Audit: QRS - DMT for Health & Longevity

Audit conducted on 05/08/2026 02:41 using AI4L / Opus 5

Iterations

Summary

Items	Count
Total	91
Passed	81
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.	🟢	All protocol values (21.5 mg over 10 minutes; 15 mg then 60 mg), time-to-effect values, all 9 biomarker targets, cadence, gates, benefit and risk tiers trace to ER lines 348, 372, 376, 386, 428, 452, 456–464, 468–480.
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.	🟢	“durability not established” (time_2_sub) mirrors ER line 180 “Durability beyond a day was not established”; “open-label” qualifier retained in time_3_sub per ER line 194.
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 retained at absolute strength (pregnancy and breastfeeding; MAOIs); interactions retained at caution strength, matching ER line 348 and lines 332–346.
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 drawn only from the ER “Populations who should avoid this intervention” bullet; Key Interactions only from the ER interaction bullets; no modifying factors surfaced as gates.
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 identifiers, author names, sponsor names, or brand names appear anywhere in the QRS.
1.6	The QRS does not introduce new attributions.	🟢	No attributions of any kind 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, evidentiary register matching the ER throughout.
2.2	The tone of the QRS is simultaneously expert, accessible, objective, and data-driven, but also empowering and encouraging	🟢	Quantified targets and tiered benefit/risk framing without alarmism or promotion.
2.3	The QRS reads as a trusted, knowledgeable guide rather than a prescriptive doctor	🟢	Items are stated as observed protocol and measurement practice, not as orders.
2.4	The QRS avoids language that implies medical or clinical advice	🟢	No imperatives; monitoring cadence is phrased descriptively (“Continuous vital signs during and for 60–90 minutes after the session”).
2.5	The QRS “presents information” instead of “providing guidance”, “recommending”, or “advising”	🟢	No instances of “recommend”, “should”, “advise”, or “guidance”.
2.6	The QRS never addresses “the reader” directly — it presents evidence, not guidance	🟢	No second-person pronouns anywhere in the document.
2.7	The QRS is written in plain language, avoiding unnecessary medical jargon	🟢	Retained technical terms (NYHA Class III–IV, Child-Pugh Class B or C, QTc) are load-bearing decision-gate qualifiers carried verbatim from ER line 348.
2.8	Information is presented in a concise and very compact manner	🟢	All items are noun-phrase length; no explanatory clauses in gates, benefits, or risks.
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.	🟢	Functional (not conventional) biomarker ranges and full contraindication detail assume a proactive, risk-aware 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.	🟢	Protocol panel presents supervised infusion/vaporization and a front-loaded monitoring cadence without hedging on effort.
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.	🟢	No general-population framing or simplification of the screening burden.
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 names the concentration of serious harms in a specific screenable subgroup, matching ER line 512.
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 string “anti-aging” does not occur; the header uses “DMT for Health & 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)”; “injection” not “shot”; “adverse event” not “bad reaction”). Direct quotes from sources are exempt.	🟢	“myocardial infarction”, “intracranial haemorrhage”, “hallucinogen persisting perception disorder”, “monoamine oxidase inhibitors” used throughout.

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 fourteen fixed strings verified at lines 445, 488, 536, 565, 587, 616, 647, 651–653, 774 and in the tier labels of the benefits and risks cards.
3.2	All “…” from the [qrs_template] are present in the the QRS.	🟢	68 data-qrs-var spans present, covering every variable family named in the checklist: page_title, header_, at_a_glance, action_1–3_, time_1–3*, benefits, stop_items, caution_items, risks_, marker_1–9_*, monitoring_cadence, qualitative_item_1–7.
3.3	Spans that are not addressed in a checklist item are left unchanged	🟢	The non-variable template spans website="evidence_review", website="audit", and website="full_review" (lines 423, 426, 439) are intact and unmodified.

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 feeding the QRS is empty; every source section (Protocol, Expected Benefits, Potential Risks & Side Effects, Key Interactions & Contraindications, Monitoring) is populated.
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.	🟢	action_1–3_label reproduce ER lines 372, 376, 386 verbatim; qualitative_item_1–7 reproduce the ER bold labels at lines 468–480 verbatim.
4.3	Labels are not paraphrased, abbreviated, or invented.	🟢	All nine marker names match the ER biomarker table (lines 456–464) exactly, including “Blood pressure (seated, rested)” and “Electrocardiogram, QTc interval”.
4.4	The QRS DOES NOT use emoji indicators (no 🟩, 🟥, 🟨, etc.). Color and emphasis are conveyed through CSS and bold labels.	🟢	Zero emoji characters in the file; tiers are conveyed by bold labels plus the green/red card CSS.
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 expression — single-clause gate items, noun-phrase benefit/risk items, and three-to-six-word “Why” cells — with no elaboration retained anywhere.

