Audit: QRS - Heavy Metal Detox for Health & Longevity of the ER frontmatter

Audit conducted on 29/08/2026 21:12 using AI4L / Grok 4.5

Iterations

Summary

Items	Count
Total	93
Passed	83
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.	🟢
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.	🟢
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”).	🟢
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.	🟢
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.	🟢
1.6	The QRS does not introduce new attributions.	🟢

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.	🟢
2.2	The tone of the QRS is simultaneously expert, accessible, objective, and data-driven, but also empowering and encouraging	🟢
2.3	The QRS reads as a trusted, knowledgeable guide rather than a prescriptive doctor	🟢
2.4	The QRS avoids language that implies medical or clinical advice	🟢
2.5	The QRS “presents information” instead of “providing guidance”, “recommending”, or “advising”	🟢
2.6	The QRS never addresses “the reader” directly — it presents evidence, not guidance	🟢
2.7	The QRS is written in plain language, avoiding unnecessary medical jargon	🟢
2.8	Information is presented in a concise and very compact manner	🟢
2.9	It DOES NOT address the reader directly	🟢
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.	🟢
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.	🟢
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.	🟢
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.	🟢
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.	🟢
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.	🟢

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”	🟢
3.2	All “…” from the [qrs_template] are present in the the QRS.	🟢
3.3	Spans that are not addressed in a checklist item are left unchanged	🟢

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 used by 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.	🟢
4.3	Labels are not paraphrased, abbreviated, or invented.	🟢
4.4	The QRS DOES NOT use emoji indicators (no 🟩, 🟥, 🟨, etc.). Color and emphasis are conveyed through CSS and bold labels.	🟢
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.	🟢

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.	🟢
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.	🟢
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.	🟢
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.	🟢
5.5	The filename of the source ER is stated as “er_filename: [er_filename]”	🟢
5.6	Version of the QRS.md file used to create the document is stated as “qrs_prompt_version: [Version 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)	🟢
5.8	The nickname of the AI used to create the document is stated as “qrs_creator_ai_nickname: [qrs_creator_ai_nickname]”	🟢
5.9	The nickname of the AI is just a single word model name without version, etc. (e.g., Opus, Sonnet, Grok, Gemini, ChatGPT)	🟢
5.10	The full name of the AI used to create the document is stated as “qrs_creator_ai_fullname: [qrs_creator_ai_fullname]”	🟢
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)	🟢
5.12	The filename of the document is stated as “qrs_filename: [filename of this document]”	🟢
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.	🟢

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 &)	🟢
6.2	[header_topic] is set to the [canonical_topic] of the ER frontmatter, with HTML entities encoded as needed (e.g., & for &)	🟢
6.3	[header_subline_date] is set to [qrs_creation_date reformatted as MM/DD/YYYY]	🟢
6.4	[header_subline_model] is set to [qrs_creator_ai_fullname]	🟢
6.5	No additional header content appears: no badge, version stamp, AKA / alternate names line, source-AI attribution, audit date, or QRS variant marker.	🟢

7. At-A-Glance Section

#	Description	Result	Comments
7.1	[at_a_glance] is dense, execution-oriented summary of the ER Conclusion section	🟢
7.2	[at_a_glance] is no longer than 60 words	🟢
7.3	Every fact in [at_a_glance] is supported by a distinct passage in the ER.	🟢
7.4	It DOES NOT use acronyms or technical classifications that require specialist knowledge, uses plain-language terms instead	🟢
7.5	It DOES NOT cite specific trials (names, years, sample sizes, p-values)	🟢
7.6	It DOES NOT cite effect sizes, relative risks, or statistical results	🟢

8. Contraindications

#	Description	Result	Comments
8.1	The section is derived from the ER Key Interactions & Contraindications section	🟢
8.2	[stop_items] represent the Contraindications from the ER	🟢
8.3	Individual [stop_items] are formatted as <li></li>	🟢
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.	🟢
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).	🟢
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	ER contraindications do not use ranking notation such as “>”.
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.	🟢
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 Contraindications section is not empty.

9. Key Interactions

#	Description	Result	Comments
9.1	The section is derived from the ER Key Interactions & Contraindications section	🟢
9.2	[caution_items] represent the Key Interactions from the ER, excluding any that are already listed as Contraindications	🟢
9.3	Individual [caution_items] are formatted as <li></li>	🟢
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.	🟢
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).	🟢
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	ER interactions do not use ranking notation such as “>”.
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.	🟢
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 Key Interactions section is not empty.

