Audit: QRS - Polygala tenuifolia for Health & Longevity

Audit conducted on 20/08/2026 21:30 using AI4L / Opus 5

Iterations

Summary

Items	Count
Total	93
Passed	86
Failed	0
N/A	7
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 (100 mg three times daily / 300 mg / four weeks; 3–9 g dried root), time-to-effect values (4 weeks; 30–60 minutes), all six biomarker targets, the cadence, the five contraindications, the eight interactions, and all benefit/risk tier items trace verbatim or near-verbatim to ER lines 229, 251, 284–298, 300–310, 332–342, 385, 415–420, 424–432, 456–458.
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.	🟢	The at-a-glance retains the ER’s hedges (“The clearest human signal”, “rest almost entirely on animal work”); marker_5_why keeps “the theoretical saponin haemolysis signal”; time_1_sub keeps “assessed only at four weeks, so that is the realistic evaluation window”.
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”).	🟢	Pregnancy and breastfeeding remain under Contraindications, not Key Interactions; sedative-hypnotics, antidepressants and NSAIDs remain Key Interactions, matching the ER’s own split at lines 284–310.
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.	🟢	Gates draw only from Key Interactions & Contraindications; Benefits only from Expected Benefits; Risks only from Potential Risks & Side Effects; Monitoring and Qualitative Assessment only from Monitoring Protocol & Defining Success. No Benefit- or Risk-Modifying Factor was promoted into 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.	🟢	The QRS contains no PMIDs, no author-year citations, no NCT identifiers and no brand names (BT-11, Kan Herb, Plum Flower, Nootropics Depot are all absent).
1.6	The QRS does not introduce new attributions.	🟢	No investigator, institution, organisation or vendor is named anywhere in the QRS body.

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.	🟢	Measured, evidence-weighted register matching the ER; the same “broad in animals, thin in people” framing carries into the at-a-glance.
2.2	The tone of the QRS is simultaneously expert, accessible, objective, and data-driven, but also empowering and encouraging	🟢	Quantified targets and dose figures sit alongside plain-language framing; the sheet presents an actionable, low-cost, well-characterised downside profile without alarmism.
2.3	The QRS reads as a trusted, knowledgeable guide rather than a prescriptive doctor	🟢	Statements are descriptive (“the only regimen tested in randomized human trials”, “Split dosing is preferred”) rather than directives issued to a patient.
2.4	The QRS avoids language that implies medical or clinical advice	🟢	No prescriptive second-person instruction anywhere; the only occurrence of “advice” is the fixed template disclaimer.
2.5	The QRS “presents information” instead of “providing guidance”, “recommending”, or “advising”	🟢	No instance of “recommend”, “advise”, “should” or “must” in the QRS body.
2.6	The QRS never addresses “the reader” directly — it presents evidence, not guidance	🟢	Scan of the rendered body text returns no “you”, “your”, “we” or “our”.
2.7	The QRS is written in plain language, avoiding unnecessary medical jargon	🟢	Retained technical terms (Child-Pugh Class B or C, faecal calprotectin, hs-CRP, haptoglobin) are decision-gate thresholds and biomarker names that item 8.5 and section 14 require to be preserved.
2.8	Information is presented in a concise and very compact manner	🟢	Gate items are noun phrases; benefit and risk tiers are bare descriptors; marker “why” cells are single clauses.
2.9	It DOES NOT address the reader directly	🟢	Confirmed — no second-person pronouns or imperative address in the QRS body.
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.	🟢	The sheet assumes self-directed implementation: titration-relevant dosing, six-marker bloodwork panel, and self-tracked qualitative endpoints.
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.	🟢	Three-times-daily split dosing, baseline plus 12-week bloodwork, faecal calprotectin testing and nightly sleep ratings all presuppose a high-effort reader.
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 simplified “ask your doctor” framing; the monitoring panel and dose-form distinctions are beyond general-population content.
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 at-a-glance flags that the clearest signal is in older adults with measurable decline — the ER’s key discriminator between an average reader and an optimizing one — and the Protocol names the trial regimen versus the pharmacopoeial one.
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.	🟢	“Longevity” appears in the title and header topic; “anti-aging” appears nowhere 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.	🟢	“Mucosal irritation”, “intestinal barrier disruption”, “sedation and daytime drowsiness”, “uterine stimulation” are used in the tiered cards; no “pill”, “shot” or “bad reaction”. The one colloquial term, “gut”, is carried verbatim from the ER’s own wording (ER lines 418, 458).

