Test 138

Jan 1, 2028 / 3 facts

Request

Please post a concise comment on archive-index document `doc_archive_feb2023_churn` that points reviewers to the original main working document for the February 2023 mid-segment churn investigation. Identify the document, its owner and intended document status, and the analytical sections it was initially set up to hold. Keep this as an archival pointer rather than reconstructing the investigation’s findings.

Required memory

Fact 303

Riley Tanaka owns the Notion document “Mid-seg churn spike -- Feb 2023 investigation.”

Source evidence (2)

000010Feb 7, 2023 / 14:00 UTC-06:00

opened a Notion doc so this stops living in scratch notes: 'Mid-seg churn spike -- Feb 2023 investigation'. owner is me. just a skeleton rn -- signal writeup, baselines, hypothesis list TBD, cohort cuts TBD. gonna keep it as a living doc and dump each pass in there as we go, esp if Marcus keeps trying to run the pricing-page test in parallel.

Message 000010 in history

002407Jan 15, 2025 / 14:10 UTC-06:00

I completed the lifecycle-critical state map for Helio Start admission, Expansion Assist eligibility, lifecycle messaging, activation reporting, and CS nudges, including each source, accountable owner, unit of analysis, freshness requirement, and decision boundary. The map shows overlapping dependencies without one accountable operating layer. Priya is sponsoring a proposed formal Lifecycle Systems remit with me as proposed lead, Owen on measurement and state semantics, Ines on lifecycle governance, and Daniela's organization responsible for engineering reliability. This is only a charter proposal, not an approved function or a live shared-state implementation, and Tomás will make the final organizational decision on January 24, 2025 at 3:00pm. Create the Lifecycle Systems charter-proposal document in the Growth folder and schedule the January 24 organizational-decision meeting from 3:00pm to 3:30pm with Riley Tanaka, Priya Devarajan, Tomás Vega, Owen Pham, Ines Kovac, and Daniela Schultz.

Message 002407 in history

Fact 304

The Notion document “Mid-seg churn spike -- Feb 2023 investigation” is currently a skeleton containing a signal writeup, baselines, a pending hypothesis list, and pending cohort cuts.

Source evidence (1)

000010Feb 7, 2023 / 14:00 UTC-06:00

Message 000010 in history

Fact 305

Riley Tanaka plans to maintain “Mid-seg churn spike -- Feb 2023 investigation” as a living document and add each investigation pass, particularly if Marcus continues trying to run the pricing-page test in parallel.

Source evidence (1)

000010Feb 7, 2023 / 14:00 UTC-06:00

Message 000010 in history

Expected tool calls

post_doc_comment

Grading

1. field_equals / post_doc_comment

{
  "type": "field_equals",
  "tool": "post_doc_comment",
  "action_id": "archive_pointer_comment",
  "path": "result.ok",
  "value": true,
  "check_id": "riley_138_00"
}

2. field_equals / post_doc_comment

{
  "check_id": "riley_138_01",
  "type": "field_equals",
  "tool": "post_doc_comment",
  "action_id": "archive_pointer_comment",
  "path": "args.doc_id",
  "value": "doc_archive_feb2023_churn"
}

3. field_llm_judge / post_doc_comment

{
  "type": "field_llm_judge",
  "tool": "post_doc_comment",
  "action_id": "archive_pointer_comment",
  "path": "args",
  "criterion": "The comment clearly identifies the original main working document as titled “Mid-seg churn spike -- Feb 2023 investigation,” rather than presenting the later institutional writeup as the original working document.\n\nThe comment states that Riley owned the working document and that it was intended to remain a living document updated throughout the investigation.\n\nThe comment says the document was initially designed to hold the signal writeup, baselines, hypothesis list, and cohort cuts. It remains a concise archival pointer and does not reconstruct the investigation’s findings.",
  "check_id": "riley_138_02"
}

Complete grading specification

{
  "type": "tool_trace",
  "config": {
    "check_version": 2,
    "today": "2028-01-01",
    "semantic_judge_version": 2,
    "assertions": [
      {
        "type": "field_equals",
        "tool": "post_doc_comment",
        "action_id": "archive_pointer_comment",
        "path": "result.ok",
        "value": true,
        "check_id": "riley_138_00"
      },
      {
        "check_id": "riley_138_01",
        "type": "field_equals",
        "tool": "post_doc_comment",
        "action_id": "archive_pointer_comment",
        "path": "args.doc_id",
        "value": "doc_archive_feb2023_churn"
      },
      {
        "type": "field_llm_judge",
        "tool": "post_doc_comment",
        "action_id": "archive_pointer_comment",
        "path": "args",
        "criterion": "The comment clearly identifies the original main working document as titled “Mid-seg churn spike -- Feb 2023 investigation,” rather than presenting the later institutional writeup as the original working document.\n\nThe comment states that Riley owned the working document and that it was intended to remain a living document updated throughout the investigation.\n\nThe comment says the document was initially designed to hold the signal writeup, baselines, hypothesis list, and cohort cuts. It remains a concise archival pointer and does not reconstruct the investigation’s findings.",
        "check_id": "riley_138_02"
      }
    ]
  }
}

App state

Download JSON

Source file

tests/riley/138.yaml

SHA-256: 0004b3c1c06db672e52b3ebaf5e68f6b7abd3aa3137557b22197356e86a3ba05