Audit: QRS - Lipoic Acid Trisulfide for Muscle Preservation

Audit conducted on 19/09/2026 08:52 using AI4L / Opus 5

Iterations

Summary

Items	Count
Total	93
Passed	85
Failed	0
N/A	8
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.	🟢	Every populated span traces to an ER passage: ≈280 mg / 70 kg adult (ER 314), fasted 30 min dosing (ER 320), split dosing (ER 324), 3 days / months (ER 371), 5 days persistence (ER 341), all nine biomarkers (ER 405–413), all six qualitative markers (ER 417–422).
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.	🟢	“No established human protocol”, “Untested.”, “an arithmetic conversion, not a tested human dose”, “Unknown in humans”, “Duration in humans is unknown”, “no comparison exists” all carried over verbatim.
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”).	🟢	Absolute contraindications stay absolute (platinum chemotherapy, pregnancy/lactation, under 18); the split-dosing value is hedged in its sub-line exactly as the ER hedges it.
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.	🟢	No content from Benefit-Modifying Factors or Risk-Modifying Factors appears in the gates or risk card; gate content comes solely from Key Interactions & Contraindications.
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, citations, author names or NCT identifiers appear anywhere in the QRS; drug names (glimepiride, apixaban, omeprazole, etc.) all appear in ER 251–271.
1.6	The QRS does not introduce new attributions.	🟢	No attributions of any kind 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.	🟢	Reserved, evidence-forward register matching the ER’s own restraint about an untested compound.
2.2	The tone of the QRS is simultaneously expert, accessible, objective, and data-driven, but also empowering and encouraging	🟢	Specific thresholds and windows throughout; the At-A-Glance closes on the actionable alternative (“mechanical loading, its enabling condition, works without it”) rather than on discouragement.
2.3	The QRS reads as a trusted, knowledgeable guide rather than a prescriptive doctor	🟢	No imperatives; cells state what was tested and what is unknown.
2.4	The QRS avoids language that implies medical or clinical advice	🟢	Gate items are population and exposure lists, not instructions.
2.5	The QRS “presents information” instead of “providing guidance”, “recommending”, or “advising”	🟢	No occurrences of “recommend”, “advise”, “should” in the document’s own voice.
2.6	The QRS never addresses “the reader” directly — it presents evidence, not guidance	🟢	No second-person pronouns anywhere in the file.
2.7	The QRS is written in plain language, avoiding unnecessary medical jargon	🟢	Technical terms retained are decision-bearing thresholds required by 8.5 (Child-Pugh Class C, HLA-DRB1*04:06, ETHE1); “estimated glomerular filtration rate” is spelled out rather than abbreviated.
2.8	Information is presented in a concise and very compact manner	🟢	Gate items are noun phrases; tier lines are semicolon-joined headings; no ER bullet is reproduced in full.
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.	🟢	Content assumes willingness to genotype, monitor capillary glucose, and source research-grade material.
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.	🟢	Fasted dosing, split dosing, nine-marker panel and a 12-month monitoring cadence are presented 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.	🟢	Plasma total sulfane sulfur (a research-only assay) and HLA genotype gating are retained.
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.	🟢	All benefits sit at Speculative and the sourcing/loading constraint leads the At-A-Glance, matching the ER’s weighting for a self-experimenting 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.	🟢	No occurrence of “anti-aging” in the file.
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.	🟢	No route-of-administration colloquialisms; “low blood sugar” is the ER’s own wording (ER 448, 420) and is required by 7.4 in the lede.

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 headings match the template byte-for-byte (lines 440, 477, 519, 536, 552, 575, 596, 600–602, 718); populated tier labels “Speculative: “ and “Low: “ are unchanged.
3.2	All “…” from the [qrs_template] are present in the the QRS.	🟢	67 spans present: every template name accounted for, with marker_# expanded to 1–9 and qualitative_item_# to 1–6.
3.3	Spans that are not addressed in a checklist item are left unchanged	🟢	Structural diff against the template shows only the expected row/item repetitions; website="evidence_review", website="audit" and website="full_review" spans are untouched.