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 present verbatim at QRS lines 446, 492, 539, 565, 580, 611, 636, 640–642, 742 and in the tier <strong> labels at lines 542–557 and 614–629.
3.2	All “…” from the [qrs_template] are present in the the QRS.	🟢	Set comparison of span names against the template returns zero template variables missing; the only additional names are the numbered expansions of the template’s repeatable marker_#_* and qualitative_item_# rows.
3.3	Spans that are not addressed in a checklist item are left unchanged	🟢	The non-variable <span website="evidence_review">, <span website="audit"> and <span website="full_review"> elements are byte-identical to the template, as are the header subline wording, the footer disclaimer and the entire stylesheet block (lines 24–409).

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 drawn on by the QRS is empty — all four benefit tiers, all four risk tiers, the contraindication list, the interaction list, the protocol, the biomarker table and the qualitative list are populated in the ER.
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_label “Standardized extract, the clinical-trial approach” and action_2_label “Traditional decoction, the pharmacopoeial approach” and action_3_label “Best time of day” reproduce the ER bold labels at lines 332, 334 and 340 exactly.
4.3	Labels are not paraphrased, abbreviated, or invented.	🟢	Time-to-effect labels are drawn from the ER’s own wording at line 385 (“Measurable memory endpoints…”, “Subjective calm-alert effects…”); biomarker names match the ER table’s first column verbatim.
4.4	The QRS DOES NOT use emoji indicators (no 🟩, 🟥, 🟨, etc.). Color and emphasis are conveyed through CSS and bold labels.	🟢	Character scan of the document body returns no code points above U+2100; the ER’s 🟩/🟥/🟨/⚠️ markers were all 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.	🟢	Content is within the one-page budget: 60-word at-a-glance, 3 protocol cells, 2 time cells (third hidden), 4 benefit and 4 risk lines, 5 contraindications, 8 interactions, 6 biomarker rows, 5 qualitative items. Long ER bullets were condensed rather than carried in full.

---

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 metadata comment opens on line 2, immediately after <!doctype html> on line 1, and closes on line 14 before the template comment on 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 descriptive text on line 2 precedes 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.	🟢	Entirely enclosed in an HTML comment; none of the values (er_filename, git_issue, duration) reappear in the head or 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.	🟢	All values are single-space-separated with no trailing whitespace; only duration: "00:03" is quoted, correctly so because the value contains a colon.
5.5	The filename of the source ER is stated as “er_filename: [er_filename]”	🟢	Line 4: er_filename: polygala_tenuifolia_2026-0825-1951_Opus_ER.md, matching the ER’s own filename field at ER line 17.
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 version badge at the top of QRS.md.
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: 2026-0820-2118 — correct 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]”	🟢	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” — single word, 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, with no context-window or tier qualifier appended.
5.12	The filename of the document is stated as “qrs_filename: [filename of this document]”	🟢	Line 9: qrs_filename: polygala_tenuifolia_2026-0825-1951_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 (lines 4–12); duration is the only quoted value and its colon requires the 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: Polygala tenuifolia for Health & Longevity - Quick Reference Sheet, matching ER canonical_topic (ER line 8) 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 &)	🟢	Line 417: Polygala tenuifolia for Health & Longevity.
6.3	[header_subline_date] is set to [qrs_creation_date reformatted as MM/DD/YYYY]	🟢	Line 421: 08/20/2026, the correct MM/DD/YYYY rendering of qrs_creation_date 2026-0820-2118.
6.4	[header_subline_model] is set to [qrs_creator_ai_fullname]	🟢	Line 425: Opus 5, matching the frontmatter 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.	🟢	The header block (lines 415–428) is structurally identical to the template; the ER’s “Also known as” line (ER line 31) was correctly not carried over.

