Audit: QRS - Ibogaine for Health & Longevity

Audit conducted on 04/08/2026 20:10 using AI4L / Opus 5

Iterations

Summary

Items	Count
Total	91
Passed	82
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.	🟢	Verified item by item against the ER: doses (line 402), test dose and booster (412), morning fasted dosing (408), time to effect (455, 435), all 10 biomarker rows (483-492), cadence (479, 494), qualitative markers (498-503), benefit and risk tier headings (176-228, 252-336), contraindications and interactions (356-374).
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 is carried through: “apparently lasting change” mirrors ER line 529 “appears to trigger lasting change”; “appear to reduce, not eliminate” mirrors ER 531 “has not been eliminated”.
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 found; absolute contraindications stay absolute and caution-level interactions stay caution-level.
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.	🟢	Categories are preserved: ER contraindications map to [stop_items], ER caution-level interactions map to [caution_items], ER benefit and risk tiers map to the matching QRS tiers.
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 contains no PMIDs, citations, expert names, NCT identifiers, or brand names.
1.6	The QRS does not introduce new attributions.	🟢	No attributions of any kind appear 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.	🟢	Tone matches the ER: measured, evidence-graded, explicit about uncertainty.
2.2	The tone of the QRS is simultaneously expert, accessible, objective, and data-driven, but also empowering and encouraging	🟢	Expert, objective and data-driven throughout while remaining accessible.
2.3	The QRS reads as a trusted, knowledgeable guide rather than a prescriptive doctor	🟢	Presents evidence and thresholds rather than issuing instructions.
2.4	The QRS avoids language that implies medical or clinical advice	🟢	No advisory constructions; the fixed footer disclaimer is template content.
2.5	The QRS “presents information” instead of “providing guidance”, “recommending”, or “advising”	🟢	Content is stated declaratively, not as recommendation or advice.
2.6	The QRS never addresses “the reader” directly — it presents evidence, not guidance	🟢	No second-person address anywhere in the document (verified by search for “you”/”your”).
2.7	The QRS is written in plain language, avoiding unnecessary medical jargon	🟢	Plain language used, with abbreviations expanded where budget allows (e.g., “Corrected QT interval (QTc)”, “Estimated glomerular filtration rate (eGFR)”, “Thyroid-stimulating hormone (TSH)”, “New York Heart Association”).
2.8	Information is presented in a concise and very compact manner	🟢	Every entry is a compact phrase; benefits and risks are reduced to tier headings only.
2.9	It DOES NOT address the reader directly	🟢	No direct address of the reader.
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 is pitched at risk-aware adults evaluating the intervention (screening thresholds, functional biomarker 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.	🟢	Assumes willingness to undertake genotyping, echocardiography, multi-day telemetry and structured washouts.
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 audience; assumes engagement with demanding screening and monitoring protocols.
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.	🟢	Framing reflects the audience, including the functional rather than conventional biomarker ranges.
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” usage anywhere in the QRS.
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 throughout (“ventricular arrhythmia”, “adverse”, “hepatic enzyme elevation”); the plain-language At-A-Glance wording is required by item 7.4.

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 verified verbatim against [qrs_template]: “Protocol”, “Time to effect”, “Benefits”, “Risk & Side Effects”, “Monitoring”, “Qualitative Assessment”, “Contraindications”, “Key Interactions”, tier labels, and “Marker”/”Target”/”Why”.
3.2	All “<span data-qrs-var=”NAME”>…</span>” from the [qrs_template] are present in the the QRS.	🟢	All 26 distinct template variables are present, with marker_#* expanded to 10 rows and qualitative_item# expanded to 6 items.
3.3	Spans that are not addressed in a checklist item are left unchanged	🟢	Normalised structural diff against [qrs_template] shows no change outside the data-qrs-var regions; the three website= spans, all CSS, 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	N/A — no source ER section is empty; the ER Expected Benefits High tier carries explanatory prose and is handled by item 12.5, not by empty-state phrasing.
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 used verbatim: “Standard single flood dose”, “Single versus split dosing”, “Timing within the day” (ER 402, 412, 408) and all six qualitative labels (ER 498-503).
4.3	Labels are not paraphrased, abbreviated, or invented.	🟢	Labels are taken verbatim from the ER; biomarker row names are condensed only within the one-page budget allowed by item 4.5.
4.4	The QRS DOES NOT use emoji indicators (no 🟩, 🟥, 🟨, etc.). Color and emphasis are conveyed through CSS and bold labels.	🟢	No emoji indicators present; the ER tier emojis 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 rather than extended: benefits and risks carry tier headings only, contraindications are single-clause items, and the cadence paragraph is reduced to one sentence.

