{
  "alignment": {
    "level": "sample",
    "n_observations_total": 197,
    "n_samples": 197,
    "profile_scores": {
      "integrity_risk": 0.5744507663297569,
      "local_artefact_risk": 1.0,
      "noise_risk": 0.0003072503498255455,
      "outlier_pressure": 1.0,
      "reference_spread": 1.0,
      "repeatability_risk": 0.0,
      "shape_drift": 1.0,
      "structure_complexity": 1.0
    },
    "reps_per_sample": {
      "max": 1,
      "mean": 1.0,
      "min": 1
    },
    "sample_id_available": false
  },
  "assets": {
    "sources": {},
    "variables": []
  },
  "generated_at": "2026-10-28T14:51:09.134942+00:00",
  "governance": {
    "access_policy": "Open per source license.",
    "license": "CC0-1.0",
    "permitted_use": "Research and benchmarking.",
    "redistribution_rights": "Dryad source recorded as CC0-1.0 in blocked inventory; manual download retained as provenance.",
    "tier": "public"
  },
  "identity": {
    "description": "Gastropod reflectance spectra. v2.0 standardized NIRS package: 1 spectral source(s), 0 declared target(s). Auto-generated from dataset_card.json (verify before publication).",
    "domain": "dryad",
    "id": "dryad_gastropods_reflectance_manual",
    "keywords": [
      "nir",
      "v2",
      "dryad"
    ],
    "name": "Gastropod reflectance spectra",
    "tier": "public"
  },
  "integrity": {
    "content_hash": "d0b90e9ba67449b0397146489ee5c68034ccb31399cf2740b64392faf269eb04",
    "manifest": "manifest.json",
    "metadata_hash": "609e4d194a7f166e628d6c10232e8b5829b099481f9ef245ae4d2af20f7583a8",
    "processing_hash": "c200b1a0e74e8d76802a7b0010ea956e9a57480422c7ac2ea99ba5b0ceeeb493"
  },
  "protocol_version": "5",
  "provenance": {
    "contributor": "DRYAD gastropods",
    "conversion_status": null,
    "origin_sources": [
      {
        "access": "open",
        "kind": "url",
        "license": null,
        "locator": "10.5061/dryad.905qfttnv",
        "title": "Dryad"
      },
      {
        "access": "manual",
        "kind": "script",
        "license": null,
        "locator": "source_to_standard.py",
        "title": "standardization script (maintainer-only)"
      }
    ],
    "publications": [],
    "reference_method": null,
    "warnings": [
      "Original-source loading retains source observations and native axes; this revision supersedes the inherited standardized snapshot counts. See docs/PUBLIC_ORIGIN_LOADING.md."
    ]
  },
  "schema_version": "2.0",
  "sources": [
    {
      "assets": [],
      "axis_max": 1709.137,
      "axis_min": 187.574,
      "axis_unit": "nm",
      "instrument_name": null,
      "modality": "NIR",
      "n_observations": 197,
      "n_variables": 2482,
      "name": "X",
      "signal_type": null,
      "signal_type_confidence": 0.0,
      "source_id": "X",
      "spectral": {
        "dimensionality": {
          "cumulative_top10": null,
          "effective_rank": null,
          "n_components_95": null,
          "n_components_99": null
        },
        "mean_max": 181.91198216053436,
        "mean_min": -606.0874707825898,
        "n_outliers": 107,
        "pca": null,
        "profile": {
          "amplitude": {
            "area_under_curve": 37975.41529137328,
            "mean_reflectance": 23.063552546741654,
            "peak_to_peak": 787.9994529431242,
            "variance": 41360.77393403978
          },
          "artefacts": {
            "clip_fraction": 4.211324250910699e-06,
            "jump_count": 25053,
            "jump_rate": 0.05125860089983366,
            "spike_count": 30534,
            "spike_rate": 0.06249795316849517
          },
          "diagnostics": [
            {
              "evidence": [
                {
                  "level": 1.0,
                  "signal": "Spike rate"
                },
                {
                  "level": 1.0,
                  "signal": "Jump rate"
                },
                {
                  "level": 1.0,
                  "signal": "RMS/SAM r\u00e9f\u00e9rence"
                },
                {
                  "level": 1.0,
                  "signal": "SNR non d\u00e9grad\u00e9"
                },
                {
                  "level": 0.9684260025812331,
