{ "generated_by": "site/gen_data.py", "taxonomy_version": "2026.11", "default_types": [ "ADDRESS", "EMAIL", "GOV_ID", "IP_ADDRESS", "PAYMENT", "PERSON", "PHONE", "SECRET", "USERNAME" ], "types": [ { "name": "SECRET", "class": "secret", "rank": 40, "prefer": "rule", "default": true }, { "name": "GOV_ID", "class": "gov_id", "rank": 30, "prefer": "rule", "default": true }, { "name": "PAYMENT", "class": "payment", "rank": 20, "prefer": "rule", "default": true }, { "name": "ADDRESS", "class": "person", "rank": 10, "prefer": "model", "default": true }, { "name": "EMAIL", "class": "contact", "rank": 10, "prefer": "rule", "default": true }, { "name": "IP_ADDRESS", "class": "contact", "rank": 10, "prefer": "rule", "default": true }, { "name": "PERSON", "class": "person", "rank": 10, "prefer": "model", "default": true }, { "name": "PHONE", "class": "contact", "rank": 10, "prefer": "rule", "default": true }, { "name": "USERNAME", "class": "contact", "rank": 10, "prefer": "model", "default": true }, { "name": "DATE_OF_BIRTH", "class": "quasi", "rank": 0, "prefer": "model", "default": false }, { "name": "ORG", "class": "quasi", "rank": 0, "prefer": "model", "default": false } ], "lanes": [ { "name": "rules", "label": "Rules and checksums", "revision": "rules", "repo_id": null, "note": "No weights, no download. Patterns and checksums only, so names stay out." }, { "name": "en-closed", "label": "Closed encoder (ModernBERT)", "revision": "3d0f39eceaf0c95fc07943064c58fba3fff60243", "repo_id": "antoniogr7/pii-identifier-v0.1", "note": "Local ModernBERT weights. Finds names and addresses as well as structured forms." } ], "examples": [ { "id": "support-ticket", "title": "A support ticket", "blurb": "A phone number, an email, and a test card. The order id stays clear.", "why": "Three structured forms, each confirmed by a grammar or a checksum. `Order 48291` is not PII, so it stays visible.", "tags": [ "EMAIL", "PHONE", "PAYMENT" ], "text": "Customer Ada Lovelace called from +852 5555 0101. Email ada@example.com. Card 4242424242424242. Order 48291.", "chars": 108, "lanes": { "rules": { "spans": [ { "type": "PHONE", "class": "contact", "start": 34, "end": 48, "text": "+852 5555 0101", "score": null, "detector_id": "rules.phone", "raw_label": "phone" }, { "type": "EMAIL", "class": "contact", "start": 56, "end": 71, "text": "ada@example.com", "score": null, "detector_id": "rules.email", "raw_label": "email" }, { "type": "PAYMENT", "class": "payment", "start": 78, "end": 94, "text": "4242424242424242", "score": 1.0, "detector_id": "rules.card", "raw_label": "card_number" } ], "masked": "Customer Ada Lovelace called from . Email . Card . Order 48291.", "vault": [ { "placeholder": "", "value": "+852 5555 0101" }, { "placeholder": "", "value": "ada@example.com" }, { "placeholder": "", "value": "4242424242424242" } ], "dropped": 0, "revision": "rules" }, "en-closed": { "spans": [ { "type": "PERSON", "class": "person", "start": 9, "end": 12, "text": "Ada", "score": 0.9992867112159729, "detector_id": "hf.antoniogr7/pii-identifier-v0.1", "raw_label": "first_name" }, { "type": "PERSON", "class": "person", "start": 13, "end": 21, "text": "Lovelace", "score": 0.9986006617546082, "detector_id": "hf.antoniogr7/pii-identifier-v0.1", "raw_label": "last_name" }, { "type": "PHONE", "class": "contact", "start": 34, "end": 48, "text": "+852 5555 0101", "score": null, "detector_id": "rules.phone", "raw_label": "phone" }, { "type": "EMAIL", "class": "contact", "start": 56, "end": 71, "text": "ada@example.com", "score": null, "detector_id": "rules.email", "raw_label": "email" }, { "type": "PAYMENT", "class": "payment", "start": 78, "end": 94, "text": "4242424242424242", "score": 