Audit: QRS - Cruciferous Vegetables for Health & Longevity

Audit conducted on 03/09/2026 04:08 using AI4L / Opus 5

Iterations

Summary

Items	Count
Total	93
Passed	83
Failed	0
N/A	10
Pass Rate	100.00%

• Total = Passed + Failed + N/A
• Pass Rate = Passed / (Passed + Failed) × 100
• N/A items are excluded from the pass rate calculation

---

1. General Rules

#	Description	Result	Comments
1.1	Every claim, magnitude, label, recommendation, and statement in the QRS is literally supported by content in the source ER.	🟢	Spot-checked every populated span: protocol values (3–5 servings weekly, 300 g/day, 30–60 g/day 3-day sprouts, 20–60 mg sulforaphane potential) map to ER Therapeutic Protocol lines 357–361; all 10 monitoring rows and targets map to the ER biomarker table lines 452–461; time-to-effect values map to ER line 420.
1.2	Where the ER uses cautious phrasing (“not formally studied”, “None documented in human trials to date”, “theoretical concern”, “data are limited”), the QRS uses the same phrasing.	🟢	The one place the ER declines to set a value — urinary isothiocyanate excretion, “No established target exists” (ER line 461) — is carried as “None established; change from own baseline” (QRS line 753). No ER hedge is dropped or replaced by a firmer formulation.
1.3	The QRS never strengthens an ER claim (e.g., “not formally studied” → “not required”) or softens one (e.g., “do not use during pregnancy” → “use with caution during pregnancy”).	🟢	Radioactive iodine remains an absolute-gate item under Contraindications (QRS line 570), matching ER line 323; raw sprouts remain a hard avoid for pregnancy/over-65/under-5/immunocompromised (QRS line 571 vs ER line 333). CYP1A2 stays a Medium risk, thyroid and anticoagulation stay Low, matching ER tiers.
1.4	The QRS does not relabel an ER fact under a different decision category. A “Benefit-Modifying Factor” from ER section is not surfaced as a “Caution”; a “Risk-Modifying Factor” is not surfaced as a “Side Effect”; etc.	🟢	Gate items are drawn only from ER Key Interactions & Contraindications (lines 313–335); Benefits from Expected Benefits; Risks from Potential Risks & Side Effects; markers and qualitative items from Monitoring Protocol & Defining Success. No modifying factor is promoted into a gate.
1.5	PubMed IDs, study citations, expert names, clinical trial identifiers (NCT*), and brand names appear in the QRS only if they appear in the source ER for the same fact.	🟢	The QRS carries none: no PMIDs, no NCT identifiers, no Talalay/Fahey/Mithen attribution, no Avmacol or Beneforté brand names, although all appear in the ER.
1.6	The QRS does not introduce new attributions.	🟢	No named source, institution, author or organisation appears anywhere in the QRS body.

