Download benchmark_summary.json from mindbomber/aana: direct link, hf CLI and curl.
- Browser
- Download file 2.26 kB
-
https://huggingface.co/mindbomber/aana/resolve/main/benchmark_summary.json
- Command line
-
hf download hf://mindbomber/aana/benchmark_summary.json
-
curl -L -o benchmark_summary.json https://huggingface.co/mindbomber/aana/resolve/main/benchmark_summary.json
2.26 kB
| { | |
| "model_id": "mindbomber/aana", | |
| "architecture": "Alignment-Aware Neural Architecture", | |
| "system_model": "S = (f_theta, E_phi, R, Pi_psi, G)", | |
| "results": [ | |
| { | |
| "benchmark": "PIIMB", | |
| "submission": "https://huggingface.co/datasets/piimb/pii-masking-benchmark-results/discussions/3", | |
| "model_card": "https://huggingface.co/mindbomber/aana-presidio-piimb-policy-v1", | |
| "dataset": "piimb/pii-masking-benchmark", | |
| "dataset_revision": "df8299e90ff053fa6fd1d3678f6693a454f4ecc0", | |
| "subset": "sentences", | |
| "base_detector": "microsoft/presidio-analyzer", | |
| "base_average_masking_f2": 0.4492985573, | |
| "aana_average_masking_f2": 0.5629171363, | |
| "delta_average_masking_f2": 0.113618579, | |
| "base_average_recall": 0.4008557794, | |
| "aana_average_recall": 0.5159532273, | |
| "delta_average_recall": 0.1150974479, | |
| "scope": "official PIIMB submission showing AANA verifier/correction gain over the same specialist detector" | |
| }, | |
| { | |
| "benchmark": "PIIMB", | |
| "submission": "https://huggingface.co/datasets/piimb/pii-masking-benchmark-results/discussions/2", | |
| "model_card": "https://huggingface.co/mindbomber/aana-piimb-policy-baseline", | |
| "dataset": "piimb/pii-masking-benchmark", | |
| "dataset_revision": "df8299e90ff053fa6fd1d3678f6693a454f4ecc0", | |
| "subset": "sentences", | |
| "aana_average_masking_f2": 0.5195345497, | |
| "scope": "official PIIMB submission for a zero-parameter deterministic policy baseline" | |
| }, | |
| { | |
| "benchmark": "TruthfulQA", | |
| "dataset": "truthfulqa/truthful_qa", | |
| "configuration": "multiple_choice", | |
| "split": "validation", | |
| "sample_size": 100, | |
| "base_generator": "openai/gpt-4o-mini", | |
| "mc1_accuracy": 0.85, | |
| "scope": "local AANA-gated run and public artifact publication, not an official leaderboard submission" | |
| } | |
| ], | |
| "claim_limits": [ | |
| "AANA is a runtime architecture, not a standalone neural-weight checkpoint.", | |
| "Current public results do not claim state-of-the-art performance.", | |
| "Current public results do not guarantee hallucination removal, PII removal, or production safety.", | |
| "Production readiness requires external deployment evidence beyond local benchmark results." | |
| ] | |
| } | |