                  "signal": "PCA Q"
                }
              ],
              "interpretation": "Rupture aux jonctions de d\u00e9tecteurs, calibration locale ou sonde diff\u00e9rente.",
              "key": "splice",
              "label": "Splice / raccord d\u00e9tecteurs",
              "score": 0.9336667654952571,
              "strength": "forte"
            },
            {
              "evidence": [
                {
                  "level": 1.0,
                  "signal": "Mahalanobis / T2"
                },
                {
                  "level": 1.0,
                  "signal": "Baseline/mean/area"
                },
                {
                  "level": 1.0,
                  "signal": "RMS/SAM r\u00e9f\u00e9rence"
                },
                {
                  "level": 1.0,
                  "signal": "artefacts locaux"
                },
                {
                  "level": 0.9684260025812331,
                  "signal": "PCA Q"
                }
              ],
              "interpretation": "D\u00e9calage syst\u00e9matique entre campagnes, instruments ou r\u00e9f\u00e9rence blanche.",
              "key": "white_calibration",
              "label": "Erreur calibration / r\u00e9f\u00e9rence blanche",
              "score": 0.8697376670968722,
              "strength": "forte"
            },
            {
              "evidence": [
                {
                  "level": 1.0,
                  "signal": "Mahalanobis / T2"
                },
                {
                  "level": 1.0,
                  "signal": "Baseline/mean/area"
                },
                {
                  "level": 1.0,
                  "signal": "RMS/SAM r\u00e9f\u00e9rence"
                },
                {
                  "level": 0.9684260025812331,
                  "signal": "PCA Q"
                }
              ],
              "interpretation": "Effet syst\u00e9matique du support, blanc/noir, transflectance ou environnement de mesure.",
              "key": "background_shift",
              "label": "Fond diff\u00e9rent",
              "score": 0.8280710004302055,
              "strength": "forte"
            },
            {
              "evidence": [
                {
                  "level": 1.0,
                  "signal": "Mahalanobis / T2"
                },
                {
                  "level": 1.0,
                  "signal": "Spike rate"
                },
                {
                  "level": 1.0,
                  "signal": "Jump rate"
                },
                {
                  "level": 1.0,
                  "signal": "RMS/SAM r\u00e9f\u00e9rence"
                },
                {
                  "level": 0.9684260025812331,
                  "signal": "PCA Q"
                }
              ],
              "interpretation": "Combinaison possible changement de sonde + splice, amplifi\u00e9e par g\u00e9om\u00e9trie, fond ou calibration.",
              "key": "vera25_like",
              "label": "Signature VERA25-like",
              "score": 0.7818536686077846,
              "strength": "forte"
            },
            {
              "evidence": [
                {
                  "level": 1.0,
                  "signal": "Spike rate"
                },
                {
                  "level": 1.0,
                  "signal": "Jump rate"
                },
                {
                  "level": 1.0,
                  "signal": "SNR normal/\u00e9lev\u00e9"
                },
                {
                  "level": 0.9996927496501744,
                  "signal": "Noise RMS faible"
                },
                {
                  "level": 0.9684260025812331,
                  "signal": "PCA Q"
                }
              ],
              "interpretation": "Artefacts num\u00e9riques ou traitement spectral incorrect.",
              "key": "resampling_error",
              "label": "Erreur interpolation / r\u00e9\u00e9chantillonnage",
              "score": 0.7695239507075101,
              "strength": "forte"
            },
            {
              "evidence": [
                {
