zero-slop 2.5.8 → 2.7.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -1,6 +1,6 @@
1
1
  # The Tell Taxonomy
2
2
 
3
- A hundred and five tells in six families, merged from WP:AICATCH (Wikipedia's editor
3
+ A hundred and thirteen tells in six families, merged from WP:AICATCH (Wikipedia's editor
4
4
  catalog, built from thousands of caught instances), the de-slop/stop-slop
5
5
  detector line, petergyang/no-ai-slop, blader/humanizer, the academic
6
6
  lexicon studies (Kobak, Liang, Juzek & Ward), and community taxonomies of
@@ -26,6 +26,8 @@ as weak evidence unless it is generic in context or appears in a cluster. A
26
26
  lone dash, formal sentence, transition, or supported contrast remains a style
27
27
  choice. See `evidence.md` for the study, limitations, and adoption decision.
28
28
 
29
+ Contextual review names six checks explicitly: paragraph-order dependence, unsupported novelty, self-labeling significance, moral-adjective category error, recap-flattery, and wall-of-text reply.
30
+
29
31
  ## 1. Lexical
30
32
 
31
33
  | Tell | Fix |
@@ -76,6 +78,8 @@ choice. See `evidence.md` for the study, limitations, and adoption decision.
76
78
  | Mechanical sentence openings: several consecutive sentences begin with the same subject or frame without building deliberate rhythm | Merge or vary the sentences; preserve purposeful anaphora |
77
79
  | Jargon compression: invented compound terms in place of explanation — "threshold cliff", "length-blind floor", "pinned high forever" | Unpack into the plain explanation once, then a short name only if the document truly reuses it; the fix is unpacking, not a synonym |
78
80
  | Stat pile-up: several datasets or tests crammed into one paragraph with no connective explanation | One test per paragraph, opening with what the test checks in plain words ("The first test checks that the score falls as humans get more involved"), numbers after the plain-language setup |
81
+ | Paragraph-order dependence: prose paragraphs can be shuffled without changing the argument | Rebuild a progression in which each paragraph earns the next; exempt FAQs, reference entries, independent findings, and genuine lists |
82
+ | Wall-of-text reply: an answer hides distinct steps or decisions in one unbroken block | Add only the paragraph breaks or list structure the reader needs; length alone is not the signal |
79
83
 