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.	🟢	The metadata comment is the first element after “<!doctype html>” (lines 2-14), before any other comment, head or body 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 line 3 and “—” at line 13; the leading title text sits before the opening delimiter.
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; nothing on the sheet surfaces it.
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 and unquoted except duration: "00:04", which contains a colon and therefore requires quoting.
5.5	The filename of the source ER is stated as “er_filename: [er_filename]”	🟢	er_filename: ibogaine_2026-0804-1609_Opus_ER.md 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: 2026-0804-1909 follows the YYYY-MMDD-HHMM format.
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.
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.
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 the nickname plus the version number with no additional qualifier.
5.12	The filename of the document is stated as “qrs_filename: [filename of this document]”	🟢	qrs_filename: ibogaine_2026-0804-1609_Opus_QRS.html matches the actual filename.
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.	🟢	All frontmatter values are clean; only the colon-bearing duration value is quoted.

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., &amp; for &)	🟢	<title>Ibogaine for Health &amp; Longevity - Quick Reference Sheet</title> matches the ER canonical_topic 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., &amp; for &)	🟢	[header_topic] is “Ibogaine for Health & Longevity”, matching the ER canonical_topic.
6.3	[header_subline_date] is set to [qrs_creation_date reformatted as MM/DD/YYYY]	🟢	“08/04/2026” is qrs_creation_date 2026-0804 in MM/DD/YYYY.
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, version stamp, alternate-names line, 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 three-paragraph ER Conclusion (lines 529-533) into the clearest signals plus the cardiac hazard.
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 traces to a distinct ER Conclusion passage (529 for the signals and the uncontrolled-study caveat, 531 for the fatal rhythm disturbances and their mitigability).
7.4	It DOES NOT use acronyms or technical classifications that require specialist knowledge, uses plain-language terms instead	🟢	Uses plain terms throughout (“plant-derived compound”, “day-long altered state”, “fatal heart-rhythm disturbances”, “comparison groups”); no acronyms or specialist classifications.
7.5	It DOES NOT cite specific trials (names, years, sample sizes, p-values)	🟢	No study 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 14 items trace to the ER Key Interactions & Contraindications section (lines 356-374).
8.2	[stop_items] represent the Contraindications from the ER	🟢	All 11 absolute exclusions from ER line 374 plus the absolute contraindications stated in ER 356, 358, 362 and 364 are represented.
8.3	Individual [stop_items] are formatted as <li></li>	🟢	All 14 items are individual <li> elements 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 with no rationale, attribution, 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).	🟢	Thresholds and staging preserved: “>450 ms (men), >460 ms (women)”, “New York Heart Association Class III-IV”, “within 6 months”, “<3.8 mmol/L”, “<0.75 mmol/L”, “Child-Pugh Class B or C”, “eGFR <30 mL/min/1.73 m2”, “before 50”.
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	N/A — the ER Key Interactions & Contraindications section uses no ranking notation inside parentheses.
8.7	If no [stop_items] are present the section is left empty	N/A	N/A — 14 [stop_items] are present.

9. Key Interactions

#	Description	Result	Comments
9.1	The section is derived from the ER Key Interactions & Contraindications section	🟢	All 7 items trace to the ER Key Interactions & Contraindications section (lines 360-372).
9.2	[caution_items] represent the Key Interactions from the ER, excluding any that are already listed as Contraindications	🟢	The seven caution-level ER interaction bullets are present; the absolute ones (QT-prolonging medications, methadone maintenance, monoamine oxidase inhibitors) correctly appear under Contraindications instead.
9.3	Individual [caution_items] are formatted as <li></li>	🟢	All 7 items are individual <li> elements 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.	🟢	Items are bare facts with no mechanistic rationale or trailing dash clause.
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 and qualifiers preserved: CYP2D6 inhibitor list with the “fluoxetine 5-week washout” window, SSRI/SNRI examples, the over-the-counter list, the supplement list, “(monitor rather than avoid)”, and “in the preceding week”.
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	N/A — the ER Key Interactions & Contraindications section uses no ranking notation inside parentheses.
9.7	If no [caution_items] are present the section is left empty	N/A	N/A — 7 [caution_items] are present.

