{
  "alignment": {
    "level": "sample",
    "n_observations_total": 2737,
    "n_samples": 2737,
    "profile_scores": {
      "integrity_risk": 0.147276665805489,
      "local_artefact_risk": 1.0,
      "noise_risk": 0.0008791692385469085,
      "outlier_pressure": 0.5697954278423871,
      "reference_spread": 0.6011429475375438,
      "repeatability_risk": 0.0,
      "shape_drift": 0.672192753530885,
      "structure_complexity": 0.9722658007093455
    },
    "reps_per_sample": {
      "max": 1,
      "mean": 1.0,
      "min": 1
    },
    "sample_id_available": false
  },
  "assets": {
    "sources": {},
    "variables": []
  },
  "generated_at": "2026-10-28T14:51:13.483566+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": "Tree leaf girdling reflectance 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_tree_leaf_girdling_visnir_manual",
    "keywords": [
      "nir",
      "v2",
      "dryad"
    ],
    "name": "Tree leaf girdling reflectance spectra",
    "tier": "public"
  },
  "integrity": {
    "content_hash": "c51ef833ceef6343885fe0993a56d1a1d00fdec268e051482d4fa4f03dc5febf",
    "manifest": "manifest.json",
    "metadata_hash": "7114df7988abe7428ae4e7e5843a82d79e50131e5e67502009ccb243e959b862",
    "processing_hash": "21b87e9bd2872d162f5218a6c73d4bd0f10f0a5b49aea7c2bbc14221cad2abe5"
  },
  "protocol_version": "5",
  "provenance": {
    "contributor": "DRYAD tree leaf",
    "conversion_status": null,
    "origin_sources": [
      {
        "access": "open",
        "kind": "url",
        "license": null,
        "locator": "10.5061/dryad.d51c5b01n",
        "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": 2500.0,
      "axis_min": 350.0,
      "axis_unit": "nm",
      "instrument_name": null,
      "modality": "NIR",
      "n_observations": 2737,
      "n_variables": 2151,
      "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": 0.49474921053859233,
        "mean_min": 0.046235056851611306,
        "n_outliers": 966,
        "pca": null,
        "profile": {
          "amplitude": {
            "area_under_curve": 538.4110185405308,
            "mean_reflectance": 0.25136002799901436,
            "peak_to_peak": 0.448514153686981,
            "variance": 0.029947192681630867
          },
          "artefacts": {
            "clip_fraction": 3.4223521347092557e-07,
            "jump_count": 255713,
            "jump_rate": 0.043454979565132425,
            "spike_count": 322840,
            "spike_rate": 0.05488783815466421
          },
          "diagnostics": [
            {
              "evidence": [
                {
                  "level": 1.0,
                  "signal": "Spike rate"
                },
                {
                  "level": 1.0,
                  "signal": "Jump rate"
                },
                {
                  "level": 1.0,
                  "signal": "SNR non d\u00e9grad\u00e9"
                },
                {
                  "level": 0.6011429475375438,
                  "signal": "RMS/SAM r\u00e9f\u00e9rence"
                },
                {
                  "level": 0.5697954278423871,
                  "signal": "PCA Q"
                }
              ],
              "interpretation": "Rupture aux jonctions de d\u00e9tecteurs, calibration locale ou sonde diff\u00e9rente.",
              "key": "splice",
              "label": "Splice / raccord d\u00e9tecteurs",
              "score": 0.7741349249216734,
              "strength": "forte"
            },
            {
              "evidence": [
                {
                  "level": 1.0,
                  "signal": "Spike rate"
                },
                {
                  "level": 1.0,
                  "signal": "Jump rate"
                },
                {
                  "level": 1.0,
                  "signal": "SNR normal/\u00e9lev\u00e9"
                },
                {
                  "level": 0.9991208307614531,
                  "signal": "Noise RMS faible"
                },
                {
                  "level": 0.5697954278423871,
                  "signal": "PCA Q"
                }
              ],
              "interpretation": "Artefacts num\u00e9riques ou traitement spectral incorrect.",
              "key": "resampling_error",
