Audit: QRS - LSD Analogues for Health & Longevity

Audit conducted on 22/09/2026 18:36 using AI4L / Opus 5

Iterations

Summary

Items	Count
Total	94
Passed	84
Failed	0
N/A	10
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 across every populated span: dose 100–200 µg and the 113/117/121/126 µg conversions (ER 443), 14-day interval (ER 424, 474), morning/before 10:00 (ER 449), onset 30–90 min and 1–2 h low-dose (ER 498), all 14 benefit and 14 risk headings, all 11 contraindications (ER 411), all 10 biomarkers and targets (ER 526–535), cadence (ER 522).
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.	🟢	“Cumulative effects over 2–4 weeks are described, not confirmed by controlled evidence” mirrors ER 498; “(conflicted)” carries the ER’s ⚠️ Conflicted markers in text form; “predicted” retained for the computational toxicity signals.
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 conflicted benefit/risk items keep their conflicted flag; no tier was shifted.
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’s “Populations who should avoid this intervention entirely” bullet; interactions from the interaction bullets; benefits and risks from their own tiers. No modifying factor was promoted to a gate.
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.	🟢	Only Fadiman and Stamets appear, both named in the ER for exactly those schedules (ER 445). No PMIDs, NCT IDs, or brand names.
1.6	The QRS does not introduce new attributions.	🟢	No attribution beyond the two schedule originators already in the ER.

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.	🟢	Sceptical, measurement-first framing matching the ER’s own register.
2.2	The tone of the QRS is simultaneously expert, accessible, objective, and data-driven, but also empowering and encouraging	🟢	Quantified targets and thresholds throughout, presented as decision inputs rather than warnings.
2.3	The QRS reads as a trusted, knowledgeable guide rather than a prescriptive doctor	🟢	Protocol cells describe the models in use rather than instructing the reader.
2.4	The QRS avoids language that implies medical or clinical advice	🟢	No “should”, “take”, or “consult” outside the template disclaimer.
2.5	The QRS “presents information” instead of “providing guidance”, “recommending”, or “advising”	🟢	No recommending verbs anywhere in the populated spans.
2.6	The QRS never addresses “the reader” directly — it presents evidence, not guidance	🟢	No second-person pronouns in the document.
2.7	The QRS is written in plain language, avoiding unnecessary medical jargon	🟢	Technical terms are confined to the gate and monitoring surfaces where they are unavoidable; the lede is plain.
2.8	Information is presented in a concise and very compact manner	🟢	Benefit and risk tiers are semicolon-separated headings; monitoring “Why” entries are reduced to noun phrases.
2.9	It DOES NOT address the reader directly	🟢	Confirmed — no direct address.
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.	🟢	Screening thresholds, cycling caps, and batch verification all assume a proactive reader.
2.11	The target audience is willing to employ lifestyle and behavioral changes as well as follow protocols that may be inconvenient, costly, or require effort.	🟢	Echocardiogram, CYP2D6 genotype, and pre/post-dose blood pressure are all effortful items retained.
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 monitoring and interaction detail is well beyond general-population material.
2.13	Framing, takeaways, and risk/benefit weighting throughout the document reflect this audience, including where an intervention’s signal for the average person differs from its signal for this audience.	🟢	The lede leads with the delivery-shell distinction and the label-accuracy problem, which is the decision-relevant signal for this audience.
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; the title uses “Longevity”.
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 is given as “oral doses”; “shells”, “visions”, and “tiny doses” are the ER’s own conclusion wording (ER 573–575).

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 column headers are byte-identical to the template.
3.2	All “…” from the [qrs_template] are present in the the QRS.	🟢	All 34 template variable names present; marker_#* and qualitative_item# correctly expanded to 10 and 6 numbered instances.
3.3	Spans that are not addressed in a checklist item are left unchanged	🟢	A normalised diff against the template shows only the repeated monitoring rows and qualitative list items added; the website=”evidence_review”, website=”audit”, and website=”full_review” spans and the footer are untouched.

