open-research-protocol 0.4.7 → 0.4.8

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 (46) hide show
  1. package/README.md +9 -0
  2. package/cli/orp.py +668 -43
  3. package/docs/ORP_REASONING_KERNEL_AGENT_PILOT.md +125 -0
  4. package/docs/ORP_REASONING_KERNEL_AGENT_REPLICATION.md +97 -0
  5. package/docs/ORP_REASONING_KERNEL_CANONICAL_CONTINUATION_PILOT.md +100 -0
  6. package/docs/ORP_REASONING_KERNEL_COMPARISON_PILOT.md +116 -0
  7. package/docs/ORP_REASONING_KERNEL_CONTINUATION_PILOT.md +86 -0
  8. package/docs/ORP_REASONING_KERNEL_EVALUATION_PLAN.md +261 -0
  9. package/docs/ORP_REASONING_KERNEL_EVIDENCE_MATRIX.md +131 -0
  10. package/docs/ORP_REASONING_KERNEL_EVOLUTION.md +123 -0
  11. package/docs/ORP_REASONING_KERNEL_PICKUP_PILOT.md +107 -0
  12. package/docs/ORP_REASONING_KERNEL_TECHNICAL_VALIDATION.md +140 -22
  13. package/docs/ORP_REASONING_KERNEL_V0_1.md +11 -0
  14. package/docs/benchmarks/orp_reasoning_kernel_agent_pilot_v0_1.json +796 -0
  15. package/docs/benchmarks/orp_reasoning_kernel_agent_replication_task_smoke.json +487 -0
  16. package/docs/benchmarks/orp_reasoning_kernel_agent_replication_v0_1.json +1927 -0
  17. package/docs/benchmarks/orp_reasoning_kernel_agent_replication_v0_2.json +10217 -0
  18. package/docs/benchmarks/orp_reasoning_kernel_canonical_continuation_task_smoke.json +174 -0
  19. package/docs/benchmarks/orp_reasoning_kernel_canonical_continuation_v0_1.json +598 -0
  20. package/docs/benchmarks/orp_reasoning_kernel_comparison_v0_1.json +688 -0
  21. package/docs/benchmarks/orp_reasoning_kernel_continuation_task_smoke.json +150 -0
  22. package/docs/benchmarks/orp_reasoning_kernel_continuation_v0_1.json +448 -0
  23. package/docs/benchmarks/orp_reasoning_kernel_pickup_v0_1.json +594 -0
  24. package/docs/benchmarks/orp_reasoning_kernel_v0_1_validation.json +769 -41
  25. package/examples/README.md +2 -0
  26. package/examples/kernel/comparison/comparison-corpus.json +337 -0
  27. package/examples/kernel/comparison/next-task-continuation.json +55 -0
  28. package/examples/kernel/corpus/operations/habanero-routing.checkpoint.kernel.yml +12 -0
  29. package/examples/kernel/corpus/operations/runner-routing.policy.kernel.yml +9 -0
  30. package/examples/kernel/corpus/product/project-home.decision.kernel.yml +11 -0
  31. package/examples/kernel/corpus/research/kernel-handoff.experiment.kernel.yml +16 -0
  32. package/examples/kernel/corpus/research/lane-drift.hypothesis.kernel.yml +11 -0
  33. package/examples/kernel/corpus/software/trace-widget.task.kernel.yml +13 -0
  34. package/examples/kernel/corpus/writing/kernel-launch.result.kernel.yml +12 -0
  35. package/package.json +4 -1
  36. package/scripts/orp-kernel-agent-pilot.py +673 -0
  37. package/scripts/orp-kernel-agent-replication.py +307 -0
  38. package/scripts/orp-kernel-benchmark.py +471 -2
  39. package/scripts/orp-kernel-canonical-continuation.py +381 -0
  40. package/scripts/orp-kernel-ci-check.py +138 -0
  41. package/scripts/orp-kernel-comparison.py +592 -0
  42. package/scripts/orp-kernel-continuation-pilot.py +384 -0
  43. package/scripts/orp-kernel-pickup.py +401 -0
