CompressionBenchmark / FINAL160_FORMAT_AUDIT.json
jzxiao's picture
Apply uniform min128 dataset scope and compact Overall rows
86c9d33 verified
Raw History Blame Contribute Delete
142 kB
{
"classification_counts": {
"bound_source_to_typed_contract_pass_no_processing_error_found": 36,
"proven_old_input_incomplete_corrected_input_ready_results_pending": 1,
"proven_old_input_incomplete_new_input_required": 2,
"proven_prior_input_error_corrected_and_published": 3,
"source_to_typed_pass_duplicate_scientific_workload_identity": 2,
"source_to_typed_semantics_audited_no_processing_error": 2
},
"conclusions": {
"all_flagged_old_value_payloads_numeric": true,
"already_corrected_and_published_dataset_count": 3,
"caveat": "Metadata-contract pass proves the frozen source/export/typed bindings checked here; it does not prove every upstream scientific labeling choice. The three cap/precision/row-cleaning defects use separate full-source or upstream audits.",
"corrected_input_ready_results_pending_dataset_count": 1,
"current_numeric_results_to_quarantine_count": 3,
"datasets_with_explicit_additional_temporal_coordinate": 9,
"duplicate_scientific_workload_identity_count": 2,
"high_ratio_alone_is_error": false,
"new_input_required_dataset_count": 2,
"old_bound_metadata_contract_pass_count": 46,
"proven_input_defect_dataset_count": 6
},
"datasets": [
{
"classification": "bound_source_to_typed_contract_pass_no_processing_error_found",
"dataset_id": "africa_senegal_mauritania_crops_spi",
"finding": "Pinned source scans, row/column counts, source SHA bindings, entity mapping, numeric roles/dtypes and identity conversions passed. No cap loss, policy row filtering, string-to-value coercion or source-to-typed mismatch was found. The mean valid run is short, so per-frame overhead is a plausible expansion driver.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 22,
"dropped_value_columns": 0,
"eligible_rows": 27075,
"emitted_rows": 27075,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 30.48677914882901,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 22,
"rows": 27075,
"series": 722,
"source_data_same_pass_sha256": "2af5a2be176aa8faf1e102bd72db38904d173422767ea269859f441943f09a2d",
"source_manifest_sha256": "56c83c3f1eccfe5e743694fea4fc992986fa4f74455bc6da6a191f49279fe0c7",
"source_rows": 27075,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "7d13ad8ef221f1996ee5f7ccc75d7c33e9dffd763021c546a25d18905e72c728",
"value_columns": 22,
"value_dtype_counts": {
"float64": 22
},
"value_logical_blocks": 7942,
"value_missing_cells": 55699,
"value_valid_cells": 242126
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 3.296454677048872,
"evaluated_numeric_overall_algorithms": 74,
"fraction_gt_1_among_numeric": 1.0,
"numeric_pairs_without_overall": 0,
"original_numeric_bytes_max": 1937008,
"original_numeric_bytes_min": 1937008,
"ratio_max": 7.403405664819144,
"ratio_median": 3.1576457092588157,
"ratio_min": 2.6355828163848574,
"ratios_gt_1": 74,
"source_profiles": {
"cpp-native166-current-recovery-v3-baseline86-fixed-profiles-20260919-v3": 1,
"cpp-native166-main-458a218f": 72,
"cpp-native166-v9-recovery-baseline86-fixed-profiles-20260919-v3": 1
},
"terminal_not_applicable_pairs": 11,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "bound_source_to_typed_contract_pass_no_processing_error_found",
"dataset_id": "auto_production_sf",
"finding": "Pinned source scans, row/column counts, source SHA bindings, entity mapping, numeric roles/dtypes and identity conversions passed. No cap loss, policy row filtering, string-to-value coercion or source-to-typed mismatch was found. The bound numeric input is complete; poor compressibility/high entropy and fixed frame cost remain plausible expansion drivers.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 1,
"dropped_value_columns": 0,
"eligible_rows": 367,
"emitted_rows": 367,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 367.0,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 1,
"rows": 367,
"series": 1,
"source_data_same_pass_sha256": "79343b4758070573800e3e44e6d8629de1089dc869299736e59608e213c92171",
"source_manifest_sha256": "ac085dbadb9e7184e4ab6c568a68cd5f8419f22f89ee299f56fc8e8732f61843",
"source_rows": 367,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "826f3ee8ec3b3315e4fe9f7c356ca2e214810120b60b992b3fd4aea6c2a33eca",
"value_columns": 1,
"value_dtype_counts": {
"float32": 1
},
"value_logical_blocks": 1,
"value_missing_cells": 0,
"value_valid_cells": 367
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 1.3215258855585832,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 0.9830508474576272,
"numeric_pairs_without_overall": 0,
"original_numeric_bytes_max": 1468,
"original_numeric_bytes_min": 1468,
"ratio_max": 2.4107629427792916,
"ratio_median": 1.305858310626703,
"ratio_min": 0.9925068119891008,
"ratios_gt_1": 58,
"source_profiles": {
"cpp-native166-main-458a218f": 58,
"cpp-native166-v9-recovery-baseline86-fixed-profiles-20260919-v3": 1
},
"terminal_not_applicable_pairs": 26,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "bound_source_to_typed_contract_pass_no_processing_error_found",
"dataset_id": "azure2019_u",
"finding": "Pinned source scans, row/column counts, source SHA bindings, entity mapping, numeric roles/dtypes and identity conversions passed. No cap loss, policy row filtering, string-to-value coercion or source-to-typed mismatch was found. The bound numeric input is complete; poor compressibility/high entropy and fixed frame cost remain plausible expansion drivers.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 1,
"dropped_value_columns": 0,
"eligible_rows": 329019,
"emitted_rows": 329019,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 1406.0641025641025,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 1,
"rows": 329019,
"series": 234,
"source_data_same_pass_sha256": "5ddf838583cf08115b4dc93b97a167f94b43183514ca4e60916406f2997dd507",
"source_manifest_sha256": "56bca5b5542688ffc6b8ec4389dcea701645fdff68fb71cef5b009b219ba8642",
"source_rows": 329019,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "4b35feb998503f368fb201a1f8a201993d090325d3a316fc06ade78d150eee23",
"value_columns": 1,
"value_dtype_counts": {
"float32": 1
},
"value_logical_blocks": 234,
"value_missing_cells": 0,
"value_valid_cells": 329019
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 1.0946282995042118,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 0.7457627118644068,
"numeric_pairs_without_overall": 0,
"original_numeric_bytes_max": 1316076,
"original_numeric_bytes_min": 1316076,
"ratio_max": 2.1294621283269355,
"ratio_median": 1.1312272239597105,
"ratio_min": 0.9175404763858622,
"ratios_gt_1": 44,
"source_profiles": {
"cpp-native166-current-recovery-v3-baseline86-fixed-profiles-20260919-v3": 1,
"cpp-native166-main-458a218f": 58
},
"terminal_not_applicable_pairs": 26,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "bound_source_to_typed_contract_pass_no_processing_error_found",
"dataset_id": "car_parts",
"finding": "Pinned source scans, row/column counts, source SHA bindings, entity mapping, numeric roles/dtypes and identity conversions passed. No cap loss, policy row filtering, string-to-value coercion or source-to-typed mismatch was found. The mean valid run is short, so per-frame overhead is a plausible expansion driver.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 1,
"additional_temporal_coordinate_dtype_counts": {
"int64": 1
},
"additional_temporal_coordinate_sources": [
{
"conversion": "policy_temporal_string_to_int64_us",
"output_dtype": "int64",
"source_column": "start_timestamp",
"source_type": "STRING"
}
],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 2,
"dropped_value_columns": 0,
"eligible_rows": 135746,
"emitted_rows": 135746,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 50.76514584891548,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 2,
"rows": 135746,
"series": 2674,
"source_data_same_pass_sha256": "78c0c22e05f46db088895679f628eed4a9a0f706a17bb9fb54aff7b133455dc6",
"source_manifest_sha256": "6798716422ab204051894da2b24e8595ac3b70fa58a4b6a514b26e78224657f1",
"source_rows": 135746,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "3deda1e663dfc0f1255b0ddac83b7859d6c6e44ab1790f64b4d311147c6842fe",
"value_columns": 1,
"value_dtype_counts": {
"float32": 1
},
"value_logical_blocks": 2674,
"value_missing_cells": 0,
"value_valid_cells": 135746
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 2.311183509397453,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 1.0,
"numeric_pairs_without_overall": 13,
"original_numeric_bytes_max": 1628952,
"original_numeric_bytes_min": 1628952,
"ratio_max": 5.721246543790118,
"ratio_median": 2.109143793064498,
"ratio_min": 1.9161006585829417,
"ratios_gt_1": 59,
"source_profiles": {
"cpp-native166-current-recovery-v3-baseline86-fixed-profiles-20260919-v3": 2,
"cpp-native166-main-458a218f": 56,
"cpp-native166-v9-recovery-baseline86-fixed-profiles-20260919-v3": 1
},
"terminal_not_applicable_pairs": 13,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "bound_source_to_typed_contract_pass_no_processing_error_found",
"dataset_id": "commodity_import",
"finding": "Pinned source scans, row/column counts, source SHA bindings, entity mapping, numeric roles/dtypes and identity conversions passed. No cap loss, policy row filtering, string-to-value coercion or source-to-typed mismatch was found. The bound numeric input is complete; poor compressibility/high entropy and fixed frame cost remain plausible expansion drivers.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 1,
"dropped_value_columns": 0,
"eligible_rows": 5578,
"emitted_rows": 5578,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 697.25,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 1,
"rows": 5578,
"series": 8,
"source_data_same_pass_sha256": "47666f5e173d900a7e61e1339ac67a773498600557bdfe7a7ee59b00e8be0b05",
"source_manifest_sha256": "2a20a6a22523a724d7d6a01b942b89c1a06ce4df1481376bb26dfdc9185e9227",
"source_rows": 5578,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "aa4773cea4f52bcea10118cd08a3abcff08e47842977599a951fa48927c8c54f",
"value_columns": 1,
"value_dtype_counts": {
"float32": 1
},
"value_logical_blocks": 8,
"value_missing_cells": 0,
"value_valid_cells": 5578
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 1.0507023658318697,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 0.5423728813559322,
"numeric_pairs_without_overall": 0,
"original_numeric_bytes_max": 22312,
"original_numeric_bytes_min": 22312,
"ratio_max": 2.0986464682681967,
"ratio_median": 1.0677214055216924,
"ratio_min": 0.7535855145213338,
"ratios_gt_1": 32,
"source_profiles": {
"cpp-native166-main-458a218f": 58,
"cpp-native166-v9-recovery-baseline86-fixed-profiles-20260919-v3": 1
},
"terminal_not_applicable_pairs": 26,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "bound_source_to_typed_contract_pass_no_processing_error_found",
"dataset_id": "commodity_production",
"finding": "Pinned source scans, row/column counts, source SHA bindings, entity mapping, numeric roles/dtypes and identity conversions passed. No cap loss, policy row filtering, string-to-value coercion or source-to-typed mismatch was found. The bound numeric input is complete; poor compressibility/high entropy and fixed frame cost remain plausible expansion drivers.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 1,