80
84
  ## 3. Rhetorical
81
85
 
@@ -86,6 +90,9 @@ choice. See `evidence.md` for the study, limitations, and adoption decision.
86
90
  | Manufactured stakes: "in today's fast-paced world", "now more than ever" | Start where the reader needs to start |
87
91
  | Performed candor: "let's be honest", "here's the thing", "truth be told" | State the point |
88
92
  | Rhetorical-question openers: "Ever wondered…?", "What if I told you…?" | The answer, as a statement |
93
+ | Unsupported novelty: "the problem nobody is naming" without a comparison or source | Make the narrower supported claim, or ask for the missing basis |
94
+ | Self-labeling significance: "this matters", "this is important", or "the key insight" substitutes a label for a consequence | State the concrete consequence and let it carry the weight |
95
+ | Moral-adjective category error: a technical choice or metric is called brave, honest, ethical, or courageous without a moral agent or decision | Name the engineering property or trade-off; preserve a real moral judgment when the source supports one |
89
96
  | Throat-clearing: "The uncomfortable truth is", "Let me be clear" | Cut; the claim stands alone |
90
97
  | Emphasis crutches: "Make no mistake", "Let that sink in", "Read that again" | Show the weight with the fact itself |
91
98
  | Meta-commentary: "In this post we'll explore", "Let me walk you through" | Just do it |
@@ -113,6 +120,8 @@ choice. See `evidence.md` for the study, limitations, and adoption decision.
113
120
  | Hyperbole universals: "nothing on earth", "on the planet", "in history", "known to man" | State the actual scope; the honest comparison is smaller and stronger |
114
121
  | Cute meta-taglines and campaign framing: "a meter you can argue with", "the fight against X" as a slogan | Describe the thing; "posts about writing quality" beats a campaign poster. "The fight against" is real usage in history and civic prose — flag the marketing register, not the phrase |
115
122
  | Staccato antithesis: two short balanced sentences, the second landing the twist — "Not perfect. Honest.", "Slop isn't a vibe. It's measurable.", "The draft was cheap. The signal it sent was not." | One plain sentence with the claim; at most one antithesis per piece |
123
+ | Unmarked antithesis: the same figure with no negation marker at all, so the whole "not X, it's Y" family walks past it. Four shapes — bare subject swap ("Llama is open-weights. Dolma releases the data."); isocolon, one verb frame with both arguments swapped ("Open weights let you adapt a model. An open stack lets you adapt the machinery that created it."); the stock closer ("Ai2 argues for a principle. This is what that principle looks like."); unmarked reversal ("No frontier lab had to decide. Thai researchers made that call themselves.") | State the claim once, plainly. The meter now catches the last three (`isocolon-ditransitive`, `this-is-what-looks-like`, `no-x-had-to`); bare subject swap stays a judgment call. **Count them** — one is a device, three in a short piece is the register |
124
+ | Significance scaffolding: a sentence announcing that a point matters instead of delivering it — "Here's the detail that matters:", "This is what that principle looks like when it works." | Delete the announcement and keep the point. Budget: zero |
116
125
  | Extended conceit: a process or abstraction dressed as physical drama — billing ("the bill lands on reputation", "gets billed to a reader"), courtroom ("never allowed to convict"), forensics ("rhythm leaves prints"), machinery ("opens the hood"), recipe ("has four ingredients") | At most one metaphor per piece, then plain language; name the actual mechanism |
117
126
  | Vibe-slang: "just a vibe", "vibe check", "argue with vibes", "has receipts" | The plain word: impression, judgment, evidence |
118
127
  | One-word drama beat: "Fine." dropped between claims as a rhythm device | Cut it or fold it into the sentence it interrupts |
@@ -125,13 +134,28 @@ same costume seen at detection time instead of rewrite time. The scorer
125
134
  catches the mechanical subset (`hired-adversary`, `turns-out-payoff`,
126
135
  `has-receipts`, `hyperbole-universal`, `argue-with-artifact`,
127
136
  `vibe-register`, `where-x-lives`, `billed-conceit`, `on-the-tin`,
128
- `minding-own-business`, `economics-brutal`, `opens-the-hood`, and the
129
- rider-gated "fight against"); epigram cadence, staccato antithesis, most
130
- conceits, jargon compression, and tagline register need the judgment pass,
131
- because their literal forms are legitimate in news, history, crime, and
132
- civic writing. The human-flagged spans that motivated the family live in
137
+ `minding-own-business`, `economics-brutal`, `opens-the-hood`, the
138
+ rider-gated "fight against", and since v2.5.10 — three of the four unmarked
139
+ antithesis shapes: `isocolon-ditransitive`, `this-is-what-looks-like`, and
140
+ `no-x-had-to`. Epigram cadence, marked staccato antithesis, bare subject swap,
141
+ most conceits, jargon compression, and tagline register still need the
142
+ performed-register pass, because their literal forms are legitimate in news,
143
+ history, crime, and civic writing.
144
+
145
+ `isocolon-ditransitive` is worth reading closely, because it marks the boundary
146
+ between what a rule can safely reach and what it cannot. It fires only when the
147
+ **same verb** is repeated in a give-you frame across a sentence break. That
148
+ identity requirement is the whole safety property: rhetorical anaphora repeats
149
+ its frame with a *different* verb every time — "we can not dedicate, we can not
150
+ consecrate, we can not hallow" — so the rule cannot touch it. Relaxing the
151
+ backreference from the verb to the frame was tested and fires on the Gettysburg
152
+ Address, the Federalist, and an ESL engineer's email. Do not relax it.
153
+
154
+ The human-flagged spans that motivated the family live in
133
155
  `data/corpus/performed-register/` — the mechanical half is regression-tested,
134
- the judgment half is the read-aloud pass's fixture list.
156
+ the judgment half is the performed-register pass's fixture list. Files move
157
+ between the two halves in both directions: `verdict-arithmetic.txt` graduated
158
+ from judgment to mechanical in v2.5.10 when a safe rule finally reached it.
135
159
 
136
160
  ## 4. Punctuation & formatting
137
161
 
@@ -153,6 +177,7 @@ the judgment half is the read-aloud pass's fixture list.
153
177
  |---|---|
154
178
  | Assistant voice: "Great question!", "I hope this helps", "I'd be happy to" | Delete |
155
179
  | Reflexive agreement or praise: approving the premise before checking it, flattering the writer, or refusing to take a supported position | Answer the substance first; agree, qualify, or disagree according to the facts |
180
+ | Recap-flattery: a reply opens by praising and paraphrasing the question before answering it | Start with the answer; keep only context the reader actually needs |
156
181
  | Chatbot residue: "Would you like me to…", "Let me know if you'd like…", "my training data" | Delete — it is proof of paste, not style |
157
182
  | Knowledge-cutoff residue: "as of my last update", "not widely documented" | Delete; verify the claim |
158
183
  | Passive or subjectless wording that hides an actor who matters | Name the actor and use the direct verb; keep passive voice when the actor is unknown, irrelevant, or native to the genre |