Audit: QRS - Phosphatidylcholine for Health & Longevity

Audit conducted on 24/08/2026 20:29 using AI4L / Opus 5

Iterations

Summary

Items	Count
Total	93
Passed	82
Failed	0
N/A	11
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 cells trace to ER lines 366/374/378; time cells to ER line 419; all 10 benefit items and all 10 risk items are verbatim ER sub-headings; all 11 monitoring rows and targets match the ER table (lines 449–459); the 4 contraindications match ER lines 341–344; the 10 interactions match ER lines 319–337.
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.	🟢	Cautious ER wording is carried verbatim, e.g. marker_10_target “No established optimal target; track change from baseline” (ER line 458) and marker_11_target “No range applies; the result is a genotype, tested once” (ER line 459).
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”).	🟢	Contraindications remain absolute exclusions; time_3_sub keeps the ER’s hedge “Signals where present; weaker and less consistent” (ER lines 419/490); at_a_glance keeps “unsettled cardiovascular question” (ER line 494).
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.	🟢	stop_items come only from the ER’s “Populations who should avoid Phosphatidylcholine” list; caution_items only from the ER interaction bullets; no Benefit- or Risk-Modifying Factor (ER lines 220–232, 304–314) is surfaced anywhere.
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.	🟢	No PMIDs, NCT identifiers, author names or brand names (Essentiale, Nattermann, Sanofi, Opella) appear anywhere in the QRS.
1.6	The QRS does not introduce new attributions.	🟢	No attributions of any kind are present.

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, evidence-weighted register matching the ER throughout.
2.2	The tone of the QRS is simultaneously expert, accessible, objective, and data-driven, but also empowering and encouraging	🟢	Numeric targets and tiered evidence grading carry the data; at_a_glance closes on the actionable “Cheap and well tolerated” framing.
2.3	The QRS reads as a trusted, knowledgeable guide rather than a prescriptive doctor	🟢	Content is stated as observed evidence, not instruction.
2.4	The QRS avoids language that implies medical or clinical advice	🟢	No imperatives directed at a reader; the footer disclaimer defers decisions to a clinician.
2.5	The QRS “presents information” instead of “providing guidance”, “recommending”, or “advising”	🟢	No occurrence of “recommend”, “advise”, or “should” in the QRS body.
2.6	The QRS never addresses “the reader” directly — it presents evidence, not guidance	🟢	No second-person pronouns anywhere in the document.
2.7	The QRS is written in plain language, avoiding unnecessary medical jargon	🟢	Terms are spelled out in full rather than abbreviated (“alanine aminotransferase”, “estimated glomerular filtration rate”, “trimethylamine N-oxide”); no unexplained acronyms.
2.8	Information is presented in a concise and very compact manner	🟢	Benefits, risks, contraindications and interactions are reduced to bare headings; monitoring “Why” cells are single clauses.
2.9	It DOES NOT address the reader directly	🟢	Confirmed — no direct address.
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.	🟢	Functional-range targets (ALT <20 U/L, ApoB <80 mg/dL) and genotype testing address an optimizing audience, not a general one.
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.	🟢	Assumes FibroScan access, specialist-laboratory plasma choline, and PEMT genotyping.
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.	🟢	Targets sit well below conventional laboratory cutoffs, which only a proactive audience would act on.
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.	🟢	The trimethylamine N-oxide question is surfaced as a measurable marker with a target rather than as a generic warning.
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 appear; the title uses “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.	🟢	Formal register throughout; the few plain terms (“fishy body odor”, “stomach injury”) are the ER’s own sub-heading wording (ER lines 181, 257).

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 unmodified: lines 446, 491, 535, 608, 634, 800 (headings), 566 and 583 (gates), 538/542/549/556 and 616/621/627 (tiers), 638–640 (column headers).
3.2	All “…” from the [qrs_template] are present in the the QRS.	🟢	Full set present: page_title, header_topic, header_subline_date, header_subline_model, at_a_glance, action_1–3 label/value/sub, time_1–3 label/value/sub, benefits_high/medium/low/speculative, stop_items, caution_items, risks_high/medium/low/speculative, marker_1–11 name/target/why, monitoring_cadence, qualitative_item_1–6.
3.3	Spans that are not addressed in a checklist item are left unchanged	🟢	The non-variable template spans <span website="evidence_review">Evidence Review</span> (line 423), <span website="audit"></span> (line 426) and <span website="full_review"></span> (line 440) are untouched.

