Audit: QRS - Low-Level Light Therapy for Health & Longevity

Audit conducted on 06/08/2026 07:43 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.	🟢	Every span traced to source: at-a-glance to ER Conclusion (lines 631–633), protocol cells to Therapeutic Protocol (483–487), time-to-effect to Practical Considerations (545), benefit/risk tiers to the ER sub-headings, gates to Key Interactions & Contraindications (432–455), monitoring to the ER biomarker table (573–580) and cadence paragraph (589), qualitative items to ER lines 593–599.
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.	🟢	Hedges are carried through: “Speculative” tiers retain the ER’s speculative framing; “Loss of effect from overdosing” and “Stimulation of occult malignancy” keep the ER’s own labels. No ER hedge is dropped.
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 remain in the STOP gate (pregnancy, photodynamic sensitisation, malignant lesion); “monitor”-grade ER items (antioxidants, same-outcome interventions) remain in the CAUTION gate. No tier migration.
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 ER Benefit-Modifying Factors (314–330) or Risk-Modifying Factors (410–426) appears in the gates or risk card; all gate items come from Key Interactions & Contraindications, all risk items from Potential Risks & Side Effects.
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, citations, expert names, NCT identifiers, or brand names anywhere.
1.6	The QRS does not introduce new attributions.	🟢	No attributions of any kind are 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.	🟢	Measured, non-promotional register matching the ER; British spellings (“colour”, “haemoglobin”, “sensitisation”) carried through consistently.
2.2	The tone of the QRS is simultaneously expert, accessible, objective, and data-driven, but also empowering and encouraging	🟢	Quantified protocol values, biomarker targets, and time-to-effect windows give the reader actionable footing without hype.
2.3	The QRS reads as a trusted, knowledgeable guide rather than a prescriptive doctor	🟢	Content is presented as noun-phrase facts (e.g., “3–5 sessions per week”), never as instructions to a patient.
2.4	The QRS avoids language that implies medical or clinical advice	🟢	No imperatives anywhere; the footer disclaimer is the template’s fixed text.
2.5	The QRS “presents information” instead of “providing guidance”, “recommending”, or “advising”	🟢	No occurrence of “recommend”, “advise”, “should”, or “must” in any populated span.
2.6	The QRS never addresses “the reader” directly — it presents evidence, not guidance	🟢	No second-person pronouns. The ER’s “Anyone judging the intervention before 8–12 weeks…” was recast impersonally in [time_3_sub].
2.7	The QRS is written in plain language, avoiding unnecessary medical jargon	🟢	Technical terms retained are the ER’s own condition and marker names; every acronym in the Monitoring table is expanded on first appearance (hs-CRP, CK, HbA1c, TSH, TPO-Ab).
2.8	Information is presented in a concise and very compact manner	🟢	Every ER paragraph is reduced to a short phrase; benefit and risk tiers are semicolon-separated single lines.
2.9	It DOES NOT address the reader directly	🟢	Confirmed — no “you”/”your” anywhere in the document.
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-range biomarker targets (hs-CRP < 0.5 mg/L, HbA1c 4.8–5.4%) and the eight-marker panel address an optimisation-oriented 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.	🟢	3–5 sessions weekly for 16–26 weeks, dose calculation in J/cm², and a repeat laboratory panel are presented without softening.
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 or motivational framing; the sheet assumes the reader will measure irradiance and track markers.
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 names both the narrow dose window and the ocular hazard; “Direct extension of healthspan or lifespan” is kept in the Speculative tier rather than promoted.
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 title uses “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.	🟢	Formal register throughout (“erythema”, “post-inflammatory hyperpigmentation”, “axial”); the plain-language “mouth ulcers” in the at-a-glance is the ER’s own Conclusion wording, required by section 7.

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 verified byte-for-byte against the template: lines 445, 485, 530, 591, 618, 727 (headings), 558, 573 (gates), 534/539/544/549 and 595/600/605/610 (tiers), 622–624 (column headers).
3.2	All “…” from the [qrs_template] are present in the the QRS.	🟢	Full set present: page_title, header_topic, header_subline_date, header_subline_model, at_a_glance, action_1–3 (label/value/sub), time_1–3 (label/value/sub), benefits_×4, stop_items, caution_items, risks_×4, marker_1–8 (name/target/why), monitoring_cadence, qualitative_item_1–7.
3.3	Spans that are not addressed in a checklist item are left unchanged	🟢	A normalized diff against the template shows the only structural differences are legitimate marker_#/qualitative_item_# row expansion; the website="evidence_review", website="audit" and website="full_review" spans, the stylesheet link, and the entire CSS block 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 source ER section that feeds the QRS is empty — all four benefit tiers, all four risk tiers, the protocol, the gates, and the monitoring panel 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] “Standard wavelength selection”, [action_2_label] “Standard dose per session”, [action_3_label] “Standard frequency and course length” match the ER bold labels at lines 483, 485, 487 verbatim.
4.3	Labels are not paraphrased, abbreviated, or invented.	🟢	Protocol labels are verbatim; monitoring marker names match the ER table’s Biomarker column exactly; tier labels are the template’s fixed set.
4.4	The QRS DOES NOT use emoji indicators (no 🟩, 🟥, 🟨, etc.). Color and emphasis are conveyed through CSS and bold labels.	🟢	The ER’s 🟩/🟥/🟨 tier markers were dropped; the QRS contains no emoji, relying on .benefits/.risks/.gate CSS and <strong> 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.	🟢	The template’s single-sheet layout, print rules, and @page size: A4 are unmodified, and every section is condensed rather than extended: multi-paragraph ER entries are reduced to single phrases, the eight-row monitoring table to fragment-length “Why” cells, and the ER’s parenthetical glosses stripped throughout.

