paperlint 6.0.0 → 6.2.0

package/presets/venue-profile.schema.json

@@ -137,8 +137,187 @@
       }
     },
     "rules": {
-      "description": "Rules the venue implies, rule id \u2192 ESLint entry (a severity, or [severity, options]). Applied to every paper that extends this preset, before the paper's own rules.",
+      "description": "Rules the venue implies, rule id → ESLint entry (a severity, or [severity, options]). Applied to every paper that extends this preset, before the paper's own rules.",
       "type": "object"
+    },
+    "register": {
+      "description": "The register rules' anchors (`tex/contrast-frames`, `tex/claim-emphasis`, `tex/relation-markers`): accepted papers of the venue, or of its parent conference, each with its body's word count and its count of each measure as paperlint's own counters give them. A measure's band is the anchors' range widened by two Poisson standard deviations at each end (docs/rules/tex/contrast-frames.md). A child preset's block replaces its parent's.",
+      "type": "object",
+      "additionalProperties": false,
+      "required": ["anchors"],
+      "properties": {
+        "anchors": {
+          "type": "array",
+          "minItems": 1,
+          "items": {
+            "type": "object",
+            "additionalProperties": false,
+            "required": [
+              "paper",
+              "words",
+              "contrast_frames",
+              "claim_emphasis",
+              "relation_markers"
+            ],
+            "properties": {
+              "paper": {
+                "description": "The anchor: a directory under fixtures/accepted-papers/ when the paper is there, or how to find it.",
+                "type": "string",
+                "minLength": 1
+              },
+              "words": {
+                "description": "Words of the body, as the register rules count them.",
+                "type": "integer",
+                "minimum": 1
+              },
+              "contrast_frames": {
+                "type": "integer",
+                "minimum": 0
+              },
+              "claim_emphasis": {
+                "type": "integer",
+                "minimum": 0
+              },
+              "relation_markers": {
+                "type": "integer",
+                "minimum": 0
+              }
+            }
+          }
+        }
+      }
+    },
+    "talk": {
+      "description": "What the venue asks a presenter to send, judged by the talk/* rules on the finished files (src/talk-rules.ts). Read only for a paper whose paperlint.json declares `talk`. A child preset's block replaces its parent's whole. Durations in seconds.",
+      "type": "object",
+      "additionalProperties": false,
+      "properties": {
+        "modes": {
+          "description": "The presentation modes the venue allows.",
+          "type": "array",
+          "items": {
+            "type": "string",
+            "enum": ["in-person", "remote-video", "remote-live"]
+          },
+          "uniqueItems": true,
+          "minItems": 1
+        },
+        "artifacts": {
+          "description": "What each mode owes: the files required, and those that may be sent.",
+          "type": "object",
+          "propertyNames": {
+            "type": "string",
+            "enum": ["in-person", "remote-video", "remote-live"]
+          },
+          "additionalProperties": {
+            "type": "object",
+            "additionalProperties": false,
+            "required": ["required"],
+            "properties": {
+              "required": {
+                "type": "array",
+                "items": {
+                  "type": "string",
+                  "enum": [
+                    "video",
+                    "one-slide",
+                    "captions",
+                    "slides-pdf",
+                    "poster"
+                  ]
+                },
+                "uniqueItems": true
+              },
+              "optional": {
+                "type": "array",
+                "items": {
+                  "type": "string",
+                  "enum": [
+                    "video",
+                    "one-slide",
+                    "captions",
+                    "slides-pdf",
+                    "poster"
+                  ]
+                },
+                "uniqueItems": true
+              }
+            }
+          }
+        },
+        "kinds": {
+          "description": "The talk slot per paper kind (the names of format.kinds; the paper's `kind` selects one).",
+          "type": "object",
+          "additionalProperties": {
+            "type": "object",
+            "additionalProperties": false,
+            "required": ["slot_s", "talk_s_max"],
+            "properties": {
+              "slot_s": {
+                "description": "The whole slot, talk and questions. Informational.",
+                "type": "number",
+                "exclusiveMinimum": 0
+              },
+              "talk_s_min": {
+                "description": "The shortest talk the venue asks for (talk/duration-floor).",
+                "type": "number",
+                "minimum": 0
+              },
+              "talk_s_max": {
+                "description": "The longest talk (talk/duration).",
+                "type": "number",
+                "exclusiveMinimum": 0
+              },
+              "qa_s": {
+                "description": "The questions' share. Informational.",
+                "type": "number",
+                "minimum": 0
+              }
+            }
+          }
+        },
+        "video": {
+          "description": "The venue's limits on the video file (talk/video-format).",
+          "type": "object",
+          "additionalProperties": false,
+          "properties": {
+            "container": {
+              "type": "string",
+              "enum": ["mp4"]
+            },
+            "min_height_px": {
+              "description": "The lowest vertical resolution; HD is 720.",
+              "type": "integer",
+              "minimum": 1
+            },
+            "max_bytes": {
+              "type": "integer",
+              "minimum": 1
+            },
+            "captions": {
+              "description": "`required`: a captions file is owed with the video (talk/required-files).",
+              "type": "string",
+              "enum": ["required", "optional"]
+            }
+          }
+        },
+        "one_slide": {
+          "description": "The one-slide image's size in pixels (talk/one-slide-size), when the venue states one.",
+          "type": "object",
+          "additionalProperties": false,
+          "required": ["width_px", "height_px"],
+          "properties": {
+            "width_px": {
+              "type": "integer",
+              "minimum": 1
+            },
+            "height_px": {
+              "type": "integer",
+              "minimum": 1
+            }
+          }
+        }
+      }
     }
   },
   "allOf": [

