sable-sphynx 0.7.0.dev0__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (174) hide show
  1. sable_sphynx-0.7.0.dev0.dist-info/METADATA +152 -0
  2. sable_sphynx-0.7.0.dev0.dist-info/RECORD +174 -0
  3. sable_sphynx-0.7.0.dev0.dist-info/WHEEL +5 -0
  4. sable_sphynx-0.7.0.dev0.dist-info/top_level.txt +1 -0
  5. sphynx/__init__.py +469 -0
  6. sphynx/__init__.pyi +376 -0
  7. sphynx/_analytical_client.py +77 -0
  8. sphynx/_analytical_values.py +252 -0
  9. sphynx/_audit_client.py +173 -0
  10. sphynx/_comparison_adapters.py +113 -0
  11. sphynx/_componentized_full_rag.py +34 -0
  12. sphynx/_composed_pipeline.py +109 -0
  13. sphynx/_full_rag_grading.py +218 -0
  14. sphynx/_full_rag_trace.py +221 -0
  15. sphynx/_local_eval.py +268 -0
  16. sphynx/_pipeline_core.py +243 -0
  17. sphynx/_pr_client.py +237 -0
  18. sphynx/_rag_diagnostics_calibration.py +285 -0
  19. sphynx/_rag_diagnostics_catalog.py +39 -0
  20. sphynx/_rag_diagnostics_common.py +26 -0
  21. sphynx/_rag_diagnostics_contracts.py +186 -0
  22. sphynx/_rag_diagnostics_engine.py +243 -0
  23. sphynx/_rag_diagnostics_importers.py +242 -0
  24. sphynx/_rag_diagnostics_ranking.py +81 -0
  25. sphynx/_rag_diagnostics_semantic.py +325 -0
  26. sphynx/_rag_ranking.py +149 -0
  27. sphynx/_speech_benchmark_scoring.py +140 -0
  28. sphynx/_speech_benchmark_sources.py +275 -0
  29. sphynx/_speech_complete_scoring.py +218 -0
  30. sphynx/_speech_complete_source.py +118 -0
  31. sphynx/_speech_kido.py +294 -0
  32. sphynx/_speech_scoring.py +77 -0
  33. sphynx/_track_capture.py +213 -0
  34. sphynx/analytical_views.py +515 -0
  35. sphynx/assessment_contracts.py +378 -0
  36. sphynx/assessment_selection.py +57 -0
  37. sphynx/audit_access.py +245 -0
  38. sphynx/audit_contracts.py +204 -0
  39. sphynx/audit_requests.py +180 -0
  40. sphynx/authoring.py +188 -0
  41. sphynx/benchmarks.py +568 -0
  42. sphynx/candidates.py +62 -0
  43. sphynx/catalog.py +272 -0
  44. sphynx/chunking.py +372 -0
  45. sphynx/clickhouse_reader.py +169 -0
  46. sphynx/client.py +486 -0
  47. sphynx/comparison_core.py +149 -0
  48. sphynx/comparison_views.py +223 -0
  49. sphynx/components.py +1661 -0
  50. sphynx/contracts.py +514 -0
  51. sphynx/customer_rerank.py +299 -0
  52. sphynx/customer_retrieval.py +146 -0
  53. sphynx/data/benchmark-releases.v1.json +164 -0
  54. sphynx/data/public-benchmark-release.v1.json +354 -0
  55. sphynx/data/rag-diagnostics-synthetic.v1.json +6982 -0
  56. sphynx/data/rag-paper-references.v1.json +176 -0
  57. sphynx/data/rag-paper-schemas.v1.json +1069 -0
  58. sphynx/data/rag-rerank-v1.json +507 -0
  59. sphynx/dataset_catalog_data.py +1214 -0
  60. sphynx/dataset_readiness.py +138 -0
  61. sphynx/dataset_v3.py +999 -0
  62. sphynx/demo.py +130 -0
  63. sphynx/demo_candidates/__init__.py +1 -0
  64. sphynx/demo_candidates/dense.py +11 -0
  65. sphynx/demo_candidates/lexical.py +21 -0
  66. sphynx/diagnostics.py +207 -0
  67. sphynx/documentation.py +737 -0
  68. sphynx/documentation_candidate.py +939 -0
  69. sphynx/evals.py +538 -0
  70. sphynx/evaluation_protocols.py +124 -0
  71. sphynx/evaluator_bindings.py +370 -0
  72. sphynx/evidence.py +352 -0
  73. sphynx/execution_capabilities.py +109 -0
  74. sphynx/fast_search.py +285 -0
  75. sphynx/full_rag.py +341 -0
  76. sphynx/hosted/__init__.py +18 -0
  77. sphynx/hosted/benchmark_intake.py +218 -0
  78. sphynx/hosted/contracts.py +361 -0
  79. sphynx/hosted/model_admission.py +130 -0
  80. sphynx/hosted/model_artifacts.py +298 -0
  81. sphynx/hosted/model_contracts.py +63 -0
  82. sphynx/hosted/model_gcs.py +181 -0
  83. sphynx/hosted/model_history.py +84 -0
  84. sphynx/hosted/model_session.py +233 -0
  85. sphynx/hosted/public_suite.py +74 -0
  86. sphynx/hosted/registry.py +97 -0
  87. sphynx/hosted/revisions.py +126 -0
  88. sphynx/hosted/sandbox.py +105 -0
  89. sphynx/hosted/submission.py +287 -0
  90. sphynx/hosted_workflow.py +451 -0
  91. sphynx/http_transport.py +86 -0
  92. sphynx/integrated_rag.py +352 -0
  93. sphynx/integrated_workflow.py +552 -0
  94. sphynx/integration_contracts.py +474 -0
  95. sphynx/invocation.py +791 -0
  96. sphynx/invocation_candidates.py +392 -0
  97. sphynx/invocation_catalog_data.py +40 -0
  98. sphynx/learned_catalog_data.py +30 -0
  99. sphynx/learned_rerank.py +267 -0
  100. sphynx/legacy_full_rag.py +67 -0
  101. sphynx/lifecycle.py +885 -0
  102. sphynx/lifecycle_workflow.py +490 -0
  103. sphynx/metric_views.py +474 -0
  104. sphynx/metrics.py +282 -0
  105. sphynx/model_adapters.py +438 -0
  106. sphynx/model_catalog_data.py +30 -0
  107. sphynx/official_benchmarks.py +385 -0
  108. sphynx/packs.py +258 -0
  109. sphynx/pipeline.py +313 -0
  110. sphynx/pipeline_workflow.py +551 -0
  111. sphynx/pr_evaluations.py +560 -0
  112. sphynx/progress.py +89 -0
  113. sphynx/public_bundle.py +173 -0
  114. sphynx/public_eval.py +62 -0
  115. sphynx/public_rerank.py +355 -0
  116. sphynx/py.typed +0 -0
  117. sphynx/pytest_plugin.py +62 -0
  118. sphynx/question_robustness.py +437 -0
  119. sphynx/rag.py +329 -0
  120. sphynx/rag_diagnostics.py +309 -0
  121. sphynx/rag_papers/__init__.py +29 -0
  122. sphynx/rag_papers/__main__.py +45 -0
  123. sphynx/rag_papers/candidates.py +19 -0
  124. sphynx/rag_papers/contracts.py +282 -0
  125. sphynx/rag_papers/datasets.py +291 -0
  126. sphynx/rag_papers/experiments.py +116 -0
  127. sphynx/rag_papers/judges.py +308 -0
  128. sphynx/rag_papers/registry.py +33 -0
  129. sphynx/rag_papers/runner.py +176 -0
  130. sphynx/rag_papers/sable.py +135 -0
  131. sphynx/rag_papers/schemas.py +12 -0
  132. sphynx/rag_papers/scoring.py +249 -0
  133. sphynx/rag_papers/semantic.py +288 -0
  134. sphynx/rag_papers/trec.py +80 -0
  135. sphynx/recorded_scores.py +352 -0
  136. sphynx/records.py +124 -0
  137. sphynx/reflex_traces.py +193 -0
  138. sphynx/report_rendering.py +71 -0
  139. sphynx/rerank_family_contracts.py +150 -0
  140. sphynx/rerank_workflow.py +424 -0
  141. sphynx/research_candidate.py +190 -0
  142. sphynx/results.py +852 -0
  143. sphynx/retrieval.py +750 -0
  144. sphynx/retrieval_candidates.py +295 -0
  145. sphynx/retrieval_catalog_data.py +19 -0
  146. sphynx/retrieval_recordings.py +125 -0
  147. sphynx/reviewer_audit.py +266 -0
  148. sphynx/routing_policies.py +375 -0
  149. sphynx/runner.py +544 -0
  150. sphynx/sable_rerank.py +489 -0
  151. sphynx/score_reliability.py +393 -0
  152. sphynx/speech_benchmarks.py +204 -0
  153. sphynx/speech_campaigns.py +378 -0
  154. sphynx/speech_complete.py +236 -0
  155. sphynx/speech_contracts.py +225 -0
  156. sphynx/speech_evidence.py +429 -0
  157. sphynx/speech_listening.py +115 -0
  158. sphynx/speech_multilingual.py +71 -0
  159. sphynx/speech_tts.py +479 -0
  160. sphynx/sql/001_sync_v1.sql +30 -0
  161. sphynx/stage_contracts.py +199 -0
  162. sphynx/statistical_catalog_data.py +53 -0
  163. sphynx/statistical_rerank.py +232 -0
  164. sphynx/sync.py +797 -0
  165. sphynx/workbench.py +378 -0
  166. sphynx/workbench_catalog_data.py +13 -0
  167. sphynx/workbench_tracks.py +78 -0
  168. sphynx/workflow_async.py +197 -0
  169. sphynx/workflow_contracts.py +594 -0
  170. sphynx/workflow_decisions.py +211 -0
  171. sphynx/workflow_defaults.py +16 -0
  172. sphynx/workflow_extensions.py +212 -0
  173. sphynx/workflow_registry.py +513 -0
  174. sphynx/workflows.py +792 -0
@@ -0,0 +1,1214 @@
1
+ """Audited content-free release metadata; readiness never grants data authorization."""