4. Formatting

#	Description	Result	Comments
4.1	When the source ER section is empty, the QRS uses the ER’s own empty-state phrasing verbatim. Typical phrasings are “None documented in human trials to date” and “Not formally studied”	N/A	No ER section that feeds the QRS is empty.
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.	🟢	All six qualitative items carry the ER’s bold labels verbatim (ER 539–549); monitoring row labels match the ER biomarker column verbatim. Protocol and time cells are composites of several ER bullets, so no single ER bold label applies.
4.3	Labels are not paraphrased, abbreviated, or invented.	🟢	No qualitative or monitoring label was altered.
4.4	The QRS DOES NOT use emoji indicators (no 🟩, 🟥, 🟨, etc.). Color and emphasis are conveyed through CSS and bold labels.	🟢	No emoji anywhere in the file; the ER’s ⚠️ marker is rendered as the word “(conflicted)”.
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.	🟢	Item counts are fixed by the completeness rules (8.2, 9.2, 14.2, 15.2); wording is condensed to the minimum — “Why” cells reduced to noun phrases, interaction drug lists trimmed to two or three exemplars, benefit and risk tiers reduced to bare headings.

---

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.
5.2	Inside that HTML comment the YAML block is delimited by a line “—” opening and a line “—” closing. Text before the opening “—” is permitted but is not parsed as YAML.	🟢	Opening “—” at line 3, closing at line 13.
5.3	The metadata is not visible in any rendered view of the QRS and is not surfaced by any other element on the sheet.	🟢	Enclosed in an HTML comment; no metadata value is repeated in the body.
5.4	All frontmatter values are trimmed: no leading or trailing whitespace, no surrounding quotes unless the value contains a colon, bracket, or leading special character that requires YAML quoting.	🟢	Only duration: "00:02" is quoted, and it contains a colon.
5.5	The filename of the source ER is stated as “er_filename: [er_filename]”	🟢	er_filename: lsd_analogues_2026-0805-0259_Opus_ER.md (line 4).
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: 26.9.22 matches the prompt version.
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: 2026-0922-1756.
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)	🟢	Single word, no version.
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” — nickname plus version, no qualifier.
5.12	The filename of the document is stated as “qrs_filename: [filename of this document]”	🟢	qrs_filename: lsd_analogues_2026-0805-0259_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.	🟢	Re-verified: every value trimmed, only the colon-bearing duration 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., & for &)	🟢	“LSD Analogues for Health & Longevity - Quick Reference Sheet” (line 22).
6.2	[header_topic] is set to the [canonical_topic] of the ER frontmatter, with HTML entities encoded as needed (e.g., & for &)	🟢	“LSD Analogues for Health & Longevity” (line 417).
6.3	[header_subline_date] is set to [qrs_creation_date reformatted as MM/DD/YYYY]	🟢	2026-0922-1756 → 09/22/2026 (line 421).
6.4	[header_subline_model] is set to [qrs_creator_ai_fullname]	🟢	“Opus 5” (line 425).
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 contains only the title and the template subline.

7. At-A-Glance Section

#	Description	Result	Comments
7.1	[at_a_glance] opens by saying what the intervention is — its kind (e.g., dietary supplement, prescription medication, peptide, plant, procedure, practice) — and what it is used for, in plain language, before any verdict on the evidence	🟢	Opens “LSD analogues are laboratory-made relatives of LSD sold online, used mostly as repeated tiny oral doses for mood and mental sharpness” — kind and purpose before any verdict.
7.2	[at_a_glance] is dense, execution-oriented summary of the ER Conclusion section	🟢	Compresses the two-group distinction, the inherited effects, the animal-only status of the engineered branch, and the evidence verdict from ER 573–577.
7.3	[at_a_glance] is no longer than 70 words	🟢	69 words.
7.4	Every fact in [at_a_glance] is supported by a distinct passage in the ER.	🟢	“sold online” ← ER 481; “repeated tiny doses for mood and mental sharpness” ← ER 39; the remaining four clauses ← ER 573–577.
7.5	It DOES NOT use acronyms or technical classifications that require specialist knowledge, uses plain-language terms instead	🟢	Only “LSD” appears, which a non-specialist uses unprompted; “shells the body strips away” and “brain-remodelling” replace prodrug and neuroplasticity.
7.6	It DOES NOT cite specific trials (names, years, sample sizes, p-values)	🟢	No trial reference of any kind.
7.7	It DOES NOT cite effect sizes, relative risks, or statistical results	🟢	No numbers at all.

