Audit: QRS - Borage Oil for Health & Longevity

Audit conducted on 14/09/2026 04:38 using AI4L / Opus 5

Iterations

Summary

Items	Count
Total	93
Passed	86
Failed	0
N/A	7
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.	🟢	Every span traces to ER text: protocol cells to ER lines 374/380/384, time cells to ER 399/425, benefits/risks to the ER benefit and risk headings, gates to ER 329–354, monitoring to the ER table at 451–461, qualitative items to ER 465–469.
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.	🟢	“No established target; track the change from the individual’s own baseline” (marker_3_target) and “the theoretical concern behind alkaloid contamination” (marker_5_why) carry the ER’s hedged wording verbatim.
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 stay contraindications and interactions stay interactions; “Eczema does not hold up” matches the ER’s negative net reading rather than softening it.
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.	🟢	Contraindications come only from the ER’s “Populations who should avoid Borage Oil” list; interactions only from the ER interaction bullets; no Benefit- or Risk-Modifying Factor is reused elsewhere.
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 no PMIDs, author names, NCT identifiers or brand names at all.
1.6	The QRS does not introduce new attributions.	🟢	No attributions beyond the template’s AI4L link.

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 reused from the ER, including “blood fats”, “the calming route” and “mild and mostly digestive”.
2.2	The tone of the QRS is simultaneously expert, accessible, objective, and data-driven, but also empowering and encouraging	🟢	Concrete doses, thresholds and targets are supplied without overselling; the lede states where the signal is clearest.
2.3	The QRS reads as a trusted, knowledgeable guide rather than a prescriptive doctor	🟢	Content is stated as evidence and ranges, not as orders.
2.4	The QRS avoids language that implies medical or clinical advice	🟢	Monitoring “Target” values reproduce the ER’s optimal functional ranges; no instruction to act is issued.
2.5	The QRS “presents information” instead of “providing guidance”, “recommending”, or “advising”	🟢	No “recommended”, “advised” or “should” constructions in the QRS’s own voice.
2.6	The QRS never addresses “the reader” directly — it presents evidence, not guidance	🟢	No second-person pronoun occurs anywhere in the file.
2.7	The QRS is written in plain language, avoiding unnecessary medical jargon	🟢	Technical terms appear only where the ER requires them (Child-Pugh class, dihomo-gamma-linolenic acid ratio); the lede is jargon-free.
2.8	Information is presented in a concise and very compact manner	🟢	Benefit and risk items are bare descriptors; monitoring “Why” cells are trimmed from the ER’s longer sentences.
2.9	It DOES NOT address the reader directly	🟢	Confirmed by a full-file search for you/your/yours/yourself: no matches.
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.	🟢	Nine-marker monitoring panel, cadence schedule and a decision-gate layout address a proactive, risk-aware 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.	🟢	Split dosing, specialist fatty acid panels and repeat clotting tests are presented without apology.
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.	🟢	Content assumes access to specialist panels and willingness to track ratios over months.
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 lede flags that most benefits rest on a single controlled trial, the framing this audience needs to weigh the case.
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.	🟢	“Longevity” appears in the title and header; “anti-aging” appears nowhere.
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)”; “oral” / “administered orally” not “taken by mouth” / “given by mouth”; “injection” not “shot”; “adverse event” not “bad reaction”). This holds on EVERY surface, including the QRS lede — the stricter plain-language bar (see 2.7) does not license lay phrasing for route of administration. Direct quotes from sources are exempt.	🟢	Route of administration is expressed as “with a meal” / “largest fat-containing meal”; clinical terms (alanine aminotransferase, international normalised ratio, Child-Pugh Class) are used in full.

