Audit: QRS - Bhringaraj for Hair Growth

Audit conducted on 19/09/2026 09:11 using AI4L / Opus 5

Iterations

Summary

Items	Count
Total	93
Passed	85
Failed	0
N/A	8
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.	🟢	All protocol amounts (5–10 mL 2–3× weekly, 10–20 g 30–45 min, 3 g/day 60 days), time points (60/120 days), benefit and risk tiers, all 8 contraindications, all 9 interactions, all 8 biomarker rows and all 6 qualitative items trace to ER text.
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.	🟢	“caution, theoretical” (UGT1A1 substrates) and “no interaction identified” (topical minoxidil) carry the ER’s hedging 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 remain absolute; the ER’s “⭕️ Not Central to Hair Growth” markers are carried as “not central to hair growth” in both Benefits and Time to Effect.
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.	🟢	Gates draw only from Key Interactions & Contraindications; Benefits from Expected Benefits; Risks from Potential Risks & Side Effects; Monitoring and Qualitative from Monitoring Protocol & Defining Success. No Benefit- or Risk-Modifying Factor content is surfaced.
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, citations, author names, NCT identifiers or brand names appear anywhere in the QRS.
1.6	The QRS does not introduce new attributions.	🟢	No attributions beyond the template’s fixed 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 matching the ER’s own restrained framing of a thin human evidence base.
2.2	The tone of the QRS is simultaneously expert, accessible, objective, and data-driven, but also empowering and encouraging	🟢	Concrete amounts, thresholds and targets are given throughout, enabling action without overselling.
2.3	The QRS reads as a trusted, knowledgeable guide rather than a prescriptive doctor	🟢	Presents amounts, gates and targets as evidence, not as orders.
2.4	The QRS avoids language that implies medical or clinical advice	🟢	No directive second-person or prescriptive constructions.
2.5	The QRS “presents information” instead of “providing guidance”, “recommending”, or “advising”	🟢	Interaction labels (“caution”, “monitor”) are the ER’s own severity descriptors, not advice issued by the QRS.
2.6	The QRS never addresses “the reader” directly — it presents evidence, not guidance	🟢	No occurrence of “you” / “your” anywhere in the file.
2.7	The QRS is written in plain language, avoiding unnecessary medical jargon	🟢	Technical terms retained only where they are the marker or condition name (trichoscopy, Child-Pugh, sesquiterpene lactone).
2.8	Information is presented in a concise and very compact manner	🟢	Every gate item, benefit and risk is reduced to the key fact; mitigations, mechanisms and citations stripped.
2.9	It DOES NOT address the reader directly	🟢	Confirmed: no second-person forms.
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.	🟢	Optimal functional ranges (ferritin 70–100/100–150 ng/mL, TSH 0.5–2.0 mIU/L) rather than conventional reference ranges.
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.	🟢	Overnight oiling, trichoscopy tracking, venous lead testing and weekly blood pressure all assume a willing, effortful reader.
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.	🟢	The monitoring panel and 120-day assessment horizon are well beyond general-population expectations.
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 foregrounds the supply-chain metal hazard over the modest topical risks, which is the distinction that matters to a proactive user.
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 in the file.
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 consistently “oral use” / “topical use” / “divided capsules”; “Glucose-lowering medication”, “antihypertensives and diuretics” used formally.

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 headings present verbatim (lines 445, 488, 536, 565, 589, 652, 678, 682–684, 816); Medium/Low/Speculative tier labels intact, High tiers correctly hidden per 12.5/13.5.
3.2	All “…” from the [qrs_template] are present in the the QRS.	🟢	All 38 template variables present; marker_#_* expanded to marker_1–8 and qualitative_item_# to qualitative_item_1–6.
3.3	Spans that are not addressed in a checklist item are left unchanged	🟢	Diff of the QRS head/style block against the template shows the only difference is [page_title]; the website="evidence_review", website="audit" and website="full_review" spans and the footer disclaimer are byte-identical to the template.

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 High benefit and High risk sub-tiers are governed by 12.5 / 13.5 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.	🟢	Protocol labels (“Standard topical oil regimen”, “Powder paste alternative”, “Oral whole-leaf approach”) and all nine interaction labels carry the ER’s bold labels, with example lists trimmed as 9.5 permits.
4.3	Labels are not paraphrased, abbreviated, or invented.	🟢	Marker names follow the ER table rows; only explanatory glosses (“(the iron storage protein)”, “(magnified scalp imaging)”) are dropped.
4.4	The QRS DOES NOT use emoji indicators (no 🟩, 🟥, 🟨, etc.). Color and emphasis are conveyed through CSS and bold labels.	🟢	Unicode scan for emoji/pictographic ranges returns no matches; the ER’s ⭕️ marker is rendered as the words “not central to hair growth”.
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 its per-section budget: interaction mitigations, contraindication rationales, benefit magnitudes and risk effect sizes are all stripped; item counts are the minimum the completeness items (8.2, 9.2, 14.2, 15.2) permit.

