Audit: QRS - Arnica for Health & Longevity

Audit conducted on 17/08/2026 03:48 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.	🟢	All content traces to ER text: at-a-glance to Conclusion, protocol cells to Therapeutic Protocol, gates to Key Interactions & Contraindications, tiers to Expected Benefits / Potential Risks & Side Effects, markers to the Monitoring Protocol & Defining Success table.
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 preserved, e.g. “same-day relief is not expected” (ER Practical Considerations) and “no change in performance or muscle damage” (ER Low benefit).
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 keep absolute force (“Pregnancy at any stage and breastfeeding”); interactions keep the ER’s own “Caution” / “Monitor” verbs.
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.	🟢	Benefit- and risk-modifying factors are not surfaced as gates; the gates carry only Key Interactions & Contraindications content.
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, study names, NCT identifiers, expert names, or brands 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.	🟢	Neutral, evidence-first register matching the ER, including its two-preparations framing.
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 remaining readable; tiers and gates give the reader an actionable picture.
2.3	The QRS reads as a trusted, knowledgeable guide rather than a prescriptive doctor	🟢	Facts are stated, not ordered; no imperative constructions.
2.4	The QRS avoids language that implies medical or clinical advice	🟢	No advice verbs; entries are descriptive noun phrases and observed findings.
2.5	The QRS “presents information” instead of “providing guidance”, “recommending”, or “advising”	🟢	No “recommend”, “advise”, or “should” in the document body (only a CSS comment inherited from the template contains the word “Must”).
2.6	The QRS never addresses “the reader” directly — it presents evidence, not guidance	🟢	No second-person address anywhere.
2.7	The QRS is written in plain language, avoiding unnecessary medical jargon	🟢	Plain language throughout; technical terms retained only where the ER itself relies on them (e.g., Compositae patch test, INR).
2.8	Information is presented in a concise and very compact manner	🟢	Every field is condensed to a short phrase; no prose paragraphs outside At-A-Glance.
2.9	It DOES NOT address the reader directly	🟢	Confirmed by scan: no “you”/”your” in the rendered content.
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.	🟢	Content assumes a proactive, risk-aware reader: patch testing, INR tracking, species verification.
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 and monitoring entries assume willingness to follow a multi-week regimen with laboratory follow-up.
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.	🟢	Depth of gates, markers and cadence is beyond general-population framing.
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.	🟢	Risk/benefit weighting mirrors the ER: modest topical signal, hard allergy and ingestion limits, forgone-benefit risk.
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.	🟢	The term “anti-aging” does not appear.
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 terminology used (“pellets”, “tincture”, “adverse”-grade phrasing); no colloquialisms.

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, gate headings, tier labels and table headers are byte-identical to the template.
3.2	All “…” from the [qrs_template] are present in the the QRS.	🟢	All template spans present; marker_#* expanded to marker_1..5 and qualitative_item# to 1..6 as intended.
3.3	Spans that are not addressed in a checklist item are left unchanged	🟢	Diff against the template shows changes confined to variable regions; CSS, structure and the website=”…” spans 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 High benefit tier carries an explanatory sentence rather than an empty-state phrase, and is handled under 12.5.
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 protocol”, “Time of day”, “Competing approach — homeopathic oral”, and all six interaction labels.
4.3	Labels are not paraphrased, abbreviated, or invented.	🟢	Time-to-effect labels are lifted from ER wording (“joint pain”, “bruising after a procedure”, “Delayed-Onset Muscle Soreness After Hard Training”); nothing invented.
4.4	The QRS DOES NOT use emoji indicators (no 🟩, 🟥, 🟨, etc.). Color and emphasis are conveyed through CSS and bold labels.	🟢	Scan confirms no emoji characters in the file.
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.	🟢	Each section is condensed to the per-section budget: 8 gate items, 6 interactions, one line per tier, 5 markers, 6 qualitative items.