  44. package/spec/v1/kernel-extension.schema.json +96 -0
  45. package/spec/v1/kernel-proposal.schema.json +115 -0
  46. package/spec/v1/kernel.schema.json +2 -1
@@ -2,8 +2,8 @@
2
2
  "schema_version": "1.0.0",
3
3
  "kind": "orp_reasoning_kernel_validation_report",
4
4
  "metadata": {
5
- "generated_at_utc": "2026-03-23T04:42:53Z",
6
- "repo_commit": "5c87faf4fbd54d203cc0ca05683544355c306d55",
5
+ "generated_at_utc": "2026-03-23T05:47:03Z",
6
+ "repo_commit": "c2f7f2a52744a00fb719d37de583da1f4ae615bd",
7
7
  "repo_branch": "main",
8
8
  "package_version": "0.4.7",
9
9
  "python_version": "3.9.6",
@@ -15,22 +15,22 @@
15
15
  "iterations": 5,
16
16
  "observed": {
17
17
  "init": {
18
- "mean_ms": 245.853,
19
- "median_ms": 242.029,
20
- "min_ms": 239.454,
21
- "max_ms": 257.57
18
+ "mean_ms": 242.098,
19
+ "median_ms": 241.566,
20
+ "min_ms": 239.332,
21
+ "max_ms": 246.235
22
22
  },
23
23
  "validate": {
24
- "mean_ms": 169.097,
25
- "median_ms": 167.938,
26
- "min_ms": 165.273,
27
- "max_ms": 173.245
24
+ "mean_ms": 162.684,
25
+ "median_ms": 163.009,
26
+ "min_ms": 160.644,
27
+ "max_ms": 164.874
28
28
  },
29
29
  "gate_run": {
30
- "mean_ms": 242.618,
31
- "median_ms": 239.599,
32
- "min_ms": 238.174,
33
- "max_ms": 252.913
30
+ "mean_ms": 239.282,
31
+ "median_ms": 239.591,
32
+ "min_ms": 235.63,
33
+ "max_ms": 242.402
34
34
  }
35
35
  },
36
36
  "targets": {
@@ -44,8 +44,8 @@
44
44
  "gate_run": true
45
45
  },
46
46
  "sample_run_records": [
47
- "orp/artifacts/run-20260323-044247-956825/RUN.json",
48
- "orp/artifacts/run-20260323-044248-621472/RUN.json"
47
+ "orp/artifacts/run-20260323-054649-399519/RUN.json",
48
+ "orp/artifacts/run-20260323-054650-067823/RUN.json"
49
49
  ]
50
50
  },
51
51
  "artifact_roundtrip": {
@@ -53,52 +53,52 @@
53
53
  "rows": [
54
54
  {
55
55
  "artifact_class": "task",
56
- "scaffold_ms": 162.963,
57
- "validate_ms": 161.02
56
+ "scaffold_ms": 163.862,
57
+ "validate_ms": 161.249
58
58
  },
59
59
  {
60
60
  "artifact_class": "decision",
61
- "scaffold_ms": 162.639,
62
- "validate_ms": 161.466
61
+ "scaffold_ms": 160.34,
62
+ "validate_ms": 160.534
63
63
  },
64
64
  {
65
65
  "artifact_class": "hypothesis",
66
- "scaffold_ms": 162.337,
67
- "validate_ms": 165.228
66
+ "scaffold_ms": 160.201,
67
+ "validate_ms": 162.374
68
68
  },
69
69
  {
70
70
  "artifact_class": "experiment",
71
- "scaffold_ms": 171.011,
72
- "validate_ms": 160.825
71
+ "scaffold_ms": 161.288,
72
+ "validate_ms": 161.434
73
73
  },
74
74
  {
75
75
  "artifact_class": "checkpoint",
76
- "scaffold_ms": 161.705,
77
- "validate_ms": 163.51
76
+ "scaffold_ms": 161.496,
77
+ "validate_ms": 161.043
78
78
  },
79
79
  {
80
80
  "artifact_class": "policy",
81
- "scaffold_ms": 160.807,
82
- "validate_ms": 163.85
81
+ "scaffold_ms": 161.216,
82
+ "validate_ms": 162.252
83
83
  },
84
84
  {
85
85
  "artifact_class": "result",
86
- "scaffold_ms": 163.882,
87
- "validate_ms": 162.509
86
+ "scaffold_ms": 161.431,
87
+ "validate_ms": 162.602
88
88
  }
89
89
  ],
90
90
  "observed": {
91
91
  "scaffold": {
92
- "mean_ms": 163.621,
93
- "median_ms": 162.639,
94
- "min_ms": 160.807,
95
- "max_ms": 171.011
92