"dropped_value_columns": 0,
"eligible_rows": 10403,
"emitted_rows": 10403,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 325.09375,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 1,
"rows": 10403,
"series": 32,
"source_data_same_pass_sha256": "53c01d38f45fcbe8dbd5bdc67ceca9766d8d5e1acb08c9c4064322d42a64abff",
"source_manifest_sha256": "ce42c13e075c219501eb265689fe603d625af7504f9677bb898e612c4dddd0a7",
"source_rows": 10403,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "63bbd8e4b788c365f911542ae99144c660b94ffe8b3ceec1bb4065ab1fa96fdb",
"value_columns": 1,
"value_dtype_counts": {
"float32": 1
},
"value_logical_blocks": 32,
"value_missing_cells": 0,
"value_valid_cells": 10403
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 1.2772839321121514,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 0.9661016949152542,
"numeric_pairs_without_overall": 0,
"original_numeric_bytes_max": 41612,
"original_numeric_bytes_min": 41612,
"ratio_max": 2.2925358069787563,
"ratio_median": 1.280664231471691,
"ratio_min": 0.9553974814957223,
"ratios_gt_1": 57,
"source_profiles": {
"cpp-native166-current-recovery-v3-baseline86-fixed-profiles-20260919-v3": 1,
"cpp-native166-main-458a218f": 55,
"cpp-native166-v9-recovery-baseline86-fixed-profiles-20260919-v3": 3
},
"terminal_not_applicable_pairs": 26,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "bound_source_to_typed_contract_pass_no_processing_error_found",
"dataset_id": "dmi-aarhus-weather-data",
"finding": "Pinned source scans, row/column counts, source SHA bindings, entity mapping, numeric roles/dtypes and identity conversions passed. No cap loss, policy row filtering, string-to-value coercion or source-to-typed mismatch was found. The mean valid run is short, so per-frame overhead is a plausible expansion driver.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 2,
"additional_temporal_coordinate_dtype_counts": {
"int64": 2
},
"additional_temporal_coordinate_sources": [
{
"conversion": "policy_source_bound_integer_epoch_to_int64_us",
"output_dtype": "int64",
"source_column": "reference_time",
"source_type": "INT64"
},
{
"conversion": "policy_temporal_string_to_int64_us",
"output_dtype": "int64",
"source_column": "reference_time",
"source_type": "STRING"
}
],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 92,
"dropped_value_columns": 0,
"eligible_rows": 43910,
"emitted_rows": 43910,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 45.0082201236156,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 92,
"rows": 43910,
"series": 874,
"source_data_same_pass_sha256": "15643b76cbe39fd2622b534ad5b13eec64665c70ac04438e9d588bcd3d68df6b",
"source_manifest_sha256": "61a13c21d9a83529864551ab1d53aebd1f0a0f05bb981691027edf92ebe56a07",
"source_rows": 43910,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "07816de98eda4e4567d96cfd1f0f0017b9476aad776dfb338c4dac9e0fb496d4",
"value_columns": 90,
"value_dtype_counts": {
"float64": 77,
"int64": 13
},
"value_logical_blocks": 63746,
"value_missing_cells": 202944,
"value_valid_cells": 2869094
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 2.040529349340417,
"evaluated_numeric_overall_algorithms": 63,
"fraction_gt_1_among_numeric": 1.0,
"numeric_pairs_without_overall": 22,
"original_numeric_bytes_max": 23304032,
"original_numeric_bytes_min": 23304032,
"ratio_max": 4.675825153346854,
"ratio_median": 1.8857719985966377,
"ratio_min": 1.7216321621940787,
"ratios_gt_1": 63,
"source_profiles": {
"cpp-native166-current-recovery-v3-baseline86-fixed-profiles-20260919-v3": 1,
"cpp-native166-main-458a218f": 60,
"cpp-native166-v9-recovery-baseline86-fixed-profiles-20260919-v3": 2
},
"terminal_not_applicable_pairs": 0,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "bound_source_to_typed_contract_pass_no_processing_error_found",
"dataset_id": "ecdc_covid",
"finding": "Pinned source scans, row/column counts, source SHA bindings, entity mapping, numeric roles/dtypes and identity conversions passed. No cap loss, policy row filtering, string-to-value coercion or source-to-typed mismatch was found. The bound numeric input is complete; poor compressibility/high entropy and fixed frame cost remain plausible expansion drivers.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 1,
"dropped_value_columns": 0,
"eligible_rows": 12696,
"emitted_rows": 12696,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 491.6,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 1,
"rows": 12696,
"series": 25,
"source_data_same_pass_sha256": "95588cd8e1e8c85d38c91213b241b17318e821c1b6da178987c3e2907d62b50d",
"source_manifest_sha256": "ab44eccbc942a86f8fa769088e3ea4e01c87afb975febb2cc800730625ccf35d",
"source_rows": 12696,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "b3c3f67c0d8976c8ace32792ea9f3546e95c0a037fbe8a58d527a4ed6332efc0",
"value_columns": 1,
"value_dtype_counts": {
"float32": 1
},
"value_logical_blocks": 25,
"value_missing_cells": 406,
"value_valid_cells": 12290
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 1.033938299016701,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 0.5254237288135594,
"numeric_pairs_without_overall": 0,
"original_numeric_bytes_max": 49160,
"original_numeric_bytes_min": 49160,
"ratio_max": 2.064117168429618,
"ratio_median": 1.0520748576078112,
"ratio_min": 0.7532343368592351,
"ratios_gt_1": 31,
"source_profiles": {
"cpp-native166-current-recovery-v3-baseline86-fixed-profiles-20260919-v3": 3,
"cpp-native166-main-458a218f": 56
},
"terminal_not_applicable_pairs": 26,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "bound_source_to_typed_contract_pass_no_processing_error_found",
"dataset_id": "electricity_production",
"finding": "Pinned source scans, row/column counts, source SHA bindings, entity mapping, numeric roles/dtypes and identity conversions passed. No cap loss, policy row filtering, string-to-value coercion or source-to-typed mismatch was found. The bound numeric input is complete; poor compressibility/high entropy and fixed frame cost remain plausible expansion drivers.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 1,
"dropped_value_columns": 0,
"eligible_rows": 397,
"emitted_rows": 397,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 397.0,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 1,
"rows": 397,
"series": 1,
"source_data_same_pass_sha256": "16c71cc9240f019c3c6b96970388c0b9d51fe3cbab6411e849162414983f089f",
"source_manifest_sha256": "7a639d940946aa25439d207d6e23be33f36687f334f2c91db48ede79a4c602c5",
"source_rows": 397,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "a98f876267f9ab3dc0010d212ecd9155576943e9343bd470bb9ba5782c4a303b",
"value_columns": 1,
"value_dtype_counts": {
"float32": 1
},
"value_logical_blocks": 1,
"value_missing_cells": 0,
"value_valid_cells": 397
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 1.4083166118772148,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 1.0,
"numeric_pairs_without_overall": 0,
"original_numeric_bytes_max": 1588,
"original_numeric_bytes_min": 1588,
"ratio_max": 2.408690176322418,
"ratio_median": 1.4042821158690175,
"ratio_min": 1.1769521410579344,
"ratios_gt_1": 59,
"source_profiles": {
"cpp-native166-current-recovery-v3-baseline86-fixed-profiles-20260919-v3": 1,
"cpp-native166-main-458a218f": 58
},
"terminal_not_applicable_pairs": 26,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "bound_source_to_typed_contract_pass_no_processing_error_found",
"dataset_id": "forex_factory_calendar",
"finding": "Pinned source scans, row/column counts, source SHA bindings, entity mapping, numeric roles/dtypes and identity conversions passed. No cap loss, policy row filtering, string-to-value coercion or source-to-typed mismatch was found. The mean valid run is short, so per-frame overhead is a plausible expansion driver.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 3,
"dropped_value_columns": 0,
"eligible_rows": 83427,
"emitted_rows": 83427,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 19.805200945626478,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 3,
"rows": 83427,
"series": 705,
"source_data_same_pass_sha256": "3c5d8c8a75579c1e442a9efd2c897a144d0f1ff8380e5f3474fe771071357ade",
"source_manifest_sha256": "54125fded7c918a24d0d82023e9761df1a2d32561546ac07951619121f1fec97",
"source_rows": 83427,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "567b0348c0eba7ff3d55665d2615dff67654636d51a7387da065f8892e32217d",
"value_columns": 3,
"value_dtype_counts": {
"float64": 3
},
"value_logical_blocks": 2115,
"value_missing_cells": 208393,
"value_valid_cells": 41888
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 4.217338739857122,
"evaluated_numeric_overall_algorithms": 74,
"fraction_gt_1_among_numeric": 1.0,
"numeric_pairs_without_overall": 0,
"original_numeric_bytes_max": 335104,
"original_numeric_bytes_min": 335104,
"ratio_max": 4.90449830500382,
"ratio_median": 4.239095922459893,
"ratio_min": 3.7254225553857907,
"ratios_gt_1": 74,
"source_profiles": {
"cpp-native166-current-recovery-v3-baseline86-fixed-profiles-20260919-v3": 2,
"cpp-native166-main-458a218f": 71,
"cpp-native166-v9-recovery-baseline86-fixed-profiles-20260919-v3": 1
},
"terminal_not_applicable_pairs": 11,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "proven_old_input_incomplete_corrected_input_ready_results_pending",
"dataset_id": "freshretailnet_50k",
"finding": "The published ratio rows still use the old 74/114-column 1 GB-capped input. Forty train columns were omitted. A new full114 input is independently READY and must replace the old 85-family row atomically after its replacement campaign is accepted.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 114,
"dropped_value_columns": 40,
"eligible_rows": 4850000,
"emitted_rows": 4850000,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 26.06756756756757,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 74,
"rows": 4850000,
"series": 100000,
"source_data_same_pass_sha256": "7884559c9ae04d2f040ebe1d32a3f3b637521d89cbd09c9be1834f33f1c557d7",
"source_manifest_sha256": "a3863424fd5b31d8bea73d920324b401a7cc9342e0ae565a2b514478ac9ad297",
"source_rows": 4850000,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "b5af41a84bcf4d585279620acd2a4cd4d0bc827c39b4099d1d1778afa6ce919b",
"value_columns": 74,
"value_dtype_counts": {
"float32": 59,
"float64": 10,
"int64": 5
},
"value_logical_blocks": 3700000,
"value_missing_cells": 0,
"value_valid_cells": 96450000
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 5.019930072462313,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 1.0,
"numeric_pairs_without_overall": 24,
"original_numeric_bytes_max": 506400000,
"original_numeric_bytes_min": 506400000,
"ratio_max": 12.293124701816746,
"ratio_median": 4.718273775671406,
"ratio_min": 4.280599439178515,
"ratios_gt_1": 59,
"source_profiles": {
"cpp-native166-current-recovery-v3-baseline86-fixed-profiles-20260919-v3": 3,
"cpp-native166-main-458a218f": 53,
"cpp-native192-lzg-level5-fastfalse-lzg-level5-fast0-ngf1-fixed-20261010-v1": 1,
"cpp-native192-next5-baseline86-fixed-profiles-20260919-v3": 2
},
"terminal_not_applicable_pairs": 2,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": true,
"rerun_requirement": "57 remaining replacement families on full114 input; 50 whole-pair plus seven column families (798 column tasks)."