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 source ER section is empty. The only unpopulated QRS tier is risks_high, and the ER’s High risk section is not empty — it carries an explanatory sentence (ER line 241) — so item 13.5, which mandates display:none rather than empty-state phrasing, governs instead.
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.	🟢	action_1_label “Standard liver protocol”, action_2_label “Best time of day” and action_3_label “Single versus split dosing” reproduce the ER bold labels at lines 366, 374 and 378 verbatim; all 11 marker names reproduce the ER table’s first column verbatim.
4.3	Labels are not paraphrased, abbreviated, or invented.	🟢	Time-to-effect labels are drawn from the ER’s own wording inside the “Time to effect” bullet (ER line 419: “Liver enzymes and triglycerides”, “liver-fat measurements”, “Cognitive and muscle signals”); no label is invented.
4.4	The QRS DOES NOT use emoji indicators (no 🟩, 🟥, 🟨, etc.). Color and emphasis are conveyed through CSS and bold labels.	🟢	No emoji present; the ER’s 🟩/🟥/🟨 tier markers and ⚠️ Conflicted flags were correctly stripped, with tiering conveyed by bold labels and the .benefits/.risks CSS palettes.
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.	🟢	Every section is condensed to the minimum the checklist permits: benefit and risk tiers are bare headings joined by semicolons, interaction and contraindication items are stripped of all trailing rationale, and monitoring “Why” cells are single clauses. The row counts that remain (11 markers, 10 interactions, 6 qualitative items) are mandated by items 14.2, 9.2 and 15.2.

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.	🟢	Lines 2–14; <!doctype html> is line 1 and nothing intervenes.
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 preamble text sits on line 2.
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.	🟢	Enclosed in an HTML comment; none of its values are repeated in body content.
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 contains a colon requiring it.
5.5	The filename of the source ER is stated as “er_filename: [er_filename]”	🟢	Line 4: er_filename: phosphatidylcholine_2026-0822-0009_Opus_ER.md.
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 QRS.md version badge.
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: 2026-0824-2000.
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” — single word, no version.
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 qualifier.
5.12	The filename of the document is stated as “qrs_filename: [filename of this document]”	🟢	Line 9 matches the file on disk: phosphatidylcholine_2026-0822-0009_Opus_QRS.html.
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; git_user, git_issue and the rest are unquoted and untrimmed of nothing.

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: “Phosphatidylcholine for Health & Longevity - Quick Reference Sheet”, matching ER canonical_topic (ER line 8) with the ampersand 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: “Phosphatidylcholine for Health & Longevity”.
6.3	[header_subline_date] is set to [qrs_creation_date reformatted as MM/DD/YYYY]	🟢	Line 421: “08/24/2026”, correctly derived from qrs_creation_date 2026-0824-2000.
6.4	[header_subline_model] is set to [qrs_creator_ai_fullname]	🟢	Line 425: “Opus 5”, matching the frontmatter value.
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 standard subline; the ER’s “Also known as” list (ER line 30) is correctly absent.

7. At-A-Glance Section

#	Description	Result	Comments
7.1	[at_a_glance] is dense, execution-oriented summary of the ER Conclusion section	🟢	Compresses all four Conclusion paragraphs (ER lines 488–494): nutrient framing, liver evidence as strongest, tolerability, and the open cardiovascular question.
7.2	[at_a_glance] is no longer than 60 words	🟢	59 words.
7.3	Every fact in [at_a_glance] is supported by a distinct passage in the ER.	🟢	“main building block of cell membranes… chief store of choline” → ER line 488; “purified soy preparations lower liver fat and enzymes” → ER line 490; “preventing outright choline shortfall protects liver and muscle” → ER line 490; “Cheap and well tolerated… unsettled cardiovascular question at higher doses” → ER line 494.
7.4	It DOES NOT use acronyms or technical classifications that require specialist knowledge, uses plain-language terms instead	🟢	No acronyms; “cell membranes”, “liver fat”, “fatty liver disease” and “nutrient” are lay terms, and “choline” is the nutrient named in the topic itself.
7.5	It DOES NOT cite specific trials (names, years, sample sizes, p-values)	🟢	No trial names, years, sample sizes or p-values.
7.6	It DOES NOT cite effect sizes, relative risks, or statistical results	🟢	No numeric results of any kind.