2
+ from .catalog import DatasetDescriptor
3
+
4
+ _DATA = [{'dataset_id': 'synthetic.rerank.v1',
5
+ 'pack_id': 'rag.rerank.v1',
6
+ 'release': 'v1',
7
+ 'track': 'rag_rerank',
8
+ 'dataset_schema_version': 'rag-evals.dataset.v2',
9
+ 'source_digest': 'sha256:74884a0176738649d85cc8b681323103961939aaa0f3d5f1dd1565ed2e53d86b',
10
+ 'reference_digest': 'sha256:74884a0176738649d85cc8b681323103961939aaa0f3d5f1dd1565ed2e53d86b',
11
+ 'population': 'synthetic',
12
+ 'split': 'dev-and-test',
13
+ 'case_count': 6,
14
+ 'relevance_threshold': 2.0,
15
+ 'review_status': 'illustrative_synthetic',
16
+ 'state': 'ready',
17
+ 'reason': None,
18
+ 'source_case_count': None,
19
+ 'candidate_depth': None,
20
+ 'first_stage': None,
21
+ 'family_status': 'unknown',
22
+ 'family_digest': None,
23
+ 'repeated_question_status': 'unknown',
24
+ 'relationships': [],
25
+ 'authorization_requirements': [],
26
+ 'local_prerequisites': [],
27
+ 'implementation_status': 'available',
28
+ 'previously_exercised': None,
29
+ 'superseded_by': [],
30
+ 'schema_version': 'sphynx.dataset-descriptor.v1'},
31
+ {'dataset_id': 'sable.mc1.rerank.v1',
32
+ 'pack_id': 'rag.rerank.sable.dev.v1',
33
+ 'release': 'v1.external',
34
+ 'track': 'rag_rerank',
35
+ 'dataset_schema_version': 'rag-evals.dataset.v2',
36
+ 'source_digest': 'sha256:9b4a756e43714c98a9a3625a2fad7fc48e4a81210a474f52a1805e8abdb8a154',
37
+ 'reference_digest': 'sha256:9b4a756e43714c98a9a3625a2fad7fc48e4a81210a474f52a1805e8abdb8a154',
38
+ 'population': 'five_customer_development',
39
+ 'split': 'development',
40
+ 'case_count': 82,
41
+ 'relevance_threshold': 2.0,
42
+ 'review_status': 'owner_development_labels',
43
+ 'state': 'ready',
44
+ 'reason': None,
45
+ 'source_case_count': 100,
46
+ 'candidate_depth': None,
47
+ 'first_stage': None,
48
+ 'family_status': 'unknown',
49
+ 'family_digest': None,
50
+ 'repeated_question_status': 'unknown',
51
+ 'relationships': [],
52
+ 'authorization_requirements': ['Owner authorization for customer corpus and labels.'],
53
+ 'local_prerequisites': ['Exact owner-held mc1 dataset; 18 upstream misses excluded from this rerank '
54
+ 'cohort.'],
55
+ 'implementation_status': 'available',
56
+ 'previously_exercised': True,
57
+ 'superseded_by': [],
58
+ 'schema_version': 'sphynx.dataset-descriptor.v1'},
59
+ {'dataset_id': 'sable.hybrid100.retrieve.v1',
60
+ 'pack_id': 'rag.retrieve.v1',
61
+ 'release': 'v1.external',
62
+ 'track': 'rag_retrieve',
63
+ 'dataset_schema_version': 'sphynx.rag.retrieve.dataset.v1',
64
+ 'source_digest': 'sha256:fafb5784f4d25f5e164ce377120ef1a23836a7837246aa2153dc025a5eb8c557',
65
+ 'reference_digest': 'sha256:fafb5784f4d25f5e164ce377120ef1a23836a7837246aa2153dc025a5eb8c557',
66
+ 'population': 'five_customer_development',
67
+ 'split': 'development',
68
+ 'case_count': 100,
69
+ 'relevance_threshold': None,
70
+ 'review_status': 'owner_development_labels',
71
+ 'state': 'ready',
72
+ 'reason': None,
73
+ 'source_case_count': None,
74
+ 'candidate_depth': None,
75
+ 'first_stage': None,
76
+ 'family_status': 'unknown',
77
+ 'family_digest': None,
78
+ 'repeated_question_status': 'unknown',
79
+ 'relationships': [{'dataset_id': 'sable.mc1.rerank.v1',
80
+ 'kind': 'shared_source',
81
+ 'case_count': 82,
82
+ 'family_digest': None}],
83
+ 'authorization_requirements': ['Owner authorization for customer corpus and labels.'],
84
+ 'local_prerequisites': ['Exact owner-held full 100-case retrieval dataset with 1655 chunks.'],
85
+ 'implementation_status': 'available',
86
+ 'previously_exercised': True,
87
+ 'superseded_by': [],
88
+ 'schema_version': 'sphynx.dataset-descriptor.v1'},
89
+ {'dataset_id': 'invocation.excerpt-free-200',
90
+ 'pack_id': 'rag.invoke.v1',
91
+ 'release': 'v1-development-200',
92
+ 'track': 'rag_invoke',
93
+ 'dataset_schema_version': 'sphynx.jev-hybrid-safe200.v1',
94
+ 'source_digest': 'sha256:7316862d37a7185ed7c995278a5d5f9ae34ff0ae05afe5c4d281e2c00303d2bf',
95
+ 'reference_digest': 'sha256:ee66b8193deceb4c82f5fe87a4344278b94cca9436724e4b2bc7d1b1f51dedef',
96
+ 'population': 'authored_development',
97
+ 'split': 'development',
98
+ 'case_count': 200,
99
+ 'relevance_threshold': None,
100
+ 'review_status': 'authored_local_audit_pending',
101
+ 'state': 'ready',
102
+ 'reason': None,
103
+ 'source_case_count': 200,
104
+ 'candidate_depth': None,
105
+ 'first_stage': None,
106
+ 'family_status': 'known',
107
+ 'family_digest': 'sha256:17d1ac6cfb8db0f78ddeb714c70f042a84b8c299b24b0ecd67fadf42c413dab1',
108
+ 'repeated_question_status': 'known',
109
+ 'relationships': [{'dataset_id': 'invocation.development-300',
110
+ 'kind': 'subset_of',
111
+ 'case_count': 200,
112
+ 'family_digest': None},
113
+ {'dataset_id': 'invocation.development-300',
114
+ 'kind': 'repeated_question',
115
+ 'case_count': 200,
116
+ 'family_digest': None},
117
+ {'dataset_id': 'invocation.six-customer.v1-20260918',
118
+ 'kind': 'repeated_question',
119
+ 'case_count': 198,
120
+ 'family_digest': None},
121
+ {'dataset_id': 'invocation.six-customer.v1-20260918-r2',
122
+ 'kind': 'repeated_question',
123
+ 'case_count': 198,
124
+ 'family_digest': None},
125
+ {'dataset_id': 'invocation.six-customer.v1-20260918-r3',
126
+ 'kind': 'repeated_question',
127
+ 'case_count': 200,
128
+ 'family_digest': None},
129
+ {'dataset_id': 'invocation.development-300',
130
+ 'kind': 'shared_family',
131
+ 'case_count': 200,
132
+ 'family_digest': 'sha256:06b194d2ce25b12c1a29ed6256689baafa09247137ca2db3948528f7b8b35445'},
133
+ {'dataset_id': 'invocation.six-customer.v1-20260918',
134
+ 'kind': 'shared_family',
135
+ 'case_count': 198,
136
+ 'family_digest': 'sha256:a5ef5d820c4682092c7c0ab5c69011b771f129b34ba5c591d5d4cdc27860020a'},
137
+ {'dataset_id': 'invocation.six-customer.v1-20260918-r2',
138
+ 'kind': 'shared_family',
139
+ 'case_count': 198,
140
+ 'family_digest': 'sha256:a5ef5d820c4682092c7c0ab5c69011b771f129b34ba5c591d5d4cdc27860020a'},
141
+ {'dataset_id': 'invocation.six-customer.v1-20260918-r3',
142
+ 'kind': 'shared_family',
143
+ 'case_count': 200,
144
+ 'family_digest': 'sha256:06b194d2ce25b12c1a29ed6256689baafa09247137ca2db3948528f7b8b35445'}],
145
+ 'authorization_requirements': ['Owner authorization for routing inputs and gold labels.'],
146
+ 'local_prerequisites': ['Pinned bank directory and retained source/reference bytes.'],
147
+ 'implementation_status': 'available',
148
+ 'previously_exercised': True,
149
+ 'superseded_by': [],
150
+ 'schema_version': 'sphynx.dataset-descriptor.v1'},
151
+ {'dataset_id': 'invocation.development-300',
152
+ 'pack_id': 'rag.invoke.v1',
153
+ 'release': 'v1-20260918-r3-five-customer',
154
+ 'track': 'rag_invoke',
155
+ 'dataset_schema_version': 'sable.invocation-question-corpus.v1',
156
+ 'source_digest': 'sha256:80336bade48c6bc1acadbae8c66e321d68008e0ee6d2d18fd473e56d566319a6',
157
+ 'reference_digest': 'sha256:b886cc3cb572249018e94656ceeff796c576dc7bc5162b30e90d9ed039a02472',
158
+ 'population': 'authored_development',
159
+ 'split': 'development',
160
+ 'case_count': 300,
161
+ 'relevance_threshold': None,
162
+ 'review_status': 'authored_local_audit_pending',
163
+ 'state': 'ready',
164
+ 'reason': None,
165
+ 'source_case_count': 360,
166
+ 'candidate_depth': None,
167
+ 'first_stage': None,
168
+ 'family_status': 'known',
169
+ 'family_digest': 'sha256:9c4b7ab48b94b9177b888ce7497ffa9b6bdf484335b5cae2ad4b2bf666fa86d5',
170
+ 'repeated_question_status': 'known',
171
+ 'relationships': [{'dataset_id': 'invocation.excerpt-free-200',
172
+ 'kind': 'repeated_question',
173
+ 'case_count': 200,
174
+ 'family_digest': None},
175
+ {'dataset_id': 'invocation.six-customer.v1-20260918',
176
+ 'kind': 'repeated_question',
177
+ 'case_count': 198,
178
+ 'family_digest': None},
179
+ {'dataset_id': 'invocation.six-customer.v1-20260918-r2',
180