2. Focus, Tone & Audience

#	Description	Result	Comments
2.1	The QRS follows the tone of the ER, which is determined by the ER’s own language, phrasing, and framing.	🟢	Measured and deflationary in the same way as the ER conclusion — “Lifespan extension shown only in animals” (QRS line 438) mirrors ER line 493.
2.2	The tone of the QRS is simultaneously expert, accessible, objective, and data-driven, but also empowering and encouraging	🟢	Concrete actionable doses in the Protocol panel and concrete monitoring targets give the reader something to act on, while tiered Benefits/Risks keep the framing objective.
2.3	The QRS reads as a trusted, knowledgeable guide rather than a prescriptive doctor	🟢	Protocol cells describe the approaches used in trials (“Trial dosing 300 g/day…”, QRS line 457) rather than instructing.
2.4	The QRS avoids language that implies medical or clinical advice	🟢	No imperatives to the reader; monitoring targets and cadence are stated as tracked ranges and intervals carried verbatim from ER lines 446–461.
2.5	The QRS “presents information” instead of “providing guidance”, “recommending”, or “advising”	🟢	No instance of “recommend”, “advise”, “should”, or “you should” in the QRS body.
2.6	The QRS never addresses “the reader” directly — it presents evidence, not guidance	🟢	Verified: no second-person pronoun (“you”, “your”, “yours”) appears anywhere in the file.
2.7	The QRS is written in plain language, avoiding unnecessary medical jargon	🟢	Retained technical terms (CYP1A2, glucoraphanin, myrosinase, Brassicaceae) have no plain-language equivalent and are all carried from the ER; the acronyms HbA1c, ALT and INR are each expanded at their marker row before reuse in the cadence line.
2.8	Information is presented in a concise and very compact manner	🟢	Every gate item, benefit and risk is a bare noun phrase; monitoring “Why” cells run 3–6 words.
2.9	It DOES NOT address the reader directly	🟢	Confirmed by the same second-person scan as 2.6; also no vocative or imperative constructions.
2.10	The target audience is health- and longevity-oriented adults who are risk-aware, proactive, and actively seeking to optimize health or apply the intervention under review.	🟢	The sheet assumes a reader who will run a 10-marker panel and titrate a 300 g/day intake — a proactive optimiser, not a casual reader.
2.11	The target audience is willing to employ lifestyle and behavioral changes as well as follow protocols that may be inconvenient, costly, or require effort.	🟢	Home sprouting with twice-daily rinsing (QRS line 470) and a quarterly-to-annual biomarker cadence (QRS lines 765–767) both presuppose effort.
2.12	The document is NOT written for the general population, who are unwilling to employ lifestyle and behavioral changes or follow protocols that may be inconvenient, costly, or require effort.	🟢	Functional-range targets (HbA1c 4.8–5.4%, ALT below 25/20 U/L) sit well below conventional cut-offs and are meaningful only to an optimising audience.
2.13	Framing, takeaways, and risk/benefit weighting throughout the document reflect this audience, including where an intervention’s signal for the average person differs from its signal for this audience.	🟢	At-a-glance states plainly that lifespan extension is animal-only and that the human wins are modest, which is the honest signal for a longevity-oriented reader; the CYP1A2 and raw-sprout hazards are given gate-level prominence.
2.14	The document’s own voice frames usage in longevity terms, not “anti-aging” (e.g., “anti-aging clinics”, “anti-aging community”, “anti-aging medicine”). Proper names that contain “anti-aging” (e.g., “American Academy of Anti-Aging Medicine”) are quoted verbatim.	🟢	“anti-aging” does not occur; the title and header use “Health & Longevity”.
2.15	The document’s own voice uses formal clinical and scientific terminology, not colloquial or consumer-grade language (e.g., “oral medication” not “pill(s)”; “injection” not “shot”; “adverse event” not “bad reaction”). Direct quotes from sources are exempt.	🟢	Body sections use “gastrointestinal intolerance”, “destabilised anticoagulation”, “alanine aminotransferase”. The plainer register in At-A-Glance (“medicines wearing off faster”) is required there by item 7.4 and mirrors the ER conclusion’s own wording.

3. Template Integrity

#	Description	Result	Comments
3.1	The following labels and headings on the QRS are fixed and not modified: Card and section headings: “Protocol”, “Time to effect”, “Benefits”, “Risk & Side Effects”, “Monitoring”, “Qualitative Assessment”; Gate headings: “Contraindications”, “Key Interactions”; Tier labels: “High”, “Medium”, “Low”, “Speculative”; Table column headers in Monitoring: “Marker”, “Target”, “Why”	🟢	All present and byte-identical to the template: lines 446, 489, 537, 602, 630, 774 (card/section), 567 and 580 (gates), 540/544/550/556 and 606/611/615/621 (tiers), 634–636 (table headers).
3.2	All “…” from the [qrs_template] are present in the the QRS.	🟢	Extracted both var sets and compared: every one of the 38 template names is present, with the indexed placeholders correctly expanded (marker_#* → marker_1..10*, qualitative_item_# → qualitative_item_1..5). No template span is missing and no unknown span was invented.
3.3	Spans that are not addressed in a checklist item are left unchanged	🟢	A full line diff of the QRS against [qrs_template] returns only the frontmatter fill-in, the three appended frontmatter keys, and the variable substitutions themselves — no CSS, no structural markup, no comment and no website= span was altered.

