Audit: QRS - Dandelion Root to Treat Cancer

Audit conducted on 28/08/2026 17:00 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.	🟢	Protocol cells trace to ER lines 310–318; time cells to ER line 369; gates to ER lines 257–286; markers to ER table lines 403–409.
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.	🟢	“None to state” mirrors ER “no time to effect to state”; “would shift within days if the bitter action is doing anything” mirrors ER line 413.
1.3	The QRS never strengthens an ER claim (e.g., “not formally studied” → “not required”) or softens one (e.g., “do not use during pregnancy” → “use with caution during pregnancy”).	🟢	Contraindications remain contraindications; the conflicted chemotherapy-combination benefit is balanced by the speculative risk “Weakening of a standard chemotherapy drug”.
1.4	The QRS does not relabel an ER fact under a different decision category. A “Benefit-Modifying Factor” from ER section is not surfaced as a “Caution”; a “Risk-Modifying Factor” is not surfaced as a “Side Effect”; etc.	🟢	Contraindications come from the ER “Populations who should avoid” list; interactions from the ER interaction bullets; no Modifying-Factor content is surfaced as 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 only named body is “Commission E”, present in the ER Protocol bullet for the same dosing fact (ER line 310). No PMIDs, NCTs, or brands.
1.6	The QRS does not introduce new attributions.	🟢	No attribution appears that is absent from the ER.

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.	🟢	Matches the ER’s blunt, null-evidence framing without amplifying or softening it.
2.2	The tone of the QRS is simultaneously expert, accessible, objective, and data-driven, but also empowering and encouraging	🟢	Presents thresholds, ranges, and gates that let a reader act, while remaining faithful to a negative evidence base.
2.3	The QRS reads as a trusted, knowledgeable guide rather than a prescriptive doctor	🟢	Statements are declarative facts, not instructions to a patient.
2.4	The QRS avoids language that implies medical or clinical advice	🟢	No imperatives; gates and markers are stated as conditions and reference values.
2.5	The QRS “presents information” instead of “providing guidance”, “recommending”, or “advising”	🟢	No “recommend”, “advise”, or “should” constructions 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 rendered content.
2.7	The QRS is written in plain language, avoiding unnecessary medical jargon	🟢	Retained technical terms (eGFR, ALT, CBC, Child-Pugh, P-glycoprotein) are load-bearing decision gates carried from the ER; risk and benefit lines use the ER’s plain headings.
2.8	Information is presented in a concise and very compact manner	🟢	Gate items, tier lines, and marker rows are all reduced to the key fact.
2.9	It DOES NOT address the reader directly	🟢	Confirmed; no direct address.
2.10	The target audience is health- and longevity-oriented adults who are risk-aware, proactive, and actively seeking to optimize health or apply the intervention under review.	🟢	Functional biomarker ranges and a monitoring cadence assume a proactive, self-monitoring 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.	🟢	Baseline/2-week/6-week/3-month cadence and annual blood lead testing presuppose that willingness.
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.	🟢	Content density and biomarker specificity are above general-population level.
2.13	Framing, takeaways, and risk/benefit weighting throughout the document reflect this audience, including where an intervention’s signal for the average person differs from its signal for this audience.	🟢	At-A-Glance foregrounds the substitution harm, which is the decision-relevant point for a reader considering the herb against standard care.
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 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.	🟢	Risk and benefit lines reproduce the ER’s own subsection headings verbatim, as item 1.2 requires; no colloquialism is introduced.

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 byte-identical to the template (lines 440, 477, 519, 538, 561, 582, 608, 705); surviving tier labels “Speculative: “, “Medium: “, “Low: “ unmodified; column headers unchanged (lines 612–614).
3.2	All “…” from the [qrs_template] are present in the the QRS.	🟢	All 38 template variable names present; the repeatable marker_#_* and qualitative_item_# spans are expanded to 7 and 6 numbered instances respectively.
3.3	Spans that are not addressed in a checklist item are left unchanged	🟢	website="evidence_review", website="audit", and website="full_review" spans and all CSS, footer, and comment markup are byte-identical to the template.