+ 'kind': 'repeated_question',
181
+ 'case_count': 297,
182
+ 'family_digest': None},
183
+ {'dataset_id': 'invocation.six-customer.v1-20260918-r3',
184
+ 'kind': 'repeated_question',
185
+ 'case_count': 300,
186
+ 'family_digest': None},
187
+ {'dataset_id': 'invocation.excerpt-free-200',
188
+ 'kind': 'shared_family',
189
+ 'case_count': 300,
190
+ 'family_digest': 'sha256:06b194d2ce25b12c1a29ed6256689baafa09247137ca2db3948528f7b8b35445'},
191
+ {'dataset_id': 'invocation.six-customer.v1-20260918',
192
+ 'kind': 'shared_family',
193
+ 'case_count': 297,
194
+ 'family_digest': 'sha256:a5ef5d820c4682092c7c0ab5c69011b771f129b34ba5c591d5d4cdc27860020a'},
195
+ {'dataset_id': 'invocation.six-customer.v1-20260918-r2',
196
+ 'kind': 'shared_family',
197
+ 'case_count': 297,
198
+ 'family_digest': 'sha256:a5ef5d820c4682092c7c0ab5c69011b771f129b34ba5c591d5d4cdc27860020a'},
199
+ {'dataset_id': 'invocation.six-customer.v1-20260918-r3',
200
+ 'kind': 'shared_family',
201
+ 'case_count': 300,
202
+ 'family_digest': 'sha256:06b194d2ce25b12c1a29ed6256689baafa09247137ca2db3948528f7b8b35445'}],
203
+ 'authorization_requirements': ['Owner authorization for routing inputs and gold labels.'],
204
+ 'local_prerequisites': ['Pinned bank directory and retained source/reference bytes.'],
205
+ 'implementation_status': 'available',
206
+ 'previously_exercised': True,
207
+ 'superseded_by': [],
208
+ 'schema_version': 'sphynx.dataset-descriptor.v1'},
209
+ {'dataset_id': 'invocation.narrow-policy-90',
210
+ 'pack_id': 'rag.invoke.v1',
211
+ 'release': 'v1-20260925',
212
+ 'track': 'rag_invoke',
213
+ 'dataset_schema_version': 'sphynx.invocation-holdout.v1',
214
+ 'source_digest': 'sha256:ecde7c3141fa8b508386e5b59468296acba55e14aa4f64e1e2f8143de977878e',
215
+ 'reference_digest': 'sha256:01430c66f73a58562834c7521186bace303d8a2ecc52e46a96da64e93cd769a9',
216
+ 'population': 'previously_exercised_regression',
217
+ 'split': 'regression',
218
+ 'case_count': 90,
219
+ 'relevance_threshold': None,
220
+ 'review_status': 'authored_local_audit_pending',
221
+ 'state': 'ready',
222
+ 'reason': None,
223
+ 'source_case_count': 90,
224
+ 'candidate_depth': None,
225
+ 'first_stage': None,
226
+ 'family_status': 'known',
227
+ 'family_digest': 'sha256:19aca72a256a0d2b37309d965a7e0e90c06ff69f4d0f87b971df454dc68b5cf8',
228
+ 'repeated_question_status': 'known',
229
+ 'relationships': [{'dataset_id': 'invocation.narrow-gate-20260925-r2',
230
+ 'kind': 'repeated_question',
231
+ 'case_count': 60,
232
+ 'family_digest': None},
233
+ {'dataset_id': 'invocation.narrow-gate-20260925-r4',
234
+ 'kind': 'repeated_question',
235
+ 'case_count': 30,
236
+ 'family_digest': None},
237
+ {'dataset_id': 'invocation.narrow-gate-20260925-r5',
238
+ 'kind': 'repeated_question',
239
+ 'case_count': 30,
240
+ 'family_digest': None},
241
+ {'dataset_id': 'invocation.narrow-gate-20260925-r2',
242
+ 'kind': 'shared_family',
243
+ 'case_count': 90,
244
+ 'family_digest': 'sha256:fab8f8bf2f1994b374263d10db8fbbadf4509ead4addffcbbfc4b7a8d13cf85a'},
245
+ {'dataset_id': 'invocation.narrow-gate-20260925-r4',
246
+ 'kind': 'shared_family',
247
+ 'case_count': 90,
248
+ 'family_digest': 'sha256:fab8f8bf2f1994b374263d10db8fbbadf4509ead4addffcbbfc4b7a8d13cf85a'},
249
+ {'dataset_id': 'invocation.narrow-gate-20260925-r5',
250
+ 'kind': 'shared_family',
251
+ 'case_count': 90,
252
+ 'family_digest': 'sha256:fab8f8bf2f1994b374263d10db8fbbadf4509ead4addffcbbfc4b7a8d13cf85a'}],
253
+ 'authorization_requirements': ['Owner authorization for routing inputs and gold labels.'],
254
+ 'local_prerequisites': ['Pinned bank directory and retained source/reference bytes.'],
255
+ 'implementation_status': 'available',
256
+ 'previously_exercised': True,
257
+ 'superseded_by': [],
258
+ 'schema_version': 'sphynx.dataset-descriptor.v1'},
259
+ {'dataset_id': 'invocation.decision-boundary-80',
260
+ 'pack_id': 'rag.invoke.v1',
261
+ 'release': 'v1-20260925',
262
+ 'track': 'rag_invoke',
263
+ 'dataset_schema_version': 'sphynx.decision-boundary-holdout.v1',
264
+ 'source_digest': 'sha256:f1aea9ab88c55586ed01a6bf5aee4ac78661ae11727dfea12ecee14da09ea2b6',
265
+ 'reference_digest': 'sha256:fc3f39b79435eab66033b9ac2d919a2931b26568f848542cce2f6a27dc15eb44',
266
+ 'population': 'previously_exercised_regression',
267
+ 'split': 'regression',
268
+ 'case_count': 80,
269
+ 'relevance_threshold': None,
270
+ 'review_status': 'authored_local_audit_pending',
271
+ 'state': 'ready',
272
+ 'reason': None,
273
+ 'source_case_count': 80,
274
+ 'candidate_depth': None,
275
+ 'first_stage': None,
276
+ 'family_status': 'known',
277
+ 'family_digest': 'sha256:f0fb0002ba6eea1d165fb8a2ba182dfa500200afcae2c2a90518162e368870e8',
278
+ 'repeated_question_status': 'known',
279
+ 'relationships': [],
280
+ 'authorization_requirements': ['Owner authorization for routing inputs and gold labels.'],
281
+ 'local_prerequisites': ['Pinned bank directory and retained source/reference bytes.'],
282
+ 'implementation_status': 'available',
283
+ 'previously_exercised': True,
284
+ 'superseded_by': [],
285
+ 'schema_version': 'sphynx.dataset-descriptor.v1'},
286
+ {'dataset_id': 'invocation.narrow-gate-20260925-r2',
287
+ 'pack_id': 'rag.invoke.v1',
288
+ 'release': 'narrow-gate-20260925-r2',
289
+ 'track': 'rag_invoke',
290
+ 'dataset_schema_version': 'sphynx.invocation-holdout.v1',
291
+ 'source_digest': 'sha256:fea544f918248f710be172bcadfdf1e6506ca2f4e08ab97c6099bd3afed1d316',
292
+ 'reference_digest': 'sha256:45dc2201b9e92efb2713282781ece6605f208855240b7f3087892275fcc5e4c1',
293
+ 'population': 'previously_exercised_regression',
294
+ 'split': 'regression',
295
+ 'case_count': 90,
296
+ 'relevance_threshold': None,
297
+ 'review_status': 'authored_unreviewed_do_not_score_yet',
298
+ 'state': 'blocked',
299
+ 'reason': 'Pinned release loader is available; authored/unreviewed source is marked do_not_score_yet '
300
+ 'and requires owner review authorization before scoring.',
301
+ 'source_case_count': 90,
302
+ 'candidate_depth': None,
303
+ 'first_stage': None,
304
+ 'family_status': 'known',
305
+ 'family_digest': 'sha256:58e76bcdb78618d5d9bcb9db4b3a60e8bfbe92f8eca7f57f7f6d0a00b5c4e169',
306
+ 'repeated_question_status': 'known',
307
+ 'relationships': [{'dataset_id': 'invocation.narrow-policy-90',
308
+ 'kind': 'revised_from',
309
+ 'case_count': 90,
310
+ 'family_digest': None},
311
+ {'dataset_id': 'invocation.narrow-policy-90',
312
+ 'kind': 'repeated_question',
313
+ 'case_count': 60,
314
+ 'family_digest': None},
315
+ {'dataset_id': 'invocation.narrow-gate-20260925-r4',
316
+ 'kind': 'repeated_question',
317
+ 'case_count': 36,
318
+ 'family_digest': None},
319
+ {'dataset_id': 'invocation.narrow-gate-20260925-r5',
320
+ 'kind': 'repeated_question',
321
+ 'case_count': 36,
322
+ 'family_digest': None},
323
+ {'dataset_id': 'invocation.narrow-policy-90',
324
+ 'kind': 'shared_family',
325
+ 'case_count': 90,
326
+ 'family_digest': 'sha256:fab8f8bf2f1994b374263d10db8fbbadf4509ead4addffcbbfc4b7a8d13cf85a'},
327
+ {'dataset_id': 'invocation.narrow-gate-20260925-r4',
328
+ 'kind': 'shared_family',
329
+ 'case_count': 90,
330
+ 'family_digest': 'sha256:fab8f8bf2f1994b374263d10db8fbbadf4509ead4addffcbbfc4b7a8d13cf85a'},
331
+ {'dataset_id': 'invocation.narrow-gate-20260925-r5',
332
+ 'kind': 'shared_family',
333
+ 'case_count': 90,
334
+ 'family_digest': 'sha256:fab8f8bf2f1994b374263d10db8fbbadf4509ead4addffcbbfc4b7a8d13cf85a'}],
335
+ 'authorization_requirements': ['Owner authorization for revised routing inputs and labels.'],
336
+ 'local_prerequisites': ['Exact revised bank manifest, model-input and gold files.'],
337
+ 'implementation_status': 'available',
338
+ 'previously_exercised': True,
339
+ 'superseded_by': [],
340
+ 'schema_version': 'sphynx.dataset-descriptor.v1'},