package/skills/grade-paper-writing/SKILL.md

@@ -4,7 +4,7 @@ description: Use when asking "does this paper read well?" / "is the writing any
 allowed-tools: [Read, Write, Edit, Grep, Glob, Agent, Skill]
 ---
 
-<!-- vigiles:sha256:baf1f69df2502086 compiled from skills/grade-paper-writing/SKILL.md.spec.ts -->
+<!-- vigiles:sha256:03d0377baf71967f compiled from skills/grade-paper-writing/SKILL.md.spec.ts -->
 
 # grade-paper-writing — grade how the paper READS, then fix it sentence by sentence
 
@@ -172,16 +172,41 @@ is what happened.
 3. **For every dimension scoring ≤3, name the specific offending sentence or section** and write the fix —
    not "tighten the prose" but the rewritten sentence, or "move the point from ¶3 to ¶1", or "gloss
    `operation-normalized` in plain words at first use." Fixes must be applyable, not vibes.
-3a. **Grade #10, register distance, against the venue's own papers — not against the exemplars.**
-   Take 2–3 papers accepted at the target venue (or, for a first-edition workshop, at its parent
-   conference) in the same paper type: fetch them from the proceedings or the program page, or use the
-   ones the author supplies. Read the abstract, the introduction and the conclusion of each beside the
-   draft's, and record, for both sides: how each result is owned (*we measured* · a citation · a named
-   population), how often a point is made by contrast (*not X but Y*, *rather than*, *instead of* —
-   the measured difference between this corpus and accepted papers), sentence length and fragments,
-   and whether any sentence is an aphorism or a closing punchline. The
-   score is the distance: 5 = a reviewer could not tell the draft from the reference papers by register;
-   1 = it reads as a different genre. Quote the reference sentence beside each draft sentence you flag.
+3a. **Grade #10, register distance, against the venue's own papers, section by section — not against
+   the exemplars.** The rules count and this step judges; it starts from their numbers, not from a
+   count of its own.
+   - **Take the counts from the rules.** `npx paperlint lint <paper-dir>` reports
+     `tex/contrast-frames`, `tex/claim-emphasis` and `tex/relation-markers` when the venue preset
+     records anchors (AIDC does): each gives the body's rate per 10,000 words, the band, and the
+     anchors' range, and above the band it reports every frame and every claim in bold where it
+     stands. Those locations are the worklist. Do not recount them by grep — a narrower count is
+     gamed by rewording (*, not* → *rather than*), and the rules count every form.
+   - **Take the reference papers from the preset.** Its `register.anchors` names the accepted papers
+     the band comes from (AIDC: five ACSAC papers, all on arXiv under CC licences). Read two or three
+     of the same paper type as LaTeX source (`https://arxiv.org/e-print/<id>`) or as built PDFs. A
+     preset without anchors: fetch 2–3 accepted papers of the venue (or, for a first-edition workshop,
+     of its parent conference) from the proceedings or the program page, or use the ones the author
+     supplies.
+   - **Compare section by section, not the paper as a whole:** abstract, introduction, threat model or
+     background, method, results, limitations, conclusion. For each, put the draft's section beside the
+     same section of each reference paper and record, for both sides: how each result is owned (*we
+     measured* · a citation · a named population); how the relation between neighbouring sentences is
+     named (*because*, *therefore*, *however*, *for example*) or left to infer (a colon, a dash, a short
+     sentence); how often a point is made by what it is not; what is set in bold; and whether any
+     sentence is an aphorism, a fragment or a closing punchline. Quote the reference sentence beside
+     each draft sentence you flag.
+   - **Return concrete rewrites, and every one keeps every number and claim.** For each flagged sentence:
+     the draft sentence → the rewrite → the reference sentence it is modelled on → one line saying that
+     every number, citation and hedge is unchanged and the claim is neither softened nor strengthened.
+     A contrast frame is rewritten by saying what the thing is and naming the relation (*because*,