---

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; the comment opens immediately after the doctype at line 1 and precedes the template comment at line 16.
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; the preamble text at line 2 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.	🟢	The block is inside an HTML comment and is not duplicated in any 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.	🟢	Only duration: "00:05" is quoted, correctly, because it contains a colon.
5.5	The filename of the source ER is stated as “er_filename: [er_filename]”	🟢	Line 4: er_filename: dmt_2026-0805-0002_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: 26.7.02, 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: 2026-0805-0154, correctly formatted.
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” = nickname plus version, no qualifier.
5.12	The filename of the document is stated as “qrs_filename: [filename of this document]”	🟢	Line 9: qrs_filename: dmt_2026-0805-0002_Opus_QRS.html, matching 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 across all nine keys; no stray whitespace or unnecessary quoting.

6. Page Title & Header

#	Description	Result	Comments
6.1	[page_title] is set to the [canonical_topic] of the ER frontmatter followed by “ - Quick Reference Sheet” (e.g., “Intervention - Quick Reference Sheet”). The [canonical_topic] is HTML-entity-encoded as needed (e.g., & for &)	🟢	Line 22: “DMT for Health & Longevity - Quick Reference Sheet”, matching ER frontmatter canonical_topic with the ampersand 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: “DMT for Health & Longevity”.
6.3	[header_subline_date] is set to [qrs_creation_date reformatted as MM/DD/YYYY]	🟢	Line 421: “08/05/2026”, the correct MM/DD/YYYY rendering of 2026-0805-0154.
6.4	[header_subline_model] is set to [qrs_creator_ai_fullname]	🟢	Line 425: “Opus 5”, matching the frontmatter value.
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; the ER’s alternate_names list is not reproduced.

7. At-A-Glance Section

#	Description	Result	Comments
7.1	[at_a_glance] is dense, execution-oriented summary of the ER Conclusion section	🟢	Compresses ER Conclusion lines 508, 510, and 512 into identity, strongest benefit, and concentration of serious harm.
7.2	[at_a_glance] is no longer than 60 words	🟢	52 words.
7.3	Every fact in [at_a_glance] is supported by a distinct passage in the ER.	🟢	Plant/trace-amount origin and twenty-minute duration from line 508; depression durability from line 510; psychosis/mania concentration from line 512.
7.4	It DOES NOT use acronyms or technical classifications that require specialist knowledge, uses plain-language terms instead	🟢	No acronyms; “psychosis” and “mania” are carried verbatim from the ER’s own plain-language Conclusion at line 512.
7.5	It DOES NOT cite specific trials (names, years, sample sizes, p-values)	🟢	No trial names, years, or sample sizes appear.
7.6	It DOES NOT cite effect sizes, relative risks, or statistical results	🟢	No effect sizes or statistics; “sometimes months-long” is a duration, not a statistic.

8. Contraindications

#	Description	Result	Comments
8.1	The section is derived from the ER Key Interactions & Contraindications section	🟢	All nine items map to the “Populations who should avoid this intervention” bullet at ER line 348 and the MAOI bullet at line 332.
8.2	[stop_items] represent the Contraindications from the ER	🟢	Complete coverage of the ER exclusion list with no additions and no omissions.
8.3	Individual [stop_items] are formatted as <li></li>	🟢	Nine discrete <li> elements at lines 568–582.
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.	🟢	The ER’s explanatory glosses for NYHA class, QTc, and Child-Pugh are stripped; no trailing dash clauses remain.
8.5	Parenthetical qualifiers from the ER bullet — time windows, severity classes, threshold values, clinical staging — ARE preserved as part of the item, kept as concise as possible (shortened or trimmed where needed to fit the one-page budget, but never dropped entirely).	🟢	“(above 140/90 mmHg)”, “(within 90 days)”, “NYHA Class III–IV”, “QTc >500 ms”, and “Child-Pugh Class B or C” 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 inside parentheses in this section; the only “>” is the QTc numeric threshold.
8.7	If no [stop_items] are present the section is left empty	N/A	Nine stop_items are present.

