🕵️ Rewriting Biographies¶

Instead of replacing entities with tokens, rewrite mode generates a privacy-safe transformation of the entire text. The run() / preview() pipeline:

1. Detects entities (same as replace mode, plus latent entity detection)
2. Classifies the domain and assigns sensitivity dispositions
3. Generates a rewritten version that obscures sensitive entities
4. Evaluates quality (utility) and privacy (leakage) with an automated repair loop

Afterward, a separate optional evaluate() call runs LLM judges for detection validity and holistic privacy, quality, and style scores.

📚 What you'll learn¶

• Configure rewrite mode with PrivacyGoal to specify what to protect and what to preserve
• Set evaluation criteria and risk tolerance for automated quality checks
• Preview rewritten text and inspect utility / leakage scores
• Triage flagged records with needs_human_review
• Run evaluate() for detection validity and holistic judge scores (privacy, quality, style)

Tip: First time running notebooks? Start with setup instructions.

⚙️ Setup¶

• Install the notebook extra, then provide credentials for the configured external LLM providers.
• create_anonymizer() starts pinned GLiNER2 locally and selects CUDA, MPS, or CPU automatically.
• The default external LLM models currently use OpenRouter; its terms and privacy practices apply.

Data boundary: GLiNER2 detection runs locally in this notebook environment. LLM-assisted validation, augmentation, replacement, rewriting, repair, and evaluation use configured external hosts and may send them original or tagged input text. Do not treat this configuration as an all-local privacy boundary.

• configure_logging(LoggingConfig.default()) keeps logs at INFO. Switch to LoggingConfig.debug() when troubleshooting.

In [1]:

import getpass
import os
import subprocess
import sys

package_spec = os.getenv("ANONYMIZER_NOTEBOOK_PACKAGE", "nemo-anonymizer[notebooks]")
subprocess.check_call([sys.executable, "-m", "pip", "install", "--quiet", package_spec])

import getpass import os import subprocess import sys package_spec = os.getenv("ANONYMIZER_NOTEBOOK_PACKAGE", "nemo-anonymizer[notebooks]") subprocess.check_call([sys.executable, "-m", "pip", "install", "--quiet", package_spec])

Out[1]:

0

In [2]:

from anonymizer.notebooks import required_api_key_environment_variables

for variable in required_api_key_environment_variables():
    key = getpass.getpass(f"Enter {variable}: ").strip()
    if not key:
        raise RuntimeError(f"{variable} is required by the configured external model providers.")
    os.environ[variable] = key

from anonymizer.notebooks import required_api_key_environment_variables for variable in required_api_key_environment_variables(): key = getpass.getpass(f"Enter {variable}: ").strip() if not key: raise RuntimeError(f"{variable} is required by the configured external model providers.") os.environ[variable] = key

In [3]:

from anonymizer import (
    AnonymizerConfig,
    AnonymizerInput,
    LoggingConfig,
    PrivacyGoal,
    Rewrite,
    configure_logging,
)
from anonymizer.notebooks import create_anonymizer, stop_local_runtime

configure_logging(LoggingConfig.default())

from anonymizer import ( AnonymizerConfig, AnonymizerInput, LoggingConfig, PrivacyGoal, Rewrite, configure_logging, ) from anonymizer.notebooks import create_anonymizer, stop_local_runtime configure_logging(LoggingConfig.default())

In [4]:

anonymizer = create_anonymizer()

anonymizer = create_anonymizer()

[00:33:02] [INFO] 🔧 Anonymizer initialized with 5 model configs

[00:33:02] [INFO]   |-- 🔎 detector:  local-gliner2-pii

[00:33:02] [INFO]   |-- ✅ validator: gpt-oss-120b

[00:33:02] [INFO]   |-- 🧩 augmenter: gpt-oss-120b

GLiNER2 ready: model=fastino/gliner2-privacy-filter-PII-multi revision=59894c087cb2923b01f337d4ee72f6ff84d5bdd6 device=mps endpoint=http://127.0.0.1:55416/v1

📦 Input data¶

• Same biographies dataset used in earlier notebooks -- familiar data makes it easy to compare rewrite output against replace output.

