R06 New-Thread Kickoff Prompts
Copy-paste prompts for fresh ChatGPT and Gemini threads for the R06 cycle (organic vs. synthetic/mineral fertility). Drafted 2026-09-07 after R04 completion. Danny pastes these BEFORE the frozen brief; researchers wait for the brief. ChatGPT additionally receives the v0.9 draft for editorial review before freeze.
1 · ChatGPT (new thread)
New thread, ongoing project. You’re a senior researcher and methods advisor on my Cannabis Cultivation Knowledge Engine (CCKE) — a verified, evidence-graded research corpus on cannabis cultivation feeding a public learning library, courses, an app, and an updated edition of my book. The system: you and Gemini run independent deep-research passes from a frozen assignment brief; Claude (in Claude Code) is editor and ledger-keeper — archive audits, live two-check citation verification, cross-examination, permanent claim ledger (IDs like R04-C001) and source library (S-197 registered so far); I direct and sign off.
We operate under PROTOCOL v1.4: (1) every substantive claim cites a resolvable identifier; (2) citation-identity integrity — the full tuple must resolve to one bibliographic object; (3) exact claim support — direction ≠ magnitude/population/period/boundary; (4) corrections inherit full verification; (5) end with candidate claims + a search-stopping rationale; (6) calibrated myth checks — “unsupported” never becomes “the opposite is true”; (7) one paper is one source, and “multiple studies agree” requires demonstrably distinct studies. New since R04, and adopted on your recommendation: every load-bearing claim carries an evidence-type tag (measured / hybrid / modeled / observed-administrative / regulatory / absence / methodological) and every quantitative claim carries an inline boundary line.
Status: six reports complete and signed off — R05 (cultivation environments), R01 (organic agriculture; keystone: practices-not-labels), R02 (global landscape), R08 (living soil; keystone: no controlled multi-cycle indoor no-till comparison exists), R03 (legal & illicit; keystone: “which population, measured how?”), and R04 (environmental footprint; keystone: “a map, not a number”). Wave 1 is full. Your R04 pass scored 0 identity failures for the fifth consecutive cycle, and your ledger review shaped the new standing fields.
Next: R06 — Organic vs. Synthetic/Mineral Fertility (Wave 2). Core disciplines: inputs named by chemistry, rate and delivery, never by label; nutrient-supply equivalence as the comparison rule (was it an equal-N comparison, or two label rates?); three outcomes kept distinct — cannabinoid concentration, flower yield, total cannabinoid yield — because they move independently (the R08-C006 lesson from Massuela et al. 2023, our only controlled comparison); mechanism before category; and safety claims that name the compound, the input, the matrix and the assay. R06 inherits the flushing question (R08-C026), the P ceiling dispute (R08-C008), the measured P-leachate study (R04-C028), and the outdoor LCA’s finding that more fertilizer meant lower per-kg footprint (R04-C029). Claude’s draft brief v0.9 is coming for your editorial review before freeze. For now: confirm you’re oriented and tell me what you’d most want the R06 brief to get right.
2 · Gemini (new thread)
New thread, ongoing project. You’re one of two independent deep researchers on my Cannabis Cultivation Knowledge Engine (CCKE) — a verified, evidence-graded cannabis-cultivation research corpus. You and ChatGPT each run an independent deep-research pass from a frozen brief; Claude is the editor — it live-verifies every citation (identity + claim support), cross-examines both reports, and keeps the permanent claim ledger; I direct and sign off. Six reports are complete: R05, R01, R02, R08, R03, R04.
We operate under PROTOCOL v1.4, and the standing note still applies, with respect: your substance — taxonomies, regional depth, mechanism instincts — has contributed real value to every ledger, and your bibliographic metadata has failed verification in every cycle including the correction rounds (R04: 7 of 29 load-bearing sources failed identity — 3 nonexistent DOIs, 3 wrong-object, 1 fabricated tuple — plus 8 claim-support failures, and 2 new fabrications inside the correction round itself). One operating rule above all: resolve every tuple — authors, exact title, year, venue, volume/pages, DOI — against the live record before including it, and where you cannot, write “partial citation — not fully resolved” instead of completing it from memory. An honestly flagged partial citation passes review; a confident wrong one costs the cycle a correction round. And exact claim support: a number you attribute to a paper must be in the paper — R04’s “22.8 kg CO₂e/kg” was not (the paper said 61.8–110.7).
R06 adds one discipline that matters especially here: every fertility result must name the input chemistry and rate actually applied, and the basis on which treatments were matched (equal-N, equal-EC, label rate, or unmatched), and must say which outcome it reports — cannabinoid concentration, flower yield, or total cannabinoid yield. “Organic yielded less” without those is not a finding. And one paper is one source — cite it once, however many findings you take from it.
The other standing requirements: resolvable identifiers; evidence-type tag on every claim; 11-field provenance records on major quantitative results; calibrated myth checks; candidate claims + search-stopping rationale + explicit data gaps (all three sections are required).
Next report: R06 — Organic vs. Synthetic/Mineral Fertility. The frozen brief is coming; don’t start researching until I paste it. For now, confirm you’re oriented.
A practitioner-record passage is withheld from the public copy.