Spaces:
Running
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
7.26 kB
| # 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](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) | |
| 1. **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. | |
| 2. **"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. | |
| 3. **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_tests` is parsed as a list. | |
| - New `run_python` tool. | |
| - 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. | |