philipjohnbasile's picture
Add registered competitive short-hole FIM v1 evidence (null result)
186479f verified
Raw
History Blame Contribute Delete
4.9 kB
{
"bins": [
"8_token_ish",
"16_token_ish",
"32_token_ish",
"64_token_ish"
],
"contract_id": "wisp-short-hole-fim-competitive-v1",
"descriptive_intervals": {
"Qwen__Qwen2.5-Coder-0.5B": {
"16_token_ish": [
0.038461538461538464,
0.08875739644970414
],
"32_token_ish": [
0.0,
0.02416918429003021
],
"64_token_ish": [
0.0,
0.012468827930174564
],
"8_token_ish": [
0.1092896174863388,
0.19680851063829788
]
},
"bigcode__tiny_starcoder_py": {
"16_token_ish": [
0.0,
0.0125
],
"32_token_ish": [
0.0,
0.010050251256281407
],
"64_token_ish": [
0.0,
0.0
],
"8_token_ish": [
0.007614213197969543,
0.04895104895104895
]
},
"codeparrot__codeparrot-small": {
"16_token_ish": [
0.0027548209366391185,
0.022950819672131147
],
"32_token_ish": [
0.0,
0.010050251256281407
],
"64_token_ish": [
0.0,
0.0
],
"8_token_ish": [
0.006369426751592357,
0.03990610328638498
]
},
"ibm-granite__granite-4.0-350m-base": {
"16_token_ish": [
0.0,
0.024305555555555556
],
"32_token_ish": [
0.0,
0.01557632398753894
],
"64_token_ish": [
0.0,
0.0
],
"8_token_ish": [
0.01483679525222552,
0.050793650793650794
]
},
"wisp": {
"16_token_ish": [
0.0025974025974025974,
0.02464788732394366
],
"32_token_ish": [
0.0,
0.0
],
"64_token_ish": [
0.0,
0.0
],
"8_token_ish": [
0.00974025974025974,
0.04814814814814815
]
}
},
"method": "paired nonparametric repository cluster bootstrap",
"model_replicate_macro_means": {
"Qwen__Qwen2.5-Coder-0.5B": {
"descriptive95": [
0.044585987261146494,
0.06975308641975309
],
"mean": 0.05684153680081007
},
"bigcode__tiny_starcoder_py": {
"descriptive95": [
0.0037128712871287127,
0.01419558359621451
],
"mean": 0.008733842367255456
},
"codeparrot__codeparrot-small": {
"descriptive95": [
0.003633720930232558,
0.015277777777777777
],
"mean": 0.009366252755936293
},
"ibm-granite__granite-4.0-350m-base": {
"descriptive95": [
0.005952380952380952,
0.018493150684931507
],
"mean": 0.01170650003827442
},
"wisp": {
"descriptive95": [
0.005028735632183908,
0.01551094890510949
],
"mean": 0.010161879398330735
}
},
"models": [
"Qwen__Qwen2.5-Coder-0.5B",
"bigcode__tiny_starcoder_py",
"codeparrot__codeparrot-small",
"ibm-granite__granite-4.0-350m-base",
"wisp"
],
"n_repositories": 24,
"paired_deltas": {
"Qwen__Qwen2.5-Coder-0.5B": {
"bonferroni_onesided_95_lower": -0.06115107913669065,
"delta_mean": -0.04667965740247933,
"descriptive95": [
-0.06,
-0.0339943342776204
],
"lower_exceeds_zero": false
},
"bigcode__tiny_starcoder_py": {
"bonferroni_onesided_95_lower": -0.005033557046979867,
"delta_mean": 0.0014280370310752804,
"descriptive95": [
-0.004629629629629629,
0.007472826086956521
],
"lower_exceeds_zero": false
},
"codeparrot__codeparrot-small": {
"bonferroni_onesided_95_lower": -0.0024590163934426236,
"delta_mean": 0.0007956266423944429,
"descriptive95": [
-0.002252252252252252,
0.004325259515570935
],
"lower_exceeds_zero": false
},
"ibm-granite__granite-4.0-350m-base": {
"bonferroni_onesided_95_lower": -0.008384146341463417,
"delta_mean": -0.0015446206399436838,
"descriptive95": [
-0.007812499999999998,
0.004451038575667655
],
"lower_exceeds_zero": false
}
},
"repositories": [
"0xPlaygrounds/rig",
"D4Vinci/Scrapling",
"DataWithBaraa/sql-data-warehouse-project",
"DietrichGebert/ponytail",
"EpicGames/raddebugger",
"Fission-AI/OpenSpec",
"JuliusBrussee/caveman",
"Netflix/maestro",
"OpenCut-app/OpenCut",
"TecharoHQ/anubis",
"asg017/sqlite-vec",
"browser-use/browser-use",
"cloudwego/eino",
"dockur/windows",
"henrygd/beszel",
"j178/prek",
"jackwener/OpenCLI",
"microsoft/RustTraining",
"microsoft/markitdown",
"modelcontextprotocol/java-sdk",
"nicbarker/clay",
"steipete/agent-scripts",
"unitycatalog/unitycatalog",
"upstash/context7"
],
"samples": 10000,
"schema_version": 1,
"seed": 20260731
}