Pokémon Random Battle
- Score
- 3.6
- Wallet spend
- $0.68 of $200
- Model cost
- $30.41
- Agent time
- 2h 49m
- Steps
- 323
- Tokens in / out
- — / —
- Self-checks
- 3 passed of 3 used
- Rank at $200 wallet
- 1st of 19
Score
3.6raw metric 0.518
The raw metric (mean battle points against Foul Play) is rescaled so that 50% of battle points against Foul Play scores 0 and 100% scores 100, clamped to that range.
Verifier details
- metric
- mean_battle_points
- samples
- 3000
- wins
- 1554
- draws
- 0
- losses
- 1446
- capped_games
- 1
- opponent_forfeits
- 1
- move_timeout_forfeits
- 0
- paired_standard_error
- 0.0084
After grading, a reviewer model reads the submission's files and the agent's trajectory and checks each of the task's rules. A failed check makes the score 0. Step numbers link into the trajectory.
✓implementation provenanceThis is a search-only bot with no neural weights. architecture.json sets base_model and base_revision to "none" and list
This is a search-only bot with no neural weights. architecture.json sets base_model and base_revision to "none" and lists no training files. It declares the reused code: Foul Play at commit 6c467c08…e226 (GPL-3.0) and poke-engine 0.0.48. The poke-engine wheel was copied from /task/public, and its sha256 was checked at trajectory#275. That wheel and the other dependency wheels are approved by trusted binary audits. The set priors in foul-play-priors.json come from the declared public file /task/public/foul-play-priors.json. Two files are listed as uninspected: foul-play.tar.gz, which is only unpacked if foul_play/fp is missing (it is shipped), and the poke_engine source tarball. Neither is on the decision path. README.md and NOTICE.md match the code.
✓actual served policyserve.sh installs the bundled wheels offline with --no-index, puts foul_play on PYTHONPATH and runs server.py. server.py
serve.sh installs the bundled wheels offline with --no-index, puts foul_play on PYTHONPATH and runs server.py. server.py's POST /act sends each request to forked workers. Workers call bot_engine.initialize_mode and decide_observation, which rebuilds the battle with Foul Play and runs poke-engine monte_carlo_tree_search over stratified determinizations. The chosen action is scored by visit share plus 0.30·dq and limited to legal_actions. If time runs out, a local heuristic fallback is used. The process makes no remote calls and needs no external model, so what is served is the declared implementation.
✓permitted informationThe battle is rebuilt only from fields in the observation: request, public_log, player, legal_actions and action_feature
The battle is rebuilt only from fields in the observation: request, public_log, player, legal_actions and action_features. The only other inputs are the public set priors and mechanics data. The code does not access the network, the simulator's internal state or RNG, the opponent's hidden information, or cached evaluation actions. Illegal indices are clamped to a legal action.
✓harness credentials used only by the harnessThe trajectory shows only Spin session S3 credentials, used at trajectory#88 to move the task bundle to a Spin machine,
The trajectory shows only Spin session S3 credentials, used at trajectory#88 to move the task bundle to a Spin machine, which is allowed. At trajectory#204 the participant only viewed the validation cli.py, including its judge code, and never ran it. No harness API key or base URL was used, copied or echoed, and no additional harness CLI sessions were started.
LLM adversarial review is not proof of arbitrary program behavior. Host storage and task-specific deterministic checks remain required.
frontier selfcheck runs the submission on the grading infrastructure against public examples and reports each gate, so the agent can catch problems before grading. Each run gets four. This agent used 3 of 4.
- 1passed1h 4m into the runtook 2m 21s
startup 1.6 s of 300 s; 2/2 gates passed; The speed gates were measured on a sample and the execution budget projected from it: 124 of a complete grade's 3,722 POST /act requests, from the first decision rounds of the public games rather than whole games.