In [5]:

input_data = AnonymizerInput(
    source="https://raw.githubusercontent.com/NVIDIA-NeMo/Anonymizer/refs/heads/main/docs/data/NVIDIA_synthetic_biographies.csv",
    text_column="biography",
    data_summary="Biographical profiles",
)

input_data = AnonymizerInput( source="https://raw.githubusercontent.com/NVIDIA-NeMo/Anonymizer/refs/heads/main/docs/data/NVIDIA_synthetic_biographies.csv", text_column="biography", data_summary="Biographical profiles", )

🎛️ Configure¶

• PrivacyGoal spells out what to protect and what to preserve -- this gives the rewriter clear, domain-specific guidance.
• risk_tolerance (default "low") and max_repair_iterations (default 3) control the automated quality gate -- see Risk tolerance for presets.

In [6]:

config = AnonymizerConfig(
    rewrite=Rewrite(
        privacy_goal=PrivacyGoal(
            protect="All direct identifiers and quasi-identifier combinations (names, locations, employers, dates)",
            preserve="Career trajectory, educational background, and professional accomplishments",
        ),
        risk_tolerance="low",
        max_repair_iterations=3,
    ),
)

config = AnonymizerConfig( rewrite=Rewrite( privacy_goal=PrivacyGoal( protect="All direct identifiers and quasi-identifier combinations (names, locations, employers, dates)", preserve="Career trajectory, educational background, and professional accomplishments", ), risk_tolerance="low", max_repair_iterations=3, ), )

👁️ Preview¶

• preview() runs on a small sample so you can iterate on privacy goals and evaluation criteria before committing to a full run.

In [7]:

preview = anonymizer.preview(
    config=config,
    data=input_data,
    num_records=3,
)

preview.display_record(0)

preview = anonymizer.preview( config=config, data=input_data, num_records=3, ) preview.display_record(0)

[00:33:02] [INFO] 👀 Preview mode: 📂 Loaded 3 records from https://raw.githubusercontent.com/NVIDIA-NeMo/Anonymizer/refs/heads/main/docs/data/NVIDIA_synthetic_biographies.csv (column: 'biography')

[00:33:02] [INFO] 🔍 Running entity detection on 3 records

[00:33:02] [INFO] detection labels in scope: (default: 65 labels; see anonymizer.DEFAULT_ENTITY_LABELS for list)

[00:35:00] [INFO]   |-- 📋 Detection complete — 86 entities found across 3 records (0 failed) [117.8s]

[00:35:00] [INFO]   |-- labels: first_name=23, organization_name=7, occupation=6, age=5, field_of_study=5, company_name=5, city=4, degree=4, university=4, last_name=3, state=3, language=3, political_view=3, place_name=2, race_ethnicity=2, street_address=2, religious_belief=2, nationality=1, date_of_birth=1, landmark=1

[00:35:00] [INFO] ✏️ Running rewrite pipeline

[00:39:23] [INFO] Evaluate-repair loop: all rows pass at iteration 0

[00:39:23] [INFO]   |-- 📋 Rewrite complete (0 failed) [262.9s]

[00:39:23] [INFO] 🎉 Pipeline complete — 3 records processed, 0 total failures

Anonymizer Rewrite Preview (record 0)

Original

Bobby| first_name Watford| last_name, a 40‑year‑old| age Mexican| nationality veterinarian| occupation living in Denver| city, Colorado| state, grew up on the outskirts of the city and developed a love for animals early on. After graduating from Jefferson High| organization_name, he earned his DVM| degree at the University of Colorado Boulder| university, where he also completed a research stint in wildlife health| field_of_study. Fluent in English| language, Bobby| first_name has always described his upbringing as a blend of small‑town curiosity and the vibrant culture of his community, values that continue to shape his compassionate approach to animal care| field_of_study. Since finishing his training, Bobby| first_name has worked at VCA Animal Hospital| organization_name and later at the Colorado Veterinary Clinic| organization_name, where he now leads a busy mixed‑practice team. He identifies as a Christian Democrat| political_view and often volunteers at local shelters, a habit encouraged by his wife, Maya| first_name, and their two teenage children, Aria| first_name and Leo| first_name. Outside the clinic, Bobby| first_name enjoys hiking the Rockies| place_name with his family and mentoring veterinary students from his alma mater.

