{ "split": "test", "queries": 3000, "candidates_per_query": 3000, "repositories": 444, "dataset_sha256": "b9e150337e195838efb5fe3f4ecafd63dfa99a55cf3635764c893912f4747596", "evaluator_source_sha256": "29c942b9cbfff21ba8514511e27752527f0ec5e2cad5fbf57ec3b220fc7acd0b", "fusion": { "dense_weight": 0.5, "per_method_limit": 100, "k": 60 }, "evaluation_ids_sha256": "27c4062864258ea8f93c3e35b1ef6f65038dc24d15673afc930168dec349b3ba", "protocol": "one labeled positive per query; all split snippets are candidates; docstrings removed", "limitations": [ "Other semantically correct snippets may be counted as negatives", "This is function retrieval, not a bug-fixing or multi-file context benchmark", "No downstream Astra task-success evaluation has been run", "Base-model pretraining contamination cannot be excluded" ], "models": { "pretrained": { "fingerprint": "78f9f86bd7f71186560e631f0ed43678868c5d39ec07512adc52bc9185009f82", "parameters": 22713216, "config": { "format_version": 1, "base_model": "sentence-transformers/all-MiniLM-L6-v2", "revision": "1110a243fdf4706b3f48f1d95db1a4f5529b4d41", "max_length": 256, "query_length": 96, "pooling": "attention-masked-mean-l2", "code_normalization": "strip-python-docstrings-comments-v1" }, "embedding_seconds": 14.739996934000374 }, "trained": { "fingerprint": "2bb5197791e4a0caf85af4e92c7ad9f2394cc4c01dafa0b0b18d7e32f0fc5697", "parameters": 22713216, "config": { "format_version": 1, "base_model": "sentence-transformers/all-MiniLM-L6-v2", "revision": "1110a243fdf4706b3f48f1d95db1a4f5529b4d41", "max_length": 256, "query_length": 96, "pooling": "attention-masked-mean-l2", "code_normalization": "strip-python-docstrings-comments-v1" }, "embedding_seconds": 14.511412101001042 } }, "metrics": { "bm25": { "mrr": 0.559536732255293, "mrr_at_10": 0.5529096560846561, "recall_at_1": 0.4673333333333333, "recall_at_5": 0.668, "recall_at_10": 0.7263333333333334, "median_rank": 2.0, "macro_repository_mrr": 0.5716105643053901 }, "pretrained_dense": { "mrr": 0.6819148989769989, "mrr_at_10": 0.6770041005291004, "recall_at_1": 0.587, "recall_at_5": 0.7976666666666666, "recall_at_10": 0.8523333333333334, "median_rank": 1.0, "macro_repository_mrr": 0.6956670635572176 }, "pretrained_hybrid": { "mrr": 0.6879723629119775, "mrr_at_10": 0.6825018518518519, "recall_at_1": 0.5963333333333334, "recall_at_5": 0.796, "recall_at_10": 0.8496666666666667, "median_rank": 1.0, "macro_repository_mrr": 0.6997776730651677 }, "trained_dense": { "mrr": 0.7784403489523588, "mrr_at_10": 0.7752448412698412, "recall_at_1": 0.701, "recall_at_5": 0.8746666666666667, "recall_at_10": 0.9156666666666666, "median_rank": 1.0, "macro_repository_mrr": 0.7791868690119261 }, "trained_hybrid": { "mrr": 0.7220843512885813, "mrr_at_10": 0.7164558201058201, "recall_at_1": 0.6406666666666667, "recall_at_5": 0.815, "recall_at_10": 0.8663333333333333, "median_rank": 1.0, "macro_repository_mrr": 0.7273184680219402 } }, "trained_vs_pretrained_dense_mrr": { "delta": 0.09652544997535988, "ci95": [ 0.0848868558350596, 0.10748017710804628 ], "method": "paired repository-cluster bootstrap, 2000 resamples", "repository_clusters": 444 }, "trained_hybrid_vs_bm25_mrr": { "delta": 0.16254761903328815, "ci95": [ 0.150834640125844, 0.1763703573684562 ], "method": "paired repository-cluster bootstrap, 2000 resamples", "repository_clusters": 444 }, "trained_dense_vs_bm25_mrr": { "delta": 0.21890361669706576, "ci95": [ 0.2004503288862072, 0.23732116908748563 ], "method": "paired repository-cluster bootstrap, 2000 resamples", "repository_clusters": 444 }, "elapsed_seconds": 39.51678221300244 }