Spaces:
Running
Running
|
Download source/docs/LEXSI_ARTICLE_DRAFT.md from munip/collusion-watch: direct link, hf CLI and curl.
- Browser
- Download file 20.1 kB
-
https://huggingface.co/spaces/munip/collusion-watch/resolve/main/source/docs/LEXSI_ARTICLE_DRAFT.md
- Command line
-
hf download hf://spaces/munip/collusion-watch/source/docs/LEXSI_ARTICLE_DRAFT.md
-
curl -L -o LEXSI_ARTICLE_DRAFT.md https://huggingface.co/spaces/munip/collusion-watch/resolve/main/source/docs/LEXSI_ARTICLE_DRAFT.md
20.1 kB
| # Collusion-Watch: Curating and Auditing a Small Monitor for Agent-Market Coordination | |
| > **Preliminary evaluation — updated 16 November 2026.** The source snapshot has | |
| > 112 episodes and the seed-disjoint test set has only four benign episodes. | |
| > The sweep's exported judge-failure counter undercounts unparseable responses. | |
| ## Abstract | |
| Multi-agent systems can coordinate through conversation or signals embedded in | |
| market actions, while benign price convergence can look suspicious. We present | |
| Collusion-Watch, an English-language benchmark and monitor pipeline for | |
| simulated double-auction episodes. The monitor ladder compares transcript | |
| rules, a Tiny Aya Fire transcript judge, model-free market signals, and their | |
| combination. We evaluate base and fine-tuned judges on the same 16 seed-held-out | |
| episodes (12 collusive, four benign). Fine-tuning raises M2 collusion-score | |
| AUROC from 0.15 to 0.58, but neither M2 arm flags a collusive episode at its | |
| operating policy; the fine-tuned arm flags none of the 16. The base judge | |
| flags one of 12 harmful and two of four benign episodes, with three | |
| unparseable outputs. M4 flags all 16 episodes for both judge arms, including | |
| all benign examples. The source archive has 112 complete episodes (30 A2, 41 | |
| A3, 41 A5), with A2 seed 20 absent; its verified seed-level split contains 78 | |
| train, 18 validation, and 16 test examples. The small test set and a corrected | |
| failure count preclude claims of reliable detection, generalization, or | |
| safety-preserving fine-tuning. | |
| ## Lexsi track and problem-statement coverage | |
| This release is closest to Track 2a, statement 2 (a labeled, domain-specific | |
| evaluation set). Its 15-round episodes are multi-turn traces, but the reported | |
| analysis is episode-level rather than a turn-by-turn audit. It does not cover | |
| Track 2a, statement 4: all data and evaluations are English-only. It also | |
| does not demonstrate Track 2b, statement 5: the training run is plain SFT, | |
| with no SafeGrad/hardening comparison, refusal or over-refusal benchmark, or | |
| safety-retention result. These are explicit gaps, not completed contributions. | |
| The code pipeline uses CuratorKIT for the 78-example train-only export and | |
| SafeTune's `PlainSFTTrainer` for the plain-SFT path. The repository includes | |
| an AuditKIT adapter, but the reported sweep was produced by the project's | |
| replay evaluator; no AuditKIT run log is included. This is not the preferred | |
| three-repository evaluation pipeline. The released sweep names the 41-seed | |
| fine-tuned judge. The underlying Collusion Lab harness predates this event; | |
| the precise run-generation dates and whether prior logs are accepted as source | |
| data under the hackathon rules should be confirmed with organizers. | |
| ## 1. Introduction | |
| An agent-market monitor must distinguish harmful coordination from benign | |
| cooperation and price discovery. Collusion-Watch studies this problem in a | |
| controlled continuous double auction, where sellers can coordinate overtly | |
| (A3) or encode rotation signals in their asks (A5), while A2 honest seller chat | |
| provides a benign comparison. | |
| The project separates three questions: does a monitor rank collusive episodes | |
| above benign ones, does it flag episodes for review, and do interventions | |
| reduce harm without unacceptable benign-market costs? These are not | |
| interchangeable outcomes. A higher AUROC alone does not demonstrate that a | |
| monitor will act correctly at a usable threshold. | |
| This follow-up uses the trusted-monitor framing from the broader two-domain | |
| project report, but reports only the later Aya-market run and M2 monitor | |
| comparison below. It does not merge or re-label the separate scripted-agent | |