Rewritten

Ethan Henderson, in his early 40s, is a Mexican veterinarian living in a city in Colorado. He grew up on the outskirts of the city and developed a love for animals early on. After graduating from his high school, he earned his DVM at a state university, where he also completed a research stint in wildlife health. Fluent in English, Ethan has always described his upbringing as a blend of small‑town curiosity and the vibrant culture of his community, values that continue to shape his compassionate approach to animal care. Since finishing his training, Ethan has worked at a veterinary clinic and later at another veterinary clinic, where he now leads a busy mixed‑practice team. He identifies with a centrist political view and often volunteers at local shelters. Outside the clinic, Ethan enjoys hiking the Rockies and mentoring veterinary students from his alma mater.

Scores

Utility: 0.70Leakage: 0.00Weighted Leakage Rate: 0.00Rewrite Needs Review: No

Entity Disposition

Entity	Label	Sensitivity	Protection
Bobby	first_name	high	replace
Watford	last_name	high	replace
Maya	first_name	high	replace
Aria	first_name	high	replace
Leo	first_name	high	replace
40‑year‑old	age	high	generalize
Denver	city	high	generalize
Colorado	state	low	leave_as_is
Mexican	nationality	low	leave_as_is
veterinarian	occupation	low	leave_as_is
VCA Animal Hospital	organization_name	high	generalize
Colorado Veterinary Clinic	organization_name	high	generalize
Jefferson High	organization_name	medium	generalize
DVM	degree	low	leave_as_is
University of Colorado Boulder	university	medium	generalize
Christian Democrat	political_view	medium	generalize
English	language	low	leave_as_is
Rockies	place_name	low	leave_as_is
wildlife health	field_of_study	low	leave_as_is
animal care	field_of_study	low	leave_as_is
married	marital_status	medium	suppress_inference
two	number_of_children	low	leave_as_is
bachelor's degree	education_level	low	leave_as_is
team lead	current_position	low	leave_as_is
mixed practice	practice_setting	low	leave_as_is
Christian	religious_affiliation	low	leave_as_is

In [8]:

preview.display_record(1)

preview.display_record(1)

Anonymizer Rewrite Preview (record 1)

Original

Idilio| first_name Bell| last_name is a 37‑year‑old| age astronomer| occupation living in Edison| city, New Jersey| state. Born on November 21, 1988| date_of_birth, he grew up in a bilingual Italian| race_ethnicity household and speaks English| language at home and work. He earned his bachelor’s degree| degree in physics| field_of_study from the University of New Jersey| university and later completed a PhD| degree in astrophysics| field_of_study at Princeton| university, where his dissertation focused on exoplanet atmospheres| field_of_study. After graduation he spent three years at NASA| company_name’s Goddard Space Flight Center| landmark before joining SpaceX| company_name’s research division| organization_name, where he now leads a team analyzing data from the Starlink| organization_name telescope array. Idilio| first_name describes himself as secular and leans progressive| political_view on most political issues, often volunteering for science outreach programs in his community. Outside the lab, Idilio| first_name shares a modest house on West Roberts Drive| street_address with his wife, Maya| first_name, and their two young daughters, Lina| first_name and Zara| first_name. His mother, Elena| first_name, lives nearby and still cook| occupations the family’s favorite pasta on Sundays, while his father, Marco| first_name, retired from an engineering firm| organization_name in New York| city. Family gatherings are a mix of lively conversation and stargazing sessions on the backyard deck| place_name, where Idilio| first_name points out constellations and tells stories of the cosmos that inspire his children’s curiosity.