1.0, "detector_id": "rules.card", "raw_label": "card_number" } ], "masked": "Customer called from . Email . Card . Order 48291.", "vault": [ { "placeholder": "", "value": "Ada" }, { "placeholder": "", "value": "Lovelace" }, { "placeholder": "", "value": "+852 5555 0101" }, { "placeholder": "", "value": "ada@example.com" }, { "placeholder": "", "value": "4242424242424242" } ], "dropped": 0, "revision": "3d0f39eceaf0c95fc07943064c58fba3fff60243" } } }, { "id": "secret-note", "title": "A note with a password", "blurb": "The password is masked. It never enters the vault.", "why": "A secret is irreversible on purpose. Restoring it would write a password into the next system.", "tags": [ "SECRET", "EMAIL", "PHONE" ], "text": "Ask Ada Lovelace to call +1 202 555 0147 about ticket 77. Do not include the password hunter2 in the note.", "chars": 124, "lanes": { "rules": { "spans": [ { "type": "EMAIL", "class": "contact", "start": 18, "end": 33, "text": "ada@example.com", "score": null, "detector_id": "rules.email", "raw_label": "email" }, { "type": "PHONE", "class": "contact", "start": 43, "end": 58, "text": "+1 202 555 0147", "score": 1.0, "detector_id": "rules.phone", "raw_label": "phone" }, { "type": "SECRET", "class": "secret", "start": 104, "end": 111, "text": "hunter2", "score": null, "detector_id": "rules.secret", "raw_label": "password" } ], "masked": "Ask Ada Lovelace <> to call about ticket 77. Do not include the password in the note.", "vault": [ { "placeholder": "", "value": "ada@example.com" }, { "placeholder": "", "value": "+1 202 555 0147" } ], "dropped": 0, "revision": "rules" }, "en-closed": { "spans": [ { "type": "PERSON", "class": "person", "start": 4, "end": 7, "text": "Ada", "score": 0.9978262782096863, "detector_id": "hf.antoniogr7/pii-identifier-v0.1", "raw_label": "first_name" }, { "type": "PERSON", "class": "person", "start": 8, "end": 16, "text": "Lovelace", "score": 0.9881123900413513, "detector_id": "hf.antoniogr7/pii-identifier-v0.1", "raw_label": "last_name" }, { "type": "EMAIL", "class": "contact", "start": 18, "end": 33, "text": "ada@example.com", "score": null, "detector_id": "rules.email", "raw_label": "email" }, { "type": "PHONE", "class": "contact", "start": 43, "end": 58, "text": "+1 202 555 0147", "score": 1.0, "detector_id": "rules.phone", "raw_label": "phone" }, { "type": "SECRET", "class": "secret", "start": 104, "end": 111, "text": "hunter2", "score": null, "detector_id": "rules.secret", "raw_label": "password" } ], "masked": "Ask <> to call about ticket 77. Do not include the password in the note.", "vault": [ { "placeholder": "", "value": "Ada" }, { "placeholder": "", "value": "Lovelace" }, { "placeholder": "", "value": "ada@example.com" }, { "placeholder": "", "value": "+1 202 555 0147" } ], "dropped": 0, "revision": "3d0f39eceaf0c95fc07943064c58fba3fff60243" } } }, { "id": "payments", "title": "A wire transfer", "blurb": "A valid IBAN is found. A card that fails Luhn is ignored.", "why": "The IBAN passes the MOD-97 check. `4242424242424243` fails Luhn, so the rule refuses it rather than guessing.", "tags": [ "PAYMENT", "EMAIL", "IP_ADDRESS" ], "text": "Wire to IBAN GB82WEST12345698765432 from card 4242424242424243. Reach ops at ops@example.org or 203.0.113.10.", "chars": 109, "lanes": { "rules": { "spans": [ { "type": "PAYMENT", "class": "payment", "start": 13, "end": 35, "text": "GB82WEST12345698765432", "score": 1.0, "detector_id": "rules.iban", "raw_label": "iban" }, { "type": "EMAIL", "class": "contact", "start": 77, "end": 92, "text": "ops@example.org", "score": null, "detector_id": "rules.email", "raw_label": "email" }, { "type": "IP_ADDRESS", "class": "contact", "start": 96, "end": 108, "text": "203.0.113.10", "score": 