7. At-A-Glance Section

#	Description	Result	Comments
7.1	[at_a_glance] is dense, execution-oriented summary of the ER Conclusion section	🟢	Lines 434–438 compress all three Conclusion paragraphs (ER lines 456–460) into what the herb is, where the human signal is clearest, where it is animal-only, and the practical mitigation (processed root with food).
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.	🟢	“processed plant root … memory, mood and sleep” ← ER line 456; “clearest human signal … older adults with measurable decline” ← ER line 456; “reduced low mood inside traditional multi-herb formulas” ← ER line 456; “Calming and sleep effects rest almost entirely on animal work” ← ER line 456 verbatim; “irritate the throat and gut … processed root with food” ← ER line 458.
7.4	It DOES NOT use acronyms or technical classifications that require specialist knowledge, uses plain-language terms instead	🟢	Vocabulary is entirely lay: “plant root”, “better thinking”, “low mood”, “multi-herb formulas”, “animal work”, “throat and gut”. No acronyms, no clinical-register terms.
7.5	It DOES NOT cite specific trials (names, years, sample sizes, p-values)	🟢	No trial name, year, participant count or p-value appears.
7.6	It DOES NOT cite effect sizes, relative risks, or statistical results	🟢	No MMSE points, standardized mean differences, confidence intervals or risk ratios — all of which the ER carries — were brought across.

8. Contraindications

#	Description	Result	Comments
8.1	The section is derived from the ER Key Interactions & Contraindications section	🟢	All five items map one-to-one onto the ER’s “Populations who should avoid Polygala tenuifolia” bullets at ER lines 302–310.
8.2	[stop_items] represent the Contraindications from the ER	🟢	Complete coverage: pregnancy/breastfeeding, peptic ulcer / erosive gastritis / IBD flare, moderate-severe liver impairment, children under 18, and the 14-day pre-surgery window. None omitted, none added.
8.3	Individual [stop_items] are formatted as <li></li>	🟢	Lines 568–575: five discrete <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.	🟢	The ER’s trailing rationale clauses were stripped: “— reported uterine-stimulant activity and no human exposure data”, “— no clearance data exist for a multi-component botanical”, “, in whom neither dose nor safety has been characterized…”, and “because of the additive sedative load”. No dash-led clause remains in any item.
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).	🟢	“(faecal calprotectin above 250 µg/g)”, “(Child-Pugh Class B or C)”, “during a flare”, “under 18” and “Within 14 days of elective surgery under general anaesthesia” all retained; the Child-Pugh gloss (“a scoring system for liver-disease severity”) was correctly trimmed while the class itself was kept.
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.	🟢	The ER uses no ranking symbols in these bullets; the one comparative threshold is written in words (“above 250 µg/g”) and is carried through as words.
8.7	The section is left empty ONLY IF the ER’s Key Interactions & Contraindications section identifies no population, condition, or scenario for which the intervention should be avoided, deferred, or used only under specialist supervision.	🟢	The section is populated, and correctly so — the ER names five such populations at lines 302–310.
8.8	If the section is left empty, an HTML comment inside the [stop_items] span records the ER basis for the absence, naming or quoting the ER text relied on. E.g.	N/A	The section is not left empty.