              "label": "Erreur interpolation / r\u00e9\u00e9chantillonnage",
              "score": 0.6555804791630921,
              "strength": "moyenne"
            },
            {
              "evidence": [
                {
                  "level": 1.0,
                  "signal": "Spike rate"
                },
                {
                  "level": 1.0,
                  "signal": "Jump rate"
                },
                {
                  "level": 0.6011429475375438,
                  "signal": "RMS/SAM r\u00e9f\u00e9rence"
                },
                {
                  "level": 0.5697954278423871,
                  "signal": "PCA Q"
                },
                {
                  "level": 0.5594910180796514,
                  "signal": "Mahalanobis / T2"
                }
              ],
              "interpretation": "Combinaison possible changement de sonde + splice, amplifi\u00e9e par g\u00e9om\u00e9trie, fond ou calibration.",
              "key": "vera25_like",
              "label": "Signature VERA25-like",
              "score": 0.5999712531356409,
              "strength": "moyenne"
            },
            {
              "evidence": [
                {
                  "level": 1.0,
                  "signal": "artefacts locaux"
                },
                {
                  "level": 0.672192753530885,
                  "signal": "Baseline/mean/area"
                },
                {
                  "level": 0.6011429475375438,
                  "signal": "RMS/SAM r\u00e9f\u00e9rence"
                },
                {
                  "level": 0.5697954278423871,
                  "signal": "PCA Q"
                },
                {
                  "level": 0.5594910180796514,
                  "signal": "Mahalanobis / T2"
                }
              ],
              "interpretation": "D\u00e9calage syst\u00e9matique entre campagnes, instruments ou r\u00e9f\u00e9rence blanche.",
              "key": "white_calibration",
              "label": "Erreur calibration / r\u00e9f\u00e9rence blanche",
              "score": 0.5761612658495762,
              "strength": "moyenne"
            },
            {
              "evidence": [
                {
                  "level": 0.672192753530885,
                  "signal": "Baseline/mean/area"
                },
                {
                  "level": 0.6011429475375438,
                  "signal": "RMS/SAM r\u00e9f\u00e9rence"
                },
                {
                  "level": 0.5697954278423871,
                  "signal": "PCA Q"
                },
                {
                  "level": 0.5594910180796514,
                  "signal": "Mahalanobis / T2"
                }
              ],
              "interpretation": "Effet syst\u00e9matique du support, blanc/noir, transflectance ou environnement de mesure.",
              "key": "background_shift",
              "label": "Fond diff\u00e9rent",
              "score": 0.5124691500868921,
              "strength": "moyenne"
            },
            {
              "evidence": [
                {
                  "level": 0.9722658007093455,
                  "signal": "Structure PCA"
                },
                {
                  "level": 0.6011429475375438,
                  "signal": "RMS/SAM r\u00e9f\u00e9rence"
                },
                {
                  "level": 0.5697954278423871,
                  "signal": "PCA Q"
                },
                {
                  "level": 0.5594910180796514,
                  "signal": "Mahalanobis / T2"
                }
              ],
              "interpretation": "M\u00e9lange de campagnes, op\u00e9rateurs, lots, setups ou sous-populations spectrales.",
              "key": "multi_regime",
              "label": "Dataset multi-r\u00e9gimes",
              "score": 0.4953675809969041,
              "strength": "moyenne"
            },
            {
              "evidence": [
                {
                  "level": 0.672192753530885,
                  "signal": "Baseline/mean/area"
                },
                {
                  "level": 0.6011429475375438,
                  "signal": "RMS/SAM r\u00e9f\u00e9rence"
                },
                {
                  "level": 0.5697954278423871,