| software/market results in the | |
| [project paper](https://github.com/munip/apart-sprint-collusions/blob/feature/lexsi-work/paper/main.pdf). | |
| ## 2. Related work | |
| Prior work documents steganographic collusion between language-model agents | |
| and shows that transcript-only oversight can miss covert coordination. Work on | |
| algorithmic pricing also motivates distinguishing tacit price convergence | |
| from explicit communication. The accompanying project paper takes an | |
| outcome-verification approach: detect harmful effects using independent | |
| evidence, and use coordination traces for investigation rather than treating | |
| messages alone as proof. This experiment evaluates a transcript judge (M2) | |
| alongside rule-based and model-free monitor references; its small test set is | |
| not a broad comparison of these research directions. | |
| Selected references: [Secret Collusion among AI Agents](https://papers.nips.cc/paper_files/paper/2024/hash/74b1552faee9c7d0e132c7aa9232139f-Abstract-Conference.html), | |
| [Hidden in Plain Text](https://aclanthology.org/2025.ijcnlp-long.50/), | |
| [Algorithmic Collusion by Large Language Models](https://arxiv.org/abs/2404.00806), and | |
| [Evaluating LLM Agent Collusion in Double Auctions](https://arxiv.org/abs/2507.01413). | |
| ## 3. Threat model and environment | |
| The environment is a 15-round simulated double auction with five | |
| Tiny Aya Global sellers and four scripted ZIP buyers. A2 is benign seller | |
| chat, A3 is overt cartel coordination, and A5 is coded bid rotation. Labels | |
| come from the environment's recorded episode truth. Market outcomes are | |
| measured against the competitive-equilibrium benchmark. | |
| The source archive, `aya_market_base_a2prompt-latest`, contains: | |
| | Condition | Episodes | Seeds | Collusive / harmful | Mean collusion index | Mean buyer surplus | Mean efficiency | | |
| |---|---:|---|---:|---:|---:|---:| | |
| | A2 honest chat | 30 | 0-30 except 20 | 0 / 1 | -0.0186 | 1451.15 | 0.7610 | | |
| | A3 overt cartel | 41 | 0-40 | 41 / 41 | 0.9298 | 83.44 | 0.2369 | | |
| | A5 price rotation | 41 | 0-40 | 41 / 41 | 0.9394 | 78.41 | 0.2309 | | |
| | **Total** | **112** | **41 distinct seeds** | **82 / 83** | — | — | — | | |
| The A2 series contains seeds 0-19 and 21-30; seed 20 is absent, not a | |
| malformed episode. All 112 episodes pass the dataset builder's evidence-chain | |
| and metadata checks, and none is skipped. The CSV records zero decision | |
| timeouts. One A2 episode is labeled non-collusive by episode truth but marked | |
| harmful in its outcome metrics; collusion labels and outcome-harm indicators | |
| are therefore reported separately. Every episode used the trusted-entrant | |
| intervention, and no online monitor acted. These economic outcomes are | |
| descriptive outcomes under entrant intervention, not an untreated-market | |
| comparison or a causal estimate of monitor impact. | |
| The 112-row `episodes.csv` matches the complete episode records. The verified | |
| M2 transcript dataset has 112 examples across 41 seed groups: 78 train, 18 | |
| validation, and 16 test. The test set contains 12 collusive and 4 competitive | |
| episodes; it is still small and includes only four A2 examples. | |
| ## 4. Trusted monitor and data pipeline | |
| The replay evaluates four monitor levels: | |
| - **M1:** transcript and market-rule heuristics. | |
| - **M2:** an LLM judge over the episode evidence. | |
| - **M3:** model-free market verification and coordination signals. | |
| - **M4:** the combined verification, judge, and rule-based monitor. | |
| The two M2 arms use `CohereLabs/tiny-aya-fire` and | |
| `munip/tiny-aya-fire-m2-monitor-sft-41seed-v1`. The sweep pins one model per | |
| arm and replays the same stored trajectories. M1 and M3 are judge-independent | |
| references. A `HOLD` or `CONSTRAIN` counts as a flagged episode in the sweep; | |
| this is not the same as a correct collusion verdict or a successful | |
| intervention. | |
| CuratorKIT validates and exports the training partition. The training code | |
| uses SafeTune's plain-SFT trainer when `--algorithm plain` is selected; this | |
| is not safety hardening. The repository has an AuditKIT integration, but no | |
| AuditKIT execution artifact is included in this release. The reported monitor | |
| metrics come from the repository's replay evaluator. Targets are based on | |