10. Protocol

#	Description	Result	Comments
10.1	The section is derived from the ER Protocol section	🟢	All three action sets derive from the ER Therapeutic Protocol section (lines 402, 408, 412).
10.2	The three sets of [action] items cover the three most important actionable implementation aspects from the ER Protocol section	🟢	Covers dose magnitude, dose structure, and dose timing - the three directly executable elements of the ER protocol.
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	N/A — three distinct actionable implementation aspects are present in the ER Therapeutic Protocol section.
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 substantive ER-derived content.

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	🟢	Covers the three time-to-effect aspects stated in ER line 455: mood/trauma/cognitive change, opioid withdrawal, and craving reduction.
11.2	The sets are picked and ordered by the magnitude of the related benefit	🟢	Ordered by magnitude: the mood/trauma outcome carries the ER’s largest reported effects (Cohen’s d 2.13-2.80, line 192), followed by withdrawal suppression and craving reduction.
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	N/A — three distinct time-to-effect aspects are present in the ER.
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 substantive ER-derived content (ER 455 and 435).
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	N/A — the ER provides time-to-effect information (Practical Considerations, line 455).

12. Benefits

#	Description	Result	Comments
12.1	The section is derived from the ER Expected Benefits section	🟢	All tiers derive from the ER Expected Benefits section (lines 170-228).
12.2	Key variables are [benefits_high], [benefits_medium], [benefits_low], [benefits_speculative]	🟢	All four benefit variables are present and correctly assigned.
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 ER sub-section headings with no magnitudes or mechanisms.
12.4	Parenthetical content — including effect sizes, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parenthetical content carried over.
12.5	If no items of a specific sub-section (high, medium, low, speculative) are present the respective <SPAN> is set to “display=none”, not filled with “None documented in human trials to date” or similar empty-state phrasing.	🟢	The ER High tier holds no qualifying benefit (line 172), and [benefits_high] is set to style=”display: none” rather than filled with empty-state text.

13. Risks

#	Description	Result	Comments
13.1	The section is derived from the ER Potential Risks & Side Effects section	🟢	All tiers derive from the ER Potential Risks & Side Effects section (lines 250-336).
13.2	Key variables are [risks_high], [risks_medium], [risks_low], [risks_speculative]	🟢	All four risk variables are present and correctly assigned.
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 ER sub-section headings with no frequencies or mechanisms.
13.4	Parenthetical content — including frequencies, severity grades, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parenthetical content carried over; the ER’s Conflicted markers are correctly dropped.
13.5	If no items of a specific sub-section (high, medium, low, speculative) are present the respective <SPAN> is set to “display=none”, not filled with “None documented in human trials to date” or similar empty-state phrasing.	N/A	N/A — all four risk sub-sections (high, medium, low, speculative) carry items.

14. Monitoring

#	Description	Result	Comments
14.1	The section is derived from the ER Monitoring section	🟢	All 10 rows derive from the ER Monitoring Protocol & Defining Success table (lines 481-492).
14.2	All measurable/quantifiable biomarkers from the Monitoring section are listed	🟢	All 10 ER biomarkers are listed: QTc, potassium, magnesium, ionised calcium, ALT/AST, eGFR, CYP2D6 genotype, TSH, complete blood count, and echocardiogram.
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.	🟢	Populated with the full ER cadence (lines 479 and 494): baseline within 30 days, morning-of repeat, 48-hour telemetry, 24/72-hour and one-week checks, four-week liver and kidney function, and three-month plus six-to-twelve-month follow-up.

15. Qualitative Assessment

#	Description	Result	Comments
15.1	The section is derived from the ER Monitoring section	🟢	All six items derive from the ER Monitoring Protocol & Defining Success section (lines 498-503).
15.2	All subjective/qualitative biomarkers from the Monitoring section are listed	🟢	All six ER qualitative markers are present: craving, sleep, cognitive clarity, emotional reactivity, motivation/anhedonia, and behavioural flexibility.

Issues 04/08/2026 20:10

Pass rate 100.00%. No issues found.