                  "signal": "PCA Q"
                },
                {
                  "level": 0.5594910180796514,
                  "signal": "Mahalanobis / T2"
                }
              ],
              "interpretation": "Modification de l'illumination, collecte, angle ou distance sonde-\u00e9chantillon.",
              "key": "probe_geometry",
              "label": "Diff\u00e9rence de sonde / g\u00e9om\u00e9trie",
              "score": 0.49323173528435243,
              "strength": "moyenne"
            },
            {
              "evidence": [
                {
                  "level": 0.9722658007093455,
                  "signal": "Structure PCA"
                },
                {
                  "level": 0.6011429475375438,
                  "signal": "RMS/SAM r\u00e9f\u00e9rence"
                },
                {
                  "level": 0.5594910180796514,
                  "signal": "Mahalanobis / T2"
                }
              ],
              "interpretation": "Vari\u00e9t\u00e9, esp\u00e8ce, lot ou condition diff\u00e9rente mais physiquement plausible.",
              "key": "out_of_domain",
              "label": "Spectre hors domaine valide",
              "score": 0.48014220883867764,
              "strength": "moyenne"
            }
          ],
          "integrity": {
            "finite_ratio": 0.9926361667097255,
            "inf_count": 0,
            "nan_ratio": 0.0073638332902744505,
            "zero_column_ratio": 0.0,
            "zero_ratio": 0.006576543660942638
          },
          "noise": {
            "bandwise_snr_median": 11384.6126927043,
            "bandwise_snr_min": 4.288471868580628,
            "noise_rms": 1.971599234872471e-05,
            "snr": 12749.30009807127,
            "snr_db": 82.10972687675046,
            "worst_band_axis": 352.0,
            "worst_band_index": 2
          },
          "outliers": {
            "hotelling_t2_max": 67.66801780068337,
            "hotelling_t2_median": 1.7531787691527954,
            "hotelling_t2_p95": 7.847102195431422,
            "hotelling_t2_ratio": 4.475928144637211,
            "mahalanobis_h_max": 8.22605724516207,
            "mahalanobis_h_median": 1.3240765721027337,
            "mahalanobis_h_p95": 2.8012671336146044,
            "mahalanobis_h_ratio": 2.1156383192899337,
            "pca_q_max": 2.9053795572278727,
            "pca_q_median": 0.08500095991289401,
            "pca_q_p95": 0.38746526656464836,
            "pca_q_ratio": 4.558363422739097
          },
          "profile_scores": {
            "integrity_risk": 0.147276665805489,
            "local_artefact_risk": 1.0,
            "noise_risk": 0.0008791692385469085,
            "outlier_pressure": 0.5697954278423871,
            "reference_spread": 0.6011429475375438,
            "repeatability_risk": 0.0,
            "shape_drift": 0.672192753530885,
            "structure_complexity": 0.9722658007093455
          },
          "reference": {
            "affine_gain_median": 0.9929759337705094,
            "affine_gain_p95_abs_delta": 0.25132824236169954,
            "affine_offset_median": -0.0017713519587441995,
            "affine_offset_p95_abs": 0.04901089727852132,
            "affine_residual_rms_median": 0.011776702315350593,
            "affine_residual_rms_p95": 0.027501188959582434,
            "peak_position_std": 114.26645121525587,
            "rms_to_mean_spectrum": 0.024748457519392583,
            "rms_to_mean_spectrum_p95": 0.06740528008992468,
            "sam_to_mean_spectrum": 0.05159150553316539,
            "sam_to_mean_spectrum_p95": 0.12146405615662527,
            "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": -0.15074398198221314,
            "curvature_rms": 0.001976074175562291,
            "d1_rms": 0.0021904861849951157,
            "edge_noise_ratio": 0.22365837757387944
          },
          "structure": {
            "density_cv": 1.4174111334457125,
            "isolation_forest_score_p95": 0.5608378551882094,
            "local_outlier_factor_p95": 2.9167974021280365,
            "pca_score_density": 4.376423266576378
          }
        },
        "quality": {
          "dynamic_range": 0.448514153686981,
          "noise_proxy_db": null,
          "saturation_fraction": 1.698575252064321e-07,
          "smoothness": null