4. Formatting

#	Description	Result	Comments
4.1	When the source ER section is empty, the QRS uses the ER’s own empty-state phrasing verbatim. Typical phrasings are “None documented in human trials to date” and “Not formally studied”	N/A	No ER section feeding the QRS is empty: Expected Benefits, Potential Risks & Side Effects, Key Interactions & Contraindications, Therapeutic Protocol and Monitoring Protocol & Defining Success are all populated, and all four evidence tiers carry items in both Benefits and Risks.
4.2	Where the ER presents a bulleted item as “Label: content”, the QRS uses the ER’s bold label verbatim as the cell or row label.	🟢	The three protocol labels are verbatim ER bold labels — “Whole-food baseline”, “Broccoli sprout protocol”, “Standardised extract protocol” (QRS lines 450, 463, 476 vs ER lines 357, 359, 361). Monitoring row labels reproduce the ER biomarker column verbatim.
4.3	Labels are not paraphrased, abbreviated, or invented.	🟢	No invented label; all ten marker names match the ER table cell text character-for-character, including “Glycated haemoglobin (HbA1c)” and “International normalised ratio (INR)”.
4.4	The QRS DOES NOT use emoji indicators (no 🟩, 🟥, 🟨, etc.). Color and emphasis are conveyed through CSS and bold labels.	🟢	Zero emoji characters in the file; the ER’s 🟩/🟥/🟨 tier markers and ⚠️ Conflicted flags were correctly dropped, with tiering carried by the bold “High:”/”Medium:”/”Low:”/”Speculative:” labels and the card CSS.
4.5	The QRS is designed to render on one A4 page. Any section that has more content in the ER than fits the per-section budget is condensed by the LLM, not extended onto a second page.	🟢	Condensation is applied throughout rather than content being spilled: benefit and risk headings are reduced to bare noun phrases, gate parentheticals are trimmed to 2–3 named examples, monitoring “Why” cells to 3–6 words, and the four-paragraph ER monitoring narrative to a four-sentence cadence line. No section was appended beyond the template’s single-sheet structure.

---

5. Metadata

#	Description	Result	Comments
5.1	The metadata is placed inside a single HTML comment that is the first element after “<!doctype html>” and before any other comment, head, or body content.	🟢	The comment opens at line 2, immediately after <!doctype html> on line 1, and closes at line 14 before the template comment on line 16.
5.2	Inside that HTML comment the YAML block is delimited by a line “—” opening and a line “—” closing. Text before the opening “—” is permitted but is not parsed as YAML.	🟢	Opening --- at line 3, closing --- at line 13; the preceding descriptive line “QRS — Metadata (invisible, parsed by audit tooling)” sits before the opener as permitted.
5.3	The metadata is not visible in any rendered view of the QRS and is not surfaced by any other element on the sheet.	🟢	It is inside an HTML comment and therefore not rendered; none of its values is echoed in the body except through the separately specified header spans.
5.4	All frontmatter values are trimmed: no leading or trailing whitespace, no surrounding quotes unless the value contains a colon, bracket, or leading special character that requires YAML quoting.	🟢	Only duration: "00:03" is quoted, and it must be because the value contains a colon; all other values are bare and untrimmed of nothing.
5.5	The filename of the source ER is stated as “er_filename: [er_filename]”	🟢	Line 4: er_filename: cruciferous_vegetables_2026-0903-0002_Opus_ER.md, matching the ER’s own filename frontmatter key.
5.6	Version of the QRS.md file used to create the document is stated as “qrs_prompt_version: [Version of QRS.md]”	🟢	Line 5: qrs_prompt_version: 26.7.02, matching the version badge at the head of QRS.md.
5.7	Creation date and time of the document is stated as “qrs_creation_date: [YYYY-MMDD-HHMM]” (e.g., 2026-0501-1430)	🟢	Line 6: qrs_creation_date: 2026-0903-0324 — correct YYYY-MMDD-HHMM shape.
5.8	The nickname of the AI used to create the document is stated as “qrs_creator_ai_nickname: [qrs_creator_ai_nickname]”	🟢	Line 7: qrs_creator_ai_nickname: Opus.
5.9	The nickname of the AI is just a single word model name without version, etc. (e.g., Opus, Sonnet, Grok, Gemini, ChatGPT)	🟢	“Opus” — one word, no version, no qualifier.
5.10	The full name of the AI used to create the document is stated as “qrs_creator_ai_fullname: [qrs_creator_ai_fullname]”	🟢	Line 8: qrs_creator_ai_fullname: Opus 5.
5.11	The full name of the AI consists of the [qrs_creator_ai_nickname] and the model version number and no additional qualifier (e.g., Opus 4.6, Sonnet 3.2, Grok 4.5, Gemini 3.1, ChatGPT 5.4)	🟢	“Opus 5” = nickname plus version, no context-window or tier qualifier appended.
5.12	The filename of the document is stated as “qrs_filename: [filename of this document]”	🟢	Line 9: qrs_filename: cruciferous_vegetables_2026-0903-0002_Opus_QRS.html, matching the file on disk.
5.13	All frontmatter values are trimmed: no leading or trailing whitespace, no surrounding quotes unless the value contains a colon, bracket, or leading special character that requires YAML quoting.	🟢	Re-verified across all nine keys including the three appended ones (duration, git_user, git_issue): no stray whitespace, and the single quoted value is quoted for a colon.