+     *as a result*), not by switching to another contrast form; a claim in bold loses the bold and
+     gains its owner (*we measured*, `\ref` to the table); a relation left to infer gets its word.
+     Where the frame IS the claim (the paper's thesis sets one mechanism against another), keep it
+     once, in the abstract and the introduction, and say so.
+   - **Score the distance:** 5 = a reviewer could not tell the draft from the reference papers by
+     register, section by section; 1 = it reads as a different genre. After the rewrites, run
+     `npx paperlint lint` again: every register rule inside its band is the floor for a 4, not the
+     score itself.
    If no accepted paper can be fetched or supplied, write `#10: not graded — no reference papers` and
    say which were tried; a register score from memory is the guess this dimension exists to replace.
 4. **Find the paper's three-move opportunities:** what held assumption could open it? what is its single
@@ -353,10 +378,13 @@ changes neither meaning nor register — and never rewrite a cited work's title
 **Signposting is the register, not a tic, and this skill never removes it on style grounds.** Frame
 markers and relation words — *we show*, *this section*, *first … finally*, *in contrast*, *therefore*,
 *however* — are how academic prose tells the reader what kind of claim comes next and how it relates to
-the last one. Their count does not separate a draft from accepted papers (see "Contrast framing"
-below); removing them does, in the wrong direction. Flag a connective only when it asserts a relation
-the two sentences do not have (a *therefore* that does not follow), or when it is empty filler (*it is
-worth noting that*). Never flag one for being academic.
+the last one. Relation words are a floor: `tex/relation-markers` reports a body below the band its
+venue's accepted papers set (AIDC: 25.4 per 10,000 words; the paper reviewers called a blog post stood
+at 19.1, and never wrote *however* once, where every accepted ACSAC paper writes it 6–11 times). Frame
+markers do not separate a draft from accepted papers in either direction (see "Contrast framing"
+below). Flag a connective only when it asserts a relation the two sentences do not have (a *therefore*
+that does not follow), or when it is empty filler (*it is worth noting that*). Never flag one for being
+academic.
 
 **Other markers worth a pass:** nominalisation density (*an honest accounting of what the construction
 costs* — abstract nouns doing the work verbs should do) and statistics chained through a paragraph
@@ -382,14 +410,15 @@ Two separable failures:
 
 ### 1. Contrast framing, and a frame that carries nothing
 
-**What separates this corpus from accepted papers is contrast, not signposting — measure that
-first.** Counted with the same counter on five accepted ACSAC 2024/25 ML-security papers against a
-paper of ours: *"not X but Y"* at 35.5 per 10,000 words in ours against at most 4.9 there (and five
-of their six hits were *"not only … but also"*); *"rather than / instead of"* at 19.9 against at most
-5.4. Every sentence that defines its point by what it is not is a sentence whose point the reader
-must reconstruct. **Rewrite heuristic:** state the thing; move the rejected alternative to its own
-sentence, or drop it if nobody proposed it. Check *instead of · rather than · not … but* first,
-against the same count on the reference papers of dimension #10.
+**What separates this corpus from accepted papers is contrast, not signposting — and a rule counts
+it.** `tex/contrast-frames` counts every form (*X, not Y* · *not X but Y* · *rather than* ·
+*instead of* · *as opposed to*) per 10,000 words against the band the venue preset's anchors set: the
+five accepted ACSAC papers measure 1.3–5.5, AIDC's band is 0–10.4, and the paper reviewers called a blog
+post measured 101 before its rewrite and 28 after it. Every sentence that defines its point by what
+it is not is a sentence whose point the reader must reconstruct. **Rewrite heuristic:** state the
+thing and name the relation; move the rejected alternative to its own sentence, or drop it if nobody
+proposed it. Swapping one form for another (*, not* → *rather than*) moves nothing — the rule counts
+both, and so does a reviewer.
 
