Audit: QRS - Calendula officinalis for Health & Longevity

Audit conducted on 14/09/2026 03:25 using AI4L / Opus 5

Iterations

Summary

Items	Count
Total	93
Passed	84
Failed	0
N/A	9
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 against the ER; all content traces to ER text (e.g. protocol cells to ER lines 377-383, markers to the ER table lines 466-474).
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 phrasing retained (e.g. “weakest link” at line 434, “Nothing supports a body-wide or life-extending effect” mirrors ER Conclusion line 508).
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”).	🟢	No strengthening or softening; contraindication scoping (“oral preparations”) preserved from ER lines 345-353.
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 from the ER avoid-list, Key Interactions from the ER interaction bullets; no Benefit- or Risk-Modifying Factor is recategorised.
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 IDs, trial names, expert names or brand names appear; drug names in Key Interactions are generic and all present in ER lines 319-339.
1.6	The QRS does not introduce new attributions.	🟢	No attributions of any kind in the QRS.

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.	🟢	Matches the ER’s plain, sceptical register.
2.2	The tone of the QRS is simultaneously expert, accessible, objective, and data-driven, but also empowering and encouraging	🟢	Expert and data-driven while stating where the intervention does work.
2.3	The QRS reads as a trusted, knowledgeable guide rather than a prescriptive doctor	🟢	Descriptive noun phrases and passive constructions throughout (e.g. “Inserted by applicator each night”, line 470).
2.4	The QRS avoids language that implies medical or clinical advice	🟢	No imperative or prescriptive instruction to a patient.
2.5	The QRS “presents information” instead of “providing guidance”, “recommending”, or “advising”	🟢	Content is presented, not recommended or advised.
2.6	The QRS never addresses “the reader” directly — it presents evidence, not guidance	🟢	No second-person forms; verified no occurrence of “you”/”your”.
2.7	The QRS is written in plain language, avoiding unnecessary medical jargon	🟢	Plain language; technical terms appear only where they are the marker or condition name.
2.8	Information is presented in a concise and very compact manner	🟢	Every field is a condensed phrase; no sentence carries redundant elaboration.
2.9	It DOES NOT address the reader directly	🟢	Confirmed: no direct address anywhere in the file.
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.	🟢	Framed for proactive, risk-aware adults applying the intervention.
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.	🟢	Protocol cells present multi-daily reapplication and fixed courses without softening for convenience.
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.	🟢	Not written for a general, low-effort 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 the local-only reach and the absence of a longevity signal, the weighting this audience needs.
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.	🟢	No “anti-aging” phrasing present.
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.	🟢	Formal register used throughout: “oral use”, “oral preparations”, “topical”, “co-application”; no consumer-grade route 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 fixed headings match [qrs_template] verbatim, including “Risk & Side Effects” (line 632) and the Monitoring column headers (lines 664-666).
3.2	All “…” from the [qrs_template] are present in the the QRS.	🟢	Diff of data-qrs-var names against [qrs_template] shows full coverage; marker_#* and qualitative_item# correctly expanded to 9 and 5 instances.
3.3	Spans that are not addressed in a checklist item are left unchanged	🟢	Diff against [qrs_template] shows head, CSS, footer and the website=”…” spans byte-identical.

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 section of the source ER is empty, so no empty-state phrasing is called for.
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.	🟢	ER bold labels reused verbatim: “Standard topical preparation”, “Vaginal preparation”, “Oral and mucosal rinse”, and all eleven Key Interaction labels.
4.3	Labels are not paraphrased, abbreviated, or invented.	🟢	Labels are the ER’s own; the Time-to-Effect labels name the three aspects of the ER’s single “Time to effect” bullet, which carries no per-aspect label.
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 ⚠️ Conflicted markers and tier squares are stripped.
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 minimum: benefit and risk tiers are bare noun phrases, Key Interaction drug lists are trimmed to one exemplar each, and Monitoring “Why” cells are shortened from the ER wording.