4. Formatting

#	Description	Result	Comments
4.1	When the source ER section is empty, the QRS uses the ER’s own empty-state phrasing verbatim. Typical phrasings are “None documented in human trials to date” and “Not formally studied”	N/A	No ER section surfaced in the QRS is empty; absent benefit/risk tiers are governed by the more specific rules 12.5 and 13.5.
4.2	Where the ER presents a bulleted item as “Label: content”, the QRS uses the ER’s bold label verbatim as the cell or row label.	🟢	“Human-equivalent estimate”, “Best time of day”, “Single versus split dosing” and “Effect outlasts exposure” match ER bold labels at lines 314, 320, 324, 341; monitoring row labels match the ER table’s Biomarker column.
4.3	Labels are not paraphrased, abbreviated, or invented.	🟢	The only constructed labels are time_1 and time_2, which split the ER’s single Time to effect bullet (ER 371) into its two stated aspects as required by 11.1; no ER bold label is paraphrased.
4.4	The QRS DOES NOT use emoji indicators (no 🟩, 🟥, 🟨, etc.). Color and emphasis are conveyed through CSS and bold labels.	🟢	No emoji present; the ER’s ⚠️ Conflicted and ⭕️ markers were stripped.
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 phrase-level entries; the item counts retained (9 contraindications, 11 interactions, 9 markers) are the minimum permitted by 8.2, 9.2 and 14.2.

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 “—” line 3, closing “—” 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 header 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.	🟢	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 matches the source ER filename exactly.
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: 26.9.11, 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: 2026-0919-0825.
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: 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 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: 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 context-window or other qualifier.
5.12	The filename of the document is stated as “qrs_filename: [filename of this document]”	🟢	Line 9 matches the actual 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 &)	🟢	“Lipoic Acid Trisulfide for Muscle Preservation - Quick Reference Sheet”; no characters require entity encoding.
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 matches ER frontmatter canonical_topic exactly.
6.3	[header_subline_date] is set to [qrs_creation_date reformatted as MM/DD/YYYY]	🟢	2026-0919-0825 → “09/19/2026” (line 421).
6.4	[header_subline_model] is set to [qrs_creator_ai_fullname]	🟢	Line 425: “Opus 5”.
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 “Also known as” line was 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	🟢	Four clauses map to the four decision-relevant points of ER 446–450: mechanism, evidence depth, inherited risk, access plus the loading alternative.
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.	🟢	“chemically spoiled” signal → ER 446; “cell-culture and one short mouse experiment; no humans studied” → ER 446; autoimmune insulin link → ER 448; research-grade access and loading available without it → ER 450.
7.4	It DOES NOT use acronyms or technical classifications that require specialist knowledge, uses plain-language terms instead	🟢	No acronyms; “low blood sugar” rather than hypoglycaemia, “muscle stem cells” rather than satellite cells, “sulfur-enriched form of lipoic acid” rather than trisulfide nomenclature.
7.5	It DOES NOT cite specific trials (names, years, sample sizes, p-values)	🟢	No study, author or year named.
7.6	It DOES NOT cite effect sizes, relative risks, or statistical results	🟢	No numeric effect measures; “a small but real link” is the ER’s own qualitative phrasing.