1.0, "detector_id": "rules.ip", "raw_label": "ip_address" } ], "masked": "Wire to IBAN from card 4242424242424243. Reach ops at or .", "vault": [ { "placeholder": "", "value": "GB82WEST12345698765432" }, { "placeholder": "", "value": "ops@example.org" }, { "placeholder": "", "value": "203.0.113.10" } ], "dropped": 0, "revision": "rules" }, "en-closed": { "spans": [ { "type": "PAYMENT", "class": "payment", "start": 13, "end": 35, "text": "GB82WEST12345698765432", "score": 1.0, "detector_id": "rules.iban", "raw_label": "iban" }, { "type": "EMAIL", "class": "contact", "start": 77, "end": 92, "text": "ops@example.org", "score": null, "detector_id": "rules.email", "raw_label": "email" }, { "type": "IP_ADDRESS", "class": "contact", "start": 96, "end": 108, "text": "203.0.113.10", "score": 1.0, "detector_id": "rules.ip", "raw_label": "ip_address" } ], "masked": "Wire to IBAN from card 4242424242424243. Reach ops at or .", "vault": [ { "placeholder": "", "value": "GB82WEST12345698765432" }, { "placeholder": "", "value": "ops@example.org" }, { "placeholder": "", "value": "203.0.113.10" } ], "dropped": 0, "revision": "3d0f39eceaf0c95fc07943064c58fba3fff60243" } } }, { "id": "chinese", "title": "A Chinese contact line", "blurb": "A Chinese mobile number and an email, on the rule lane.", "why": "The rule lane is language neutral for structured forms. The phone still passes libphonenumber.", "tags": [ "PHONE", "EMAIL" ], "text": "联系人张伟，手机13800138000，邮箱wei@example.com。", "chars": 38, "lanes": { "rules": { "spans": [ { "type": "PHONE", "class": "contact", "start": 8, "end": 19, "text": "13800138000", "score": 1.0, "detector_id": "rules.phone", "raw_label": "phone" }, { "type": "EMAIL", "class": "contact", "start": 22, "end": 37, "text": "wei@example.com", "score": null, "detector_id": "rules.email", "raw_label": "email" } ], "masked": "联系人张伟，手机，邮箱。", "vault": [ { "placeholder": "", "value": "13800138000" }, { "placeholder": "", "value": "wei@example.com" } ], "dropped": 0, "revision": "rules" }, "en-closed": { "spans": [ { "type": "PERSON", "class": "person", "start": 3, "end": 5, "text": "张伟", "score": 0.562475860118866, "detector_id": "hf.antoniogr7/pii-identifier-v0.1", "raw_label": "first_name" }, { "type": "PHONE", "class": "contact", "start": 8, "end": 19, "text": "13800138000", "score": 1.0, "detector_id": "rules.phone", "raw_label": "phone" }, { "type": "EMAIL", "class": "contact", "start": 22, "end": 37, "text": "wei@example.com", "score": null, "detector_id": "rules.email", "raw_label": "email" } ], "masked": "联系人，手机，邮箱。", "vault": [ { "placeholder": "", "value": "张伟" }, { "placeholder": "", "value": "13800138000" }, { "placeholder": "", "value": "wei@example.com" } ], "dropped": 0, "revision": "3d0f39eceaf0c95fc07943064c58fba3fff60243" } } }, { "id": "placeholders", "title": "Two people, two placeholders", "blurb": "A repeat reuses its token. A new slice gets a new number.", "why": "The same address twice gets `` twice. A second address gets ``.", "tags": [ "EMAIL" ], "text": "Write to ada@example.com or grace@example.com. The desk address is ada@example.com.", "chars": 83, "lanes": { "rules": { "spans": [ { "type": "EMAIL", "class": "contact", "start": 9, "end": 24, "text": "ada@example.com", "score": null, "detector_id": "rules.email", "raw_label": "email" }, { "type": "EMAIL", "class": "contact", "start": 28, "end": 45, "text": "grace@example.com", "score": null, "detector_id": "rules.email", "raw_label": "email" }, { "type": "EMAIL", "class": "contact", "start": 67, "end": 82, "text": "ada@example.com", "score": null, "detector_id": "rules.email", "raw_label": "email" } ], "masked": "Write to or . The desk address is .", "vault": [ { "placeholder": "", "value": "ada@example.com" }, { "placeholder": "", "value": "grace@example.com" } ], "dropped": 0, "revision": "rules" }, "en-closed": { "spans": [ { "type": "EMAIL", "class": "contact", "start": 9, "end": 24, "text": "ada@example.com", "score": null, "detector_id": "rules.email", "raw_label": "email" }, { "type": "EMAIL", "class": "contact", "start": 28, "end": 45, "text": "grace@example.com", "score": null, "detector_id": "rules.email", "raw_label": "email" }, { "type": "EMAIL", "class": "contact", "start": 67, "end": 82, "text": "ada@example.com", "score": null, "detector_id": "rules.email", "raw_label": "email" } ], "masked": "Write to or . The desk address is .", "vault": [ { "placeholder": "", "value": "ada@example.com" }, { "placeholder": "", "value": "grace@example.com" } ], "dropped": 0, "revision": "3d0f39eceaf0c95fc07943064c58fba3fff60243" } } }, { "id": "negatives", "title": "Text with no PII", "blurb": "An order id, a SKU, and a plain sentence.", "why": "These look numeric, and none is a published PII form. A locator that spans them is guessing.", "tags": [], "text": "Order 48291 ships as SKU-77219 from warehouse 4. The build finished in 12 minutes on node 3.", "chars": 92, "lanes": { "rules": { "spans": [], "masked": "Order 48291 ships as SKU-77219 from warehouse 4. The build finished in 12 minutes on node 3.", "vault": [], "dropped": 0, "revision": "rules" }, "en-closed": { "spans": [], "masked": "Order 48291 ships as SKU-77219 from warehouse 4. The build finished in 12 minutes on node 3.", "vault": [], "dropped": 0, "revision": "3d0f39eceaf0c95fc07943064c58fba3fff60243" } } }, { "id": "long-text", "title": "Long text, original offsets", "blurb": "The email sits far into the string. The offset still indexes the whole source.", "why": "A long document is split into windows internally. The public offset is never a window offset.", "tags": [ "EMAIL" ], "text": "Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Email ada@example.com for the desk.", "chars": 395, "lanes": { "rules": { "spans": [ { "type": "EMAIL", "class": "contact", "start": 366, "end": 381, "text": "ada@example.com", "score": null, "detector_id": "rules.email", "raw_label": "email" } ], "masked": "Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Email for the desk.", "vault": [ { "placeholder": "", "value": "ada@example.com" } ], "dropped": 0, "revision": "rules" }, "en-closed": { "spans": [ { "type": "EMAIL", "class": "contact", "start": 366, "end": 381, "text": "ada@example.com", "score": null, "detector_id": "rules.email", "raw_label": "email" } ], "masked": "Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Note. Email for the desk.", "vault": [ { "placeholder": "", "value": "ada@example.com" } ], "dropped": 0, "revision": "3d0f39eceaf0c95fc07943064c58fba3fff60243" } } }, { "id": "logs", "title": "A log line", "blurb": "An IP address and an email inside a structured line.", "why": "An IP address passes an RFC 4291 or RFC 3986 match and then a stdlib parse.", "tags": [ "IP_ADDRESS", "EMAIL" ], "text": "2026-11-04T09:12:33Z level=warn user=ada@example.com src=198.51.100.7 path=/v1/orders action=denied", "chars": 99, "lanes": { "rules": { "spans": [ { "type": "EMAIL", "class": "contact", "start": 32, "end": 52, "text": "user=ada@example.com", "score": null, "detector_id": "rules.email", "raw_label": "email" }, { "type": "IP_ADDRESS", "class": "contact", "start": 57, "end": 69, "text": "198.51.100.7", "score": 1.0, "detector_id": "rules.ip", "raw_label": "ip_address" } ], "masked": "2026-11-04T09:12:33Z level=warn src= path=/v1/orders action=denied", "vault": [ { "placeholder": "", "value": "user=ada@example.com" }, { "placeholder": "", "value": "198.51.100.7" } ], "dropped": 