09b2add673
New evalharness/fingerprint/ package (from evalstone fp_fusion v1.1, 2026-09-07 pruning final): probe battery -> concurrent collection -> five scoring views (verify/attribution/variant/adversarial/robustness), bundled family aliases + 27 reference fingerprints (12 fp_fusion schema). - CLI: 'evalharness fingerprint run ...' (REMAINDER passthrough, single source of arg definitions) + 'fingerprint list' for bundled references - imports rewritten package-relative; direct 'python3 run_fp_fusion.py' execution kept working via package bootstrap - offline analysis/collection scripts made path-independent (previously pinned to a /opt/evalscope path absent on this host) - shell scripts: hardcoded API key -> FP_API_KEY/OPENAI_API_KEY env vars - --reference accepts short names resolved against bundled references/ - pyproject: +httpx dependency, package-data references/*.json - tests/test_fingerprint.py: 10 offline tests (battery definitions, assembly counts, normalization, signals, verdict ladder, CLI wiring) - README: fingerprint section + architecture entry Verified on H20-1: tests 10/10, installed CLI OK, full-protocol run vs vectron GLM-5.3 reproduces baseline (score 0.9451, s_idn 0.846).
174 lines
4.3 KiB
JSON
174 lines
4.3 KiB
JSON
{
|
|
"formatVersion": 1,
|
|
"protocol": "one-token/v1",
|
|
"model": "GLM-5.2-w4a8-p800-2",
|
|
"collectedAt": "2026-08-21T05:46:46.778Z",
|
|
"samplesPerCell": 25,
|
|
"postReasoning": false,
|
|
"cells": {
|
|
"random-number-1-100:en": {
|
|
"cellId": "random-number-1-100:en",
|
|
"counts": {
|
|
"42": 21,
|
|
"73": 4
|
|
},
|
|
"validCount": 25,
|
|
"invalidCount": 0,
|
|
"refusalCount": 0,
|
|
"emptyCount": 0,
|
|
"errorCount": 0,
|
|
"totalCount": 25,
|
|
"entropyBits": 0.6343095546405662,
|
|
"normalizedEntropy": 0.09547310124153574,
|
|
"medianLatencyMs": 439.03478600000017,
|
|
"meanCompletionTokens": 2,
|
|
"meanReasoningTokens": 0
|
|
},
|
|
"random-number-1-100:zh": {
|
|
"cellId": "random-number-1-100:zh",
|
|
"counts": {
|
|
"42": 23,
|
|
"73": 2
|
|
},
|
|
"validCount": 25,
|
|
"invalidCount": 0,
|
|
"refusalCount": 0,
|
|
"emptyCount": 0,
|
|
"errorCount": 0,
|
|
"totalCount": 25,
|
|
"entropyBits": 0.4021791902022728,
|
|
"normalizedEntropy": 0.06053399994136682,
|
|
"medianLatencyMs": 440.52718300000015,
|
|
"meanCompletionTokens": 2.24,
|
|
"meanReasoningTokens": 0
|
|
},
|
|
"random-color:en": {
|
|
"cellId": "random-color:en",
|
|
"counts": {
|
|
"blue": 11,
|
|
"cerulean": 3,
|
|
"teal": 3,
|
|
"magenta": 4,
|
|
"azure": 1,
|
|
"turquoise": 2,
|
|
"green": 1
|
|
},
|
|
"validCount": 25,
|
|
"invalidCount": 0,
|
|
"refusalCount": 0,
|
|
"emptyCount": 0,