Issues 04/08/2026 19:59

1. 1.2 / 1.3 — Hedges dropped in At-A-Glance: [at_a_glance] renders the ER’s “they rest almost entirely on small studies with no comparison group” (ER line 529) as “all from small studies without comparison groups” and the ER’s “appears to be reducible through screening, mineral correction and multi-day monitoring” (ER line 531) as “screening and monitoring reduce, not eliminate, that hazard”, strengthening both claims.
2. 1.1 — Booster timing over-specified: [action_2_sub] (QRS lines 470-471) states the optional 1–3 mg/kg booster is given “the next day”, whereas ER line 412 says “on a subsequent day”.

Fixes 04/08/2026 19:59

1. 1.2 / 1.3 — At-A-Glance hedges restored: Changed “all from small studies without comparison groups” to “nearly all from small studies without comparison groups” and “screening and monitoring reduce, not eliminate, that hazard” to “screening and monitoring appear to reduce, not eliminate, that hazard”, matching the ER’s “almost entirely” and “appears to be reducible”. The section remains within the 60-word limit.
2. 1.1 — Booster timing matched to ER: Changed [action_2_sub] from “optional 1–3 mg/kg booster the next day” to “optional 1–3 mg/kg booster on a subsequent day”, matching ER line 412.

Issues 04/08/2026 19:50

1. 7.2 — At-A-Glance exceeds 60 words: The [at_a_glance] span (lines 434–438) contains 61 words, one over the limit set by the checklist item.
2. 4.5 — Sheet overflows one A4 page: Measured against the template’s own type metrics, the populated sheet runs to roughly two A4 pages — the 14-item Contraindications gate alone occupies ~20 wrapped lines, and the Risks card, 10-row Monitoring table, cadence paragraph and 6-item Qualitative Assessment all fall past the first-page boundary.

Fixes 04/08/2026 19:50

1. 7.2 — At-A-Glance trimmed under word cap: Reworded [at_a_glance] (“improved mood, trauma symptoms and thinking” → “better mood, trauma symptoms and thinking”; “screening and monitoring appear to reduce” → “screening and monitoring reduce”), bringing it from 61 to 58 words.
2. 4.5 — Sheet condensed toward one A4 page: Tightened every over-long span without dropping any required item or qualifier — Protocol and Time-to-effect sub-lines shortened (e.g. “Effects are essentially immediate, within the first 24–48 hours.” → “Effects are essentially immediate.”), Contraindications 8 and 12 reduced to single lines, Key Interactions drug lists trimmed, all ten Monitoring “Why” cells and four marker names shortened, the cadence paragraph tightened, and the six Qualitative Assessment descriptions cut back.

Issues 04/08/2026 19:43

1. 2.7 — Unexpanded abbreviations not in ER: “NYHA Class III–IV” (line 583) and “SAMe” (line 616) are abbreviations introduced by the QRS that never appear in the ER (which writes “New York Heart Association Class III or IV” and “S-adenosylmethionine”) and are never expanded anywhere on the sheet.
2. 4.3 — Monitoring row labels altered: Three biomarker names deviate from the ER table — “Serum and red blood cell magnesium” for “Serum magnesium and red blood cell magnesium” (line 705), “CYP2D6 genotype and metaboliser status” for “CYP2D6 genotype and predicted metaboliser status” (line 763), and “Complete blood count, haemoglobin and haematocrit” for “Complete blood count with haemoglobin and haematocrit” (line 789).

Fixes 04/08/2026 19:43

1. 2.7 — Abbreviations expanded to ER wording: “NYHA Class III–IV” in [stop_items] was replaced with “New York Heart Association Class III–IV”, and “SAMe” in [caution_items] was replaced with “S-adenosylmethionine”, matching the ER’s own terms.
2. 4.3 — Monitoring row labels restored: The three altered biomarker names were restored to the ER wording — “Serum magnesium and red blood cell magnesium”, “CYP2D6 genotype and predicted metaboliser status”, and “Complete blood count with haemoglobin and haematocrit”.

Issues 04/08/2026 19:37

1. 4.5 — Sheet renders to about two A4 pages: Estimated rendered height is roughly 2110 px against the ~1033 px usable on an A4 print page at the template’s 12 mm margins; the Monitoring card (~517 px) and Contraindications gate (~457 px) alone consume most of the budget, and neither was condensed to a per-section budget.
2. 1.1 — Booster timing narrowed: action_2_sub states the 1–3 mg/kg booster is added “the next day”, whereas the ER Therapeutic Protocol section says providers add it “on a subsequent day”.

