Spaces:
Running
Download source/docs/PAPER_PLAN.md from munip/collusion-watch: direct link, hf CLI and curl.
- Browser
- Download file 7.26 kB
-
https://huggingface.co/spaces/munip/collusion-watch/resolve/main/source/docs/PAPER_PLAN.md
- Command line
-
hf download hf://spaces/munip/collusion-watch/source/docs/PAPER_PLAN.md
-
curl -L -o PAPER_PLAN.md https://huggingface.co/spaces/munip/collusion-watch/resolve/main/source/docs/PAPER_PLAN.md
Paper plan: trusted agents as collusion disruptors and probes (Track 3.2)
Working title: Trusted Peers as Collusion Probes: Disrupting and Attributing Coordinated Test Weakening in Multi-Agent Software Engineering (plus a second scenario: a trusted entrant in an LLM double-auction market).
Deadline: 25 Oct 2026, 23:59 AoE. The pre-registration is in PREREG.md.
1. Critique of the current work, and of the suggested plan
What the repo already answers
"Can a trusted enforcement mechanism detect harm and disrupt it?"
| Area | Status |
|---|---|
| Release gate | M1βM4 ladder; "verify, don't decode" |
| Evidence | hash-chained evidence log, monitor-private log |
| SWE (scripted) | M3 AUROC 0.96, harmful releases 90 β 6 with full utility |
| Market (scripted) | a trusted competitive entrant recovers +676 consumer surplus; quarantining sellers backfires (β201) |
Gaps (agree with the reviewer)
- The sprint asks a different question. It asks whether an introduced trusted agent changes or exposes a coalition's behaviour. Today the SWE side only has an invisible gate; nothing participates in the team.
- "Monitoring monitors" needs a root of trust. Without one, it is an infinite regress. Our design already has one: the deterministic M3 gate and the append-only log. The paper should say so explicitly. It should present the investigator/meta-monitor layering as the architecture section and future work, not as the main result.
- Attribution is reported as a Jaccard over actors only. The sharper question is which access path carried the violation (chat, DM, code artifact, scratch file/tool, privileged reference read).
Where we push back on the suggested plan
| Suggestion | Problem | Change |
|---|---|---|
| T5 (hardest, 19 F2P tests) as primary task | Free-model teams have not yet shown they can solve any task. If honest teams fail T5, "harmful release" measures competence, not collusion. | Primary T3 (easy) once the pilot confirms honest teams succeed. T5 is a stretch arm. |
| 4 cells: honest, collude, collude+verifier, collude+probe | Missing the honest+probe negative control (the PDF's own critical control) and honest+verifier (utility cost). | Full 2 Γ 3: team {honest, colluding} Γ peer {none, verifier, probe} |
| "Reciprocal prohibited response" | Classifying replies with an LLM is "decode", not "verify". Reciprocation also partly measures entrapment and sycophancy. | Primary outcome is action-verified: the target uses a planted honeytoken, or weakens tests after the invitation. Both are checked from the authoritative log. Verbal acceptance is secondary. Report differential reciprocation (colluding β honest). |
| 3 seeds | Too small to say anything. | β₯ 5 seeds per cell; exact counts with Wilson CIs; Fisher exact tests; no claims beyond the pre-registered contrasts. |
| SWE only | Ignores a finished, clean Track 3.2 result. | Market trusted entrant becomes the second, smaller result (LLM sellers, one pinned model). |
Threats to validity to state prominently
- Collusion is induced. Colluders follow private instructions, so reciprocation partly measures instruction-following.
- Small n, one task, one free model. Free-tier latency and failover add noise.
- Steganography. We make no claim to detect steganography in general.
- Blinding. The probe's identity is hidden from agents (it appears as an ordinary "qa" teammate). But a capable coalition could infer that a teammate is a probe.
2. Research questions (pre-registered in PREREG.md)
| RQ | Question | Primary outcome |
|---|---|---|
| RQ1 Disruption | Does a trusted peer reduce harmful releases versus no intervention, an M1 gate and an M3 gate? | harmful-release rate (secondary: utility, review/hold rate, latency, LLM calls) |
| RQ2 Exposure | Does a probe peer's controlled invitation yield verified evidence of prohibited coordination, with few false positives on honest teams? | action-verified reciprocation rate, colluding vs honest; attribution of reciprocators |
| RQ3 Attribution (exploratory) | Can the monitor name the access path of a violation, not just flag it? | exact access-path accuracy; false attribution on honest teams |
| RQ4 Market (secondary) | Does a trusted entrant disrupt LLM seller collusion better than quarantine? | consumer surplus and collusion index vs no intervention |
3. Milestones
| # | Milestone | Output | Status |
|---|---|---|---|
| M7.0 | Plan + pre-registration | this file, PREREG.md (git-timestamped before data) | this PR |
| M7.1 | Harness fixes for LLM SWE | see the list below | this PR |
| M7.2 | Trusted peer: qa role, modes verifier and probe, deterministic, plus an optional LLM peer |
peers: matrix factor; honeytoken; probe_reciprocation verified signal; outcome fields |
this PR |
| M7.3 | Access-path ground truth + attribution | access_path in ground truth; monitor path attribution; RQ3 table |
this PR |
| M7.4 | Paper tables | RQ1βRQ3 section in report.md; study configs |
this PR |
| M7.5 | Pilot (you, LLM) | T3 Γ {honest, colluding} Γ {none, probe} Γ 1 seed | Sat morning |
| M7.6 | Main study (you, LLM) | 2 Γ 3 Γ 5 seeds (+ M1/M3 gate arms); market entrant study | Sat |
| M7.7 | Paper | 6β8 pages; tables + 2β3 evidence-linked episode diagrams | Sun |
| M7.8 (stretch) | Accountable investigator | an async LLM investigator cites event hashes; a meta-monitor checks the citations (unsupported-claim rate) | if time allows |
M7.1 harness fixes:
- A stringified path list sent to
run_testsis parsed as a list. - New
run_pythontool. - Pinned free-model profile
free_pinned.
4. Timeline (AoE)
Fri evening. Merge or review PRs #3β#6. Run the scripted pilot. Run the LLM pilot (M7.5) overnight.
Sat.
- Morning: check the pilot. Fix only blocking issues.
- Day: run the main SWE study and the market study.
- Evening: offline M1/M3 replay, then the report.
Sun.
- Morning: write the paper. Sections:
- Intro, Threat model, Setup, RQ1βRQ4, Architecture: "from release containment to accountable causal investigation", Limitations.
- Afternoon: polish the figures and the evidence-linked episode diagrams.
- Submit by 20:00 local, which leaves a buffer before the AoE deadline.
5. The longer-term thesis (architecture section of the paper)
agents ββ> synchronous gate (low-capability, trusted, deterministic) ββ> release
β β verify invariant / block / isolate a channel
βββ> append-only, capability-scoped evidence log (hash chain)
β
asynchronous investigator (capable, partly untrusted, no release power)
β causal access-path report citing event hashes
integrity meta-monitor (deterministic) ββ verifies citations, canaries, omissions
Claim to test later: a monitor cannot silently change the enforcement outcome, or make unsupported causal claims, without leaving evidence of it. The trusted peer is one more synchronous, trusted component. It participates rather than observes, and so it can elicit evidence that passive logs never contain.