+ "mean_ms": 161.405,
93
+ "median_ms": 161.288,
94
+ "min_ms": 160.201,
95
+ "max_ms": 163.862
96
96
  },
97
97
  "validate": {
98
- "mean_ms": 162.63,
99
- "median_ms": 162.509,
100
- "min_ms": 160.825,
101
- "max_ms": 165.228
98
+ "mean_ms": 161.641,
99
+ "median_ms": 161.434,
100
+ "min_ms": 160.534,
101
+ "max_ms": 162.602
102
102
  }
103
103
  },
104
104
  "targets": {
@@ -112,7 +112,7 @@
112
112
  },
113
113
  "gate_modes": {
114
114
  "hard_mode": {
115
- "ms": 174.339,
115
+ "ms": 172.719,
116
116
  "exit_code": 1,
117
117
  "overall": "FAIL",
118
118
  "kernel_valid": false,
@@ -122,13 +122,13 @@
122
122
  ]
123
123
  },
124
124
  "soft_mode": {
125
- "ms": 173.082,
125
+ "ms": 166.79,
126
126
  "exit_code": 0,
127
127
  "overall": "PASS",
128
128
  "kernel_valid": false
129
129
  },
130
130
  "legacy_compatibility": {
131
- "ms": 172.431,
131
+ "ms": 175.379,
132
132
  "exit_code": 0,
133
133
  "overall": "PASS",
134
134
  "has_kernel_validation": false
@@ -138,9 +138,701 @@
138
138
  "soft_allows_invalid_artifact_with_advisory": true,
139
139
  "legacy_structure_kernel_remains_compatible": true
140
140
  }
141
+ },
142
+ "schema_alignment": {
143
+ "schema_requirements": {
144
+ "task": [
145
+ "object",
146
+ "goal",
147
+ "boundary",
148
+ "constraints",
149
+ "success_criteria"
150
+ ],
151
+ "decision": [
152
+ "question",
153
+ "chosen_path",
154
+ "rejected_alternatives",
155
+ "rationale",
156
+ "consequences"
157
+ ],
158
+ "hypothesis": [
159
+ "claim",
160
+ "boundary",
161
+ "assumptions",
162
+ "test_path",
163
+ "falsifiers"
164
+ ],
165
+ "experiment": [
166
+ "objective",
167
+ "method",
168
+ "inputs",
169
+ "outputs",
170
+ "evidence_expectations",
171
+ "interpretation_limits"
172
+ ],
173
+ "checkpoint": [
174
+ "completed_unit",
175
+ "current_state",
176
+ "risks",
177
+ "next_handoff_target",
178
+ "artifact_refs"
179
+ ],
180
+ "policy": [
181
+ "scope",
182
+ "rule",
183
+ "rationale",
184
+ "invariants",
185
+ "enforcement_surface"
186
+ ],
187
+ "result": [
188
+ "claim",
189
+ "evidence_paths",
190
+ "status",
191
+ "interpretation_limits",
192
+ "next_follow_up"
193
+ ]
194
+ },
195
+ "cli_requirements": {
196
+ "task": [
197
+ "object",
198
+ "goal",
199
+ "boundary",
200
+ "constraints",
201
+ "success_criteria"
202
+ ],
203
+ "decision": [
204
+ "question",
205
+ "chosen_path",
206
+ "rejected_alternatives",
207
+ "rationale",
208
+ "consequences"
209
+ ],
210
+ "hypothesis": [
211
+ "claim",
212
+ "boundary",
213
+ "assumptions",
214
+ "test_path",
215
+ "falsifiers"
216
+ ],
217
+ "experiment": [
218
+ "objective",
219
+ "method",
220
+ "inputs",
221
+ "outputs",
222
+ "evidence_expectations",
223
+ "interpretation_limits"
224
+ ],
225
+ "checkpoint": [
226
+ "completed_unit",
227
+ "current_state",
228
+ "risks",
229
+ "next_handoff_target",
230
+ "artifact_refs"
231
+ ],
232
+ "policy": [
233
+ "scope",
234
+ "rule",
235
+ "rationale",
236
+ "invariants",
237
+ "enforcement_surface"
238
+ ],
239
+ "result": [
240
+ "claim",
241
+ "evidence_paths",
242
+ "status",
243
+ "interpretation_limits",
244
+ "next_follow_up"
245
+ ]
246
+ },
247