---

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 on 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 “—” line 3, closing “—” line 13; preamble text 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; 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, because it contains a colon.
5.5	The filename of the source ER is stated as “er_filename: [er_filename]”	🟢	Line 4: er_filename: bhringaraj_hair_2026-0919-0611_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: 2026-0919-0845.
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 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” — nickname plus version, no additional qualifier.
5.12	The filename of the document is stated as “qrs_filename: [filename of this document]”	🟢	Line 9 matches the file’s actual 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: “Bhringaraj for Hair Growth - Quick Reference Sheet”; no characters requiring entity encoding.
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: “Bhringaraj for Hair Growth”, matching ER frontmatter canonical_topic.
6.3	[header_subline_date] is set to [qrs_creation_date reformatted as MM/DD/YYYY]	🟢	Line 421: “09/19/2026”, correct reformat of 2026-0919-0845.
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 block (lines 415–428) is structurally identical to the template; the ER’s long “Also known as” list is 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 three Conclusion paragraphs: the two unequal evidence bodies, the modest avoidable risks, and the supply-chain hazard.
7.2	[at_a_glance] is no longer than 60 words	🟢	55 words.
7.3	Every fact in [at_a_glance] is supported by a distinct passage in the ER.	🟢	Each of the six clauses maps to a distinct Conclusion sentence (ER lines 447, 449).
7.4	It DOES NOT use acronyms or technical classifications that require specialist knowledge, uses plain-language terms instead	🟢	No acronyms; “resting follicles”, “scalp-oil herb”, “toxic metal” replace the ER’s telogen/coumestan/heavy-metal register.
7.5	It DOES NOT cite specific trials (names, years, sample sizes, p-values)	🟢	“the only human hair study” is referenced generically, with no name, year, n or p-value.
7.6	It DOES NOT cite effect sizes, relative risks, or statistical results	🟢	No numbers of any kind appear.

8. Contraindications

#	Description	Result	Comments
8.1	The section is derived from the ER Key Interactions & Contraindications section	🟢	All eight items map to the ER’s “Populations who should avoid Bhringaraj” list (ER lines 298–305).
8.2	[stop_items] represent the Contraindications from the ER	🟢	8 <li> items against 8 ER bullets; none omitted, none added.
8.3	Individual [stop_items] are formatted as <li></li>	🟢	Lines 568–584, each a discrete <li>.
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.	🟢	Rationales stripped throughout (“given the coumestan content…”, “because of the diuretic and sodium-losing effect”, “until an independently tested product is sourced”); no trailing dash clauses remain.
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).	🟢	Retains “Child-Pugh Class B or C … (moderate to severe cirrhosis)”, “below 30 mL/min/1.73 m²”, “below 100 mmHg”, “above 5 µg/dL”, “under 12”, and the route qualifiers.
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.	🟢	The ER names eight such populations and the section is correctly populated rather than 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 map to the ER’s nine interaction bullets (ER lines 278–294).
9.2	[caution_items] represent the Key Interactions from the ER, excluding any that are already listed as Contraindications	🟢	9 <li> items against 9 ER bullets; no overlap with the Contraindications gate.
9.3	Individual [caution_items] are formatted as <li></li>	🟢	Lines 592–642, each a discrete <li>.
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 “Mitigation is…” clause and mechanistic sentence removed; each item reduced to label plus severity verdict.
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 retained in every bullet that has one, trimmed for budget (e.g. antihypertensives to amlodipine, lisinopril, hydrochlorothiazide) but never dropped.
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.	🟢	The ER names nine interactions and the section is correctly populated rather than empty.
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 (ER lines 325–329).
10.2	The three sets of [action] items cover the three most important actionable implementation aspects from the ER Protocol section	🟢	The three delivery routes — topical oil, powder paste, oral whole leaf — are the ER’s three actionable regimens; the remaining bullets are context, not 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 mentions three distinct actionable aspects; 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 variables populated: 5–10 mL 2–3× weekly, 10–20 g 30–45 min, 3 g/day for 60 days, each with an ER-derived sub-line.

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	🟢	60-day oral cardiometabolic endpoint, 120-day hair density/thickness/growth-rate endpoint, and 120-day greying/flaking endpoint — the only measured time points in the ER.
11.2	The sets are picked and ordered by the magnitude of the related benefit	🟢	Ordered Medium tier (blood pressure and cholesterol) before the two Low-tier outcomes, matching the ER’s benefit grading.
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 time-to-effect 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.	🟢	All nine variables populated; sub-lines echo ER lines 154, 162, 168, 174 and 381.
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 time-to-effect information (ER line 381 and the trial durations), so the section is retained.

12. Benefits

#	Description	Result	Comments
12.1	The section is derived from the ER Expected Benefits section	🟢	All six benefit headings from ER lines 152–194 are represented in their correct tiers.
12.2	Key variables are [benefits_high], [benefits_medium], [benefits_low], [benefits_speculative]	🟢	All four spans present (lines 538, 539, 545, 552).
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.	🟢	All Magnitude figures (15% MAP, 17% cholesterol, 277.6 hairs/cm², p-values) and trial descriptions dropped; only the ER’s benefit headings remain.
12.4	Parenthetical content — including effect sizes, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parentheses remain in any benefits 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.	🟢	Line 538: <span data-qrs-var="benefits_high" style="display: none"></span>, matching the ER’s “No benefit reaches High”.