                  "level": 1.0,
                  "signal": "Mahalanobis / T2"
                },
                {
                  "level": 1.0,
                  "signal": "RMS/SAM r\u00e9f\u00e9rence"
                },
                {
                  "level": 1.0,
                  "signal": "Structure PCA"
                }
              ],
              "interpretation": "Vari\u00e9t\u00e9, esp\u00e8ce, lot ou condition diff\u00e9rente mais physiquement plausible.",
              "key": "out_of_domain",
              "label": "Spectre hors domaine valide",
              "score": 0.74,
              "strength": "forte"
            },
            {
              "evidence": [
                {
                  "level": 1.0,
                  "signal": "Mahalanobis / T2"
                },
                {
                  "level": 1.0,
                  "signal": "Baseline/mean/area"
                },
                {
                  "level": 1.0,
                  "signal": "RMS/SAM r\u00e9f\u00e9rence"
                },
                {
                  "level": 0.9684260025812331,
                  "signal": "PCA Q"
                }
              ],
              "interpretation": "Modification de l'illumination, collecte, angle ou distance sonde-\u00e9chantillon.",
              "key": "probe_geometry",
              "label": "Diff\u00e9rence de sonde / g\u00e9om\u00e9trie",
              "score": 0.7169180003687475,
              "strength": "moyenne"
            },
            {
              "evidence": [
                {
                  "level": 1.0,
                  "signal": "Structure PCA"
                },
                {
                  "level": 1.0,
                  "signal": "RMS/SAM r\u00e9f\u00e9rence"
                },
                {
                  "level": 1.0,
                  "signal": "Mahalanobis / T2"
                },
                {
                  "level": 0.9684260025812331,
                  "signal": "PCA Q"
                }
              ],
              "interpretation": "M\u00e9lange de campagnes, op\u00e9rateurs, lots, setups ou sous-populations spectrales.",
              "key": "multi_regime",
              "label": "Dataset multi-r\u00e9gimes",
              "score": 0.7149481604129972,
              "strength": "moyenne"
            }
          ],
          "integrity": {
            "finite_ratio": 0.9712774616835121,
            "inf_count": 0,
            "nan_ratio": 0.02872253831648785,
            "zero_column_ratio": 0.0,
            "zero_ratio": 0.0
          },
          "noise": {
            "bandwise_snr_median": 1574.072781008118,
            "bandwise_snr_min": 0.030543709959009905,
            "noise_rms": 0.01210565537895567,
            "snr": 2166.0384831618207,
            "snr_db": 66.713323365974,
            "worst_band_axis": 188.037,
            "worst_band_index": 1
          },
          "outliers": {
            "hotelling_t2_max": 155.08465757691704,
            "hotelling_t2_median": 0.18284582239915684,
            "hotelling_t2_p95": 27.516994730397595,
            "hotelling_t2_ratio": 150.49288175874935,
            "mahalanobis_h_max": 12.453299063979674,
            "mahalanobis_h_median": 0.42760475020649247,
            "mahalanobis_h_p95": 5.2456270478689975,
            "mahalanobis_h_ratio": 12.267466732621324,
            "pca_q_max": 35926276.22591325,
            "pca_q_median": 1894739.5999924364,
            "pca_q_p95": 14679320.774024319,
            "pca_q_ratio": 7.747408020649865
          },
          "profile_scores": {
            "integrity_risk": 0.5744507663297569,
            "local_artefact_risk": 1.0,
            "noise_risk": 0.0003072503498255455,
            "outlier_pressure": 1.0,
            "reference_spread": 1.0,
            "repeatability_risk": 0.0,
            "shape_drift": 1.0,
            "structure_complexity": 1.0
          },
          "reference": {
            "affine_gain_median": 0.3227717209854951,
            "affine_gain_p95_abs_delta": 5.048400773500632,
            "affine_offset_median": 15.45058804777924,
            "affine_offset_p95_abs": 130.82698882799258,
