@@ -0,0 +1,147 @@
1+# Research Notes for `human-writing`
2+
3+This file captures the research basis behind the skill. Keep the
4+main `SKILL.md` practical; keep detailed evidence here.
5+
6+## Wikipedia article and source
7+
8+### Wikipedia: Signs of AI writing
9+Source page:
10+- https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing
11+- Source wikitext: https://en.wikipedia.org/w/index.php?title=Wikipedia:Signs_of_AI_writing&action=raw
12+
13+Key takeaways used in the skill:
14+- The page treats AI tells as **patterns**, not proof. A single word or
15+ one awkward sentence is not enough.
16+- Many strong tells are about **generic significance claims**,
17+ **superficial analysis**, **promotional wording**, **vague
18+ attribution**, and **rigid essay structure**.
19+- It flags repeated "AI vocabulary" clusters such as `additionally`,
20+ `align with`, `delve`, `underscore`, `pivotal`, `vibrant`,
21+ `showcase`, and `tapestry`.
22+- It highlights broader structural habits: rule-of-three phrasing,
23+ overused em dashes, Markdown-heavy output, canned collaborative
24+ phrasing, and generic "challenges / future outlook" conclusions.
25+- It also includes a useful warning section on **ineffective
26+ indicators**: blandness, transition words in isolation, and formal
27+ prose are not reliable proof by themselves.
28+
29+How it shaped the skill:
30+- Focus on removing formulaic phrasing and generic uplift, not on
31+ banning individual words absolutely.
32+- Emphasize specificity, judgment, and natural rhythm over detector
33+ gaming.
34+- Add boundaries so the skill does not encourage false claims of human
35+ authorship.
36+
37+## Research on distinctive AI style
38+
39+### Russell, Karpinska, Iyyer (ACL 2025)
40+Source: https://aclanthology.org/2025.acl-long.267/
41+
42+Why it matters:
43+- Frequent ChatGPT users were strong detectors of AI-generated text and
44+ outperformed many automated detectors.
45+- Their explanations relied not just on word lists, but also on
46+ **formality, originality, and clarity**.
47+
48+How it shaped the skill:
49+- The skill focuses on overall feel and judgment, not only lexical
50+ substitutions.
51+- "Human" writing should sound selective and situated, not just less
52+ detectable.
53+
54+### Juzek and Ward (COLING 2025)
55+Source: https://aclanthology.org/2025.coling-main.426/
56+
57+Why it matters:
58+- Documents lexical overrepresentation in LLM writing, with words such
59+ as `delve`, `intricate`, and `underscore` appearing far more often
60+ after LLM adoption.
61+- Treats this as a measurable linguistic drift, not just a meme.
62+
63+How it shaped the skill:
64+- Include a short watchlist of repeated AI-favorite wording.
65+- Frame the issue as **clusters and repetition**, not one forbidden
66+ token.
67+
68+### Kobak et al. (Science Advances 2025)
69+Source: https://www.science.org/doi/10.1126/sciadv.adt3813
70+
71+Why it matters:
72+- Shows abrupt post-2022 increases in excess vocabulary across more
73+ than 15 million biomedical abstracts.
74+- Reinforces that LLM writing leaves a measurable lexical footprint at
75+ scale.
76+
77+How it shaped the skill:
78+- Prefer plain verbs and concrete nouns over polished but generic
79+ vocabulary.
80+- Warn against abstract noun piles and repetitive stylistic markers.
81+
82+### Rudnicka (Scientific American, 2025)
83+Source: https://www.scientificamerican.com/article/chatgpt-and-gemini-ai-have-uniquely-different-writing-styles
84+
85+Why it matters:
86+- Argues that major chatbots have distinct **idiolects**, much like
87+ humans do.
88+- Implies that AI tells shift over time and differ by model.
89+
90+How it shaped the skill:
91+- Avoid hard-coded, forever bans.
92+- Teach broader habits: specificity, rhythm, audience matching, and
93+ selective judgment.
94+
95+### Saha and Feizi (2025)
96+Source: https://arxiv.org/abs/2502.15666
97+
98+Why it matters:
99+- Detectors often flag even lightly AI-polished human text as AI.
100+- This creates false accusations and shows the limits of detector-first
101+ thinking.
102+
103+How it shaped the skill:
104+- Optimize for better writing, not for beating detectors.
105+- Keep the skill centered on readable, honest prose.
106+
107+## Official style guidance on sounding human without sounding sloppy
108+
109+### Google developer documentation style guide - Voice and tone
110+Source: https://developers.google.com/style/tone
111+
112+Key takeaways used in the skill:
113+- Aim for a voice that is conversational, friendly, respectful, and
114+ natural.
115+- Sound like a **knowledgeable friend**, not a pedant and not a clown.
116+- Avoid buzzwords, placeholder phrases, choppy repetition, and
117+ long-winded sentences.
118+
119+### Digital.gov - Plain Language Web Writing Tips
120+Source: https://digital.gov/resources/plain-language-web-writing-tips
121+
122+Key takeaways used in the skill:
123+- Get to the point quickly.
124+- Use contractions, active voice, familiar words, and short paragraphs.
125+- Put the most important information first.
126+
127+### 18F Content Guide - Be concise
128+Source: https://guides.18f.gov/content-guide/our-approach/be-concise/
129+
130+Key takeaways used in the skill:
131+- Be specific, informative, brisk, and human.
132+- Use contractions and short sentences.
133+- Vary sentence length so writing stays readable without sounding
134+ robotic or clipped.
135+- Avoid adjective-heavy spin and caveat-bloated grammar.
136+
137+## Practical synthesis
138+
139+Across the sources, the same advice keeps showing up:
140+
141+1. Lead with the point.
142+2. Prefer concrete nouns and verbs over abstract uplift.
143+3. Use contractions when natural.
144+4. Vary sentence rhythm.
145+5. Match the audience's register.
146+6. Avoid repeated formulae, hype, and canned summaries.
147+7. Keep clarity and honesty above "sounding human".