|
|
"errorCount": 0,
|
|
"totalCount": 25,
|
|
"entropyBits": 2.3413152774012365,
|
|
"normalizedEntropy": 0.4771484572117065,
|
|
"medianLatencyMs": 463.81122400000004,
|
|
"meanCompletionTokens": 2.6,
|
|
"meanReasoningTokens": 0
|
|
},
|
|
"random-animal:en": {
|
|
"cellId": "random-animal:en",
|
|
"counts": {
|
|
"elephant": 6,
|
|
"capybara": 2,
|
|
"platypus": 4,
|
|
"hippopotamus": 6,
|
|
"giraffe": 3,
|
|
"tiger": 2,
|
|
"pangolin": 1,
|
|
"axolotl": 1
|
|
},
|
|
"validCount": 25,
|
|
"invalidCount": 0,
|
|
"refusalCount": 0,
|
|
"emptyCount": 0,
|
|
"errorCount": 0,
|
|
"totalCount": 25,
|
|
"entropyBits": 2.7328786893420305,
|
|
"normalizedEntropy": 0.4842218861446776,
|
|
"medianLatencyMs": 747.7474070000007,
|
|
"meanCompletionTokens": 4.12,
|
|
"meanReasoningTokens": 0
|
|
},
|
|
"random-number-1-10:en": {
|
|
"cellId": "random-number-1-10:en",
|
|
"counts": {
|
|
"7": 25
|
|
},
|
|
"validCount": 25,
|
|
"invalidCount": 0,
|
|
"refusalCount": 0,
|
|
"emptyCount": 0,
|
|
"errorCount": 0,
|
|
"totalCount": 25,
|
|
"entropyBits": 0,
|
|
"normalizedEntropy": 0,
|
|
"medianLatencyMs": 439.4792090000001,
|
|
"meanCompletionTokens": 2,
|
|
"meanReasoningTokens": 0
|
|
},
|
|
"random-letter:en": {
|
|
"cellId": "random-letter:en",
|
|
"counts": {
|
|
"q": 14,
|
|
"k": 9,
|
|
"j": 1,
|
|
"r": 1
|
|
},
|
|
"validCount": 25,
|
|
"invalidCount": 0,
|
|
"refusalCount": 0,
|
|
"emptyCount": 0,
|
|
"errorCount": 0,
|
|
"totalCount": 25,
|
|
"entropyBits": 1.3705644329032338,
|
|
"normalizedEntropy": 0.2915821742407662,
|
|
"medianLatencyMs": 438.21875999999975,
|
|
"meanCompletionTokens": 2,
|
|
"meanReasoningTokens": 0
|
|
},
|
|
"random-color:zh": {
|
|
"cellId": "random-color:zh",
|
|
"counts": {
|
|
"紫": 2,
|
|
"红": 7,
|
|
"蔚蓝": 1,
|
|
"蓝": 13,
|
|
"靛": 1,
|
|
"青": 1
|
|
},
|
|
"validCount": 25,
|
|
"invalidCount": 0,
|
|
"refusalCount": 0,
|
|
"emptyCount": 0,
|
|
"errorCount": 0,
|
|
"totalCount": 25,
|
|
"entropyBits": 1.8535681581652277,
|
|
"normalizedEntropy": 0.37774801007874537,
|
|
"medianLatencyMs": 439.9340409999995,
|
|
"meanCompletionTokens": 2.12,
|
|
"meanReasoningTokens": 0
|
|
},
|
|
"coin-flip:en": {
|
|
"cellId": "coin-flip:en",
|
|
"counts": {
|
|
"heads": 24,
|
|
"tails": 1
|
|
},
|
|
"validCount": 25,
|
|
"invalidCount": 0,
|
|
"refusalCount": 0,
|
|
"emptyCount": 0,
|
|
"errorCount": 0,
|
|
"totalCount": 25,
|
|
"entropyBits": 0.24229218908241482,
|
|
"normalizedEntropy": 0.24229218908241482,
|
|
"medianLatencyMs": 488.98918400000184,
|
|
"meanCompletionTokens": 2.8,
|
|
"meanReasoningTokens": 0
|
|
}
|
|
},
|
|
"meta": {
|
|
"tool": "llm-fingerprint-detector"
|
|
}
|
|
}
|