返回

📊 pokemon-tcg-ai-battle

Best win_rate: 0.8478   Best LB: 551.2   Experiments: 129 including running (✓10 ✗23)
GPU: 30.0h
ExpVersionwin_rate LBStatusLinkConsole
exp_0222v10.0capability_discovery_source_claim_falsified🔗
exp_0221v10.0capability_discovery_source_claim_falsified🔗
exp_0220v10.0capability_discovery_source_claim_falsified🔗
exp_0219v—0.0idea_proposal_failed
exp_0218v—0.0static_prescreen_source_claim_falsified
exp_0217v10.0capability_discovery_inconclusive🔗
exp_0216v—0.0static_prescreen_source_claim_falsified
exp_0215v10.0capability_discovery_execution_failed🔗
exp_0214v—0.0static_prescreen_source_claim_falsified
exp_0213v10.0capability_discovery_execution_failed🔗
exp_0212v10.0capability_discovery_falsified🔗
exp_0211v10.0capability_discovery_falsified🔗
exp_0210v10.0build_error🔗
exp_0209v—0.0capability_discovery_inconclusive
exp_0208v10.0capability_discovery_inconclusive🔗
exp_0207v10.0capability_discovery_falsified🔗
exp_0206v10.0capability_discovery_inconclusive🔗
exp_0205v10.0capability_discovery_falsified🔗
exp_0204v10.0no_change_precheck🔗
exp_0203v10.0no_change_precheck🔗
exp_0202v—0.0provider_quota
exp_0201v—0.0provider_quota
exp_0200v10.0build_error🔗
exp_0199v10.0capability_discovery_complete🔗
exp_0198v10.514no_divergence_skip🔗
exp_0197v—0.0provider_quota
exp_0196v10.46no_divergence_skip🔗
exp_0195v10.514targeted_evidence_missing🔗
exp_0194v10.4947targeted_evidence_missing🔗
exp_0193v10.055gate_rejected🔗
exp_0192v—0.0provider_quota
exp_0191v10.0error🔗
exp_0190v10.0capability_discovery_complete🔗
exp_0189v10.0capability_discovery_inconclusive🔗
exp_0188v10.0artifact_validation_failed🔗
exp_0187v—0.0provider_quota
exp_0186v10.0build_error🔗
exp_0185v10.3269no_divergence_skip🔗
exp_0184v10.4978gate_rejected🔗
exp_0183v—0.0failed
exp_0182v—failed
exp_0181v10.4219gate_rejected🔗
exp_0180v10.4052gate_rejected🔗
exp_0179v10.501gate_rejected🔗
exp_0178v10.4048no_divergence_skip🔗
exp_0177v—0.0failed
exp_0176v10.3966gate_rejected🔗
exp_0175v10.4778no_divergence_skip🔗
exp_0174v10.515no_divergence_skip🔗
exp_0173v—0.0failed
exp_0172v10.6385smoke_passed_no_promote🔗
exp_0171v—0.0failed
exp_0170v10.7024🔗
exp_0169v—0.0failed
exp_0168v—0.0failed
exp_0167v23complete🔗
exp_0166v22complete🔗
exp_0165v21error🔗
exp_0164v—0.0provider_quota
exp_0163v10.4368gate_rejected🔗
exp_0162-reeval-1v10.527gate_rejected🔗
exp_0162v10.7656517.5🔗
exp_0161v10.7656472.1🔗
exp_0160v—0.0idea_proposal_failed
exp_0159v—0.0idea_proposal_failed
exp_0158v—0.0idea_proposal_failed
exp_0157v—0.0idea_proposal_failed
exp_0156v—0.0idea_proposal_failed
exp_0155v—0.0idea_proposal_failed
exp_0154v—0.0idea_proposal_failed
exp_0153v—0.0idea_proposal_failed
exp_0152v—0.0idea_proposal_failed
exp_0151v—0.0idea_proposal_failed
exp_0150v—0.0idea_proposal_failed
exp_0149v—0.0idea_proposal_failed
exp_0148v—0.0idea_proposal_failed
exp_0147v—0.0idea_proposal_failed
exp_0146v—0.0idea_proposal_failed
exp_0145v—0.0idea_proposal_failed
exp_0144v—0.0idea_proposal_failed
exp_0143v—0.0idea_proposal_failed
exp_0142v—0.0idea_proposal_failed
exp_0141v—0.0idea_proposal_failed
exp_0140v—0.0idea_proposal_failed
exp_0139v—0.0idea_proposal_failed
exp_0138v—0.0idea_proposal_failed
exp_0137v—0.0idea_proposal_failed
exp_0136v—0.0idea_proposal_failed
exp_0135v—0.0idea_proposal_failed
exp_0134v—0.0idea_proposal_failed
exp_0133v—0.0idea_proposal_failed
exp_0132v—0.0idea_proposal_failed
exp_0131v10.6765535.8🔗
exp_0130v—0.0idea_proposal_failed
exp_0129v—0.0idea_proposal_failed
exp_0128v—0.0idea_proposal_failed
exp_0127v—0.0idea_proposal_failed
exp_0126v—0.0idea_proposal_failed
exp_0125v—0.0idea_proposal_failed
exp_0124v—0.0idea_proposal_failed
exp_0123v—0.0idea_proposal_failed
exp_0122v—0.0idea_proposal_failed
exp_0121v—0.0idea_proposal_failed
exp_0120v—0.0idea_proposal_failed
exp_0119v—0.0idea_proposal_failed
exp_0118v—0.0idea_proposal_failed
exp_0117v—0.0idea_proposal_failed
exp_0116v—0.0idea_proposal_failed
exp_0115v—0.0idea_proposal_failed
exp_0114v10.7024533.3🔗
exp_0113-reeval-1v10.4876gate_rejected🔗
exp_0113v10.6875challenger_pending🔗
exp_0112-reeval-1v10.4609gate_rejected🔗
exp_0112v10.6338challenger_pending🔗
exp_0111v10.8478523.3🔗
exp_0110-reeval-1v10.5gate_rejected🔗
exp_0110v10.6977challenger_pending🔗
exp_0109v10.6837475.4🔗
exp_0108-reeval-1v10.5016gate_rejected🔗
exp_0108v10.7429challenger_pending🔗
exp_0107v10.7179551.2🔗
exp_0106v—0.0timeout
exp_0105v—0.0idea_proposal_failed
exp_0104v10.4659gate_rejected🔗
exp_0103v10.451gate_rejected🔗
exp_0102v—0.0cancelled
exp_0101v—0.0timeout
exp_0100v10.4375gate_rejected🔗
exp_0099v10.4893gate_rejected🔗
129 experiments from exp_0099, including running work (newest first)

win_rate = vs champion (moving target, not cross-round comparable)