8. Contraindications

#	Description	Result	Comments
8.1	The section is derived from the ER Key Interactions & Contraindications section	🟢	All four items map to the ER’s “Populations who should avoid Phosphatidylcholine” list (ER lines 341–344).
8.2	[stop_items] represent the Contraindications from the ER	🟢	Complete 4-for-4 coverage: trimethylaminuria/FMO3, chronic kidney disease, soy/egg allergy, coronary disease with type 2 diabetes.
8.3	Individual [stop_items] are formatted as <li></li>	🟢	Lines 569–578 — four <li> elements inside the 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.	🟢	All four ER em-dash clauses are stripped (“— absolute contraindication, as even food-level intake provokes symptoms”, “— impaired clearance of trimethylamine N-oxide”, “— source-specific”, “— the subgroup in which the dietary mortality association was strongest”).
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 eGFR threshold “below 30 mL/min/1.73 m², or on dialysis” and the source parentheticals “(soy-derived lecithin)” / “(egg-derived phosphatidylcholine)” are preserved.
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 uses no ranking notation inside parentheses in this section.
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.	N/A	The section is populated; the ER names four such 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.

9. Key Interactions

#	Description	Result	Comments
9.1	The section is derived from the ER Key Interactions & Contraindications section	🟢	All ten items map to the ER’s interaction bullets at lines 319–337.
9.2	[caution_items] represent the Key Interactions from the ER, excluding any that are already listed as Contraindications	🟢	All ten ER interaction bullets are carried; none duplicates a contraindication.
9.3	Individual [caution_items] are formatted as <li></li>	🟢	Lines 586–598 — ten <li> elements inside the 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.	🟢	Each item is reduced to the drug class plus named examples; the ER’s “Caution”/”Monitor” verdicts and mechanistic sentences are all stripped.
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).	🟢	Example drug lists are preserved on all eight bullets that carry them; the anticholinergic list is trimmed to three of four exemplars for the one-page budget, which the item explicitly permits.
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	The ER uses no ranking notation inside parentheses in this section.
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.	N/A	The section is populated; the ER names ten interactions.
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.

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 366, 374 and 378.
10.2	The three sets of [action] items cover the three most important actionable implementation aspects from the ER Protocol section	🟢	Dose/duration (standard liver protocol), timing (with fat-containing meals) and frequency (split dosing) are the three aspects that determine how the intervention is actually taken.
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 twelve protocol bullets; all three sets are used.
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; no placeholder text remains (lines 450–486).

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	🟢	Liver enzymes/triglycerides, liver fat and cognition/muscle are the only three time-to-effect aspects the ER names (line 419).
11.2	The sets are picked and ordered by the magnitude of the related benefit	🟢	Ordered Medium → Medium → Low: liver enzymes/triglycerides and liver fat both attach to Medium-tier benefits (ER lines 169, 175), cognition/muscle to a Low-tier benefit (ER line 195).
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 three distinct aspects; all three sets are used.
11.4	All used [time_#label], [time#value], [time#_sub] items are filled with meaningful content derived from the ER.	🟢	“4–8 weeks”, “3 months” and “6 months or longer” reproduce the ER’s intervals exactly (line 419); the sub-lines are ER-derived (lines 419, 490).
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 does provide time-to-effect information, so the section is correctly retained.

12. Benefits

#	Description	Result	Comments
12.1	The section is derived from the ER Expected Benefits section	🟢	All ten items are the ER’s benefit sub-headings (ER lines 155–215), tier for tier.
12.2	Key variables are [benefits_high], [benefits_medium], [benefits_low], [benefits_speculative]	🟢	All four spans present at lines 537, 540, 547 and 554.
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.	🟢	Items are bare sub-headings joined by semicolons; every ER “Magnitude” figure, conflict-of-interest note and ⚠️ Conflicted flag is stripped.
12.4	Parenthetical content — including effect sizes, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parentheses appear in any benefit item.
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 tiers carry items in the ER, so no tier needs hiding.

