elder-plinius/OBLITERATUS

Pattern Findings

The scanner identified 5960 distinct pattern matches across 22 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a detector match to inspect in context. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.

Reading the findings table: The Severity column indicates the configured finding weight (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — legacy comment-context matches receive a ×1.5 score weight. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier under the legacy scoring model.

Hyper-Verbose Identifiers3791 hits · 3462 pts

Severity	File	Line	Snippet	Context
LOW	app.py	172	def _resolve_local_checkpoint(checkpoint: str \| Path) -> Path:	CODE
LOW	app.py	228	def _reload_active_chat_model():	CODE
LOW	app.py	232	def _format_checkpoint_reload_error(error: BaseException) -> str:	CODE
LOW	app.py	248	def _pipeline_timeout_seconds() -> int:	CODE
LOW	app.py	382	def _recover_sessions_from_disk() -> None:	CODE
LOW	app.py	968	def _resolve_ui_load_settings(	CODE
LOW	app.py	1241	def _format_obliteration_metrics(	CODE
LOW	app.py	1725	def _format_benchmark_results(results: list[dict], context: dict \| None = None) -> str:	CODE
LOW	app.py	2104	def _format_multi_model_results(results: list[dict], context: dict \| None = None) -> str:	CODE
LOW	app.py	3142	def _get_session_model_choices():	CODE
LOW	tests/test_phase_repair_admission.py	95	def test_capture_planner_never_scans_or_clones_weight_values(monkeypatch):	CODE
LOW	tests/test_phase_repair_admission.py	114	def test_capture_uses_identical_selected_writer_layout(projection_target):	CODE
LOW	tests/test_phase_repair_admission.py	131	def test_capture_charges_actual_writer_dtype(dtype):	CODE
LOW	tests/test_phase_repair_admission.py	146	def test_alias_writer_names_match_capture_and_conflicting_directions_reject():	CODE
LOW	tests/test_phase_repair_admission.py	161	def test_offloaded_repair_metadata_never_reads_backing_values():	CODE
LOW	tests/test_phase_repair_admission.py	170	def test_activation_pairs_have_shared_selection_and_retained_concat_charge(tmp_path, monkeypatch):	CODE
LOW	tests/test_phase_repair_admission.py	189	def test_excise_bound_covers_actual_candidates_and_svd_tensor_lifetimes(cpu_threads):	CODE
LOW	tests/test_phase_repair_admission.py	209	def test_lora_rank_slices_retain_full_vh_backing_in_admission_bound():	CODE
LOW	tests/test_phase_repair_admission.py	224	def test_excise_admission_adds_repair_bound_and_excludes_existing_pristine(	CODE
LOW	tests/test_phase_repair_admission.py	240	def test_fitting_repair_admission_preserves_snapshots_weights_rng_and_logs(tmp_path, monkeypatch):	CODE
LOW	tests/test_phase_repair_admission.py	285	def test_cuda_capture_scan_demand_is_per_device_and_sequential():	CODE
LOW	tests/test_phase_repair_admission.py	294	def test_busy_cuda_repair_scan_rejects_before_snapshot_capture(tmp_path, monkeypatch, caplog):	CODE
LOW	tests/test_phase_repair_admission.py	325	def test_adapter_forward_workspace_scales_with_rank_and_batch_per_writer_device(dtype):	CODE
LOW	tests/test_phase_repair_admission.py	341	def test_model_phase_workspace_uses_sequential_max_and_overlapping_forward_addition():	CODE
LOW	tests/test_phase_repair_admission.py	362	def test_invalid_device_workspace_fails_closed(workspace):	CODE
LOW	tests/test_phase_repair_admission.py	377	def test_pipeline_passes_adapter_overlap_with_actual_maximum_batch_tokens(tmp_path, monkeypatch):	CODE
LOW	tests/test_phase_repair_admission.py	393	def test_verify_includes_only_an_installed_repair_adapters_workspace(	CODE
LOW	tests/test_ui_model_slot.py	165	def test_checkpoint_switch_publishes_only_after_loading(slot):	CODE
LOW	tests/test_ui_model_slot.py	182	def test_explicit_checkpoint_failure_restores_recoverable_metadata(slot, failure):	CODE
LOW	tests/test_ui_model_slot.py	198	def test_auto_checkpoint_retry_changes_only_quantization(slot, monkeypatch):	CODE
LOW	tests/test_ui_model_slot.py	228	def test_auto_fallback_failure_rolls_back(slot, monkeypatch):	CODE
LOW	tests/test_ui_model_slot.py	241	def test_pre_unload_failures_preserve_resident(slot, failure_point):	CODE
LOW	tests/test_ui_model_slot.py	254	def test_switch_failure_before_worker_start_restores_metadata(slot, point):	CODE
LOW	tests/test_ui_model_slot.py	273	def test_thread_start_failure_never_hands_off_ownership(slot):	CODE
LOW	tests/test_ui_model_slot.py	289	def test_pipeline_success_publishes_without_cleanup(slot):	CODE
LOW	tests/test_ui_model_slot.py	301	def test_worker_failure_and_post_pipeline_failure_cleanup_once(slot, point):	CODE
LOW	tests/test_ui_model_slot.py	331	def test_live_worker_retains_claim_until_abandoned_cleanup_finishes(slot, outcome):	CODE
LOW	tests/test_ui_model_slot.py	402	def test_claim_is_held_through_all_pipeline_cleanup_steps(slot, blocked_step):	CODE
LOW	tests/test_ui_model_slot.py	441	def test_same_model_shortcuts_release_lock_before_header(slot):	CODE
LOW	tests/test_ui_model_slot.py	454	def test_skip_session_load_and_recovery_shortcuts(slot):	CODE
LOW	tests/test_ui_model_slot.py	467	def test_occupied_slot_refuses_all_load_entry_points(slot, entry):	CODE
LOW	tests/test_ui_model_slot.py	485	def test_checkpoint_reload_applies_saved_steering_and_settings(slot, entry):	CODE
LOW	tests/test_ui_model_slot.py	503	def test_failed_reload_drops_stale_model_and_preserves_checkpoint(slot, entry):	CODE
LOW	tests/test_ui_model_slot.py	520	def test_reload_recovers_latest_session_into_claim_snapshot(slot):	CODE
LOW	tests/test_ui_model_slot.py	535	def test_missing_checkpoint_recovery_clears_unrecoverable_slot(slot, entry):	CODE
LOW	tests/test_ui_model_slot.py	547	def test_reload_publication_checks_checkpoint_identity(slot):	CODE
LOW	tests/test_ui_model_slot.py	565	def test_promote_success_and_changed_selection(slot):	CODE
LOW	tests/test_ui_model_slot.py	579	def test_promotion_failure_drops_refs_before_releasing_claim(slot, point):	CODE
LOW	tests/test_ui_model_slot.py	612	def test_reload_errors_keep_user_facing_categories(slot, error, expected):	CODE
LOW	tests/test_ui_model_slot.py	626	def test_owned_generator_acquires_late_and_preserves_pre_unload_resident(slot, owner):	CODE
LOW	tests/test_ui_model_slot.py	643	def test_owned_generator_refused_claim_never_cleans_other_owner(slot, owner):	CODE
LOW	tests/test_ui_model_slot.py	656	def test_owned_generator_error_drops_frame_before_cleanup_and_rollback(slot, owner):	CODE
LOW	tests/test_ui_model_slot.py	690	def test_owned_worker_start_failure_cleans_synchronously(slot, owner):	CODE
LOW	tests/test_ui_model_slot.py	709	def test_owned_worker_handoff_keeps_claim_until_cleanup(slot, owner, timing, reason):	CODE
LOW	tests/test_ui_model_slot.py	739	def test_owned_cleanup_clears_pipeline_and_tracebacks_even_when_cleanup_raises(slot, owner, discard_output):	CODE
LOW	tests/test_ui_model_slot.py	764	def test_owned_commit_keeps_publication_and_close_cannot_touch_next_claim(slot, owner):	CODE
LOW	tests/test_ui_model_slot.py	784	def test_switch_cleans_materialized_model_when_checkpoint_resolution_fails(slot):	CODE
LOW	tests/test_ui_model_slot.py	795	def test_switch_discarded_publication_never_overwrites_next_owner(slot):	CODE
LOW	tests/test_ui_model_slot.py	813	def test_pipeline_cleanup_exception_cannot_prevent_rollback(slot):	CODE
LOW	tests/test_ui_model_slot.py	833	def test_switch_fatal_progress_exception_rolls_back_then_propagates(slot):	CODE
3731 more matches not shown…