}
},
{
"classification": "proven_old_input_incomplete_new_input_required",
"dataset_id": "freshretailnet_lt",
"finding": "The old export retained 66/114 table-qualified numeric columns and dropped 48 trailing train columns under the 1 GB cap. All 7,939,549 source rows were retained, but the value-column universe is incomplete.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 114,
"dropped_value_columns": 48,
"eligible_rows": 7939549,
"emitted_rows": 7939549,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 96.35629421560408,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 66,
"rows": 7939549,
"series": 32939,
"source_data_same_pass_sha256": "4a375af6f579df6f593406584e84fc31f97c187c75803fee5168b054f7bb294e",
"source_manifest_sha256": "561e6fd7ab894fca99c3d702aac367f0009edcc05b75308649c5c80fab5e7057",
"source_rows": 7939549,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "08b1d7abcecb2df3724937e6c4b760ea47ac1e191b379ce6f81bf1aa763435ef",
"value_columns": 66,
"value_dtype_counts": {
"float32": 51,
"float64": 10,
"int64": 5
},
"value_logical_blocks": 776451,
"value_missing_cells": 0,
"value_valid_cells": 74815941
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 1.3152925517120657,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 1.0,
"numeric_pairs_without_overall": 24,
"original_numeric_bytes_max": 490652940,
"original_numeric_bytes_min": 490652940,
"ratio_max": 2.9758906488973653,
"ratio_median": 1.2271027031856774,
"ratio_min": 1.0762331109235788,
"ratios_gt_1": 59,
"source_profiles": {
"cpp-native166-current-recovery-v3-baseline86-fixed-profiles-20260919-v3": 4,
"cpp-native166-main-458a218f": 51,
"cpp-native192-first12-baseline86-fixed-profiles-20260919-v3": 3,
"cpp-native192-lzg-level5-fastfalse-lzg-level5-fast0-ngf1-fixed-20261010-v1": 1
},
"terminal_not_applicable_pairs": 2,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": true,
"rerun_requirement": "All 85 active families on the new full114 input after independent input acceptance."
}
},
{
"classification": "proven_prior_input_error_corrected_and_published",
"corrected_input": {
"rows": 85173,
"series": 14500,
"value_dtype_counts": {
"int64": 3
}
},
"dataset_id": "github_top_projects",
"finding": "The 423,098 source rows are snapshots, not missing input. Last-complete(owner,name,date) yields the intended 85,173-row/14,500-entity workload; corrected integer-preserving results are published.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 3,
"dropped_value_columns": 0,
"eligible_rows": 85173,
"emitted_rows": 85173,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 5.401241379310345,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 3,
"rows": 85173,
"series": 14500,
"source_data_same_pass_sha256": "2e65fff666839ea89a25ce3d97e2aa2cc087e2c4f3dc8d589a062c2fa49b123d",
"source_manifest_sha256": "4722fb417eff3a33b55b19cf6eea9f478a3419b9f41c196506dc5355d72a79da",
"source_rows": 85173,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "d730890e1f98b8f7e88235c3b848b1ab07b82e0b1342394f9866be085c3d6097",
"value_columns": 3,
"value_dtype_counts": {
"float32": 2,
"int64": 1
},
"value_logical_blocks": 43500,
"value_missing_cells": 20565,
"value_valid_cells": 234954
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 14.629772587577426,
"evaluated_numeric_overall_algorithms": 72,
"fraction_gt_1_among_numeric": 1.0,
"numeric_pairs_without_overall": 0,
"original_numeric_bytes_max": 1879632,
"original_numeric_bytes_min": 1879632,
"ratio_max": 34.76760610587604,
"ratio_median": 14.024594973909785,
"ratio_min": 12.782586165802668,
"ratios_gt_1": 72,
"source_profiles": {
"cpp-native166-corrected-five-20261012-v1": 72
},
"terminal_not_applicable_pairs": 0,
"terminal_unsupported_pairs": 13
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "bound_source_to_typed_contract_pass_no_processing_error_found",
"dataset_id": "global_influenza",
"finding": "Pinned source scans, row/column counts, source SHA bindings, entity mapping, numeric roles/dtypes and identity conversions passed. No cap loss, policy row filtering, string-to-value coercion or source-to-typed mismatch was found. The bound numeric input is complete; poor compressibility/high entropy and fixed frame cost remain plausible expansion drivers.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 1,
"dropped_value_columns": 0,
"eligible_rows": 12293,
"emitted_rows": 12293,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 201.75,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 1,
"rows": 12293,
"series": 60,
"source_data_same_pass_sha256": "9bab1ec34871ac59fbc24d6c66746dafb690c3353187cd42a62cf35d024a21ed",
"source_manifest_sha256": "809f2b0df59bcf65b3d09553b9ba01638e0f47843c601568299ccc8668bdd8ba",
"source_rows": 12293,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "abad355b9650bb55d3ee0f1751ee96b8f319aebae1fa44401901f4d8cb02d35d",
"value_columns": 1,
"value_dtype_counts": {
"float32": 1
},
"value_logical_blocks": 60,
"value_missing_cells": 188,
"value_valid_cells": 12105
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 1.5375209151562248,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 1.0,
"numeric_pairs_without_overall": 0,
"original_numeric_bytes_max": 48420,
"original_numeric_bytes_min": 48420,
"ratio_max": 2.5853366377529947,
"ratio_median": 1.546695580338703,
"ratio_min": 1.2051218504750103,
"ratios_gt_1": 59,
"source_profiles": {
"cpp-native166-current-recovery-v3-baseline86-fixed-profiles-20260919-v3": 1,
"cpp-native166-main-458a218f": 56,
"cpp-native166-v9-recovery-baseline86-fixed-profiles-20260919-v3": 2
},
"terminal_not_applicable_pairs": 26,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "bound_source_to_typed_contract_pass_no_processing_error_found",
"dataset_id": "global_price",
"finding": "Pinned source scans, row/column counts, source SHA bindings, entity mapping, numeric roles/dtypes and identity conversions passed. No cap loss, policy row filtering, string-to-value coercion or source-to-typed mismatch was found. The bound numeric input is complete; poor compressibility/high entropy and fixed frame cost remain plausible expansion drivers.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 1,
"dropped_value_columns": 0,
"eligible_rows": 8520,
"emitted_rows": 8520,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 141.06666666666666,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 1,
"rows": 8520,
"series": 60,
"source_data_same_pass_sha256": "8e984cfab3dc524fcf6db05fe555a8fb9aabb9b7861afdb366783b9bf7218097",
"source_manifest_sha256": "b103dd60d12358548cea6f322ceab2317232bfc56a58e89aaab79885993577fe",
"source_rows": 8520,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "b92c5c6df2e35f2ee1410c1ffc20433f3f3c1bbbc423e61b735f32c5310c28ee",
"value_columns": 1,
"value_dtype_counts": {
"float32": 1
},
"value_logical_blocks": 60,
"value_missing_cells": 56,
"value_valid_cells": 8464
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 2.142094333728493,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 1.0,
"numeric_pairs_without_overall": 0,
"original_numeric_bytes_max": 33856,
"original_numeric_bytes_min": 33856,
"ratio_max": 3.7629076086956523,
"ratio_median": 2.0687913516068055,
"ratio_min": 1.909469517958412,
"ratios_gt_1": 59,
"source_profiles": {
"cpp-native166-main-458a218f": 57,
"cpp-native166-v9-recovery-baseline86-fixed-profiles-20260919-v3": 2
},
"terminal_not_applicable_pairs": 26,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "bound_source_to_typed_contract_pass_no_processing_error_found",
"dataset_id": "greatplains_multisource_2000_2024",
"finding": "Pinned source scans, row/column counts, source SHA bindings, entity mapping, numeric roles/dtypes and identity conversions passed. No cap loss, policy row filtering, string-to-value coercion or source-to-typed mismatch was found. The bound numeric input is complete; poor compressibility/high entropy and fixed frame cost remain plausible expansion drivers.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 5,
"dropped_value_columns": 0,
"eligible_rows": 1143,
"emitted_rows": 1143,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 1143.0,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 5,
"rows": 1143,
"series": 1,
"source_data_same_pass_sha256": "fb0c6ecf2648f739c2df4bdf748b5c320b277c7a3705bce9199ff5f67703f89c",
"source_manifest_sha256": "db58ee65078354939f8d8945c2a7d3af439b77e08a1146245c1d0c2551fbf531",
"source_rows": 1143,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "7a13bf97cbaf1b64fbaf0bf856e10b844810d202757ed85380ff133d1d1b375a",
"value_columns": 5,
"value_dtype_counts": {
"float32": 5
},
"value_logical_blocks": 5,
"value_missing_cells": 0,
"value_valid_cells": 5715
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 1.1412384892566396,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 0.9152542372881356,
"numeric_pairs_without_overall": 0,
"original_numeric_bytes_max": 22860,
"original_numeric_bytes_min": 22860,
"ratio_max": 2.1570428696412947,
"ratio_median": 1.1605424321959754,
"ratio_min": 0.9771653543307086,
"ratios_gt_1": 54,
"source_profiles": {
"cpp-native166-main-458a218f": 59
},
"terminal_not_applicable_pairs": 26,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "bound_source_to_typed_contract_pass_no_processing_error_found",
"dataset_id": "hospital-monash",
"finding": "Pinned source scans, row/column counts, source SHA bindings, entity mapping, numeric roles/dtypes and identity conversions passed. No cap loss, policy row filtering, string-to-value coercion or source-to-typed mismatch was found. The bound numeric input is complete; poor compressibility/high entropy and fixed frame cost remain plausible expansion drivers.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 1,
"additional_temporal_coordinate_dtype_counts": {
"int64": 1
},
"additional_temporal_coordinate_sources": [
{
"conversion": "policy_temporal_string_to_int64_us",
"output_dtype": "int64",
"source_column": "start_timestamp",
"source_type": "STRING"
}
],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 2,
"dropped_value_columns": 0,
"eligible_rows": 64428,
"emitted_rows": 64428,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 84.0,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 2,
"rows": 64428,
"series": 767,
"source_data_same_pass_sha256": "1c63432d694c7ffd4bd48b18dafc7591d915e4309df1a3a51f24a8b018fa85d6",
"source_manifest_sha256": "0cc2e3a1f9707569bd5d3ed2e26134701a8575d059457c5c115a23b6d8d896bd",
"source_rows": 64428,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "9ccb7c12def299f710a0b5418f3fb31cea3caf22b651dccd532531e8519a1e56",
"value_columns": 1,
"value_dtype_counts": {
"float32": 1
},
"value_logical_blocks": 767,
"value_missing_cells": 0,
"value_valid_cells": 64428
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 1.5748470065476672,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 1.0,
"numeric_pairs_without_overall": 13,
"original_numeric_bytes_max": 773136,
"original_numeric_bytes_min": 773136,
"ratio_max": 3.674168580948242,
"ratio_median": 1.4389525258169327,
"ratio_min": 1.2659971854887109,
"ratios_gt_1": 59,
"source_profiles": {
"cpp-native166-main-458a218f": 58,
"cpp-native166-v9-recovery-baseline86-fixed-profiles-20260919-v3": 1
},
"terminal_not_applicable_pairs": 13,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "bound_source_to_typed_contract_pass_no_processing_error_found",
"dataset_id": "hourly_electricity_demand_brazil",