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 is the first element after “<!doctype html>” (lines 2-14).
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 opens at line 3 and closes at line 13 with “—”.
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; not rendered or duplicated on the sheet.
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: "00:03" 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]”	🟢	“er_filename: arnica_2026-0825-0132_Opus_ER.md” (line 4) matches the source ER.
5.6	Version of the QRS.md file used to create the document is stated as “qrs_prompt_version: [Version of QRS.md]”	🟢	“qrs_prompt_version: 26.7.02” matches 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)	🟢	“qrs_creation_date: 2026-0817-0252” is in YYYY-MMDD-HHMM form.
5.8	The nickname of the AI used to create the document is stated as “qrs_creator_ai_nickname: [qrs_creator_ai_nickname]”	🟢	“qrs_creator_ai_nickname: Opus” present at line 7.
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]”	🟢	“qrs_creator_ai_fullname: Opus 5” present at line 8.
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, no extra qualifier.
5.12	The filename of the document is stated as “qrs_filename: [filename of this document]”	🟢	“qrs_filename: arnica_2026-0825-0132_Opus_QRS.html” matches the file on disk.
5.13	All frontmatter values are trimmed: no leading or trailing whitespace, no surrounding quotes unless the value contains a colon, bracket, or leading special character that requires YAML quoting.	🟢	Values are clean and consistently formatted; 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 &)	🟢	Title is “Arnica for Health & Longevity - Quick Reference Sheet”, with the ampersand 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 &)	🟢	[header_topic] is “Arnica for Health & Longevity”, matching canonical_topic.
6.3	[header_subline_date] is set to [qrs_creation_date reformatted as MM/DD/YYYY]	🟢	qrs_creation_date 2026-0817-0252 renders as “08/17/2026”.
6.4	[header_subline_model] is set to [qrs_creator_ai_fullname]	🟢	[header_subline_model] is “Opus 5”, matching qrs_creator_ai_fullname.
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 template subline; 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	🟢	Condenses the ER Conclusion: the two-preparation split, the clearest topical signals, and the documented harms.
7.2	[at_a_glance] is no longer than 60 words	🟢	Word count is exactly 60.
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 (paragraphs 1, 2 and 3).
7.4	It DOES NOT use acronyms or technical classifications that require specialist knowledge, uses plain-language terms instead	🟢	No acronyms; “homeopathic” is rendered as “extreme dilutions by mouth” and NF-κB / Asteraceae are absent.
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 effect sizes, relative risks or statistical results.

8. Contraindications

#	Description	Result	Comments
8.1	The section is derived from the ER Key Interactions & Contraindications section	🟢	All eight items come from the ER’s “Populations who should avoid Arnica” list plus the absolute contraindication in the “Other interventions” bullet.
8.2	[stop_items] represent the Contraindications from the ER	🟢	All seven avoid-population bullets plus the open-wound/mucous-membrane contraindication are represented.
8.3	Individual [stop_items] are formatted as <li></li>	🟢	Each item is a discrete <li> inside the [stop_items] span.
8.4	Items are as concise as possible. No trailing explanations, no elaborations, no mechanistic rationale, no attributions, no citations, no study details. No content after an em-dash, en-dash, or hyphen-dash (e.g., “— dose reduction required”, “— reduced efficacy”) — these trailing clauses are stripped. Just the key fact.	🟢	Items are bare facts; no rationale, citation or trailing dash clause.
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: patch-test basis, INR 2.0-3.0 over three months, Child-Pugh B/C, CKD stage 4-5, age under 12, oral-herbal route.
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 section is populated, correctly, since the ER names multiple populations that should avoid arnica.
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 six items come from the ER Key Interactions & Contraindications bullets.
9.2	[caution_items] represent the Key Interactions from the ER, excluding any that are already listed as Contraindications	🟢	The six interaction bullets are carried; the “Other interventions” bullet is excluded because its content is an absolute contraindication already in [stop_items].
9.3	Individual [caution_items] are formatted as <li></li>	🟢	Each item is a discrete <li> inside the [caution_items] span.
9.4	Items are as concise as possible. No trailing explanations, no elaborations, no mechanistic rationale, no attributions, no citations, no study details. No content after an em-dash, en-dash, or hyphen-dash (e.g., “— dose reduction required”, “— reduced efficacy”) — these trailing clauses are stripped. Just the key fact.	🟢	Each item is reduced to label plus the ER verdict (“Caution”, “Caution, herbal form”, “Monitor”); mechanism and mitigation sentences are 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).	🟢	All ER example-drug lists are preserved verbatim in parentheses.
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 section is populated, correctly, since the ER names six 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 action sets come from the ER Therapeutic Protocol bullets.
10.2	The three sets of [action] items cover the three most important actionable implementation aspects from the ER Protocol section	🟢	Covers the tested regimen, the schedule, and the competing homeopathic route — the three actionable aspects in the ER.
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 names more than three 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 fields carry ER-derived content (50 g tincture per 100 g gel, 1:20 extract, morning/evening, 6C-30C pellets).

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 pain, post-procedure bruising and post-training soreness are the three time-to-effect aspects the ER supplies.
11.2	The sets are picked and ordered by the magnitude of the related benefit	🟢	Ordered by benefit magnitude: two Medium-tier outcomes first, the Low-tier soreness outcome last.
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 fields carry ER-derived content (“Two to three weeks”, “Days 5 to 7”, “72 hours”).
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 row is retained.