6. Page Title & Header

#	Description	Result	Comments
6.1	[page_title] is set to the [canonical_topic] of the ER frontmatter followed by “ - Quick Reference Sheet” (e.g., “Intervention - Quick Reference Sheet”). The [canonical_topic] is HTML-entity-encoded as needed (e.g., & for &)	🟢	Line 22: Cruciferous Vegetables for Health & Longevity - Quick Reference Sheet; the ampersand in the ER canonical_topic is correctly entity-encoded.
6.2	[header_topic] is set to the [canonical_topic] of the ER frontmatter, with HTML entities encoded as needed (e.g., & for &)	🟢	Line 417: Cruciferous Vegetables for Health & Longevity, matching ER frontmatter line 8 with the ampersand encoded.
6.3	[header_subline_date] is set to [qrs_creation_date reformatted as MM/DD/YYYY]	🟢	Line 421: 09/03/2026, the correct MM/DD/YYYY rendering of 2026-0903-0324.
6.4	[header_subline_model] is set to [qrs_creator_ai_fullname]	🟢	Line 425: Opus 5, matching the qrs_creator_ai_fullname frontmatter value exactly.
6.5	No additional header content appears: no badge, version stamp, AKA / alternate names line, source-AI attribution, audit date, or QRS variant marker.	🟢	The header holds only the title and the template subline; the ER’s five alternate names (Brassica Vegetables, Brassicas, Cruciferae, Cole Crops, Mustard Family Vegetables) were correctly not carried over, and no badge or audit stamp was added.

7. At-A-Glance Section

#	Description	Result	Comments
7.1	[at_a_glance] is dense, execution-oriented summary of the ER Conclusion section	🟢	Each of its four sentences tracks one movement of the ER conclusion (lines 491–495): the mechanism, the strongest human findings, the drawbacks, and the animal-only lifespan result.
7.2	[at_a_glance] is no longer than 60 words	🟢	56 words, counted programmatically on the extracted span text.
7.3	Every fact in [at_a_glance] is supported by a distinct passage in the ER.	🟢	“switch on the body’s own defensive enzymes” ← ER line 491; “small improvements in blood sugar control and a fall in blood pressure over two weeks” ← ER line 493; “digestive discomfort at large portions, some medicines wearing off faster” ← ER line 495; “Lifespan extension shown only in animals” ← ER line 493.
7.4	It DOES NOT use acronyms or technical classifications that require specialist knowledge, uses plain-language terms instead	🟢	No acronym appears. Technical vocabulary is deliberately rendered plainly — “sulfur compounds” for isothiocyanates, “the body’s own defensive enzymes” for Nrf2-driven phase II induction, “some medicines wearing off faster” for CYP1A2 induction.
7.5	It DOES NOT cite specific trials (names, years, sample sizes, p-values)	🟢	No trial name, author, year, enrolment figure or p-value; “two weeks” is a duration carried from the conclusion, not a trial citation.
7.6	It DOES NOT cite effect sizes, relative risks, or statistical results	🟢	No mmHg, mmol/L, hazard ratio, odds ratio or confidence interval, although all are available in the ER magnitude lines.

