AUREOLE-R-v3 / results_v3 /release_validation.json
PureOne's picture
AUREOLE-R 3.0.0-hf.1: standalone public research release
9d6c005 verified
Raw
History Blame Contribute Delete
2.94 kB
{
"version": "3.0.0",
"passed": true,
"gates_passed": 15,
"gates_total": 15,
"tests": 58,
"gates": [
{
"name": "required_files",
"passed": true,
"details": {
"missing": []
}
},
{
"name": "current_tests",
"passed": true,
"details": {
"passed_count": 44,
"expected": 44
}
},
{
"name": "foundational_tests",
"passed": true,
"details": {
"passed_count": 14,
"expected": 14
}
},
{
"name": "held_out_splits",
"passed": true,
"details": {
"new_motion_scenes": 12,
"new_query_scenes": 8
}
},
{
"name": "motion_raw_consistency",
"passed": true,
"details": {
"records": 18144,
"queries": 8202625,
"max_summary_difference": 0.0
}
},
{
"name": "supported_certificate_audit",
"passed": true,
"details": {
"false_acceptances": 0,
"max_interval_violation": 2.7755575615628914e-16
}
},
{
"name": "unsafe_negative_control_retained",
"passed": true,
"details": {
"false_acceptances_in_deliberately_unsafe_ablation": 1366418
}
},
{
"name": "query_family_accounting",
"passed": true,
"details": {
"initialization": 147456,
"residual_queries": 535303,
"shared_baseline": 2949120
}
},
{
"name": "independent_readout_audit",
"passed": true,
"details": {
"false_certificates": 0,
"max_linear_error": 0
}
},
{
"name": "frozen_protocol_hashes",
"passed": true,
"details": {
"both_match": true
}
},
{
"name": "prior_evidence_retained",
"passed": true,
"details": {
"v2_frame_method_records": 12672
}
},
{
"name": "full_v3_replay",
"passed": true,
"details": {
"metrics": 298,
"max_difference": 0.0,
"timings_excluded": true
}
},
{
"name": "finite_completion_demo",
"passed": true,
"details": {
"frames": 24,
"physical_queries": 27648,
"full_domain_terms": 27648,
"zero_query_final_frames": 6,
"final_max_error": 0.0,
"records": "see demo JSON",
"scope": "Finite static-scene visibility completion with a constant prior; no GPU or full neural pipeline."
}
},
{
"name": "source_syntax",
"passed": true,
"details": {
"files": 20
}
},
{
"name": "honest_scope",
"passed": true,
"details": {
"maturity_is_subjective": true,
"no_gpu_or_full_pipeline_claim": true,
"executable_tests": 58
}
}
],
"scope": "Acceptance of the finite CPU reference; not full scientific maturity or production certification."
}