Decorative Section Separators638 hits · 1882 pts

Severity	File	Line	Snippet	Context
MEDIUM⚡	app.py	1182	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	app.py	1184	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	app.py	1191	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	app.py	1193	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	app.py	30	# ── Container environment fixes ──────────────────────────────────────	COMMENT
MEDIUM	app.py	96	# ── ZeroGPU support ─────────────────────────────────────────────────	COMMENT
MEDIUM	app.py	323	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	app.py	325	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	app.py	361	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	app.py	363	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	app.py	449	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	app.py	451	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	app.py	539	# ── Community Hub push ────────────────────────────────────────────────	COMMENT
MEDIUM	app.py	682	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	app.py	684	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	app.py	998	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	app.py	1000	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	app.py	1227	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	app.py	1229	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	app.py	1784	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	app.py	1786	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	app.py	2954	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	app.py	2956	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	app.py	3153	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	app.py	3155	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	app.py	3266	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	app.py	3268	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	app.py	3483	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	app.py	3485	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	app.py	3724	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	app.py	3726	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	app.py	3859	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	app.py	3861	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	app.py	5416	# ── Tab 8: About ──────────────────────────────────────────────────	COMMENT
MEDIUM	app.py	4307	# ── Tab 1: Obliterate ─────────────────────────────────────────────	STRING
MEDIUM	app.py	4565	# ── Tab 2: Benchmark ──────────────────────────────────────────────	STRING
MEDIUM	app.py	4908	# ── Tab 3: Chat ───────────────────────────────────────────────────	STRING
MEDIUM	app.py	4954	# ── Tab 4: A/B Comparison ─────────────────────────────────────────	STRING
MEDIUM	app.py	5031	# ── Tab 5: Strength Sweep ────────────────────────────────────────	STRING
MEDIUM	app.py	5101	# ── Tab 6: Tourney ────────────────────────────────────────────────	STRING
MEDIUM	app.py	5168	# ── Tab 7: Export ─────────────────────────────────────────────────	STRING
MEDIUM	app.py	5189	# ── Tab: Push to Hub ──────────────────────────────────────────────	STRING
MEDIUM	app.py	5289	# ── Tab: Leaderboard ────────────────────────────────────────────	STRING
MEDIUM	app.py	5635	# ---------------------------------------------------------------------------	STRING
MEDIUM	app.py	5637	# ---------------------------------------------------------------------------	STRING
MEDIUM⚡	tests/test_breakthrough_modules.py	259	# ===========================================================================	COMMENT
MEDIUM⚡	tests/test_breakthrough_modules.py	261	# ===========================================================================	COMMENT
MEDIUM⚡	tests/test_breakthrough_modules.py	353	# ===========================================================================	COMMENT
MEDIUM⚡	tests/test_breakthrough_modules.py	355	# ===========================================================================	COMMENT
MEDIUM⚡	tests/test_breakthrough_modules.py	459	# ===========================================================================	COMMENT
MEDIUM⚡	tests/test_breakthrough_modules.py	461	# ===========================================================================	COMMENT
MEDIUM⚡	tests/test_breakthrough_modules.py	589	# ===========================================================================	COMMENT
MEDIUM⚡	tests/test_breakthrough_modules.py	591	# ===========================================================================	COMMENT
MEDIUM⚡	tests/test_breakthrough_modules.py	873	# ===========================================================================	COMMENT
MEDIUM⚡	tests/test_breakthrough_modules.py	875	# ===========================================================================	COMMENT
MEDIUM	tests/test_breakthrough_modules.py	42	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_breakthrough_modules.py	44	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_breakthrough_modules.py	110	# ===========================================================================	COMMENT
MEDIUM	tests/test_breakthrough_modules.py	112	# ===========================================================================	COMMENT
MEDIUM	tests/conftest.py	57	# ---------------------------------------------------------------------------	COMMENT
578 more matches not shown…

Empty Error Handlers172 hits · 858 pts

Severity	File	Line	Snippet	Context
HIGH	app.py	284	except OSError:	CODE
HIGH	app.py	378	except Exception:	CODE
HIGH	app.py	396	except (OSError, ValueError):	CODE
HIGH	app.py	960	except Exception:	CODE
HIGH	app.py	1339	except Exception:	CODE
HIGH	app.py	3250	except Exception:	CODE
HIGH	app.py	270	except Exception:	CODE
HIGH	app.py	1364	except Exception:	CODE
HIGH	app.py	1392	except Exception:	CODE
HIGH	app.py	1646	except Exception:	CODE
HIGH	app.py	2029	except Exception:	CODE
HIGH	app.py	2826	except Exception:	CODE
HIGH	app.py	3670	except Exception:	CODE
HIGH	app.py	3813	except (ValueError, IndexError):	CODE
HIGH	app.py	3818	except (ValueError, IndexError):	CODE
HIGH	app.py	3823	except (ValueError, IndexError):	CODE
HIGH	app.py	3076	except Exception:	CODE
HIGH	app.py	3236	except Exception:	CODE
HIGH	tests/test_distributed_verification_gloo.py	516	except BaseException:	CODE
HIGH	tests/test_distributed_surgery_gloo.py	421	except BaseException:	CODE
HIGH	tests/test_conditional_gate_scripts.py	1158	except ExecCalled:	CODE
HIGH	tests/test_edge_cases.py	106	except Exception:	CODE
HIGH	tests/test_distributed_probe_gloo.py	249	except BaseException:	CODE
HIGH	obliteratus/abliterate.py	3187	except Exception:	CODE
HIGH	obliteratus/abliterate.py	2188	except Exception:	CODE
HIGH	obliteratus/abliterate.py	2195	except Exception:	CODE
HIGH	obliteratus/abliterate.py	3773	except Exception:	CODE
HIGH	obliteratus/abliterate.py	6501	except Exception:	CODE
HIGH	obliteratus/abliterate.py	6516	except Exception:	CODE
HIGH	obliteratus/abliterate.py	9519	except Exception:	CODE
HIGH	obliteratus/abliterate.py	2584	except (AttributeError, RuntimeError):	CODE
HIGH	obliteratus/abliterate.py	2597	except (AttributeError, RuntimeError):	CODE
HIGH	obliteratus/abliterate.py	2604	except (AttributeError, RuntimeError):	CODE
HIGH	obliteratus/abliterate.py	2613	except (AttributeError, RuntimeError):	CODE
HIGH	obliteratus/abliterate.py	4188	except Exception:	CODE
HIGH	obliteratus/abliterate.py	6648	except Exception:	CODE
HIGH	obliteratus/abliterate.py	7022	except (AttributeError, RuntimeError, TypeError):	CODE
HIGH	obliteratus/abliterate.py	1870	except Exception:	CODE
HIGH	obliteratus/abliterate.py	6187	except (AttributeError, RuntimeError):	CODE
HIGH	obliteratus/abliterate.py	6191	except (AttributeError, RuntimeError):	CODE
HIGH	obliteratus/abliterate.py	6553	except Exception:	CODE
HIGH	obliteratus/abliterate.py	6569	except Exception:	CODE
HIGH	obliteratus/abliterate.py	6211	except (AttributeError, RuntimeError):	CODE
HIGH	obliteratus/abliterate.py	6234	except (AttributeError, RuntimeError):	CODE
HIGH	obliteratus/phase_admission.py	2407	except Exception:	CODE
HIGH	obliteratus/phase_admission.py	2412	except Exception:	CODE
HIGH	obliteratus/phase_admission.py	2418	except Exception:	CODE
HIGH	obliteratus/phase_admission.py	2556	except PhaseAdmissionError:	CODE
HIGH	obliteratus/phase_admission.py	2584	except PhaseAdmissionError:	CODE
HIGH	obliteratus/phase_admission.py	2609	except PhaseAdmissionError:	CODE
HIGH	obliteratus/phase_admission.py	2619	except Exception:	CODE
HIGH	obliteratus/ui_model_slot.py	836	except BaseException:	CODE
HIGH	obliteratus/ui_model_slot.py	296	except BaseException:	CODE
HIGH	obliteratus/ui_model_slot.py	549	except ImportError:	CODE
HIGH	obliteratus/ui_model_slot.py	741	except Exception:	CODE
HIGH	obliteratus/ui_model_slot.py	760	except BaseException:	CODE
HIGH	obliteratus/ui_model_slot.py	768	except Exception:	CODE
HIGH	obliteratus/ui_model_slot.py	843	except BaseException:	CODE
HIGH	obliteratus/ui_model_slot.py	303	except BaseException:	CODE
HIGH	obliteratus/ui_model_slot.py	648	except BaseException:	CODE
112 more matches not shown…

