gliner25-base-litert / validation-full.json
spybyscript's picture
Every trained head: explicit spans, relations and records; reference runtime; phone results
ff95cf8 verified
Raw History Blame Contribute Delete
4.24 kB
{
"about": "Every call type against gliner2 2.0.0 with the original weights (runtime/verify_parity.py): LiteRT 2.2.0 on the CPU, wfp16 encoder.",
"source": "fastino/gliner2.5-base-v1@1a8bc24e00dc7300b9017c81d63e3dcdabb26596",
"corpus": {
"file": "runtime/parity_corpus.json",
"requests": 296,
"identical": 296,
"byCallType": {
"entities": {
"calls": 40,
"refused": 0,
"matched": 40,
"items": 148,
"minSpanF1": 1.0,
"maxConfidenceDifference": 0.000228
},
"entities_single": {
"calls": 8,
"refused": 0,
"matched": 8,
"items": 16,
"minSpanF1": 1.0,
"maxConfidenceDifference": 5e-06
},
"relations_work": {
"calls": 24,
"refused": 0,
"matched": 24,
"items": 62,
"minSpanF1": 1.0,
"maxConfidenceDifference": 0.000883
},
"record_natural": {
"calls": 16,
"refused": 0,
"matched": 16,
"items": 28,
"minSpanF1": 1.0,
"maxConfidenceDifference": 0.00013
},
"record_latent": {
"calls": 24,
"refused": 0,
"matched": 24,
"items": 429,
"minSpanF1": 1.0,
"maxConfidenceDifference": 0.000641
},
"attributes": {
"calls": 16,
"refused": 0,
"matched": 16,
"items": 31,
"minSpanF1": 1.0,
"maxConfidenceDifference": 0.000298
},
"classification_topic": {
"calls": 40,
"refused": 0,
"matched": 40,
"items": 40,
"minSpanF1": 1.0,
"maxConfidenceDifference": 0.001305
},
"mixed": {
"calls": 16,
"refused": 0,
"matched": 16,
"items": 68,
"minSpanF1": 1.0,
"maxConfidenceDifference": 0.001358
},
"relations_family": {
"calls": 8,
"refused": 0,
"matched": 8,
"items": 15,
"minSpanF1": 1.0,
"maxConfidenceDifference": 0.00033
},
"classification_described": {
"calls": 24,
"refused": 0,
"matched": 24,
"items": 24,
"minSpanF1": 1.0,
"maxConfidenceDifference": 0.001187
},
"record_anchorless": {
"calls": 8,
"refused": 0,
"matched": 8,
"items": 2,
"minSpanF1": 1.0,
"maxConfidenceDifference": 0.000258
},
"structure_event": {
"calls": 24,
"refused": 0,
"matched": 24,
"items": 45,
"minSpanF1": 1.0,
"maxConfidenceDifference": 0.000897
},
"classification_multi": {
"calls": 16,
"refused": 0,
"matched": 16,
"items": 22,
"minSpanF1": 1.0,
"maxConfidenceDifference": 0.000356
},
"entities_described": {
"calls": 16,
"refused": 0,
"matched": 16,
"items": 40,
"minSpanF1": 1.0,
"maxConfidenceDifference": 0.000411
},
"structure_order": {
"calls": 8,
"refused": 0,
"matched": 8,
"items": 22,
"minSpanF1": 1.0,
"maxConfidenceDifference": 0.001252
},
"relations_event": {
"calls": 8,
"refused": 0,
"matched": 8,
"items": 15,
"minSpanF1": 1.0,
"maxConfidenceDifference": 0.0002
}
}
},
"fixtures": {
"about": "FluidInference's eleven verify-full-extraction fixtures",
"identical": 11,
"total": 11,
"rows": [
{
"case": "entities",
"structureMatch": true,
"maxConfidenceDifference": 1e-06
},
{
"case": "entities_multi",
"structureMatch": true,
"maxConfidenceDifference": 3e-06
},
{
"case": "relations",
"structureMatch": true,
"maxConfidenceDifference": 2.2e-05
},
{
"case": "relations_two",
"structureMatch": true,
"maxConfidenceDifference": 6e-06
},
{
"case": "record_natural",
"structureMatch": true,
"maxConfidenceDifference": 0.000134
},
{
"case": "record_latent",
"structureMatch": true,
"maxConfidenceDifference": 0.000352
},
{
"case": "record_anchorless",
"structureMatch": true,
"maxConfidenceDifference": null
},
{
"case": "attributes",
"structureMatch": true,
"maxConfidenceDifference": 2.8e-05
},
{
"case": "mixed_classification",
"structureMatch": true,
"maxConfidenceDifference": 1e-06
},
{
"case": "classification_only",
"structureMatch": true,
"maxConfidenceDifference": 6.4e-05
},
{
"case": "enum_choice",
"structureMatch": true,
"maxConfidenceDifference": 0.0
}
]
}
}