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.	🟢	Metadata comment opens at line 2, immediately after <!doctype html> and before any other content.
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.	🟢	YAML delimited by “—” at lines 3 and 13 inside the comment.
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.	🟢	Sits inside an HTML comment; no value is echoed by a rendered element.
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.	🟢	All values trimmed; only duration is quoted, which is required because it contains a colon.
5.5	The filename of the source ER is stated as “er_filename: [er_filename]”	🟢	Line 4: er_filename: calendula_officinalis_2026-0914-0009_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: 26.9.11, 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: 2026-0914-0248
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 number only.
5.12	The filename of the document is stated as “qrs_filename: [filename of this document]”	🟢	Line 9: qrs_filename matches the file’s own name.
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: no stray whitespace or unnecessary quoting in any value.

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: “Calendula officinalis for Health & Longevity - Quick Reference Sheet”, with & 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: “Calendula officinalis for Health & Longevity”, matching the ER canonical_topic.
6.3	[header_subline_date] is set to [qrs_creation_date reformatted as MM/DD/YYYY]	🟢	Line 421: 09/14/2026, the MM/DD/YYYY form of qrs_creation_date 2026-0914-0248.
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.	🟢	Subline carries only the template’s date, source and model text; no badge, AKA line, version stamp or audit date.

7. At-A-Glance Section

#	Description	Result	Comments
7.1	[at_a_glance] is dense, execution-oriented summary of the ER Conclusion section	🟢	Lines 434-438 distil the ER Conclusion (ER lines 508-514) into local reach, tiered benefit, weakest indication and the single recurring harm.
7.2	[at_a_glance] is no longer than 60 words	🟢	59 words, under the 60-word limit.
7.3	Every fact in [at_a_glance] is supported by a distinct passage in the ER.	🟢	Each clause maps to a distinct Conclusion passage: local action, acute wounds/episiotomy, the three lesser indications, radiation, absence of systemic effect, permanent daisy-family allergy.
7.4	It DOES NOT use acronyms or technical classifications that require specialist knowledge, uses plain-language terms instead	🟢	Plain-language throughout: “daisy-family” not Asteraceae, “the surgical cut made during childbirth” not episiotomy, “body-wide” not systemic.
7.5	It DOES NOT cite specific trials (names, years, sample sizes, p-values)	🟢	No trial name, year, sample size or p-value.
7.6	It DOES NOT cite effect sizes, relative risks, or statistical results	🟢	No effect size, odds ratio or confidence interval.

8. Contraindications

#	Description	Result	Comments
8.1	The section is derived from the ER Key Interactions & Contraindications section	🟢	All six items come from the ER’s “Populations who should avoid Calendula officinalis” list, ER lines 343-353.
8.2	[stop_items] represent the Contraindications from the ER	🟢	All six ER avoid-list entries are represented, none added.
8.3	Individual [stop_items] are formatted as <li></li>	🟢	Each item is a discrete <li> inside the [stop_items] span, lines 571-582.
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.	🟢	Trailing rationale stripped in every item (e.g. “— absolute contraindication for topical and oral use” and “where calendula displaces required wound care”); no dash-clause remains.
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).	🟢	Qualifiers preserved: the Compositae/sesquiterpene lactone patch-test parenthetical, “at any trimester”, “Wagner 2 or above”, “within 14 days”, “under 1 month of age”.
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 notation inside parentheses.
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, and the ER does name populations that should avoid the intervention, so the empty-state condition does not arise.
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 left empty.

9. Key Interactions

#	Description	Result	Comments
9.1	The section is derived from the ER Key Interactions & Contraindications section	🟢	All eleven items come from the ER’s interaction bullets, ER lines 319-339.
9.2	[caution_items] represent the Key Interactions from the ER, excluding any that are already listed as Contraindications	🟢	All eleven ER interaction bullets are present; none duplicates a Contraindication.
9.3	Individual [caution_items] are formatted as <li></li>	🟢	Each item is a discrete <li> inside the [caution_items] span, lines 590-622.
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.	🟢	Mechanistic rationale removed throughout (e.g. the additive-drowsiness and surface-dose explanations); no dash-clause remains.
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).	🟢	Each ER example-drug list is retained in trimmed form (diazepam, amlodipine, metformin, hydrocortisone, diphenhydramine, povidone-iodine, valerian, chamomile, berberine/beetroot nitrate); none dropped entirely.
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’s Key Interactions & Contraindications section uses no ranking notation inside parentheses.
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 and the ER does describe interactions, so the empty-state condition does not arise.
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 left empty.