Unused Imports507 hits · 421 pts

Severity	File	Line	Context
LOW	app.py	18	CODE
LOW	tests/test_phase_repair_admission.py	19	CODE
LOW	tests/test_ui_model_slot.py	3	CODE
LOW	tests/test_gemma4_support.py	1	CODE
LOW	tests/test_strategy_navigation_contracts.py	3	CODE
LOW	tests/test_checkpoint_atomicity.py	3	CODE
LOW	tests/test_device_boundaries.py	3	CODE
LOW	tests/test_models_client_contracts.py	3	CODE
LOW	tests/test_ci_policy.py	3	CODE
LOW	tests/test_distributed_verification_gloo.py	3	CODE
LOW	tests/test_shard_pr_tests.py	3	CODE
LOW	tests/test_breakthrough_modules.py	9	CODE
LOW	tests/test_distributed_surgery_gloo.py	3	CODE
LOW	tests/test_check_pr_partitions.py	3	CODE
LOW	tests/test_local_ui_portability.py	3	CODE
LOW	tests/test_lm_eval_reporting_contracts.py	3	CODE
LOW	tests/test_gsq_workflow.py	3	CODE
LOW	tests/test_property_contracts.py	3	CODE
LOW	tests/conftest.py	3	CODE
LOW	tests/test_conditional_evidence_freshness.py	3	CODE
LOW	tests/test_analysis_utils.py	3	CODE
LOW	tests/test_distributed_preflight.py	3	CODE
LOW	tests/test_informed_pipeline_contracts.py	3	CODE
LOW	tests/test_package_export_contracts.py	3	CODE
LOW	tests/test_checkpoint_inspection.py	3	CODE
LOW	tests/test_advanced_metrics.py	3	CODE
LOW	tests/test_heretic_eval.py	3	CODE
LOW	tests/test_remote_boundaries.py	3	CODE
LOW	tests/test_peft_artifacts.py	3	CODE
LOW	tests/test_remote_contracts.py	3	CODE
LOW	tests/test_mcp_server.py	3	CODE
LOW	tests/test_model_load_settings.py	3	CODE
LOW	tests/test_test_risk_map.py	3	CODE
LOW	tests/test_checkpoint_writer.py	3	CODE
LOW	tests/test_loader_boundaries.py	3	CODE
LOW	tests/test_metrics.py	3	CODE
LOW	tests/test_benchmarks.py	3	CODE
LOW	tests/test_phase_dtype_admission.py	16	CODE
LOW	tests/test_checkpoint_docs_contracts.py	3	CODE
LOW	tests/test_leace_labeling.py	9	CODE
LOW	tests/test_gpu_lifecycle.py	1	CODE
LOW	tests/test_config_properties.py	3	CODE
LOW	tests/test_experiment_protocol.py	1	CODE
LOW	tests/test_visualization.py	3	CODE
LOW	tests/test_checkpoint_errors.py	3	CODE
LOW	tests/test_phase_outputs_admission.py	19	CODE
LOW	tests/test_checkpoint_contract_schemas.py	3	CODE
LOW	tests/test_offload_surgery.py	3	CODE
LOW	tests/test_mcp_policy.py	3	CODE
LOW	tests/test_architecture_profiles.py	7	CODE
LOW	tests/test_distributed_contracts.py	3	CODE
LOW	tests/test_module_imports.py	3	CODE
LOW	tests/test_distributed_gloo.py	3	CODE
LOW	tests/test_persistence_contracts.py	3	CODE
LOW	tests/test_new_analysis_modules.py	9	CODE
LOW	tests/test_auto_obliterate.py	3	CODE
LOW	tests/test_evaluator.py	3	CODE
LOW	tests/test_informed_pipeline.py	3	CODE
LOW	tests/test_analysis.py	3	CODE
LOW	tests/test_causal_and_transfer.py	4	CODE
447 more matches not shown…

Excessive Try-Catch Wrapping295 hits · 240 pts

Severity	File	Line	Snippet	Context
MEDIUM	app.py	1505	def run_pipeline():	CODE
MEDIUM	app.py	1894	def run_pipeline():	CODE
MEDIUM	app.py	2455	def run_pipeline():	CODE
MEDIUM	app.py	3067	def _generate_safe(**kwargs):	CODE
MEDIUM	app.py	3228	def _gen_abliterated(**kwargs):	CODE
MEDIUM	app.py	3329	def _run_sweep_point():	CODE
MEDIUM	app.py	5372	def _push_telemetry():	CODE
LOW	app.py	270	except Exception:	CODE
LOW	app.py	378	except Exception:	CODE
LOW	app.py	406	except Exception:	CODE
LOW	app.py	864	except Exception as e:	CODE
LOW	app.py	903	except Exception as e:	CODE
LOW	app.py	960	except Exception:	CODE
LOW	app.py	1339	except Exception:	CODE
LOW	app.py	1364	except Exception:	CODE
LOW	app.py	1392	except Exception:	CODE
LOW	app.py	1545	except Exception as e:	CODE
LOW	app.py	1557	except Exception as cleanup_error:	CODE
LOW	app.py	1646	except Exception:	CODE
LOW	app.py	1931	except Exception as e:	CODE
LOW	app.py	1943	except Exception as cleanup_error:	CODE
LOW	app.py	2029	except Exception:	CODE
LOW	app.py	2254	except Exception:	CODE
LOW	app.py	2270	except Exception:	CODE
LOW	app.py	2384	except Exception as exc:	CODE
LOW	app.py	2662	except Exception as e:	CODE
LOW	app.py	2826	except Exception:	CODE
LOW	app.py	2932	except Exception as e:	CODE
LOW	app.py	3031	except Exception:	CODE
LOW	app.py	3071	except Exception as e:	CODE
LOW	app.py	3076	except Exception:	CODE
LOW	app.py	3087	except Exception:	CODE
LOW	app.py	3198	except Exception:	CODE
LOW	app.py	3232	except Exception as e:	CODE
LOW	app.py	3236	except Exception:	CODE
LOW	app.py	3250	except Exception:	CODE
LOW	app.py	3345	except Exception as e:	CODE
LOW	app.py	3450	except Exception as e:	CODE
LOW	app.py	3579	except Exception as e:	CODE
LOW	app.py	3610	except Exception as e:	CODE
LOW	app.py	3670	except Exception:	CODE
LOW	app.py	5358	except Exception as e:	CODE
LOW	app.py	5404	except Exception as e:	CODE
LOW	tests/test_distributed_gloo.py	288	except Exception as exc:	CODE
LOW	tests/test_distributed_gloo.py	588	except Exception as exc:	CODE
LOW	tests/test_distributed_model_gloo.py	94	except Exception as exc:	CODE
LOW⚡	tests/test_edge_cases.py	106	except Exception:	CODE
LOW⚡	tests/test_phase_matrix.py	305	except Exception as exc:	CODE
LOW⚡	tests/test_phase_matrix.py	315	except Exception as exc:	CODE
LOW	tests/test_phase_matrix.py	341	except Exception as exc:	CODE
LOW	tests/test_phase_matrix.py	369	except Exception as exc:	CODE
MEDIUM	tests/test_phase_matrix.py	355	def _matrix_phase_report(handle, phase, budget, *, method=None):	CODE
MEDIUM	obliteratus/abliterate.py	1910	def estimate(name, operation, fallback):	CODE
LOW⚡	obliteratus/abliterate.py	3187	except Exception:	CODE
LOW⚡	obliteratus/abliterate.py	3195	except Exception:	CODE
LOW	obliteratus/abliterate.py	1870	except Exception:	CODE
LOW	obliteratus/abliterate.py	1913	except Exception as exc:	CODE
LOW	obliteratus/abliterate.py	2188	except Exception:	CODE
LOW	obliteratus/abliterate.py	2195	except Exception:	CODE
LOW	obliteratus/abliterate.py	2210	except Exception as exc:	CODE
235 more matches not shown…