8. Contraindications

#	Description	Result	Comments
8.1	The section is derived from the ER Key Interactions & Contraindications section	🟢	All four items trace to that section — the radioactive-iodine bullet (ER line 323) and the three “Populations who should avoid” bullets (ER lines 333–335).
8.2	[stop_items] represent the Contraindications from the ER	🟢	Complete and exclusive: the ER’s one absolute contraindication plus its three avoid-populations, with nothing merely cautionary promoted into the stop gate.
8.3	Individual [stop_items] are formatted as <li></li>	🟢	Four discrete <li> elements at QRS lines 570–575, all inside the stop_items span.
8.4	Items are as concise as possible. No trailing explanations, no elaborations, no mechanistic rationale, no attributions, no citations, no study details. No content after an em-dash, en-dash, or hyphen-dash (e.g., “— dose reduction required”, “— reduced efficacy”) — these trailing clauses are stripped. Just the key fact.	🟢	The ER’s em-dash clause on the raw-sprout bullet (“— including solid-organ transplant recipients … absolute neutrophil count below 1.0 × 10⁹/L”, ER line 333) is stripped, as is the EU-allergen rationale on the mustard bullet (ER line 335) and the thiocyanate mechanism on the radioiodine bullet (ER line 323). No dash-trailing clause survives.
8.5	Parenthetical qualifiers from the ER bullet — time windows, severity classes, threshold values, clinical staging — ARE preserved as part of the item, kept as concise as possible (shortened or trimmed where needed to fit the one-page budget, but never dropped entirely).	🟢	The decisive qualifiers all survive: the “(low-iodine preparation window)” time window, the “(urinary iodine below 20 µg/L)” threshold, the “(Brassicaceae)” family qualifier, and the four age/status classes on the raw-sprout item.
8.6	When the ER uses ranking notation inside parens (e.g., “>” for severity ordering) that depends on an explanatory phrase to interpret, normalize the items to a plain comma-separated list rather than carrying through the bare symbol.	N/A	The ER’s Key Interactions & Contraindications section uses no ranking or ordering notation inside parentheses; every parenthetical is a plain example list or a threshold value.
8.7	The section is left empty ONLY IF the ER’s Key Interactions & Contraindications section identifies no population, condition, or scenario for which the intervention should be avoided, deferred, or used only under specialist supervision.	🟢	The section is populated, which is correct — the ER names both an absolute contraindication and three avoid-populations.
8.8	If the section is left empty, an HTML comment inside the [stop_items] span records the ER basis for the absence, naming or quoting the ER text relied on. E.g.	N/A	The section is not empty, so the empty-state comment requirement does not arise.

9. Key Interactions

#	Description	Result	Comments
9.1	The section is derived from the ER Key Interactions & Contraindications section	🟢	All eight items trace to ER lines 313–329.
9.2	[caution_items] represent the Key Interactions from the ER, excluding any that are already listed as Contraindications	🟢	The ER lists nine interaction bullets; all eight non-contraindication bullets are carried, and the ninth (radioactive iodine, ER line 323) is correctly routed to the Contraindications gate instead of being duplicated here.
9.3	Individual [caution_items] are formatted as <li></li>	🟢	Eight discrete <li> elements at QRS lines 583–592, all inside the caution_items span.
9.4	Items are as concise as possible. No trailing explanations, no elaborations, no mechanistic rationale, no attributions, no citations, no study details. No content after an em-dash, en-dash, or hyphen-dash (e.g., “— dose reduction required”, “— reduced efficacy”) — these trailing clauses are stripped. Just the key fact.	🟢	Every ER action verdict and mechanism sentence is stripped: “Caution, not avoidance”, “Induction of 20–40% can push plasma levels below effect”, “Sulforaphane lowers hepatic glucose output by a route resembling metformin’s”, and “Caution pending oncologist input” are all absent. Each item is reduced to the drug or exposure class alone.
9.5	Parenthetical qualifiers from the ER bullet — example drug lists, time windows, severity classes, threshold values, clinical staging — ARE preserved as part of the item, kept as concise as possible (shortened or trimmed where needed to fit the one-page budget, but never dropped entirely).	🟢	Every ER parenthetical is retained in trimmed form rather than dropped: warfarin/phenprocoumon from three; theophylline, clozapine, tizanidine from six; methimazole from two; metformin, sulfonylureas from four; nitrate, garlic, magnesium from four; and both caffeine and paracetamol keep their “(dietary and over-the-counter tablets)” / “(over-the-counter)” qualifiers in full. The “with a narrow margin” severity qualifier on CYP1A2 substrates is also preserved.
9.6	When the ER uses ranking notation inside parens (e.g., “>” for severity ordering) that depends on an explanatory phrase to interpret, normalize the items to a plain comma-separated list rather than carrying through the bare symbol.	N/A	No ranking notation appears in any ER interaction parenthetical; all are already plain comma-separated example lists.
9.7	The section is left empty ONLY IF the ER’s Key Interactions & Contraindications section identifies no interaction, additive effect, or exposure that changes how the intervention is used.	🟢	The section is populated, which is correct — the ER documents nine such interactions, including two explicitly additive ones.
9.8	If the section is left empty, an HTML comment inside the [caution_items] span records the ER basis for the absence, naming or quoting the ER text relied on. E.g.	N/A	The section is not empty, so the empty-state comment requirement does not arise.