9. Key Interactions

#	Description	Result	Comments
9.1	The section is derived from the ER Key Interactions & Contraindications section	🟢	All seven items map to ER lines 334–346.
9.2	[caution_items] represent the Key Interactions from the ER, excluding any that are already listed as Contraindications	🟢	Seven of the ER’s eight interaction bullets appear; the MAOI bullet is correctly excluded because it is carried as a contraindication.
9.3	Individual [caution_items] are formatted as <li></li>	🟢	Seven discrete <li> elements at lines 590–606.
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.	🟢	The ER’s “— caution, monitor”, “— caution”, and “— monitor” suffixes and all mitigation/washout 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).	🟢	Named exemplars retained for every class: sertraline/venlafaxine; amitriptyline/clomipramine; dextromethorphan/chlorpheniramine/pseudoephedrine; St. John’s wort/5-HTP/Syrian rue; yohimbine/synephrine/high-dose caffeine; psilocybin/LSD/ketamine.
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	If no [caution_items] are present the section is left empty	N/A	Seven caution_items are present.

10. Protocol

#	Description	Result	Comments
10.1	The section is derived from the ER Protocol section	🟢	All three action sets map to ER Therapeutic Protocol lines 372, 376, and 386.
10.2	The three sets of [action] items cover the three most important actionable implementation aspects from the ER Protocol section	🟢	Intravenous infusion (the pharmaceutical standard and the only placebo-controlled synthetic-DMT protocol), the emerging inhaled route, and the single-versus-repeated dosing decision are the three highest-leverage implementation choices in the ER section.
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 describes five distinct routes plus dosing-schedule guidance; all three action 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.	🟢	Nine of nine cells populated; values “21.5 mg over 10 minutes”, “15 mg then 60 mg”, and “One or two single doses” all trace to the ER.

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	🟢	Depressive symptoms (ER line 428), mindfulness and self-compassion (ER line 180), and quality of life and life satisfaction (ER line 196).
11.2	The sets are picked and ordered by the magnitude of the related benefit	🟢	Ordered High → Medium → Low, matching the ER benefit tiers for depression, mindfulness/self-compassion, and quality of life respectively.
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 or more distinct time-to-effect aspects are present in the ER; 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.	🟢	Nine of nine cells populated with ER-sourced content including the 3-month and 12-month durability qualifiers.
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 explicit time-to-effect data at lines 168, 180, 196, and 428.

12. Benefits

#	Description	Result	Comments
12.1	The section is derived from the ER Expected Benefits section	🟢	All nine benefit headings from ER lines 164–216 are represented in their original tiers.
12.2	Key variables are [benefits_high], [benefits_medium], [benefits_low], [benefits_speculative]	🟢	All four spans present and populated at lines 538–558.
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 entry is a bare noun phrase; the ER’s Magnitude lines (MADRS −7.35, Hedges’ g 0.94) and the “⚠️ Conflicted” markers are all omitted.
12.4	Parenthetical content — including effect sizes, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parentheses appear in any benefits item.
12.5	If no items of a specific sub-section (high, medium, low, speculative) are present the respective is set to “display=none”, not filled with “None documented in human trials to date” or similar empty-state phrasing.	N/A	All four tiers contain items in the ER, so no span needed hiding.

13. Risks

#	Description	Result	Comments
13.1	The section is derived from the ER Potential Risks & Side Effects section	🟢	All eleven risk headings from ER lines 242–312 are represented in their original tiers.
13.2	Key variables are [risks_high], [risks_medium], [risks_low], [risks_speculative]	🟢	All four spans present and populated at lines 618–640.
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 entry reduced to a noun phrase; the ER’s Magnitude figures (25.7% systolic rise, 4% serious adverse events, 3504 participants) are all omitted.
13.4	Parenthetical content — including frequencies, severity grades, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parentheses appear in any risks item.
13.5	If no items of a specific sub-section (high, medium, low, speculative) are present the respective is set to “display=none”, not filled with “None documented in human trials to date” or similar empty-state phrasing.	N/A	All four tiers contain items in the ER, so no span needed hiding.

