lllin000_PaperForge/scripts/dev/caption_pattern_analysis.json

{
  "summary": {
    "total_papers": 731,
    "papers_with_captions": 712,
    "papers_with_figure_map": 8,
    "total_caption_blocks": 5822,
    "errors": 0
  },
  "caption_role_breakdown": {
    "figure_caption": {
      "standard_numeric": 3952,
      "unclassified": 376,
      "letter_only": 7,
      "numeric_alpha": 25,
      "supplementary": 1,
      "appendix": 1
    },
    "figure_caption_candidate": {
      "unclassified": 1134,
      "standard_numeric": 307,
      "letter_only": 8,
      "numeric_alpha": 4,
      "supplementary": 5,
      "appendix": 2
    }
  },
  "pattern_distribution": {
    "standard_numeric": {
      "total": 4259,
      "with_figure_map": 44,
      "matched_in_inventory": 44,
      "unmatched_in_inventory": 0,
      "no_figure_map": 4215,
      "unmatched_rate": 0.0
    },
    "supplementary": {
      "total": 6,
      "with_figure_map": 0,
      "matched_in_inventory": 0,
      "unmatched_in_inventory": 0,
      "no_figure_map": 6,
      "unmatched_rate": null
    },
    "appendix": {
      "total": 3,
      "with_figure_map": 0,
      "matched_in_inventory": 0,
      "unmatched_in_inventory": 0,
      "no_figure_map": 3,
      "unmatched_rate": null
    },
    "letter_only": {
      "total": 15,
      "with_figure_map": 0,
      "matched_in_inventory": 0,
      "unmatched_in_inventory": 0,
      "no_figure_map": 15,
      "unmatched_rate": null
    },
    "numeric_alpha": {
      "total": 29,
      "with_figure_map": 0,
      "matched_in_inventory": 0,
      "unmatched_in_inventory": 0,
      "no_figure_map": 29,
      "unmatched_rate": null
    },
    "box": {
      "total": 0,
      "with_figure_map": 0,
      "matched_in_inventory": 0,
      "unmatched_in_inventory": 0,
      "no_figure_map": 0,
      "unmatched_rate": null
    },
    "unclassified": {
      "total": 1510,
      "with_figure_map": 15,
      "matched_in_inventory": 0,
      "unmatched_in_inventory": 15,
      "no_figure_map": 1495,
      "unmatched_rate": 1.0
    }
  },
  "examples_by_category": {
    "standard_numeric": [
      "Figure 1 Measurement of inferior osteophyte (O) and inferior joint distension (JD) on coronal image from magnetic resona",
      "Figure 3 shows a flow diagram of study enrollment. Between 2009 and 2014, 126 consecutive patients presented with clinic",
      "Figure 2 Compression of supraspinatus on sagittal images from magnetic resonance imaging scans: no contact (A), adjacent",
      "Figure 3 Flowchart of study enrollment. AC, acromioclavicular.",
      "FIGURE 1: The process of the OCD regeneration in rabbits. A: the OCD were generated by electric drill in the femoral pat"
    ],
    "unclassified": [
      "Source: own",
      "Source: own",
      "Source: own",
      "Source: own",
      "Source: own"
    ],
    "letter_only": [
      "Figure I. Diagram displaying the relationship between level of performance (response) and activity (dose) with performan",
      "Figure I. Search algorithm used to identify and screen studies to be included in the review of published literature.",
      "Figure I. PEMF modulates AMSC-derived exosomes in the incubator. PEMF = pulsed electromagnetic field; AMSC = adipose tis",
      "Figure I. Study flow diagram.",
      "Figure I. Schematic diagram of an indirect coupling system to stimulate in vitro cell cultures. (A) Configuration to app"
    ],
    "numeric_alpha": [
      "Figure 1A. International Cartilage Repair Society evaluation form showing the grid map of the knee. Published with permi",
      "Figure 1B. Anatomical grading of the depth of the cartilage injury according to the International Cartilage Repair Socie",
      "Fig. 2A–D (A) The inferior bony projection that looks like the heel of a shoe is shown in this diagram. This kind of spu",
      "Fig. 3A–B (A) The acromial spur is located at the lateral end of the acromion and is congruent with the acromial undersu",
      "Fig. 4A–C (A) The acromial spur is located at the lateral end of the acromion. It is not congruent with the acromial und"
    ],
    "supplementary": [
      "Figure 1a and Figure S2 (Supporting Information) show the fabrication process for the coiled PDA/CNT yarn (CPCY) that is",
      "(A) Cells in the HPCS are present across all profiled tumors. Fraction of cells that were mappable (y axis) from each tu",
      "Fig. S1. (A) Titration curve in potentiometric titration method. (B) Storage (G') and loss (G\") modulus of CS-2GNP sampl",
      "Fig. S2. (A) Macroscopic image of chitosan-stabilized gold nanoparticle (CS-GNP) solution (2% w/v GNP). (B) Transmission",
      "Figure S1. $ ^{13} $C NMR spectra (a) P-37, (b) L-37."