10. Protocol

#	Description	Result	Comments
10.1	The section is derived from the ER Protocol section	🟢	All three cells derive from the ER Therapeutic Protocol bullets at lines 357, 359 and 361.
10.2	The three sets of [action] items cover the three most important actionable implementation aspects from the ER Protocol section	🟢	The ER’s sixteen protocol bullets reduce to three delivery routes with an actual dose attached — whole food, home-sprouted broccoli, standardised extract — and those are exactly the three selected. The remaining bullets (chop-and-wait, mustard-seed rescue, half-life, split dosing, genotype, microbiome, sex, age, baseline) are refinements of those three rather than independent implementation aspects.
10.3	If less that three distinct actionable implementation aspects are mentioned in the ER the unused sets are left empty and made invisible, not filled with placeholder text or empty-state phrasing.	N/A	The ER supplies three or more distinct actionable aspects and all three sets are used, so the empty-set rule does not apply.
10.4	All used [action_#label], [action#value], [action#_sub] items are filled with meaningful content derived from the ER Protocol section.	🟢	All nine spans carry substantive ER-derived content: labels verbatim from the ER bold labels, values carrying real doses (3–5 servings weekly; 30–60 g/day fresh 3-day sprouts; 20–60 mg sulforaphane potential daily), and subs carrying the trial dose, the sprout handling requirement and the myrosinase condition. No placeholder survives.

11. Time to Effect

#	Description	Result	Comments
11.1	The three sets of [time] items cover the three most important time-to-effect aspects from the ER	🟢	ER line 420 lists six horizons; the three selected — glucose, blood pressure, liver enzymes — are the three that attach to a graded clinical benefit. The two omitted short horizons (enzyme induction within 24 hours, gut-flora conversion within days) are mechanistic biomarkers, and the omitted long one (cancer, decade-scale) is not actionable on a reference sheet.
11.2	The sets are picked and ordered by the magnitude of the related benefit	🟢	Correct descending order: glucose maps to the sole High-tier benefit (ER line 153), blood pressure to the first-listed Medium benefit (ER line 161), liver enzymes to the last-listed Medium benefit (ER line 179).
11.3	If less that three distinct time-to-effect aspects are mentioned in the ER the unused sets are left empty and made invisible, not filled with placeholder text or empty-state phrasing.	N/A	The ER supplies six time-to-effect horizons and all three sets are used, so the empty-set rule does not apply.
11.4	All used [time_#label], [time#value], [time#_sub] items are filled with meaningful content derived from the ER.	🟢	All nine spans are substantive: values “Twelve weeks”, “Two weeks”, “Two months” match ER line 420 exactly, and each sub adds the ER’s own population context — “Largest where glucose is dysregulated” (ER line 155/234), “24-hour systolic in older adults” (ER line 163), “In fatty liver disease” (ER line 181).
11.5	If the ER does not provide any information on time to effect, the section is removed completely from the Protocol Panel	N/A	The ER provides an explicit “Time to effect” bullet (line 420), so the removal condition is not met and the section is correctly retained.

12. Benefits

#	Description	Result	Comments
12.1	The section is derived from the ER Expected Benefits section	🟢	Every listed benefit corresponds to an #### heading under ER Expected Benefits (lines 151–225), in the ER’s own tier and order.
12.2	Key variables are [benefits_high], [benefits_medium], [benefits_low], [benefits_speculative]	🟢	All four spans present and populated at QRS lines 539, 542, 548 and 555.
12.3	Items are as concise as possible. No explanations, no elaborations, no effect sizes, no qualifiers, no attributions, no citations, no study details, no mechanistic explanations, etc. Just the key fact.	🟢	Each of the twelve benefits is a bare noun phrase. The ER’s magnitude lines — hazard ratio 0.78, the 2.5 mmHg systolic fall, the 63.2% mercapturic-acid rise, the 34% behaviour-scale change — are all absent, as are the trial descriptions.
12.4	Parenthetical content — including effect sizes, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parentheses appear in any of the four benefit spans; the ER’s “⚠️ Conflicted” flags on glycaemic control, Helicobacter pylori and autism are also correctly dropped as tier-redundant qualifiers.
12.5	If no items of a specific sub-section (high, medium, low, speculative) are present the respective is set to “display=none”, not filled with “None documented in human trials to date” or similar empty-state phrasing.	N/A	All four ER benefit tiers carry at least one item (1 High, 4 Medium, 5 Low, 2 Speculative), so no span needed hiding.