341
+ {'dataset_id': 'invocation.narrow-gate-20260925-r4',
342
+ 'pack_id': 'rag.invoke.v1',
343
+ 'release': 'narrow-gate-20260925-r4',
344
+ 'track': 'rag_invoke',
345
+ 'dataset_schema_version': 'sphynx.invocation-holdout.v1',
346
+ 'source_digest': 'sha256:2af3d98cb92146511e85de1a6c038d01f4bf7c117b622c61c6425a03f6e4a391',
347
+ 'reference_digest': 'sha256:7b593b9838e0bbfd3a74f359ddefe9eed7af476f0a914040ccff8889352750d5',
348
+ 'population': 'previously_exercised_regression',
349
+ 'split': 'regression',
350
+ 'case_count': 90,
351
+ 'relevance_threshold': None,
352
+ 'review_status': 'authored_unreviewed_do_not_score_yet',
353
+ 'state': 'blocked',
354
+ 'reason': 'Pinned release loader is available; authored/unreviewed source is marked do_not_score_yet '
355
+ 'and requires owner review authorization before scoring.',
356
+ 'source_case_count': 90,
357
+ 'candidate_depth': None,
358
+ 'first_stage': None,
359
+ 'family_status': 'known',
360
+ 'family_digest': 'sha256:63b8240daad1d8457eb686cb4eabd3fbeb39403ed6ff14ecbfd3443468b9ef6d',
361
+ 'repeated_question_status': 'known',
362
+ 'relationships': [{'dataset_id': 'invocation.narrow-gate-20260925-r2',
363
+ 'kind': 'revised_from',
364
+ 'case_count': 90,
365
+ 'family_digest': None},
366
+ {'dataset_id': 'invocation.narrow-policy-90',
367
+ 'kind': 'repeated_question',
368
+ 'case_count': 30,
369
+ 'family_digest': None},
370
+ {'dataset_id': 'invocation.narrow-gate-20260925-r2',
371
+ 'kind': 'repeated_question',
372
+ 'case_count': 36,
373
+ 'family_digest': None},
374
+ {'dataset_id': 'invocation.narrow-gate-20260925-r5',
375
+ 'kind': 'repeated_question',
376
+ 'case_count': 90,
377
+ 'family_digest': None},
378
+ {'dataset_id': 'invocation.narrow-policy-90',
379
+ 'kind': 'shared_family',
380
+ 'case_count': 90,
381
+ 'family_digest': 'sha256:fab8f8bf2f1994b374263d10db8fbbadf4509ead4addffcbbfc4b7a8d13cf85a'},
382
+ {'dataset_id': 'invocation.narrow-gate-20260925-r2',
383
+ 'kind': 'shared_family',
384
+ 'case_count': 90,
385
+ 'family_digest': 'sha256:fab8f8bf2f1994b374263d10db8fbbadf4509ead4addffcbbfc4b7a8d13cf85a'},
386
+ {'dataset_id': 'invocation.narrow-gate-20260925-r5',
387
+ 'kind': 'shared_family',
388
+ 'case_count': 90,
389
+ 'family_digest': 'sha256:fab8f8bf2f1994b374263d10db8fbbadf4509ead4addffcbbfc4b7a8d13cf85a'}],
390
+ 'authorization_requirements': ['Owner authorization for revised routing inputs and labels.'],
391
+ 'local_prerequisites': ['Exact revised bank manifest, model-input and gold files.'],
392
+ 'implementation_status': 'available',
393
+ 'previously_exercised': True,
394
+ 'superseded_by': [],
395
+ 'schema_version': 'sphynx.dataset-descriptor.v1'},
396
+ {'dataset_id': 'invocation.narrow-gate-20260925-r5',
397
+ 'pack_id': 'rag.invoke.v1',
398
+ 'release': 'narrow-gate-20260925-r5',
399
+ 'track': 'rag_invoke',
400
+ 'dataset_schema_version': 'sphynx.invocation-holdout.v1',
401
+ 'source_digest': 'sha256:c230ad79a9aba6cef17266b83345d273e93eba0871408ce23f87d59e27543194',
402
+ 'reference_digest': 'sha256:7b593b9838e0bbfd3a74f359ddefe9eed7af476f0a914040ccff8889352750d5',
403
+ 'population': 'previously_exercised_regression',
404
+ 'split': 'regression',
405
+ 'case_count': 90,
406
+ 'relevance_threshold': None,
407
+ 'review_status': 'authored_unreviewed_do_not_score_yet',
408
+ 'state': 'blocked',
409
+ 'reason': 'Pinned release loader is available; authored/unreviewed source is marked do_not_score_yet '
410
+ 'and requires owner review authorization before scoring.',
411
+ 'source_case_count': 90,
412
+ 'candidate_depth': None,
413
+ 'first_stage': None,
414
+ 'family_status': 'known',
415
+ 'family_digest': 'sha256:63b8240daad1d8457eb686cb4eabd3fbeb39403ed6ff14ecbfd3443468b9ef6d',
416
+ 'repeated_question_status': 'known',
417
+ 'relationships': [{'dataset_id': 'invocation.narrow-gate-20260925-r4',
418
+ 'kind': 'revised_from',
419
+ 'case_count': 90,
420
+ 'family_digest': None},
421
+ {'dataset_id': 'invocation.narrow-policy-90',
422
+ 'kind': 'repeated_question',
423
+ 'case_count': 30,
424
+ 'family_digest': None},
425
+ {'dataset_id': 'invocation.narrow-gate-20260925-r2',
426
+ 'kind': 'repeated_question',
427
+ 'case_count': 36,
428
+ 'family_digest': None},
429
+ {'dataset_id': 'invocation.narrow-gate-20260925-r4',
430
+ 'kind': 'repeated_question',
431
+ 'case_count': 90,
432
+ 'family_digest': None},
433
+ {'dataset_id': 'invocation.narrow-policy-90',
434
+ 'kind': 'shared_family',
435
+ 'case_count': 90,
436
+ 'family_digest': 'sha256:fab8f8bf2f1994b374263d10db8fbbadf4509ead4addffcbbfc4b7a8d13cf85a'},
437
+ {'dataset_id': 'invocation.narrow-gate-20260925-r2',
438
+ 'kind': 'shared_family',
439
+ 'case_count': 90,
440
+ 'family_digest': 'sha256:fab8f8bf2f1994b374263d10db8fbbadf4509ead4addffcbbfc4b7a8d13cf85a'},
441
+ {'dataset_id': 'invocation.narrow-gate-20260925-r4',
442
+ 'kind': 'shared_family',
443
+ 'case_count': 90,
444
+ 'family_digest': 'sha256:fab8f8bf2f1994b374263d10db8fbbadf4509ead4addffcbbfc4b7a8d13cf85a'}],
445
+ 'authorization_requirements': ['Owner authorization for revised routing inputs and labels.'],
446
+ 'local_prerequisites': ['Exact revised bank manifest, model-input and gold files.'],
447
+ 'implementation_status': 'available',
448
+ 'previously_exercised': True,
449
+ 'superseded_by': [],
450
+ 'schema_version': 'sphynx.dataset-descriptor.v1'},
451
+ {'dataset_id': 'invocation.six-customer.v1-20260918',
452
+ 'pack_id': 'rag.invoke.v1',
453
+ 'release': 'v1-20260918',
454
+ 'track': 'rag_invoke',
455
+ 'dataset_schema_version': 'sable.invocation-question-corpus.v1',
456
+ 'source_digest': 'sha256:797cf8793b901a1f87460bf079216a48385ac31bcb965210e588251ef430694b',
457
+ 'reference_digest': 'sha256:92db1243cd6decaa2ca84ee1302ec07b22d08af4235c8946fcd86522e0ea4977',
458
+ 'population': 'six_customer_authored_development',
459
+ 'split': 'development',
460
+ 'case_count': 360,
461
+ 'relevance_threshold': None,
462
+ 'review_status': 'independent_human_review_incomplete',
463
+ 'state': 'ready',
464
+ 'reason': None,
465
+ 'source_case_count': 360,
466
+ 'candidate_depth': None,
467
+ 'first_stage': None,
468
+ 'family_status': 'known',
469
+ 'family_digest': 'sha256:2ccfdfffc35f6b238c32a02f1e8a5aa6efdd57f3aa49c9f6738397121dc3e38f',
470
+ 'repeated_question_status': 'known',
471
+ 'relationships': [{'dataset_id': 'invocation.excerpt-free-200',
472
+ 'kind': 'repeated_question',
473
+ 'case_count': 198,
474
+ 'family_digest': None},
475
+ {'dataset_id': 'invocation.development-300',
476
+ 'kind': 'repeated_question',
477
+ 'case_count': 198,
478
+ 'family_digest': None},
479
+ {'dataset_id': 'invocation.six-customer.v1-20260918-r2',
480
+ 'kind': 'repeated_question',
481
+ 'case_count': 238,
482
+ 'family_digest': None},
483
+ {'dataset_id': 'invocation.six-customer.v1-20260918-r3',
484
+ 'kind': 'repeated_question',
485
+ 'case_count': 238,
486
+ 'family_digest': None},
487
+ {'dataset_id': 'invocation.excerpt-free-200',
488
+ 'kind': 'shared_family',
489
+ 'case_count': 297,
490
+ 'family_digest': 'sha256:a5ef5d820c4682092c7c0ab5c69011b771f129b34ba5c591d5d4cdc27860020a'},
491
+ {'dataset_id': 'invocation.development-300',
492
+ 'kind': 'shared_family',
493
+ 'case_count': 297,
494
+ 'family_digest': 'sha256:a5ef5d820c4682092c7c0ab5c69011b771f129b34ba5c591d5d4cdc27860020a'},
495
+ {'dataset_id': 'invocation.six-customer.v1-20260918-r2',
496
+ 'kind': 'shared_family',
497
+ 'case_count': 360,
498
+ 'family_digest': 'sha256:23f0e828a60e5eef7c3fbd1d4df7bef5cde11ab2bd20d9d129b5d9536a0e2009'},
499
+ {'dataset_id': 'invocation.six-customer.v1-20260918-r3',
500
+ 'kind': 'shared_family',
501
+ 'case_count': 357,
502
+ 'family_digest': 'sha256:45dfeb91b14aa8c87b06f4e65b9a263060d2472f49a36c29b2736aa82d3b57c9'}],
503