9. Key Interactions

#	Description	Result	Comments
9.1	The section is derived from the ER Key Interactions & Contraindications section	🟢	All eight items map one-to-one onto the ER’s interaction bullets at lines 284–298.
9.2	[caution_items] represent the Key Interactions from the ER, excluding any that are already listed as Contraindications	🟢	All eight ER interaction bullets are represented; none duplicates any of the five contraindications.
9.3	Individual [caution_items] are formatted as <li></li>	🟢	Lines 583–601: eight discrete <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.	🟢	Every ER “Caution — …” / “Monitor — …” rationale was stripped, including the mitigation clauses (“two-hour dose separation”, “lower herb dose or a separated evening dose”) and the Kai-Xin-San aside. No dash-led clause remains.
9.5	Parenthetical qualifiers from the ER bullet — example drug lists, time windows, severity classes, threshold values, clinical staging — ARE preserved as part of the item, kept as concise as possible (shortened or trimmed where needed to fit the one-page budget, but never dropped entirely).	🟢	All named example drugs are retained: zolpidem/zopiclone/temazepam/diazepam; donepezil/rivastigmine/galantamine; sertraline/fluoxetine/venlafaxine plus phenelzine; ibuprofen/naproxen/aspirin; diphenhydramine/doxylamine; valerian/kava/melatonin/ashwagandha/magnolia bark; Panax ginseng/quillaja/Bacopa monnieri.
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.	🟢	No ranking symbols in the ER bullets; the drug lists are carried through as plain comma- and semicolon-separated lists.
9.7	The section is left empty ONLY IF the ER’s Key Interactions & Contraindications section identifies no interaction, additive effect, or exposure that changes how the intervention is used.	🟢	The section is populated, and correctly so — the ER names eight such 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 left empty.

10. Protocol

#	Description	Result	Comments
10.1	The section is derived from the ER Protocol section	🟢	All three cells derive from the ER Therapeutic Protocol section (ER lines 332–342).
10.2	The three sets of [action] items cover the three most important actionable implementation aspects from the ER Protocol section	🟢	The two dose regimens the ER foregrounds — the only trialled standardized extract and the pharmacopoeial decoction — plus timing, the ER’s third actionable dimension. Non-actionable modifier bullets (genotype, sex, age, biomarkers) were correctly not promoted.
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 implementation aspects, so all three sets are used and no set needed hiding.
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 populated: labels verbatim from the ER bold labels; values “100 mg three times daily”, “3–9 g dried root daily”, “Breakfast, lunch, dinner or bedtime”; subs condensed from ER lines 332, 334, 340 and 342.

11. Time to Effect

#	Description	Result	Comments
11.1	The three sets of [time] items cover the three most important time-to-effect aspects from the ER	🟢	The ER supplies exactly two distinct time-to-effect aspects (ER line 385): the four-week memory-endpoint window and the 30–60-minute subjective onset. Both are covered; no third exists to carry.
11.2	The sets are picked and ordered by the magnitude of the related benefit	🟢	Memory endpoints (tied to Cognitive Function, the ER’s only High-tier benefit) precede subjective calm-alert effects (tied to the Low-tier anxiety/sleep domains).
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.	🟢	The third set is hidden with style="display: none" at line 523 and its three spans are empty (lines 525, 528, 531) — no placeholder or empty-state phrasing.
11.4	All used [time_#label], [time#value], [time#_sub] items are filled with meaningful content derived from the ER.	🟢	time_1 “Memory endpoints / 4 weeks” with the ER’s own sentence; time_2 “Subjective calm-alert effects / 30–60 minutes” with the ER’s own phrasing — both from ER line 385.
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 section is correctly retained.