13. Risks

#	Description	Result	Comments
13.1	The section is derived from the ER Potential Risks & Side Effects section	🟢	All seven risks correspond to #### headings under ER lines 249–293, in the ER’s own tiers.
13.2	Key variables are [risks_high], [risks_medium], [risks_low], [risks_speculative]	🟢	All four spans present and populated at QRS lines 604, 610, 613 and 619.
13.3	Items are as concise as possible. No explanations, no elaborations, no effect sizes, no qualifiers, no attributions, no citations, no study details, no mechanistic explanations, etc. Just the key fact.	🟢	Each risk is a bare noun phrase; the ER’s 20–40% CYP1A2 induction figure, the 150 µg/day vitamin K threshold, the raffinose-fermentation mechanism and the myxedema case report are all absent.
13.4	Parenthetical content — including frequencies, severity grades, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parentheses appear in any of the four risk spans; the three “⚠️ Conflicted” flags carried by the ER risk headings are correctly dropped.
13.5	If no items of a specific sub-section (high, medium, low, speculative) are present the respective is set to “display=none”, not filled with “None documented in human trials to date” or similar empty-state phrasing.	N/A	All four ER risk tiers carry at least one item (2 High, 1 Medium, 2 Low, 2 Speculative), so no span needed hiding.

14. Monitoring

#	Description	Result	Comments
14.1	The section is derived from the ER Monitoring section	🟢	The table reproduces the ER Monitoring Protocol & Defining Success biomarker table (lines 450–461); the “Why” cells are condensed from the ER’s “Why Measure It?” column and the ER’s fourth “Context/Notes” column is correctly not carried.
14.2	All measurable/quantifiable biomarkers from the Monitoring section are listed	🟢	All ten ER rows are present in ER order: thyroid-stimulating hormone, free thyroxine, urinary iodine concentration, glycated haemoglobin, fasting glucose, home systolic blood pressure, high-sensitivity C-reactive protein, alanine aminotransferase, international normalised ratio, urinary isothiocyanate excretion. Targets match the ER exactly, including the sex-split ALT thresholds and the INR’s “own prescribed target, typically 2.0–3.0”.
14.3	[monitoring_cadence] is populated with the monitoring cadence/frequency derived from the ER Monitoring section. It is not left with placeholder text or empty.	🟢	Populated at QRS lines 764–768 and faithful to ER line 448: blood pressure at 2 and 4 weeks then quarterly; HbA1c and liver panel at 3 and 6 months then 6–12 monthly; thyroid at 3 months and annually where iodine is low or raw intake high; INR 1–2 weeks after a sustained change.

15. Qualitative Assessment

#	Description	Result	Comments
15.1	The section is derived from the ER Monitoring section	🟢	All five items come from the qualitative-markers list at ER lines 465–469, which sits inside Monitoring Protocol & Defining Success.
15.2	All subjective/qualitative biomarkers from the Monitoring section are listed	🟢	All five are carried, none omitted: digestive tolerance, palatability and adherence, perceived caffeine potency, energy and post-meal alertness, and sensitivity to the sulfur taste — each keeping the ER’s own explanatory clause in condensed form.

Issues 03/09/2026 04:08

Pass rate 100.00%. No issues found.

Issues 03/09/2026 03:59

1. 4.3 — Qualitative label paraphrased: qualitative_item_5 (line 801) reads “Sulfur-taste sensitivity”, paraphrasing the ER’s own label “Sensitivity to the sulfur taste” (ER line 469).

Fixes 03/09/2026 03:59

1. 4.3 — Qualitative label restored verbatim: Changed qualitative_item_5 from “Sulfur-taste sensitivity” to the ER’s own label “Sensitivity to the sulfur taste”.