+ 'authorization_requirements': ['Owner authorization for all six customer routing records.'],
504
+ 'local_prerequisites': ['Exact full original bank; an extracted slice needs its own cohort identity.'],
505
+ 'implementation_status': 'available',
506
+ 'previously_exercised': None,
507
+ 'superseded_by': [],
508
+ 'schema_version': 'sphynx.dataset-descriptor.v1'},
509
+ {'dataset_id': 'invocation.six-customer.v1-20260918-r2',
510
+ 'pack_id': 'rag.invoke.v1',
511
+ 'release': 'v1-20260918-r2',
512
+ 'track': 'rag_invoke',
513
+ 'dataset_schema_version': 'sable.invocation-question-corpus.v1',
514
+ 'source_digest': 'sha256:d4f60c0046b9c55fc992dacc699ffbb8743c2c331dfc6ce73f5601be1c6c78fb',
515
+ 'reference_digest': 'sha256:c21dd65089f2a1a06f891e9f2c618fda4f69ec8b6d67ea42a83afac7bdff9e29',
516
+ 'population': 'six_customer_authored_development',
517
+ 'split': 'development',
518
+ 'case_count': 360,
519
+ 'relevance_threshold': None,
520
+ 'review_status': 'independent_human_review_incomplete',
521
+ 'state': 'ready',
522
+ 'reason': None,
523
+ 'source_case_count': 360,
524
+ 'candidate_depth': None,
525
+ 'first_stage': None,
526
+ 'family_status': 'known',
527
+ 'family_digest': 'sha256:2ccfdfffc35f6b238c32a02f1e8a5aa6efdd57f3aa49c9f6738397121dc3e38f',
528
+ 'repeated_question_status': 'known',
529
+ 'relationships': [{'dataset_id': 'invocation.excerpt-free-200',
530
+ 'kind': 'repeated_question',
531
+ 'case_count': 198,
532
+ 'family_digest': None},
533
+ {'dataset_id': 'invocation.development-300',
534
+ 'kind': 'repeated_question',
535
+ 'case_count': 297,
536
+ 'family_digest': None},
537
+ {'dataset_id': 'invocation.six-customer.v1-20260918',
538
+ 'kind': 'repeated_question',
539
+ 'case_count': 238,
540
+ 'family_digest': None},
541
+ {'dataset_id': 'invocation.six-customer.v1-20260918-r3',
542
+ 'kind': 'repeated_question',
543
+ 'case_count': 357,
544
+ 'family_digest': None},
545
+ {'dataset_id': 'invocation.excerpt-free-200',
546
+ 'kind': 'shared_family',
547
+ 'case_count': 297,
548
+ 'family_digest': 'sha256:a5ef5d820c4682092c7c0ab5c69011b771f129b34ba5c591d5d4cdc27860020a'},
549
+ {'dataset_id': 'invocation.development-300',
550
+ 'kind': 'shared_family',
551
+ 'case_count': 297,
552
+ 'family_digest': 'sha256:a5ef5d820c4682092c7c0ab5c69011b771f129b34ba5c591d5d4cdc27860020a'},
553
+ {'dataset_id': 'invocation.six-customer.v1-20260918',
554
+ 'kind': 'shared_family',
555
+ 'case_count': 360,
556
+ 'family_digest': 'sha256:23f0e828a60e5eef7c3fbd1d4df7bef5cde11ab2bd20d9d129b5d9536a0e2009'},
557
+ {'dataset_id': 'invocation.six-customer.v1-20260918-r3',
558
+ 'kind': 'shared_family',
559
+ 'case_count': 357,
560
+ 'family_digest': 'sha256:45dfeb91b14aa8c87b06f4e65b9a263060d2472f49a36c29b2736aa82d3b57c9'}],
561
+ 'authorization_requirements': ['Owner authorization for all six customer routing records.'],
562
+ 'local_prerequisites': ['Exact full original bank; an extracted slice needs its own cohort identity.'],
563
+ 'implementation_status': 'available',
564
+ 'previously_exercised': None,
565
+ 'superseded_by': [],
566
+ 'schema_version': 'sphynx.dataset-descriptor.v1'},
567
+ {'dataset_id': 'invocation.six-customer.v1-20260918-r3',
568
+ 'pack_id': 'rag.invoke.v1',
569
+ 'release': 'v1-20260918-r3',
570
+ 'track': 'rag_invoke',
571
+ 'dataset_schema_version': 'sable.invocation-question-corpus.v1',
572
+ 'source_digest': 'sha256:80336bade48c6bc1acadbae8c66e321d68008e0ee6d2d18fd473e56d566319a6',
573
+ 'reference_digest': 'sha256:b886cc3cb572249018e94656ceeff796c576dc7bc5162b30e90d9ed039a02472',
574
+ 'population': 'six_customer_authored_development',
575
+ 'split': 'development',
576
+ 'case_count': 360,
577
+ 'relevance_threshold': None,
578
+ 'review_status': 'independent_human_review_incomplete',
579
+ 'state': 'ready',
580
+ 'reason': None,
581
+ 'source_case_count': 360,
582
+ 'candidate_depth': None,
583
+ 'first_stage': None,
584
+ 'family_status': 'known',
585
+ 'family_digest': 'sha256:3fa06a52cacb60b7144f3ca75c74163ba0a1e073562b0ad5e385b13c10892501',
586
+ 'repeated_question_status': 'known',
587
+ 'relationships': [{'dataset_id': 'invocation.excerpt-free-200',
588
+ 'kind': 'repeated_question',
589
+ 'case_count': 200,
590
+ 'family_digest': None},
591
+ {'dataset_id': 'invocation.development-300',
592
+ 'kind': 'repeated_question',
593
+ 'case_count': 300,
594
+ 'family_digest': None},
595
+ {'dataset_id': 'invocation.six-customer.v1-20260918',
596
+ 'kind': 'repeated_question',
597
+ 'case_count': 238,
598
+ 'family_digest': None},
599
+ {'dataset_id': 'invocation.six-customer.v1-20260918-r2',
600
+ 'kind': 'repeated_question',
601
+ 'case_count': 357,
602
+ 'family_digest': None},
603
+ {'dataset_id': 'invocation.excerpt-free-200',
604
+ 'kind': 'shared_family',
605
+ 'case_count': 300,
606
+ 'family_digest': 'sha256:06b194d2ce25b12c1a29ed6256689baafa09247137ca2db3948528f7b8b35445'},
607
+ {'dataset_id': 'invocation.development-300',
608
+ 'kind': 'shared_family',
609
+ 'case_count': 300,
610
+ 'family_digest': 'sha256:06b194d2ce25b12c1a29ed6256689baafa09247137ca2db3948528f7b8b35445'},
611
+ {'dataset_id': 'invocation.six-customer.v1-20260918',
612
+ 'kind': 'shared_family',
613
+ 'case_count': 357,
614
+ 'family_digest': 'sha256:45dfeb91b14aa8c87b06f4e65b9a263060d2472f49a36c29b2736aa82d3b57c9'},
615
+ {'dataset_id': 'invocation.six-customer.v1-20260918-r2',
616
+ 'kind': 'shared_family',
617
+ 'case_count': 357,
618
+ 'family_digest': 'sha256:45dfeb91b14aa8c87b06f4e65b9a263060d2472f49a36c29b2736aa82d3b57c9'}],
619
+ 'authorization_requirements': ['Owner authorization for all six customer routing records.'],
620
+ 'local_prerequisites': ['Exact full original bank; an extracted slice needs its own cohort identity.'],
621
+ 'implementation_status': 'available',
622
+ 'previously_exercised': None,
623
+ 'superseded_by': [],
624
+ 'schema_version': 'sphynx.dataset-descriptor.v1'},
625
+ {'dataset_id': 'beir.original.development.v1',
626
+ 'pack_id': 'rag.rerank.beir.v1',
627
+ 'release': 'v1.external',
628
+ 'track': 'rag_rerank_public',
629
+ 'dataset_schema_version': 'expanded-reranker.frozen-pools.v1',
630
+ 'source_digest': 'sha256:89b713acfd071cafd65fc40581d721399aeee79a132c87e20b03a2b6c401941e',
631
+ 'reference_digest': 'sha256:89b713acfd071cafd65fc40581d721399aeee79a132c87e20b03a2b6c401941e',
632
+ 'population': 'six_public_domains',
633
+ 'split': 'development',
634
+ 'case_count': 90,
635
+ 'relevance_threshold': 1.0,
636
+ 'review_status': 'public_native_qrels',
637
+ 'state': 'ready',
638
+ 'reason': None,
639
+ 'source_case_count': 180,
640
+ 'candidate_depth': 15,
641
+ 'first_stage': 'bm25_okapi_public_screen',
642
+ 'family_status': 'unknown',
643
+ 'family_digest': None,
644
+ 'repeated_question_status': 'known',
645
+ 'relationships': [],
646
+ 'authorization_requirements': ['Authorized external public frozen-pools source or approved '
647
+ 'public-only export.'],
648
+ 'local_prerequisites': ['Exact pinned public pools; 15 queries per domain in the selected original '
649
+ 'split.'],
650
+ 'implementation_status': 'available',
651
+ 'previously_exercised': True,
652
+ 'superseded_by': [],
653
+ 'schema_version': 'sphynx.dataset-descriptor.v1'},
654
+ {'dataset_id': 'beir.original.confirmation.v1',
655
+ 'pack_id': 'rag.rerank.beir.v1',
656
+ 'release': 'v1.external',
657
+ 'track': 'rag_rerank_public',
658
+ 'dataset_schema_version': 'expanded-reranker.frozen-pools.v1',
659
+ 'source_digest': 'sha256:89b713acfd071cafd65fc40581d721399aeee79a132c87e20b03a2b6c401941e',
660
+ 'reference_digest': 'sha256:89b713acfd071cafd65fc40581d721399aeee79a132c87e20b03a2b6c401941e',
661
+ 'population': 'six_public_domains',
662
+ 'split': 'confirmation',
663
+ 'case_count': 90,
664
+ 'relevance_threshold': 1.0,
665
+ 'review_status': 'public_native_qrels',
