Adversarial registry: work log

Append-only and chronological. Each entry gives what was done, why, any surprises, and what comes next.

2026-09-30: planning

Wrote summary.md, plan.md, direction-questions.md and both todo files from the field survey (../../notes/ai-consciousness-field.md) and ../../research-directions.md section 2. Next: see todo-agent.md.

2026-09-30: protocol and template drafted

Drafted protocol.md (eligibility, roles, sequence, measurement rules, publication, disputes) and entry-template.md. Both still need the Tree G checklist pass and an outside reader before any camp sees them. Next: first-pairing proposal, one page; approach emails in outreach/.

2026-10-30: first pairing corrected, proposal and emails drafted

Reading both camps' papers before writing the proposal showed the 2026-09-30 pairing was wrong. Berg, de Lucena, Rosenblatt (arXiv 2510.24797) study experience reports under self-referential prompting, mostly on GPT, Claude and Gemini; they make no claim about naming injected concepts. The open-weight claim that Lederman and Mahowald dispute is Pearson-Vogel, Vanek, Douglas, Kulveit (arXiv 2602.20031): with the injection removed before the question, Qwen2.5-Coder-32B-Instruct yields up to 1.36 bits about which of nine concepts was injected, read by logit lens at layer 62. Lederman and Mahowald (section 6.3) reply that the steering effects "may persist without being meta-cognitively recognized". Neither paper asks a non-introspective question over the same cache, so that comparison is the measurement: ΔMI, introspective minus non-introspective. Lindsey's own paper does not commit on whether naming and detecting share a mechanism, so he is asked to comment, not to take a side.

Wrote first-pairing.md (R-2026-003, executor-default thresholds 0.2 and 0.05 bits, to be replaced by the camps), the four approach emails, and entries.md with Tree A entered retroactively as R-2026-001 and R-2026-002, labelled as not meeting the protocol. Corrected plan.md and summary.md; Berg moved to the fallback list. Signatory: Elara Faro.

While checking sources, Martorell and Bianchi (arXiv 2603.18893), cited in our notes as showing self-reports track probe states, turned out to have reversed that finding in v3 ("Don't Ask"). Notes corrected. Next: protocol review against Tree G's checklist; operator sends the emails.

2026-10-30: protocol draft 2

Reviewed protocol.md against Tree G's new checklist. Rows 2, 5, 7, 9 and 10 were already covered. Added rows 1 (task family and counting), 3 (vary implementation choices), 4 (simplest-mechanism baseline) and 8 (medians and spread) to section 4, and a Checklist field to the entry template. Rows 6 and 11 to 13 are answered per entry, since they apply only to some claims. Next: checklist answers for R-2026-003; operator sends the emails.