8. Contraindications

#	Description	Result	Comments
8.1	The section is derived from the ER Key Interactions & Contraindications section	🟢	All nine items trace to ER 259 and 277–284.
8.2	[stop_items] represent the Contraindications from the ER	🟢	All eight ER “Populations who should avoid” bullets are present, plus platinum chemotherapy, which ER 259 labels an absolute contraindication.
8.3	Individual [stop_items] are formatted as <li></li>	🟢	Nine <li> elements inside the 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.	🟢	Explanatory glosses stripped: “(extra copies of the receptor gene)”, “(ethylmalonic encephalopathy)”, “(the most advanced grade of liver failure)” and “for whom no reproductive toxicology exists”; no dash-trailing 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).	🟢	“within the last 5 years”, “(Child-Pugh Class C)”, “below 30 mL/min/1.73 m²”, “under 18 years”, “during treatment” and the MET-amplified tumour types all retained.
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 section is populated, correctly, since ER 275–284 names eight such populations.
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 eleven items trace to ER 251–273.
9.2	[caution_items] represent the Key Interactions from the ER, excluding any that are already listed as Contraindications	🟢	Eleven of the ER’s twelve interaction bullets are carried; platinum chemotherapy is correctly excluded because it is an absolute contraindication. The insulin/sulfonylurea bullet is dual-classified by the ER itself (“Caution, or absolute contraindication where insulin autoantibodies are present”, ER 251), and the two gate entries carve different populations.
9.3	Individual [caution_items] are formatted as <li></li>	🟢	Eleven <li> elements inside the 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.	🟢	All “Caution.” clauses, mechanisms and “Mitigation:” sentences stripped; the ER’s “Other interventions —” prefix removed from the loading item.
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 drug list retained; category glosses “vessel-relaxing drugs:” and “acid-suppressing agents:” dropped while the drug names survive, and only one example (glucoraphanin) trimmed from the sulfur-donor list.
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 section is populated, correctly, since ER 251–273 names twelve interactions.
9.8	If the section is left empty, an HTML comment inside the [caution_items] span records the ER basis for the absence, naming or quoting the ER text relied on. E.g.	N/A	The section is not empty.

10. Protocol

#	Description	Result	Comments
10.1	The section is derived from the ER Protocol section	🟢	All three cells trace to ER Therapeutic Protocol lines 310–324.
10.2	The three sets of [action] items cover the three most important actionable implementation aspects from the ER Protocol section	🟢	Dose (human-equivalent estimate), timing (best time of day) and administration pattern (single versus split) are the three executable dimensions; the remaining ER bullets are modifiers or competing approaches, not implementation parameters.
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 supplies more than three actionable aspects; all three sets are populated.
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 ER-derived content; no placeholder or empty-state 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	🟢	Human muscle endpoint (ER 371), the measured mouse chemical endpoint (ER 371) and persistence after withdrawal (ER 341).
11.2	The sets are picked and ordered by the magnitude of the related benefit	🟢	The targeted clinical outcome leads, followed by the measured mechanistic endpoint, then its duration — descending order of benefit magnitude.
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 exist in the ER; all three sets are populated.
11.4	All used [time_#label], [time#value], [time#_sub] items are filled with meaningful content derived from the ER.	🟢	All nine spans carry ER-derived content, each retaining the ER’s “unknown in humans” hedge where the ER states it.
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 time-to-effect information at lines 341 and 371.

12. Benefits

#	Description	Result	Comments
12.1	The section is derived from the ER Expected Benefits section	🟢	The three speculative entries are the ER’s three muscle-central H4 headings (ER 141, 145, 149).
12.2	Key variables are [benefits_high], [benefits_medium], [benefits_low], [benefits_speculative]	🟢	All four spans present at lines 521–529.
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.	🟢	Headings only; the ER’s supporting sentences, molar ratios and citations are all dropped.
12.4	Parenthetical content — including effect sizes, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parentheticals present; the ER’s ⭕️ “Not Central to Muscle Preservation” benefits are correctly omitted.
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.	🟢	benefits_high, benefits_medium and benefits_low all carry style="display: none" with no content; the ER’s explanatory no-benefit sentences were not carried over.

13. Risks

#	Description	Result	Comments
13.1	The section is derived from the ER Potential Risks & Side Effects section	🟢	Three Low and four Speculative entries match the ER’s H4 headings at lines 197–231.
13.2	Key variables are [risks_high], [risks_medium], [risks_low], [risks_speculative]	🟢	All four spans present at lines 577–590.
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.	🟢	Headings only; every “Magnitude:” paragraph, case count and citation dropped.
13.4	Parenthetical content — including frequencies, severity grades, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parentheticals; the ER’s ⚠️ Conflicted marker on the training-adaptation risk is stripped as a qualifier.
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.	🟢	risks_high and risks_medium carry style="display: none" with no content.