---

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 on line 2, immediately after <!doctype html> on line 1, and precedes the template comment on line 16 and <html> on line 17.
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 --- on line 3, closing --- on 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.	🟢	Enclosed in an HTML comment; none of the values reappear in <head> or <body> except [header_subline_model], which section 6.4 requires.
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 single-spaced after the colon with no trailing whitespace; only duration: "00:03" 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: low_level_light_therapy_2026-0806-0355_Opus_ER.md, matching the ER’s own filename field.
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 head 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: 2026-0806-0711 — 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 + version number, no qualifier.
5.12	The filename of the document is stated as “qrs_filename: [filename of this document]”	🟢	Line 9: qrs_filename: low_level_light_therapy_2026-0806-0355_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, including the appended git_user: evipedia-1 and git_issue: 4834; 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: “Low-Level Light Therapy for Health & Longevity - Quick Reference Sheet” — matches the ER canonical_topic with the ampersand correctly 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: “Low-Level Light Therapy for Health & Longevity”.
6.3	[header_subline_date] is set to [qrs_creation_date reformatted as MM/DD/YYYY]	🟢	Line 421: “08/06/2026”, the correct MM/DD/YYYY rendering of qrs_creation_date: 2026-0806-0711.
6.4	[header_subline_model] is set to [qrs_creator_ai_fullname]	🟢	Line 425: “Opus 5”, matching the frontmatter 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.	🟢	The header holds only the title and the template’s fixed subline; the ER’s “Also known as” list (ER line 30) 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	🟢	Four sentences drawn from ER lines 631–633: mechanism, the three firmest benefits, the two-sided dose window, and the principal hazard.
7.2	[at_a_glance] is no longer than 60 words	🟢	58 words.
7.3	Every fact in [at_a_glance] is supported by a distinct passage in the ER.	🟢	“too weak to heat tissue… produce energy and handle stress” (ER 631); “more hair on a thinning scalp, less pain in arthritic joints and tendons, and fewer mouth ulcers during cancer treatment” (ER 631); “too little light does nothing, and too much reverses the benefit” (ER 633); “The clearest hazard is to the eyes” (ER 633).
7.4	It DOES NOT use acronyms or technical classifications that require specialist knowledge, uses plain-language terms instead	🟢	No acronyms and no clinical-register words: “mouth ulcers” rather than mucositis, “arthritic joints” rather than osteoarthritis, “thinning scalp” rather than androgenetic alopecia.
7.5	It DOES NOT cite specific trials (names, years, sample sizes, p-values)	🟢	No trial names, author names, years, or sample sizes appear.
7.6	It DOES NOT cite effect sizes, relative risks, or statistical results	🟢	No numbers of any kind; the ER’s SMDs and confidence intervals are absent.

8. Contraindications

#	Description	Result	Comments
8.1	The section is derived from the ER Key Interactions & Contraindications section	🟢	All eight items map one-to-one onto the ER’s “Populations who should avoid this intervention” sub-list (ER lines 446–455).
8.2	[stop_items] represent the Contraindications from the ER	🟢	Complete: malignant/pre-malignant lesion, photodynamic sensitisation, photosensitivity disorders, eye-directed devices, pregnancy, thyroid-directed use, implanted device/infection/swelling, children and adolescents. None omitted, none added.
8.3	Individual [stop_items] are formatted as <li></li>	🟢	Lines 561–568: eight 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.	🟢	No dashes and no trailing clauses; the ER’s explanatory tails such as “(avoid — no safety data rather than evidence of harm)” (ER 452) and “given documented exceedance of ANSI group 1 limits…” (ER 455) were correctly stripped.
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).	🟢	Retained: “(until assessed)”, “(full clearance interval)”, “intraocular surgery within 90 days”, “without specialist supervision”, “(abdominal and pelvic application)”, “untreated” Graves’, “active” thyroid eye disease, “without endocrinology input”, “(laser-class ocular devices)”.
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’s contraindication bullets (lines 446–455) contain no ranking notation; the only symbolic range in the ER, “Fitzpatrick IV–VI”, does not appear in this section.
8.7	If no [stop_items] are present the section is left empty	N/A	Eight stop items are present.