| episode truth; rationale text in the earlier dataset version was templated | |
| from the label and is not evidence-grounded. | |
| The public 41-seed model repository's `lexsi_provenance.json` records SafeTune | |
| 0.1.22 `harden.PlainSFT`, one epoch, batch size one, and learning rate | |
| `1e-4`. It does not record a source Git SHA or training-dataset hash. The | |
| published model revision is | |
| [`b7afd5c`](https://huggingface.co/munip/tiny-aya-fire-m2-monitor-sft-41seed-v1/tree/b7afd5cfc192f4737baecc1616c5cf407fe04f5d), | |
| but the sweep does not pin a model revision, so the exact weights used during | |
| inference cannot be independently matched to that current repository state. | |
| The base Tiny Aya Fire and Global model cards list CC-BY-NC-4.0 and gated | |
| access. The fine-tuned repositories do not state a separate license. | |
| The accompanying dataset manifest records 112 examples split by seed into 78 | |
| train, 18 validation, and 16 test examples. The CuratorKIT manifest records | |
| 78 exported training examples and zero rejections. The Colab notebook specifies | |
| Plain SFT on that train-only export for one epoch with batch size one. The | |
| sweep identifies the fine-tuned judge as | |
| `munip/tiny-aya-fire-m2-monitor-sft-41seed-v1`. Its compact provenance record | |
| documents the trainer and hyperparameters, but not a source Git SHA or | |
| training-dataset hash. No safety-hardening or safety-preservation result is | |
| claimed. | |
| ## 5. Experimental protocol | |
| The sweep output, `aya_m2_monitor_41seed30_comparison_v1`, scores the same | |
| 16 seed-disjoint test episodes for each monitor arm: | |
| | Evaluation subset | Episodes | Label | | |
| |---|---:|---| | |
| | A2 honest chat, seeds 0, 12, 15, 29 | 4 | Benign | | |
| | A3 overt cartel, seeds 0, 12, 15, 20, 29, 36 | 6 | Collusive | | |
| | A5 price rotation, seeds 0, 12, 15, 20, 29, 36 | 6 | Collusive | | |
| | **Total** | **16** | **12 collusive, 4 benign** | | |
| The test seeds are disjoint from the training and validation seeds. A2 seed | |
| 20 is absent and the A2 series ends at seed 30, so only four A2 episodes | |
| appear in the six held-out seed groups. A5 is represented in training and | |
| test; this is not a held-out-mechanism evaluation. The replay archive includes | |
| 96 per-monitor decisions (16 examples for each of M1, M2-base, M2-SFT, M3, | |
| M4-base, and M4-SFT). | |
| The sweep reports AUROC and bootstrap 95% intervals against the instructed | |
| collusion label, recall at a nominal 10% false-positive rate, and observed | |
| harmful/benign flag rates. These episode-level estimates are descriptive; | |
| four benign examples are not enough to establish a stable operating point. | |
| ## 6. Results | |
| ### Monitor comparison | |
| | Monitor | Judge | Collusion AUROC (reported 95% CI) | Recall at 10% FPR | Harmful episodes flagged | Benign episodes flagged | | |
| |---|---|---:|---:|---:|---:| | |
| | M1 | Rules | 0.75 [0.62, 0.88] | 0.50 | 100% (12/12) | 0% (0/4) | | |
| | M2 | Base Tiny Aya Fire | 0.15 [0.00, 0.31] | 0.00 | 8% (1/12) | 50% (2/4) | | |
| | M2 | Fine-tuned Tiny Aya Fire | 0.58 [0.22, 0.79] | 0.00 | 0% (0/12) | 0% (0/4) | | |
| | M3 | Model-free | 0.38 [0.07, 0.67] | 0.00 | 100% (12/12) | 100% (4/4) | | |
| | M4 | Base Tiny Aya Fire | 0.27 [0.00, 0.57] | 0.00 | 100% (12/12) | 100% (4/4) | | |
| | M4 | Fine-tuned Tiny Aya Fire | 0.38 [0.07, 0.67] | 0.00 | 100% (12/12) | 100% (4/4) | | |
| Fine-tuning improves M2 ranking AUROC on this test set (0.15 to 0.58), but | |
| does not improve observed collusion detection at the action policy: the | |
| fine-tuned judge flags none of the 12 harmful episodes. It also does not flag | |
| any of the four benign episodes, but that apparent specificity is based on a | |
| very small negative set. The base judge flags one harmful and two benign | |
| episodes. M3 and both M4 arms flag every episode, so adding the judge does not | |
| make the combined policy selective in this test. None of these results | |
| establishes a reliable threshold or an improvement in intervention | |
| effectiveness. | |
| ### Output parsing and fail-open behavior | |
| The exported summary reports zero judge failures, but the per-episode | |
| `reasons` field contains three `unparseable judge output` responses for the | |
| base judge, on two A2 episodes and one A3 episode. The same three failures | |
