accompanied by documentation detailing their performance characteristics. In this paper, we propose a framework that we call model cards, to encourage such transparent model reporting. Model cards are short documents accompanying trained machine learning models that provide benchmarked evaluation in a variety of conditions, such as across different cultural, demographic, or phenotypic groups (e.g., race, geographic location, sex, Fitzpatrick skin type) and intersectional groups (e.g., age and race, or sex and Fitzpatrick skin type) that are relevant to the intended application domains. Model cards also disclose the context in which models are intended to be used, details of the performance evaluation procedures, and other relevant information. While we focus primarily on human-centered machine learning models in the application fields of computer vision and natural language processing, this framework can be used to document any trained machine learning model. To solidify the concept, we provide cards for two supervised models: One trained to detect smiling faces in images, and one trained to detect toxic comments in text. We propose model cards as a step towards the responsible democratization of machine learning and related AI technology, increasing transparency into how well AI technology works. We hope this work encourages those releasing trained machine learning models to accompany model releases with similar detailed evaluation numbers and other relevant documentation.

For agents

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

get_harvested_code_for_paper("1810.03993")
get_code_for_paper("1810.03993")
have("1810.03993")

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

curl https://syntology.ai/api/ran/1810.03993.json

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

[![Syntology run record](https://syntology.ai/api/ran/1810.03993.svg)](https://syntology.ai/paper/1810.03993)

Connect an agent — have() is free.