14. Monitoring

#	Description	Result	Comments
14.1	The section is derived from the ER Monitoring section	🟢	Table content maps row-for-row to the ER biomarker table at lines 456–464.
14.2	All measurable/quantifiable biomarkers from the Monitoring section are listed	🟢	All nine ER biomarkers present with targets reproduced exactly, including “ALT and AST 10–26 U/L; creatinine 0.7–1.1 mg/dL” and “Glucose 75–86 mg/dL; HbA1c 4.8–5.2%”.
14.3	[monitoring_cadence] is populated with the monitoring cadence/frequency derived from the ER Monitoring section. It is not left with placeholder text or empty.	🟢	Lines 764–768 reproduce the ER’s front-loaded cadence from line 452: continuous vitals for 60–90 minutes, review at 24 hours / 1 week / 4 weeks, laboratory review at 3 months then every 6–12 months.

15. Qualitative Assessment

#	Description	Result	Comments
15.1	The section is derived from the ER Monitoring section	🟢	All seven items map to the qualitative-marker bullets at ER lines 468–480.
15.2	All subjective/qualitative biomarkers from the Monitoring section are listed	🟢	Seven of seven ER qualitative markers present, with the ER bold labels retained verbatim.

Issues 05/08/2026 02:41

Pass rate 100.00%. No issues found.

Issues 05/08/2026 02:34

1. 4.5 — Sheet overruns one A4 page: The rendered print height is roughly 1.9 A4 pages; the largest single contributor is the Monitoring card, where seven of the nine “Why” cells wrap to a second line, with further avoidable wrapping in Benefits, Risks, Key Interactions, and action_2_sub.

Fixes 05/08/2026 02:34

1. 4.5 — Monitoring “Why” column condensed: Shortened all nine marker_#_why cells so each fits a single line (e.g. “Arrhythmia risk the sympathetic surge could unmask” → “Screens for arrhythmia risk”; “Vascular disease that drives the main acute risk” → “Metabolic health screen”), removing seven wrapped lines from the tallest card.
2. 4.5 — Benefits entries trimmed: Reduced the Low and Speculative tiers to one line each (“sustained improvement in quality of life and life satisfaction” → “improved quality of life”; “promotion of adult neurogenesis and structural brain repair” → “adult neurogenesis and brain repair”).
3. 4.5 — Risks entries trimmed: Condensed the Medium, Low, and Speculative tiers (“Acute psychotic reaction or precipitation of mania” → “Acute psychosis or mania”; “destabilization of psychiatric baseline in the weeks after dosing” → “psychiatric destabilization”).
4. 4.5 — Decision-gate items shortened: Reduced wrapping in both gates — “Valvular heart disease or aortic aneurysm; QTc above 500 ms” → “Valvular disease or aortic aneurysm; QTc >500 ms”, and dropped the redundant “Supplements with additive” / “Interaction with” prefixes from three Key Interactions entries while keeping every example drug list.
5. 4.5 — Protocol subtext shortened: action_2_sub reduced from “Fixed-order escalation by temperature-controlled vaporizer; avoids venous access.” to “Temperature-controlled vaporizer; avoids venous access.”

Issues 05/08/2026 02:23

1. 1.2 — Hedge “proposed” dropped from sigma-1: marker_7_why (QRS line 751) reads “Baseline inflammatory tone (sigma-1 mechanism)” while the ER (line 462) writes “relevant to the proposed sigma-1 anti-inflammatory mechanism”, so the ER’s cautious framing of an unestablished mechanism is lost.
2. 1.3 — Conditional “could” dropped from QTc rationale: marker_3_why (QRS line 695) asserts “Arrhythmia risk unmasked by the sympathetic surge”, strengthening the ER’s “arrhythmia risk that the sympathetic surge could unmask” (ER line 458) into a statement of fact.

Fixes 05/08/2026 02:23

1. 1.2 — Restored “proposed” hedge on sigma-1: marker_7_why changed from “Baseline inflammatory tone (sigma-1 mechanism)” to “Baseline inflammatory tone (proposed sigma-1 mechanism)”, matching the ER’s cautious framing.
2. 1.3 — Restored conditional in QTc rationale: marker_3_why changed from “Arrhythmia risk unmasked by the sympathetic surge” to “Arrhythmia risk the sympathetic surge could unmask”, reinstating the ER’s “could”.