 **Frame markers do not separate us from accepted papers, and are not a target in either direction.**
 Hyland's *frame markers* (*this paper · this section · we show · first … finally · in what follows*)
@@ -464,10 +493,13 @@ one did, and it was the worst section in the paper by measured density both time
 
 ### What is NOT mechanizable here
 
-Whether a frame marker carries its claim (*"we claim nothing there"* genuinely scopes one) and
-whether a hedge is honest or defensive. The mechanical leg that does exist: `tex/claim-provenance`
-reports every sentence of the body that holds a number and no owner. Count them, surface them, and leave the verdict to a reader.
-The counter's job is that nobody can say afterwards they did not know.
+Whether a frame marker carries its claim (*"we claim nothing there"* genuinely scopes one), whether a
+hedge is honest or defensive, whether a given contrast frame is the one a reader needs, and whether a
+rewrite kept every claim at its strength. The mechanical legs that do exist: `tex/claim-provenance`
+reports every sentence of the body that holds a number and no owner, and `tex/contrast-frames`,
+`tex/claim-emphasis` and `tex/relation-markers` report a body outside its venue's band. Count them,
+surface them, and leave the verdict to a reader. The counter's job is that nobody can say afterwards
+they did not know.
 
 ## Compose with
 - `harden-paper` — the multi-axis pre-submit gate calls this as its *writing* axis (the one a defect-hunt

