← Back to Reliability Explorer
Measured selection evidence
DeepWiki MCP
deepwiki-mcp
Measured historical tool-selection reliability from frozen benchmark evidence.
Multi-batchS2-backedObserved missesMixed provenance
Mixed live and version-bound evidence. Historical evidence does not establish current endpoint availability or current production behavior.
6independent benchmark batches
52measured frozen cases
S1, S2evidence level(s)
5observed semantic misses
First measurement: 2026-09-10 13:23:12.077611 UTC · Last measurement: 2026-09-10 19:13:49.842728 UTC · Observed strict accuracy range: 57.1%–100.0%
Batch history
Each immutable benchmark batch is shown separately. No pooled accuracy is calculated here.
| Benchmark / batch | Type | Frozen cases | Strict score | Wilson 95% CI | Provider-valid coverage | Infrastructure failures | Evidence / measured |
|---|---|---|---|---|---|---|---|
selection-evidence-expansion-v1selection-evidence-expansion-v1 |
CONSTRUCTED_FROZEN_SELECTION_BENCHMARK | 24 | 24/24 100.0% |
Not recorded–Not recorded | 24 / 24 (100.0%) | 0 | S1 2026-09-10 13:23:12.077611 UTC |
external-gold-expansion-v2-batch1external-gold-expansion-v2-batch1 |
EXTERNAL_INDEPENDENT_GOLD_BENCHMARK | 4 | 3/4 75.0% |
30.1%–95.4% | 4 / 4 (100.0%) | 0 | S2 2026-09-10 15:38:03.968297 UTC |
external-gold-expansion-v2-batch2external-gold-expansion-v2-batch2 |
EXTERNAL_INDEPENDENT_GOLD_BENCHMARK | 5 | 5/5 100.0% |
56.6%–100.0% | 5 / 5 (100.0%) | 0 | S2 2026-09-10 16:49:53.346446 UTC |
external-gold-expansion-v2-batch3external-gold-expansion-v2-batch3 |
EXTERNAL_INDEPENDENT_GOLD_BENCHMARK | 6 | 6/6 100.0% |
61.0%–100.0% | 6 / 6 (100.0%) | 0 | S2 2026-09-10 17:45:38.245198 UTC |
external-gold-expansion-v2-batch4external-gold-expansion-v2-batch4 |
EXTERNAL_INDEPENDENT_GOLD_BENCHMARK | 6 | 5/6 83.3% |
43.6%–97.0% | 6 / 6 (100.0%) | 0 | S2 2026-09-10 18:47:01.455700 UTC |
external-gold-expansion-v2-batch5external-gold-expansion-v2-batch5 |
EXTERNAL_INDEPENDENT_GOLD_BENCHMARK | 7 | 4/7 57.1% |
25.0%–84.2% | 7 / 7 (100.0%) | 0 | S2 2026-09-10 19:13:49.842728 UTC |
Observed semantic misses
These are preserved adjudicated historical observations, attributable to a benchmark, batch, and case.
| Benchmark / batch | Case ID | Expected tool | Selected tool | Boundary family | Adjudication |
|---|---|---|---|---|---|
external-gold-expansion-v2-batch1external-gold-expansion-v2-batch1 |
deepwiki-004 | ask_question |
read_wiki_structure | NOT_RECORDED_IN_SOURCE_EVIDENCE | SEMANTIC_MISS |
external-gold-expansion-v2-batch4external-gold-expansion-v2-batch4 |
b4-dw-005 | read_wiki_contents |
read_wiki_structure | CONTENTS_VS_QUESTION | VALID_GOLD_RETAINED |
external-gold-expansion-v2-batch5external-gold-expansion-v2-batch5 |
b5-dw-003 | read_wiki_contents |
read_wiki_structure | CONTENTS_VS_QUESTION | VALID_GOLD_RETAINED |
external-gold-expansion-v2-batch5external-gold-expansion-v2-batch5 |
b5-dw-004 | ask_question |
read_wiki_contents | QUESTION_VS_CONTENTS | VALID_GOLD_RETAINED |
external-gold-expansion-v2-batch5external-gold-expansion-v2-batch5 |
b5-dw-006 | read_wiki_contents |
read_wiki_structure | CONTENTS_VS_STRUCTURE | VALID_GOLD_RETAINED |
Evidence provenance
Technical identities are secondary detail for auditability.