14. Monitoring

#	Description	Result	Comments
14.1	The section is derived from the ER Monitoring section	🟢	All rows trace to the ER Monitoring Protocol & Defining Success table (ER 403–413).
14.2	All measurable/quantifiable biomarkers from the Monitoring section are listed	🟢	All nine ER biomarkers present, with the ER’s optimal ranges and “Why Measure It?” text carried verbatim; the ER’s Context/Notes column is correctly not carried.
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.	🟢	Line 709–712 condenses ER 399–401: baseline, 2 and 4 weeks, 12 weeks, then every 6 months, with body composition at 6 and 12 months.

15. Qualitative Assessment

#	Description	Result	Comments
15.1	The section is derived from the ER Monitoring section	🟢	All six items come from the ER’s qualitative-marker list (ER 417–422).
15.2	All subjective/qualitative biomarkers from the Monitoring section are listed	🟢	All six ER bullets present, in ER order, verbatim.

Issues 19/09/2026 08:52

Pass rate 100.00%. No issues found.

Issues 19/09/2026 08:46

1. 1.4 — Monitoring cadence used as time-to-effect: [time_1_sub] (QRS line 489) presents the ER’s monitoring-cadence sentence from Monitoring Protocol & Defining Success (ER line 401) as Time-to-Effect evidence, duplicating [monitoring_cadence] while leaving the ER’s actual time-to-effect statement (Practical Considerations, ER line 371) unused.

Fixes 19/09/2026 08:46

1. 1.4 — Monitoring cadence used as time-to-effect: Replaced [time_1_sub] with the ER’s own time-to-effect statement from Practical Considerations, changing “Unknown in humans. Body composition and strength are repeated at 6 and 12 months, since nothing shorter can register a real change in muscle.” to “Unknown in humans. Any change in human muscle mass or strength would take months to appear.”, which also removes the duplication with [monitoring_cadence].

Issues 19/09/2026 08:38

1. 9.2 — Insulin/sulfonylurea interaction omitted: The ER’s insulin and sulfonylurea bullet (ER line 251, “Caution, or absolute contraindication where insulin autoantibodies are present”, with named examples glimepiride, gliclazide, glipizide) appears nowhere in [caution_items] (QRS lines 554-565). The Contraindications gate (QRS line 541) covers only the two narrower subsets — autoantibody-positive users and users who cannot monitor glucose — so the ER’s general caution for every other insulin or sulfonylurea user, whose stated consequence is severe hypoglycaemia, is carried by neither decision gate.

Fixes 19/09/2026 08:38

1. 9.2 — Insulin/sulfonylurea interaction added: Added <li>Insulin and sulfonylureas (glimepiride, gliclazide, glipizide)</li> as the first entry of [caution_items], so the ER’s general caution for insulin and sulfonylurea users is now carried by the Key Interactions gate alongside the narrower Contraindications entry.

Issues 19/09/2026 08:30

1. 4.2 / 4.3 — Protocol dose label invented: action_1_label is “Dose” (line 444), but the ER bullet it condenses is “Human-equivalent estimate:” (ER line 314), so the ER’s bold label was not used verbatim.
2. 4.2 / 4.3 — Time-to-effect label paraphrased: time_3_label is “Effect after dosing stops” (line 505), a paraphrase of the ER’s bold label “Effect outlasts exposure:” (ER line 341).
3. 10.1 — Cycling content in Protocol cell: action_3_value reads “Split, pulsed rather than lifelong” (line 469); “pulsed rather than lifelong” is an ER Discontinuation & Cycling bullet label (ER line 339), not content from the ER Therapeutic Protocol section.

Fixes 19/09/2026 08:30

1. 4.2 / 4.3 — Protocol dose label restored: action_1_label changed from the invented “Dose” to the ER’s bold label “Human-equivalent estimate”.
2. 4.2 / 4.3 — Time-to-effect label restored: time_3_label changed from the paraphrase “Effect after dosing stops” to the ER’s bold label “Effect outlasts exposure”; time_3_value changed from the now-redundant “Outlasts exposure” to “5 days in mice”, the duration the ER reports.
3. 10.1 — Cycling content removed from Protocol cell: action_3_value changed from “Split, pulsed rather than lifelong” to “Split dosing”, dropping the phrase imported from the ER Discontinuation & Cycling section.