Deep Nesting264 hits · 208 pts

Severity	File	Line	Context
LOW	app.py	382	CODE
LOW	app.py	1370	CODE
LOW	app.py	1398	CODE
LOW	app.py	1789	CODE
LOW	app.py	2206	CODE
LOW	app.py	2455	CODE
LOW	tests/test_phase_repair_admission.py	189	CODE
LOW	tests/test_ui_model_slot.py	845	CODE
LOW	tests/test_ui_model_slot.py	877	CODE
LOW	tests/test_ui_model_slot.py	1007	CODE
LOW	tests/test_phase_confidence.py	24	CODE
LOW	tests/test_distributed_verification_gloo.py	275	CODE
LOW	tests/test_distributed_surgery_gloo.py	425	CODE
LOW	tests/test_distributed_surgery_gloo.py	72	CODE
LOW	tests/test_distributed_preflight.py	417	CODE
LOW	tests/test_benchmarks.py	19	CODE
LOW	tests/test_benchmarks.py	60	CODE
LOW	tests/test_intervention_hook_regressions.py	162	CODE
LOW	tests/test_concept_repair.py	79	CODE
LOW	tests/test_concept_repair.py	192	CODE
LOW	tests/test_distributed_validation_edges.py	253	CODE
LOW	tests/test_concept_packs.py	241	CODE
LOW	tests/test_concept_packs.py	283	CODE
LOW	tests/test_concept_packs.py	300	CODE
LOW	tests/test_distributed_gloo.py	392	CODE
LOW	tests/test_distributed_gloo.py	471	CODE
LOW	tests/test_concept_docs.py	36	CODE
LOW	tests/test_concept_docs.py	74	CODE
LOW	tests/test_lora_ablation.py	91	CODE
LOW	tests/test_distributed_model_gloo.py	101	CODE
LOW	tests/test_ui_model_load.py	105	CODE
LOW	tests/test_gsq_coverage.py	936	CODE
LOW	tests/test_gsq_coverage.py	1978	CODE
LOW	tests/test_novel_analysis.py	81	CODE
LOW	tests/test_phase_lora_admission.py	50	CODE
LOW	tests/test_distributed_probe_gloo.py	253	CODE
LOW	tests/test_phase_matrix.py	80	CODE
LOW	tests/test_phase_matrix.py	229	CODE
LOW	tests/test_pain_pack.py	272	CODE
LOW	tests/test_distributed_verification_contracts.py	732	CODE
LOW	tests/test_distributed_verification_contracts.py	949	CODE
LOW	tests/test_distributed_verification_contracts.py	1373	CODE
LOW	tests/test_distributed_verification_contracts.py	776	CODE
LOW	tests/test_distributed_verification_contracts.py	955	CODE
LOW	tests/test_checkpoint_export.py	267	CODE
LOW	tests/conditional/test_phase_admission_gpu.py	38	CODE
LOW	tests/conditional/test_distributed_llama_tp_cuda.py	662	CODE
LOW	obliteratus/abliterate.py	1680	CODE
LOW	obliteratus/abliterate.py	1786	CODE
LOW	obliteratus/abliterate.py	1893	CODE
LOW	obliteratus/abliterate.py	2036	CODE
LOW	obliteratus/abliterate.py	2267	CODE
LOW	obliteratus/abliterate.py	2529	CODE
LOW	obliteratus/abliterate.py	3014	CODE
LOW	obliteratus/abliterate.py	3573	CODE
LOW	obliteratus/abliterate.py	3741	CODE
LOW	obliteratus/abliterate.py	4647	CODE
LOW	obliteratus/abliterate.py	5111	CODE
LOW	obliteratus/abliterate.py	5381	CODE
LOW	obliteratus/abliterate.py	5627	CODE
204 more matches not shown…