DeepWiki MCP
- Canonical subject ID
deepwiki-mcp- Provenance type
- CONSTRUCTED_FROZEN_SELECTION_BENCHMARK
- Identity mode
- LIVE_TOOLS_LIST_SNAPSHOT
- Identity source
LIVE_TOOLS_LIST
DeepWiki
- Canonical subject ID
deepwiki-mcp- Provenance type
- EXTERNAL_INDEPENDENT_GOLD_BENCHMARK
- Identity mode
- LIVE_TOOLS_LIST_SNAPSHOT
- Identity source
CURRENT_LIVE_TOOLS_LIST_INHERITED_V1_AND_FROZEN_BY_COPY
DeepWiki
- Canonical subject ID
deepwiki-mcp- Provenance type
- EXTERNAL_INDEPENDENT_GOLD_BENCHMARK
- Identity mode
- LIVE_TOOLS_LIST_SNAPSHOT
- Identity source
CURRENT_LIVE_TOOLS_LIST_FROZEN_BY_EXISTING_IMMUTABLE_SNAPSHOT
DeepWiki
- Canonical subject ID
deepwiki-mcp- Provenance type
- EXTERNAL_INDEPENDENT_GOLD_BENCHMARK
- Identity mode
- VERSION_BOUND_SNAPSHOT
- Identity source
CURRENT_OR_VERSION_BOUND_SNAPSHOT_REUSED_FROM_QUALIFIED_CORPUS
selection-evidence-expansion-v1 immutable identities
- case_freeze_sha256
5d248e845fc1b52ef53585682a97a592fecd0d3c1b8c9e561c758a4222273aed- freeze_commit_sha
d2937086b419ba0bf77517da772540de1975c45f- measurement_artifact_sha256
27f281b49b50fe5218102274c57db0110f3119091ca5dd53ebe954997f4fe826- model_lock_sha256
a8df78457b76e0dea73f66e2a75907feab3c42885db23658caada6973c5cb478- promotion_policy_sha256
6714ca504b2c5679c0f1ba0c7da2e5ee52f61b70b0e814ecaf9071f080f9f61d
external-gold-expansion-v2-batch1 immutable identities
- case_freeze_sha256
17777d2c3983cd444353b8d69dcc98836a1909ee6fde6f5c8cf18cf9b059427e- final_freeze_receipt_commit
b691170- freeze_input_commit
c614ae51750d12ce113b5e3d51429f52e529f08c- measurement_artifact_sha256
01243422aa946296f235810aaee6f065ec21d9e78a01017ee8161e5e61a8b5e8- measurement_commit
b9f358b1a65aba348fa1c0e625eac6da1f31b651- model_lock_sha256
c4330165deb3d8587e224a2ca1b3d886db60801ca436710a0edace55525923d2- policy_evaluation_commit
3e560e5767f181831c65569b893ca789cd3bdff0- policy_evaluation_sha256
4e710a9c5205660cc07603d2fd7538aa063eda4c2574c29308f9f255e4706f82- promotion_policy_sha256
6714ca504b2c5679c0f1ba0c7da2e5ee52f61b70b0e814ecaf9071f080f9f61d- raw_predictions_sha256
ab085cedf13eef5724f4e160b0f49f8402d62bc5b10203de0f8d81e41f2a017e
external-gold-expansion-v2-batch2 immutable identities
- case_freeze_sha256
ce21fc085bd9a0185c9e37d0d795221f286397cbc477ee941e876be24f7ba1b4- final_freeze_receipt_commit
d3c55d2f96a4e45bf2577225ea16929877f2ded1- freeze_input_commit
61f6511c41562c24019cd441b37bc6ee07283951- measurement_artifact_sha256
dd13aec8a90b2b5490c934c9ad9650c37733c65f18d824e2ae6066202176ced9- measurement_commit
f0b6cd33be044d8bad800c20b4f2684e6d8431ce- model_lock_sha256
153647f94eed0ee3d3069229545846eef864fd43fa821f2d311dc3fb5d265ba9- policy_evaluation_commit
f0b6cd33be044d8bad800c20b4f2684e6d8431ce- policy_evaluation_sha256
736f154a5d5c3b8f0d77cd58fa0644ca97ad94c7a6b46af98d394c1dc1578f9a- promotion_policy_sha256
6714ca504b2c5679c0f1ba0c7da2e5ee52f61b70b0e814ecaf9071f080f9f61d- raw_predictions_sha256