8. Contraindications

#	Description	Result	Comments
8.1	The section is derived from the ER Key Interactions & Contraindications section	🟢	All eleven items trace to the “Populations who should avoid this intervention entirely” bullet (ER 411) plus the lithium bullet (ER 385).
8.2	[stop_items] represent the Contraindications from the ER	🟢	All eleven ER exclusions are present, none added.
8.3	Individual [stop_items] are formatted as <li></li>	🟢	Eleven <li> elements inside the span (lines 542–552).
8.4	Items are as concise as possible. No trailing explanations, no elaborations, no mechanistic rationale, no attributions, no citations, no study details. No content after an em-dash, en-dash, or hyphen-dash (e.g., “— dose reduction required”, “— reduced efficacy”) — these trailing clauses are stripped. Just the key fact.	🟢	The ER’s explanatory parentheses (NYHA expansion, “a heart valve that leaks blood backwards”) are stripped; no trailing clause remains. The only en-dash is the “III–IV” staging range.
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).	🟢	“within 12 months”, “above 140/90 mmHg”, “within 6 months”, “NYHA III–IV”, “Moderate or severe”, “Child-Pugh B or C”, “within 24 hours” all preserved.
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 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 identifies eleven such populations and the section is populated accordingly.
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 thirteen items trace to ER 387–409.
9.2	[caution_items] represent the Key Interactions from the ER, excluding any that are already listed as Contraindications	🟢	Lithium is correctly excluded (it sits in Contraindications); psychotherapy is correctly omitted as the ER states it “carries no interaction severity”. TMS/ketamine and alcohol from the “Other interventions” bullet are both carried.
9.3	Individual [caution_items] are formatted as <li></li>	🟢	Thirteen <li> elements inside the span (lines 560–572).
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 item is a drug class plus exemplars; no mechanism, severity verdict, or mitigation carried over, and no dash clauses.
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).	🟢	Every ER bullet carrying a drug list retains a trimmed version of it; 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 uses no ranking notation 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 identifies twelve interaction bullets and the section is populated accordingly.
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	🟢	Dose and conversions from ER 443, timing from ER 449 and 453, low-dose schedules from ER 445; the 14-day minimum and the 8–12 week cap are the ER’s own protocol parameters (ER 424, 426, 474).
10.2	The three sets of [action] items cover the three most important actionable implementation aspects from the ER Protocol section	🟢	Dose, Timing, and Interval — the three parameters the ER treats as determining, with interval described as a pharmacological requirement.
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	Three distinct aspects are present and all three sets are used.
10.4	All used [action_#label], [action#value], [action#_sub] items are filled with meaningful content derived from the ER Protocol section.	🟢	All nine spans carry substantive 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	🟢	Full-dose onset, post-session mood benefit, and low-dose energy effect — the three timings the ER gives (ER 498).
11.2	The sets are picked and ordered by the magnitude of the related benefit	🟢	Acute full-dose course first, the Medium-tier mood benefit second, the conflicted low-dose vigour effect 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	Three distinct aspects are present and all three sets are used.
11.4	All used [time_#label], [time#value], [time#_sub] items are filled with meaningful content derived from the ER.	🟢	All nine spans populated from ER 498; the peak and resolution window is carried in the first sub.
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 a dedicated “Time to effect” bullet.