12. Benefits

#	Description	Result	Comments
12.1	The section is derived from the ER Expected Benefits section	🟢	All items are the ER’s Expected Benefits sub-headings (ER lines 155–200).
12.2	Key variables are [benefits_high], [benefits_medium], [benefits_low], [benefits_speculative]	🟢	All four spans present and populated (lines 541–558), each under the correct fixed tier label.
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.	🟢	Bare domain names only. The ER’s magnitude paragraphs (MMSE +2.57, SMD 1.28, CIs) and all PMID citations were dropped, as were the “⚠️ Conflicted” flag and the tier emoji.
12.4	Parenthetical content — including effect sizes, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parentheses appear in any benefit item; the ER’s parenthetical glosses (MMSE, ADAS-cog, PPARγ, C. elegans) are absent.
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 are populated 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 items are the ER’s Potential Risks & Side Effects sub-headings (ER lines 225–264).
13.2	Key variables are [risks_high], [risks_medium], [risks_low], [risks_speculative]	🟢	All four spans present and populated (lines 613–630), each under the correct fixed tier label.
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.	🟢	Bare descriptors only. The LD50 figures (7.79 / 14.55 / 15.99 g/kg), the 1.31 risk ratio, the 120–240 mg/kg mouse doses and all citations were dropped, as was the “at High or Prolonged Doses” dose qualifier on the Medium item.
13.4	Parenthetical content — including frequencies, severity grades, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parentheses appear in any risk item; the ER’s parenthetical gloss on haemolysis was removed.
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 are populated in the ER, so no span needed hiding.

14. Monitoring

#	Description	Result	Comments
14.1	The section is derived from the ER Monitoring section	🟢	The table reproduces the ER Monitoring Protocol & Defining Success biomarker table (ER lines 413–420).
14.2	All measurable/quantifiable biomarkers from the Monitoring section are listed	🟢	All six ER rows present with targets verbatim: ALT 10–26 U/L, AST 10–26 U/L, hs-CRP below 0.5 mg/L, faecal calprotectin below 50 µg/g, haemoglobin/haptoglobin, serum albumin 4.2–5.0 g/dL. Each “Why” cell matches the ER’s third column word for word.
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 732–736 condense ER lines 409–411 into the full schedule: baseline before the first dose, clinical tolerability over the first two weeks, bloodwork at 12 weeks then every six to twelve months, cognitive test repeated at 8 to 12 weeks.

15. Qualitative Assessment

#	Description	Result	Comments
15.1	The section is derived from the ER Monitoring section	🟢	All five items come from the ER’s qualitative-markers list at ER lines 424–432.
15.2	All subjective/qualitative biomarkers from the Monitoring section are listed	🟢	All five ER bullets present and none omitted: recognition memory in daily life, working-memory load, sleep onset latency and morning grogginess, mood stability and the “stimulating yet calm” quality, and throat sensation/appetite/stool consistency.

Issues 20/08/2026 21:30

Pass rate 100.00%. No issues found.

Issues 20/08/2026 21:23

1. 1.3 — Hedge dropped in At-A-Glance: [at_a_glance] (line 436) states “Calming and sleep effects rest on animal work”, dropping the ER’s qualifier “almost entirely” (ER line 456) and converting a hedged claim into an absolute one.
2. 1.4 / 11.1 / 11.3 — Trial duration presented as time to effect: [time_2_label] / [time_2_value] / [time_2_sub] (lines 511–521) present “Depressive symptoms, formula trials — 8–12 weeks”, drawn from the ER’s Discontinuation & Cycling → “Intended duration” bullet (ER line 357), under the “Time to effect” heading; the ER names only two time-to-effect aspects (ER line 385), so the third set should have been left empty and hidden.

Fixes 20/08/2026 21:23

1. 1.3 — At-A-Glance hedge restored: [at_a_glance] now reads “Calming and sleep effects rest almost entirely on animal work”, matching the ER’s qualifier; “taken” was dropped from the final clause to keep the section at 60 words.
2. 1.4 / 11.1 / 11.3 — Trial duration removed from Time to effect: The “Depressive symptoms, formula trials — 8–12 weeks” cell was removed; the subjective calm-alert item moved into [time_2], and the now-unused [time_3] set was emptied and hidden with style="display: none" while keeping its spans in place.