Rewritten

Darius Hawke is an astronomer in his late 30s living in Edison, New Jersey. Born on April 12, 1984, he grew up in a bilingual Italian household and speaks English at home and work. He earned his bachelor’s degree in physics from a state university and later completed a PhD in astrophysics at an Ivy League university, where his dissertation focused on exoplanet atmospheres. After graduation he spent three years at a national space agency’s research center before joining a private aerospace company's research division, where he now leads a team analyzing data from the Starlink telescope array. Darius describes himself as secular and leans progressive on most political issues, often volunteering for science outreach programs in his community. Outside the lab, Darius shares a modest house on North Maple Avenue with his wife, Sofia, and their two young daughters, Nina and Leah. His mother, Clara, lives nearby and still cooks the family’s favorite pasta on Sundays, while his father, Victor, retired from an engineering firm in New York. Family gatherings are a mix of lively conversation and stargazing sessions on the backyard deck, where Darius points out constellations and tells stories of the cosmos that inspire his children’s curiosity.

Scores

Utility: 0.98Leakage: 0.00Weighted Leakage Rate: 0.00Rewrite Needs Review: No

Entity Disposition

Entity	Label	Sensitivity	Protection
Idilio	first_name	high	replace
Bell	last_name	high	replace
Maya	first_name	high	replace
Lina	first_name	high	replace
Zara	first_name	high	replace
Elena	first_name	high	replace
Marco	first_name	high	replace
37‑year‑old	age	medium	generalize
November 21, 1988	date_of_birth	high	replace
West Roberts Drive	street_address	high	replace
Edison	city	low	leave_as_is
New Jersey	state	low	leave_as_is
New York	city	low	leave_as_is
NASA	company_name	medium	generalize
Goddard Space Flight Center	landmark	medium	generalize
SpaceX	company_name	medium	generalize
research division	organization_name	low	leave_as_is
Starlink	organization_name	low	leave_as_is
University of New Jersey	university	medium	generalize
Princeton	university	medium	generalize
bachelor’s degree	degree	low	leave_as_is
PhD	degree	low	leave_as_is
physics	field_of_study	low	leave_as_is
astrophysics	field_of_study	low	leave_as_is
exoplanet atmospheres	field_of_study	low	leave_as_is
astronomer	occupation	low	leave_as_is
cook	occupation	low	leave_as_is
engineering firm	organization_name	low	leave_as_is
progressive	political_view	low	leave_as_is
English	language	low	leave_as_is
Italian	race_ethnicity	low	leave_as_is
backyard deck	place_name	low	leave_as_is
married	marital_status	medium	leave_as_is
2	num_children	medium	leave_as_is
retired engineer	father_occupation	medium	leave_as_is

How to interpret leakage: Leakage is measured against the sensitivity disposition. Details marked leave_as_is may remain without increasing leakage_mass. If an output retains something you expected the privacy goal to protect, inspect the Entity Disposition table.

🚀 Full run¶

• result.dataframe has user-facing columns: rewritten text, scores, and the review flag.
• result.trace_dataframe has every intermediate column for debugging.

In [9]:

result = anonymizer.run(config=config, data=input_data)

result.dataframe.head()

result = anonymizer.run(config=config, data=input_data) result.dataframe.head()

[00:39:24] [INFO] 📂 Loaded 25 records from https://raw.githubusercontent.com/NVIDIA-NeMo/Anonymizer/refs/heads/main/docs/data/NVIDIA_synthetic_biographies.csv (column: 'biography')

[00:39:24] [INFO] 🔍 Running entity detection on 25 records

[00:39:24] [INFO] detection labels in scope: (default: 65 labels; see anonymizer.DEFAULT_ENTITY_LABELS for list)

[00:45:34] [INFO]   |-- 📋 Detection complete — 697 entities found across 25 records (0 failed) [370.3s]