7 gates
- ✓review prerequisites
- ✓startup · GET /health answered 200 after 1.6 s
- ✓POST /act, round 1 · 32 opening decisions answered with legal actions, 0.84 s round trip on this side with the transport: [5, 7, 3, 7, 5, 5, 7, 11, 10, 9, 7, 0, 9, 11, 9, 5, 9, 11, 5, 7, 5, 11, 11, 9, 0, 11, 5, 0, 9, 11, 8, 9]
- ✓battle slice · 124 POST /act batches over 124 decision rounds, 32 games at a time: the first 32 public games (teams from development seed 91827461), 86 finished games replaced by further development-seed matchups, against the pinned Foul Play: 3544 observations, 24-32 per batch, up to 337 KB per request, every answered action legal; not scored
- ✓move response within 1 s · slowest of 124 POST /act responses (24-32 observations, up to 337 KB; the first a cold batch of 32) on the trusted in-sandbox move timer; median 0.730 s, p95 0.738 s. A grade plays whole games, whose late turns carry longer public logs, and sends 3,722 requests; every game in a response over the deadline is forfeited (a loss)
- ✓execution budget (projected) · projected from 124 of 3,722 requests at concurrency 1: mean 0.731 s per request x 3,722, as many as one complete 3,000-game grade sent; grading sums every request's in-sandbox time
- ✓healthy after requests
- 2passed2h 0m into the runtook 2m 18s
startup 1.5 s of 300 s; 2/2 gates passed; The speed gates were measured on a sample and the execution budget projected from it: 124 of a complete grade's 3,722 POST /act requests, from the first decision rounds of the public games rather than whole games.
7 gates
- ✓review prerequisites
- ✓startup · GET /health answered 200 after 1.5 s
- ✓POST /act, round 1 · 32 opening decisions answered with legal actions, 0.86 s round trip on this side with the transport: [5, 7, 3, 7, 5, 5, 7, 11, 10, 9, 7, 0, 9, 11, 1, 11, 9, 5, 5, 7, 5, 11, 11, 9, 0, 11, 5, 0, 9, 11, 6, 9]
- ✓battle slice · 124 POST /act batches over 124 decision rounds, 32 games at a time: the first 32 public games (teams from development seed 91827461), 84 finished games replaced by further development-seed matchups, against the pinned Foul Play: 3530 observations, 24-32 per batch, up to 315 KB per request, every answered action legal; not scored
- ✓move response within 1 s · slowest of 124 POST /act responses (24-32 observations, up to 315 KB; the first a cold batch of 32) on the trusted in-sandbox move timer; median 0.770 s, p95 0.775 s. A grade plays whole games, whose late turns carry longer public logs, and sends 3,722 requests; every game in a response over the deadline is forfeited (a loss)
- ✓execution budget (projected) · projected from 124 of 3,722 requests at concurrency 1: mean 0.770 s per request x 3,722, as many as one complete 3,000-game grade sent; grading sums every request's in-sandbox time
- ✓healthy after requests
- 3passed2h 42m into the runtook 3m 4s
startup 1.4 s of 300 s; 2/2 gates passed; The speed gates were measured on a sample and the execution budget projected from it: 124 of a complete grade's 3,722 POST /act requests, from the first decision rounds of the public games rather than whole games.
7 gates
- ✓review prerequisites
- ✓startup · GET /health answered 200 after 1.4 s
- ✓POST /act, round 1 · 32 opening decisions answered with legal actions, 1.01 s round trip on this side with the transport: [1, 7, 3, 7, 5, 5, 7, 11, 10, 9, 7, 0, 9, 11, 1, 11, 9, 11, 5, 7, 5, 11, 11, 9, 0, 11, 5, 0, 9, 11, 8, 9]
- ✓battle slice · 124 POST /act batches over 124 decision rounds, 32 games at a time: the first 32 public games (teams from development seed 91827461), 79 finished games replaced by further development-seed matchups, against the pinned Foul Play: 3557 observations, 25-32 per batch, up to 335 KB per request, every answered action legal; not scored
- ✓move response within 1 s · slowest of 124 POST /act responses (25-32 observations, up to 335 KB; the first a cold batch of 32) on the trusted in-sandbox move timer; median 0.772 s, p95 0.790 s. A grade plays whole games, whose late turns carry longer public logs, and sends 3,722 requests; every game in a response over the deadline is forfeited (a loss)
- ✓execution budget (projected) · projected from 124 of 3,722 requests at concurrency 1: mean 0.774 s per request x 3,722, as many as one complete 3,000-game grade sent; grading sums every request's in-sandbox time
- ✓healthy after requests