SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.14169 · ACL · 2023

TABGENIE: A Toolkit for Table-to-Text Generation

Ondřej Dušek, Zdeněk Kasner, Ekaterina Garanina, Ondřej Plátek

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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 3 have no contract verdict; 0 failures of our instrument; 0 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/2302.14169.json · badge: /api/ran/2302.14169.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
kasnerz/tabgenie canonical (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
FunctionStatusWhere it lives
filter_empty_recursive Ran
ran on a synthesized input
kasnerz/tabgenie/tabgenie/loaders/multiwoz22.py
code served (permissive licence) · get_code("75ceac77d0101f5d")
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 torch
import numpy as np

torch.manual_seed(0)

# Analyze the function: filter_empty_recursive processes nested structures
# (lists, dicts, strings, and other types) recursively, filtering out empty values.
# The function takes a single parameter 'c' which can be:
# - a list (recursively processed)
# - a dict (recursively processed)
# - a string (filtered if empty)
# - any other type (returned as-is)

# Create a complex nested structure with various types including:
# empty strings, None values, empty lists, empty dicts, and valid data
test_data = {
    "valid_string": "hello",
    "empty_string": "",
    "nested_list": [
        "item1",
        "",
        None,
        ["nested", "", "data"],
        [],
    ],
    "nested_dict": {
        "key1": "value1",
        "key2": "",
        "key3": None,
        "key4": {
            "deep_key": "deep_value",
            "empty_key": "",
        },
    },
    "empty_dict": {},
    "number": 42,
    "tensor": torch.tensor([1.0, 2.0, 3.0]),
    "list_with_none": [None, None],
    "mixed_list": [
        {"a": "b"},
        "",
        None,
        [1, 2, 3],
    ],
}

ARGS = {
    "c": test_data,
}
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 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
generate_natural_user_prompt Ran
ran on a synthesized input
kasnerz/tabgenie/tabgenie/loaders/multiwoz22.py
code served (permissive licence) · get_code("f13ab779f871fd47")
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 generator. 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
import numpy as np

# Analyze the function signature and body
# The function takes user_actions which is iterable of tuples: (domain, act, slot, value)
# It iterates through them, sorts them, and yields strings based on the content
# The function uses: .sort() on user_actions, iterates through tuples unpacking 4 elements

# Create valid user_actions - a list of tuples with (domain, act, slot, value)
user_actions = [
    ('Hotel', 'Inform', 'area', 'north'),
    ('Hotel', 'Inform', 'pricerange', 'expensive'),
    ('Attraction', 'Inform', 'type', 'museum'),
    ('Attraction', 'Request', 'parking', None),
    ('Restaurant', 'Inform', 'area', 'south'),
    ('Train', 'Request', 'duration', None),
    ('Taxi', 'Inform', 'departure', 'station'),
]

ARGS = {
    'user_actions': user_actions,
}
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 generator — a generator output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a generator 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
just_user_acts Ran
ran on a synthesized input
kasnerz/tabgenie/tabgenie/loaders/multiwoz22.py
code served (permissive licence) · get_code("39d31de10a3a5bb8")
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 list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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
import numpy as np

# Create a mock turns object that the function expects
# The function accesses turns['speaker'] and turns['dialogue_acts']
# and checks they have the same length

turns = {
    'speaker': [0, 1, 0, 1, 0],  # USER=0, SYSTEM=1
    'dialogue_acts': [
        'inform',
        'request',
        'confirm',
        'offer',
        'goodbye'
    ]
}

ARGS = {
    'turns': turns
}
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 list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 3 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

Heterogenity of data-to-text generation datasets limits the research on data-to-text generation systems. We present TABGENIE -a toolkit which enables researchers to explore, preprocess, and analyze a variety of data-to-text generation datasets through the unified framework of table-to-text generation. In TABGENIE, all inputs are represented as tables with associated metadata. The tables can be explored through a web interface, which also provides an interactive mode for debugging table-to-text generation, facilitates side-by-side comparison of generated system outputs, and allows easy exports for manual analysis. Furthermore, TAB-GENIE is equipped with command line processing tools and Python bindings for unified dataset loading and processing. We release TABGENIE as a PyPI package 1 and provide its open-source code and a live demo at https: //github.com/kasnerz/tabgenie.

For agents

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

get_harvested_code_for_paper("2302.14169")
get_code_for_paper("2302.14169")
have("2302.14169")

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

curl https://syntology.ai/api/ran/2302.14169.json

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

[![Syntology run record](https://syntology.ai/api/ran/2302.14169.svg)](https://syntology.ai/paper/2302.14169)

Connect an agent — have() is free.