[00:45:34] [INFO]   |-- labels: first_name=153, field_of_study=50, occupation=47, organization_name=46, company_name=44, city=40, university=35, degree=27, last_name=26, age=26, state=25, political_view=25, religious_belief=24, street_address=23, language=19, race_ethnicity=18, place_name=17, nationality=10, county=10, date_of_birth=9, employment_status=7, education_level=6, date=5, landmark=1, event_name=1, country=1, sexuality=1, postcode=1

[00:45:34] [INFO] ✏️ Running rewrite pipeline

[00:46:43] [WARNING] Replacement map repaired synthetic-original collision entries for record e5b7b47e3bf55ba0af4d43c7fd6ad509; repaired=1 (repaired_by_label={'state': 1})

[00:48:55] [WARNING] Required rewrite replacement was unavailable; marking rewritten text unavailable.

[00:49:21] [WARNING] Entity 23 (label='first_name'): combined_risk_level='low' conflicts with protection_method_suggestion='remove'; promoting risk to 'medium'.

[00:49:21] [WARNING] Entity 23 (label='first_name'): combined_risk_level='low' conflicts with protection_method_suggestion='remove'; promoting risk to 'medium'.

[00:49:21] [WARNING] Entity 23 (label='first_name'): combined_risk_level='low' conflicts with protection_method_suggestion='remove'; promoting risk to 'medium'.

[00:49:21] [WARNING] Entity 24 (label='first_name'): combined_risk_level='low' conflicts with protection_method_suggestion='remove'; promoting risk to 'medium'.

[00:49:21] [WARNING] Entity 24 (label='first_name'): combined_risk_level='low' conflicts with protection_method_suggestion='remove'; promoting risk to 'medium'.

[00:49:21] [WARNING] Entity 24 (label='first_name'): combined_risk_level='low' conflicts with protection_method_suggestion='remove'; promoting risk to 'medium'.

[00:58:08] [INFO] Evaluate-repair loop iteration 0: 5/25 rows need repair

[00:59:05] [INFO] Evaluate-repair loop iteration 1: 2/25 rows need repair

[00:59:45] [INFO] Evaluate-repair loop iteration 2: 2/25 rows need repair

[01:00:17] [INFO]   |-- 📋 Rewrite complete (0 failed) [883.0s]

[01:00:17] [INFO] 🎉 Pipeline complete — 25 records processed, 0 total failures

Out[9]:

	biography	biography_rewritten	utility_score	leakage_mass	weighted_leakage_rate	any_high_leaked	needs_human_review
0	Bobby Watford, a 40‑year‑old Mexican veterinar...	Ethan Hawthorne, an early‑40s Mexican veterina...	0.98	0.0	0.0	False	False
1	Idilio Bell is a 37‑year‑old astronomer living...	Luca Hawthorne is an astronomer in his late 30s...	0.908333	0.0	0.0	False	False
2	Jodi Allison, 36, lives at 204 Bluegrass in Cl...	Leah Harper, 36, lives at 312 Maple Lane in Cl...	0.945455	0.0	0.0	False	False
3	James Mills is a 69‑year‑old paramedic who liv...	Robert Harper is a paramedic in his late 60s w...	0.87	0.0	0.0	False	False
4	Nancy Burton is a 21‑year‑old cashier who live...	Aisha Khan is a 21‑year‑old cashier who lives ...	0.975	0.0	0.0	False	False

In [10]:

result.dataframe[["biography_rewritten", "utility_score", "leakage_mass", "needs_human_review"]].head()

result.dataframe[["biography_rewritten", "utility_score", "leakage_mass", "needs_human_review"]].head()

