{
  "alignment": {
    "level": "sample",
    "n_observations_total": 62,
    "n_samples": 62,
    "profile_scores": {
      "integrity_risk": 0.0,
      "local_artefact_risk": 1.0,
      "noise_risk": 0.00017016376577206284,
      "outlier_pressure": 1.0,
      "reference_spread": 0.47485649549740383,
      "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": "2026-10-28T14:51:10.473057+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 RAR download retained as provenance.",
    "tier": "public"
  },
  "identity": {
    "description": "Sea cucumber representative NIR spectra. v2.0 standardized NIRS package: 1 spectral source(s), 1 declared target(s). Auto-generated from dataset_card.json (verify before publication).",
    "domain": "dryad",
    "id": "dryad_sea_cucumber_representative_nir_manual",
    "keywords": [
      "nir",
      "v2",
      "dryad"
    ],
    "name": "Sea cucumber representative NIR spectra",
    "tier": "public"
  },
  "integrity": {
    "content_hash": "7a52a320f8ca44123afa09c445d0438c213d849889e2c457521fff80ea1d1f8b",
    "manifest": "manifest.json",
    "metadata_hash": "91fa51fb7d6329eb328756e1da23383868cebe4078c99427468143463768e4dc",
    "processing_hash": "6e00126e8b1d8773f8301e2bc5ce4c79866b47e0c31345885e9408e2bb09c4c6"
  },
  "protocol_version": "5",
  "provenance": {
    "contributor": "DRYAD sea cucumber",
    "conversion_status": null,
    "origin_sources": [
      {
        "access": "open",
        "kind": "url",
        "license": null,
        "locator": "10.5061/dryad.n1066",
        "title": "Dryad"
      },
      {
        "access": "manual",
        "kind": "script",
        "license": null,
        "locator": "source_to_standard.py",
        "title": "standardization script (maintainer-only)"
      }
    ],
    "publications": [],
    "reference_method": null,
    "warnings": [
      "Y.csv has no observation_id; conversion assumes Y/M paired row order when counts match and M observation order matches an X block. Y row pairing is not independently verified.",
      "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": 2500.13516,
      "axis_min": 800.44463,
      "axis_unit": "nm",
      "instrument_name": null,
      "modality": "NIR",
      "n_observations": 62,
      "n_variables": 3439,
      "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": 3.1265015909748692,
        "mean_min": 0.9809354889777399,
        "n_outliers": 32,
        "pca": null,
        "profile": {
          "amplitude": {
            "area_under_curve": 3448.766682857614,
            "mean_reflectance": 2.0289524004097736,
            "peak_to_peak": 2.1455661019971295,
            "variance": 0.5099732004454033
          },
          "artefacts": {
            "clip_fraction": 2.3450177752347364e-05,
            "jump_count": 5173,
            "jump_rate": 0.02426861078271313,
            "spike_count": 6643,
            "spike_rate": 0.03117403587149333
          },
          "diagnostics": [
            {
              "evidence": [
                {
                  "level": 1.0,
                  "signal": "Spike rate"
                },
                {
                  "level": 1.0,
                  "signal": "Jump rate"
                },
                {
                  "level": 1.0,
                  "signal": "SNR non d\u00e9grad\u00e9"
                },
                {
                  "level": 0.5245071628054443,
                  "signal": "PCA Q"
                },
                {
                  "level": 0.47485649549740383,
                  "signal": "RMS/SAM r\u00e9f\u00e9rence"
                }
              ],
              "interpretation": "Rupture aux jonctions de d\u00e9tecteurs, calibration locale ou sonde diff\u00e9rente.",
              "key": "splice",
              "label": "Splice / raccord d\u00e9tecteurs",
              "score": 0.7398625218346233,
              "strength": "forte"
            },
            {
              "evidence": [
                {
                  "level": 1.0,
                  "signal": "Mahalanobis / T2"
                },
                {
                  "level": 1.0,
                  "signal": "Baseline/mean/area"
                },
                {
                  "level": 1.0,
                  "signal": "artefacts locaux"
                },
                {
                  "level": 0.5245071628054443,
                  "signal": "PCA Q"
                },
                {
                  "level": 0.47485649549740383,
                  "signal": "RMS/SAM r\u00e9f\u00e9rence"
                }
              ],
              "interpretation": "D\u00e9calage syst\u00e9matique entre campagnes, instruments ou r\u00e9f\u00e9rence blanche.",
              "key": "white_calibration",
              "label": "Erreur calibration / r\u00e9f\u00e9rence blanche",
              "score": 0.7082272763838081,