package/skills/grade-paper-writing/SKILL.md.spec.ts

@@ -178,16 +178,41 @@ is what happened.
 3. **For every dimension scoring ≤3, name the specific offending sentence or section** and write the fix —
    not "tighten the prose" but the rewritten sentence, or "move the point from ¶3 to ¶1", or "gloss
    \`operation-normalized\` in plain words at first use." Fixes must be applyable, not vibes.
-3a. **Grade #10, register distance, against the venue's own papers — not against the exemplars.**
-   Take 2–3 papers accepted at the target venue (or, for a first-edition workshop, at its parent
-   conference) in the same paper type: fetch them from the proceedings or the program page, or use the
-   ones the author supplies. Read the abstract, the introduction and the conclusion of each beside the
-   draft's, and record, for both sides: how each result is owned (*we measured* · a citation · a named
-   population), how often a point is made by contrast (*not X but Y*, *rather than*, *instead of* —
-   the measured difference between this corpus and accepted papers), sentence length and fragments,
-   and whether any sentence is an aphorism or a closing punchline. The
-   score is the distance: 5 = a reviewer could not tell the draft from the reference papers by register;
-   1 = it reads as a different genre. Quote the reference sentence beside each draft sentence you flag.
+3a. **Grade #10, register distance, against the venue's own papers, section by section — not against
+   the exemplars.** The rules count and this step judges; it starts from their numbers, not from a
+   count of its own.
+   - **Take the counts from the rules.** \`npx paperlint lint <paper-dir>\` reports
+     \`tex/contrast-frames\`, \`tex/claim-emphasis\` and \`tex/relation-markers\` when the venue preset
+     records anchors (AIDC does): each gives the body's rate per 10,000 words, the band, and the
+     anchors' range, and above the band it reports every frame and every claim in bold where it
+     stands. Those locations are the worklist. Do not recount them by grep — a narrower count is
+     gamed by rewording (*, not* → *rather than*), and the rules count every form.
+   - **Take the reference papers from the preset.** Its \`register.anchors\` names the accepted papers
+     the band comes from (AIDC: five ACSAC papers, all on arXiv under CC licences). Read two or three
+     of the same paper type as LaTeX source (\`https://arxiv.org/e-print/<id>\`) or as built PDFs. A
+     preset without anchors: fetch 2–3 accepted papers of the venue (or, for a first-edition workshop,
+     of its parent conference) from the proceedings or the program page, or use the ones the author
+     supplies.
+   - **Compare section by section, not the paper as a whole:** abstract, introduction, threat model or
+     background, method, results, limitations, conclusion. For each, put the draft's section beside the
+     same section of each reference paper and record, for both sides: how each result is owned (*we
+     measured* · a citation · a named population); how the relation between neighbouring sentences is
+     named (*because*, *therefore*, *however*, *for example*) or left to infer (a colon, a dash, a short
+     sentence); how often a point is made by what it is not; what is set in bold; and whether any
+     sentence is an aphorism, a fragment or a closing punchline. Quote the reference sentence beside
+     each draft sentence you flag.
+   - **Return concrete rewrites, and every one keeps every number and claim.** For each flagged sentence:
+     the draft sentence → the rewrite → the reference sentence it is modelled on → one line saying that
+     every number, citation and hedge is unchanged and the claim is neither softened nor strengthened.
+     A contrast frame is rewritten by saying what the thing is and naming the relation (*because*,
+     *as a result*), not by switching to another contrast form; a claim in bold loses the bold and
+     gains its owner (*we measured*, \`\\ref\` to the table); a relation left to infer gets its word.
+     Where the frame IS the claim (the paper's thesis sets one mechanism against another), keep it
+     once, in the abstract and the introduction, and say so.
+   - **Score the distance:** 5 = a reviewer could not tell the draft from the reference papers by
+     register, section by section; 1 = it reads as a different genre. After the rewrites, run
+     \`npx paperlint lint\` again: every register rule inside its band is the floor for a 4, not the
+     score itself.
    If no accepted paper can be fetched or supplied, write \`#10: not graded — no reference papers\` and
    say which were tried; a register score from memory is the guess this dimension exists to replace.
 4. **Find the paper's three-move opportunities:** what held assumption could open it? what is its single
@@ -359,10 +384,13 @@ changes neither meaning nor register — and never rewrite a cited work's title
 **Signposting is the register, not a tic, and this skill never removes it on style grounds.** Frame
 markers and relation words — *we show*, *this section*, *first … finally*, *in contrast*, *therefore*,
 *however* — are how academic prose tells the reader what kind of claim comes next and how it relates to
-the last one. Their count does not separate a draft from accepted papers (see "Contrast framing"
-below); removing them does, in the wrong direction. Flag a connective only when it asserts a relation
-the two sentences do not have (a *therefore* that does not follow), or when it is empty filler (*it is
-worth noting that*). Never flag one for being academic.
+the last one. Relation words are a floor: \`tex/relation-markers\` reports a body below the band its
+venue's accepted papers set (AIDC: 25.4 per 10,000 words; the paper reviewers called a blog post stood
+at 19.1, and never wrote *however* once, where every accepted ACSAC paper writes it 6–11 times). Frame
+markers do not separate a draft from accepted papers in either direction (see "Contrast framing"
+below). Flag a connective only when it asserts a relation the two sentences do not have (a *therefore*
+that does not follow), or when it is empty filler (*it is worth noting that*). Never flag one for being
+academic.
 
 **Other markers worth a pass:** nominalisation density (*an honest accounting of what the construction
 costs* — abstract nouns doing the work verbs should do) and statistics chained through a paragraph
@@ -388,14 +416,15 @@ Two separable failures:
 
 ### 1. Contrast framing, and a frame that carries nothing
 
-**What separates this corpus from accepted papers is contrast, not signposting — measure that
-first.** Counted with the same counter on five accepted ACSAC 2024/25 ML-security papers against a
-paper of ours: *"not X but Y"* at 35.5 per 10,000 words in ours against at most 4.9 there (and five
-of their six hits were *"not only … but also"*); *"rather than / instead of"* at 19.9 against at most
-5.4. Every sentence that defines its point by what it is not is a sentence whose point the reader
-must reconstruct. **Rewrite heuristic:** state the thing; move the rejected alternative to its own
-sentence, or drop it if nobody proposed it. Check *instead of · rather than · not … but* first,
-against the same count on the reference papers of dimension #10.
+**What separates this corpus from accepted papers is contrast, not signposting — and a rule counts
+it.** \`tex/contrast-frames\` counts every form (*X, not Y* · *not X but Y* · *rather than* ·
+*instead of* · *as opposed to*) per 10,000 words against the band the venue preset's anchors set: the
+five accepted ACSAC papers measure 1.3–5.5, AIDC's band is 0–10.4, and the paper reviewers called a blog
+post measured 101 before its rewrite and 28 after it. Every sentence that defines its point by what
+it is not is a sentence whose point the reader must reconstruct. **Rewrite heuristic:** state the
+thing and name the relation; move the rejected alternative to its own sentence, or drop it if nobody
+proposed it. Swapping one form for another (*, not* → *rather than*) moves nothing — the rule counts
+both, and so does a reviewer.
 