"finding": "Pinned source scans, row/column counts, source SHA bindings, entity mapping, numeric roles/dtypes and identity conversions passed. No cap loss, policy row filtering, string-to-value coercion or source-to-typed mismatch was found. The bound numeric input is complete; poor compressibility/high entropy and fixed frame cost remain plausible expansion drivers.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 1,
"dropped_value_columns": 0,
"eligible_rows": 185280,
"emitted_rows": 185280,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 9264.0,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 1,
"rows": 185280,
"series": 4,
"source_data_same_pass_sha256": "8a6db48f356819cf124fcc37a3051256c7668b4f2fc9be9a14fa1945ddaa093d",
"source_manifest_sha256": "f57ff8f63077a211f44337209c31995d262c2f742ada7e7fccc7bcc20a1bd6bc",
"source_rows": 185280,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "ac4053eaf5624e276c32f226d5b90ee9819a3d2b4d2acc24ac4e76b80963f7df",
"value_columns": 1,
"value_dtype_counts": {
"float32": 1
},
"value_logical_blocks": 20,
"value_missing_cells": 0,
"value_valid_cells": 185280
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 0.9796606967740992,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 0.5254237288135594,
"numeric_pairs_without_overall": 0,
"original_numeric_bytes_max": 741120,
"original_numeric_bytes_min": 741120,
"ratio_max": 2.0385011873920553,
"ratio_median": 1.0092495142487046,
"ratio_min": 0.7969667530224525,
"ratios_gt_1": 31,
"source_profiles": {
"cpp-native166-main-458a218f": 58,
"cpp-native166-v9-recovery-baseline86-fixed-profiles-20260919-v3": 1
},
"terminal_not_applicable_pairs": 26,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "bound_source_to_typed_contract_pass_no_processing_error_found",
"dataset_id": "housing_inventory",
"finding": "Pinned source scans, row/column counts, source SHA bindings, entity mapping, numeric roles/dtypes and identity conversions passed. No cap loss, policy row filtering, string-to-value coercion or source-to-typed mismatch was found. The bound numeric input is complete; poor compressibility/high entropy and fixed frame cost remain plausible expansion drivers.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 1,
"dropped_value_columns": 0,
"eligible_rows": 456,
"emitted_rows": 456,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 114.0,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 1,
"rows": 456,
"series": 4,
"source_data_same_pass_sha256": "bdeaa1dff7cb69f30811d45f45a2327a67392c1f0ce716f8fa76a508e43c56e0",
"source_manifest_sha256": "75a3fe2037008569d00431f0415722450036b9222813079f141a1727f599a27a",
"source_rows": 456,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "798085150daf04292d158ce9220ec446580bf2f7bef0b9c77822f738f2964d0b",
"value_columns": 1,
"value_dtype_counts": {
"float32": 1
},
"value_logical_blocks": 4,
"value_missing_cells": 0,
"value_valid_cells": 456
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 2.2260909158489444,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 1.0,
"numeric_pairs_without_overall": 0,
"original_numeric_bytes_max": 1824,
"original_numeric_bytes_min": 1824,
"ratio_max": 4.243421052631579,
"ratio_median": 2.155701754385965,
"ratio_min": 1.868969298245614,
"ratios_gt_1": 59,
"source_profiles": {
"cpp-native166-main-458a218f": 58,
"cpp-native166-v9-recovery-baseline86-fixed-profiles-20260919-v3": 1
},
"terminal_not_applicable_pairs": 26,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "bound_source_to_typed_contract_pass_no_processing_error_found",
"dataset_id": "job_claims",
"finding": "Pinned source scans, row/column counts, source SHA bindings, entity mapping, numeric roles/dtypes and identity conversions passed. No cap loss, policy row filtering, string-to-value coercion or source-to-typed mismatch was found. The bound numeric input is complete; poor compressibility/high entropy and fixed frame cost remain plausible expansion drivers.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 1,
"dropped_value_columns": 0,
"eligible_rows": 392,
"emitted_rows": 392,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 196.0,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 1,
"rows": 392,
"series": 2,
"source_data_same_pass_sha256": "61e6868cc1f952ae12c3c2a902967b0b9a2c823a0d0f76efda2794434b90928b",
"source_manifest_sha256": "47af6f353996558a1f4b5a19fe11c898f7a47378b0466141d616141ca734d4de",
"source_rows": 392,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "5d58409abbe8f4e69b75b96a0f89219d1232bae4c8d1061f235467c1e93c5704",
"value_columns": 1,
"value_dtype_counts": {
"float32": 1
},
"value_logical_blocks": 2,
"value_missing_cells": 0,
"value_valid_cells": 392
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 1.7068164130058803,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 1.0,
"numeric_pairs_without_overall": 0,
"original_numeric_bytes_max": 1568,
"original_numeric_bytes_min": 1568,
"ratio_max": 2.8309948979591835,
"ratio_median": 1.6766581632653061,
"ratio_min": 1.3966836734693877,
"ratios_gt_1": 59,
"source_profiles": {
"cpp-native166-main-458a218f": 58,
"cpp-native166-v9-recovery-baseline86-fixed-profiles-20260919-v3": 1
},
"terminal_not_applicable_pairs": 26,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "bound_source_to_typed_contract_pass_no_processing_error_found",
"dataset_id": "jolts",
"finding": "Pinned source scans, row/column counts, source SHA bindings, entity mapping, numeric roles/dtypes and identity conversions passed. No cap loss, policy row filtering, string-to-value coercion or source-to-typed mismatch was found. The bound numeric input is complete; poor compressibility/high entropy and fixed frame cost remain plausible expansion drivers.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 1,
"dropped_value_columns": 0,
"eligible_rows": 1782,
"emitted_rows": 1782,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 297.0,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 1,
"rows": 1782,
"series": 6,
"source_data_same_pass_sha256": "c6af0a88930aacf84ca54c763696393d289c55b40bfd86b299a769aa651260f6",
"source_manifest_sha256": "388e216763e48f93d8e246831a1b42fc0351e0205372855c8dba25652df94356",
"source_rows": 1782,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "ec04f191edfa0e449111b7d9c4740215767c1416e345526592ed91634198635c",
"value_columns": 1,
"value_dtype_counts": {
"float32": 1
},
"value_logical_blocks": 6,
"value_missing_cells": 0,
"value_valid_cells": 1782
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 1.3411492514599859,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 1.0,
"numeric_pairs_without_overall": 0,
"original_numeric_bytes_max": 7128,
"original_numeric_bytes_min": 7128,
"ratio_max": 2.467171717171717,
"ratio_median": 1.3671436588103254,
"ratio_min": 1.00827721661055,
"ratios_gt_1": 59,
"source_profiles": {
"cpp-native166-main-458a218f": 58,
"cpp-native166-v9-recovery-baseline86-fixed-profiles-20260919-v3": 1
},
"terminal_not_applicable_pairs": 26,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "proven_old_input_incomplete_new_input_required",
"dataset_id": "kaggle_web_traffic",
"finding": "The old export retained only 33,860,956 of 116,476,879 eligible source rows because of the 1 GB cap (82,615,923 rows lost). The one scientific value is FLOAT target; physical Time is the temporal coordinate and TAG fields (including start_timestamp) are metadata, not value payload.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 2,
"dropped_value_columns": 1,
"eligible_rows": 116476879,
"emitted_rows": 33860956,
"lost_rows_due_to_byte_cap": 82615923,
"mean_valid_values_per_value_block": 233.422416467328,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 1,
"rows": 33860956,
"series": 145063,
"source_data_same_pass_sha256": "ac194b44801518d73192b3d695947a8e74920076c8ad434ec04fba8030f5aa9a",
"source_manifest_sha256": "b145cc56b4bd06f9b21c74e00ed02ab26c94e8a218edd803fc5dee7a430166d0",
"source_rows": 116476879,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "b0c2aaedfb408b87eec99a20f21bc61dfa668a444f987e7e11bf2ad375b41ade",
"value_columns": 1,
"value_dtype_counts": {
"float32": 1
},
"value_logical_blocks": 145063,
"value_missing_cells": 0,
"value_valid_cells": 33860956
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 1.282586011577384,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 0.9830508474576272,
"numeric_pairs_without_overall": 0,
"original_numeric_bytes_max": 135443824,
"original_numeric_bytes_min": 135443824,
"ratio_max": 2.245959734568628,
"ratio_median": 1.2710712450056048,
"ratio_min": 0.9766709037984633,
"ratios_gt_1": 58,
"source_profiles": {
"cpp-native166-current-recovery-v3-baseline86-fixed-profiles-20260919-v3": 3,
"cpp-native166-main-458a218f": 54,
"cpp-native166-v9-recovery-baseline86-fixed-profiles-20260919-v3": 2
},
"terminal_not_applicable_pairs": 26,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": true,
"rerun_requirement": "All 85 active families on a full-row target-only input after independent input acceptance; preserve all 7,018,638 source target NaNs as canonical NaN bits."
}
},
{
"classification": "bound_source_to_typed_contract_pass_no_processing_error_found",
"dataset_id": "kaggle_web_traffic_weekly",
"finding": "Pinned source scans, row/column counts, source SHA bindings, entity mapping, numeric roles/dtypes and identity conversions passed. No cap loss, policy row filtering, string-to-value coercion or source-to-typed mismatch was found. The bound numeric input is complete; poor compressibility/high entropy and fixed frame cost remain plausible expansion drivers.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 1,
"additional_temporal_coordinate_dtype_counts": {
"int64": 1
},
"additional_temporal_coordinate_sources": [
{
"conversion": "policy_temporal_string_to_int64_us",
"output_dtype": "int64",
"source_column": "start_timestamp",
"source_type": "STRING"
}
],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 2,
"dropped_value_columns": 0,
"eligible_rows": 16537182,
"emitted_rows": 16537182,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 114.0,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 2,
"rows": 16537182,
"series": 145063,
"source_data_same_pass_sha256": "552defb386160443ef2484f705a764082c9666508bdd8a566b14692367743b24",
"source_manifest_sha256": "92c9a8faedc0fa1d6ea5c1363b483e576e73623ce3fffa0f9fdb12fe9ef58100",
"source_rows": 16537182,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "a3f024f36d98062db4d52b6b11e403ca998ee5c1088dc84f0fddadc2cc978b94",
"value_columns": 1,
"value_dtype_counts": {
"float32": 1
},
"value_logical_blocks": 145063,
"value_missing_cells": 0,
"value_valid_cells": 16537182
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 1.289115026071839,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 1.0,
"numeric_pairs_without_overall": 13,
"original_numeric_bytes_max": 198446184,
"original_numeric_bytes_min": 198446184,
"ratio_max": 2.849832743571426,
"ratio_median": 1.18361054501305,
"ratio_min": 1.0243342648503637,
"ratios_gt_1": 59,
"source_profiles": {
"cpp-native166-current-recovery-v3-baseline86-fixed-profiles-20260919-v3": 2,
"cpp-native166-main-458a218f": 54,
"cpp-native166-v9-recovery-baseline86-fixed-profiles-20260919-v3": 3
},
"terminal_not_applicable_pairs": 13,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "proven_prior_input_error_corrected_and_published",
"corrected_input": {
"missing_cells": 18,
"rows": 36,
"series": 1,
"value_dtype_counts": {
"float64": 6
}
},
"dataset_id": "magseven_ml_ready_high_frequency_anomaly",
"finding": "The old float32 conversion changed all 198 non-null values. The corrected 36-row, six-float64 event-anchor input preserves source binary64 bits and 18 nulls; corrected results are published.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 6,