13. Risks

#	Description	Result	Comments
13.1	The section is derived from the ER Potential Risks & Side Effects section	🟢	All nine items are the ER’s risk sub-headings (ER lines 245–299), tier for tier.
13.2	Key variables are [risks_high], [risks_medium], [risks_low], [risks_speculative]	🟢	All four spans present at lines 610, 613, 619 and 626.
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.	🟢	Bare sub-headings only; the hazard ratios, confidence intervals and conflict notes from the ER Magnitude lines are all stripped.
13.4	Parenthetical content — including frequencies, severity grades, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parentheses appear in any risk item.
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.	🟢	risks_high carries style="display: none" at line 610 with an HTML comment citing the ER basis; no empty-state phrasing was substituted.

14. Monitoring

#	Description	Result	Comments
14.1	The section is derived from the ER Monitoring section	🟢	Rows and targets are taken from the ER Monitoring Protocol & Defining Success table (ER lines 447–459).
14.2	All measurable/quantifiable biomarkers from the Monitoring section are listed	🟢	All 11 ER table rows appear, in ER order, with targets reproduced exactly: ALT, GGT, controlled attenuation parameter, trimethylamine N-oxide, apolipoprotein B, triglycerides, hemoglobin A1c, eGFR, homocysteine, plasma free choline, PEMT rs12325817 genotype.
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.	🟢	Lines 790–794 condense ER line 445: liver enzymes and trimethylamine N-oxide at 8–12 weeks, lipids and glycemic marker at 3 months, liver fat at 6 months, then every 6–12 months.

15. Qualitative Assessment

#	Description	Result	Comments
15.1	The section is derived from the ER Monitoring section	🟢	All six items map to the ER’s “Qualitative markers worth tracking” list (ER lines 463–468).
15.2	All subjective/qualitative biomarkers from the Monitoring section are listed	🟢	Complete 6-for-6 coverage: abdominal fullness, daytime energy, cognition, stool form, fish-like odor, dream vividness.

Issues 24/08/2026 20:29

Pass rate 100.00%. No issues found.

Issues 24/08/2026 20:23

1. 1.1 — Unsupported trial attribution in time cell: [time_1_sub] at line 503 reads “Shift reported in the fatty-liver and lipid trials”, but the ER’s “Time to effect” bullet (ER line 419) attributes the 4–8 week window to no trial or trial class.
2. 1.3 — Dose hedge dropped: [action_1_value] at line 453 states “1.8 g daily” where the ER Therapeutic Protocol bullet (ER line 366) says “roughly 1.8 g daily”, presenting an approximate regimen dose as exact.

Fixes 24/08/2026 20:23

1. 1.1 — Unsupported trial attribution removed: [time_1_sub] changed from “Shift reported in the fatty-liver and lipid trials” to “The earliest measurable change reported”, removing the trial-class attribution the ER does not make for the 4–8 week window.
2. 1.3 — Dose hedge restored: [action_1_value] changed from “1.8 g daily” to “~1.8 g daily”, matching the ER’s “roughly 1.8 g daily”.

Issues 24/08/2026 20:15

1. 1.3 — At-a-glance generalises liver claim: [at_a_glance] (lines 434-437) states “purified soy preparations lower liver fat and liver enzymes” and “preventing choline shortfall protects liver and muscle”, dropping the ER Conclusion’s population restriction (“in people with fatty liver disease and metabolic problems”) and its hedge (“outright” choline shortfall), which strengthens both claims beyond the ER.

Fixes 24/08/2026 20:15

1. 1.3 — At-a-glance liver claim restored: Rewrote [at_a_glance] to carry the ER Conclusion’s qualifiers, restoring the population restriction (“lower liver fat and enzymes in fatty liver disease”) and the hedge (“preventing outright choline shortfall”); the passage remains within the 60-word budget at 59 words.

Issues 24/08/2026 20:09

1. 2.15 — Consumer-grade “heart” for “cardiovascular”: at_a_glance (line 437) ends “with an unsettled heart question at higher doses” where the ER Conclusion uses the formal “an unsettled cardiovascular question attached to higher doses”; the QRS itself uses “Cardiovascular” in risks_medium (line 614), making the register inconsistent.

Fixes 24/08/2026 20:09

1. 2.15 — Consumer-grade “heart” for “cardiovascular”: Replaced “an unsettled heart question at higher doses” with “an unsettled cardiovascular question at higher doses” in at_a_glance, restoring the ER Conclusion wording and matching the register used in risks_medium.