0, "revision": "rules" }, "en-closed": { "spans": [ { "type": "EMAIL", "class": "contact", "start": 32, "end": 52, "text": "user=ada@example.com", "score": null, "detector_id": "rules.email", "raw_label": "email" }, { "type": "IP_ADDRESS", "class": "contact", "start": 57, "end": 69, "text": "198.51.100.7", "score": 1.0, "detector_id": "rules.ip", "raw_label": "ip_address" } ], "masked": "2026-11-04T09:12:33Z level=warn src= path=/v1/orders action=denied", "vault": [ { "placeholder": "", "value": "user=ada@example.com" }, { "placeholder": "", "value": "198.51.100.7" } ], "dropped": 0, "revision": "3d0f39eceaf0c95fc07943064c58fba3fff60243" } } }, { "id": "prompt", "title": "A prompt before it leaves", "blurb": "What a caller sends to a model after masking.", "why": "This is the product case: keep the sentence, remove the person, prove which characters left.", "tags": [ "EMAIL", "PERSON", "SECRET" ], "text": "Summarise this for the on-call engineer: Ada Lovelace reported that ada@example.com cannot reset the password hunter2 from Lisbon.", "chars": 130, "lanes": { "rules": { "spans": [ { "type": "EMAIL", "class": "contact", "start": 68, "end": 83, "text": "ada@example.com", "score": null, "detector_id": "rules.email", "raw_label": "email" }, { "type": "SECRET", "class": "secret", "start": 110, "end": 117, "text": "hunter2", "score": null, "detector_id": "rules.secret", "raw_label": "password" } ], "masked": "Summarise this for the on-call engineer: Ada Lovelace reported that cannot reset the password from Lisbon.", "vault": [ { "placeholder": "", "value": "ada@example.com" } ], "dropped": 0, "revision": "rules" }, "en-closed": { "spans": [ { "type": "PERSON", "class": "person", "start": 41, "end": 44, "text": "Ada", "score": 0.9981321692466736, "detector_id": "hf.antoniogr7/pii-identifier-v0.1", "raw_label": "first_name" }, { "type": "PERSON", "class": "person", "start": 45, "end": 53, "text": "Lovelace", "score": 0.9971973896026611, "detector_id": "hf.antoniogr7/pii-identifier-v0.1", "raw_label": "last_name" }, { "type": "EMAIL", "class": "contact", "start": 68, "end": 83, "text": "ada@example.com", "score": null, "detector_id": "rules.email", "raw_label": "email" }, { "type": "SECRET", "class": "secret", "start": 110, "end": 117, "text": "hunter2", "score": null, "detector_id": "rules.secret", "raw_label": "password" } ], "masked": "Summarise this for the on-call engineer: reported that cannot reset the password from Lisbon.", "vault": [ { "placeholder": "", "value": "Ada" }, { "placeholder": "", "value": "Lovelace" }, { "placeholder": "", "value": "ada@example.com" } ], "dropped": 0, "revision": "3d0f39eceaf0c95fc07943064c58fba3fff60243" } } }, { "id": "names", "title": "Two names", "blurb": "A person name needs a model lane. The rule lane finds neither.", "why": "A name has no grammar and no checksum. Rules own structured forms, models own names.", "tags": [ "PERSON" ], "text": "Ada Lovelace met Grace Hopper at the lab to review the schedule.", "chars": 64, "lanes": { "rules": { "spans": [], "masked": "Ada Lovelace met Grace Hopper at the lab to review the schedule.", "vault": [], "dropped": 0, "revision": "rules" }, "en-closed": { "spans": [ { "type": "PERSON", "class": "person", "start": 0, "end": 3, "text": "Ada", "score": 0.9990211725234985, "detector_id": "hf.antoniogr7/pii-identifier-v0.1", "raw_label": "first_name" }, { "type": "PERSON", "class": "person", "start": 4, "end": 12, "text": "Lovelace", "score": 0.9959753155708313, "detector_id": "hf.antoniogr7/pii-identifier-v0.1", "raw_label": "last_name" }, { "type": "PERSON", "class": "person", "start": 17, "end": 22, "text": "Grace", "score": 