"dropped_value_columns": 0,
"eligible_rows": 36,
"emitted_rows": 36,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 33.0,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 6,
"rows": 36,
"series": 1,
"source_data_same_pass_sha256": "b77c03d8f779175c87ed030f093645f396a86cd87be54f4fcf415a6ada4824f1",
"source_manifest_sha256": "6f5ea21b7922d2fbb198a7db61fa66798fe5450bc2405700cdbbf2b3036f6032",
"source_rows": 36,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "141fac60237fc673c1041022a54cf99cbb74855f668d4becfc9e61e0b48faac5",
"value_columns": 6,
"value_dtype_counts": {
"float32": 6
},
"value_logical_blocks": 6,
"value_missing_cells": 18,
"value_valid_cells": 198
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 3.2762762762762763,
"evaluated_numeric_overall_algorithms": 74,
"fraction_gt_1_among_numeric": 1.0,
"numeric_pairs_without_overall": 0,
"original_numeric_bytes_max": 1584,
"original_numeric_bytes_min": 1584,
"ratio_max": 7.078914141414141,
"ratio_median": 3.1515151515151514,
"ratio_min": 2.5,
"ratios_gt_1": 74,
"source_profiles": {
"cpp-native166-corrected-five-20261012-v1": 74
},
"terminal_not_applicable_pairs": 0,
"terminal_unsupported_pairs": 11
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "bound_source_to_typed_contract_pass_no_processing_error_found",
"dataset_id": "national_illness",
"finding": "Pinned source scans, row/column counts, source SHA bindings, entity mapping, numeric roles/dtypes and identity conversions passed. No cap loss, policy row filtering, string-to-value coercion or source-to-typed mismatch was found. The bound numeric input is complete; poor compressibility/high entropy and fixed frame cost remain plausible expansion drivers.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 7,
"dropped_value_columns": 0,
"eligible_rows": 966,
"emitted_rows": 966,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 966.0,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 7,
"rows": 966,
"series": 1,
"source_data_same_pass_sha256": "f1c0554546620cc39bff5023551ed88c4da60a11640cb2be3fefa3d050a5e798",
"source_manifest_sha256": "86f1e69bc59a4c80f528ee06d1e5b1f215d1baef87a50b91b9aa7098290d2b2f",
"source_rows": 966,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "0956823b7e985e1a9acf508330f03701a3758d02f46b8b82b1c41b24e7e2a9e1",
"value_columns": 7,
"value_dtype_counts": {
"float32": 7
},
"value_logical_blocks": 7,
"value_missing_cells": 0,
"value_valid_cells": 6762
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 1.0598897628321777,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 0.6271186440677966,
"numeric_pairs_without_overall": 0,
"original_numeric_bytes_max": 27048,
"original_numeric_bytes_min": 27048,
"ratio_max": 2.150769003253475,
"ratio_median": 1.0578231292517006,
"ratio_min": 0.8122966577935522,
"ratios_gt_1": 37,
"source_profiles": {
"cpp-native166-main-458a218f": 58,
"cpp-native166-v9-recovery-baseline86-fixed-profiles-20260919-v3": 1
},
"terminal_not_applicable_pairs": 26,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "bound_source_to_typed_contract_pass_no_processing_error_found",
"dataset_id": "ne_china_wind",
"finding": "Pinned source scans, row/column counts, source SHA bindings, entity mapping, numeric roles/dtypes and identity conversions passed. No cap loss, policy row filtering, string-to-value coercion or source-to-typed mismatch was found. The bound numeric input is complete; poor compressibility/high entropy and fixed frame cost remain plausible expansion drivers.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 1,
"dropped_value_columns": 0,
"eligible_rows": 35056,
"emitted_rows": 35056,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 8764.0,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 1,
"rows": 35056,
"series": 4,
"source_data_same_pass_sha256": "0f6ac7fe3e5d4f61e7d23b58b293c08c1153d67c15be0cd926840ddc24ec3b1d",
"source_manifest_sha256": "56c797eac7cbeaa24673b38e30360613aee02705e0f31f82cc087762f1b1bdd5",
"source_rows": 35056,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "d3b8b41efc752d0dfe844bffcf42567e3700deb7b058385e1b5dab513a2b8e26",
"value_columns": 1,
"value_dtype_counts": {
"float32": 1
},
"value_logical_blocks": 4,
"value_missing_cells": 0,
"value_valid_cells": 35056
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 1.025969224059906,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 0.6101694915254238,
"numeric_pairs_without_overall": 0,
"original_numeric_bytes_max": 140224,
"original_numeric_bytes_min": 140224,
"ratio_max": 2.0408061387494296,
"ratio_median": 1.0474383842994066,
"ratio_min": 0.8697512551346417,
"ratios_gt_1": 36,
"source_profiles": {
"cpp-native166-current-recovery-v3-baseline86-fixed-profiles-20260919-v3": 1,
"cpp-native166-main-458a218f": 58
},
"terminal_not_applicable_pairs": 26,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "bound_source_to_typed_contract_pass_no_processing_error_found",
"dataset_id": "niederschlag_station_4091_bavaria_germany",
"finding": "Pinned source scans, row/column counts, source SHA bindings, entity mapping, numeric roles/dtypes and identity conversions passed. No cap loss, policy row filtering, string-to-value coercion or source-to-typed mismatch was found. The mean valid run is short, so per-frame overhead is a plausible expansion driver.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 1,
"dropped_value_columns": 0,
"eligible_rows": 60,
"emitted_rows": 60,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 60.0,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 1,
"rows": 60,
"series": 1,
"source_data_same_pass_sha256": "c49f119797578ae4e1fa9220be1edeaaa574f93791a501d07c42e55d76563591",
"source_manifest_sha256": "4c3a8c25af6b8d323c1d3a154c3b4608467806b88e08f2be200007f296a6e022",
"source_rows": 60,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "dc85be141a65df6aceac18b72dcd960f5f81e1118a5432e00604da6e7eb27131",
"value_columns": 1,
"value_dtype_counts": {
"float64": 1
},
"value_logical_blocks": 1,
"value_missing_cells": 0,
"value_valid_cells": 60
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 1.9813344594594595,
"evaluated_numeric_overall_algorithms": 74,
"fraction_gt_1_among_numeric": 1.0,
"numeric_pairs_without_overall": 0,
"original_numeric_bytes_max": 480,
"original_numeric_bytes_min": 480,
"ratio_max": 4.047916666666667,
"ratio_median": 1.8760416666666666,
"ratio_min": 1.5479166666666666,
"ratios_gt_1": 74,
"source_profiles": {
"cpp-native166-main-458a218f": 73,
"cpp-native166-v9-recovery-baseline86-fixed-profiles-20260919-v3": 1
},
"terminal_not_applicable_pairs": 11,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "bound_source_to_typed_contract_pass_no_processing_error_found",
"dataset_id": "nn5_weekly",
"finding": "Pinned source scans, row/column counts, source SHA bindings, entity mapping, numeric roles/dtypes and identity conversions passed. No cap loss, policy row filtering, string-to-value coercion or source-to-typed mismatch was found. The bound numeric input is complete; poor compressibility/high entropy and fixed frame cost remain plausible expansion drivers.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 1,
"additional_temporal_coordinate_dtype_counts": {
"int64": 1
},
"additional_temporal_coordinate_sources": [
{
"conversion": "policy_temporal_string_to_int64_us",
"output_dtype": "int64",
"source_column": "start_timestamp",
"source_type": "STRING"
}
],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 2,
"dropped_value_columns": 0,
"eligible_rows": 12543,
"emitted_rows": 12543,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 113.0,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 2,
"rows": 12543,
"series": 111,
"source_data_same_pass_sha256": "75c5a26d45529c15acb0b9ae4f873766e3d71e592f0e88759a28559faf66aaf0",
"source_manifest_sha256": "1eec6f7e8ab4c35ed7298bea1e351f0e2a55de0dcfda6ff8de91eccb6b6928f6",
"source_rows": 12543,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "7fbd87675bfd087093114168c8f972f6217790061438aa4db98cf0357a4d98ca",
"value_columns": 1,
"value_dtype_counts": {
"float32": 1
},
"value_logical_blocks": 111,
"value_missing_cells": 0,
"value_valid_cells": 12543
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 1.3745019956209397,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 1.0,
"numeric_pairs_without_overall": 13,
"original_numeric_bytes_max": 150516,
"original_numeric_bytes_min": 150516,
"ratio_max": 2.963425815195727,
"ratio_median": 1.2494751388556697,
"ratio_min": 1.1501700815860108,
"ratios_gt_1": 59,
"source_profiles": {
"cpp-native166-main-458a218f": 58,
"cpp-native166-v9-recovery-baseline86-fixed-profiles-20260919-v3": 1
},
"terminal_not_applicable_pairs": 13,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "bound_source_to_typed_contract_pass_no_processing_error_found",
"dataset_id": "online_retail_2_uci",
"finding": "Pinned source scans, row/column counts, source SHA bindings, entity mapping, numeric roles/dtypes and identity conversions passed. No cap loss, policy row filtering, string-to-value coercion or source-to-typed mismatch was found. The bound numeric input is complete; poor compressibility/high entropy and fixed frame cost remain plausible expansion drivers.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 1,
"dropped_value_columns": 0,
"eligible_rows": 739,
"emitted_rows": 739,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 739.0,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 1,
"rows": 739,
"series": 1,
"source_data_same_pass_sha256": "aac764844094ee9e6688a1e4454e0f9a4a0207a51e43fcde987bcce5384579c0",
"source_manifest_sha256": "600bf2f6ecda750ae6491f8d8d426a7515c4d7a65b27e76f18500ab3ef023c9a",
"source_rows": 739,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "17c99514b26eb9e5016f2b9b69ace51f3628bb010dce6ac561be7bb7193a25ac",
"value_columns": 1,
"value_dtype_counts": {
"float32": 1
},
"value_logical_blocks": 1,
"value_missing_cells": 0,
"value_valid_cells": 739
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 1.1380300910529575,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 0.8983050847457628,
"numeric_pairs_without_overall": 0,
"original_numeric_bytes_max": 2956,
"original_numeric_bytes_min": 2956,
"ratio_max": 1.9370771312584574,
"ratio_median": 1.1288903924221922,
"ratio_min": 0.9783491204330176,
"ratios_gt_1": 53,
"source_profiles": {
"cpp-native166-main-458a218f": 59
},
"terminal_not_applicable_pairs": 26,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "bound_source_to_typed_contract_pass_no_processing_error_found",
"dataset_id": "port_activity",
"finding": "Pinned source scans, row/column counts, source SHA bindings, entity mapping, numeric roles/dtypes and identity conversions passed. No cap loss, policy row filtering, string-to-value coercion or source-to-typed mismatch was found. The bound numeric input is complete; poor compressibility/high entropy and fixed frame cost remain plausible expansion drivers.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 1,
"dropped_value_columns": 0,
"eligible_rows": 481338,
"emitted_rows": 481338,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 1215.5,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 1,
"rows": 481338,
"series": 396,
"source_data_same_pass_sha256": "4cc1c94120475f61579af54d450c9a77f54e544c8c8ff9a09c3da7c42e29aba6",
"source_manifest_sha256": "5105b4dd6b35c0724f0fee6b3f3833f885501bcde7845d21a33d925086d13c38",
"source_rows": 481338,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "f11c5a5304fc8f284b9fb3a2ceeae0db07873d34df5ead80492e41ddc5fc4c29",
"value_columns": 1,
"value_dtype_counts": {
"float32": 1
},
"value_logical_blocks": 396,