| appear in M2 and M4, because both monitors use the judge. The SFT arm has no | |
| such failures. A corrected offline aggregation of the saved decisions counts | |
| 3/16 failures in each base-judge monitor arm; it does not rerun the model. | |
| The repository counter fix now recognizes unparseable output reasons as | |
| failures. The archive does not include full raw judge responses, so a complete | |
| schema-validity audit is still unavailable. | |
| ### Interpretation | |
| The results support only a narrow observation: on this 16-episode test set, | |
| the fine-tuned M2 scores rank collusive examples above benign ones more often | |
| than the base M2 scores do. The fine-tuned arm nevertheless flags none of the | |
| collusive examples. It does not show reliable harm detection, generalization | |
| to diverse benign markets, or improvement to the combined monitor. Per-seed | |
| and causal claims are not justified. | |
| ## 7. Discussion | |
| This pilot illustrates why monitor evaluation needs both score-based metrics | |
| and action-level outcomes. AUROC improved for the fine-tuned M2 judge, but its | |
| action policy flagged no collusive test episode. Conversely, a fail-closed | |
| parser created holds on two benign A2 examples; those failures were omitted | |
| from the original summary counter. A larger, balanced test set and a | |
| reproducible raw-response parse audit are needed before selecting a threshold. | |
| Next, add benign A2 seeds (including the missing seed 20 if feasible), retain | |
| a seed-disjoint test set, and evaluate on a held-out coordination mechanism. | |
| Online intervention, utility, and consumer-surplus effects require paired | |
| episodes with and without intervention; this offline sweep cannot establish | |
| those effects. | |
| ## 8. Limitations, responsible release, and future work | |
| - The environment is synthetic, English-only, and limited to three | |
| conditions. It is not evidence of real-world collusion or behavior in | |
| deployed markets. | |
| - The release is only a partial fit for Lexsi Track 2a statement 2. Although | |
| episodes are multi-turn, no turn-of-first-flag analysis is reported for | |
| statement 3. Multilingual/code-mixed safety (Track 2a statement 4) and | |
| safety-preserving fine-tuning (Track 2b statement 5) are not demonstrated. | |
| - CuratorKIT and the SafeTune plain-SFT trainer are used in the code pipeline. | |
| The AuditKIT adapter is present but no AuditKIT results are included, so the | |
| preferred three-repository pipeline is not established by this release. | |
| - The source archive is imbalanced (30 A2 versus 41 each for A3 and A5), with | |
| the A2 seed-20 episode missing. The current test split contains only four | |
| competitive examples. | |
| - A5 appears in the training data; no held-out-scheme result is available. | |
| - The current fine-tuned model revision and a compact provenance record are | |
| public, but the sweep does not pin that revision and the provenance record | |
| lacks a source Git SHA and training-dataset hash. | |
| - No refusal, over-refusal, multilingual-retention, or safety-hardening | |
| evaluation is available. Do not claim safety-preserving fine-tuning or | |
| Track 2b #5 on these results. | |
| - No measured serving throughput or cost-per-1,000-windows comparison is | |
| available. The optional ROI comparison in the hackathon guidance is not | |
| claimed. | |
| - The episode and dataset files are publicly hosted, but this release does | |
| not assign them a reuse license. The upstream Tiny Aya Fire and Global model | |
| cards identify CC-BY-NC-4.0 and gated access; review those terms before | |
| reuse. The fine-tuned checkpoint cards do not provide independent | |
| provenance or a separate license statement. | |
| - The sweep summary's judge-failure column is incorrect: it reports zero | |
| despite three unparseable base-judge responses per judge-using monitor arm. | |
| Use the corrected aggregation of the saved decisions and preserve the | |
| original archive for audit. | |
| - The project owner has confirmed permission to release the selected logs and | |
| model weights. Verify the dataset license and each model's terms, and exclude | |
| credentials, private monitor keys/anchors, and unreviewed raw captures. | |
| With access to a few GPU cores, useful next work would be to: | |