12. Benefits

#	Description	Result	Comments
12.1	The section is derived from the ER Expected Benefits section	🟢	All fourteen items are the ER’s own benefit headings, tier for tier.
12.2	Key variables are [benefits_high], [benefits_medium], [benefits_low], [benefits_speculative]	🟢	All four spans present and populated: 1 / 4 / 5 / 4 items, matching the ER counts exactly.
12.3	Items are as concise as possible. No explanations, no elaborations, no effect sizes, no qualifiers, no attributions, no citations, no study details, no mechanistic explanations, etc. Just the key fact.	🟢	Each item is a bare ER heading; no magnitudes, mechanisms, or study references carried over.
12.4	Parenthetical content — including effect sizes, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No ER parenthetical survives; the only parentheses are the “(conflicted)” rendering of the ER’s own ⚠️ Conflicted marker, required by 1.2 and 1.3 and permitted because 4.4 bars the emoji form.
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 tiers have items in the ER.

13. Risks

#	Description	Result	Comments
13.1	The section is derived from the ER Potential Risks & Side Effects section	🟢	All fourteen items are the ER’s own risk headings, tier for tier.
13.2	Key variables are [risks_high], [risks_medium], [risks_low], [risks_speculative]	🟢	All four spans present and populated: 5 / 4 / 3 / 2 items, matching the ER counts exactly.
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.	🟢	No frequencies (the 4% serious-event figure), mechanisms, or citations carried over.
13.4	Parenthetical content — including frequencies, severity grades, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No ER parenthetical survives; the only parenthesis is the “(conflicted)” rendering of the ER’s ⚠️ Conflicted marker on HPPD.
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 tiers have items in the ER.

14. Monitoring

#	Description	Result	Comments
14.1	The section is derived from the ER Monitoring section	🟢	Rows and targets taken from the ER biomarker table (ER 526–535).
14.2	All measurable/quantifiable biomarkers from the Monitoring section are listed	🟢	All ten ER biomarkers present in ER order, with targets reproduced verbatim including the sex-specific ALT, haemoglobin, QTc, and prolactin ranges.
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.	🟢	Reproduces all four cadence elements from ER 522: pre/2 h post-dose vitals, blood panel at 3 months, then 6–12 monthly, echocardiogram at 24 months for more-than-monthly dosing.

15. Qualitative Assessment

#	Description	Result	Comments
15.1	The section is derived from the ER Monitoring section	🟢	All six items come from the qualitative marker list at ER 539–549.
15.2	All subjective/qualitative biomarkers from the Monitoring section are listed	🟢	All six are present, in ER order, with the ER’s bold labels intact.

Issues 22/09/2026 18:36

Pass rate 100.00%. No issues found.

Issues 22/09/2026 18:23

1. 4.3 — SSRI class label abbreviated: Caution item 1 (line 560) renders the ER’s “Selective serotonin reuptake inhibitors and serotonin-noradrenaline reuptake inhibitors” (ER line 387) as “Serotonin and serotonin-noradrenaline reuptake inhibitors”, dropping “Selective” and naming a broader drug class than the ER does.
2. 2.7 — Truncated ordinal breaks sense: Qualitative item 1 (line 734) reads “not normalised by the second indicates too dense a schedule”; the ER’s “by the second off-day” (ER line 539) lost its noun, leaving the ordinal dangling.

Fixes 22/09/2026 18:23

1. 4.3 — SSRI class label restored: Caution item 1 changed from “Serotonin and serotonin-noradrenaline reuptake inhibitors” to “Selective serotonin and serotonin-noradrenaline reuptake inhibitors”, matching the ER’s drug-class naming.
2. 2.7 — Dangling ordinal completed: Qualitative item 1 changed from “not normalised by the second” to “not normalised by the second off-day”, restoring the noun the ER supplies.

Issues 22/09/2026 18:19

1. 4.5 — Sheet overruns one A4 page: At the template’s print geometry the sheet’s ~6,840 characters of visible body text render to roughly 2.4 A4 pages; the Decision Gates block (lines 541–573), the Protocol sub-lines (lines 450–511), the Monitoring cadence (line 725) and the Qualitative Assessment items (lines 734–749) each exceed their per-section budget and need condensing.