+ "schema_fields_total": 37,
248
+ "cli_fields_total": 37,
249
+ "meets_expectations": {
250
+ "requirements_match": true,
251
+ "fields_match": true
252
+ }
253
+ },
254
+ "cross_domain_corpus": {
255
+ "fixtures_total": 7,
256
+ "domains_total": 5,
257
+ "artifact_classes_total": 7,
258
+ "rows": [
259
+ {
260
+ "fixture": "operations/habanero-routing.checkpoint.kernel.yml",
261
+ "domain": "operations",
262
+ "artifact_class": "checkpoint",
263
+ "validate_ms": 170.231
264
+ },
265
+ {
266
+ "fixture": "operations/runner-routing.policy.kernel.yml",
267
+ "domain": "operations",
268
+ "artifact_class": "policy",
269
+ "validate_ms": 172.243
270
+ },
271
+ {
272
+ "fixture": "product/project-home.decision.kernel.yml",
273
+ "domain": "product",
274
+ "artifact_class": "decision",
275
+ "validate_ms": 171.039
276
+ },
277
+ {
278
+ "fixture": "research/kernel-handoff.experiment.kernel.yml",
279
+ "domain": "research",
280
+ "artifact_class": "experiment",
281
+ "validate_ms": 170.106
282
+ },
283
+ {
284
+ "fixture": "research/lane-drift.hypothesis.kernel.yml",
285
+ "domain": "research",
286
+ "artifact_class": "hypothesis",
287
+ "validate_ms": 170.106
288
+ },
289
+ {
290
+ "fixture": "software/trace-widget.task.kernel.yml",
291
+ "domain": "software",
292
+ "artifact_class": "task",
293
+ "validate_ms": 170.004
294
+ },
295
+ {
296
+ "fixture": "writing/kernel-launch.result.kernel.yml",
297
+ "domain": "writing",
298
+ "artifact_class": "result",
299
+ "validate_ms": 165.422
300
+ }
301
+ ],
302
+ "observed": {
303
+ "validate": {
304
+ "mean_ms": 169.879,
305
+ "median_ms": 170.106,
306
+ "min_ms": 165.422,
307
+ "max_ms": 172.243
308
+ }
309
+ },
310
+ "targets": {
311
+ "domains_min": 5,
312
+ "fixtures_min": 7,
313
+ "validate_mean_lt_ms": 200.0
314
+ },
315
+ "meets_targets": {
316
+ "domains": true,
317
+ "fixtures": true,
318
+ "validate": true
319
+ }
320
+ },
321
+ "requirement_enforcement": {
322
+ "cases_total": 36,
323
+ "rows": [
324
+ {
325
+ "artifact_class": "task",
326
+ "removed_field": "object",
327
+ "exit_code": 1,
328
+ "valid": false,
329
+ "missing_fields": [
330
+ "object"
331
+ ],
332
+ "validate_ms": 151.206
333
+ },
334
+ {
335
+ "artifact_class": "task",
336
+ "removed_field": "goal",
337
+ "exit_code": 1,
338
+ "valid": false,
339
+ "missing_fields": [
340
+ "goal"
341
+ ],
342
+ "validate_ms": 149.479
343
+ },
344
+ {
345
+ "artifact_class": "task",
346
+ "removed_field": "boundary",
347
+ "exit_code": 1,
348
+ "valid": false,
349
+ "missing_fields": [
350
+ "boundary"
351
+ ],
352
+ "validate_ms": 153.563
353
+ },
354
+ {
355
+ "artifact_class": "task",
356
+ "removed_field": "constraints",
357
+ "exit_code": 1,
358
+ "valid": false,
359
+ "missing_fields": [
360
+ "constraints"
361
+ ],
362
+ "validate_ms": 153.891
363
+ },
364
+ {
365
+ "artifact_class": "task",
366
+ "removed_field": "success_criteria",
367
+ "exit_code": 1,
368
+ "valid": false,
369
+ "missing_fields": [
370
+ "success_criteria"
371
+ ],
372
+ "validate_ms": 153.669
373
+ },
374
+ {
375
+ "artifact_class": "decision",
376
+ "removed_field": "question",
377
+ "exit_code": 1,
378
+ "valid": false,