Out[10]:

	biography_rewritten	utility_score	leakage_mass	needs_human_review
0	Ethan Hawthorne, an early‑40s Mexican veterina...	0.98	0.0	False
1	Luca Hawthorne is an astronomer in his late 30s...	0.908333	0.0	False
2	Leah Harper, 36, lives at 312 Maple Lane in Cl...	0.945455	0.0	False
3	Robert Harper is a paramedic in his late 60s w...	0.87	0.0	False
4	Aisha Khan is a 21‑year‑old cashier who lives ...	0.975	0.0	False

In [11]:

result.trace_dataframe.columns.tolist()

result.trace_dataframe.columns.tolist()

Out[11]:

['biography',
 '_anonymizer_record_id',
 '_raw_detected_entities',
 '_seed_entities',
 '_tag_notation',
 '_seed_validation_candidates',
 '_seed_tagged_text',
 '_validated_entities',
 '_seed_entities_json',
 '_initial_tagged_text',
 '_validated_seed_entities',
 '_augmented_entities',
 '_merged_entities',
 '_merged_tagged_text',
 '_validation_candidates',
 '_detected_entities',
 'biography_with_spans',
 '_latent_entities',
 'final_entities',
 '_entities_by_value',
 '_replacement_map',
 '_replacement_map_source',
 '_domain',
 '_domain_supplement',
 '_domain_supplement_privacy',
 '_sensitivity_disposition',
 '_privacy_qa',
 '_rewrite_disposition_block',
 '_sensitivity_disposition_block',
 '_replacement_map_for_prompt',
 '_rewrite_tagged_text',
 '_replacement_application',
 '_rewrite_replacement_ready',
 '_rewrite_baseline_text',
 '_meaning_units',
 '_meaning_units_serialized',
 '_full_rewrite',
 'biography_rewritten',
 '_quality_qa',
 '_repair_iterations',
 '_quality_qa_reanswer',
 '_privacy_qa_reanswer',
 '_quality_qa_compare',
 'utility_score',
 'leakage_mass',
 'weighted_leakage_rate',
 'any_high_leaked',
 '_needs_repair',
 '_leaked_privacy_items',
 '_rewritten_text__next',
 'needs_human_review']

🚩 Filter by review flag¶

• Records where automated metrics exceed thresholds are flagged for manual review.
• needs_human_review is threshold-based, so a record can have small nonzero leakage without being flagged.
• Use this to prioritize human attention on the records that need it most.
• See Working with flagged records for guidance on diagnosing and resolving flagged records.

In [12]:

df = result.dataframe
flagged = df[df["needs_human_review"] == True]  # noqa: E712
print(f"{len(flagged)} of {len(df)} records flagged for human review")
flagged.head()

df = result.dataframe flagged = df[df["needs_human_review"] == True] # noqa: E712 print(f"{len(flagged)} of {len(df)} records flagged for human review") flagged.head()

1 of 25 records flagged for human review

Out[12]:

	biography	biography_rewritten	utility_score	leakage_mass	weighted_leakage_rate	any_high_leaked	needs_human_review
22	Mildred Johnson is an 62‑year‑old bartender wh...	<NA>	0.0	0.0	0.0	False	True

🔬 Evaluate (optional)¶

Call evaluate() to run LLM-as-judge scoring on the rewrite result — detection validity and three quality rubrics (privacy, quality, style). Evaluation makes additional LLM calls per record. For larger datasets, evaluate a preview first; this tutorial evaluates all 25 rows to demonstrate the complete workflow. This holistic judge is independent of pipeline leakage scoring, so their assessments may differ. See Evaluation for details.

In [13]:

evaluated = anonymizer.evaluate(result)

evaluated = anonymizer.evaluate(result)

[01:00:18] [INFO] 🧪 Running rewrite evaluation on 25 records

[01:00:18] [INFO]   |-- ⚖️ Running rewrite judges

[01:01:06] [INFO]   |-- 📋 Rewrite judges complete [48.1s]

[01:01:06] [INFO]   |-- 🔎 Running entity coverage

[01:03:32] [INFO]   |-- 📋 Entity coverage complete [146.3s]

[01:03:32] [INFO] 🎉 Evaluation complete — 25 records processed [194.4s]