666
+ 'state': 'ready',
667
+ 'reason': None,
668
+ 'source_case_count': 180,
669
+ 'candidate_depth': 15,
670
+ 'first_stage': 'bm25_okapi_public_screen',
671
+ 'family_status': 'unknown',
672
+ 'family_digest': None,
673
+ 'repeated_question_status': 'known',
674
+ 'relationships': [],
675
+ 'authorization_requirements': ['Authorized external public frozen-pools source or approved '
676
+ 'public-only export.'],
677
+ 'local_prerequisites': ['Exact pinned public pools; 15 queries per domain in the selected original '
678
+ 'split.'],
679
+ 'implementation_status': 'available',
680
+ 'previously_exercised': True,
681
+ 'superseded_by': [],
682
+ 'schema_version': 'sphynx.dataset-descriptor.v1'},
683
+ {'dataset_id': 'beir.fresh-e2.confirmation.v1',
684
+ 'pack_id': 'rag.rerank.beir.v1',
685
+ 'release': 'fresh-e2.v1',
686
+ 'track': 'rag_rerank_public',
687
+ 'dataset_schema_version': 'expanded-reranker.fresh-snowflake-pools.v1',
688
+ 'source_digest': 'sha256:1168a3f2079ae192bc54ed681976004ad375882fbc7800b611c5bb50fbf7b8b4',
689
+ 'reference_digest': 'sha256:1168a3f2079ae192bc54ed681976004ad375882fbc7800b611c5bb50fbf7b8b4',
690
+ 'population': 'six_public_domains',
691
+ 'split': 'confirmation',
692
+ 'case_count': 120,
693
+ 'relevance_threshold': 1,
694
+ 'review_status': 'public_qrels_previously_opened',
695
+ 'state': 'ready',
696
+ 'reason': None,
697
+ 'source_case_count': 120,
698
+ 'candidate_depth': 15,
699
+ 'first_stage': 'snowflake_arctic_embed_m_v1_5_public_proxy',
700
+ 'family_status': 'unknown',
701
+ 'family_digest': None,
702
+ 'repeated_question_status': 'known',
703
+ 'relationships': [],
704
+ 'authorization_requirements': ['Authorized external revised public source.'],
705
+ 'local_prerequisites': ['Exact 120-query pool; original 90-query identities must remain unchanged.'],
706
+ 'implementation_status': 'available',
707
+ 'previously_exercised': True,
708
+ 'superseded_by': [],
709
+ 'schema_version': 'sphynx.dataset-descriptor.v1'},
710
+ {'dataset_id': 'beir.guarded-jina.confirmation.v1',
711
+ 'pack_id': 'rag.rerank.beir.v1',
712
+ 'release': 'guarded-jina.v1',
713
+ 'track': 'rag_rerank_public',
714
+ 'dataset_schema_version': 'expanded-reranker.fresh-snowflake-pools.v1',
715
+ 'source_digest': 'sha256:8a519db2b0e62622705c7e05d71aac3c526d4a3dc97308e248839c5558f9ce49',
716
+ 'reference_digest': 'sha256:8a519db2b0e62622705c7e05d71aac3c526d4a3dc97308e248839c5558f9ce49',
717
+ 'population': 'six_public_domains',
718
+ 'split': 'confirmation',
719
+ 'case_count': 120,
720
+ 'relevance_threshold': 1,
721
+ 'review_status': 'public_qrels_previously_opened',
722
+ 'state': 'ready',
723
+ 'reason': None,
724
+ 'source_case_count': 120,
725
+ 'candidate_depth': 15,
726
+ 'first_stage': 'snowflake_arctic_embed_m_v1_5_public_proxy',
727
+ 'family_status': 'unknown',
728
+ 'family_digest': None,
729
+ 'repeated_question_status': 'known',
730
+ 'relationships': [],
731
+ 'authorization_requirements': ['Authorized external revised public source.'],
732
+ 'local_prerequisites': ['Exact 120-query pool; original 90-query identities must remain unchanged.'],
733
+ 'implementation_status': 'available',
734
+ 'previously_exercised': True,
735
+ 'superseded_by': [],
736
+ 'schema_version': 'sphynx.dataset-descriptor.v1'},
737
+ {'dataset_id': 'question-robustness.pilot.v1',
738
+ 'pack_id': 'rag.question_robustness.v1',
739
+ 'release': 'v1.external',
740
+ 'track': 'rag_question_robustness',
741
+ 'dataset_schema_version': 'sphynx.rag.question_robustness.pilot.draft.v1',
742
+ 'source_digest': 'sha256:cbb64ec35a6798f3f500ef61adbd48434b7433ea6b18e8cdc1674eb3295c5b78',
743
+ 'reference_digest': 'sha256:cbb64ec35a6798f3f500ef61adbd48434b7433ea6b18e8cdc1674eb3295c5b78',
744
+ 'population': 'paired_owner_development',
745
+ 'split': 'pilot',
746
+ 'case_count': 60,
747
+ 'relevance_threshold': None,
748
+ 'review_status': 'pending_human_review',
749
+ 'state': 'blocked',
750
+ 'reason': 'Semantic verdicts require separate capture-bound human review; original authored labels '
751
+ 'remain provisional.',
752
+ 'source_case_count': None,
753
+ 'candidate_depth': None,
754
+ 'first_stage': None,
755
+ 'family_status': 'unknown',
756
+ 'family_digest': None,
757
+ 'repeated_question_status': 'unknown',
758
+ 'relationships': [],
759
+ 'authorization_requirements': ['Owner authorization for the paired pilot and reviewer judgments.'],
760
+ 'local_prerequisites': ['Exact manifest and every pinned pilot file.'],
761
+ 'implementation_status': 'available',
762
+ 'previously_exercised': True,
763
+ 'superseded_by': [],
764
+ 'schema_version': 'sphynx.dataset-descriptor.v1'},
765
+ {'dataset_id': 'historical.sable-n11.v1',
766
+ 'pack_id': 'rag.rerank.sable.dev.v1',
767
+ 'release': 'historical.v1',
768
+ 'track': 'rag_rerank',
769
+ 'dataset_schema_version': 'unknown',
770
+ 'source_digest': None,
771
+ 'reference_digest': None,
772
+ 'population': 'historical_report_only',
773
+ 'split': 'historical',
774
+ 'case_count': 30,
775
+ 'relevance_threshold': None,
776
+ 'review_status': 'raw_source_unavailable',
777
+ 'state': 'blocked',
778
+ 'reason': 'Curated research checkout contains reports only; exact raw cohort, labels and frozen score '
779
+ 'responses need owner restoration and a versioned importer.',
780
+ 'source_case_count': None,
781
+ 'candidate_depth': None,
782
+ 'first_stage': None,
783
+ 'family_status': 'unknown',
784
+ 'family_digest': None,
785
+ 'repeated_question_status': 'unknown',
786
+ 'relationships': [],
787
+ 'authorization_requirements': [],
788
+ 'local_prerequisites': [],
789
+ 'implementation_status': 'external_import_required',
790
+ 'previously_exercised': None,
791
+ 'superseded_by': [],
792
+ 'schema_version': 'sphynx.dataset-descriptor.v1'},
793
+ {'dataset_id': 'historical.public-n11.v1',
794
+ 'pack_id': 'rag.rerank.beir.v1',
795
+ 'release': 'historical.v1',
796
+ 'track': 'rag_rerank',
797
+ 'dataset_schema_version': 'unknown',
798
+ 'source_digest': None,
799
+ 'reference_digest': None,
800
+ 'population': 'historical_report_only',
801
+ 'split': 'historical',
802
+ 'case_count': 100,
803
+ 'relevance_threshold': None,
804
+ 'review_status': 'raw_source_unavailable',
805
+ 'state': 'blocked',
806
+ 'reason': 'Curated research checkout contains reports only; exact raw cohort, labels and frozen score '
807
+ 'responses need owner restoration and a versioned importer.',
808
+ 'source_case_count': None,
809
+ 'candidate_depth': None,
810
+ 'first_stage': None,
811
+ 'family_status': 'unknown',
812
+ 'family_digest': None,
813
+ 'repeated_question_status': 'unknown',
814
+ 'relationships': [],
815
+ 'authorization_requirements': [],
816
+ 'local_prerequisites': [],
817
+ 'implementation_status': 'external_import_required',
818
+ 'previously_exercised': None,
819
+ 'superseded_by': [],
820
+ 'schema_version': 'sphynx.dataset-descriptor.v1'},
821
+ {'dataset_id': 'historical.nfcorpus-t22.v1',
822
+ 'pack_id': 'rag.rerank.beir.v1',
823
+ 'release': 'historical.v1',
824
+ 'track': 'rag_rerank',
825
+ 'dataset_schema_version': 'unknown',
826
+ 'source_digest': None,
827
+ 'reference_digest': None,
828
+ 'population': 'historical_report_only',
829
+ 'split': 'historical',
830
+ 'case_count': 60,
831
+ 'relevance_threshold': 2,
832
+ 'review_status': 'raw_source_unavailable',
833
+ 'state': 'blocked',
834
+ 'reason': 'Curated research checkout contains reports only; exact raw cohort, labels and frozen score '
835
+ 'responses need owner restoration and a versioned importer.',
836
+ 'source_case_count': None,
837
+ 'candidate_depth': 11,
838
+ 'first_stage': None,
839
+ 'family_status': 'unknown',
840
+ 'family_digest': None,
841
+ 'repeated_question_status': 'unknown',
842
+ 'relationships': [],
843
+ 'authorization_requirements': [],