379
+ "missing_fields": [
380
+ "question"
381
+ ],
382
+ "validate_ms": 154.283
383
+ },
384
+ {
385
+ "artifact_class": "decision",
386
+ "removed_field": "chosen_path",
387
+ "exit_code": 1,
388
+ "valid": false,
389
+ "missing_fields": [
390
+ "chosen_path"
391
+ ],
392
+ "validate_ms": 153.467
393
+ },
394
+ {
395
+ "artifact_class": "decision",
396
+ "removed_field": "rejected_alternatives",
397
+ "exit_code": 1,
398
+ "valid": false,
399
+ "missing_fields": [
400
+ "rejected_alternatives"
401
+ ],
402
+ "validate_ms": 153.983
403
+ },
404
+ {
405
+ "artifact_class": "decision",
406
+ "removed_field": "rationale",
407
+ "exit_code": 1,
408
+ "valid": false,
409
+ "missing_fields": [
410
+ "rationale"
411
+ ],
412
+ "validate_ms": 154.418
413
+ },
414
+ {
415
+ "artifact_class": "decision",
416
+ "removed_field": "consequences",
417
+ "exit_code": 1,
418
+ "valid": false,
419
+ "missing_fields": [
420
+ "consequences"
421
+ ],
422
+ "validate_ms": 154.753
423
+ },
424
+ {
425
+ "artifact_class": "hypothesis",
426
+ "removed_field": "claim",
427
+ "exit_code": 1,
428
+ "valid": false,
429
+ "missing_fields": [
430
+ "claim"
431
+ ],
432
+ "validate_ms": 154.362
433
+ },
434
+ {
435
+ "artifact_class": "hypothesis",
436
+ "removed_field": "boundary",
437
+ "exit_code": 1,
438
+ "valid": false,
439
+ "missing_fields": [
440
+ "boundary"
441
+ ],
442
+ "validate_ms": 154.27
443
+ },
444
+ {
445
+ "artifact_class": "hypothesis",
446
+ "removed_field": "assumptions",
447
+ "exit_code": 1,
448
+ "valid": false,
449
+ "missing_fields": [
450
+ "assumptions"
451
+ ],
452
+ "validate_ms": 153.622
453
+ },
454
+ {
455
+ "artifact_class": "hypothesis",
456
+ "removed_field": "test_path",
457
+ "exit_code": 1,
458
+ "valid": false,
459
+ "missing_fields": [
460
+ "test_path"
461
+ ],
462
+ "validate_ms": 154.244
463
+ },
464
+ {
465
+ "artifact_class": "hypothesis",
466
+ "removed_field": "falsifiers",
467
+ "exit_code": 1,
468
+ "valid": false,
469
+ "missing_fields": [
470
+ "falsifiers"
471
+ ],
472
+ "validate_ms": 157.235
473
+ },
474
+ {
475
+ "artifact_class": "experiment",
476
+ "removed_field": "objective",
477
+ "exit_code": 1,
478
+ "valid": false,
479
+ "missing_fields": [
480
+ "objective"
481
+ ],
482
+ "validate_ms": 160.037
483
+ },
484
+ {
485
+ "artifact_class": "experiment",
486
+ "removed_field": "method",
487
+ "exit_code": 1,
488
+ "valid": false,
489
+ "missing_fields": [
490
+ "method"
491
+ ],
492
+ "validate_ms": 157.138
493
+ },
494
+ {
495
+ "artifact_class": "experiment",
496
+ "removed_field": "inputs",
497
+ "exit_code": 1,
498
+ "valid": false,
499
+ "missing_fields": [
500
+ "inputs"
501
+ ],
502
+ "validate_ms": 153.241
503
+ },
504
+ {
505
+ "artifact_class": "experiment",
506
+ "removed_field": "outputs",
507
+ "exit_code": 1,
508
+ "valid": false,
509
+ "missing_fields": [
510
+ "outputs"
511
+ ],
512
+ "validate_ms": 154.474
513
+ },
514
+ {
515
+ "artifact_class": "experiment",
516
+ "removed_field": "evidence_expectations",
517
+ "exit_code": 1,
518
+ "valid": false,
519
+ "missing_fields": [
520
+ "evidence_expectations"
521
+ ],
522
+ "validate_ms": 154.047