13. Risks

#	Description	Result	Comments
13.1	The section is derived from the ER Potential Risks & Side Effects section	🟢	All seven risk headings from ER lines 222–260 are represented in their correct tiers.
13.2	Key variables are [risks_high], [risks_medium], [risks_low], [risks_speculative]	🟢	All four spans present (lines 654, 655, 661, 667).
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.	🟢	The 20.7% contamination figure, the 1.2% patch-test rate and all mechanistic detail are dropped; only the ER’s risk headings remain.
13.4	Parenthetical content — including frequencies, severity grades, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parentheses remain in any risks 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.	🟢	Line 654: <span data-qrs-var="risks_high" style="display: none"></span>, matching the ER’s “No risk reaches High”.

14. Monitoring

#	Description	Result	Comments
14.1	The section is derived from the ER Monitoring section	🟢	Derived from the ER Monitoring Protocol & Defining Success biomarker table (ER lines 411–420).
14.2	All measurable/quantifiable biomarkers from the Monitoring section are listed	🟢	All 8 ER biomarker rows present as marker_1–marker_8: ferritin, 25-hydroxyvitamin D, TSH, seated blood pressure, ALT/AST, venous blood lead, potassium and sodium, hair density by trichoscopy. Targets and “why” text match the ER.
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 805–810 reproduce the ER’s cadence paragraph (ER line 409): baseline, imaging at four and eight months, weekly then monthly pressure, liver enzymes and lead at three months then six to twelve monthly.

15. Qualitative Assessment

#	Description	Result	Comments
15.1	The section is derived from the ER Monitoring section	🟢	Derived from the ER’s “Qualitative markers worth tracking alongside the numbers” list (ER lines 424–429).
15.2	All subjective/qualitative biomarkers from the Monitoring section are listed	🟢	All 6 ER qualitative markers present verbatim as qualitative_item_1–6.

Issues 19/09/2026 09:11

Pass rate 100.00%. No issues found.

Issues 19/09/2026 09:02

1. 4.5 — Sheet overflows one A4 page: The Protocol and Time-to-effect sub-cells (lines 455–487 and 503–534) carry 98–153 characters of multi-sentence prose each, the Key Interactions column (lines 597–649) runs roughly 24 rendered lines at 9.5pt, and at_a_glance (lines 433–437) and monitoring_cadence (lines 811–816) each run a line longer than needed — which, on top of the mandatory eight-row Monitoring table and six-item Qualitative list, pushes the sheet past the 273 mm A4 print box.

Fixes 19/09/2026 09:02

1. 4.5 — At-a-glance tightened: Condensed at_a_glance from 59 to 55 words (398 → 355 characters), collapsing “strong laboratory support and thin human evidence” to “strong laboratory but thin human evidence” and dropping the redundant “in animals and cells / in people” scaffolding, with all four Conclusion facts retained.
2. 4.5 — Protocol sub-cells condensed: Cut the three action_#_sub cells to single clauses — dropping the massage-duration detail, the paste-and-rinse restatement and the standardised-extract aside — from 121/149/128 down to 79/75/61 characters.
3. 4.5 — Time-to-effect sub-cells condensed: Cut the three time_#_sub cells from 98/153/122 to 68/72/72 characters, e.g. “The hair cycle sets the floor. Standardised photographs are unreliable before four months; change within weeks reflects conditioning and shine, not growth.” became “The hair cycle sets the floor; earlier change reflects shine, not growth.”
4. 4.5 — Key Interactions example lists trimmed: Shortened the three longest parenthetical drug lists per the item 9.5 one-page budget clause — antihypertensives 5 → 3 examples, other Asteraceae supplements 6 → 4, additive blood-pressure supplements 6 → 4 — saving about three rendered lines in the taller gate column.
5. 4.5 — Monitoring cadence compacted: Reworded monitoring_cadence from 350 to 306 characters (“repeat at four and eight months” → “at four and eight months”; “weekly for the first month of any oral dosing, monthly after that” → “weekly for the first month of oral dosing, then monthly”), keeping every interval and the “beyond the baseline” qualifier.

Issues 19/09/2026 08:53

1. 1.3 — Hedge dropped in lede: [at_a_glance] at line 436 reads “Skin reactions and blocked pores are modest, avoidable risks”, strengthening the ER Conclusion’s “The risks are modest and mostly avoidable” (ER line 449).

Fixes 19/09/2026 08:53

1. 1.3 — Hedge restored in lede: Changed [at_a_glance] from “Skin reactions and blocked pores are modest, avoidable risks” to “Skin reactions and blocked pores are modest and mostly avoidable”, matching the ER Conclusion’s hedge; the section remains within the 60-word limit at 59 words.