0.9987951517105103, "detector_id": "hf.antoniogr7/pii-identifier-v0.1", "raw_label": "first_name" }, { "type": "PERSON", "class": "person", "start": 23, "end": 29, "text": "Hopper", "score": 0.9965230226516724, "detector_id": "hf.antoniogr7/pii-identifier-v0.1", "raw_label": "last_name" } ], "masked": " met at the lab to review the schedule.", "vault": [ { "placeholder": "", "value": "Ada" }, { "placeholder": "", "value": "Lovelace" }, { "placeholder": "", "value": "Grace" }, { "placeholder": "", "value": "Hopper" } ], "dropped": 0, "revision": "3d0f39eceaf0c95fc07943064c58fba3fff60243" } } }, { "id": "address", "title": "A postal address", "blurb": "A street address, a person, and an email together.", "why": "An address is a model type. The email beside it is a rule type. The locator merges both.", "tags": [ "ADDRESS", "PERSON", "EMAIL" ], "text": "Ship the replacement to Grace Hopper, 12 Rue de Rivoli, Paris. Confirm on grace@example.com before Friday.", "chars": 106, "lanes": { "rules": { "spans": [ { "type": "EMAIL", "class": "contact", "start": 74, "end": 91, "text": "grace@example.com", "score": null, "detector_id": "rules.email", "raw_label": "email" } ], "masked": "Ship the replacement to Grace Hopper, 12 Rue de Rivoli, Paris. Confirm on before Friday.", "vault": [ { "placeholder": "", "value": "grace@example.com" } ], "dropped": 0, "revision": "rules" }, "en-closed": { "spans": [ { "type": "PERSON", "class": "person", "start": 24, "end": 29, "text": "Grace", "score": 0.9971740245819092, "detector_id": "hf.antoniogr7/pii-identifier-v0.1", "raw_label": "first_name" }, { "type": "PERSON", "class": "person", "start": 30, "end": 36, "text": "Hopper", "score": 0.9974498748779297, "detector_id": "hf.antoniogr7/pii-identifier-v0.1", "raw_label": "last_name" }, { "type": "ADDRESS", "class": "person", "start": 38, "end": 54, "text": "12 Rue de Rivoli", "score": 0.9966519474983215, "detector_id": "hf.antoniogr7/pii-identifier-v0.1", "raw_label": "street_address" }, { "type": "ADDRESS", "class": "person", "start": 56, "end": 61, "text": "Paris", "score": 0.8685413002967834, "detector_id": "hf.antoniogr7/pii-identifier-v0.1", "raw_label": "city" }, { "type": "EMAIL", "class": "contact", "start": 74, "end": 91, "text": "grace@example.com", "score": null, "detector_id": "rules.email", "raw_label": "email" } ], "masked": "Ship the replacement to , , . Confirm on before Friday.", "vault": [ { "placeholder": "", "value": "Grace" }, { "placeholder": "", "value": "Hopper" }, { "placeholder": "", "value": "12 Rue de Rivoli" }, { "placeholder": "", "value": "Paris" }, { "placeholder": "", "value": "grace@example.com" } ], "dropped": 0, "revision": "3d0f39eceaf0c95fc07943064c58fba3fff60243" } } }, { "id": "gov-id", "title": "A national id", "blurb": "A US SSN pattern. The rule lane is silent, and the model lane is not.", "why": "V1 ships no national id pattern, by design. This row shows what the model lane buys.", "tags": [ "GOV_ID", "PERSON" ], "text": "Applicant Ada Lovelace, SSN 121-45-6789, signed the form today.", "chars": 63, "lanes": { "rules": { "spans": [], "masked": "Applicant Ada Lovelace, SSN 121-45-6789, signed the form today.", "vault": [], "dropped": 0, "revision": "rules" }, "en-closed": { "spans": [ { "type": "PERSON", "class": "person", "start": 10, "end": 13, "text": "Ada", "score": 0.9978285431861877, "detector_id": "hf.antoniogr7/pii-identifier-v0.1", "raw_label": "first_name" }, { "type": "PERSON", "class": "person", "start": 14, "end": 22, "text": "Lovelace", "score": 0.9963391423225403, "detector_id": "hf.antoniogr7/pii-identifier-v0.1", "raw_label": "last_name" }, { "type": "GOV_ID", "class": "gov_id", "start": 28, "end": 