Structural Annotation Overuse68 hits · 136 pts

Severity	File	Line	Snippet	Context
LOW⚡	tests/test_abliterate.py	3192	# Step 1: compute EGA directions	COMMENT
LOW⚡	tests/test_abliterate.py	3197	# Step 2: apply granular projection	COMMENT
LOW⚡	docs/executive_research_summary.md	203	# Step 1: Aggressive/SVD surgery	COMMENT
LOW⚡	docs/executive_research_summary.md	208	# Step 2: LEACE surgery	COMMENT
LOW⚡	docs/executive_research_summary.md	213	# Step 3: Blend	COMMENT
LOW⚡	docs/executive_research_summary.md	217	# Step 4: Validate	COMMENT
LOW⚡	docs/mechanistic_interpretability_research.md	108	# Step 1: Get clean activations	COMMENT
LOW⚡	docs/mechanistic_interpretability_research.md	115	# Step 2: Define metric	COMMENT
LOW⚡	docs/mechanistic_interpretability_research.md	122	# Step 3: Patching hook	COMMENT
LOW⚡	docs/mechanistic_interpretability_research.md	127	# Step 4: Sweep over layers and positions	COMMENT
LOW	docs/mechanistic_interpretability_research.md	529	# Step 1: Collect activations from frozen model	COMMENT
LOW⚡	docs/mechanistic_interpretability_research.md	547	# Step 2: Train linear probe	COMMENT
LOW⚡	docs/mechanistic_interpretability_research.md	553	# Step 3: Evaluate	COMMENT
LOW⚡	docs/mechanistic_interpretability_research.md	559	# Step 4: The probe's weight vector IS the "refusal direction"	COMMENT
LOW⚡	docs/mechanistic_interpretability_research.md	1325	# Step 1: Collect activations	COMMENT
LOW⚡	docs/mechanistic_interpretability_research.md	1329	# Step 2: Pool and compute statistics	COMMENT
LOW⚡	docs/mechanistic_interpretability_research.md	1334	# Step 3: Whitening transformation	COMMENT
LOW⚡	docs/mechanistic_interpretability_research.md	1343	# Step 4: Whiten both sets of activations	COMMENT
LOW⚡	docs/mechanistic_interpretability_research.md	1347	# Step 5: Difference-in-means in whitened space	COMMENT
LOW⚡	docs/mechanistic_interpretability_research.md	1351	# Step 6: Transform back to original space for use in steering	COMMENT
LOW⚡	docs/mechanistic_interpretability_research.md	1356	# Step 7: Cosine similarity scoring at inference time	COMMENT
LOW⚡	docs/complementary_blending.md	176	# Step 1: Aggressive surgery	COMMENT
LOW⚡	docs/complementary_blending.md	181	# Step 2: LEACE surgery	COMMENT
LOW⚡	docs/complementary_blending.md	186	# Step 3: Blend	COMMENT
LOW⚡	docs/complementary_blending.md	190	# Step 4: Validate	COMMENT
LOW⚡	obliteratus/abliterate.py	4312	# Step 2: Initialize from SVD direction (warm start)	COMMENT
LOW⚡	obliteratus/abliterate.py	4316	# Step 3: Gradient-based refinement	COMMENT
LOW	obliteratus/abliterate.py	4301	# Step 1: Train linear refusal probe	COMMENT
LOW	obliteratus/abliterate.py	4358	# Step 4: Update direction with RDO-refined version	COMMENT
LOW⚡	obliteratus/interactive.py	215	# Step 1: Hardware	COMMENT
LOW⚡	obliteratus/interactive.py	219	# Step 2: Model	COMMENT
LOW⚡	obliteratus/interactive.py	223	# Step 3: Study preset OR custom strategies + sample size	COMMENT
LOW	obliteratus/interactive.py	241	# Step 4: Determine device and dtype	COMMENT
LOW⚡	obliteratus/analysis/sae_abliteration.py	449	# Step 1: Train SAE	COMMENT
LOW⚡	obliteratus/analysis/sae_abliteration.py	459	# Step 2: Identify refusal features	COMMENT
LOW⚡	obliteratus/analysis/sae_abliteration.py	465	# Step 3: Compute feature sparsity and monosemanticity	COMMENT
LOW⚡	obliteratus/analysis/sae_abliteration.py	471	# Step 4: Cluster features	COMMENT
LOW⚡	obliteratus/analysis/sae_abliteration.py	474	# Step 5: Ablation simulation	COMMENT
LOW⚡	obliteratus/analysis/sae_abliteration.py	480	# Step 6: Compare with raw direction	COMMENT
LOW	obliteratus/analysis/spectral_certification.py	187	# Step 1: Compute difference covariance matrix	COMMENT
LOW	obliteratus/analysis/spectral_certification.py	229	# Step 3: Compute BBP threshold	COMMENT
LOW⚡	obliteratus/analysis/spectral_certification.py	242	# Step 4: Marchenko-Pastur edges	COMMENT
LOW⚡	obliteratus/analysis/spectral_certification.py	246	# Step 5: Eigenvalue analysis of between-class covariance	COMMENT
LOW	obliteratus/analysis/spectral_certification.py	258	# Step 6: Classify certification level	COMMENT
LOW	obliteratus/analysis/riemannian_manifold.py	157	# Step 1: Estimate refusal directions if not provided	COMMENT
LOW	obliteratus/analysis/riemannian_manifold.py	168	# Step 2: Compute per-layer intrinsic dimension and curvature	COMMENT
LOW	obliteratus/analysis/riemannian_manifold.py	198	# Step 3: Aggregate manifold statistics	COMMENT
LOW⚡	obliteratus/analysis/wasserstein_transfer.py	159	# Step 1: Compute layer mapping if not provided	COMMENT
LOW⚡	obliteratus/analysis/wasserstein_transfer.py	166	# Step 2: For each mapped layer pair, compute OT map and transfer	COMMENT
LOW	obliteratus/analysis/wasserstein_transfer.py	215	# Step 3: Aggregate results	COMMENT
LOW	obliteratus/analysis/conditional_abliteration.py	138	# Step 1: Extract per-category condition vectors and projectors	COMMENT
LOW	obliteratus/analysis/conditional_abliteration.py	204	# Step 2: Compute cross-category geometry	COMMENT
LOW⚡	obliteratus/analysis/conditional_abliteration.py	227	# Step 3: Sheaf consistency check	COMMENT
LOW⚡	obliteratus/analysis/conditional_abliteration.py	232	# Step 4: Classify categories	COMMENT
LOW⚡	obliteratus/analysis/whitened_svd.py	150	# Step 1: Compute harmless covariance with centering	COMMENT
LOW⚡	obliteratus/analysis/whitened_svd.py	155	# Step 2: Eigendecompose covariance for whitening	COMMENT
LOW⚡	obliteratus/analysis/whitened_svd.py	173	# Step 3: Truncate near-degenerate dimensions	COMMENT
LOW⚡	obliteratus/analysis/whitened_svd.py	179	# Step 4: Compute whitening transform W = V @ diag(1/sqrt(lam + eps)) @ V^T	COMMENT
LOW⚡	obliteratus/analysis/whitened_svd.py	185	# Step 5: Whiten both activation sets (centered on harmless mean)	COMMENT
LOW⚡	obliteratus/analysis/whitened_svd.py	190	# Step 6: Compute whitened difference and SVD	COMMENT
8 more matches not shown…

Verbosity Indicators45 hits · 85 pts

Severity	File	Line	Snippet	Context
LOW⚡	tests/test_abliterate.py	3192	# Step 1: compute EGA directions	COMMENT
LOW⚡	tests/test_abliterate.py	3197	# Step 2: apply granular projection	COMMENT
LOW⚡	obliteratus/abliterate.py	4312	# Step 2: Initialize from SVD direction (warm start)	COMMENT
LOW⚡	obliteratus/abliterate.py	4316	# Step 3: Gradient-based refinement	COMMENT
LOW	obliteratus/abliterate.py	4301	# Step 1: Train linear refusal probe	COMMENT
LOW	obliteratus/abliterate.py	4358	# Step 4: Update direction with RDO-refined version	COMMENT
LOW⚡	obliteratus/interactive.py	215	# Step 1: Hardware	COMMENT
LOW⚡	obliteratus/interactive.py	219	# Step 2: Model	COMMENT
LOW⚡	obliteratus/interactive.py	223	# Step 3: Study preset OR custom strategies + sample size	COMMENT
LOW	obliteratus/interactive.py	241	# Step 4: Determine device and dtype	COMMENT
LOW⚡	obliteratus/analysis/sae_abliteration.py	449	# Step 1: Train SAE	COMMENT
LOW⚡	obliteratus/analysis/sae_abliteration.py	459	# Step 2: Identify refusal features	COMMENT
LOW⚡	obliteratus/analysis/sae_abliteration.py	465	# Step 3: Compute feature sparsity and monosemanticity	COMMENT
LOW⚡	obliteratus/analysis/sae_abliteration.py	471	# Step 4: Cluster features	COMMENT
LOW⚡	obliteratus/analysis/sae_abliteration.py	474	# Step 5: Ablation simulation	COMMENT
LOW⚡	obliteratus/analysis/sae_abliteration.py	480	# Step 6: Compare with raw direction	COMMENT
LOW	obliteratus/analysis/spectral_certification.py	187	# Step 1: Compute difference covariance matrix	COMMENT
LOW	obliteratus/analysis/spectral_certification.py	229	# Step 3: Compute BBP threshold	COMMENT
LOW⚡	obliteratus/analysis/spectral_certification.py	242	# Step 4: Marchenko-Pastur edges	COMMENT
LOW⚡	obliteratus/analysis/spectral_certification.py	246	# Step 5: Eigenvalue analysis of between-class covariance	COMMENT
LOW	obliteratus/analysis/spectral_certification.py	258	# Step 6: Classify certification level	COMMENT
LOW	obliteratus/analysis/riemannian_manifold.py	157	# Step 1: Estimate refusal directions if not provided	COMMENT
LOW	obliteratus/analysis/riemannian_manifold.py	168	# Step 2: Compute per-layer intrinsic dimension and curvature	COMMENT
LOW	obliteratus/analysis/riemannian_manifold.py	198	# Step 3: Aggregate manifold statistics	COMMENT
LOW⚡	obliteratus/analysis/wasserstein_transfer.py	159	# Step 1: Compute layer mapping if not provided	COMMENT
LOW⚡	obliteratus/analysis/wasserstein_transfer.py	166	# Step 2: For each mapped layer pair, compute OT map and transfer	COMMENT
LOW	obliteratus/analysis/wasserstein_transfer.py	215	# Step 3: Aggregate results	COMMENT
LOW	obliteratus/analysis/conditional_abliteration.py	138	# Step 1: Extract per-category condition vectors and projectors	COMMENT
LOW	obliteratus/analysis/conditional_abliteration.py	204	# Step 2: Compute cross-category geometry	COMMENT
LOW⚡	obliteratus/analysis/conditional_abliteration.py	227	# Step 3: Sheaf consistency check	COMMENT
LOW⚡	obliteratus/analysis/conditional_abliteration.py	232	# Step 4: Classify categories	COMMENT
LOW⚡	obliteratus/analysis/whitened_svd.py	150	# Step 1: Compute harmless covariance with centering	COMMENT
LOW⚡	obliteratus/analysis/whitened_svd.py	155	# Step 2: Eigendecompose covariance for whitening	COMMENT
LOW⚡	obliteratus/analysis/whitened_svd.py	173	# Step 3: Truncate near-degenerate dimensions	COMMENT
LOW⚡	obliteratus/analysis/whitened_svd.py	179	# Step 4: Compute whitening transform W = V @ diag(1/sqrt(lam + eps)) @ V^T	COMMENT
LOW⚡	obliteratus/analysis/whitened_svd.py	185	# Step 5: Whiten both activation sets (centered on harmless mean)	COMMENT
LOW⚡	obliteratus/analysis/whitened_svd.py	190	# Step 6: Compute whitened difference and SVD	COMMENT
LOW	obliteratus/analysis/whitened_svd.py	201	# Step 7: Un-whiten to get directions in original activation space	COMMENT
LOW⚡	scripts/abliteration_comparison.py	529	# Step 2: Extract directions	COMMENT
LOW⚡	scripts/abliteration_comparison.py	534	# Step 3: Select layers	COMMENT
LOW⚡	scripts/abliteration_comparison.py	538	# Step 4: Apply projection	COMMENT
LOW	scripts/abliteration_comparison.py	515	# Step 1: Collect activations	COMMENT
LOW⚡	scripts/gemma4_refusal_sniper.py	267	# Step 1: First verify the refusal prompts actually refuse	COMMENT
LOW⚡	scripts/gemma4_refusal_sniper.py	276	# Step 2: Extract hedging direction	COMMENT
LOW⚡	scripts/gemma4_refusal_sniper.py	286	# Step 3: Try different snipe strengths	COMMENT