844
+ 'local_prerequisites': [],
845
+ 'implementation_status': 'external_import_required',
846
+ 'previously_exercised': None,
847
+ 'superseded_by': [],
848
+ 'schema_version': 'sphynx.dataset-descriptor.v1'},
849
+ {'dataset_id': 'historical.three-customer-routing-t022.v1',
850
+ 'pack_id': 'rag.invoke.v1',
851
+ 'release': 'historical.v1',
852
+ 'track': 'rag_invoke',
853
+ 'dataset_schema_version': 'unknown',
854
+ 'source_digest': None,
855
+ 'reference_digest': None,
856
+ 'population': 'historical_report_only',
857
+ 'split': 'historical',
858
+ 'case_count': None,
859
+ 'relevance_threshold': None,
860
+ 'review_status': 'raw_source_unavailable',
861
+ 'state': 'blocked',
862
+ 'reason': 'Curated research checkout contains reports only; exact raw cohort, labels and frozen score '
863
+ 'responses need owner restoration and a versioned importer.',
864
+ 'source_case_count': None,
865
+ 'candidate_depth': None,
866
+ 'first_stage': None,
867
+ 'family_status': 'unknown',
868
+ 'family_digest': None,
869
+ 'repeated_question_status': 'unknown',
870
+ 'relationships': [],
871
+ 'authorization_requirements': [],
872
+ 'local_prerequisites': [],
873
+ 'implementation_status': 'external_import_required',
874
+ 'previously_exercised': None,
875
+ 'superseded_by': [],
876
+ 'schema_version': 'sphynx.dataset-descriptor.v1'},
877
+ {'dataset_id': 'customer-v3.beehiiv',
878
+ 'pack_id': 'rag.dataset.v3',
879
+ 'release': 'approved-pack.pending',
880
+ 'track': 'rag_workbench',
881
+ 'dataset_schema_version': 'sable.rag.dataset.v3',
882
+ 'source_digest': None,
883
+ 'reference_digest': None,
884
+ 'population': 'customer_owner_held',
885
+ 'split': 'unknown',
886
+ 'case_count': None,
887
+ 'relevance_threshold': None,
888
+ 'review_status': 'approved_pack_missing',
889
+ 'state': 'blocked',
890
+ 'reason': 'Approved DatasetV3 customer pack is missing from the audited registry; owner must supply '
891
+ 'approved corpus, labels and digest.',
892
+ 'source_case_count': None,
893
+ 'candidate_depth': None,
894
+ 'first_stage': None,
895
+ 'family_status': 'unknown',
896
+ 'family_digest': None,
897
+ 'repeated_question_status': 'unknown',
898
+ 'relationships': [],
899
+ 'authorization_requirements': ['Owner approval for DatasetV3 customer data and labels.'],
900
+ 'local_prerequisites': [],
901
+ 'implementation_status': 'external_import_required',
902
+ 'previously_exercised': None,
903
+ 'superseded_by': [],
904
+ 'schema_version': 'sphynx.dataset-descriptor.v1'},
905
+ {'dataset_id': 'customer-v3.cherry',
906
+ 'pack_id': 'rag.dataset.v3',
907
+ 'release': 'approved-pack.pending',
908
+ 'track': 'rag_workbench',
909
+ 'dataset_schema_version': 'sable.rag.dataset.v3',
910
+ 'source_digest': None,
911
+ 'reference_digest': None,
912
+ 'population': 'customer_owner_held',
913
+ 'split': 'unknown',
914
+ 'case_count': None,
915
+ 'relevance_threshold': None,
916
+ 'review_status': 'approved_pack_missing',
917
+ 'state': 'blocked',
918
+ 'reason': 'Approved DatasetV3 customer pack is missing from the audited registry; owner must supply '
919
+ 'approved corpus, labels and digest.',
920
+ 'source_case_count': None,
921
+ 'candidate_depth': None,
922
+ 'first_stage': None,
923
+ 'family_status': 'unknown',
924
+ 'family_digest': None,
925
+ 'repeated_question_status': 'unknown',
926
+ 'relationships': [],
927
+ 'authorization_requirements': ['Owner approval for DatasetV3 customer data and labels.'],
928
+ 'local_prerequisites': [],
929
+ 'implementation_status': 'external_import_required',
930
+ 'previously_exercised': None,
931
+ 'superseded_by': [],
932
+ 'schema_version': 'sphynx.dataset-descriptor.v1'},
933
+ {'dataset_id': 'customer-v3.decagon',
934
+ 'pack_id': 'rag.dataset.v3',
935
+ 'release': 'approved-pack.pending',
936
+ 'track': 'rag_workbench',
937
+ 'dataset_schema_version': 'sable.rag.dataset.v3',
938
+ 'source_digest': None,
939
+ 'reference_digest': None,
940
+ 'population': 'customer_owner_held',
941
+ 'split': 'unknown',
942
+ 'case_count': None,
943
+ 'relevance_threshold': None,
944
+ 'review_status': 'approved_pack_missing',
945
+ 'state': 'blocked',
946
+ 'reason': 'Approved DatasetV3 customer pack is missing from the audited registry; owner must supply '
947
+ 'approved corpus, labels and digest.',
948
+ 'source_case_count': None,
949
+ 'candidate_depth': None,
950
+ 'first_stage': None,
951
+ 'family_status': 'unknown',
952
+ 'family_digest': None,
953
+ 'repeated_question_status': 'unknown',
954
+ 'relationships': [],
955
+ 'authorization_requirements': ['Owner approval for DatasetV3 customer data and labels.'],
956
+ 'local_prerequisites': [],
957
+ 'implementation_status': 'external_import_required',
958
+ 'previously_exercised': None,
959
+ 'superseded_by': [],
960
+ 'schema_version': 'sphynx.dataset-descriptor.v1'},
961
+ {'dataset_id': 'customer-v3.monday',
962
+ 'pack_id': 'rag.dataset.v3',
963
+ 'release': 'approved-pack.pending',
964
+ 'track': 'rag_workbench',
965
+ 'dataset_schema_version': 'sable.rag.dataset.v3',
966
+ 'source_digest': None,
967
+ 'reference_digest': None,
968
+ 'population': 'customer_owner_held',
969
+ 'split': 'unknown',
970
+ 'case_count': None,
971
+ 'relevance_threshold': None,
972
+ 'review_status': 'approved_pack_missing',
973
+ 'state': 'blocked',
974
+ 'reason': 'Approved DatasetV3 customer pack is missing from the audited registry; owner must supply '
975
+ 'approved corpus, labels and digest.',
976
+ 'source_case_count': None,
977
+ 'candidate_depth': None,
978
+ 'first_stage': None,
979
+ 'family_status': 'unknown',
980
+ 'family_digest': None,
981
+ 'repeated_question_status': 'unknown',
982
+ 'relationships': [],
983
+ 'authorization_requirements': ['Owner approval for DatasetV3 customer data and labels.'],
984
+ 'local_prerequisites': [],
985
+ 'implementation_status': 'external_import_required',
986
+ 'previously_exercised': None,
987
+ 'superseded_by': [],
988
+ 'schema_version': 'sphynx.dataset-descriptor.v1'},
989
+ {'dataset_id': 'customer-v3.notion',
990
+ 'pack_id': 'rag.dataset.v3',
991
+ 'release': 'approved-pack.pending',
992
+ 'track': 'rag_workbench',
993
+ 'dataset_schema_version': 'sable.rag.dataset.v3',
994
+ 'source_digest': None,
995
+ 'reference_digest': None,
996
+ 'population': 'customer_owner_held',
997
+ 'split': 'unknown',
998
+ 'case_count': None,
999
+ 'relevance_threshold': None,
1000
+ 'review_status': 'approved_pack_missing',
1001
+ 'state': 'blocked',
1002
+ 'reason': 'Approved DatasetV3 customer pack is missing from the audited registry; owner must supply '
1003
+ 'approved corpus, labels and digest.',
1004
+ 'source_case_count': None,
1005
+ 'candidate_depth': None,
1006
+ 'first_stage': None,
1007
+ 'family_status': 'unknown',
1008
+ 'family_digest': None,
1009
+ 'repeated_question_status': 'unknown',
1010
+ 'relationships': [],
1011
+ 'authorization_requirements': ['Owner approval for DatasetV3 customer data and labels.'],
1012
+ 'local_prerequisites': [],
1013
+ 'implementation_status': 'external_import_required',
1014
+ 'previously_exercised': None,
1015
+ 'superseded_by': [],
1016
+ 'schema_version': 'sphynx.dataset-descriptor.v1'},
1017
+ {'dataset_id': 'customer-v3.sable',
1018
+ 'pack_id': 'rag.dataset.v3',
1019
+ 'release': 'approved-pack.pending',
1020
+ 'track': 'rag_workbench',
1021
+ 'dataset_schema_version': 'sable.rag.dataset.v3',
1022
+ 'source_digest': None,
1023
+ 'reference_digest': None,
1024
+ 'population': 'customer_owner_held',
1025
+ 'split': 'unknown',
1026
+ 'case_count': None,
1027
+ 'relevance_threshold': None,
1028
+ 'review_status': 'approved_pack_missing',
1029
+ 'state': 'blocked',
1030
+ 'reason': 'Approved DatasetV3 customer pack is missing from the audited registry; owner must supply '
1031
+ 'approved corpus, labels and digest.',
