spb/wpai0002_uqo

1{2  "created_at": "2026-11-10T22:15:47Z",3  "git": {4    "commit": "bae3119d55c76209e05d49c04f541c9fae050be6",5    "branch": "main",6    "dirty": true7  },8  "libraries": {9    "python": "3.14.4",10    "torch": "2.12.0",11    "numpy": "2.5.4",12    "anthropic": "2.3.0",13    "transformers": "5.8.1",14    "sentencepiece": "0.2.2",15    "lxml": "6.1.3",16    "pyarrow": "24.0.0",17    "sacrebleu": "2.6.0",18    "datasketch": "2.0.0",19    "rapidfuzz": "3.14.6"20  },21  "hardware": {22    "platform": "macOS-27.0-arm64-arm-64bit-Mach-O",23    "machine": "arm64",24    "cpu_count": 18,25    "chip": "Apple M5 Max",26    "ram_gb": 48.0,27    "torch_mps": true,28    "torch_cuda": false29  },30  "system": "LLM_qwen2.5-1.5b",31  "split": "val",32  "n_eval_pairs": 3000,33  "n_train_targets": 13477,34  "memorization": {35    "n": 3000,36    "mean_max_jaccard_to_train": 0.0,37    "frac_jaccard_ge_0_5": 0.0,38    "frac_jaccard_ge_0_8": 0.0,39    "max_longest_common_ngram": 0,40    "frac_lcn_ge_12": 0.0,41    "n_same_passage_leak": 0,42    "worst": [43      {44        "pair_id": "pair_e2368b58fb591253",45        "nn_train_passage": null,46        "jaccard_to_train": 0.0,47        "longest_common_ngram": 0,48        "same_passage_leak": false49      },50      {51        "pair_id": "pair_b6419b42af6a812b",52        "nn_train_passage": null,53        "jaccard_to_train": 0.0,54        "longest_common_ngram": 0,55        "same_passage_leak": false56      },57      {58        "pair_id": "pair_0246c92822d83007",59        "nn_train_passage": null,60        "jaccard_to_train": 0.0,61        "longest_common_ngram": 0,62        "same_passage_leak": false63      },64      {65        "pair_id": "pair_00f8a76190939459",66        "nn_train_passage": null,67        "jaccard_to_train": 0.0,68        "longest_common_ngram": 0,69        "same_passage_leak": false70      },71      {72        "pair_id": "pair_d4d914b305ac664d",73        "nn_train_passage": null,74        "jaccard_to_train": 0.0,75        "longest_common_ngram": 0,76        "same_passage_leak": false77      }78    ]79  },80  "within_original_agreement": {81    "n_passages": 416,82    "chrf_rewrite1_rewrite2": {83      "mean": 82.87487031606085,84      "ci_low": 82.23897761009937,85      "ci_high": 83.56394718503695,86      "n_items": 416,87      "n_groups": 21888    },89    "chrf_rewrite_original": {90      "mean": 62.69468288297017,91      "ci_low": 61.59378046359615,92      "ci_high": 63.803052401688056,93      "n_items": 416,94      "n_groups": 21895    },96    "chrf_recon1_recon2": {97      "mean": 81.42099237152523,98      "ci_low": 80.59739147307437,99      "ci_high": 82.29626225605186,100      "n_items": 416,101      "n_groups": 218102    },103    "chrf_recon_original": {104      "mean": 66.23929083774026,105      "ci_low": 65.19926328409967,106      "ci_high": 67.2929165921159,107      "n_items": 416,108      "n_groups": 218109    }110  },111  "rewrite_ambiguity": {112    "n_close_pairs": 0,113    "jaccard_threshold": 0.5,114    "n_items": 1951115  }116}117