 **Frame markers do not separate us from accepted papers, and are not a target in either direction.**
 Hyland's *frame markers* (*this paper · this section · we show · first … finally · in what follows*)
@@ -470,10 +499,13 @@ one did, and it was the worst section in the paper by measured density both time
 
 ### What is NOT mechanizable here
 
-Whether a frame marker carries its claim (*"we claim nothing there"* genuinely scopes one) and
-whether a hedge is honest or defensive. The mechanical leg that does exist: \`tex/claim-provenance\`
-reports every sentence of the body that holds a number and no owner. Count them, surface them, and leave the verdict to a reader.
-The counter's job is that nobody can say afterwards they did not know.
+Whether a frame marker carries its claim (*"we claim nothing there"* genuinely scopes one), whether a
+hedge is honest or defensive, whether a given contrast frame is the one a reader needs, and whether a
+rewrite kept every claim at its strength. The mechanical legs that do exist: \`tex/claim-provenance\`
+reports every sentence of the body that holds a number and no owner, and \`tex/contrast-frames\`,
+\`tex/claim-emphasis\` and \`tex/relation-markers\` report a body outside its venue's band. Count them,
+surface them, and leave the verdict to a reader. The counter's job is that nobody can say afterwards
+they did not know.
 
 ## Compose with
 - \`harden-paper\` — the multi-axis pre-submit gate calls this as its *writing* axis (the one a defect-hunt

package/src/adapters/latex/index.test.ts

@@ -8,6 +8,7 @@ import type * as Ast from "@unified-latex/unified-latex-types";
 import { describe, expect, it } from "vitest";
 import { runText, spanIn, type ProsePiece } from "../../domain/tex-document.ts";
 import {
+  bodyEmphasis,
   bodyProse,
   documentBodyOf,
   documentClassOf,
@@ -470,6 +471,15 @@ describe("bodyProse — run-in headings and list items", () => {
     ).toEqual(["It grows.", "It holds."]);
   });
 
