Files

Christian Nennemann d6beb9c0a0 v0.3.0: Gap-to-Draft pipeline, Living Standards Observatory, blog series

Gap-to-Draft Pipeline (ietf pipeline):
- Context builder assembles ideas, RFC foundations, similar drafts, ecosystem vision
- Generator produces outlines + sections using rich context with Claude
- Quality gates: novelty (embedding similarity), references, format, self-rating
- Family coordinator generates 5-draft ecosystem (AEM/ATD/HITL/AEPB/APAE)
- I-D formatter with proper headers, references, 72-char wrapping

Living Standards Observatory (ietf observatory):
- Source abstraction with IETF + W3C fetchers
- 7-step update pipeline: snapshot, fetch, analyze, embed, ideas, gaps, record
- Static GitHub Pages dashboard (explorer, gap tracker, timeline)
- Weekly CI/CD automation via GitHub Actions

Also includes:
- 361 drafts (expanded from 260 with 6 new keywords), 403 authors, 1,262 ideas, 12 gaps
- Blog series (8 posts planned), reports, arXiv paper figures
- Agent team infrastructure (CLAUDE.md, scripts, dev journal)
- 5 new DB tables, schema migration, ~15 new query methods

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-03-04 00:48:57 +01:00

4.2 KiB

Raw Blame History

Category Co-occurrence Report

Generated 2026-03-03 20:15 UTC — 361 drafts, 318 (88.1%) multi-category

Category Counts

Category	Count	% of Drafts
Data formats/interop	148	41.0%
A2A protocols	136	37.7%
Agent identity/auth	121	33.5%
Autonomous netops	98	27.1%
Policy/governance	93	25.8%
Agent discovery/reg	79	21.9%
ML traffic mgmt	74	20.5%
AI safety/alignment	45	12.5%
Model serving/inference	42	11.6%
Human-agent interaction	30	8.3%
Other AI/agent	26	7.2%

Co-occurrence Matrix

Number of drafts assigned to both categories simultaneously.

	Data	A2A	IdAuth	Auto	Policy	Disc	ML	Safe	Model	Human	Other
Data	148	58	33	24	26	35	19	7	14	14	3
A2A	58	136	43	39	23	51	15	12	9	8	3
IdAuth	33	43	121	7	40	27	2	26	4	6	1
Auto	24	39	7	98	19	21	29	4	11	8	9
Policy	26	23	40	19	93	4	10	27	4	10	2
Disc	35	51	27	21	4	79	6	-	4	2	2
ML	19	15	2	29	10	6	74	3	23	4	4
Safe	7	12	26	4	27	-	3	45	-	5	1
Model	14	9	4	11	4	4	23	-	42	-	3
Human	14	8	6	8	10	2	4	5	-	30	1
Other	3	3	1	9	2	2	4	1	3	1	26

Top 20 Co-occurrences

#	Category A	Category B	Count	Jaccard Index
1	A2A protocols	Data formats/interop	58	0.257
2	A2A protocols	Agent discovery/reg	51	0.311
3	A2A protocols	Agent identity/auth	43	0.201
4	Agent identity/auth	Policy/governance	40	0.230
5	A2A protocols	Autonomous netops	39	0.200
6	Agent discovery/reg	Data formats/interop	35	0.182
7	Agent identity/auth	Data formats/interop	33	0.140
8	Autonomous netops	ML traffic mgmt	29	0.203
9	AI safety/alignment	Policy/governance	27	0.243
10	Agent discovery/reg	Agent identity/auth	27	0.156
11	AI safety/alignment	Agent identity/auth	26	0.186
12	Data formats/interop	Policy/governance	26	0.121
13	Autonomous netops	Data formats/interop	24	0.108
14	ML traffic mgmt	Model serving/inference	23	0.247
15	A2A protocols	Policy/governance	23	0.112
16	Agent discovery/reg	Autonomous netops	21	0.135
17	Autonomous netops	Policy/governance	19	0.110
18	Data formats/interop	ML traffic mgmt	19	0.094
19	A2A protocols	ML traffic mgmt	15	0.077
20	Data formats/interop	Model serving/inference	14	0.080

AI Safety/Alignment Coupling Analysis (45 drafts)

Is AI safety structurally isolated from other categories?

Co-occurring Category	Count	% of Safety Drafts	Jaccard
Policy/governance	27	60.0%	0.243
Agent identity/auth	26	57.8%	0.186
A2A protocols	12	26.7%	0.071
Data formats/interop	7	15.6%	0.038
Human-agent interaction	5	11.1%	0.071
Autonomous netops	4	8.9%	0.029
ML traffic mgmt	3	6.7%	0.026
Other AI/agent	1	2.2%	0.014

Verdict: AI safety drafts have 85 co-occurrence links across 8 categories (1.9 avg links per safety draft). Safety is well-coupled with other categories, particularly policy/governance and identity/auth.

Category Clusters

Groups of categories that form natural clusters based on co-occurrence.

A2A protocols clusters with: Agent discovery/reg (lift 1.7x)
Agent identity/auth clusters with: AI safety/alignment (lift 1.7x)
Policy/governance clusters with: AI safety/alignment (lift 2.3x)
Agent discovery/reg clusters with: A2A protocols (lift 1.7x)
ML traffic mgmt clusters with: Model serving/inference (lift 2.7x)
AI safety/alignment clusters with: Policy/governance (lift 2.3x), Agent identity/auth (lift 1.7x)
Model serving/inference clusters with: ML traffic mgmt (lift 2.7x)

4.2 KiB Raw Blame History