9. Key Interactions

#	Description	Result	Comments
9.1	The section is derived from the ER Key Interactions & Contraindications section	🟢	All six items map onto ER bullets at lines 432, 436, 438, 440, 442, 444.
9.2	[caution_items] represent the Key Interactions from the ER, excluding any that are already listed as Contraindications	🟢	All six non-contraindication interaction bullets are present, and the “Photodynamic therapy photosensitisers — absolute contraindication” bullet (ER 434) is correctly excluded here, appearing only in the STOP gate.
9.3	Individual [caution_items] are formatted as <li></li>	🟢	Lines 576–581: six 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.	🟢	The ER’s “— caution; consequence: …” and “Mitigating action: …” tails are all stripped, as is the Mawu et al. 2025 citation from the same-outcome bullet (ER 444).
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 example list survives in condensed form, including the antioxidant thresholds “vitamin C above 1 g, vitamin E above 400 IU, N-acetylcysteine above 1,200 mg daily” and “high-dose” Ginkgo biloba.
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’s interaction bullets use plain prose lists with no ranking symbols.
9.7	If no [caution_items] are present the section is left empty	N/A	Six caution items are present.

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, lines 483–487.
10.2	The three sets of [action] items cover the three most important actionable implementation aspects from the ER Protocol section	🟢	Wavelength selection, dose per session, and frequency/course length are the three executable levers; the remaining ER bullets are comparative, historical, or attributive (competing approaches, who popularised each, genetics, sex, age).
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 provides more than three actionable aspects; all three sets are used.
10.4	All used [action_#label], [action#value], [action#_sub] items are filled with meaningful content derived from the ER Protocol section.	🟢	All nine spans populated and traceable: “630–670 nm red; 810–850 nm near-infrared” (ER 483), “1–10 J/cm² at the skin” with “20–100 mW/cm², about 3–15 minutes per region. Ocular protocols well below 1 J/cm².” (ER 485), “3–5 sessions per week” with the daily/twice-weekly and 16–26 / 6–12 week qualifiers (ER 487).

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	🟢	Hair density, joint pain, and cognition are the three time-to-effect windows attached to the ER’s highest-graded benefits; all three are stated in ER line 545.
11.2	The sets are picked and ordered by the magnitude of the related benefit	🟢	Descending order by ER-reported magnitude: hair density SMD 1.32 (High tier, ER 184), joint pain SMD 0.96 (High tier, ER 190), cognition SMD 0.51 (Medium tier, ER 204).
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 lists five distinct time-to-effect windows; all three sets are used.
11.4	All used [time_#label], [time#value], [time#_sub] items are filled with meaningful content derived from the ER.	🟢	All nine spans populated: “16 weeks” / “Assessed at 16 weeks; still improving at 26 weeks”, “2–4 weeks” / “Emerges over 2–4 weeks of regular sessions”, “6–12 weeks” / the ER’s 8–12-week premature-judgement caveat, all from ER line 545.
11.5	If the ER does not provide any information on time to effect, the section is removed completely from the Protocol Panel	N/A	The ER provides a dedicated “Time to effect” bullet (line 545), so the section is correctly retained.

12. Benefits

#	Description	Result	Comments
12.1	The section is derived from the ER Expected Benefits section	🟢	Every listed benefit corresponds to an ER Expected Benefits sub-heading (lines 180–310), and the tier assignment matches the ER’s own High/Medium/Low/Speculative grouping.
12.2	Key variables are [benefits_high], [benefits_medium], [benefits_low], [benefits_speculative]	🟢	All four spans present and populated at lines 532, 537, 542, 547.
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 benefit reduced to a short noun phrase; the ER’s “Magnitude:” lines, ⚠️ Conflicted markers, and mechanistic paragraphs are all absent.
12.4	Parenthetical content — including effect sizes, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parentheses occur in any benefits span; the ER’s glosses such as “(androgenetic)” and the SMD/CI figures were correctly dropped.
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 carry items in the ER (3 high, 8 medium, 8 low, 3 speculative), so no span needs hiding.