Issues 03/09/2026 03:51

1. 4.5 — QRS exceeds one A4 page: The sheet’s estimated rendered height is roughly twice the A4 print budget; the Monitoring card (lines 637–793), the eight-item Key Interactions gate (lines 584–599), the Protocol and time-to-effect sub-cells (lines 456–531) and the Benefits “Low” item (lines 550–556) all carry text that wraps to two or three lines where one would do.

Fixes 03/09/2026 03:51

1. 4.5 — Monitoring Why/Target cells condensed: Shortened eight biomarker cells so each row wraps to fewer lines, e.g. marker_2_why from “Confirms whether a raised thyroid-stimulating hormone reflects real hormone shortfall” to “Confirms a real hormone shortfall” and marker_10_target from “No established target exists; change from the individual’s own baseline” to “None established; change from own baseline”.
2. 4.5 — Monitoring cadence shortened: Rewrote the cadence paragraph to two lines, abbreviating “Glycated haemoglobin” to “HbA1c”, “every 6–12 months” to “6–12 monthly” and “Anticoagulation” to “INR”.
3. 4.5 — Key Interaction drug lists trimmed: Trimmed the parenthetical example drugs in five caution items (per item 9.5’s “shortened or trimmed where needed to fit the one-page budget”), e.g. the CYP1A2 list from six named drugs to three, dropping four wrapped lines from the gate.
4. 4.5 — Protocol and time-to-effect sub-cells condensed: Cut all three action sub-cells and all three time sub-cells to their load-bearing content, e.g. action_3_sub from “Commercial forms delivering a defined glucoraphanin dose with active myrosinase” to “Defined glucoraphanin dose with active myrosinase”.
5. 4.5 — Benefits Low and Speculative tiers tightened: Removed redundant modifiers (“airborne and dietary”, “circulating”, “abdominal”, “age-related”) so the Low item drops from three lines to two and the Speculative item to one.

Issues 03/09/2026 03:44

1. 1.3 — Hedge dropped from genotype claim: qualitative_item_5 (line 825) states “strong aversion tracks genotype”, dropping the ER’s hedge at line 469, “strong aversion often tracks genotype”, which strengthens a probabilistic claim into a categorical one.

Fixes 03/09/2026 03:44

1. 1.3 — Genotype hedge restored: Changed qualitative_item_5 from “strong aversion tracks genotype” to “strong aversion often tracks genotype”, matching the ER’s hedged wording at line 469.

Issues 03/09/2026 03:36

1. 4.5 — Free-text spans not condensed: [monitoring_cadence] (lines 787–792) reproduces the ER’s four-sentence cadence paragraph almost verbatim, the five [qualitative_item_#] spans (lines 800–829) carry full ER sentences, and [action_1_sub] (line 456) repeats a four-vegetable enumeration already implied by “mixed cruciferous vegetables” — together pushing the sheet past its one-page budget instead of being condensed to the per-section budget.

Fixes 03/09/2026 03:36

1. 4.5 — Protocol sub condensed: [action_1_sub] dropped the redundant “— broccoli, cabbage, cauliflower, Brussels sprouts —” enumeration, leaving “Trial-level dosing 300 g/day of mixed cruciferous vegetables, split across two meals”.
2. 4.5 — Monitoring cadence tightened: [monitoring_cadence] was compressed from the ER’s four-sentence paragraph, shortening the thyroid and anticoagulation clauses (“Thyroid at 3 months and annually, only where iodine intake is low or raw intake high. Anticoagulation 1–2 weeks after any large sustained change.”) without dropping any interval.
3. 4.5 — Qualitative items condensed: All five [qualitative_item_#] spans were trimmed from full ER sentences to compact phrases (e.g., “Sensitivity to the sulfur taste: strong aversion often tracks genotype and predicts poor long-term adherence” → “Sulfur-taste sensitivity: strong aversion tracks genotype and predicts poor long-term adherence”), preserving every marker.

Issues 03/09/2026 03:29

1. 7.4 — Clinical-register word in At-A-Glance: “faster clearance of a few medicines” uses “clearance” in its pharmacokinetic sense, an ordinary-looking clinical-register term that a non-specialist would not use unprompted with that exact meaning.

Fixes 03/09/2026 03:29

1. 7.4 — Plain-language At-A-Glance wording: Replaced “faster clearance of a few medicines” with “some medicines wearing off faster” in [at_a_glance], removing the pharmacokinetic sense of “clearance”; the summary remains within the 60-word budget at 56 words.