"value_missing_cells": 0,
"value_valid_cells": 481338
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 1.0702334174984407,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 0.7627118644067796,
"numeric_pairs_without_overall": 0,
"original_numeric_bytes_max": 1925352,
"original_numeric_bytes_min": 1925352,
"ratio_max": 1.9457034350082478,
"ratio_median": 1.074231621023065,
"ratio_min": 0.9581390831390831,
"ratios_gt_1": 45,
"source_profiles": {
"cpp-native166-current-recovery-v3-baseline86-fixed-profiles-20260919-v3": 1,
"cpp-native166-main-458a218f": 56,
"cpp-native166-v9-recovery-baseline86-fixed-profiles-20260919-v3": 2
},
"terminal_not_applicable_pairs": 26,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "bound_source_to_typed_contract_pass_no_processing_error_found",
"dataset_id": "scaphandre_cpu_usage",
"finding": "Pinned source scans, row/column counts, source SHA bindings, entity mapping, numeric roles/dtypes and identity conversions passed. No cap loss, policy row filtering, string-to-value coercion or source-to-typed mismatch was found. The bound numeric input is complete; poor compressibility/high entropy and fixed frame cost remain plausible expansion drivers.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 1,
"dropped_value_columns": 0,
"eligible_rows": 300,
"emitted_rows": 300,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 300.0,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 1,
"rows": 300,
"series": 1,
"source_data_same_pass_sha256": "c085cef26cd43e8f09471be7a0eb5cbf4683a1fe1948849698cdf3c38e9fd2dd",
"source_manifest_sha256": "05f1928ac0a1178f50284d6f018ff1e2b21e250988a225329d4746734a9e3992",
"source_rows": 300,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "80b2dd706ed7ca39228a321bf54a2ab0ecf1eb0d2270d9fbf009646696dced0d",
"value_columns": 1,
"value_dtype_counts": {
"float32": 1
},
"value_logical_blocks": 1,
"value_missing_cells": 0,
"value_valid_cells": 300
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 1.2444915254237288,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 0.7966101694915254,
"numeric_pairs_without_overall": 0,
"original_numeric_bytes_max": 1200,
"original_numeric_bytes_min": 1200,
"ratio_max": 2.4825,
"ratio_median": 1.23,
"ratio_min": 0.9408333333333333,
"ratios_gt_1": 47,
"source_profiles": {
"cpp-native166-main-458a218f": 58,
"cpp-native166-v9-recovery-baseline86-fixed-profiles-20260919-v3": 1
},
"terminal_not_applicable_pairs": 26,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "bound_source_to_typed_contract_pass_no_processing_error_found",
"dataset_id": "solar_weekly",
"finding": "Pinned source scans, row/column counts, source SHA bindings, entity mapping, numeric roles/dtypes and identity conversions passed. No cap loss, policy row filtering, string-to-value coercion or source-to-typed mismatch was found. The mean valid run is short, so per-frame overhead is a plausible expansion driver.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 1,
"additional_temporal_coordinate_dtype_counts": {
"int64": 1
},
"additional_temporal_coordinate_sources": [
{
"conversion": "policy_temporal_string_to_int64_us",
"output_dtype": "int64",
"source_column": "start_timestamp",
"source_type": "STRING"
}
],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 2,
"dropped_value_columns": 0,
"eligible_rows": 7124,
"emitted_rows": 7124,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 52.0,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 2,
"rows": 7124,
"series": 137,
"source_data_same_pass_sha256": "d8be48e20c4e6d0ba014d475b040d6befb354017355ec61d380f1f799deb1186",
"source_manifest_sha256": "73ad2cdb2aff1f8ead3eaace5bbcf5a2f75bb38f32903ee7311bb67781a6b99d",
"source_rows": 7124,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "cac9980160d9b29b606ba108e756240a6d512ebd9d8b115e4df68240f1e9e87a",
"value_columns": 1,
"value_dtype_counts": {
"float32": 1
},
"value_logical_blocks": 137,
"value_missing_cells": 0,
"value_valid_cells": 7124
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 2.4873763628634964,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 1.0,
"numeric_pairs_without_overall": 13,
"original_numeric_bytes_max": 85488,
"original_numeric_bytes_min": 85488,
"ratio_max": 5.783057271195958,
"ratio_median": 2.2968486805165638,
"ratio_min": 2.121525828186412,
"ratios_gt_1": 59,
"source_profiles": {
"cpp-native166-main-458a218f": 58,
"cpp-native166-v9-recovery-baseline86-fixed-profiles-20260919-v3": 1
},
"terminal_not_applicable_pairs": 13,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "source_to_typed_pass_duplicate_scientific_workload_identity",
"dataset_id": "timeseries-finance-ETF",
"finding": "The two repository IDs have byte-identical source CSV, typed value/timestamp/entity payloads and identical 85-method outcome vectors. This is a cross-dataset weighting duplicate, not a numeric conversion defect. final160 keeps both frozen IDs; identity-aware summaries must disclose or de-duplicate the scientific workload without rewriting either input.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 2,
"dropped_value_columns": 0,
"eligible_rows": 2406262,
"emitted_rows": 2406262,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 57.49729988052569,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 2,
"rows": 2406262,
"series": 41850,
"source_data_same_pass_sha256": "0dd81f32d9d6a38687997694722ecae281e00fd2a8623abb513ed3dc170fc064",
"source_manifest_sha256": "710137597745f1c427c3efed4375b505367aa55a61f4f7e672cff71f26d70a78",
"source_rows": 2406262,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "e61a1c59855ddb5847b6ec292d1c9c7bec6163bc2470ea976f17bf9d3df437bc",
"value_columns": 2,
"value_dtype_counts": {
"float32": 1,
"int64": 1
},
"value_logical_blocks": 83700,
"value_missing_cells": 0,
"value_valid_cells": 4812524
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 2.4476373737605828,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 1.0,
"numeric_pairs_without_overall": 13,
"original_numeric_bytes_max": 28875144,
"original_numeric_bytes_min": 28875144,
"ratio_max": 5.137833494440755,
"ratio_median": 2.3300417133850484,
"ratio_min": 1.9884227417186213,
"ratios_gt_1": 59,
"source_profiles": {
"cpp-native166-current-recovery-v3-baseline86-fixed-profiles-20260919-v3": 2,
"cpp-native166-main-458a218f": 54,
"cpp-native166-v9-recovery-baseline86-fixed-profiles-20260919-v3": 3
},
"terminal_not_applicable_pairs": 13,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none_for_format; aggregation/scope treatment required"
}
},
{
"classification": "source_to_typed_pass_duplicate_scientific_workload_identity",
"dataset_id": "timeseries_finance_etf_missing",
"finding": "The two repository IDs have byte-identical source CSV, typed value/timestamp/entity payloads and identical 85-method outcome vectors. This is a cross-dataset weighting duplicate, not a numeric conversion defect. final160 keeps both frozen IDs; identity-aware summaries must disclose or de-duplicate the scientific workload without rewriting either input.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 2,
"dropped_value_columns": 0,
"eligible_rows": 2406262,
"emitted_rows": 2406262,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 57.49729988052569,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 2,
"rows": 2406262,
"series": 41850,
"source_data_same_pass_sha256": "0dd81f32d9d6a38687997694722ecae281e00fd2a8623abb513ed3dc170fc064",
"source_manifest_sha256": "db845b445c126c4bdc74882c88d5a93a8aa2d18205f2e9bec76d5a8d1bad7b66",
"source_rows": 2406262,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "02a97e0106ab3fc55ee0b384a6f5594c8097d5c61c531dc5d2258a5c74667503",
"value_columns": 2,
"value_dtype_counts": {
"float32": 1,
"int64": 1
},
"value_logical_blocks": 83700,
"value_missing_cells": 0,
"value_valid_cells": 4812524
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 2.4476373737605828,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 1.0,
"numeric_pairs_without_overall": 13,
"original_numeric_bytes_max": 28875144,
"original_numeric_bytes_min": 28875144,
"ratio_max": 5.137833494440755,
"ratio_median": 2.3300417133850484,
"ratio_min": 1.9884227417186213,
"ratios_gt_1": 59,
"source_profiles": {
"cpp-native166-current-recovery-v3-baseline86-fixed-profiles-20260919-v3": 2,
"cpp-native166-main-458a218f": 54,
"cpp-native166-v9-recovery-baseline86-fixed-profiles-20260919-v3": 3
},
"terminal_not_applicable_pairs": 13,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none_for_format; aggregation/scope treatment required"
}
},
{
"classification": "bound_source_to_typed_contract_pass_no_processing_error_found",
"dataset_id": "tourism_quarterly",
"finding": "Pinned source scans, row/column counts, source SHA bindings, entity mapping, numeric roles/dtypes and identity conversions passed. No cap loss, policy row filtering, string-to-value coercion or source-to-typed mismatch was found. The bound numeric input is complete; poor compressibility/high entropy and fixed frame cost remain plausible expansion drivers.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 1,
"additional_temporal_coordinate_dtype_counts": {
"int64": 1
},
"additional_temporal_coordinate_sources": [
{
"conversion": "policy_temporal_string_to_int64_us",
"output_dtype": "int64",
"source_column": "start_timestamp",
"source_type": "STRING"
}
],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 2,
"dropped_value_columns": 0,
"eligible_rows": 42544,
"emitted_rows": 42544,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 99.63466042154566,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 2,
"rows": 42544,
"series": 427,
"source_data_same_pass_sha256": "031ff8e7587aca03b876ab29e67454c98926c699f900bed5f5586d0129cc467c",
"source_manifest_sha256": "dba3efa9f576cf5fda520428bad0f392ebb29a3e67f9f3768c8e1ded38c41eb2",
"source_rows": 42544,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "7546af1d7f49ee5480d791cb942351a4a50ac6ac644dd770a1374afd6aa42cbf",
"value_columns": 1,
"value_dtype_counts": {
"float32": 1
},
"value_logical_blocks": 427,
"value_missing_cells": 0,
"value_valid_cells": 42544
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 1.455532743236381,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 1.0,
"numeric_pairs_without_overall": 13,
"original_numeric_bytes_max": 510528,
"original_numeric_bytes_min": 510528,
"ratio_max": 3.2198880374827628,
"ratio_median": 1.339613106430989,
"ratio_min": 1.1717026294346244,
"ratios_gt_1": 59,
"source_profiles": {
"cpp-native166-current-recovery-v3-baseline86-fixed-profiles-20260919-v3": 1,
"cpp-native166-main-458a218f": 56,
"cpp-native166-v9-recovery-baseline86-fixed-profiles-20260919-v3": 2
},
"terminal_not_applicable_pairs": 13,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "bound_source_to_typed_contract_pass_no_processing_error_found",
"dataset_id": "tourism_yearly",
"finding": "Pinned source scans, row/column counts, source SHA bindings, entity mapping, numeric roles/dtypes and identity conversions passed. No cap loss, policy row filtering, string-to-value coercion or source-to-typed mismatch was found. The mean valid run is short, so per-frame overhead is a plausible expansion driver.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 1,
"additional_temporal_coordinate_dtype_counts": {
"int64": 1
},
"additional_temporal_coordinate_sources": [
{
"conversion": "policy_temporal_string_to_int64_us",
"output_dtype": "int64",
"source_column": "start_timestamp",
"source_type": "STRING"
}
],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 2,
"dropped_value_columns": 0,
"eligible_rows": 12757,