            "affine_residual_rms_median": 39.83268775690843,
            "affine_residual_rms_p95": 252.02759344986444,
            "peak_position_std": 5.49988697444647,
            "rms_to_mean_spectrum": 44.023524389702686,
            "rms_to_mean_spectrum_p95": 288.7437689211017,
            "sam_to_mean_spectrum": 1.1294390845437354,
            "sam_to_mean_spectrum_p95": 1.5171894683598113,
            "xcorr_lag_p95_axis": 6.4049999999986085,
            "xcorr_lag_p95_features": 15.0
          },
          "repeatability": {
            "cv_intra_id": null,
            "distance_to_centroid_p95": null,
            "n_repeat_groups": 0,
            "rms_intra_id": null,
            "sam_intra_id": null
          },
          "shape": {
            "baseline_slope": 28.007949719038816,
            "curvature_rms": 86.16941262236239,
            "d1_rms": 50.773643407494056,
            "edge_noise_ratio": 26.759359046613785
          },
          "structure": {
            "density_cv": 3.1324896944290517,
            "isolation_forest_score_p95": 0.4975019387245832,
            "local_outlier_factor_p95": 23.83023011018218,
            "pca_score_density": 0.0022908694693414243
          }
        },
        "quality": {
          "dynamic_range": 787.9994529431242,
          "noise_proxy_db": null,
          "saturation_fraction": 2.045182164375381e-06,
          "smoothness": null
        },
        "spacing": {
          "is_uniform": false,
          "max": 1.6159999999999854,
          "mean": 0.6132861749294639,
          "median": 0.42699999999990723,
          "min": 0.0009999999999763531,
          "std": 0.45953435714792323
        },
        "value_max": 18400.0,
        "value_min": -79585.7109375,
        "xy": []
      },
      "warnings": []
    }
  ],
  "splits": [],
  "variables": [
    {
      "assets": [],
      "balance": {
        "gini_simpson": 0.9241155402097452,
        "imbalance_ratio": 19.0,
        "minority_fraction": 0.01015228426395939,
        "n_classes": 21,
        "normalized_entropy": 0.9307877885183672
      },
      "name": "species_code",
      "role": "metadata",
      "stats": {
        "n": 197,
        "n_classes": 21,
        "n_missing": 0,
        "top_classes": [
          {
            "count": 38,
            "name": "CTRAM"
          },
          {
            "count": 16,
            "name": "DORBI"
          },
          {
            "count": 12,
            "name": "CLINE"
          },
          {
            "count": 12,
            "name": "LUNDU"
          },
          {
            "count": 12,
            "name": "PALTI"
          },
          {
            "count": 12,
            "name": "BNANU"
          },
          {
            "count": 12,
            "name": "PLATI"
          },
          {
            "count": 9,
            "name": "AUNIF"
          },
          {
            "count": 8,
            "name": "ACONS"
          },
          {
            "count": 6,
            "name": "CADEL"
          },
          {
            "count": 6,
            "name": "NATRA"
          },
          {
            "count": 6,
            "name": "NMELA"
          },
          {
            "count": 6,
            "name": "TCONI"
          },
          {
            "count": 6,
            "name": "APRAE"
          },
          {
            "count": 6,
            "name": "AROST"
          },
          {
            "count": 6,
            "name": "APORC"
          },
          {
            "count": 6,
            "name": "CODON"
          },
          {
            "count": 6,
            "name": "NFLAM"
          },
          {
            "count": 6,
            "name": "SDIEM"
          },
          {
            "count": 4,
            "name": "LVINO"
          }
        ]
      },
      "type": "categorical",
      "unit": null
    },
    {
      "assets": [],
      "balance": {
        "gini_simpson": 0.7632250251230385,
        "imbalance_ratio": 28.0,
        "minority_fraction": 0.01015228426395939,
        "n_classes": 9,
        "normalized_entropy": 0.7429192775412305
      },
      "name": "individual_id",
      "role": "metadata",
      "stats": {
        "n": 197,
        "n_classes": 9,