8c4364ab598241ddbe4adb16453ba2e12b0917a1d1852caedb07884d1a54570b
external-gold-expansion-v2-batch3 immutable identities
- case_freeze_sha256
c1595743f48fe8ae6b3f70f2ea401731052b3bd7614297feabaa8172ce190ae5- final_freeze_receipt_commit
a309bda7e8dd2867ccc7894dc7d42efbfc48395e- freeze_input_commit
8450ed889756784a12ca4ebb8d84974d73b31778- immutable_measurement_receipt_commit
9d8290160849a5124d1896fc318d53470585ef41- measurement_artifact_sha256
7dcab9d4b71e7de59094c07cbca830ebf674b601ac6de024db0d3e677e7c0067- measurement_commit
b81cc816158f7c0fbe7f8ac0a6fcf2b3f38f4c86- model_lock_sha256
48b5ed9c98f16cc2b3b76bc0da2e7ec8072ecd89ba1914683181b1c20074a3a8- policy_evaluation_sha256
3ea5b62044b4da6e92812831ebb00205970849accffe763a270248a24a0adef4- promotion_policy_sha256
6714ca504b2c5679c0f1ba0c7da2e5ee52f61b70b0e814ecaf9071f080f9f61d- raw_predictions_sha256
c5cfe765f6b72489220cc73f689acb1c1c2c9284ffd8d093de0e597b645f6fbf
external-gold-expansion-v2-batch4 immutable identities
- case_freeze_sha256
a9513c1cb9b800b75d822d75fa8c6e47041e551d86a75699f1858b6c3785204d- final_freeze_receipt_commit
224aeab80db539383018d77cc7adb849976f1db5- freeze_input_commit
003985017fbd8c1e207fb146329b97b38582e606- immutable_measurement_receipt_sha256
7d6d0a1ac4b1d501aa4c5d0044b4a4e50bb319b272bd33eb783aec6499d594c6- measurement_artifact_commit
9b10dc0c99c4eed15a3d370743e8f46439302bae- measurement_artifact_sha256
7d9a5f57e0897f2ca8b2734ac0f38dc5afd099b2edf2495dbfa25e41f088cee9- model_lock_sha256
ffc1ec351c1a62c3692cdaedba0c5a6ec2c6285923eb065e0cd31953f978e3a1- policy_evaluation_sha256
0e9b11360db41731ce139584060b3f1417ce50b31dcf86ef88180e391e56e0d5- promotion_policy_sha256
6714ca504b2c5679c0f1ba0c7da2e5ee52f61b70b0e814ecaf9071f080f9f61d- raw_predictions_sha256
869812a69814f58e73a1c6c3f94a28b6dabc2cdb729285d3a532dd528ad36c89- scanner_freeze_sha256
e31caf3131b4e03f54ff411a386bb72ac70c35fbe9027e3383b7026019c22ae1
external-gold-expansion-v2-batch5 immutable identities
- case_freeze_sha256
40847d041af701492505676ae027f824248a94dba8dad19c4c764baec224a2bc- final_freeze_receipt_commit
4c11daed10b52027a8a31130703335e4835873ec- freeze_input_commit
935e16c4cc073d72b1c64c48206196feaf28c170- immutable_measurement_receipt_commit
b064dea6a0ea488826d11fc0fc88c5b4de3d5c26- measurement_artifact_commit
87a78aba4797f79f3c99c22e202eddd1da70f034- measurement_artifact_sha256
9b5f0c7f94783f2b25d28d8ecdaebe3a5a11b9db00dd84f677f95ac008f32eeb- model_lock_sha256
60c5653e461180e44e9621a54bb77f3f474e6889ddc29d1ff30d3cb9398013fa- policy_evaluation_sha256
2ef31f2a44a722fb862425dc11755b118c3ffb712672471d10d4cd0bbcee9af1- promotion_policy_sha256
6714ca504b2c5679c0f1ba0c7da2e5ee52f61b70b0e814ecaf9071f080f9f61d- raw_predictions_sha256
612c995839a9ad1a32d87320055ada3201c511b626a0f3e8778a8bbe5201bc68- scanner_freeze_sha256
80b3b0d60a5ec2e3b5019d2c45838dd06517453ce64c9a32ed0dbda6be718795- validation_criteria_sha256
0cd5821683b9f85ae37140bfc73d25064012d69aabbbbb4363e56b058cb240a6