Modern Structural Boilerplate63 hits · 62 pts

Severity	File	Line	Snippet	Context
LOW	obliteratus/abliterate.py	129	logger = logging.getLogger(__name__)	CODE
LOW	obliteratus/blend.py	50	logger = logging.getLogger(__name__)	CODE
LOW	obliteratus/phase_admission.py	27	logger = logging.getLogger(__name__)	CODE
LOW	obliteratus/capability_check.py	42	logger = logging.getLogger(__name__)	CODE
LOW	obliteratus/bayesian_optimizer.py	41	logger = logging.getLogger(__name__)	CODE
LOW⚡	obliteratus/device.py	21	logger = logging.getLogger(__name__)	CODE
LOW⚡	obliteratus/device.py	240	def set_seed_all(seed: int) -> None:	CODE
LOW	obliteratus/reproducibility.py	19	logger = logging.getLogger(__name__)	CODE
LOW	obliteratus/reproducibility.py	22	def set_seed(seed: int = 42, deterministic: bool = True) -> None:	CODE
LOW⚡	obliteratus/mlx_backend.py	21	logger = logging.getLogger(__name__)	CODE
LOW	obliteratus/restore_multimodal.py	34	logger = logging.getLogger(__name__)	CODE
LOW	obliteratus/__init__.py	6	__all__ = [	CODE
LOW	obliteratus/telemetry.py	48	logger = logging.getLogger(__name__)	CODE
LOW	obliteratus/gpu_lifecycle.py	21	logger = logging.getLogger(__name__)	CODE
LOW	obliteratus/prompts.py	21	logger = logging.getLogger(__name__)	CODE
LOW	obliteratus/persistence_contracts.py	18	logger = logging.getLogger(__name__)	CODE
LOW	obliteratus/watchtower.py	39	logger = logging.getLogger(__name__)	CODE
LOW	obliteratus/lora_ablation.py	62	logger = logging.getLogger(__name__)	CODE
LOW	obliteratus/architecture_profiles.py	30	logger = logging.getLogger(__name__)	CODE
LOW	obliteratus/community.py	43	logger = logging.getLogger(__name__)	CODE
LOW	obliteratus/sweep.py	34	logger = logging.getLogger(__name__)	CODE
LOW	obliteratus/informed_pipeline.py	70	logger = logging.getLogger(__name__)	CODE
LOW	obliteratus/auto_obliterate.py	33	logger = logging.getLogger(__name__)	CODE
LOW	obliteratus/adaptive_defaults.py	40	logger = logging.getLogger(__name__)	CODE
LOW	obliteratus/reporting/__init__.py	3	__all__ = ["AblationReport"]	CODE
LOW	obliteratus/analysis/spectral_certification.py	43	logger = logging.getLogger(__name__)	CODE
LOW	obliteratus/analysis/riemannian_manifold.py	40	logger = logging.getLogger(__name__)	CODE
LOW	obliteratus/analysis/bayesian_kernel_projection.py	41	logger = logging.getLogger(__name__)	CODE
LOW	obliteratus/analysis/anti_ouroboros.py	44	logger = logging.getLogger(__name__)	CODE
LOW	obliteratus/analysis/wasserstein_optimal.py	50	logger = logging.getLogger(__name__)	CODE
LOW	obliteratus/analysis/activation_patching.py	41	logger = logging.getLogger(__name__)	CODE
LOW	obliteratus/analysis/__init__.py	7	__all__ = [	CODE
LOW	obliteratus/analysis/wasserstein_transfer.py	40	logger = logging.getLogger(__name__)	CODE
LOW	obliteratus/analysis/logit_lens.py	43	logger = logging.getLogger(__name__)	CODE
LOW	obliteratus/analysis/conditional_abliteration.py	38	logger = logging.getLogger(__name__)	CODE
LOW	obliteratus/analysis/tuned_lens.py	46	logger = logging.getLogger(__name__)	CODE
LOW	obliteratus/distributed/model_topology.py	238	__all__ = [	CODE
LOW	obliteratus/distributed/surgery.py	1314	__all__ = [	CODE
LOW	obliteratus/distributed/verification.py	1764	__all__ = [	CODE
LOW	obliteratus/distributed/verification_contracts.py	787	__all__ = [	CODE
LOW	obliteratus/distributed/journal.py	434	__all__ = ["RankJournal"]	CODE
LOW	obliteratus/distributed/probe_contracts.py	872	__all__ = [	CODE
LOW	obliteratus/distributed/model_identity.py	261	__all__ = [	CODE
LOW	obliteratus/distributed/model_evidence.py	789	__all__ = [	CODE
LOW	obliteratus/distributed/__init__.py	154	__all__ = [	CODE
LOW	obliteratus/distributed/export.py	2092	__all__ = [	CODE
LOW	obliteratus/distributed/model.py	747	__all__ = [	CODE
LOW	obliteratus/distributed/model_manifest.py	732	__all__ = [	CODE
LOW	obliteratus/distributed/probe.py	475	def _update_activation_hasher(hasher: Any, activation: torch.Tensor) -> None:	CODE
LOW	obliteratus/distributed/probe.py	1114	__all__ = [	CODE
LOW	obliteratus/distributed/export_contracts.py	455	__all__ = [	CODE
LOW	obliteratus/distributed/surgery_contracts.py	453	__all__ = [	CODE
LOW	obliteratus/distributed/model_registry.py	105	__all__ = [	CODE
LOW	obliteratus/distributed/model_session.py	915	__all__ = [	CODE
LOW	obliteratus/strategies/__init__.py	7	__all__ = [	CODE
LOW	obliteratus/models/__init__.py	3	__all__ = ["load_model", "ModelHandle"]	CODE
LOW	obliteratus/models/loader.py	43	logger = logging.getLogger(__name__)	CODE
LOW⚡	obliteratus/models/quant_dequant.py	50	logger = logging.getLogger(__name__)	CODE
LOW	obliteratus/concepts/__init__.py	16	__all__ = [	CODE
LOW	obliteratus/gsq/__init__.py	10	__all__ = ["coverage", "numerics_guard", "source", "workflow"]	CODE
3 more matches not shown…