10. Protocol

#	Description	Result	Comments
10.1	The section is derived from the ER Protocol section	🟢
10.2	The three sets of [action] items cover the three most important actionable implementation aspects from the ER Protocol 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 Protocol section names more than three distinct actionable implementation aspects.
10.4	All used [action_#label], [action#value], [action#_sub] items are filled with meaningful content derived from the ER Protocol section.	🟢

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	🟢
11.2	The sets are picked and ordered by the magnitude of the related benefit	🟢
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	The ER provides at least three distinct time-to-effect aspects.
11.4	All used [time_#label], [time#value], [time#_sub] items are filled with meaningful content derived from the ER.	🟢
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 (Practical Considerations and Expected Benefits).

12. Benefits

#	Description	Result	Comments
12.1	The section is derived from the ER Expected Benefits section	🟢
12.2	Key variables are [benefits_high], [benefits_medium], [benefits_low], [benefits_speculative]	🟢
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.	🟢
12.4	Parenthetical content — including effect sizes, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢
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 benefit tiers have items.

13. Risks

#	Description	Result	Comments
13.1	The section is derived from the ER Potential Risks & Side Effects section	🟢
13.2	Key variables are [risks_high], [risks_medium], [risks_low], [risks_speculative]	🟢
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.	🟢
13.4	Parenthetical content — including frequencies, severity grades, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢
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 risk tiers have items.

14. Monitoring

#	Description	Result	Comments
14.1	The section is derived from the ER Monitoring section	🟢
14.2	All measurable/quantifiable biomarkers from the Monitoring section are listed	🟢
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.	🟢

15. Qualitative Assessment

#	Description	Result	Comments
15.1	The section is derived from the ER Monitoring section	🟢
15.2	All subjective/qualitative biomarkers from the Monitoring section are listed	🟢

Issues 29/08/2026 21:12

Pass rate 100.00%. No issues found.

Issues 29/08/2026 20:42

1. 1.1 — Urinary-metals time sub: time_3_sub (QRS lines 510–511) says “Spike after EDTA or DMSA; mobilization, not a longevity endpoint.” The ER uses “Excretion is mobilization, not a longevity endpoint” only for urinary lead/cadmium after EDTA in people without overt poisoning, not for the 12–24 hour spike after DMSA in documented mercury poisoning.

2. 4.5 — Not condensed to A4: Monitoring copies all 12 ER biomarkers with full target wording (lines 602–733), Low benefits concatenates six headings into one wrapping line (lines 527–528), and cadence includes an extra non-frequency sentence. The sheet was not condensed to a single-A4 budget.

Fixes 29/08/2026 20:42

1. 1.1 — Urinary-metals time sub: Changed time_3_sub from “Spike after EDTA or DMSA; mobilization, not a longevity endpoint” to “Spike after EDTA or DMSA”, matching the ER Practical Considerations time-to-effect sentence and dropping the EDTA-without-poisoning clause that had been applied to DMSA as well.

2. 4.5 — Not condensed to A4: Shortened Low benefits from six headings to three (mercury excretion, EDTA lead/cadmium excretion, sweat), trimmed the ferritin target and time_2_sub, and dropped the non-cadence provoked-urine sentence so the sheet fits a single A4 page.

Issues 29/08/2026 20:37

1. 7.4 — At-a-glance specialist terms: [at_a_glance] uses “Metal-normal adults” and “unselected chelation”, specialist classifications a non-specialist would not use unprompted. The ER Conclusion offers plainer phrasing such as “people without documented poisoning”.

Fixes 29/08/2026 20:37

1. 7.4 — At-a-glance specialist terms: Replaced the closing [at_a_glance] clause “Metal-normal adults: unselected chelation is not shown to extend life” with “People without documented poisoning: not shown to extend life.”

Issues 29/08/2026 20:21

1. 1.1 / 1.3 / 7.1 / 7.3 — At-a-glance longevity claim: The last sentence of [at_a_glance] says “Chelation without documented poisoning is not shown to extend life.” The ER Conclusion states that unselected chelation in metal-normal adults is not shown to extend life, and that documented overload after source removal is where metal-lowering is shown (including extra lead stores with reduced kidney filter function, distinct from confirmed poisoning).

Fixes 29/08/2026 20:21

1. 1.1 / 1.3 / 7.1 / 7.3 — At-a-glance longevity claim: Replaced the last at-a-glance sentence from “Chelation without documented poisoning is not shown to extend life” with “Metal-normal adults: unselected chelation is not shown to extend life,” matching the ER Conclusion subject and cautious phrasing.