Issues 05/08/2026 02:16

1. 4.5 — Sheet exceeds one A4 page: At the template’s print geometry (A4, 12 mm sheet padding) the populated sheet lays out to roughly twice the available page height, and several sections carry avoidable length — the At-A-Glance paragraph, the three action_#_sub cells, the five- and six-item example drug lists in caution_items, the full-sentence marker_#_why cells, and the three-line monitoring_cadence.

Fixes 05/08/2026 02:16

1. 4.5 — At-A-Glance shortened: Condensed the summary from 359 to 347 characters (57 → 52 words), merging the opening two sentences and replacing “The strongest evidence is a rapid…” with “Strongest evidence: rapid…”, dropping it from five rendered lines to four.
2. 4.5 — Protocol sub-cells condensed: Cut all three action_#_sub cells from three-to-four rendered lines to two (e.g. “Single dose of DMT fumarate with psychotherapeutic support; the slow infusion gives a plateau of roughly 20–30 minutes.” → “DMT fumarate with psychotherapeutic support; plateau of 20–30 minutes.”).
3. 4.5 — Time-to-effect sub-cells condensed: Trimmed all three time_#_sub cells to two lines each (e.g. “12 months in the patient group, 14 days in healthy volunteers; open-label follow-up.” → “12 months in patients, 14 days in healthy volunteers; open-label.”).
4. 4.5 — Contraindication items tightened: Shortened four stop_items while keeping every threshold and severity class (e.g. “Uncontrolled hypertension (resting blood pressure above 140/90 mmHg)” → “Uncontrolled hypertension (above 140/90 mmHg)”; the MAOI example list trimmed to phenelzine, tranylcypromine, linezolid).
5. 4.5 — Key-interaction example lists trimmed: Reduced each caution_items parenthetical to two or three named example drugs rather than four to six, taking the caution gate from eighteen rendered lines to thirteen; no example list was emptied.
6. 4.5 — Monitoring “Why” cells condensed: Shortened seven marker_#_why cells to a single clause each (e.g. “The session raises cortisol; baseline separates drug effect from dysregulation” → “Baseline separates drug effect from dysregulation”).
7. 4.5 — Monitoring cadence shortened: Cut monitoring_cadence from 238 to 199 characters by replacing “reassessment” with “review” and folding “during the session and for 60–90 minutes afterward” into “during and for 60–90 minutes after the session”.
8. 4.5 — Qualitative tails trimmed: Shortened the explanatory tails on qualitative_item_5 and qualitative_item_6 while leaving both bold ER labels verbatim (e.g. “whether the person describes plans and hope rather than endurance” → “plans and hope rather than endurance”).

Issues 05/08/2026 02:03

1. 4.5 — Sheet exceeds one A4 page: Rendered at the template’s print geometry the sheet runs to roughly two A4 pages rather than one; the over-budget blocks are the Monitoring “Why” cells (lines 682–799), the Protocol and Time-to-effect sub-cells (lines 455–535), the Qualitative Assessment descriptions (lines 818–857), and the two decision-gate lists (lines 573–622).

Fixes 05/08/2026 02:03

1. 4.5 — Protocol and time-to-effect cells condensed: Shortened action_1_sub, action_3_sub, time_1_sub, time_2_sub, and time_3_sub; removed the redundant repetition of “Sustained … 12 months” between time_3_value and time_3_sub.
2. 4.5 — Monitoring “Why” column tightened: Rewrote all nine marker_#_why cells as noun phrases (e.g., “Determines eligibility and headroom for the acute pressor response” to “Eligibility and headroom for the acute pressor response”), removing one to two wrapped lines per table row.
3. 4.5 — Monitoring cadence trimmed: Condensed monitoring_cadence to “Continuous vital signs during the session and for 60–90 minutes afterward; symptom and blood-pressure reassessment at 24 hours, 1 week, and 4 weeks; laboratory reassessment at 3 months, then every 6–12 months if sessions continue.”
4. 4.5 — Qualitative descriptions shortened: Trimmed qualitative_item_5 and qualitative_item_7 to their key facts while leaving the ER’s bold labels verbatim.
5. 4.5 — Decision-gate drug lists trimmed: Reduced the example-agent lists in the monoamine oxidase inhibitor contraindication and in three Key Interactions items to representative agents, per the “shortened or trimmed where needed to fit the one-page budget, but never dropped entirely” allowance in 8.5 and 9.5.