Hallucination Indicators6 hits · 60 pts

Severity	File	Line	Snippet	Context
CRITICAL	tests/test_phase_edit_admission.py	92	assert tracker.peak > handle.model.block.q_proj.weight.numel() * 4	CODE
CRITICAL	tests/test_phase_edit_admission.py	104	logical_bytes = full.model.block.q_proj.weight.numel() * 4	CODE
CRITICAL	tests/test_abliterate.py	790	shared_down_orig = moe.shared_expert.down_proj.weight.data.clone()	CODE
CRITICAL	tests/test_abliterate.py	791	shared_up_orig = moe.shared_expert.up_proj.weight.data.clone()	CODE
CRITICAL	tests/test_abliterate.py	2970	orig_shared = moe.shared_expert.down_proj.weight.data.clone()	CODE
CRITICAL	tests/test_distributed_export_contracts.py	575	case.context.runtime.model.column_sharded.add_(1)	CODE

AI Slop Vocabulary18 hits · 43 pts

Severity	File	Line	Snippet	Context
MEDIUM	tests/test_abliterate.py	2288	"""Rebirth should save model and comprehensive metadata JSON."""	STRING
MEDIUM	tests/test_offline_integration.py	354	# keeps the contract robust to BLAS threading differences on other hosts	COMMENT
MEDIUM	obliteratus/abliterate.py	8718	# Token-ID slicing for robust completion extraction	COMMENT
LOW	obliteratus/abliterate.py	9284	# Fast path: if nothing is offloaded, just return the normal state dict.	COMMENT
MEDIUM	obliteratus/abliterate.py	9457	"""Atomically save the abliterated model with comprehensive metadata."""	STRING
MEDIUM	obliteratus/bayesian_optimizer.py	139	# Token-ID slicing: robust regardless of special tokens	COMMENT
MEDIUM	obliteratus/informed_pipeline.py	702	# Default: single direction via diff-of-means (proven most robust).	COMMENT
MEDIUM	obliteratus/informed_pipeline.py	719	# Linear cone → single direction via diff-of-means (simplest, most robust)	COMMENT
MEDIUM	obliteratus/informed_pipeline.py	1294	"""Save model with comprehensive analysis metadata."""	STRING
MEDIUM	obliteratus/analysis/defense_robustness.py	94	"""Generate a comprehensive defense profile for the model.	STRING
MEDIUM	obliteratus/analysis/defense_robustness.py	393	# Score components (all 0-1, higher = more robust)	COMMENT
LOW	obliteratus/analysis/wasserstein_transfer.py	331	transport = sigma_st # fallback: just use cross-covariance	CODE
MEDIUM⚡	obliteratus/evaluation/advanced_metrics.py	128	# Extended refusal substrings for more robust detection (all lowercase)	COMMENT
MEDIUM⚡	obliteratus/evaluation/heretic_eval.py	597	# ── lm-evaluation-harness Integration ────────────────────────────────	COMMENT
MEDIUM⚡	obliteratus/evaluation/heretic_eval.py	600	# preservation, all run through EleutherAI's lm-evaluation-harness.	COMMENT
MEDIUM	obliteratus/evaluation/heretic_eval.py	826	# Capability preservation (lm-eval-harness)	COMMENT
MEDIUM	obliteratus/evaluation/heretic_eval.py	1127	# Slice on token IDs (not string length) for robust extraction	COMMENT
MEDIUM	obliteratus/evaluation/heretic_eval.py	1189	# ── lm-evaluation-harness benchmarks ──	COMMENT

Cross-Language Confusion9 hits · 38 pts

Severity	File	Line	Snippet	Context
HIGH	app.py	4251	if (el.value && el.value.includes('ERROR')) {	CODE
HIGH⚡	tests/test_ci_policy.py	428	assert "CANDIDATE_SHA: ${{ github.event.pull_request.head.sha \|\| github.sha }}" in workflow	CODE
HIGH⚡	tests/test_quality_policy.py	427	meta_by_path={target: '{"exit_code_by_key": {"target__mutmut_1": null}}'},	STRING
HIGH	tests/test_quality_gate_scripts.py	63	valid_meta.write_text('{"exit_code_by_key": {"obliteratus.config.x__mutmut_1": null}}')	CODE
HIGH⚡	tests/test_quality_gate_scripts.py	99	'{"exit_code_by_key": {"obliteratus.analysis.numerical_contracts.x__mutmut_1": null}}',	CODE
HIGH	tests/test_gsq_coverage.py	2212	The pinned writer emits none of these keys; absent counts as null,	STRING
HIGH	obliteratus/abliterate.py	6778	"""Measure mean KL(P_pristine \|\| Q_current) across prompt tokens."""	STRING
HIGH	obliteratus/gsq/coverage.py	2025	as the pinned writer emits -- absent counts as null, anything	STRING
HIGH	obliteratus/evaluation/advanced_metrics.py	502	KL(P_orig \|\| Q_mod) = sum P(x) * (log P(x) - log Q(x))	STRING

Slop Phrases13 hits · 33 pts

Severity	File	Line	Snippet	Context
MEDIUM⚡	tests/test_advanced_metrics.py	110	"I cannot provide that. I am a harmless AI assistant bound by policy.",	CODE
MEDIUM⚡	tests/test_advanced_metrics.py	118	"I apologize, but I'm unable to assist.",	CODE
MEDIUM⚡	tests/test_advanced_metrics.py	119	"As an AI, I cannot provide that information.",	CODE
MEDIUM⚡	tests/test_advanced_metrics.py	165	assert _is_refusal("As an AI language model, I cannot", mode="prefix")	CODE
MEDIUM	tests/test_advanced_metrics.py	135	"I cannot provide that.",	CODE
MEDIUM⚡	tests/test_heretic_eval.py	100	"My apologies, I'm unable to help.",	CODE
MEDIUM	tests/test_refusal_detection.py	38	text = "While I understand your interest in this topic, I cannot provide instructions for that."	CODE
MEDIUM	tests/test_refusal_detection.py	103	"While I understand your interest, I cannot provide that information.",	CODE
MEDIUM	tests/test_edge_cases.py	290	"I'm sorry to hear that. Here's how you can solve the problem: first...",	CODE
MEDIUM	obliteratus/evaluation/advanced_metrics.py	66	"As a language model",	CODE
MEDIUM⚡	obliteratus/evaluation/advanced_metrics.py	138	"as a language model",	CODE
MEDIUM⚡	obliteratus/evaluation/advanced_metrics.py	144	"i'm unable to",	CODE
MEDIUM	obliteratus/evaluation/heretic_eval.py	230	"As an AI", "I'm an", "I'm just", "As a language model",	CODE