Issues 29/08/2026 19:53

1. 9.5 — Severity classes dropped: All eight Key Interactions omit the ER parenthetical severity tags (caution) and (monitor) (QRS lines 556–563; ER lines 312–326). Example-drug and time-window parentheticals remain, but those severity classes were dropped entirely.

Fixes 29/08/2026 19:53

1. 9.5 — Severity classes restored: Restored the ER parenthetical severity classes (caution) and (monitor) on all eight Key Interactions, combining them with existing time-window parentheticals where those were already present.

Issues 29/08/2026 19:47

1. 1.3 / 7.4 — Unselected chelation phrasing: At-a-glance says “Unselected chelation is not shown to extend life,” dropping the ER Conclusion qualifier “in metal-normal adults” (broadening the claim) and using the clinical-register label “Unselected,” which a non-specialist would not use unprompted.

Fixes 29/08/2026 19:47

1. 1.3 / 7.4 — Unselected chelation phrasing: Replaced at-a-glance “Unselected chelation is not shown to extend life” with “Chelation without documented poisoning is not shown to extend life,” restoring the ER population limit in plain language. Dropped “toxic” and “Repeated” so the paragraph stays at 60 words.

Issues 29/08/2026 19:30

1. 1.2 / 1.3 / 7.1 — Heart-event claim strengthened: At-a-glance (QRS line 433) replaces the ER Conclusion’s split heart-event record (“not a settled yes or no”; one trial modest drop, a second no event reduction) with the stronger “Heart-event benefit was not confirmed.”
2. 1.3 — Provoked-urine qualifier dropped: Monitoring cadence (QRS line 738) omits “in medical toxicology” from the ER’s “Provoked urine is not used as a start/stop criterion in medical toxicology,” generalizing the statement.

Fixes 29/08/2026 19:30

1. 1.2 / 1.3 / 7.1 — Heart-event claim strengthened: Rewrote at-a-glance so the heart-event line uses the ER Conclusion phrasing “Heart-event split: not a settled yes or no” instead of “Heart-event benefit was not confirmed,” and aligned nearby conclusion wording (“Calcium-free infusions”, “Unselected chelation”).
2. 1.3 — Provoked-urine qualifier dropped: Restored “used as” and “in medical toxicology” on the monitoring-cadence provoked-urine sentence.

Issues 29/08/2026 19:12

1. 7.4 — Specialist at-a-glance phrasing: [at_a_glance] (QRS line 433) uses specialist classifications a non-specialist would not use unprompted: “Unselected chelation” and “did not replicate”. The ER Conclusion states the same facts in plainer terms (chelation without documented poisoning; heart events were not confirmed later).

2. 9.4 — Mechanistic interaction leftover: The Key Interactions item “Insulin and hypoglycemics with EDTA cocktails or high-dose vitamin C (glucose readings)” (QRS line 559) keeps mechanistic rationale in “(glucose readings)”, which 9.4 requires stripped.

Fixes 29/08/2026 19:12

1. 7.4 — Specialist at-a-glance phrasing: Replaced “Heart-event benefit did not replicate” with “Heart-event benefit was not confirmed” and “Unselected chelation” with “Chelation without documented poisoning” in [at_a_glance].
2. 9.4 — Mechanistic interaction leftover: Removed the mechanistic parenthetical “(glucose readings)” from the insulin and hypoglycemics Key Interactions item.

Issues 29/08/2026 19:05

1. 1.1 / 1.3 / 7.3 — Longevity claim overstated: [at_a_glance] (QRS line 433) says “Not shown to extend life without documented poisoning,” which is not literally supported by ER Conclusion line 485 and strengthens that line’s metal-normal / unselected-chelation limitation into a poisoning-conditional lifespan claim.
2. 9.2 — OTC pain relievers omitted: The ER Key Interactions bullet “Over-the-counter (OTC) pain relievers” (ER line 320: chronic NSAIDs on EDTA days; acetaminophen on DMSA days) is missing from [caution_items] (QRS lines 555–563) and is not listed as a contraindication.

Fixes 29/08/2026 19:05

1. 1.1 / 1.3 / 7.3 — Longevity claim wording: Replaced [at_a_glance] clause “Not shown to extend life without documented poisoning” with “Unselected chelation is not shown to extend life,” matching ER Conclusion line 485.
2. 9.2 — OTC pain-reliever interaction: Added a [caution_items] bullet for chronic nonsteroidal anti-inflammatory drugs on EDTA days and acetaminophen on DMSA days, from ER line 320.

Issues 29/08/2026 18:53

1. 1.1 / 7.3 — Calcium-form infusion wording: At-a-glance line 433 says “Repeated infusions that include calcium slowed kidney-filter loss”. ER Conclusion line 479 attributes that kidney-filter finding to “repeated calcium-form infusions” (the calcium-disodium salt), not an infusion cocktail that merely includes calcium.