10. Protocol

#	Description	Result	Comments
10.1	The section is derived from the ER Protocol section	🟢	Lines 450-483 derive from the ER Therapeutic Protocol section, ER lines 377-383.
10.2	The three sets of [action] items cover the three most important actionable implementation aspects from the ER Protocol section	🟢	Standard topical preparation, vaginal preparation and oral/mucosal rinse are the three regimens serving the High- and Medium-tier benefits; the radiotherapy field protocol serves only a Low-tier, conflicted benefit.
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 four distinct dosing regimens, 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 action fields 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	🟢	The ER’s “Time to effect” bullet (ER line 434) names exactly three aspects and all three are used.
11.2	The sets are picked and ordered by the magnitude of the related benefit	🟢	Ordered wounds/dermatitis (High tier), vaginal courses (Medium), gum inflammation (Medium, slowest), matching benefit magnitude.
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 provides three 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 time fields carry ER-derived content, including the seven-night course length from ER line 408.
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, so the section is retained.

12. Benefits

#	Description	Result	Comments
12.1	The section is derived from the ER Expected Benefits section	🟢	Lines 539-561 derive from the ER Expected Benefits section, ER lines 151-229.
12.2	Key variables are [benefits_high], [benefits_medium], [benefits_low], [benefits_speculative]	🟢	All four tier variables are present and populated.
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 tier is a semicolon-separated list of bare benefit headings; no magnitude, trial detail or mechanism carried through.
12.4	Parenthetical content — including effect sizes, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parenthetical content appears 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 benefit tiers contain items in the ER, so no span needs hiding.

13. Risks

#	Description	Result	Comments
13.1	The section is derived from the ER Potential Risks & Side Effects section	🟢	Lines 634-654 derive from the ER Potential Risks & Side Effects section, ER lines 251-301.
13.2	Key variables are [risks_high], [risks_medium], [risks_low], [risks_speculative]	🟢	All four tier variables are present.
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 tier is a semicolon-separated list of bare risk headings; the odds ratios and application-difficulty percentages from the ER are not carried through.
13.4	Parenthetical content — including frequencies, severity grades, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parenthetical content appears 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.	🟢	The ER states “No risk reaches High” (ER line 253), and [risks_high] is set to style=”display: none” at line 634 rather than filled with empty-state text.

14. Monitoring

#	Description	Result	Comments
14.1	The section is derived from the ER Monitoring section	🟢	Lines 661-800 derive from the ER Monitoring Protocol & Defining Success section, ER lines 462-474.
14.2	All measurable/quantifiable biomarkers from the Monitoring section are listed	🟢	All nine ER biomarker table rows are present, with targets reproduced verbatim.
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.	🟢	Line 798 carries the full cadence condensed from ER line 462, including the weekly radiation grading from the ER table note.

15. Qualitative Assessment

#	Description	Result	Comments
15.1	The section is derived from the ER Monitoring section	🟢	Lines 807-831 derive from the ER’s qualitative marker list, ER lines 478-486.
15.2	All subjective/qualitative biomarkers from the Monitoring section are listed	🟢	All five ER qualitative markers are present, in ER order.

Issues 14/09/2026 03:25

Pass rate 100.00%. No issues found.

Issues 14/09/2026 03:18

1. 1.3 — Evidence hedges dropped in Monitoring: marker_1_why (line 681) states “Objective proof of the main benefit” where the ER says “Objective proof of the main claimed benefit”, and marker_8_why (line 776) states “Screens the hepatic signal during oral use” where the ER says “Screens the animal hepatic signal in anyone using oral preparations” — both drop the qualifier that marks the claim as asserted or animal-derived.

Fixes 14/09/2026 03:18

1. 1.3 — Evidence hedges restored in Monitoring: marker_1_why changed from “Objective proof of the main benefit” to “Objective proof of the main claimed benefit”, and marker_8_why from “Screens the hepatic signal during oral use” to “Screens the animal hepatic signal during oral use”, matching the ER’s qualifiers.

Issues 14/09/2026 03:11

1. 4.5 — One-page budget exceeded: Content volume is roughly double the single A4 budget — the Key Interactions gate carries 11 multi-clause items (lines 590–629), the Monitoring table 9 rows with two-line “Why” cells plus a three-line cadence sentence (lines 675–808), and the Qualitative Assessment 5 items with trailing rationale clauses (lines 815–845), none condensed to their per-section budget.