AI Structural Patterns23 hits · 16 pts

Severity	File	Line	Context
LOW	app.py	135	CODE
LOW	tests/test_distributed_verification_contracts.py	818	CODE
LOW	obliteratus/abliterate.py	974	CODE
LOW	obliteratus/abliterate.py	2281	CODE
LOW	obliteratus/phase_admission.py	973	CODE
LOW	obliteratus/phase_admission.py	2236	CODE
LOW	obliteratus/phase_admission.py	2464	CODE
LOW	obliteratus/remote.py	300	CODE
LOW	obliteratus/remote.py	388	CODE
LOW	obliteratus/telemetry.py	1227	CODE
LOW	obliteratus/ui_model_load.py	173	CODE
LOW	obliteratus/tourney.py	824	CODE
LOW	obliteratus/informed_pipeline.py	178	CODE
LOW	obliteratus/analysis/sae_abliteration.py	134	CODE
LOW	obliteratus/models/_load_admission.py	717	CODE
LOW	obliteratus/models/loader.py	804	CODE
LOW	obliteratus/concepts/evaluation.py	55	CODE
LOW	obliteratus/concepts/intervention.py	240	CODE
LOW	obliteratus/gsq/workflow.py	444	CODE
LOW	obliteratus/gsq/workflow.py	3296	CODE
LOW	obliteratus/evaluation/heretic_eval.py	1049	CODE
LOW	scripts/generate_checkpoint_fixtures.py	48	CODE
LOW	scripts/gemma4_chat_ui.py	76	CODE

Over-Commented Block17 hits · 11 pts

Severity	File	Line	Snippet	Context
LOW	requirements-apple.txt	1	# Optional Apple Silicon dependencies for native MLX acceleration.	COMMENT
LOW	obliteratus/abliterate.py	4261	sub = self.concept_subspaces[idx]	COMMENT
LOW	obliteratus/abliterate.py	4401	# Extends discrete integer layer targeting to continuous weights.	COMMENT
LOW	obliteratus/abliterate.py	4481		COMMENT
LOW	obliteratus/abliterate.py	5781	# With norm_preserve=True, this creates pathological amplification:	COMMENT
LOW	obliteratus/abliterate.py	6141	# already catches residual signal)	COMMENT
LOW	obliteratus/abliterate.py	6261	f"Abliteration produced ZERO projections across {len(self._strong_layers)} "	COMMENT
LOW	obliteratus/analysis/wasserstein_optimal.py	161	# Since E = d d^T is rank-1, we can solve this analytically.	COMMENT
LOW	obliteratus/gsq/coverage.py	2821	_require_no_competing_weight_files(root, key_files)	COMMENT
LOW	obliteratus/gsq/workflow.py	41	# Exclusive launch lock in the absolute training checkpoint dir. ``run``	COMMENT
LOW	obliteratus/gsq/workflow.py	61	# ``wbits=4`` and assembly never overrides it): validation certifies no	COMMENT
LOW	obliteratus/gsq/workflow.py	1541	# has exited, and bind the recomputed (unverified) values when	COMMENT
LOW	obliteratus/gsq/workflow.py	1801	run_dir = resolve_run_dir(checkpoint_dir, run_id).resolve()	COMMENT
LOW	obliteratus/gsq/source.py	761	guard_bytes = _guard_source_bytes()	COMMENT
LOW	examples/remote_gpu_node.yaml	1	# Example: Run an ablation study on a remote GPU node via SSH.	COMMENT
LOW	scripts/run_benchmark_remote.sh	1	#!/usr/bin/env bash	COMMENT
LOW	.github/actionlint.yaml	1	self-hosted-runner:	COMMENT

Self-Referential Comments5 hits · 10 pts

Severity	File	Line	Snippet	Context
MEDIUM	app.py	110	# Create a no-op decorator that mirrors spaces.GPU interface so the same	COMMENT
MEDIUM	tests/test_heretic_eval.py	135	# Create a non-uniform distribution peaked at _peak_idx	COMMENT
MEDIUM	tests/test_abliterate.py	1813	# Create a hidden state with strong refusal component	COMMENT
MEDIUM	tests/test_abliterate.py	1921	# Create a fake model whose state_dict returns a meta tensor.	COMMENT
MEDIUM	tests/test_abliteration_math.py	52	# Create a vector orthogonal to d	COMMENT

Modern AI Meta-Vocabulary4 hits · 10 pts

Severity	File	Line	Snippet	Context
MEDIUM	.aiwg/testing/gate3-increment-5-report.md	1	# Gate 3 increment 5 service-orchestration report	COMMENT
MEDIUM	tests/test_informed_pipeline_contracts.py	27	# These tests isolate orchestration/analysis with deliberately incomplete	COMMENT
MEDIUM⚡	obliteratus/abliterate.py	4495	# ── CoT-aware ablation: reasoning trace preservation ──────────	COMMENT
MEDIUM⚡	obliteratus/abliterate.py	4496	# Models with chain-of-thought reasoning (GPT-OSS, QwQ, DeepSeek-R1)	COMMENT

Synthetic Comment Markers2 hits · 10 pts

Severity	File	Line	Snippet	Context
HIGH	AGENTS.md	3	<!-- Generated by AIWG. Edit AGENTS.override.md for operator additions. -->	CODE
HIGH	docs/RESEARCH_SURVEY.md	732	Dataset: 4,289 harmful prompts + 5,711 benign pairs = 10,000 examples. Extended refusals generated by GPT-4O.	CODE

Docstring Block Structure2 hits · 10 pts

Severity	File	Line	Snippet	Context
HIGH	obliteratus/community.py	91	Save a contribution record from a completed pipeline run. Unlike telemetry, this: - Includes the public model n	STRING
HIGH	obliteratus/evaluation/lm_eval_integration.py	55	Run lm-evaluation-harness benchmarks on a model. Args: model_path: HuggingFace model name or local path.	STRING

Redundant / Tautological Comments7 hits · 10 pts

Severity	File	Line	Snippet	Context
LOW	tests/test_novel_analysis.py	60	# Assign prompts to categories	COMMENT
LOW	obliteratus/watchtower.py	346	# Check if we've already seen this model	COMMENT
LOW	obliteratus/informed_pipeline.py	1229	# Check if Ouroboros compensation is needed	COMMENT
LOW	obliteratus/auto_obliterate.py	557	# Check if we've achieved target	COMMENT
LOW	obliteratus/auto_obliterate.py	567	# Check if refusal rate is 0 — perfect score, stop early	COMMENT
LOW	obliteratus/analysis/sae_abliteration.py	574	# Assign features to nearest centroid (5 iterations)	COMMENT
LOW	obliteratus/analysis/conditional_abliteration.py	321	# Check if condition matches (would this projector fire?)	COMMENT

Fake / Example Data9 hits · 8 pts

Severity	File	Line	Snippet	Context
LOW	tests/test_ui_model_slot.py	1064	120, load_model, Streamer, lambda text: text, lambda: "fake-token",	CODE
LOW	tests/test_gsq_workflow.py	2391	with pytest.raises(ValueError, match="placeholder"):	CODE
LOW	tests/test_gsq_workflow.py	2395	with pytest.raises(ValueError, match="placeholder"):	CODE
LOW⚡	tests/test_secrets.py	123	broker.write_text("placeholder", encoding="utf-8")	CODE
LOW⚡	tests/test_secrets.py	134	broker.write_text("placeholder", encoding="utf-8")	CODE
LOW⚡	tests/test_secrets.py	150	broker.write_text("placeholder", encoding="utf-8")	CODE
LOW	tests/test_secrets.py	171	broker.write_text("placeholder", encoding="utf-8")	CODE
LOW	tests/test_secrets.py	186	broker.write_text("placeholder", encoding="utf-8")	CODE
LOW	tests/test_notebook_contract.py	159	namespace, events, hub, _ = _run_harness(monkeypatch, token="fake-token")	CODE

Example Usage Blocks2 hits · 4 pts

Severity	File	Line	Snippet	Context
LOW	examples/remote_gpu_node.yaml	3	# Usage:	COMMENT
LOW⚡	scripts/run_benchmark_remote.sh	7	# Usage:	COMMENT

Maintenance and Governance Review

Risk Review · v3

What These Metrics Mean

Pattern-Signal History

Severity Breakdown

Directory Score Breakdown

Pattern Findings