523
+ },
524
+ {
525
+ "artifact_class": "experiment",
526
+ "removed_field": "interpretation_limits",
527
+ "exit_code": 1,
528
+ "valid": false,
529
+ "missing_fields": [
530
+ "interpretation_limits"
531
+ ],
532
+ "validate_ms": 154.142
533
+ },
534
+ {
535
+ "artifact_class": "checkpoint",
536
+ "removed_field": "completed_unit",
537
+ "exit_code": 1,
538
+ "valid": false,
539
+ "missing_fields": [
540
+ "completed_unit"
541
+ ],
542
+ "validate_ms": 154.101
543
+ },
544
+ {
545
+ "artifact_class": "checkpoint",
546
+ "removed_field": "current_state",
547
+ "exit_code": 1,
548
+ "valid": false,
549
+ "missing_fields": [
550
+ "current_state"
551
+ ],
552
+ "validate_ms": 154.003
553
+ },
554
+ {
555
+ "artifact_class": "checkpoint",
556
+ "removed_field": "risks",
557
+ "exit_code": 1,
558
+ "valid": false,
559
+ "missing_fields": [
560
+ "risks"
561
+ ],
562
+ "validate_ms": 153.065
563
+ },
564
+ {
565
+ "artifact_class": "checkpoint",
566
+ "removed_field": "next_handoff_target",
567
+ "exit_code": 1,
568
+ "valid": false,
569
+ "missing_fields": [
570
+ "next_handoff_target"
571
+ ],
572
+ "validate_ms": 161.153
573
+ },
574
+ {
575
+ "artifact_class": "checkpoint",
576
+ "removed_field": "artifact_refs",
577
+ "exit_code": 1,
578
+ "valid": false,
579
+ "missing_fields": [
580
+ "artifact_refs"
581
+ ],
582
+ "validate_ms": 157.553
583
+ },
584
+ {
585
+ "artifact_class": "policy",
586
+ "removed_field": "scope",
587
+ "exit_code": 1,
588
+ "valid": false,
589
+ "missing_fields": [
590
+ "scope"
591
+ ],
592
+ "validate_ms": 153.638
593
+ },
594
+ {
595
+ "artifact_class": "policy",
596
+ "removed_field": "rule",
597
+ "exit_code": 1,
598
+ "valid": false,
599
+ "missing_fields": [
600
+ "rule"
601
+ ],
602
+ "validate_ms": 153.723
603
+ },
604
+ {
605
+ "artifact_class": "policy",
606
+ "removed_field": "rationale",
607
+ "exit_code": 1,
608
+ "valid": false,
609
+ "missing_fields": [
610
+ "rationale"
611
+ ],
612
+ "validate_ms": 153.539
613
+ },
614
+ {
615
+ "artifact_class": "policy",
616
+ "removed_field": "invariants",
617
+ "exit_code": 1,
618
+ "valid": false,
619
+ "missing_fields": [
620
+ "invariants"
621
+ ],
622
+ "validate_ms": 153.346
623
+ },
624
+ {
625
+ "artifact_class": "policy",
626
+ "removed_field": "enforcement_surface",
627
+ "exit_code": 1,
628
+ "valid": false,
629
+ "missing_fields": [
630
+ "enforcement_surface"
631
+ ],
632
+ "validate_ms": 153.484
633
+ },
634
+ {
635
+ "artifact_class": "result",
636
+ "removed_field": "claim",
637
+ "exit_code": 1,
638
+ "valid": false,
639
+ "missing_fields": [
640
+ "claim"
641
+ ],
642
+ "validate_ms": 152.901
643
+ },
644
+ {
645
+ "artifact_class": "result",
646
+ "removed_field": "evidence_paths",
647
+ "exit_code": 1,
648
+ "valid": false,
649
+ "missing_fields": [
650
+ "evidence_paths"
651
+ ],
652
+ "validate_ms": 153.866
653
+ },
654
+ {
655
+ "artifact_class": "result",
656
+ "removed_field": "status",
657
+ "exit_code": 1,
658
+ "valid": false,
659
+ "missing_fields": [
660
+ "status"
661
+ ],
662
+ "validate_ms": 155.082
663
+ },
664
+ {
665
+ "artifact_class": "result",
666
