core/evals
Shay 896e90a92b
Some checks failed
smoke / smoke (-m "not quarantine") (pull_request) Failing after 1m1s
lane-shas / verify pinned lane SHAs (pull_request) Failing after 47s
fix(third-door): align with perfected package contracts from Downloads artifacts (refs #10 #11 #12 #13)
Source artifacts from the multi-model landing package (README + Super-Blueprint
+ ADR-0238/0239/0240 + goldtether/dynamic_manifold/surprise) are now the
contractual surface, implemented on the live algebra/* kernel:

- GoldTetherMonitor.residual/update/may_relax_hitl/force_reset/autonomy
- signature_aware_pca (5×K, null-safe), conformal_procrustes, cartan_iwasawa_extract
- surprise_residual (Minkowski) + dual_procrustes_surprise audit dict

Package stubs (core.algebra.backend placeholders, scipy, identity-only
Procrustes) are replaced with dual-corrected Cl(4,1) operators. ADRs match
package decision language; docs/adr remains canonical with decisions redirects.

34/34 Third-Door tests + 7/7 ADR-0199 arena regression green.
2026-07-11 22:05:02 -07:00
..
adversarial_identity
analogical_transfer fix(third-door): align with perfected package contracts from Downloads artifacts (refs #10 #11 #12 #13) 2026-07-11 22:05:02 -07:00
anchor_lens_tour
anti_regression feat: strengthen visibility and measurement of CLOSE flywheel proposal review/ratification side (#794) 2026-06-16 19:33:25 -07:00
articulation
articulation_of_status
audio_sensorium
audit_tour chore: Refactor CLI and Governance Anchors (#926) 2026-07-03 12:34:56 -07:00
calibration chore: Refactor CLI and Governance Anchors (#926) 2026-07-03 12:34:56 -07:00
capability_index feat(reader): add overlaps_event finite-verb reader surface (B3) (#783) 2026-06-15 14:56:09 -07:00
classical_literature_ood
close_derived_climb chore: Refactor CLI and Governance Anchors (#926) 2026-07-03 12:34:56 -07:00
cognition
cold_start_grounding
combined_rate_oracle docs(cmb): lookback review + fix single-agent-attribution hygiene hazard (H3) 2026-06-08 13:27:17 -07:00
compositionality
compound_intent_decomposition
comprehension feat: one-hop sound relational entailment (inverse/symmetric) + capability-index lane (#775) 2026-06-15 11:39:41 -07:00
constraint_oracle feat(verified): P1-C — split bound_slots_digest into separate obligation 2026-06-08 17:17:31 -07:00
contemplation_quality
contradiction_detection
conversation
conversational_thread_coherence
cross_domain_transfer
curriculum_loop_closure
deductive_logic
demo_composition chore: refresh canonical demo lane reports after 3lang depth re-pin 2026-07-08 07:15:46 -07:00
determination_closure
determination_estimation Lane 4: Registry Consolidation (language_packs to packs) 2026-07-04 15:11:28 -07:00
deterministic_fluency
dimensional
discourse_paragraph
domain_contract_validation
edge_budget chore: Refactor CLI and Governance Anchors (#926) 2026-07-03 12:34:56 -07:00
elementary_mathematics_ood
english_fluency_ood
environment_falsification
event_vision_sensorium
fabrication_control
field_incidence work done towards furthering comprehension, contemplation, learning, and also began working on fixing some failing tests 2026-06-16 12:27:59 -07:00
flywheel_demo Lane 4: Registry Consolidation (language_packs to packs) 2026-07-04 15:11:28 -07:00
forward_semantic_control Lane 4: Registry Consolidation (language_packs to packs) 2026-07-04 15:11:28 -07:00
foundational_biology_ood
foundational_physics_ood
frame_verdict_text_cwa feat(frame-verdict): closed-world FrameVerdict substrate — PR-1..4 + hardening (ADR-0222 B4) (#787) 2026-06-16 06:23:03 -07:00
frontier_compare
generalization feat(evals): implement safe metadata and fail-closed evaluator check for GSM1K 2026-06-23 07:52:32 -07:00
grammatical_coverage
gsm8k_math fix: fold Gemini CGA/fraction_decrease compatibility into deck PR 2026-07-08 20:00:51 -07:00
gsm8k_parser_dev
hebrew_fluency
identity_divergence
industry_demos Lane 4: Registry Consolidation (language_packs to packs) 2026-07-04 15:11:28 -07:00
inference_closure
introspection
koine_greek_fluency
l10_always_on feat(identity): split engine identity from build provenance (ADR-0220 PR C) (#774) 2026-06-15 11:38:04 -07:00
l10_continuity test(l10): W2-R arbitrary-interruption recovery harness (ADR-0219) 2026-06-15 02:45:29 -07:00
lab
learning_arc feat(workbench): add UI catch-up evidence scaffolding (#891) 2026-06-23 10:09:45 -07:00
learning_loop fix(ci): re-pin public_demo lane SHA after showcase content drift (#807) 2026-06-17 15:42:40 -07:00
long_context_cost
math_bounded_grammar/v1
math_capability_axes
math_expert_claims/v1
math_symbolic_equivalence
math_teaching_corpus/v1
miner_loop_closure
monotonic_learning
multi_agent_composition
multi_sentence_response
multi_step_reasoning
obligation_2_ood_ratio
obligation_5_perturbation
obligation_6_depth_curve
obligation_8_adversarial
obligation_10_pack_provenance
orthogonality_tour
prompt_diversity
proof_carrying_promotion_demo feat(demos): Implement ADR-0218 PR D proof-carrying promotion demo (#927) 2026-07-03 13:01:49 -07:00
proofwriter_owa feat(eval): ProofWriter-OWA refusal-floor lane (B1) — independent oracle, measure-only (#779) 2026-06-15 12:28:20 -07:00
propositional_logic
provenance
public_demo feat: close 3-lang depth deck — same-turn roots, capability pins, public_demo budget 2026-07-08 19:15:34 -07:00
rate_oracle
realizer_guard
refusal_calibration
refusal_taxonomy fix: green test-fast suite, consolidate ADR graph under docs/adr, and complete governance cohesion anchors 2026-06-30 17:56:12 -07:00
register_diagnostics
register_tour fix(ci): re-pin public_demo lane SHA after showcase content drift (#807) 2026-06-17 15:42:40 -07:00
relational feat(reader): add overlaps_event finite-verb reader surface (B3) (#783) 2026-06-15 14:56:09 -07:00
relational_inference/v1 feat(reader): add overlaps_event finite-verb reader surface (B3) (#783) 2026-06-15 14:56:09 -07:00
relational_metric
relational_transitive feat(determine): add transitive strict-order relational inference (#781) 2026-06-15 14:20:30 -07:00
reports Lane 4: Registry Consolidation (language_packs to packs) 2026-07-04 15:11:28 -07:00
results
reviewer_registry
sample_efficiency
self_consistency_over_time
sensorimotor_sensorium
sensorium
set_membership
setup_oracle
syllogism
symbolic_logic
teaching_injection_resistance
total_ordering
vision_sensorium
walkthrough_chain
warmed_session_consistency
zero_code_domain_acquisition
__init__.py
_parallel.py
baseline_runner.py
CLAIMS.md Lane 4: Registry Consolidation (language_packs to packs) 2026-07-04 15:11:28 -07:00
cognition_cases.jsonl
framework.py
holdout_runner.py
metrics.py
parallel.py
run_cognition_eval.py