packet-store-corpus (2b): truthful corpus labels with ModelFamily and verbatim generator, whole-item S1, canonical keys, S6 no copy under a new key (squash of weksa-lowering/packet-store-corpus 491536c..f9258d5; Soul s1)

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Eureka 2026-10-29 14:34:00 +01:00
commit c47e8e415d
10 changed files with 354 additions and 37 deletions

View file

@ -55,6 +55,27 @@
"withdrawn"
],
"$defs": {
"ModelFamily": {
"description": "The family of the model that wrote a line.",
"oneOf": [
{
"type": "string",
"enum": [
"Anthropic",
"OpenAi",
"Google",
"Alibaba",
"Meta",
"Mistral"
]
},
{
"description": "Nothing records which family wrote the line.",
"type": "string",
"const": "Unrecorded"
}
]
},
"Source": {
"oneOf": [
{
@ -137,14 +158,20 @@
]
},
{
"description": "Labelled model output; never in the test split, never judged by its own family.",
"description": "Labelled model output; never in the test split, never judged by its own family.\n`family` is `Unrecorded` when nothing records one. `generator` is the\nstring the fixture or run wrote, kept verbatim.",
"type": "object",
"properties": {
"ModelWritten": {
"type": "object",
"properties": {
"model_family": {
"type": "string"
"family": {
"$ref": "#/$defs/ModelFamily"
},
"generator": {
"type": [
"string",
"null"
]
},
"prompt_digest": {
"type": [
@ -154,7 +181,7 @@
}
},
"required": [
"model_family"
"family"
]
}
},