+ "removed_field": "interpretation_limits",
667
+ "exit_code": 1,
668
+ "valid": false,
669
+ "missing_fields": [
670
+ "interpretation_limits"
671
+ ],
672
+ "validate_ms": 151.325
673
+ },
674
+ {
675
+ "artifact_class": "result",
676
+ "removed_field": "next_follow_up",
677
+ "exit_code": 1,
678
+ "valid": false,
679
+ "missing_fields": [
680
+ "next_follow_up"
681
+ ],
682
+ "validate_ms": 154.766
683
+ }
684
+ ],
685
+ "observed": {
686
+ "validate": {
687
+ "mean_ms": 154.307,
688
+ "median_ms": 153.993,
689
+ "min_ms": 149.479,
690
+ "max_ms": 161.153
691
+ }
692
+ },
693
+ "targets": {
694
+ "all_cases_detected": 36,
695
+ "validate_mean_lt_ms": 200.0
696
+ },
697
+ "meets_targets": {
698
+ "all_cases_detected": true,
699
+ "validate": true
700
+ }
701
+ },
702
+ "representation_invariance": {
703
+ "yaml_ms": 164.585,
704
+ "json_ms": 153.267,
705
+ "yaml_result": {
706
+ "path": "analysis/task.kernel.yml",
707
+ "exists": true,
708
+ "required": true,
709
+ "optional_skipped": false,
710
+ "artifact_class": "task",
711
+ "expected_artifact_class": "",
712
+ "valid": true,
713
+ "missing_fields": [],
714
+ "issues": []
715
+ },
716
+ "json_result": {
717
+ "path": "analysis/task.kernel.json",
718
+ "exists": true,
719
+ "required": true,
720
+ "optional_skipped": false,
721
+ "artifact_class": "task",
722
+ "expected_artifact_class": "",
723
+ "valid": true,
724
+ "missing_fields": [],
725
+ "issues": []
726
+ },
727
+ "meets_expectations": {
728
+ "both_valid": true,
729
+ "equivalent_results": true
730
+ }
731
+ },
732
+ "mutation_stress": {
733
+ "cases_total": 7,
734
+ "rows": [
735
+ {
736
+ "id": "unexpected_field",
737
+ "exit_code": 1,
738
+ "issues": [
739
+ "unexpected field: `mystery_field`."
740
+ ],
741
+ "validate_ms": 148.036,
742
+ "matched_expected_issue": true
743
+ },
744
+ {
745
+ "id": "whitespace_only_text",
746
+ "exit_code": 1,
747
+ "issues": [
748
+ "field `object` must be a non-empty string or a non-empty list of non-empty strings.",
749
+ "missing required fields: object"
750
+ ],
751
+ "validate_ms": 151.943,
752
+ "matched_expected_issue": true
753
+ },
754
+ {
755
+ "id": "wrong_text_list_type",
756
+ "exit_code": 1,
757
+ "issues": [
758
+ "field `constraints` must be a non-empty string or a non-empty list of non-empty strings.",
759
+ "missing required fields: constraints"
760
+ ],
761
+ "validate_ms": 153.881,
762
+ "matched_expected_issue": true
763
+ },
764
+ {
765
+ "id": "non_string_list_item",
766
+ "exit_code": 1,
767
+ "issues": [
768
+ "field `evidence_paths` must be a non-empty list of non-empty strings.",
769
+ "missing required fields: evidence_paths"
770
+ ],
771
+ "validate_ms": 157.17,
772
+ "matched_expected_issue": true
773
+ },
774
+ {
775
+ "id": "unsupported_artifact_class",
776
+ "exit_code": 1,
777
+ "issues": [
778
+ "field `artifact_class` must be one of: task, decision, hypothesis, experiment, checkpoint, policy, result.",
779
+ "unsupported artifact_class: memo.",
780
+ "artifact_class mismatch: expected `task`, found `memo`.",
781
+ "field `artifact_class` must be one of: task, decision, hypothesis, experiment, checkpoint, policy, result."