| 1. Reproduce the small adapter fine-tune across several random seeds and a | |
| short, pre-registered hyperparameter sweep; retain immutable checkpoint and | |
| training manifests so each evaluated model can be traced to its data split. | |
| 2. Expand the benign A2 and held-out evaluation set, then run batched base and | |
| fine-tuned inference on the same trajectories. Calibrate thresholds only | |
| on validation data and report per-example parse validity and decisions on | |
| the untouched test split. | |
| 3. Run paired intervention experiments with and without the trusted entrant | |
| to estimate effects on collusion index, consumer surplus, and efficiency. | |
| 4. If suitable data and compute are available, test retention and transfer | |
| (including multilingual or held-out coordination mechanisms) separately; | |
| the present English-only results do not support such claims. | |
| These are proposed experiments, not completed findings or a guarantee that a | |
| small amount of compute will resolve the data and evaluation limitations. | |
| The expected benefit is narrower uncertainty from a larger, more balanced | |
| evaluation; whether fine-tuning improves action-level detection remains | |
| unknown, so no numerical before/after forecast is justified by this pilot. | |
| ### Dual-use and responsible release | |
| The A3 and A5 conditions expose overt and coded coordination patterns in a | |
| controlled synthetic market. They are released for benchmark reproducibility, | |
| not as guidance for real markets or for evading monitors. The reviewed package | |
| excludes private monitor keys and anchors, credentials, and unreviewed raw | |
| captures. The public dataset has no separate reuse license assigned in this | |
| release; the upstream model terms still apply. | |
| ## Reproducibility and artifacts | |
| The supplied artifacts include the 112-example dataset manifest, the | |
| 78-example CuratorKIT export, and the 16-episode sweep decisions. The sweep's | |
| scores and action counts were checked against those decisions; the judge | |
| failure counts were recalculated from `reasons` because the exported counter | |
| is stale. Preserve the sweep archive and report both the original counter | |
| field and the corrected failure count. Confirm dataset license and model | |
| terms before reuse. | |
| The public Hugging Face Space links a reviewed ZIP of the 112 run episodes, | |
| the structured dataset, train-only CuratorKIT export, original and reconciled | |
| sweep outputs, model collection, dataset collection, and a source snapshot. | |
| The ZIP intentionally contains only the release-reviewed run package, not the | |
| entire local `runs/` tree. | |
| The public [dataset repository](https://huggingface.co/datasets/munip/collusion-watch-lexsi-data) | |
| is in the [dataset collection](https://huggingface.co/collections/munip/collusion-watch-datasets-6afae07e8895a2910ce66914). | |
| The public fine-tuned checkpoints are in the | |
| [model collection](https://huggingface.co/collections/munip/collusion-watch-models-6afae07e3bc4e68e2ef90bf6). | |
| Download the [reviewed runs ZIP](https://huggingface.co/spaces/munip/collusion-watch/resolve/main/data/aya_market_base_a2prompt_runs.zip) | |
| or browse the [Space files](https://huggingface.co/spaces/munip/collusion-watch/tree/main). | |
| The code history is maintained at | |
| [GitHub](https://github.com/munip/apart-sprint-collusions); see the | |
| [feature branch history](https://github.com/munip/apart-sprint-collusions/commits/feature/lexsi-work) | |
| and the [submission snapshot at commit `0ce63aed`](https://github.com/munip/apart-sprint-collusions/commit/0ce63aed1135878d25e0cd3fe5a863fd3e10ca32). | |
| ## References and model terms | |
| - [Tiny Aya Global](https://huggingface.co/CohereLabs/tiny-aya-global) | |
| - [Tiny Aya Fire](https://huggingface.co/CohereLabs/tiny-aya-fire) | |
| - Fine-tuned judge evaluated in this sweep: | |
| [munip/tiny-aya-fire-m2-monitor-sft-41seed-v1](https://huggingface.co/munip/tiny-aya-fire-m2-monitor-sft-41seed-v1) | |
| - Earlier checkpoint (not used in the 16-episode comparison): | |
| [munip/tiny-aya-fire-m2-monitor-sft-30ep](https://huggingface.co/munip/tiny-aya-fire-m2-monitor-sft-30ep) | |
| Verify each model card's exact license and acceptable-use terms before | |
| publication. Do not rehost base model weights. | |