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 QRS-mapped ER section carries an empty-state phrase; the empty benefit and risk tiers are governed by items 12.5 and 13.5, which mandate display: none instead.
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.	🟢	Protocol cell labels “Traditional decoction”, “Capsule form”, “Integrative add-on approach” are the ER’s bold labels verbatim (ER lines 310, 312, 316); monitoring row labels are the ER table’s biomarker names verbatim.
4.3	Labels are not paraphrased, abbreviated, or invented.	🟢	Time-cell labels “Cancer indication”, “Digestive effects”, “Diuretic effects” are lifted from the ER’s own wording at line 369 rather than invented.
4.4	The QRS DOES NOT use emoji indicators (no 🟩, 🟥, 🟨, etc.). Color and emphasis are conveyed through CSS and bold labels.	🟢	No emoji codepoint occurs in the file; the ER’s “⚠️ Conflicted” marker was correctly 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.	🟢	Every section is condensed rather than extended: four benefit subsections collapse to one line, nine risk subsections to three lines, ten interaction bullets to nine stripped items, and all trailing rationale clauses are removed.

---

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 <!doctype html> on line 1.
5.2	Inside that HTML comment the YAML block is delimited by a line “—” opening and a line “—” closing. Text before the opening “—” is permitted but is not parsed as YAML.	🟢	Opening --- at line 3, closing --- at line 13; the preamble text 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; no metadata value is echoed on the page except the creation date and model name, which are template header variables.
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, because it contains a colon.
5.5	The filename of the source ER is stated as “er_filename: [er_filename]”	🟢	Line 4: er_filename: dandelion_root_cancer_2026-0828-1413_Opus_ER.md, matching the ER’s own filename frontmatter value.
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: 2026-0828-1622, correct format.
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.
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 only, no qualifier.
5.12	The filename of the document is stated as “qrs_filename: [filename of this document]”	🟢	Line 9 matches the file’s actual name 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.	🟢	Confirmed across all nine keys; no stray whitespace or unnecessary quoting.

6. Page Title & Header

#	Description	Result	Comments
6.1	[page_title] is set to the [canonical_topic] of the ER frontmatter followed by “ - Quick Reference Sheet” (e.g., “Intervention - Quick Reference Sheet”). The [canonical_topic] is HTML-entity-encoded as needed (e.g., & for &)	🟢	Line 22: “Dandelion Root to Treat Cancer - 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: “Dandelion Root to Treat Cancer”, matching ER frontmatter canonical_topic.
6.3	[header_subline_date] is set to [qrs_creation_date reformatted as MM/DD/YYYY]	🟢	Line 421: “08/28/2026”, correctly derived from qrs_creation_date: 2026-0828-1622.
6.4	[header_subline_model] is set to [qrs_creator_ai_fullname]	🟢	Line 425: “Opus 5”, matching the frontmatter value.
6.5	No additional header content appears: no badge, version stamp, AKA / alternate names line, source-AI attribution, audit date, or QRS variant marker.	🟢	Header block (lines 415–428) is structurally identical to the template; 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	🟢	Condenses ER lines 440–444 into the three decision-relevant points: what it is, that the evidence is preclinical only, and where the real harm sits.
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.	🟢	“cheap, food-grade herb” and “rests entirely on laboratory dishes and mice” (ER line 440); “no cancer trial of the root is registered anywhere today” (ER line 440); the substitution harm (ER line 442); “digestive bitter” (ER line 37).
7.4	It DOES NOT use acronyms or technical classifications that require specialist knowledge, uses plain-language terms instead	🟢	No acronyms; “laboratory dishes and mice” replaces in-vitro/xenograft, and “the standard treatment people drop” replaces the substitution/refusal construct.
7.5	It DOES NOT cite specific trials (names, years, sample sizes, p-values)	🟢	No trial name, year, NCT, or sample size appears.
7.6	It DOES NOT cite effect sizes, relative risks, or statistical results	🟢	The ER’s HR 2.08 and survival percentages are deliberately absent.