782
+ ],
783
+ "validate_ms": 156.95,
784
+ "matched_expected_issue": true
785
+ },
786
+ {
787
+ "id": "wrong_schema_version",
788
+ "exit_code": 1,
789
+ "issues": [
790
+ "field `schema_version` must equal `1.0.0`.",
791
+ "field `schema_version` must equal `1.0.0`."
792
+ ],
793
+ "validate_ms": 150.621,
794
+ "matched_expected_issue": true
795
+ },
796
+ {
797
+ "id": "empty_list",
798
+ "exit_code": 1,
799
+ "issues": [
800
+ "field `boundary` must be a non-empty string or a non-empty list of non-empty strings.",
801
+ "missing required fields: boundary"
802
+ ],
803
+ "validate_ms": 149.948,
804
+ "matched_expected_issue": true
805
+ }
806
+ ],
807
+ "observed": {
808
+ "validate": {
809
+ "mean_ms": 152.65,
810
+ "median_ms": 151.943,
811
+ "min_ms": 148.036,
812
+ "max_ms": 157.17
813
+ }
814
+ },
815
+ "targets": {
816
+ "cases_total": 7,
817
+ "validate_mean_lt_ms": 200.0
818
+ },
819
+ "meets_targets": {
820
+ "all_cases_detected": true,
821
+ "validate": true
822
+ }
141
823
  }
142
824
  },
143
825
  "claims": [
826
+ {
827
+ "id": "schema_validator_alignment",
828
+ "claim": "The CLI kernel requirements and allowed fields stay aligned with the published kernel schema.",
829
+ "status": "pass",
830
+ "evidence": [
831
+ "benchmarks.schema_alignment",
832
+ "spec/v1/kernel.schema.json",
833
+ "cli/orp.py"
834
+ ]
835
+ },
144
836
  {
145
837
  "id": "starter_kernel_bootstrap",
146
838
  "claim": "orp init seeds a valid starter kernel artifact and a passing default structure_kernel gate.",
@@ -187,11 +879,47 @@
187
879
  "benchmarks.init_starter_kernel",
188
880
  "benchmarks.artifact_roundtrip"
189
881
  ]
882
+ },
883
+ {
884
+ "id": "cross_domain_corpus_fit",
885
+ "claim": "The current v0.1 kernel class set fits a small cross-domain reference corpus cleanly.",
886
+ "status": "pass",
887
+ "evidence": [
888
+ "benchmarks.cross_domain_corpus",
889
+ "examples/kernel/corpus"
890
+ ]
891
+ },
892
+ {
893
+ "id": "class_specific_requirement_enforcement",
894
+ "claim": "Each kernel artifact class rejects a candidate artifact when a required field is removed.",
895
+ "status": "pass",
896
+ "evidence": [
897
+ "benchmarks.requirement_enforcement",
898
+ "spec/v1/kernel.schema.json"
899
+ ]
900
+ },
901
+ {
902
+ "id": "representation_invariance",
903
+ "claim": "Equivalent YAML and JSON kernel artifacts validate to the same semantic result.",
904
+ "status": "pass",
905
+ "evidence": [
906
+ "benchmarks.representation_invariance"
907
+ ]
908
+ },
909
+ {
910
+ "id": "adversarial_mutation_detection",
911
+ "claim": "The validator rejects adversarial near-miss artifacts such as unknown fields, wrong types, whitespace-only text, and bad schema metadata.",
912
+ "status": "pass",
913
+ "evidence": [
914
+ "benchmarks.mutation_stress",
915
+ "spec/v1/kernel.schema.json"
916
+ ]
190
917
  }
191
918
  ],
192
919
  "summary": {
193
920
  "all_claims_pass": true,
194
921
  "artifact_classes_total": 7,
922
+ "cross_domain_corpus_domains_total": 5,
195
923
  "all_performance_targets_met": true
196
924
  }
197
925
  }