+  it("🔴 braces around a run-in heading change nothing: `{\\textbf{Side-channel eavesdropping:}}` is a heading, left out", () => {
+    // barovox-acsac24, Chapters/09_Related_Works.tex, writes its run-in headings this way.
+    expect(
+      texts(
+        "\\begin{document}\n{\\textbf{Side-channel eavesdropping:}} It has been studied.\n\\end{document}",
+      ),
+    ).toEqual(["It has been studied."]);
+  });
+
   it("the same markup inside a sentence, or without the closing mark, is prose", () => {
     expect(
       texts(
@@ -541,3 +551,84 @@ describe("documentBodyOf — the body of a source that is a document of its own"
     );
   });
 });
+
+describe("bodyEmphasis — phrases set apart inside the body's prose, and where they stand", () => {
+  /** Each phrase as `style/place: text`. */
+  const shape = (src: string): readonly string[] =>
+    bodyEmphasis(parseLatex(src)).map(
+      (e) => `${e.style}/${e.place}: ${e.text}`,
+    );
+
+  it("🔴 a bold phrase inside a sentence is inline; one opening a paragraph or an item is a label (opening)", () => {
+    expect(
+      shape(
+        "\\begin{document}\nWe find that \\textbf{the guards react to the word}.\n\n\\textbf{Varying the volume}. We vary it.\n\\begin{itemize}\n\\item \\textbf{A corpus of questions}: we release it.\n\\end{itemize}\n\\end{document}",
+      ),
+    ).toEqual([
+      "bold/inline: the guards react to the word",
+      "bold/opening: Varying the volume",
+      "bold/opening: A corpus of questions",
+    ]);
+  });
+
+  it("🔴 never a heading, a run-in heading, a caption, a table, or anything after the bibliography", () => {
+    expect(
+      shape(
+        "\\begin{document}\n\\section{\\textbf{Big}}\n\\textbf{Threats.} None \\emph{here}.\n\\begin{table}\\caption{\\textbf{C}}\\begin{tabular}{l}\\textbf{cell}\\end{tabular}\\end{table}\n\\bibliography{refs}\nAfter \\textbf{this}.\n\\end{document}",
+      ),
+    ).toEqual(["italic/inline: here"]);
+  });
+
+  it("braces around a label change nothing: `{\\textbf{Filtering}}.` opening a paragraph is a label", () => {
+    // barovox-acsac24, Chapters/08_Discussion.tex.
+    expect(
+      shape(
+        "\\begin{document}\n{\\textbf{Increasing the distance}}. The proximity matters.\n\\end{document}",
+      ),
+    ).toEqual(["bold/opening: Increasing the distance"]);
+  });
+});
+
+describe("bodyEmphasis — each style, and edge cases", () => {
+  /** Each phrase as `style/place: text`. */
+  const shape = (src: string): readonly string[] =>
+    bodyEmphasis(parseLatex(src)).map(
+      (e) => `${e.style}/${e.place}: ${e.text}`,
+    );
+
+  it("each style: \\emph and \\textit italic, \\underline underline, a `{\\bfseries …}` group bold; a footnote's phrase counts", () => {
+    expect(
+      shape(
+        "\\begin{document}\nA \\emph{b} c \\textit{d} e \\underline{f} g {\\bfseries h i} j.\\footnote{In \\textbf{k}.}\n\\end{document}",
+      ),
+    ).toEqual([
+      "italic/inline: b",
+      "italic/inline: d",
+      "underline/inline: f",
+      "bold/inline: h i",
+      "bold/inline: k",
+    ]);
+  });
+
+  it("an empty bold macro sets nothing apart, opening a paragraph or not", () => {
+    expect(
+      shape(
+        "\\begin{document}\n\\textbf{} Opens. We \\textbf{ } go.\n\\end{document}",
+      ),
+    ).toEqual([]);
+  });
+
+  it("an environment opening a paragraph opens nothing for the phrases inside it", () => {
+    expect(
+      shape(
+        "\\begin{document}\n\\begin{quote}\nWe say \\textbf{this}.\n\\end{quote}\n\\end{document}",
+      ),
+    ).toEqual(["bold/inline: this"]);
+  });
+
+  it("the span is the macro with its argument, where the source has it", () => {
+    const src = "\\begin{document}\nWe \\textbf{see it}.\n\\end{document}";
+    const [e] = bodyEmphasis(parseLatex(src));
+    expect(e && src.slice(e.span.start, e.span.end)).toBe("\\textbf{see it}");
+  });
+});

package/src/adapters/latex/index.ts

@@ -29,7 +29,7 @@ import {
 import { documentBodyOf, includesOf } from "./includes.ts";
 import { outlineOf } from "./outline.ts";
 import { parseLatex } from "./parse.ts";
-import { bodyProse } from "./prose.ts";
+import { bodyEmphasis, bodyProse } from "./prose.ts";
 import { renderedRuns } from "./rendered.ts";
 import { layoutOverridesOf } from "./layout.ts";
 
@@ -50,7 +50,7 @@ export {
 export { documentBodyOf, includesOf } from "./includes.ts";
 export { outlineOf } from "./outline.ts";
 export { parseLatex, type ParsedTex } from "./parse.ts";
-export { bodyProse } from "./prose.ts";
+export { bodyEmphasis, bodyProse } from "./prose.ts";
 export { renderedRuns } from "./rendered.ts";
 export { layoutOverridesOf } from "./layout.ts";
 
@@ -60,6 +60,7 @@ export const latexReader: LatexReader = {
   outline: (src) => outlineOf(parseLatex(src)),
   renderedRuns: (src) => renderedRuns(parseLatex(src)),
   bodyProse: (src) => bodyProse(parseLatex(src)),
+  bodyEmphasis: (src) => bodyEmphasis(parseLatex(src)),
   includes: (src) => includesOf(parseLatex(src)),
   documentBody: (src) => documentBodyOf(parseLatex(src)),
   template: parseTemplate,