8. Contraindications

#	Description	Result	Comments
8.1	The section is derived from the ER Key Interactions & Contraindications section	🟢	All eight items map to the “Populations who should avoid Dandelion Root” list at ER lines 279–286.
8.2	[stop_items] represent the Contraindications from the ER	🟢	All eight ER contraindications are present, none added.
8.3	Individual [stop_items] are formatted as <li></li>	🟢	Eight <li> elements inside the span (lines 541–556).
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.	🟢	ER’s “, on absent safety data” and the definitional glosses for cholecystitis, ileus, and eGFR are stripped; no dash clauses remain.
8.5	Parenthetical qualifiers from the ER bullet — time windows, severity classes, threshold values, clinical staging — ARE preserved as part of the item, kept as concise as possible (shortened or trimmed where needed to fit the one-page budget, but never dropped entirely).	🟢	“during and for 7 days around each cycle”, “below 30 mL/min/1.73 m²”, “Child-Pugh Class C” all retained; the Asteraceae example list is trimmed from six names to four, not dropped.
8.6	When the ER uses ranking notation inside parens (e.g., “>” for severity ordering) that depends on an explanatory phrase to interpret, normalize the items to a plain comma-separated list rather than carrying through the bare symbol.	N/A	The ER uses no ranking notation inside parentheses in this section.
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 ER names eight such populations, and the section is correspondingly populated.
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 nine items map to the interaction bullets at ER lines 257–275.
9.2	[caution_items] represent the Key Interactions from the ER, excluding any that are already listed as Contraindications	🟢	Nine of the ER’s ten interaction bullets carried; the P-glycoprotein substrate chemotherapy bullet is correctly omitted because it appears as a contraindication.
9.3	Individual [caution_items] are formatted as <li></li>	🟢	Nine <li> elements inside the span (lines 564–572).
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 “Caution. … Mitigation: …” tail is stripped, as is the ER’s em-dash gloss on sulfonylureas.
9.5	Parenthetical qualifiers from the ER bullet — example drug lists, time windows, severity classes, threshold values, clinical staging — ARE preserved as part of the item, kept as concise as possible (shortened or trimmed where needed to fit the one-page budget, but never dropped entirely).	🟢	Named drug lists retained and trimmed rather than dropped (torsemide, sirolimus, naproxen, hibiscus/green tea, chromium/ALA/cinnamon removed; at least two exemplars kept in every case).
9.6	When the ER uses ranking notation inside parens (e.g., “>” for severity ordering) that depends on an explanatory phrase to interpret, normalize the items to a plain comma-separated list rather than carrying through the bare symbol.	N/A	The ER uses no ranking notation inside parentheses in this section.
9.7	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 ER names ten such interactions, and the section is correspondingly populated.
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 the ER Therapeutic Protocol bullets at lines 310–318.
10.2	The three sets of [action] items cover the three most important actionable implementation aspects from the ER Protocol section	🟢	The two dose forms a reader can actually execute (decoction, capsule) plus the framing that determines whether use is safe (integrative add-on versus replacement).
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 Therapeutic Protocol section provides well over three distinct actionable aspects.
10.4	All used [action_#label], [action#value], [action#_sub] items are filled with meaningful content derived from the ER Protocol section.	🟢	All nine sub-variables carry substantive ER-derived content; no placeholder 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	🟢	Cancer indication, digestive effects, and diuretic effects — the only three the ER distinguishes (line 369).
11.2	The sets are picked and ordered by the magnitude of the related benefit	🟢	The cancer indication, the topic of the review and the only aspect with a benefit tier in the ER, leads; the two non-cancer effects follow.
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 distinguishes three time-to-effect aspects, so 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 sub-variables populated from ER lines 369 and 413–414; no placeholder remains.
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 line 369, so the section is correctly retained.

12. Benefits

#	Description	Result	Comments
12.1	The section is derived from the ER Expected Benefits section	🟢	The four listed items are the ER’s four Speculative 🟨 subsection headings (ER lines 153–167).
12.2	Key variables are [benefits_high], [benefits_medium], [benefits_low], [benefits_speculative]	🟢	All four spans present (lines 521–531).
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.	🟢	The ER’s “>90% xenograft reduction”, taxol/mitoxantrone naming, and caspase-8 mechanism are all omitted; only the four headline claims remain.
12.4	Parenthetical content — including effect sizes, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parenthetical survives; the ER’s “⚠️ Conflicted” marker is also correctly removed.
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.	🟢	ER states no benefit reaches High or Medium and leaves Low empty; the three corresponding spans carry style="display: none" with no empty-state text.

13. Risks

#	Description	Result	Comments
13.1	The section is derived from the ER Potential Risks & Side Effects section	🟢	All eight listed risks are ER subsection headings from lines 193–239, tier for tier.
13.2	Key variables are [risks_high], [risks_medium], [risks_low], [risks_speculative]	🟢	All four spans present (lines 584–602).
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.	🟢	The ER’s HR 2.08, the 8.5%/6,497 skin-prick figures, and the Clare 2009 and Johnson 2018 attributions are all omitted.
13.4	Parenthetical content — including frequencies, severity grades, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parenthetical content survives in any of the three populated tiers.
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.	🟢	ER states no risk reaches High; risks_high carries style="display: none" with no empty-state text.