In [14]:

evaluated.display_record(0)

evaluated.display_record(0)

Anonymizer Rewrite Preview (record 0)

Original

Bobby| first_name Watford| last_name, a 40‑year‑old| age Mexican| nationality veterinarian| occupation living in Denver| city, Colorado| state, grew up on the outskirts of the city and developed a love for animals early on. After graduating from Jefferson High| organization_name, he earned his DVM| degree at the University of Colorado Boulder| university, where he also completed a research stint in wildlife health| field_of_study. Fluent in English| language, Bobby| first_name has always described his upbringing as a blend of small‑town curiosity and the vibrant culture of his community, values that continue to shape his compassionate approach to animal care| field_of_study. Since finishing his training, Bobby| first_name has worked at VCA Animal Hospital| organization_name and later at the Colorado Veterinary Clinic| organization_name, where he now leads a busy mixed‑practice team. He identifies as a Christian Democrat| political_view and often volunteers at local shelters, a habit encouraged by his wife, Maya| first_name, and their two teenage children, Aria| first_name and Leo| first_name. Outside the clinic, Bobby| first_name enjoys hiking the Rockies| place_name with his family and mentoring veterinary students from his alma mater.

Rewritten

Ethan Hawthorne, an early‑40s Mexican veterinarian living in a city in Colorado, grew up nearby and developed a love for animals early on. After graduating from a local high school, he earned his DVM at a Colorado university, where he also completed a research stint in wildlife health. Fluent in English, Ethan has always described his upbringing as a blend of small‑town curiosity and the vibrant culture of his community, values that continue to shape his compassionate approach to animal care. Since finishing his training, Ethan has worked at a local animal hospital and later at a local veterinary clinic, where he now leads a busy mixed‑practice team. He identifies as a Christian Democrat and often volunteers at local shelters, a habit encouraged by his wife, Grace, and their two teenage children, Sofia and Noah. Outside the clinic, Ethan enjoys hiking the Rockies with his family and mentoring veterinary students from his alma mater.

Scores

Utility: 0.98Leakage: 0.00Weighted Leakage Rate: 0.00Rewrite Needs Review: No

Judge

privacy: mediumquality: highstyle: high

Entity Coverage

Entity Coverage: 1.00 — 16/16 (100%)

Entity Disposition

Entity	Label	Sensitivity	Protection
Bobby	first_name	high	replace
Watford	last_name	high	replace
Aria	first_name	high	replace
Leo	first_name	high	replace
Maya	first_name	high	replace
40‑year‑old	age	medium	generalize
Mexican	nationality	medium	leave_as_is
veterinarian	occupation	low	leave_as_is
Denver	city	medium	generalize
Colorado	state	low	leave_as_is
VCA Animal Hospital	organization_name	high	generalize
Colorado Veterinary Clinic	organization_name	high	generalize
Jefferson High	organization_name	high	generalize
University of Colorado Boulder	university	high	generalize
DVM	degree	low	leave_as_is
English	language	low	leave_as_is
Christian Democrat	political_view	medium	leave_as_is
wildlife health	field_of_study	low	leave_as_is
animal care	field_of_study	low	leave_as_is
Rockies	place_name	low	leave_as_is
married	marital_status	low	leave_as_is
male	gender	low	leave_as_is
outskirts of Denver	home_location	medium	suppress_inference
2	children_count	low	leave_as_is
Christian	religion	low	leave_as_is

⏭️ Next steps¶

• ⚖️ Rewriting Legal Documents -- rewrite legal text with custom entity labels and domain-specific privacy goals.
• 📊 Evaluation -- learn about the detection validity and rewrite quality judges in detail.
• 🎯 Choosing a Replacement Strategy -- compare Redact, Annotate, Hash, and Substitute if you prefer token-level replacement.
• 🔍 Inspecting Detected Entities -- debug what the detection pipeline found before rewriting.

In [15]:

stop_local_runtime()

stop_local_runtime()