1032
+ 'source_case_count': None,
1033
+ 'candidate_depth': None,
1034
+ 'first_stage': None,
1035
+ 'family_status': 'unknown',
1036
+ 'family_digest': None,
1037
+ 'repeated_question_status': 'unknown',
1038
+ 'relationships': [],
1039
+ 'authorization_requirements': ['Owner approval for DatasetV3 customer data and labels.'],
1040
+ 'local_prerequisites': [],
1041
+ 'implementation_status': 'external_import_required',
1042
+ 'previously_exercised': None,
1043
+ 'superseded_by': [],
1044
+ 'schema_version': 'sphynx.dataset-descriptor.v1'},
1045
+ {'dataset_id': 'customer-v3.safe-security',
1046
+ 'pack_id': 'rag.dataset.v3',
1047
+ 'release': 'approved-pack.pending',
1048
+ 'track': 'rag_workbench',
1049
+ 'dataset_schema_version': 'sable.rag.dataset.v3',
1050
+ 'source_digest': None,
1051
+ 'reference_digest': None,
1052
+ 'population': 'customer_owner_held',
1053
+ 'split': 'unknown',
1054
+ 'case_count': None,
1055
+ 'relevance_threshold': None,
1056
+ 'review_status': 'approved_pack_missing',
1057
+ 'state': 'blocked',
1058
+ 'reason': 'Approved DatasetV3 customer pack is missing from the audited registry; owner must supply '
1059
+ 'approved corpus, labels and digest.',
1060
+ 'source_case_count': None,
1061
+ 'candidate_depth': None,
1062
+ 'first_stage': None,
1063
+ 'family_status': 'unknown',
1064
+ 'family_digest': None,
1065
+ 'repeated_question_status': 'unknown',
1066
+ 'relationships': [],
1067
+ 'authorization_requirements': ['Owner approval for DatasetV3 customer data and labels.'],
1068
+ 'local_prerequisites': [],
1069
+ 'implementation_status': 'external_import_required',
1070
+ 'previously_exercised': None,
1071
+ 'superseded_by': [],
1072
+ 'schema_version': 'sphynx.dataset-descriptor.v1'},
1073
+ {'dataset_id': 'customer-v3.tipalti',
1074
+ 'pack_id': 'rag.dataset.v3',
1075
+ 'release': 'approved-pack.pending',
1076
+ 'track': 'rag_workbench',
1077
+ 'dataset_schema_version': 'sable.rag.dataset.v3',
1078
+ 'source_digest': None,
1079
+ 'reference_digest': None,
1080
+ 'population': 'customer_owner_held',
1081
+ 'split': 'unknown',
1082
+ 'case_count': None,
1083
+ 'relevance_threshold': None,
1084
+ 'review_status': 'approved_pack_missing',
1085
+ 'state': 'blocked',
1086
+ 'reason': 'Approved DatasetV3 customer pack is missing from the audited registry; owner must supply '
1087
+ 'approved corpus, labels and digest.',
1088
+ 'source_case_count': None,
1089
+ 'candidate_depth': None,
1090
+ 'first_stage': None,
1091
+ 'family_status': 'unknown',
1092
+ 'family_digest': None,
1093
+ 'repeated_question_status': 'unknown',
1094
+ 'relationships': [],
1095
+ 'authorization_requirements': ['Owner approval for DatasetV3 customer data and labels.'],
1096
+ 'local_prerequisites': [],
1097
+ 'implementation_status': 'external_import_required',
1098
+ 'previously_exercised': None,
1099
+ 'superseded_by': [],
1100
+ 'schema_version': 'sphynx.dataset-descriptor.v1'},
1101
+ {'dataset_id': 'customer-v3.vanta',
1102
+ 'pack_id': 'rag.dataset.v3',
1103
+ 'release': 'approved-pack.pending',
1104
+ 'track': 'rag_workbench',
1105
+ 'dataset_schema_version': 'sable.rag.dataset.v3',
1106
+ 'source_digest': None,
1107
+ 'reference_digest': None,
1108
+ 'population': 'customer_owner_held',
1109
+ 'split': 'unknown',
1110
+ 'case_count': None,
1111
+ 'relevance_threshold': None,
1112
+ 'review_status': 'approved_pack_missing',
1113
+ 'state': 'blocked',
1114
+ 'reason': 'Approved DatasetV3 customer pack is missing from the audited registry; owner must supply '
1115
+ 'approved corpus, labels and digest.',
1116
+ 'source_case_count': None,
1117
+ 'candidate_depth': None,
1118
+ 'first_stage': None,
1119
+ 'family_status': 'unknown',
1120
+ 'family_digest': None,
1121
+ 'repeated_question_status': 'unknown',
1122
+ 'relationships': [],
1123
+ 'authorization_requirements': ['Owner approval for DatasetV3 customer data and labels.'],
1124
+ 'local_prerequisites': [],
1125
+ 'implementation_status': 'external_import_required',
1126
+ 'previously_exercised': None,
1127
+ 'superseded_by': [],
1128
+ 'schema_version': 'sphynx.dataset-descriptor.v1'},
1129
+ {'dataset_id': 'customer-v3.zapier',
1130
+ 'pack_id': 'rag.dataset.v3',
1131
+ 'release': 'approved-pack.pending',
1132
+ 'track': 'rag_workbench',
1133
+ 'dataset_schema_version': 'sable.rag.dataset.v3',
1134
+ 'source_digest': None,
1135
+ 'reference_digest': None,
1136
+ 'population': 'customer_owner_held',
1137
+ 'split': 'unknown',
1138
+ 'case_count': None,
1139
+ 'relevance_threshold': None,
1140
+ 'review_status': 'approved_pack_missing',
1141
+ 'state': 'blocked',
1142
+ 'reason': 'Approved DatasetV3 customer pack is missing from the audited registry; owner must supply '
1143
+ 'approved corpus, labels and digest.',
1144
+ 'source_case_count': None,
1145
+ 'candidate_depth': None,
1146
+ 'first_stage': None,
1147
+ 'family_status': 'unknown',
1148
+ 'family_digest': None,
1149
+ 'repeated_question_status': 'unknown',
1150
+ 'relationships': [],
1151
+ 'authorization_requirements': ['Owner approval for DatasetV3 customer data and labels.'],
1152
+ 'local_prerequisites': [],
1153
+ 'implementation_status': 'external_import_required',
1154
+ 'previously_exercised': None,
1155
+ 'superseded_by': [],
1156
+ 'schema_version': 'sphynx.dataset-descriptor.v1'},
1157
+ {'dataset_id': 'customer-v3.zenzap',
1158
+ 'pack_id': 'rag.dataset.v3',
1159
+ 'release': 'approved-pack.pending',
1160
+ 'track': 'rag_workbench',
1161
+ 'dataset_schema_version': 'sable.rag.dataset.v3',
1162
+ 'source_digest': None,
1163
+ 'reference_digest': None,
1164
+ 'population': 'customer_owner_held',
1165
+ 'split': 'unknown',
1166
+ 'case_count': None,
1167
+ 'relevance_threshold': None,
1168
+ 'review_status': 'approved_pack_missing',
1169
+ 'state': 'blocked',
1170
+ 'reason': 'Approved DatasetV3 customer pack is missing from the audited registry; owner must supply '
1171
+ 'approved corpus, labels and digest.',
1172
+ 'source_case_count': None,
1173
+ 'candidate_depth': None,
1174
+ 'first_stage': None,
1175
+ 'family_status': 'unknown',
1176
+ 'family_digest': None,
1177
+ 'repeated_question_status': 'unknown',
1178
+ 'relationships': [],
1179
+ 'authorization_requirements': ['Owner approval for DatasetV3 customer data and labels.'],
1180
+ 'local_prerequisites': [],
1181
+ 'implementation_status': 'external_import_required',
1182
+ 'previously_exercised': None,
1183
+ 'superseded_by': [],
1184
+ 'schema_version': 'sphynx.dataset-descriptor.v1'},
1185
+ {'dataset_id': 'production-failure.challenge.v1',
1186
+ 'pack_id': 'rag.pipeline.v1',
1187
+ 'release': 'challenge.v1',
1188
+ 'track': 'rag_pipeline',
1189
+ 'dataset_schema_version': 'rag-evals.production-failure-challenge.v1',
1190
+ 'source_digest': None,
1191
+ 'reference_digest': None,
1192
+ 'population': 'registered_production_scenarios',
1193
+ 'split': 'production_confirmation',
1194
+ 'case_count': 17,
1195
+ 'relevance_threshold': None,
1196
+ 'review_status': 'labelled_pre_rerank_capture_missing',
1197
+ 'state': 'blocked',
1198
+ 'reason': 'Seventeen registered scenarios lack a complete reviewed exact labelled pre-rerank dataset; '
1199
+ 'scenarios do not establish a numerical benchmark.',
1200
+ 'source_case_count': None,
1201
+ 'candidate_depth': None,
1202
+ 'first_stage': None,
1203
+ 'family_status': 'unknown',
1204
+ 'family_digest': None,
1205
+ 'repeated_question_status': 'unknown',
1206
+ 'relationships': [],
1207
+ 'authorization_requirements': [],
1208
+ 'local_prerequisites': [],
1209
+ 'implementation_status': 'external_import_required',
1210
+ 'previously_exercised': None,
1211
+ 'superseded_by': [],
1212
+ 'schema_version': 'sphynx.dataset-descriptor.v1'}]
1213
+
1214
+ DATASETS = tuple(DatasetDescriptor.from_dict(value) for value in _DATA)