Fixes 14/09/2026 03:11

1. 4.5 — Monitoring “Why” column condensed: All nine marker_#_why cells were shortened to single-line phrasings (e.g. “Confirms the vaginal environment has normalised, not just symptom relief” → “Confirms the vaginal environment normalised”), collapsing most table rows from two rendered lines to one.
2. 4.5 — Monitoring cadence shortened: The cadence sentence was trimmed of restated nouns (“Baseline before starting” → “Baseline”, “for new eczematous reaction” dropped), cutting it from three rendered lines to two.
3. 4.5 — Qualitative Assessment items condensed: All five items had their trailing rationale clauses stripped or shortened (e.g. “Overall comfort and confidence in the treated area, which is what most users judge success by.” → “Overall comfort and confidence in the treated area.”).
4. 4.5 — Key Interactions drug lists trimmed: Each of the eleven gate items was reduced to one representative example drug (two where the ER spans two mechanisms), per 9.5’s allowance to trim but never drop, and the Radiotherapy item was shortened to “applied after each session, removed before the next”.
5. 4.5 — Protocol and Time-to-effect subs tightened: action_1_sub, action_3_sub and the three time_#_sub cells were reworded more compactly without changing the facts (e.g. “Flower extract applied to clean skin” → “Flower extract on clean skin”).

Issues 14/09/2026 03:03

1. 1.3 — “acute” dropped from wound target: [marker_1_target] at line 681 reads “near-complete closure of shallow wounds by 8–10 days”; the ER table restricts the target to “shallow acute wounds”, and the ER records repeated failure in chronic leg and foot ulcers, so the omission broadens the claim.
2. 11.4 — time_2_sub restates label and value: [time_2_sub] at line 515 reads “Vaginal courses are judged at this point.”, which merely repeats [time_2_label] and [time_2_value] and carries no additional ER content.

Fixes 14/09/2026 03:03

1. 1.3 — “acute” restored to wound target: [marker_1_target] changed from “near-complete closure of shallow wounds by 8–10 days” to “near-complete closure of shallow acute wounds by 8–10 days”, matching the ER biomarker table.
2. 11.4 — time_2_sub no longer restates label: [time_2_sub] changed from “Vaginal courses are judged at this point.” to “Fixed seven-night course; outcome judged at the end of this window.”, adding the ER’s fixed seven-night course length.

Issues 14/09/2026 02:51

1. 2.5 / 2.6 / 2.9 — Imperative in Radiotherapy interaction: The Radiotherapy entry in [caution_items] reads “apply after each session and remove before the next”, an imperative that advises and directly addresses the reader, unlike every other gate item, which is a noun phrase.
2. 4.5 — Content overruns one A4 page: At the sheet’s own print geometry the populated sections total roughly twice the ~1030 px A4 budget, driven mainly by the eleven [caution_items] (~25 wrapped lines) and the nine-row Monitoring table.

Fixes 14/09/2026 02:51

1. 2.5 / 2.6 / 2.9 — Imperative in Radiotherapy interaction: Rewrote the Radiotherapy entry in [caution_items] from the imperative “apply after each session and remove before the next” to the passive “ointment applied after each session and removed before the next”, matching the descriptive voice of the other gate items.
2. 4.5 — Key Interactions condensed: Trimmed all eleven [caution_items] by shortening the example drug lists to two or three representatives each and replacing prose connectors with a parenthetical qualifier (e.g. “oral use with benzodiazepines (diazepam, lorazepam) or barbiturates (phenobarbital)” became “oral use (diazepam, phenobarbital)”), cutting the gate from roughly 25 to 17 wrapped lines without dropping any interaction.
3. 4.5 — Monitoring cells and cadence condensed: Shortened six marker “Why” cells, one “Target” cell and [monitoring_cadence] (e.g. “Quantifies gum inflammation and plaque rather than relying on bleeding impressions” became “Quantifies gum inflammation and plaque objectively”), keeping all nine biomarkers and every cadence interval.
4. 4.5 — Qualitative, Protocol and Time cells condensed: Tightened all five [qualitative_item] entries, [action_1_sub], [action_3_sub] and [time_3_sub] by removing redundant restatement (e.g. [time_3_sub] “Gum-inflammation trials detect differences at three months; no effect accumulates over months” became “Detected at three months; no effect accumulates beyond that”).