From 94d911284b78df4c34e60bc0e4165ef145e85da8 Mon Sep 17 00:00:00 2001 From: Aymen Hammouda Date: Mon, 5 Oct 2026 20:18:09 +0200 Subject: [PATCH] agent: protect all 35 verified retrieval cases --- docs/benchmarks/regression-baseline.json | 54 ++++++++++++------------ 1 file changed, 27 insertions(+), 27 deletions(-) diff --git a/docs/benchmarks/regression-baseline.json b/docs/benchmarks/regression-baseline.json index b4a89de..9cdfa8f 100644 --- a/docs/benchmarks/regression-baseline.json +++ b/docs/benchmarks/regression-baseline.json @@ -9,21 +9,21 @@ "index_documents": 1603, "cases": { "EX-001/3.13": { - "retrieval_hit_at_5": false, + "retrieval_hit_at_5": true, "resolved_citations": [ "https://docs.python.org/3.13/library/itertools.html#itertools.accumulate" ], "seconds": 0.01075 }, "EX-002/3.13": { - "retrieval_hit_at_5": false, + "retrieval_hit_at_5": true, "resolved_citations": [ "https://docs.python.org/3.13/library/itertools.html#itertools.pairwise" ], "seconds": 0.007562 }, "EX-003/3.13": { - "retrieval_hit_at_5": false, + "retrieval_hit_at_5": true, "resolved_citations": [ "https://docs.python.org/3.13/library/itertools.html#itertools.groupby" ], @@ -37,21 +37,21 @@ "seconds": 0.066224 }, "EX-005/3.13": { - "retrieval_hit_at_5": false, + "retrieval_hit_at_5": true, "resolved_citations": [ "https://docs.python.org/3.13/library/functools.html#functools.cached_property" ], "seconds": 0.007928 }, "EX-006/3.13": { - "retrieval_hit_at_5": false, + "retrieval_hit_at_5": true, "resolved_citations": [ "https://docs.python.org/3.13/library/functools.html#functools.singledispatch" ], "seconds": 0.00741 }, "EX-007/3.13": { - "retrieval_hit_at_5": false, + "retrieval_hit_at_5": true, "resolved_citations": [ "https://docs.python.org/3.13/library/pathlib.html#pathlib.Path.glob" ], @@ -65,49 +65,49 @@ "seconds": 0.067016 }, "EX-009/3.13": { - "retrieval_hit_at_5": false, + "retrieval_hit_at_5": true, "resolved_citations": [ "https://docs.python.org/3.13/library/pathlib.html#pathlib.PurePath.is_relative_to" ], "seconds": 0.007599 }, "EX-010/3.13": { - "retrieval_hit_at_5": false, + "retrieval_hit_at_5": true, "resolved_citations": [ "https://docs.python.org/3.13/library/collections.html#collections.Counter.total" ], "seconds": 0.006916 }, "EX-011/3.13": { - "retrieval_hit_at_5": false, + "retrieval_hit_at_5": true, "resolved_citations": [ "https://docs.python.org/3.13/library/collections.html#collections.deque.rotate" ], "seconds": 0.007217 }, "EX-012/3.13": { - "retrieval_hit_at_5": false, + "retrieval_hit_at_5": true, "resolved_citations": [ "https://docs.python.org/3.13/library/statistics.html#statistics.fmean" ], "seconds": 0.007687 }, "EX-013/3.13": { - "retrieval_hit_at_5": false, + "retrieval_hit_at_5": true, "resolved_citations": [ "https://docs.python.org/3.13/library/statistics.html#statistics.NormalDist.inv_cdf" ], "seconds": 0.007249 }, "EX-014/3.13": { - "retrieval_hit_at_5": false, + "retrieval_hit_at_5": true, "resolved_citations": [ "https://docs.python.org/3.13/library/contextlib.html#contextlib.ExitStack" ], "seconds": 0.007472 }, "EX-015/3.13": { - "retrieval_hit_at_5": false, + "retrieval_hit_at_5": true, "resolved_citations": [ "https://docs.python.org/3.13/library/tempfile.html#tempfile.TemporaryDirectory" ], @@ -122,35 +122,35 @@ "seconds": 0.009367 }, "CO-002/3.13": { - "retrieval_hit_at_5": false, + "retrieval_hit_at_5": true, "resolved_citations": [ "https://docs.python.org/3.13/library/contextlib.html#contextlib.suppress" ], "seconds": 0.007925 }, "CO-003/3.13": { - "retrieval_hit_at_5": false, + "retrieval_hit_at_5": true, "resolved_citations": [ "https://docs.python.org/3.13/library/decimal.html#decimal.localcontext" ], "seconds": 0.007112 }, "CO-004/3.13": { - "retrieval_hit_at_5": false, + "retrieval_hit_at_5": true, "resolved_citations": [ "https://docs.python.org/3.13/library/asyncio-task.html#asyncio.TaskGroup" ], "seconds": 0.007918 }, "CO-005/3.13": { - "retrieval_hit_at_5": false, + "retrieval_hit_at_5": true, "resolved_citations": [ "https://docs.python.org/3.13/library/concurrent.futures.html#concurrent.futures.as_completed" ], "seconds": 0.007178 }, "CO-006/3.13": { - "retrieval_hit_at_5": false, + "retrieval_hit_at_5": true, "resolved_citations": [ "https://docs.python.org/3.13/library/csv.html#csv.DictReader" ], @@ -164,7 +164,7 @@ "seconds": 0.008294 }, "CO-008/3.13": { - "retrieval_hit_at_5": false, + "retrieval_hit_at_5": true, "resolved_citations": [ "https://docs.python.org/3.13/library/shutil.html#shutil.copy2" ], @@ -241,7 +241,7 @@ "seconds": 0.07333 }, "XV-005/3.12": { - "retrieval_hit_at_5": false, + "retrieval_hit_at_5": true, "resolved_citations": [ "https://docs.python.org/3.12/library/ssl.html" ], @@ -269,7 +269,7 @@ "seconds": 0.126592 }, "XV-007/3.12": { - "retrieval_hit_at_5": false, + "retrieval_hit_at_5": true, "resolved_citations": [ "https://docs.python.org/3.12/library/itertools.html#itertools.batched" ], @@ -283,7 +283,7 @@ "seconds": 0.025097 }, "XV-008/3.12": { - "retrieval_hit_at_5": false, + "retrieval_hit_at_5": true, "resolved_citations": [ "https://docs.python.org/3.12/library/queue.html" ], @@ -353,7 +353,7 @@ "seconds": 0.09248 }, "XV-013/3.11": { - "retrieval_hit_at_5": false, + "retrieval_hit_at_5": true, "resolved_citations": [ "https://docs.python.org/3.11/library/pathlib.html" ], @@ -367,7 +367,7 @@ "seconds": 0.008193 }, "XV-014/3.11": { - "retrieval_hit_at_5": false, + "retrieval_hit_at_5": true, "resolved_citations": [ "https://docs.python.org/3.11/library/shutil.html#shutil.rmtree" ], @@ -381,7 +381,7 @@ "seconds": 0.008078 }, "XV-015/3.11": { - "retrieval_hit_at_5": false, + "retrieval_hit_at_5": true, "resolved_citations": [ "https://docs.python.org/3.11/library/tempfile.html#tempfile.NamedTemporaryFile" ], @@ -410,7 +410,7 @@ "seconds": 0.014481 }, "PE-003/3.13": { - "retrieval_hit_at_5": false, + "retrieval_hit_at_5": true, "resolved_citations": [ "https://docs.python.org/3.13/library/warnings.html#warnings.deprecated", "https://docs.python.org/3.13/whatsnew/3.13.html#warnings" @@ -418,7 +418,7 @@ "seconds": 0.010179 }, "PE-004/3.13": { - "retrieval_hit_at_5": false, + "retrieval_hit_at_5": true, "resolved_citations": [ "https://docs.python.org/3.13/library/typing.html#typing.ReadOnly" ],