homelab/stack
1
0
Fork 0
Code Issues 251 Pull Requests 2 Actions Packages Projects 1 Releases Wiki Activity

comments: stakeholder segmentation + coordination detection #255

New Issue
Open
opened 2026-03-25 19:30:23 +00:00 by kert · 3 comments
kert commented 2026-03-25 19:30:23 +00:00
Owner
Copy Link

Objective

Identify who is commenting and detect organized campaigns.

Stakeholder Types

  • manufacturer (Organogenesis, MiMedx, etc.)
  • distributor/sales rep
  • provider (podiatrist, dermatologist, wound care NP)
  • wound care society (Alliance of Wound Care Stakeholders, WHS)
  • patient advocacy group
  • payer/insurer
  • government agency (OIG, GAO, state Medicaid)
  • academic/researcher
  • individual beneficiary

Coordination Detection (from hti5)

  • Jaccard similarity on character 5-grams (threshold 0.45)
  • Keyword fingerprinting for known campaigns
  • Temporal clustering (bulk submissions on same date)
  • Form letter identification

Key Question

Are skin substitute manufacturers/distributors orchestrating form letter campaigns to oppose reclassification? Cross-reference with entity tags from evidence base.

## Objective Identify who is commenting and detect organized campaigns. ## Stakeholder Types - manufacturer (Organogenesis, MiMedx, etc.) - distributor/sales rep - provider (podiatrist, dermatologist, wound care NP) - wound care society (Alliance of Wound Care Stakeholders, WHS) - patient advocacy group - payer/insurer - government agency (OIG, GAO, state Medicaid) - academic/researcher - individual beneficiary ## Coordination Detection (from hti5) - Jaccard similarity on character 5-grams (threshold 0.45) - Keyword fingerprinting for known campaigns - Temporal clustering (bulk submissions on same date) - Form letter identification ## Key Question Are skin substitute manufacturers/distributors orchestrating form letter campaigns to oppose reclassification? Cross-reference with entity tags from evidence base.
kert added this to the P30: CMS Rulemaking Comment Analysis — regulations.gov sentiment + coordination detection milestone 2026-03-25 19:31:53 +00:00
kert commented 2026-07-10 20:49:06 +00:00
Author
Owner
Copy Link

Status: groundwork exists, the analysis run does not. skin_subs.rulemaking_comments already has stakeholder_type, coordination_group, and is_form_letter columns with a 15-row pilot. Inputs ready (#251/#253 closed — full corpus + extracted text in bib/Zotero). Remaining: segmentation + the hti5-style similarity/coordination detection at scale.

Status: groundwork exists, the analysis run does not. `skin_subs.rulemaking_comments` already has `stakeholder_type`, `coordination_group`, and `is_form_letter` columns with a 15-row pilot. Inputs ready (#251/#253 closed — full corpus + extracted text in bib/Zotero). Remaining: segmentation + the hti5-style similarity/coordination detection at scale.
kert commented 2026-07-11 02:20:55 +00:00
Author
Owner
Copy Link

Coordination detection is implemented and run — no LLM needed for this half (c9b6a28f07):

  • rex.comments.coordination — hti5 methodology: Jaccard on character 5-gram shingles (threshold 0.45), union-find grouping, form-letter flag at ≥3 members. Texts <200 chars excluded (short agreement ≠ coordination).
  • Results for CMS-2025-0304: of the 384 skin-sub-relevant comments, 203 (53%) are form letters across 31 coordinated groups — the largest campaigns have 72 and 36 members. skin_subs.rulemaking_comments now has all 384 rows with coordination_group + is_form_letter filled.
  • Note on the key question: the top two campaigns appear to be provider-organization letters (SNF/ALF wound-care providers; AAHCM home-care) that mention skin subs inside broader letters — whether the campaigns oppose the reclassification (the manufacturer-orchestration hypothesis) gets answered when the #254 position classification runs (blocked on Anthropic API credits; the shared loader merges it in without touching these columns).

Remaining for this issue: stakeholder_type per comment (part of the #254 LLM pass) and cross-referencing campaigns against the evidence-base entity tags.

Coordination detection is implemented and **run** — no LLM needed for this half (https://git.fhirworx.io/homelab/stack/commit/c9b6a28f070394870f664dbbaacf00b6db59e9e6): - `rex.comments.coordination` — hti5 methodology: Jaccard on character 5-gram shingles (threshold 0.45), union-find grouping, form-letter flag at ≥3 members. Texts <200 chars excluded (short agreement ≠ coordination). - Results for **CMS-2025-0304**: of the 384 skin-sub-relevant comments, **203 (53%) are form letters across 31 coordinated groups** — the largest campaigns have 72 and 36 members. `skin_subs.rulemaking_comments` now has all 384 rows with `coordination_group` + `is_form_letter` filled. - Note on the key question: the top two campaigns appear to be provider-organization letters (SNF/ALF wound-care providers; AAHCM home-care) that *mention* skin subs inside broader letters — whether the campaigns oppose the reclassification (the manufacturer-orchestration hypothesis) gets answered when the #254 position classification runs (blocked on Anthropic API credits; the shared loader merges it in without touching these columns). Remaining for this issue: `stakeholder_type` per comment (part of the #254 LLM pass) and cross-referencing campaigns against the evidence-base entity tags.
kert commented 2026-08-13 23:46:55 +00:00
Author
Owner
Copy Link

Status audit (2026-08-13, repo-verified): PARTIAL. Jaccard 5-gram near-dup + union-find + form-letter flags done and loaded (384/384 rows have coordination_group/is_form_letter; rex/comments/coordination.py). Missing vs body: keyword fingerprinting for known campaigns, temporal clustering, entity-tag cross-reference; stakeholder segmentation defined but unpopulated (blocked on #254 run).

**Status audit (2026-08-13, repo-verified):** PARTIAL. Jaccard 5-gram near-dup + union-find + form-letter flags done and loaded (384/384 rows have coordination_group/is_form_letter; rex/comments/coordination.py). Missing vs body: keyword fingerprinting for known campaigns, temporal clustering, entity-tag cross-reference; stakeholder segmentation defined but unpopulated (blocked on #254 run).
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
api
REST API (FastAPI)
 auth
Authentication and authorization
 bib
Bibliography, Zotero, citations
 ci
CI/CD pipelines and Woodpecker plugins
 cli
CLI commands and UX
 cloud
Cloud provider abstraction (AWS, GCP, Azure, self-hosted)
 config
Configuration and wiring
 data
Data loading, CCLF, BCDA, seeds
 databricks
Databricks jobs and deployment
 docs
Documentation and generated references
 image:api
image:docs
image:mc
image:notebooks
image:zotero
infra
lakehouse
Nessie, Polaris, Trino, Iceberg
 llm
llm module — local RAG over comments + Zotero corpus
 notebooks
marimo notebook errors (auto-filed by nb-watcher/nb-integration)
 packaging
Python packaging, optional deps, build system
 pfs
pipeline
Pipeline execution and validation
 pipeline:ci
pipeline:deploy
pipeline:harden
pipeline:infra-ci
pipeline:rebuild-all
pipeline:release
qpp
quality
Testing, coverage, error handling
 step:build
step:deploy
step:hadolint
step:lint
step:publish
step:scan
step:test
step:validate
styles
Charts, figures, visual theming
 tree
Project directory structure and file organization
No Label
Milestone
No items
No Milestone P30: CMS Rulemaking Comment Analysis — regulations.gov sentiment + coordination detection
Projects
Clear projects
No project
Assignees
Clear assignees
kert renovate-bot
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: homelab/stack#255
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?