cls — Multi-label text classification outputs
Classifier outputs: the label set is written in full and the predicted labels carry *, so both the label space and the prediction are self-describing.
- Dominio
- NLP / support triage
- Versión
- 1
- Padre
- — (raíz)
- Clave de registros
messages- Separador de lista
,- Archivo
- forks/cls/contract.json
Campos por posición
| # | Tipo | Descripción | Parte |
|---|---|---|---|
id | str | (unique: True) | núcleo |
text | str | núcleo | |
labels | mlist | núcleo | |
conf | float | (max: 1) | núcleo |
rationale | str | (optional: True) | núcleo |
Ejemplo válido
cls|n=12|d=20260603|l=en|model=cls-support-2026|k=6
m1|The quiz froze after question 4, is that a known issue?|question*,feedback,bug*,request,praise,other|0.91|reports a malfunction and asks
m2|Great flashcards, they saved my week!|question,feedback,bug,request,praise*,other|0.97|
m3|Could you add export to Anki?|question,feedback,bug,request*,praise,other|0.94|feature request
m4|Transcription missed the last ten minutes of the lecture.|question,feedback,bug*,request,praise,other|0.9|
m5|How is my level computed?|question*,feedback,bug,request,praise,other|0.95|
m6|The map view is confusing but the summaries are excellent.|question,feedback*,bug,request,praise*,other|0.82|mixed sentiment
m7|Please support PDF slides as input.|question,feedback,bug,request*,praise,other|0.93|
m8|Nothing to report.|question,feedback,bug,request,praise,other*|0.7|
m9|Why does the same question repeat twice?|question*,feedback,bug*,request,praise,other|0.86|possible exposure-control bug
m10|Love the adaptive difficulty, keep it up.|question,feedback*,bug,request,praise*,other|0.9|
m11|Credits were deducted twice for one upload.|question,feedback,bug*,request,praise,other|0.96|billing bug
m12|Can I share a class with a friend?|question*,feedback,bug,request*,praise,other|0.88|
Con el ZIP opcional extraído, valida con mini --forks forks validate forks/cls/fixtures/valid.mini.
Notas de la familia
.mini-cls — Salidas de clasificación de texto multietiqueta#
Prefijo: cls Versión: 1 Padre: — Dominio: PLN / triaje de soporte
Salidas de clasificador: el conjunto de etiquetas se escribe completo y las etiquetas predichas llevan *, así que tanto el espacio de etiquetas como la predicción se describen solos.
Estructura del registro#
id:str | text:str | labels:mlist<str>*1+ | conf:float[0..1] | rationale:str?
| # | campo | tipo | notas |
|---|---|---|---|
| 1 | id |
str |
núcleo |
| 2 | text |
str |
núcleo |
| 3 | labels |
mlist<str>*1+ |
núcleo |
| 4 | conf |
float[0..1] |
núcleo |
| 5 | rationale |
str? |
núcleo; opcional |
Claves de cabecera#
| clave | tipo | requerida | descripción |
|---|---|---|---|
d |
str |
no | fecha de generación AAAAMMDD |
l |
str |
no | código de idioma |
model |
str |
no | |
k |
int |
no | etiquetas del conjunto de etiquetas |
n |
int |
sí | número de registros |
v |
int |
no | versión del contrato |
Ejemplo#
cls|n=12|d=20260603|l=en|model=cls-support-2026|k=6
m1|The quiz froze after question 4, is that a known issue?|question*,feedback,bug*,request,praise,other|0.91|reports a malfunction and asks
m2|Great flashcards, they saved my week!|question,feedback,bug,request,praise*,other|0.97|
…
Fixtures#
fixtures/valid.mini ↔ fixtures/canonical.json (ida y vuelta), fixtures/escaping.mini ↔ fixtures/escaping.json, y los casos negativos bad_count.mini, bad_arity.mini, bad_marker.mini, bad_type.mini.
Bloque de prompt#
Genera la especificación transferible con mini prompt cls.
cls — Multi-label text classification outputs
Classifier outputs: the label set is written in full and the predicted labels carry *, so both the label space and the prediction are self-describing.
- Domain
- NLP / support triage
- Version
- 1
- Parent
- — (root)
- Records key
messages- List separator
,- File
- forks/cls/contract.json
Fields by position
| # | Type | Description | Part |
|---|---|---|---|
id | str | (unique: True) | core |
text | str | core | |
labels | mlist | core | |
conf | float | (max: 1) | core |
rationale | str | (optional: True) | core |
Valid example
cls|n=12|d=20260603|l=en|model=cls-support-2026|k=6
m1|The quiz froze after question 4, is that a known issue?|question*,feedback,bug*,request,praise,other|0.91|reports a malfunction and asks
m2|Great flashcards, they saved my week!|question,feedback,bug,request,praise*,other|0.97|
m3|Could you add export to Anki?|question,feedback,bug,request*,praise,other|0.94|feature request
m4|Transcription missed the last ten minutes of the lecture.|question,feedback,bug*,request,praise,other|0.9|
m5|How is my level computed?|question*,feedback,bug,request,praise,other|0.95|
m6|The map view is confusing but the summaries are excellent.|question,feedback*,bug,request,praise*,other|0.82|mixed sentiment
m7|Please support PDF slides as input.|question,feedback,bug,request*,praise,other|0.93|
m8|Nothing to report.|question,feedback,bug,request,praise,other*|0.7|
m9|Why does the same question repeat twice?|question*,feedback,bug*,request,praise,other|0.86|possible exposure-control bug
m10|Love the adaptive difficulty, keep it up.|question,feedback*,bug,request,praise*,other|0.9|
m11|Credits were deducted twice for one upload.|question,feedback,bug*,request,praise,other|0.96|billing bug
m12|Can I share a class with a friend?|question*,feedback,bug,request*,praise,other|0.88|
With the optional ZIP extracted, validate with mini --forks forks validate forks/cls/fixtures/valid.mini.
Family notes
.mini-cls — Multi-label text classification outputs#
Prefix: cls Version: 1 Parent: — Domain: NLP / support triage
Classifier outputs: the label set is written in full and the predicted labels carry *, so both the label space and the prediction are self-describing.
Record layout#
id:str | text:str | labels:mlist<str>*1+ | conf:float[0..1] | rationale:str?
| # | field | type | notes |
|---|---|---|---|
| 1 | id |
str |
core |
| 2 | text |
str |
core |
| 3 | labels |
mlist<str>*1+ |
core |
| 4 | conf |
float[0..1] |
core |
| 5 | rationale |
str? |
core; optional |
Header keys#
| key | type | required | description |
|---|---|---|---|
d |
str |
no | generation date YYYYMMDD |
l |
str |
no | language code |
model |
str |
no | |
k |
int |
no | labels in the label set |
n |
int |
yes | number of records |
v |
int |
no | contract version |
Example#
cls|n=12|d=20260603|l=en|model=cls-support-2026|k=6
m1|The quiz froze after question 4, is that a known issue?|question*,feedback,bug*,request,praise,other|0.91|reports a malfunction and asks
m2|Great flashcards, they saved my week!|question,feedback,bug,request,praise*,other|0.97|
…
Fixtures#
fixtures/valid.mini ↔ fixtures/canonical.json (round-trip), fixtures/escaping.mini ↔ fixtures/escaping.json, and the negative cases bad_count.mini, bad_arity.mini, bad_marker.mini, bad_type.mini.
Prompt block#
Generate the transferable specification with mini prompt cls.