"emitted_rows": 12757,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 24.627413127413128,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 2,
"rows": 12757,
"series": 518,
"source_data_same_pass_sha256": "9acc955930897335c91d6fcc9145f1dd40371bfa2b996a579445539056ed8fc5",
"source_manifest_sha256": "b6726bd86828cab0a6e3ac05d751745e8d45b0edfc893002681a480b061c2ded",
"source_rows": 12757,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "8a9f17a8b9437b4c186ddb3a8355c76f330ed2c451385cf00d4364fd9199d55d",
"value_columns": 1,
"value_dtype_counts": {
"float32": 1
},
"value_logical_blocks": 518,
"value_missing_cells": 0,
"value_valid_cells": 12757
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 4.763674668034255,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 1.0,
"numeric_pairs_without_overall": 13,
"original_numeric_bytes_max": 153084,
"original_numeric_bytes_min": 153084,
"ratio_max": 11.628628726712131,
"ratio_median": 4.445030179509289,
"ratio_min": 4.052533249719109,
"ratios_gt_1": 59,
"source_profiles": {
"cpp-native166-main-458a218f": 58,
"cpp-native166-v9-recovery-baseline86-fixed-profiles-20260919-v3": 1
},
"terminal_not_applicable_pairs": 13,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "bound_source_to_typed_contract_pass_no_processing_error_found",
"dataset_id": "traffic_weekly",
"finding": "Pinned source scans, row/column counts, source SHA bindings, entity mapping, numeric roles/dtypes and identity conversions passed. No cap loss, policy row filtering, string-to-value coercion or source-to-typed mismatch was found. The bound numeric input is complete; poor compressibility/high entropy and fixed frame cost remain plausible expansion drivers.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 1,
"additional_temporal_coordinate_dtype_counts": {
"int64": 1
},
"additional_temporal_coordinate_sources": [
{
"conversion": "policy_temporal_string_to_int64_us",
"output_dtype": "int64",
"source_column": "start_timestamp",
"source_type": "STRING"
}
],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 2,
"dropped_value_columns": 0,
"eligible_rows": 89648,
"emitted_rows": 89648,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 104.0,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 2,
"rows": 89648,
"series": 862,
"source_data_same_pass_sha256": "ab045b78fff8b4c9ef188d5369cd1d48470ee964c62828d7248f167c26850289",
"source_manifest_sha256": "2494ba5c29b912148546f2f0fb6568fffac8cc7e8395d49ab44fc56413b4a55c",
"source_rows": 89648,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "9ba985cbc9ca1ead89e8c0ee0a533bd8517c596d0a872b467b3990f73a281440",
"value_columns": 1,
"value_dtype_counts": {
"float32": 1
},
"value_logical_blocks": 862,
"value_missing_cells": 0,
"value_valid_cells": 89648
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 1.4478755611400673,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 1.0,
"numeric_pairs_without_overall": 13,
"original_numeric_bytes_max": 1075776,
"original_numeric_bytes_min": 1075776,
"ratio_max": 3.1645054360759115,
"ratio_median": 1.315588933012077,
"ratio_min": 1.2141886415015766,
"ratios_gt_1": 59,
"source_profiles": {
"cpp-native166-current-recovery-v3-baseline86-fixed-profiles-20260919-v3": 2,
"cpp-native166-main-458a218f": 55,
"cpp-native166-v9-recovery-baseline86-fixed-profiles-20260919-v3": 2
},
"terminal_not_applicable_pairs": 13,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "source_to_typed_semantics_audited_no_processing_error",
"dataset_id": "traqq_weekly_activity",
"finding": "All 328 rows and 67 user entities were checked; four int64 and one float64 value columns match source semantics. Names/times remain metadata. No processing error was found.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 5,
"dropped_value_columns": 0,
"eligible_rows": 328,
"emitted_rows": 328,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 4.895522388059701,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 5,
"rows": 328,
"series": 67,
"source_data_same_pass_sha256": "30ce5d55178f3594d476bad8538dcbb3b6dc09f5fa617514bead1f079f75b70b",
"source_manifest_sha256": "3c9040cd3b96246f5f7004250184c00da7382df6b9879bfb3fc03f30d7fb0430",
"source_rows": 328,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "7e9b85464124cdecd8b19b0a7c6fe59632b6856e8dd3ea340add0fb9794ba1cd",
"value_columns": 5,
"value_dtype_counts": {
"float64": 1,
"int64": 4
},
"value_logical_blocks": 335,
"value_missing_cells": 0,
"value_valid_cells": 1640
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 16.57124951606659,
"evaluated_numeric_overall_algorithms": 63,
"fraction_gt_1_among_numeric": 1.0,
"numeric_pairs_without_overall": 20,
"original_numeric_bytes_max": 13120,
"original_numeric_bytes_min": 13120,
"ratio_max": 41.97743902439024,
"ratio_median": 15.668978658536586,
"ratio_min": 14.215015243902439,
"ratios_gt_1": 63,
"source_profiles": {
"cpp-native166-corrected-five-20261012-v1": 63
},
"terminal_not_applicable_pairs": 0,
"terminal_unsupported_pairs": 2
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "proven_prior_input_error_corrected_and_published",
"corrected_input": {
"rows": 13386,
"series": 2347,
"value_dtype_counts": {
"float64": 7,
"int64": 1
}
},
"dataset_id": "trending_stocks_yahoo_finance",
"finding": "Old Yahoo input was superseded: 4,249 shifted rows were quarantined and last-valid-per(symbol,date) retained 13,386 rows/2,347 entities; the corrected campaign is the published source for the ratios shown here.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 8,
"dropped_value_columns": 0,
"eligible_rows": 16376,
"emitted_rows": 16376,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 4.357670706473544,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 8,
"rows": 16376,
"series": 3383,
"source_data_same_pass_sha256": "0f5487db91a24adc3c2a0bc1bbb0071edf84903c368232492cec99a214665101",
"source_manifest_sha256": "d46b6c688d4982548a328b7e3e4112bc5cc0e86b4603cc1740c8291b20a2a6c0",
"source_rows": 16376,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "8ab43fb4b18d1c2d75b0046ac19faf81209a84e46c848d46b1619db526097633",
"value_columns": 8,
"value_dtype_counts": {
"float32": 7,
"int64": 1
},
"value_logical_blocks": 27064,
"value_missing_cells": 13072,
"value_valid_cells": 117936
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 15.21540443501704,
"evaluated_numeric_overall_algorithms": 63,
"fraction_gt_1_among_numeric": 1.0,
"numeric_pairs_without_overall": 20,
"original_numeric_bytes_max": 810336,
"original_numeric_bytes_min": 810336,
"ratio_max": 37.01849109505193,
"ratio_median": 14.432312028590609,
"ratio_min": 13.22497457844647,
"ratios_gt_1": 63,
"source_profiles": {
"cpp-native166-corrected-five-20261012-v1": 63
},
"terminal_not_applicable_pairs": 0,
"terminal_unsupported_pairs": 2
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "bound_source_to_typed_contract_pass_no_processing_error_found",
"dataset_id": "uncertainty_1m",
"finding": "Pinned source scans, row/column counts, source SHA bindings, entity mapping, numeric roles/dtypes and identity conversions passed. No cap loss, policy row filtering, string-to-value coercion or source-to-typed mismatch was found. The bound numeric input is complete; poor compressibility/high entropy and fixed frame cost remain plausible expansion drivers.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 1,
"dropped_value_columns": 0,
"eligible_rows": 2340,
"emitted_rows": 2340,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 780.0,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 1,
"rows": 2340,
"series": 3,
"source_data_same_pass_sha256": "57f2fc39dad8c680942fdc91fc196ae28bbc2f56b4178f3362e875915f1a67e7",
"source_manifest_sha256": "1cdc976e13ced8ff92bcc64c97c9d3f307950660b6948f15798b9544cbbac5f5",
"source_rows": 2340,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "88451deda3b404f8946c888bfa0612d17d63dfd344093f5b1cb6aab7cb64c622",
"value_columns": 1,
"value_dtype_counts": {
"float32": 1
},
"value_logical_blocks": 3,
"value_missing_cells": 0,
"value_valid_cells": 2340
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 1.1871613791105315,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 0.9152542372881356,
"numeric_pairs_without_overall": 0,
"original_numeric_bytes_max": 9360,
"original_numeric_bytes_min": 9360,
"ratio_max": 2.2131410256410255,
"ratio_median": 1.215491452991453,
"ratio_min": 0.9741452991452991,
"ratios_gt_1": 54,
"source_profiles": {
"cpp-native166-main-458a218f": 59
},
"terminal_not_applicable_pairs": 26,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "bound_source_to_typed_contract_pass_no_processing_error_found",
"dataset_id": "us_labor",
"finding": "Pinned source scans, row/column counts, source SHA bindings, entity mapping, numeric roles/dtypes and identity conversions passed. No cap loss, policy row filtering, string-to-value coercion or source-to-typed mismatch was found. The bound numeric input is complete; poor compressibility/high entropy and fixed frame cost remain plausible expansion drivers.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 1,
"dropped_value_columns": 0,
"eligible_rows": 5320,
"emitted_rows": 5320,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 380.0,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 1,
"rows": 5320,
"series": 14,
"source_data_same_pass_sha256": "25dce965f3cc95a7016ef2b2e5f90fdac2c7c1ba74415bdcc4ab19ea85dbecac",
"source_manifest_sha256": "7235d46e47723032002a06801d03a6ecd36357a6e220e55d4eb5c441c16a7017",
"source_rows": 5320,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "c6afdea55892ea1d555b5b854547cd7ef0748bed4f8fa4d551410ea013623866",
"value_columns": 1,
"value_dtype_counts": {
"float32": 1
},
"value_logical_blocks": 14,
"value_missing_cells": 0,
"value_valid_cells": 5320
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 1.123465974257678,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 0.6779661016949152,
"numeric_pairs_without_overall": 0,
"original_numeric_bytes_max": 21280,
"original_numeric_bytes_min": 21280,
"ratio_max": 2.2523496240601504,
"ratio_median": 1.13125,
"ratio_min": 0.8195958646616541,
"ratios_gt_1": 40,
"source_profiles": {
"cpp-native166-current-recovery-v3-baseline86-fixed-profiles-20260919-v3": 1,
"cpp-native166-main-458a218f": 56,
"cpp-native166-v9-recovery-baseline86-fixed-profiles-20260919-v3": 2
},
"terminal_not_applicable_pairs": 26,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "source_to_typed_semantics_audited_no_processing_error",
"dataset_id": "us_stock_financial_ratios",
"finding": "All 2,364 rows, 237 tickers, 39 float64 value columns and 3,881 source nulls match the pinned Parquet. The prior '44 columns' wording counted five metadata columns; the numeric input itself is correct.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 39,
"dropped_value_columns": 0,
"eligible_rows": 2364,
"emitted_rows": 2364,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 9.554798225684301,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 39,
"rows": 2364,
"series": 237,
"source_data_same_pass_sha256": "79a63a352a55c112687dea82899180815bdaddae7092ae66ef809e65d1999b13",
"source_manifest_sha256": "44895c6c06cce749c5326cb7becfa1a81ae9f4e324d2aa54ee10ee204e9846c5",
"source_rows": 2364,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "8d2625899f1ce97ae2a1d9c4c2b82132948a31bd7803bca2818d250483812c04",
"value_columns": 39,
"value_dtype_counts": {
"float64": 39
},
"value_logical_blocks": 9243,
"value_missing_cells": 3881,
"value_valid_cells": 88315
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 9.101737981824886,
"evaluated_numeric_overall_algorithms": 74,
"fraction_gt_1_among_numeric": 1.0,