39, "text": "121-45-6789", "score": 0.8991077542304993, "detector_id": "hf.antoniogr7/pii-identifier-v0.1", "raw_label": "ssn" } ], "masked": "Applicant , SSN , signed the form today.", "vault": [ { "placeholder": "", "value": "Ada" }, { "placeholder": "", "value": "Lovelace" }, { "placeholder": "", "value": "121-45-6789" } ], "dropped": 0, "revision": "3d0f39eceaf0c95fc07943064c58fba3fff60243" } } }, { "id": "account", "title": "An account handle", "blurb": "A login name, which is not a display name.", "why": "`USERNAME` is a model type. It is the string that marks an account, not the person.", "tags": [ "USERNAME", "EMAIL" ], "text": "User lkernan signed in and asked to reset access for lkernan@example.com.", "chars": 73, "lanes": { "rules": { "spans": [ { "type": "EMAIL", "class": "contact", "start": 53, "end": 72, "text": "lkernan@example.com", "score": null, "detector_id": "rules.email", "raw_label": "email" } ], "masked": "User lkernan signed in and asked to reset access for .", "vault": [ { "placeholder": "", "value": "lkernan@example.com" } ], "dropped": 0, "revision": "rules" }, "en-closed": { "spans": [ { "type": "USERNAME", "class": "contact", "start": 5, "end": 12, "text": "lkernan", "score": 0.9941150546073914, "detector_id": "hf.antoniogr7/pii-identifier-v0.1", "raw_label": "user_name" }, { "type": "EMAIL", "class": "contact", "start": 53, "end": 72, "text": "lkernan@example.com", "score": null, "detector_id": "rules.email", "raw_label": "email" } ], "masked": "User signed in and asked to reset access for .", "vault": [ { "placeholder": "", "value": "lkernan" }, { "placeholder": "", "value": "lkernan@example.com" } ], "dropped": 0, "revision": "3d0f39eceaf0c95fc07943064c58fba3fff60243" } } }, { "id": "finance", "title": "A finance note", "blurb": "A card, a routing number, and a name in a bank context.", "why": "The hardest case in the public score. A finance document does not look like a persona note.", "tags": [ "PAYMENT", "PERSON", "EMAIL" ], "text": "The transfer from Grace Hopper uses card 5490 3479 1287 6543 and routing number 271210785. Receipt to grace@example.com.", "chars": 120, "lanes": { "rules": { "spans": [ { "type": "EMAIL", "class": "contact", "start": 102, "end": 119, "text": "grace@example.com", "score": null, "detector_id": "rules.email", "raw_label": "email" } ], "masked": "The transfer from Grace Hopper uses card 5490 3479 1287 6543 and routing number 271210785. Receipt to .", "vault": [ { "placeholder": "", "value": "grace@example.com" } ], "dropped": 0, "revision": "rules" }, "en-closed": { "spans": [ { "type": "PERSON", "class": "person", "start": 18, "end": 23, "text": "Grace", "score": 0.9970589876174927, "detector_id": "hf.antoniogr7/pii-identifier-v0.1", "raw_label": "first_name" }, { "type": "PERSON", "class": "person", "start": 24, "end": 30, "text": "Hopper", "score": 0.9982434511184692, "detector_id": "hf.antoniogr7/pii-identifier-v0.1", "raw_label": "last_name" }, { "type": "PAYMENT", "class": "payment", "start": 41, "end": 60, "text": "5490 3479 1287 6543", "score": 0.9983824491500854, "detector_id": "hf.antoniogr7/pii-identifier-v0.1", "raw_label": "credit_debit_card" }, { "type": "EMAIL", "class": "contact", "start": 102, "end": 119, "text": "grace@example.com", "score": null, "detector_id": "rules.email", "raw_label": "email" } ], "masked": "The transfer from uses card and routing number 271210785. Receipt to .", "vault": [ { "placeholder": "", "value": "Grace" }, { "placeholder": "", "value": "Hopper" }, { "placeholder": "", "value": "5490 3479 1287 6543" }, { "placeholder": "", "value": "grace@example.com" } ], "dropped": 0, "revision": "3d0f39eceaf0c95fc07943064c58fba3fff60243" } } } ] }