Fixes 04/08/2026 19:37

1. 4.5 — Monitoring rows condensed: Shortened marker names and rationale cells (e.g. “Direct measure of the window in which fatal arrhythmia occurs” → “The window in which fatal arrhythmia occurs”, “Serum magnesium and red blood cell magnesium” → “Serum and red blood cell magnesium”) so most table rows collapse to a single wrapped line. All ten biomarkers and their targets are retained as required by item 14.2.
2. 4.5 — Monitoring cadence tightened: Reduced the cadence sentence to “at 24 and 72 hours and one week” and “if abnormal or repeat treatment is contemplated”, removing a wrapped line without dropping any scheduled timepoint.
3. 4.5 — Contraindications gate tightened: Reworded three items to remove line wraps (“QT-prolonging prescription medications without washout” → “QT-prolonging medications without washout”; comma to semicolon in the long QT item; reordered the structural-heart-disease item). All fourteen items and their thresholds, staging and time windows are retained as required by items 8.2 and 8.5.
4. 4.5 — Protocol, Qualitative and echocardiogram cells trimmed: Cut redundant wording in action_1_sub, time_1_sub, marker_10_target and qualitative_item_5 (“initiating effortful activity and taking pleasure in ordinary rewards” → “effortful activity and pleasure in ordinary rewards”), each removing a wrapped line. The section content mandated by items 8.2, 14.2 and 15.2 sets a floor below which the sheet cannot be shortened further.
5. 1.1 — Booster timing restored: Changed action_2_sub from “some add a 1–3 mg/kg booster the next day” to “some add a 1–3 mg/kg booster on a subsequent day”, matching the ER Therapeutic Protocol section.

Issues 04/08/2026 19:23

1. 4.5 — Sheet overflows one A4 page: The rendered sheet runs to roughly two A4 pages; the 14-item Contraindications gate (lines 576–600) and the 10-row Monitoring table plus cadence (lines 673–851) each consume close to half a page, and the descriptive fields ([marker__why], [monitoring_cadence], [action_sub], [time_sub], [qualitative_item_]) carry near-ER-length prose rather than being condensed to the per-section budget.

Fixes 04/08/2026 19:23

1. 4.5 — Condensed sections to the page budget: Trimmed the highest-volume descriptive fields so the sheet renders substantially shorter — [action_1sub]/[action_2_sub]/[action_3_sub] and [time_1_sub]–[time_3_sub] cut to one to two lines each, all ten [marker_why] cells and [marker_3_target] shortened, [monitoring_cadence] condensed (electrocardiogram expanded once, then “ECG”), and the six [qualitative_item_] descriptions tightened while keeping their bold labels verbatim.
2. 4.5 — Shortened contraindications and interactions: Applied the shortening 8.5/9.5 permit for the one-page budget without dropping any qualifier — e.g. “Baseline corrected QT interval above 450 ms” → “Baseline QTc above 450 ms”, “heart failure of New York Heart Association Class III or IV … within the previous six months” → “heart failure NYHA Class III–IV … within 6 months”, “estimated glomerular filtration rate below 30” → “(eGFR <30 …)”, and the SSRI/SNRI and supplement lists compressed while retaining every named drug.
3. 4.5 — Removed duplicated benefit wording: [benefits_low] merged the repeated “after repeated head trauma” clause into “Improved cognitive performance and measurable structural brain change after repeated head trauma”.

Issues 04/08/2026 19:16

1. 1.2 — At-A-Glance drops ER hedge: at_a_glance (QRS lines 437-438) asserts “screening and monitoring reduce that hazard without eliminating it”, while the ER Conclusion (line 531) hedges the same claim as “appears to be reducible through screening, mineral correction and multi-day monitoring”.

Fixes 04/08/2026 19:16

1. 1.2 — At-A-Glance hedge restored: Changed the closing clause of at_a_glance from “screening and monitoring reduce that hazard without eliminating it” to “screening and monitoring appear to reduce, not eliminate, that hazard”, mirroring the ER Conclusion’s “appears to be reducible”; the section remains within the 60-word limit.