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 eleven headings at QRS lines 445, 491, 541, 573, 593, 622, 644, 648–650 and 795 are byte-identical to the template; tier labels High/Medium/Low/Speculative unchanged.
3.2	All “…” from the [qrs_template] are present in the the QRS.	🟢	All 34 template variable names present; the extra 32 are the correctly enumerated repeats of marker_#* and qualitative_item#.
3.3	Spans that are not addressed in a checklist item are left unchanged	🟢	A full diff against the template shows changes confined to variable regions; the three website="…" spans, the CSS block and all structural markup 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 ER section mapped into the QRS carries an empty-state phrasing; the one empty tier (risks Medium) is governed by item 13.5, which requires display:none 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.	🟢	“Standard general dose”, “Best time of day” and “Single versus split dosing” reproduce the ER’s bold protocol labels exactly; gate items reuse the ER’s bold interaction labels.
4.3	Labels are not paraphrased, abbreviated, or invented.	🟢	Time-to-effect labels “Joint symptoms”, “Skin barrier measures” and “Lipid readings” are the ER’s own phrases from line 425.
4.4	The QRS DOES NOT use emoji indicators (no 🟩, 🟥, 🟨, etc.). Color and emphasis are conveyed through CSS and bold labels.	🟢	Zero emoji in the file; the ER’s ⚠️ and ⭕️ markers were correctly dropped.
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 completeness items allow: benefits and risks reduced to bare tier descriptors, interactions to label plus trimmed parenthetical, monitoring “Why” cells shortened from the ER’s full sentences. No ER prose is carried wholesale.

---

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, immediately after the doctype at line 1.
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.
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; no metadata value is repeated in the body.
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, correctly so because the value contains a colon.
5.5	The filename of the source ER is stated as “er_filename: [er_filename]”	🟢	Line 4: er_filename: borage_oil_2026-0914-0002_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: 26.9.11, 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: 2026-0914-0410.
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” is a single word with no version or 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” is nickname plus version with no trailing qualifier.
5.12	The filename of the document is stated as “qrs_filename: [filename of this document]”	🟢	Line 9 matches the file’s own name 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; no stray whitespace or unnecessary quoting.

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: “Borage Oil for Health & Longevity - Quick Reference Sheet”.
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: “Borage Oil for Health & Longevity”, matching ER frontmatter canonical_topic.
6.3	[header_subline_date] is set to [qrs_creation_date reformatted as MM/DD/YYYY]	🟢	Line 421: “09/14/2026”, the correct reformatting of 2026-0914-0410.
6.4	[header_subline_model] is set to [qrs_creator_ai_fullname]	🟢	Line 425: “Opus 5”.
6.5	No additional header content appears: no badge, version stamp, AKA / alternate names line, source-AI attribution, audit date, or QRS variant marker.	🟢	Header carries only the title and the template’s subline; the ER’s “Also known as” line was not carried over.

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 489–495) into the decision-relevant core: where the signal is strong, where it rests on one trial, where it fails, and the safety profile.
7.2	[at_a_glance] is no longer than 60 words	🟢	Exactly 60 words.
7.3	Every fact in [at_a_glance] is supported by a distinct passage in the ER.	🟢	Each clause maps to ER 489 (one fat, built less well with age), 491 (joints; the single-trial list; eczema) and 493 (mild, mostly digestive).
7.4	It DOES NOT use acronyms or technical classifications that require specialist knowledge, uses plain-language terms instead	🟢	No acronyms; “blood fats”, “skin barrier”, “nerve symptoms in diabetes” replace the ER’s technical terms.
7.5	It DOES NOT cite specific trials (names, years, sample sizes, p-values)	🟢	No author, year or sample size appears.
7.6	It DOES NOT cite effect sizes, relative risks, or statistical results	🟢	No numeric effect size or statistic.