"numeric_pairs_without_overall": 0,
"original_numeric_bytes_max": 706520,
"original_numeric_bytes_min": 706520,
"ratio_max": 21.7655310536149,
"ratio_median": 8.68543777953915,
"ratio_min": 7.948980920568419,
"ratios_gt_1": 74,
"source_profiles": {
"cpp-native166-corrected-five-20261012-v1": 74
},
"terminal_not_applicable_pairs": 0,
"terminal_unsupported_pairs": 11
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "bound_source_to_typed_contract_pass_no_processing_error_found",
"dataset_id": "vehicle_sales",
"finding": "Pinned source scans, row/column counts, source SHA bindings, entity mapping, numeric roles/dtypes and identity conversions passed. No cap loss, policy row filtering, string-to-value coercion or source-to-typed mismatch was found. The bound numeric input is complete; poor compressibility/high entropy and fixed frame cost remain plausible expansion drivers.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 1,
"dropped_value_columns": 0,
"eligible_rows": 5960,
"emitted_rows": 5960,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 596.0,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 1,
"rows": 5960,
"series": 10,
"source_data_same_pass_sha256": "3c595d7f8c421607370b37ebf9fbcf9d54ad9bacf3587a80d9d93f9cd81414a6",
"source_manifest_sha256": "dcb05ac79c47e09f8aa572b38ff32475d428967b352e5d81c77e5c871c0b3944",
"source_rows": 5960,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "ae52c9fea0c375526337e686d8b8524d4efc418638ce24aa6b4fa86ee803d97a",
"value_columns": 1,
"value_dtype_counts": {
"float32": 1
},
"value_logical_blocks": 10,
"value_missing_cells": 0,
"value_valid_cells": 5960
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 1.1958423387555455,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 0.9322033898305084,
"numeric_pairs_without_overall": 0,
"original_numeric_bytes_max": 23840,
"original_numeric_bytes_min": 23840,
"ratio_max": 2.2654362416107383,
"ratio_median": 1.2232802013422819,
"ratio_min": 0.9415687919463087,
"ratios_gt_1": 55,
"source_profiles": {
"cpp-native166-main-458a218f": 59
},
"terminal_not_applicable_pairs": 26,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "bound_source_to_typed_contract_pass_no_processing_error_found",
"dataset_id": "vehicle_supply",
"finding": "Pinned source scans, row/column counts, source SHA bindings, entity mapping, numeric roles/dtypes and identity conversions passed. No cap loss, policy row filtering, string-to-value coercion or source-to-typed mismatch was found. The bound numeric input is complete; poor compressibility/high entropy and fixed frame cost remain plausible expansion drivers.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 1,
"dropped_value_columns": 0,
"eligible_rows": 2346,
"emitted_rows": 2346,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 391.0,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 1,
"rows": 2346,
"series": 6,
"source_data_same_pass_sha256": "38a763e82f33205aa5bdfa63eab5ddc1205d0005d55117d55c50b9ea96bc238e",
"source_manifest_sha256": "a074eaae81523a3c14758ed6074db784df1a930b45c8dbfae9f45b881917b680",
"source_rows": 2346,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "731e325f9d09841741e48030e4de7c53c60441815093bbaa7db89a89f2af5aa6",
"value_columns": 1,
"value_dtype_counts": {
"float32": 1
},
"value_logical_blocks": 6,
"value_missing_cells": 0,
"value_valid_cells": 2346
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 1.2940327568020575,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 1.0,
"numeric_pairs_without_overall": 0,
"original_numeric_bytes_max": 9384,
"original_numeric_bytes_min": 9384,
"ratio_max": 2.2749360613810743,
"ratio_median": 1.302855924978687,
"ratio_min": 1.008312020460358,
"ratios_gt_1": 59,
"source_profiles": {
"cpp-native166-main-458a218f": 58,
"cpp-native166-v9-recovery-baseline86-fixed-profiles-20260919-v3": 1
},
"terminal_not_applicable_pairs": 26,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "bound_source_to_typed_contract_pass_no_processing_error_found",
"dataset_id": "wui_global",
"finding": "Pinned source scans, row/column counts, source SHA bindings, entity mapping, numeric roles/dtypes and identity conversions passed. No cap loss, policy row filtering, string-to-value coercion or source-to-typed mismatch was found. The bound numeric input is complete; poor compressibility/high entropy and fixed frame cost remain plausible expansion drivers.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 1,
"dropped_value_columns": 0,
"eligible_rows": 4410,
"emitted_rows": 4410,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 288.3333333333333,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 1,
"rows": 4410,
"series": 15,
"source_data_same_pass_sha256": "f11d77711a882163a771cbdbe33a7c8ff06637abd191a2c097a106dad1388e03",
"source_manifest_sha256": "05dc3b1d5c8926408ab90b57525931ef5d68a819fdd00ddc5a37db34031e0bcc",
"source_rows": 4410,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "4adb6ae4dd0204a3a9037e2e422d020b4c06040954753063b05e3c78c33a6c31",
"value_columns": 1,
"value_dtype_counts": {
"float32": 1
},
"value_logical_blocks": 15,
"value_missing_cells": 85,
"value_valid_cells": 4325
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 1.3946115410992457,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 1.0,
"numeric_pairs_without_overall": 0,
"original_numeric_bytes_max": 17300,
"original_numeric_bytes_min": 17300,
"ratio_max": 2.139884393063584,
"ratio_median": 1.337630057803468,
"ratio_min": 1.2102312138728324,
"ratios_gt_1": 59,
"source_profiles": {
"cpp-native166-current-recovery-v3-baseline86-fixed-profiles-20260919-v3": 3,
"cpp-native166-main-458a218f": 56
},
"terminal_not_applicable_pairs": 26,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
},
{
"classification": "bound_source_to_typed_contract_pass_no_processing_error_found",
"dataset_id": "zillow_viewer",
"finding": "Pinned source scans, row/column counts, source SHA bindings, entity mapping, numeric roles/dtypes and identity conversions passed. No cap loss, policy row filtering, string-to-value coercion or source-to-typed mismatch was found. The mean valid run is short, so per-frame overhead is a plausible expansion driver.",
"old_bound_input": {
"additional_temporal_coordinate_columns": 0,
"additional_temporal_coordinate_dtype_counts": {},
"additional_temporal_coordinate_sources": [],
"all_value_columns_numeric": true,
"all_value_conversions_identity": true,
"candidate_value_columns": 44,
"dropped_value_columns": 0,
"eligible_rows": 2878384,
"emitted_rows": 2878384,
"lost_rows_due_to_byte_cap": 0,
"mean_valid_values_per_value_block": 27.054357432057493,
"ordinary_strings_emitted_to_value_csv": false,
"policy_filtered_rows": 0,
"retained_value_columns": 44,
"rows": 2878384,
"series": 48619,
"source_data_same_pass_sha256": "420b4c0a3684d29a21f0d6368b1f825e1a350b190bc03c36d447810837a15ad4",
"source_manifest_sha256": "b1bff7c2af1c9bcb08ae8fc2ea86b3ca8121d1fd9f06d4e251187bf599c35c58",
"source_rows": 2878384,
"temporal_role_boundary": "These columns are explicitly typed as additional_temporal_coordinate, not value. Existing Overall results include them in original numeric bytes; physical Time remains the row coordinate and is not a value column.",
"typed_manifest_sha256": "1f60337db1ce69b7562ce2d20908e7158455f36481d4bb8cc3ffc130be997494",
"value_columns": 44,
"value_dtype_counts": {
"float32": 32,
"float64": 5,
"int64": 7
},
"value_logical_blocks": 291938,
"value_missing_cells": 7988456,
"value_valid_cells": 7898195
},
"ratio_evidence": {
"cross_algorithm_pooled_ratio": 4.619698845707705,
"evaluated_numeric_overall_algorithms": 59,
"fraction_gt_1_among_numeric": 1.0,
"numeric_pairs_without_overall": 25,
"original_numeric_bytes_max": 44014760,
"original_numeric_bytes_min": 44014760,
"ratio_max": 10.150744000421676,
"ratio_median": 4.3912506395581845,
"ratio_min": 4.061311137445712,
"ratios_gt_1": 59,
"source_profiles": {
"cpp-native166-current-recovery-v3-baseline86-fixed-profiles-20260919-v3": 4,
"cpp-native166-main-458a218f": 51,
"cpp-native192-lzg-level5-fastfalse-lzg-level5-fast0-ngf1-empty-fixed-20261010-v2": 1,
"cpp-native192-next5-baseline86-fixed-profiles-20260919-v3": 3
},
"terminal_not_applicable_pairs": 1,
"terminal_unsupported_pairs": 0
},
"result_action": {
"dataset_id_remains_in_final160": true,
"quarantine_current_numeric_results": false,
"rerun_requirement": "none"
}
}
],
"definition": {
"algorithms": "85 active canonical C++ families only; legacy-only BSS+LZ4 and Sub-column excluded",
"denominator": "numeric Overall results only",
"flag": "count(compression_ratio > 1) / numeric Overall results > 0.5",
"ratio": "published complete compressed frame bytes / published original numeric bytes; not inverted or clipped",
"scope": "Overall"
},
"generated_at": "2026-10-13T11:26:13.252620+00:00",
"schema": "final160-majority-expansion-format-audit-v1",
"scope": {
"active_algorithm_count": 85,
"final160_dataset_count": 160,
"flagged_dataset_count": 46,
"legacy_extras_excluded": [
"BSS+LZ4",
"Sub-column"
],
"strict_majority_threshold": "> 50% of numeric Overall algorithms"
},
"source_receipts": [
{
"bytes": 5591,
"name": "final160_scope",
"path": "/Users/xiaojinzhao/Documents/GitHub/web_compression/analysis_outputs/final160_scope_20261013_v1/FINAL160_SCOPE.json",
"sha256": "92a995e4278971077fe60dabd913e26e1afdccaeca1ec6181ae1de3f50929889"
},
{
"bytes": 458442,
"name": "ratio_audit",
"path": "/Users/xiaojinzhao/Documents/GitHub/web_compression/analysis_outputs/final160_dataset_format_audit_20261013_v1/RATIO_AUDIT.json",
"sha256": "3cdbd0aa33045228ef21c5faa085be9b3867d0286270f6beed35529479d44599"
},
{
"bytes": 572665,
"name": "remote_typed_metadata",
"path": "/Users/xiaojinzhao/Documents/GitHub/web_compression/analysis_outputs/final160_dataset_format_audit_20261013_v1/REMOTE_TYPED_METADATA.json",
"sha256": "9c52c302dbaaca8faeb6eb1e51b2bb0c7cd9ee92e3819e2e7a6fd2489d547035"
},
{
"bytes": 4297,
"name": "six_dataset_corrections",
"path": "/Users/xiaojinzhao/Documents/GitHub/web_compression/analysis_outputs/six_dataset_numeric_repair_20261012_v1/INPUT_CORRECTION_STATUS_V2.json",
"sha256": "60ec935bd8fe9e2557cf6e499730e9b6847c00303bf980aeab18b32313afcfb8"
},
{
"bytes": 8026,
"name": "fresh50k_frozen_ready",
"path": "/Users/xiaojinzhao/Documents/GitHub/web_compression/analysis_outputs/six_dataset_numeric_repair_20261012_v1/fresh50k/typed_ready_v2/FROZEN_READY.json",
"sha256": "1b71521fbd61e9d9ffe737d57b6ac73077b7e8e1f77661eacac45e8a4abb1dcd"
},
{
"bytes": 41665,
"name": "etf_identity",
"path": "/Users/xiaojinzhao/Documents/GitHub/web_compression/analysis_outputs/table5_dataset_expansion_audit_20261012_v1/ETF_IDENTITY_CHECK.json",
"sha256": "8fdbc49558eee006082d729213c21981e38248ff5d736e4b18e850f8b840305f"
},
{
"bytes": 1932,
"name": "yahoo_github_validation",
"path": "/Users/xiaojinzhao/Documents/GitHub/web_compression/analysis_outputs/six_dataset_numeric_repair_20261012_v1/yahoo_github/VALIDATION_V2.json",
"sha256": "309e1930698aaed5086167072b9560eb7b0ba0be06cd136fb4a96a4a53ee037f"
},
{
"bytes": 6738,
"name": "small3_audit",
"path": "/Users/xiaojinzhao/Documents/GitHub/web_compression/analysis_outputs/six_dataset_numeric_repair_20261012_v1/small3/AUDIT.json",
"sha256": "7581f3e17eb0e6137d9a2167e8398f2e7d50f8b6f3ac28775203b5d73ff85b4f"
},
{
"bytes": 3377,
"name": "mag7_review",
"path": "/Users/xiaojinzhao/Documents/GitHub/web_compression/analysis_outputs/six_dataset_numeric_repair_20261012_v1/mag7_float64_v2/INDEPENDENT_REVIEW.json",
"sha256": "1216e921d36c7fffdcf17216894f7a78bec8ceb281886464e25d86d8dc89a3ee"
}
],
"status": "audit_complete_two_input_repairs_required_replacement_results_pending"
}