13. Risks

#	Description	Result	Comments
13.1	The section is derived from the ER Potential Risks & Side Effects section	🟢	All eleven items correspond to ER Potential Risks & Side Effects sub-headings (lines 340–406), with tiers preserved.
13.2	Key variables are [risks_high], [risks_medium], [risks_low], [risks_speculative]	🟢	All four spans present and populated at lines 593, 598, 603, 608.
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 risk reduced to a short noun phrase; the ANSI exceedance figures, the 5–15% incidence numbers, and the Ostrin & Schill / Chen et al. citations are all absent.
13.4	Parenthetical content — including frequencies, severity grades, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parentheses occur in any risks span; the ER’s “(ANSI…)”, “(Fitzpatrick IV–VI)” and “Magnitude:” content was correctly dropped.
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 carry items in the ER (2 high, 4 medium, 3 low, 2 speculative), so no span needs 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 (lines 571–580) in the same order.
14.2	All measurable/quantifiable biomarkers from the Monitoring section are listed	🟢	All eight ER rows present: hs-CRP, creatine kinase, HbA1c, fasting glucose and fasting insulin, TSH, TPO-Ab, 25-hydroxyvitamin D, and complete blood count with differential — with the ER’s optimal functional ranges reproduced exactly.
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 721 condenses ER line 589 and the baseline draw at ER line 569: full panel at baseline, 12–16 weeks, then every 6–12 months; symptom/function tests at 4 weeks; photography at 8 weeks then every 3 months; dermatological and retinal examinations annually.

15. Qualitative Assessment

#	Description	Result	Comments
15.1	The section is derived from the ER Monitoring section	🟢	All seven items come from the “Qualitative markers, tracked in a simple log” list in the ER Monitoring Protocol & Defining Success section (lines 591–599).
15.2	All subjective/qualitative biomarkers from the Monitoring section are listed	🟢	All seven ER qualitative markers present in the ER’s own order: pain intensity/stiffness timing, sleep onset latency and depth, energy and perceived exertion, cognitive clarity and word-finding, skin feel, recovery quality, and treated-field redness/warmth/pigmentation with date.

Issues 06/08/2026 07:43

Pass rate 100.00%. No issues found.

Issues 06/08/2026 07:27

1. 4.5 — QRS overflows one A4 page: Measured against the template print rules (@page A4 with 12 mm sheet padding, 1032 px usable height) the sheet renders at roughly 2,210 px — about 2.1 pages; Monitoring (~473 px), the decision gates (~394 px), the Protocol panel (~355 px) and Benefits (~291 px) each exceed their per-section budget and carry wording that was not condensed.

Fixes 06/08/2026 07:27

1. 4.5 — Protocol panel condensed: Shortened all three action_#_sub and all three time_#_sub cells to single short clauses (e.g. action_1_sub from a four-clause depth/wavelength listing to “Red for skin, hair, and superficial wounds; near-infrared for joints, muscle, nerve, and transcranial targets.”), cutting the panel from ~355 px to ~281 px.
2. 4.5 — Monitoring card condensed: Rewrote all eight marker_#_why cells to one-line statements (e.g. “Systemic inflammatory load; the endpoint most likely to shift with whole-body or large-area treatment” → “Systemic inflammatory load; most likely to shift”) and trimmed monitoring_cadence from 330 to 190 characters, cutting the card from ~473 px to ~422 px.
3. 4.5 — Decision gates condensed: Trimmed all eight contraindications and all six key interactions to their shortest determinative form while keeping every parenthetical qualifier (90-day window, full clearance interval, named drugs, dose thresholds), cutting the gates from ~394 px to ~342 px.
4. 4.5 — Benefits and Qualitative Assessment condensed: Compressed the medium and low benefit tiers and all seven qualitative markers to bare outcome phrases, removing redundant qualifiers while preserving direction and every ER item.

Issues 06/08/2026 07:24

1. 2.15 — Lay short form for lupus: stop_items at line 589 reads “lupus with skin involvement” where the ER (line 450) specifies “systemic lupus erythematosus with skin involvement”; the shortened form is the consumer-grade term and also broadens the gate beyond the systemic disease the ER names.

Fixes 06/08/2026 07:24

1. 2.15 — Lay short form for lupus: Changed the stop_items entry from “lupus with skin involvement” to “systemic lupus erythematosus with skin involvement”, restoring the ER’s formal term and the systemic-disease scope of the gate.

Issues 06/08/2026 07:17

1. 4.2 / 4.3 — Protocol labels not verbatim: The three protocol cell labels — “Wavelength” (line 449), “Dose per session” (line 465) and “Frequency & course” (line 480) — are abbreviated paraphrases of the ER’s bold bullet labels “Standard wavelength selection:”, “Standard dose per session:” and “Standard frequency and course length:” in the Therapeutic Protocol section, rather than the verbatim labels required.

Fixes 06/08/2026 07:17

1. 4.2 / 4.3 — Protocol labels made verbatim: Replaced the three abbreviated protocol cell labels with the ER’s bold bullet labels — “Wavelength” → “Standard wavelength selection”, “Dose per session” → “Standard dose per session”, “Frequency & course” → “Standard frequency and course length”.