14. Monitoring

#	Description	Result	Comments
14.1	The section is derived from the ER Monitoring section	🟢	All rows and the cadence trace to the ER Monitoring Protocol & Defining Success section (lines 399–409).
14.2	All measurable/quantifiable biomarkers from the Monitoring section are listed	🟢	All seven ER table rows present: potassium, sodium, eGFR, fasting glucose, ALT, CBC, blood lead; targets and rationales carried verbatim or losslessly condensed.
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 699 captures the baseline/2-week/6-week/3-month schedule, the illness-triggered potassium recheck (ER line 399), and annual blood lead (ER line 409).

15. Qualitative Assessment

#	Description	Result	Comments
15.1	The section is derived from the ER Monitoring section	🟢	All six items come from the qualitative-marker list at ER lines 413–418.
15.2	All subjective/qualitative biomarkers from the Monitoring section are listed	🟢	All six present: appetite and post-meal comfort, night-time urination, lightheadedness on standing, skin and mouth symptoms, energy and exercise tolerance, stool frequency and consistency.

Issues 28/08/2026 17:00

Pass rate 100.00%. No issues found.

Issues 28/08/2026 16:50

1. 4.5 — Sheet overflows one A4 page: Protocol and Time-to-Effect sub cells carry two-clause sentences of 110-135 characters that wrap to 3-4 lines inside a ~230 px column (lines 450, 461, 472, 500), and four Key Interactions items carry five-name parenthetical example lists (lines 578-588) that push that gate alone to roughly 18 wrapped lines; these regions were not condensed to the per-section budget, so the sheet runs past one A4 page.

Fixes 28/08/2026 16:50

1. 4.5 — Protocol sub-cells condensed: Trimmed action_1_sub, action_2_sub and action_3_sub to single compact clauses (“Simmered in 150 mL water for 10–15 minutes. Commission E: 3–4 g twice daily.”; “Tincture 1:5 in 30% alcohol”; “Replacement use carries the mortality signal.”), removing the em-dash aside and roughly a line from each cell.
2. 4.5 — Time-to-effect sub-cells condensed: Reduced time_2_sub from a two-clause 133-character sentence to “Appetite and post-meal comfort would shift within days if the bitter action is doing anything.” and time_3_sub to “Increased urine flow from the first dose.”, dropping the duplicated “within hours of the first dose” already carried by the value cells.
3. 4.5 — Key Interactions gate shortened: Trimmed the parenthetical example lists to two or three names each (diuretics, CYP3A4 substrates, diuretic supplements, glucose-lowering supplements) while keeping every ER item and its qualifier, cutting the gate from roughly 18 wrapped lines to about 12.
4. 4.5 — Monitoring cadence and targets condensed: Shortened monitoring_cadence from 220 to 137 characters with all cadence points retained, and tightened marker_6_target to “Stable against own baseline” and marker_7_target to “Change from own baseline, below 3.5 µg/dL”.

Issues 28/08/2026 16:39

1. 8.4 — Added drug list in contraindication: The fourth [stop_items] entry (QRS lines 547-551) carries “(doxorubicin, paclitaxel, imatinib, docetaxel)”, an elaboration absent from the ER’s contraindication bullet at ER line 282.

Fixes 28/08/2026 16:39

1. 8.4 — Added drug list in contraindication: Removed the “(doxorubicin, paclitaxel, imatinib, docetaxel)” parenthetical from the fourth [stop_items] entry, restoring the ER’s own contraindication wording “Active chemotherapy with a P-glycoprotein substrate, during and for 7 days around each cycle”.

Issues 28/08/2026 16:34

1. 1.2 — ER hedge dropped from time cell: [time_2_sub] at QRS line 500 reads “appetite and post-meal comfort would improve within days”, dropping the ER’s epistemic hedge at line 413, “which the bitter action would improve within days if it is doing anything”.

Fixes 28/08/2026 16:34

1. 1.2 — ER hedge restored in time cell: [time_2_sub] now reads “…appetite and post-meal comfort would improve within days if the bitter action is doing anything”, restoring the ER’s epistemic hedge from line 413.

Issues 28/08/2026 16:28

1. 12.3 / 12.4 — Parenthetical qualifier retained in Benefits: Line 528 keeps “(conflicted)” after “added effect alongside chemotherapy drugs”, but section 12 requires qualifiers and parenthetical content to be stripped because the Speculative tier already encodes evidence strength.

Fixes 28/08/2026 16:28

1. 12.3 / 12.4 — Parenthetical qualifier stripped from Benefits: Removed “(conflicted)” from the Speculative benefits item, changing “added effect alongside chemotherapy drugs (conflicted)” to “added effect alongside chemotherapy drugs”.