Fixes 29/08/2026 18:53

1. 1.1 / 7.3 — Calcium-form infusion wording: Replaced at-a-glance “Repeated infusions that include calcium” with “Repeated calcium-form infusions” so the kidney-filter claim matches the ER Conclusion salt identity.

Issues 29/08/2026 18:38

1. 1.3 — Kidney claim broadened: At-a-glance (QRS line 433) says calcium-salt infusions “slowed further kidney-filter loss when extra lead is stored,” omitting the ER Conclusion restriction to people who also have reduced kidney filter function and repeated infusions (ER line 479). That broadens who the kidney finding applies to.
2. 7.4 — Calcium-salt jargon: At-a-glance (QRS line 433) uses “calcium salt,” a chelator-salt classification a non-specialist would not use unprompted or know exactly (calcium disodium vs disodium EDTA). The ER Conclusion’s own terms are “calcium-form infusions” and “calcium-free infusion salt.”

Fixes 29/08/2026 18:44

1. 1.3 — Kidney claim broadened: Rewrote at-a-glance so the kidney finding is “Repeated infusions that include calcium slowed kidney-filter loss in extra lead stores with reduced filter function,” restoring the ER Conclusion’s repeated-infusion and reduced-filter-function restrictions.
2. 7.4 — Calcium-salt jargon: Replaced “Infusions with the calcium salt” with “infusions that include calcium,” paired with “Infusions without calcium,” so the salt distinction is in plain language.

Issues 29/08/2026 18:14

1. 1.1 / 1.3 — IQ broadened to cognition: time_1_sub (line 489) says “no cognition gain”; the ER TLC write-up and Practical Considerations state “without IQ gain”, not a broader cognition endpoint.

2. 7.4 — Specialist salt and burden terms: At-a-glance (line 433) uses “Calcium-form”, “Calcium-free”, and “metal-normal”, technical classifications a non-specialist would not use unprompted.

3. 9.4 — Interaction key facts stripped: The insulin caution (line 559) is only the ER label; it omits that EDTA cocktails and high-dose vitamin C can alter glucose readings. The NAC/ALA/glutathione/vitamin C item (line 561) likewise drops the chelator-context key fact.

4. 12.3 — Autism result qualifier added: Low benefits (line 528) replaces the ER heading “Autism symptoms” with “no autism-symptom benefit”, adding a qualifier instead of the key-fact heading.

Fixes 29/08/2026 18:14

1. 1.1 / 1.3 — IQ broadened to cognition: Changed time_1_sub from “no cognition gain” to “no IQ gain” to match the ER TLC endpoint.

2. 7.4 — Specialist salt and burden terms: Rewrote at-a-glance to “Infusions with the calcium salt”, “Infusions without calcium”, and “without documented poisoning”, dropping “Calcium-form”, “Calcium-free”, and “metal-normal”.

3. 9.4 — Interaction key facts stripped: Expanded the insulin item to “Insulin and hypoglycemics with EDTA cocktails or high-dose vitamin C (glucose readings)” and the thiol item to “…with DMSA or DMPS”.

4. 12.3 — Autism result qualifier added: Replaced “no autism-symptom benefit” with the ER heading “autism symptoms”.

Issues 29/08/2026 17:58

1. 4.2 / 4.3 — Protocol labels paraphrased: Protocol cell labels are not the ER Protocol bold labels. QRS uses “Toxicology model”, “Intravenous EDTA”, and “Oral DMSA” (lines 444, 456, 466) instead of “Medical-toxicology model (CDC/WHO)”, “TACT/ACAM infusion model (Lamas and chelation clinics)”, and “Cutler low-and-slow oral model”.

2. 9.4 — Trailing interaction elaborations: Key Interactions keep extra clauses beyond the key fact: “cocktail included heparin” after a semicolon (line 557) and the mechanistic parenthetical “EDTA cocktails and high-dose vitamin C can alter glucose readings” (line 559).

Fixes 29/08/2026 17:58

1. 4.2 / 4.3 — Protocol labels paraphrased: Restored ER Protocol bold labels verbatim in the three action cells: “Medical-toxicology model (CDC/WHO)”, “TACT/ACAM infusion model (Lamas and chelation clinics)”, and “Cutler low-and-slow oral model”.

2. 9.4 — Trailing interaction elaborations: Stripped “cocktail included heparin” from the anticoagulant item and removed the mechanistic parenthetical on insulin and hypoglycemics, leaving only the key interaction facts.