8. Contraindications

#	Description	Result	Comments
8.1	The section is derived from the ER Key Interactions & Contraindications section	🟢	All six items come from “Populations who should avoid Borage Oil” at ER 347–354.
8.2	[stop_items] represent the Contraindications from the ER	🟢	All six ER avoidance populations are present, none added.
8.3	Individual [stop_items] are formatted as <li></li>	🟢	Six <li> elements at QRS lines 576–588.
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 pregnancy item’s rationale (“on the combined grounds of prostaglandin activity…”) and the ALT gloss were stripped; no dashes introduce trailing clauses.
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).	🟢	“platelet count below 50 × 10⁹/L”, “Within 14 days of elective surgery”, “Child-Pugh Class B or C” and “above three times the upper limit of normal” are all retained.
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.	🟢	The ER uses no ranking notation in this list; the only symbol carried, “×” in 50 × 10⁹/L, is a multiplication sign in 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 ER does identify such populations and the section is correctly populated, not empty.
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 nine items come from the ER interaction bullets at 329–345.
9.2	[caution_items] represent the Key Interactions from the ER, excluding any that are already listed as Contraindications	🟢	All nine ER interaction bullets present; none duplicates a contraindication (the seizure entries differ: drug class in the gate, personal history in the contraindications).
9.3	Individual [caution_items] are formatted as <li></li>	🟢	Nine <li> elements at QRS lines 596–612.
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 “caution/monitor” verdict, mechanism and “Mitigation:” clause was stripped; only the ER’s bold label survives.
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).	🟢	Drug lists retained throughout; the two longest were trimmed rather than dropped — the seizure entry keeps “phenothiazines, tricyclics, bupropion” and the GLA-oil entry keeps all three oils in shortened form.
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.	🟢	The ER’s semicolon-grouped explanatory drug list for seizure-threshold-lowering drugs was normalised to a plain comma-separated list.
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 ER identifies nine such interactions and the section is correctly populated.
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 map to ER Therapeutic Protocol bullets at lines 374, 380 and 384.
10.2	The three sets of [action] items cover the three most important actionable implementation aspects from the ER Protocol section	🟢	Dose, timing and split-dosing are the three executable levers; the remaining ER bullets are response modifiers rather than actions.
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 states eleven protocol bullets, well above three, so 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 ER-derived content; no placeholder text remains.

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	🟢	Joint symptoms, skin barrier and lipid readings are three of the four timings the ER gives at line 425; acne (the fourth) sits lowest in the ER’s Medium tier.
11.2	The sets are picked and ordered by the magnitude of the related benefit	🟢	Joint symptoms (the ER’s only High benefit) first, then skin barrier and lipids in the ER’s own Medium-tier order.
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 gives four distinct time-to-effect aspects, so 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.	🟢	All nine spans populated from ER lines 399 and 425 and the lipid trial description at ER 177.
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 fourteen descriptors correspond to ER benefit headings at lines 155–239.
12.2	Key variables are [benefits_high], [benefits_medium], [benefits_low], [benefits_speculative]	🟢	All four spans present at QRS lines 543, 546, 554 and 561, each with its fixed tier label.
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 item is the bare ER heading; the ER’s Magnitude paragraphs, mechanisms and citations were all dropped.
12.4	Parenthetical content — including effect sizes, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parentheses appear anywhere in the Benefits card.
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 benefit tiers carry items in the ER, 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 descriptors correspond to ER risk headings at lines 265–311.
13.2	Key variables are [risks_high], [risks_medium], [risks_low], [risks_speculative]	🟢	All four spans present at QRS lines 624, 627, 628 and 636.
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 item is the bare ER heading; the ⚠️ Conflicted markers, Magnitude figures and net readings were dropped.
13.4	Parenthetical content — including frequencies, severity grades, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parentheses appear anywhere in the Risks card.
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.	🟢	The ER states “No risk reaches Medium” (line 273); QRS line 627 correctly renders an empty risks_medium span with style="display: none".

14. Monitoring

#	Description	Result	Comments
14.1	The section is derived from the ER Monitoring section	🟢	Rows reproduce the ER biomarker table at lines 451–461 in the same order.
14.2	All measurable/quantifiable biomarkers from the Monitoring section are listed	🟢	All nine ER biomarkers present with their optimal functional ranges intact; the narrative’s liver enzymes and full blood count are covered by ALT and platelet count.
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.	🟢	QRS lines 785–789 carry the baseline, 6–8 week, 6 month and 6–12 month schedule plus the anticoagulant clotting recheck, matching ER lines 447–449.

15. Qualitative Assessment

#	Description	Result	Comments
15.1	The section is derived from the ER Monitoring section	🟢	All five items come from the ER’s qualitative marker list at lines 465–469.
15.2	All subjective/qualitative biomarkers from the Monitoring section are listed	🟢	All five ER qualitative markers present, verbatim and in the ER’s order.

