SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2202.00443 · 2022

The Text Anonymization Benchmark (TAB): A Dedicated Corpus and Evaluation Framework for Text Anonymization

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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 1 has no contract verdict; 1 failure of our instrument; 0 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/2202.00443.json · badge: /api/ran/2202.00443.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
norskregnesentral/text-anonymisation-benchmark canonical (classifier label)
classifier basis not recorded on the link
1 ran · 0 no recorded run
norskregnesentral/text-anonymization-benchmark canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
align_tokens_and_annotations_bilou Ran
ran on a synthesized input
norskregnesentral/text-anonymisation-benchmark/longformer_experiments/data_handling.py
code served (permissive licence) · get_code("280bb9ef41c94bfe")
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.

from tokenizers import Encoding

# Create a mock Encoding object with the necessary methods
class MockEncoding:
    def __init__(self):
        self.tokens = ["Hello", "world", "test"]
        # Mapping of character indices to token indices
        self._char_to_token_map = {
            0: 0, 1: 0, 2: 0, 3: 0, 4: 0,  # "Hello"
            5: 1, 6: 1, 7: 1, 8: 1, 9: 1,  # "world"
            10: 2, 11: 2, 12: 2, 13: 2     # "test"
        }
    
    def char_to_token(self, char_ix):
        return self._char_to_token_map.get(char_ix)

# Create sample annotations
annotations = [
    {
        'id': 'anno_1',
        'label': 'MASK',
        'identifier_type': 'TYPE_A',
        'start_offset': 0,
        'end_offset': 5
    },
    {
        'id': 'anno_2',
        'label': 'MASK',
        'identifier_type': 'TYPE_B',
        'start_offset': 6,
        'end_offset': 11
    }
]

# Create sample ids list
ids = []

# Create the tokenized encoding
tokenized = MockEncoding()

ARGS = {
    'tokenized': tokenized,
    'annotations': annotations,
    'ids': ids
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tokenizers — 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
get_masked_docs_from_file Ran
ran; our contract draft was wrong, not the code
norskregnesentral/text-anonymization-benchmark/evaluation.py
code served (permissive licence) · get_code("d73fefbe0c6fca76")
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 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 json
import tempfile
import os

# Create a temporary JSON file with masked spans data
temp_dir = tempfile.mkdtemp()
masked_output_file = os.path.join(temp_dir, "masked_spans.json")

# Create sample masked spans data
masked_data = {
    "doc_1": [[0, 5], [10, 15], [20, 25]],
    "doc_2": [[5, 10], [15, 20]],
    "doc_3": [[0, 3], [7, 12], [18, 22]]
}

# Write to temporary file
with open(masked_output_file, 'w') as f:
    json.dump(masked_data, f)

ARGS = {
    "masked_output_file": masked_output_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 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 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, 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 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.

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

We present a novel benchmark and associated evaluation metrics for assessing the performance of text anonymization methods. Text anonymization, defined as the task of editing a text document to prevent the disclosure of personal information, currently suffers from a shortage of privacy-oriented annotated text resources, making it difficult to properly evaluate the level of privacy protection offered by various anonymization methods. This paper presents TAB (Text Anonymization Benchmark), a new, open-source annotated corpus developed to address this shortage. The corpus comprises 1,268 English-language court cases from the European Court of Human Rights (ECHR) enriched with comprehensive annotations about the personal information appearing in each document, including their semantic category, identifier type, confidential attributes, and co-reference relations. Compared to previous work, the TAB corpus is designed to go beyond traditional de-identification (which is limited to the detection of predefined semantic categories), and explicitly marks which text spans ought to be masked in order to conceal the identity of the person to be protected. Along with presenting the corpus and its annotation layers, we also propose a set of evaluation metrics that are specifically tailored towards measuring the performance of text anonymization, both in terms of privacy protection and utility preservation. We illustrate the use of the benchmark and the proposed metrics by assessing the empirical performance of several baseline text anonymization models. The full corpus along with its privacy-oriented annotation guidelines, evaluation scripts and baseline models are available on: https://github.com/NorskRegnesentral/text-anonymisation-benchmark

For agents

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

get_harvested_code_for_paper("2202.00443")
get_code_for_paper("2202.00443")
have("2202.00443")

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

curl https://syntology.ai/api/ran/2202.00443.json

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

[![Syntology run record](https://syntology.ai/api/ran/2202.00443.svg)](https://syntology.ai/paper/2202.00443)

Connect an agent — have() is free.