              "strength": "moyenne"
            },
            {
              "evidence": [
                {
                  "level": 1.0,
                  "signal": "Mahalanobis / T2"
                },
                {
                  "level": 1.0,
                  "signal": "Baseline/mean/area"
                },
                {
                  "level": 0.5245071628054443,
                  "signal": "PCA Q"
                },
                {
                  "level": 0.47485649549740383,
                  "signal": "RMS/SAM r\u00e9f\u00e9rence"
                }
              ],
              "interpretation": "Effet syst\u00e9matique du support, blanc/noir, transflectance ou environnement de mesure.",
              "key": "background_shift",
              "label": "Fond diff\u00e9rent",
              "score": 0.6665606097171414,
              "strength": "moyenne"
            },
            {
              "evidence": [
                {
                  "level": 1.0,
                  "signal": "Spike rate"
                },
                {
                  "level": 1.0,
                  "signal": "Jump rate"
                },
                {
                  "level": 1.0,
                  "signal": "SNR normal/\u00e9lev\u00e9"
                },
                {
                  "level": 0.9998298362342279,
                  "signal": "Noise RMS faible"
                },
                {
                  "level": 0.5245071628054443,
                  "signal": "PCA Q"
                }
              ],
              "interpretation": "Artefacts num\u00e9riques ou traitement spectral incorrect.",
              "key": "resampling_error",
              "label": "Erreur interpolation / r\u00e9\u00e9chantillonnage",
              "score": 0.6427017467644893,
              "strength": "moyenne"
            },
            {
              "evidence": [
                {
                  "level": 1.0,
                  "signal": "Mahalanobis / T2"
                },
                {
                  "level": 1.0,
                  "signal": "Structure PCA"
                },
                {
                  "level": 0.47485649549740383,
                  "signal": "RMS/SAM r\u00e9f\u00e9rence"
                }
              ],
              "interpretation": "Vari\u00e9t\u00e9, esp\u00e8ce, lot ou condition diff\u00e9rente mais physiquement plausible.",
              "key": "out_of_domain",
              "label": "Spectre hors domaine valide",
              "score": 0.6349712990994808,
              "strength": "moyenne"
            },
            {
              "evidence": [
                {
                  "level": 1.0,
                  "signal": "Mahalanobis / T2"
                },
                {
                  "level": 1.0,
                  "signal": "Spike rate"
                },
                {
                  "level": 1.0,
                  "signal": "Jump rate"
                },
                {
                  "level": 0.5245071628054443,
                  "signal": "PCA Q"
                },
                {
                  "level": 0.47485649549740383,
                  "signal": "RMS/SAM r\u00e9f\u00e9rence"
                }
              ],
              "interpretation": "Combinaison possible changement de sonde + splice, amplifi\u00e9e par g\u00e9om\u00e9trie, fond ou calibration.",
              "key": "vera25_like",
              "label": "Signature VERA25-like",
              "score": 0.624864136781902,
              "strength": "moyenne"
            },
            {
              "evidence": [
                {
                  "level": 1.0,
                  "signal": "Mahalanobis / T2"
                },
                {
                  "level": 1.0,
                  "signal": "Baseline/mean/area"
                },
                {
                  "level": 0.5245071628054443,
                  "signal": "PCA Q"
                },
                {
                  "level": 0.47485649549740383,
                  "signal": "RMS/SAM r\u00e9f\u00e9rence"
                }
              ],
              "interpretation": "Modification de l'illumination, collecte, angle ou distance sonde-\u00e9chantillon.",
              "key": "probe_geometry",
              "label": "Diff\u00e9rence de sonde / g\u00e9om\u00e9trie",
              "score": 0.5784805226146926,
              "strength": "moyenne"
            },
            {
              "evidence": [
                {
                  "level": 1.0,
                  "signal": "Structure PCA"
                },
                {
                  "level": 1.0,
                  "signal": "Mahalanobis / T2"
                },
                {
                  "level": 0.5245071628054443,
                  "signal": "PCA Q"
                },
                {