Issues 14/09/2026 04:38

Pass rate 100.00%. No issues found.

Issues 14/09/2026 04:30

1. 1.1 — Monitoring rationales distort ER meaning: marker_2_why (line 675) “Holds the dose on the calming route” attributes the causal action to the omega-3 index rather than to marine omega-3 fat (ER line 454), and marker_6_why (line 733) “Sets the floor for antiplatelet effect” loses the ER’s sense that the platelet count is the floor below which added antiplatelet effect becomes unsafe (ER line 458).
2. 4.2 / 4.3 — Key Interaction labels reformulated: QRS line 605 renders the ER bold label “Supplements with additive antiplatelet effect” as “Antiplatelet supplements” and shortens “garlic extract” to “garlic”; QRS line 602 rewrites “Over-the-counter aspirin, fish oil capsules and herbal analgesics containing willow bark” as “Over-the-counter aspirin, fish oil, willow bark analgesics”.

Fixes 14/09/2026 04:30

1. 1.1 — Monitoring rationales restored to ER meaning: marker_2_why changed from “Holds the dose on the calming route” to “Sufficient marine omega-3 fat holds the dose on the calming route”, and marker_6_why from “Sets the floor for antiplatelet effect” to “Sets the floor below which added antiplatelet effect becomes unsafe”.
2. 4.2 / 4.3 — Key Interaction labels restored verbatim: “Antiplatelet supplements (fish oil, ginkgo, garlic, …)” was replaced with the ER’s label “Supplements with additive antiplatelet effect (fish oil, ginkgo, garlic extract, high-dose vitamin E, nattokinase, curcumin)”, and “Over-the-counter aspirin, fish oil, willow bark analgesics” with “Over-the-counter aspirin, fish oil capsules and herbal analgesics containing willow bark”.

Issues 14/09/2026 04:23

1. 1.2 — Hedge dropped on liver marker: marker_5_why (line 719) reads “Detects liver injury from contamination”, while the ER (line 457) frames alkaloid contamination as “the theoretical concern”; the QRS drops the hedge and, elsewhere, the ER states no liver injury has ever been attributed to borage seed oil.
2. 1.3 / 2.5 — Split-dosing stated as an instruction: action_3_value (line 480) “Split above 2 g of oil daily” turns the ER’s descriptive “splitting is typical above 2 g of oil daily” (ER line 384) into an imperative recommendation.

Fixes 14/09/2026 04:23

1. 1.2 — Hedge restored on liver marker: marker_5_why changed from “Detects liver injury from contamination” to “Detects liver injury, the theoretical concern behind alkaloid contamination”, restoring the ER’s hedge.
2. 1.3 / 2.5 — Split dosing restated as description: action_3_value changed from the imperative “Split above 2 g of oil daily” to “Splitting typical above 2 g of oil daily”, matching the ER’s descriptive framing.

Issues 14/09/2026 04:18

1. 4.5 — Sheet overruns one A4 page: At the template’s print metrics the assembled sheet runs to roughly two A4 pages; the Monitoring “Why” column (lines 661-778) and the longest Key Interactions items (lines 601-610) carry ER wording at full length instead of being condensed to the per-section budget.
2. 11.4 — Time-to-effect sub contradicts its label: [time_3_sub] (line 531) describes acne counts at ten weeks while sitting under [time_3_label] “Lipid readings” / [time_3_value] “6 weeks” (lines 524-527).

Fixes 14/09/2026 04:18

1. 11.4 — Time-to-effect sub matched to label: Replaced [time_3_sub] “Acne counts moved at ten weeks in the one controlled acne trial.” with “Triglycerides and high-density lipoprotein moved at six weeks in the one controlled borage oil lipid trial.”, so the sub now supports the “Lipid readings / 6 weeks” cell it sits under.
2. 4.5 — Sheet condensed toward the page budget: Condensed all nine Monitoring “Why” cells, the three longest Key Interactions items and [action_1_sub] to their key facts (e.g. “Sets the floor below which any added antiplatelet effect becomes unsafe” to “Sets the floor for antiplatelet effect”), cutting roughly a third of the sheet’s wrapped lines without dropping any marker, interaction or qualifier.