12. Benefits

#	Description	Result	Comments
12.1	The section is derived from the ER Expected Benefits section	🟢	Tier contents mirror the ER Expected Benefits subsection headings.
12.2	Key variables are [benefits_high], [benefits_medium], [benefits_low], [benefits_speculative]	🟢	All four benefit variables are present in the document.
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 benefit names with no effect sizes or study detail.
12.4	Parenthetical content — including effect sizes, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parenthetical content is carried into 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.	🟢	The ER grades no benefit High, and [benefits_high] is hidden with style=”display: none” plus an HTML comment quoting the ER basis; no empty-state phrasing is rendered.

13. Risks

#	Description	Result	Comments
13.1	The section is derived from the ER Potential Risks & Side Effects section	🟢	Tier contents mirror the ER Potential Risks & Side Effects subsection headings.
13.2	Key variables are [risks_high], [risks_medium], [risks_low], [risks_speculative]	🟢	All four risk variables are present and populated.
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 lists risk names only; frequencies, relative risks and mechanisms are stripped.
13.4	Parenthetical content — including frequencies, severity grades, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parenthetical content is carried into 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.	N/A	All four risk tiers contain items in the ER, so no span needs hiding.

14. Monitoring

#	Description	Result	Comments
14.1	The section is derived from the ER Monitoring section	🟢	All five markers come from the ER Monitoring Protocol & Defining Success biomarker table.
14.2	All measurable/quantifiable biomarkers from the Monitoring section are listed	🟢	All five ER biomarkers are listed: patch test, INR, platelet count, ALT, hs-CRP, with ER optimal ranges intact.
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.	🟢	Cadence carries the ER’s daily site inspection, 3- and 6-week symptom review, INR baseline plus 2 weeks, and 4-week then 6-monthly clotting/liver checks.

15. Qualitative Assessment

#	Description	Result	Comments
15.1	The section is derived from the ER Monitoring section	🟢	The six items come from the ER’s “Qualitative markers worth tracking” list.
15.2	All subjective/qualitative biomarkers from the Monitoring section are listed	🟢	All six ER qualitative markers are present, in ER order.

Issues 17/08/2026 03:48

Pass rate 100.00%. No issues found.

Issues 17/08/2026 03:41

1. 1.3 — Allergy risk overstated in marker: marker_1_why (line 645) states the patch test “Detects the delayed daisy-family allergy before exposure establishes it”, dropping the ER’s “repeated” (ER lines 230 and 417), which strengthens the claim from repeated contact to any exposure.

Fixes 17/08/2026 03:41

1. 1.3 — Allergy risk overstated in marker: Restored the ER’s qualifier in marker_1_why, from “before exposure establishes it” to “before repeated exposure establishes it”, matching ER lines 230 and 417.

Issues 17/08/2026 03:34

1. 2.7 — ALT abbreviation left unexpanded: [marker_4_name] at line 672 is the bare abbreviation “ALT” while the two other abbreviated markers in the same table are expanded (“INR (international normalised ratio)” line 650, “hs-CRP (high-sensitivity C-reactive protein)” line 683); the ER supplies “alanine aminotransferase” at line 420.

Fixes 17/08/2026 03:34

1. 2.7 — ALT abbreviation expanded: [marker_4_name] changed from “ALT” to “ALT (alanine aminotransferase)”, matching the expansion style already used for INR and hs-CRP in the same table and the ER’s own gloss at line 420.

Issues 17/08/2026 03:26

1. 1.3 — Vitamin E caution broadened: In [caution_items] (line 588) the ER’s “high-dose vitamin E” and “garlic extract” are reduced to “vitamin E” and “garlic”, extending the bleeding-tendency caution beyond the high-dose vitamin E the ER names.

Fixes 17/08/2026 03:26

1. 1.3 — Vitamin E caution broadened: Restored the ER’s exact drug list in the bleeding-tendency interaction item, changing “garlic, vitamin E” back to “garlic extract, high-dose vitamin E”.

Issues 17/08/2026 03:21

1. 4.5 — Sheet overruns one A4 page: The combined content exceeds the one-page budget — the eight contraindications (lines 571–578) and six interactions (lines 586–591) each wrap to roughly fifteen lines, and the long Monitoring “Why” cells (lines 647, 691), the three-line cadence (lines 699–701), the four-line action_3_sub (lines 483–484) and the six qualitative items push the sheet onto a second page.