        "n_missing": 0,
        "top_classes": [
          {
            "count": 56,
            "name": "3"
          },
          {
            "count": 55,
            "name": "2"
          },
          {
            "count": 52,
            "name": "1"
          },
          {
            "count": 16,
            "name": "4"
          },
          {
            "count": 4,
            "name": "5"
          },
          {
            "count": 4,
            "name": "6"
          },
          {
            "count": 4,
            "name": "7"
          },
          {
            "count": 4,
            "name": "9"
          },
          {
            "count": 2,
            "name": "8"
          }
        ]
      },
      "type": "categorical",
      "unit": null
    },
    {
      "assets": [],
      "balance": {
        "gini_simpson": 0.49998711639052806,
        "imbalance_ratio": 1.010204081632653,
        "minority_fraction": 0.49746192893401014,
        "n_classes": 2,
        "normalized_entropy": 0.9999814128006821
      },
      "name": "state",
      "role": "metadata",
      "stats": {
        "n": 197,
        "n_classes": 2,
        "n_missing": 0,
        "top_classes": [
          {
            "count": 99,
            "name": "WET"
          },
          {
            "count": 98,
            "name": "DRY"
          }
        ]
      },
      "type": "categorical",
      "unit": null
    },
    {
      "assets": [],
      "balance": {
        "gini_simpson": 0.8478445721353294,
        "imbalance_ratio": 8.0,
        "minority_fraction": 0.030456852791878174,
        "n_classes": 12,
        "normalized_entropy": 0.8571999137477206
      },
      "name": "body_region",
      "role": "metadata",
      "stats": {
        "n": 197,
        "n_classes": 12,
        "n_missing": 0,
        "top_classes": [
          {
            "count": 48,
            "name": "TOP"
          },
          {
            "count": 42,
            "name": "BAS"
          },
          {
            "count": 33,
            "name": "WHT"
          },
          {
            "count": 18,
            "name": "CHK"
          },
          {
            "count": 12,
            "name": "MID"
          },
          {
            "count": 8,
            "name": "RED"
          },
          {
            "count": 6,
            "name": "BLK"
          },
          {
            "count": 6,
            "name": "ALG"
          },
          {
            "count": 6,
            "name": "TIP"
          },
          {
            "count": 6,
            "name": "BLU"
          },
          {
            "count": 6,
            "name": "GRN"
          },
          {
            "count": 6,
            "name": "BRO"
          }
        ]
      },
      "type": "categorical",
      "unit": null
    },
    {
      "assets": [],
      "balance": {
        "gini_simpson": 0.3336339508876808,
        "imbalance_ratio": 26.5,
        "minority_fraction": 0.030456852791878174,
        "n_classes": 4,
        "normalized_entropy": 0.49194906505575026
      },
      "name": "size_code",
      "role": "metadata",
      "stats": {
        "n": 197,
        "n_classes": 4,
        "n_missing": 0,
        "top_classes": [
          {
            "count": 159,
            "name": "XXX"
          },
          {
            "count": 20,
            "name": "LRG"
          },
          {
            "count": 12,
            "name": "MED"
          },
          {
            "count": 6,
            "name": "SML"
          }
        ]
      },
      "type": "categorical",
      "unit": null
    }
  ],
  "versions": {
    "content": "1.1.0",
    "schema_protocol": "2.0"
  },
  "warnings": [
    "variable 'manual_download' declared but absent from canonical variables.parquet; skipped",
    "variable 'manual_download_source_dir' declared but absent from canonical variables.parquet; skipped",
    "variable 'manual_download_file' declared but absent from canonical variables.parquet; skipped",
    "variable 'official_source_url' declared but absent from canonical variables.parquet; skipped",
    "variable 'standardization_batch' declared but absent from canonical variables.parquet; skipped"
  ]
}