        },
        "spacing": {
          "is_uniform": true,
          "max": 1.0,
          "mean": 1.0,
          "median": 1.0,
          "min": 1.0,
          "std": 0.0
        },
        "value_max": 1.0530835390090942,
        "value_min": -0.09176594763994217,
        "xy": []
      },
      "warnings": []
    }
  ],
  "splits": [],
  "variables": [
    {
      "assets": [],
      "balance": {
        "gini_simpson": 0.4899000409682387,
        "imbalance_ratio": 1.3313458262350937,
        "minority_fraction": 0.4289367921081476,
        "n_classes": 2,
        "normalized_entropy": 0.9853793824341283
      },
      "name": "treatment",
      "role": "target",
      "stats": {
        "n": 2737,
        "n_classes": 2,
        "n_missing": 0,
        "top_classes": [
          {
            "count": 1563,
            "name": "control"
          },
          {
            "count": 1174,
            "name": "girdled"
          }
        ]
      },
      "type": "categorical",
      "unit": null
    },
    {
      "assets": [],
      "balance": {
        "gini_simpson": 0.9996322336340296,
        "imbalance_ratio": 2.0,
        "minority_fraction": 0.00036536353671903543,
        "n_classes": 2728,
        "normalized_entropy": 0.9998401250389878
      },
      "name": "leaf_code",
      "role": "metadata",
      "stats": {
        "n": 2737,
        "n_classes": 2728,
        "n_missing": 0,
        "top_classes": [
          {
            "count": 2,
            "name": "'GRD-T1477-MAC01-L500000.asd.txt'"
          },
          {
            "count": 2,
            "name": "'GRD-T1477-MAC01-L500001.asd.txt'"
          },
          {
            "count": 2,
            "name": "'GRD-T1477-MAC01-L500002.asd.txt'"
          },
          {
            "count": 2,
            "name": "CON_T83_JUN10_L400000"
          },
          {
            "count": 2,
            "name": "CON_T83_JUN10_L400001"
          },
          {
            "count": 2,
            "name": "CON_T83_JUN10_L400002"
          },
          {
            "count": 2,
            "name": "CON_T83_JUN10_L500000"
          },
          {
            "count": 2,
            "name": "CON_T83_JUN10_L500001"
          },
          {
            "count": 2,
            "name": "CON_T83_JUN10_L500002"
          },
          {
            "count": 1,
            "name": "CON_001_JAN21_L100000"
          },
          {
            "count": 1,
            "name": "CON-119-JAN21-L300002"
          },
          {
            "count": 1,
            "name": "CON-119-JAN21-L400000"
          },
          {
            "count": 1,
            "name": "CON-119-JAN21-L400001"
          },
          {
            "count": 1,
            "name": "CON-119-JAN21-L400002"
          },
          {
            "count": 1,
            "name": "CON-119-JAN21-L500000"
          },
          {
            "count": 1,
            "name": "CON-119-JAN21-L500001"
          },
          {
            "count": 1,
            "name": "CON-119-JAN21-L500002"
          },
          {
            "count": 1,
            "name": "CON-123-JAN22-L100000"
          },
          {
            "count": 1,
            "name": "CON-123-JAN22-L100001"
          },
          {
            "count": 1,
            "name": "CON-123-JAN22-L100002"
          }
        ]
      },
      "type": "categorical",
      "unit": null
    },
    {
      "assets": [],
      "balance": {
        "gini_simpson": 0.7863074508130841,
        "imbalance_ratio": 2.456140350877193,
        "minority_fraction": 0.1041286079649251,
        "n_classes": 5,
        "normalized_entropy": 0.9761492464242184
      },
      "name": "camera",
      "role": "metadata",
      "stats": {
        "n": 2737,
        "n_classes": 5,
        "n_missing": 0,
        "top_classes": [
          {
            "count": 700,
            "name": "Cam02"
          },
          {
            "count": 633,
            "name": "Cam01"
          },
          {
            "count": 597,
            "name": "Cam03"
          },
          {
            "count": 522,
            "name": "Cam04"
          },
          {
            "count": 285,
            "name": "Cam05"
          }
        ]
      },
      "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"
  ]
}