Fixes 17/08/2026 03:21

1. 4.5 — Contraindication items condensed: Trimmed the four longest stop items (“Known arnica” → “Arnica”, “at the application site” → “at the site”, dropped “when anticoagulated” from the INR item, “Child-Pugh Class B or C liver disease or chronic kidney disease stage 4–5” → “Child-Pugh B or C liver disease or kidney disease stage 4–5”), preserving every threshold, staging and time window.
2. 4.5 — Interaction drug list shortened: Reduced the bleeding-tendency supplement list to “fish oil, ginkgo, garlic, vitamin E, nattokinase, curcumin”, keeping all six named examples while dropping one wrapped line from the gate.
3. 4.5 — Protocol sub-cells shortened: Rewrote action_2_sub as “For soreness after training: immediately post-exercise, then four-hourly while awake” and cut the redundant “Neither approach is the default” tail from action_3_sub.
4. 4.5 — Time-to-effect sub-cells shortened: Condensed time_1_sub to “Twice-daily application; same-day relief is not expected” and time_3_sub to “Lower soreness at 72 hours only; no change in performance or muscle damage”.
5. 4.5 — Monitoring cells and cadence condensed: Shortened marker_1_why and rewrote the cadence line more tightly (“symptoms at 3 and 6 weeks”, “at 4 weeks then 6-monthly”), keeping every interval from the ER.
6. 4.5 — Qualitative items tightened: Reworded items 1, 3 and 6 to single-line phrasings without losing the scoring interval, timepoints or the 6-week futility marker.
7. 4.5 / 1.1 — marker_5_why restored to ER sense: Replaced the garbled “beyond a skin-limited agent” with “Separates local joint disease from a systemic inflammatory driver a skin-limited agent cannot reach”, matching the ER wording and shortening the cell.

Issues 17/08/2026 03:15

1. 1.1 — Sensitisation qualifier dropped: [marker_1_why] at line 647 reads “before exposure establishes it”, dropping the ER’s “repeated” (ER line 417: “Detects the delayed daisy-family allergy before repeated exposure establishes it”), which implies a single exposure establishes the allergy.

Fixes 17/08/2026 03:15

1. 1.1 — Sensitisation qualifier restored: [marker_1_why] changed from “Detects the delayed daisy-family allergy before exposure establishes it” to “Detects the delayed daisy-family allergy before repeated exposure establishes it”, matching the ER wording.

Issues 17/08/2026 03:08

1. 4.5 — Sheet overflows one A4 page: Rendered height runs to roughly 1.6 A4 pages; the Contraindications gate (lines 571-578, ~19 wrapped lines), the five Monitoring “Why” cells and the 253-character cadence string (lines 696-703), and the 144-character action_3_sub (lines 482-486) are carried at full ER length rather than condensed to the per-section budget.

Fixes 17/08/2026 03:08

1. 4.5 — Contraindications gate condensed: Tightened all eight stop items (e.g. “Known allergy to arnica or daisy-family plants, including a positive sesquiterpene lactone or Compositae patch test” → “Known arnica or daisy-family allergy (positive sesquiterpene lactone or Compositae patch test)”), removing roughly four wrapped lines while keeping every item and every threshold, staging and time-window qualifier.
2. 4.5 — Interaction verdicts shortened: Replaced the repeated “Caution with herbal arnica” tail with “Caution, herbal form” in the vitamin K antagonist and DOAC/heparin items; all parenthetical drug lists retained.
3. 4.5 — Monitoring “Why” cells trimmed: Shortened all five rationale cells (e.g. marker_3_why from “Establishes the reserve against which the herb’s platelet-inhibiting effect is judged” to “Reserve against which the herb’s platelet inhibition is judged”), cutting table height without dropping a biomarker.
4. 4.5 — Cadence string compressed: Reduced [monitoring_cadence] from 253 to ~200 characters (“Application site inspected daily for the first week” → “Site inspected daily for week 1”; “every 6 months” → “6-monthly”), preserving every monitoring interval.
5. 4.5 — Protocol sub-cells tightened: Condensed action_3_sub (“Typically five pellets three times daily, starting the evening before a procedure and continuing 7–14 days after” → “Five pellets three times daily, from the evening before a procedure to 7–14 days after”) and action_2_sub (“then every four hours while awake” → “then four-hourly while awake”).

Issues 17/08/2026 02:57

1. 12.3 — “Conflicted” qualifier retained in benefits: The evidence qualifier “conflicted” is carried through three times (line 546 and twice on line 551), although the section preamble states that the tier already encodes evidence strength and qualifiers are redundant detail.
2. 7.4 — Clinical-register word in At-A-Glance: Line 435 reads “The clearest signal for the strong form”, where “signal” in the evidence-of-effect sense is a clinical-register word a non-specialist would not use unprompted with that meaning.

Fixes 17/08/2026 02:57

1. 12.3 — “Conflicted” qualifier removed from benefits: Deleted the three redundant “conflicted” qualifiers from benefits_medium and benefits_low, leaving the plain benefit headings, since the tier label already encodes evidence strength.
2. 7.4 — Clinical-register word in At-A-Glance: Replaced “The clearest signal for the strong form” with “The clearest evidence for the strong form”; the span remains at 60 words.