                  "level": 0.47485649549740383,
                  "signal": "RMS/SAM r\u00e9f\u00e9rence"
                }
              ],
              "interpretation": "M\u00e9lange de campagnes, op\u00e9rateurs, lots, setups ou sous-populations spectrales.",
              "key": "multi_regime",
              "label": "Dataset multi-r\u00e9gimes",
              "score": 0.5388924451483519,
              "strength": "moyenne"
            }
          ],
          "integrity": {
            "finite_ratio": 1.0,
            "inf_count": 0,
            "nan_ratio": 0.0,
            "zero_column_ratio": 0.0,
            "zero_ratio": 0.0
          },
          "noise": {
            "bandwise_snr_median": 126667.16905923314,
            "bandwise_snr_min": 6322.184505130921,
            "noise_rms": 1.8254880381435872e-05,
            "snr": 111145.75160257405,
            "snr_db": 100.91785734055247,
            "worst_band_axis": 2494.20256,
            "worst_band_index": 3426
          },
          "outliers": {
            "hotelling_t2_max": 14.010995485815402,
            "hotelling_t2_median": 0.566132967807165,
            "hotelling_t2_p95": 9.4496684019603,
            "hotelling_t2_ratio": 16.691605928837244,
            "mahalanobis_h_max": 3.7431264319837503,
            "mahalanobis_h_median": 0.7523973744613569,
            "mahalanobis_h_p95": 3.071728866029198,
            "mahalanobis_h_ratio": 4.082588496840856,
            "pca_q_max": 6.210687433227584,
            "pca_q_median": 1.171790185472739,
            "pca_q_p95": 4.916898764684573,
            "pca_q_ratio": 4.196057302443554
          },
          "profile_scores": {
            "integrity_risk": 0.0,
            "local_artefact_risk": 1.0,
            "noise_risk": 0.00017016376577206284,
            "outlier_pressure": 1.0,
            "reference_spread": 0.47485649549740383,
            "repeatability_risk": 0.0,
            "shape_drift": 1.0,
            "structure_complexity": 1.0
          },
          "reference": {
            "affine_gain_median": 1.0460158010958926,
            "affine_gain_p95_abs_delta": 0.32060189938019473,
            "affine_offset_median": -0.07169254712377504,
            "affine_offset_p95_abs": 0.4177644875565459,
            "affine_residual_rms_median": 0.026753423274682015,
            "affine_residual_rms_p95": 0.06790145472250586,
            "peak_position_std": 17.483134432766132,
            "rms_to_mean_spectrum": 0.060328023635100946,
            "rms_to_mean_spectrum_p95": 0.25470900001309554,
            "sam_to_mean_spectrum": 0.019401144195484037,
            "sam_to_mean_spectrum_p95": 0.08231864361654616,
            "xcorr_lag_p95_axis": 0.0,
            "xcorr_lag_p95_features": 0.0
          },
          "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": 2.027965387627324,
            "curvature_rms": 0.0001296606927127243,
            "d1_rms": 0.003156862846351457,
            "edge_noise_ratio": 1.060367677595944
          },
          "structure": {
            "density_cv": 1.1781325354534118,
            "isolation_forest_score_p95": 0.6325649716073121,
            "local_outlier_factor_p95": 7.5558619859760405,
            "pca_score_density": 0.8230317169109999
          }
        },
        "quality": {
          "dynamic_range": 2.1455661019971295,
          "noise_proxy_db": 100.91785734055247,
          "saturation_fraction": 4.690035550469473e-06,
          "smoothness": 0.0002902702277616296
        },
        "spacing": {
          "is_uniform": true,
          "max": 0.4943900000002941,
          "mean": 0.4943835165794066,
          "median": 0.49438000000009197,
          "min": 0.4943799999996372,
          "std": 4.774878361138376e-06
        },
        "value_max": 3.2617499828338623,
        "value_min": 0.8660299777984619,
        "xy": []
      },
      "warnings": []
    }
  ],
  "splits": [],
  "variables": [
    {
      "assets": [],
      "balance": {
        "gini_simpson": 0.6477627471383975,
        "imbalance_ratio": 1.8,
        "minority_fraction": 0.24193548387096775,
        "n_classes": 3,
        "normalized_entropy": 0.9742398790867665
      },
      "name": "class",
      "role": "target",
      "stats": {
        "n": 62,
        "n_classes": 3,
        "n_missing": 0,
        "top_classes": [
          {
            "count": 27,
            "name": "YT"
          },
          {
            "count": 20,
            "name": "WDF"
          },
          {
            "count": 15,
            "name": "RS"
          }
        ]
      },
      "type": "categorical",
      "unit": null
    }
  ],
  "versions": {
    "content": "1.1.0",
    "schema_protocol": "2.0"
  },
  "warnings": [
    "variable 'class_label' declared but absent from canonical variables.parquet; skipped",
    "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"
  ]
}