Fixes 22/09/2026 18:19

1. 4.5 — Decision Gates condensed: Trimmed all 11 Contraindications and all 13 Key Interactions to their shortest form that still carries every threshold, time window, severity class and example-drug list (e.g. “Personal or first-degree family history of psychotic disorder or bipolar I disorder” → “Personal or first-degree history of psychotic or bipolar I disorder”; “Over-the-counter dextromethorphan and diphenhydramine” → “Dextromethorphan and diphenhydramine”). No item was dropped.
2. 4.5 — Protocol and Time-to-effect sub-lines tightened: Shortened all six sub-lines, the largest saving being the prodrug-equivalent list (“Prodrug equivalents of 100 µg parent: ≈113 µg ALD-52, 117 µg 1P-LSD…” → “Per 100 µg parent: ≈113 µg ALD-52, 117 1P-LSD…”), with every dose figure and qualifier retained.
3. 4.5 — Monitoring cadence and QTc rationale shortened: Cadence cut from 242 to 201 characters while keeping the pre/post-dose vitals, the 3-month panel, the 6–12-month interval and the 24-month echocardiogram; marker_4_why reduced to “Rhythm vulnerability flagged by computational models”.
4. 4.5 — Qualitative Assessment items trimmed: Cut the redundant tails from four of the six items (e.g. “explicitly checked rather than assumed; the earliest signal warranting discontinuation” → “the earliest signal warranting discontinuation”), leaving all six ER bold labels verbatim.

Issues 22/09/2026 18:12

1. 4.5 — Sheet exceeds one A4 page: Estimated rendered height is roughly 2.6 A4 pages; the decision gates (lines 541–573), the 10-row monitoring table with cadence (lines 611–726) and the protocol panel (lines 439–515) together consume more than a full page before the benefits, risks and qualitative cards are laid out.
2. 2.8 — Content not compact enough: The protocol and time-to-effect subs run to three sentences each (lines 450, 461, 472), all six qualitative items carry their full ER explanatory clauses (lines 734–749), and every [caution_items] entry lists five or six example drugs (lines 560–570).

Fixes 22/09/2026 18:12

1. 4.5 / 2.8 — Protocol and time subs condensed: Rewrote all six [action_#sub] and [time#_sub] cells to single compact statements, e.g. “Prodrug mass equivalents are higher: 100 µg of the parent compound ≈ 113 µg ALD-52…” to “Prodrug equivalents of 100 µg parent: ≈113 µg ALD-52…”, and “Any therapeutic mood benefit in the trial literature appears in the days following a session rather than during it” to “Therapeutic mood benefit in the trial literature appears after a session, not during it”.
2. 4.5 / 2.8 — Interaction drug lists trimmed: Reduced every [caution_items] parenthetical from five or six example drugs to two or three representatives, and shortened the class wording (e.g. “Supplements with additive blood-pressure or vasoconstrictive effects” to “Supplements raising blood pressure”), keeping each drug list present as 9.5 requires.
3. 4.5 / 2.8 — Qualitative items stripped to markers: Removed the trailing ER rationale clauses from five of the six [qualitative_item_#] entries, keeping the bold ER label verbatim and the operative instruction only.
4. 4.5 / 2.8 — Monitoring and cadence tightened: Shortened six [marker_#_why] cells (e.g. “Documents valve status before cumulative 5-HT2B exposure” to “Valve status before cumulative 5-HT2B exposure”) and compressed [monitoring_cadence] while preserving all three cadence intervals.
5. 4.5 / 2.8 — Contraindication wording compressed: Condensed three [stop_items] entries, e.g. “Personal history of any psychotic disorder or bipolar I disorder, or a first-degree relative with either” to “Personal or first-degree family history of psychotic disorder or bipolar I disorder”, retaining every threshold, time window and severity class.

Issues 22/09/2026 18:03

1. 7.3 — At-a-glance exceeds word limit: The [at_a_glance] span at line 433 runs to 71 words, one word over the 70-word maximum.

Fixes 22/09/2026 18:03

1. 7.3 — At-a-glance word count: Condensed “so they inherit its effects, risks and doses” to “inheriting its effects, risks and doses” in the [at_a_glance] span, bringing it from 71 to 69 words.