    ],
    "appendix": [
      "Figure A1. Odds ratios with CIs for the probability of a rotator cuff tear (full model). The bars represent 90% (dark bl",
      "Figure A2. Nomogram to predict the probability of a rotator cuff tear (full model). (A) I he values of a predictor varia",
      "Figure A3. Calibration curve for the fitted full model. Small vertical lines at the top of the graph denote the frequenc"
    ]
  },
  "unmatched_details": {
    "unclassified": [
      {
        "paper_id": "25K5KZAQ",
        "text_preview": "NMCH",
        "fig_number": null
      },
      {
        "paper_id": "25K5KZAQ",
        "text_preview": "BMCH",
        "fig_number": null
      },
      {
        "paper_id": "25K5KZAQ",
        "text_preview": "BMCH-TSPC",
        "fig_number": null
      },
      {
        "paper_id": "82W2IJIP",
        "text_preview": "Mechano-iontronic conversion in cartilage",
        "fig_number": null
      },
      {
        "paper_id": "PZ8B59K4",
        "text_preview": "ROC: receiver operating characteristic",
        "fig_number": null
      },
      {
        "paper_id": "PZ8B59K4",
        "text_preview": "ROC curve of each trained model",
        "fig_number": null
      },
      {
        "paper_id": "UBM39DTB",
        "text_preview": "subtypes. F The heat map depicted the relative abundance of DEGs in three tendinopathy subtypes. G Venn diagram of DEGs ",
        "fig_number": null
      },
      {
        "paper_id": "UBM39DTB",
        "text_preview": "tendinopathy subtypes (Hw, n = 35; Iw, n = 12; Ir, n = 16). G Representative HE images of diseased tendons from the thre",
        "fig_number": null
      },
      {
        "paper_id": "UBM39DTB",
        "text_preview": "1",
        "fig_number": null
      },
      {
        "paper_id": "UBM39DTB",
        "text_preview": "signal pathways with characteristic changes. The treatment recommendation is primarily directed towards specific subtype",
        "fig_number": null
      },
      {
        "paper_id": "XGT9Z257",
        "text_preview": "specificity, PPV and NPV calculated accordingly. d, Sensitivity of four subtypes (TAAD, TBAD, IMH and PAU) of AAS detect",
        "fig_number": null
      },
      {
        "paper_id": "XGT9Z257",
        "text_preview": "of the box indicate the 25th and 75th percentiles, respectively. The whiskers extend to 1.5 times the interquartile rang",
        "fig_number": null
      },
      {
        "paper_id": "XGT9Z257",
        "text_preview": "the performance of the original model and the upgraded model, respectively.\ne, Model performance metrics (AUC, accuracy,",
        "fig_number": null
      },
      {
        "paper_id": "XGT9Z257",
        "text_preview": "(n = 14,436 data samples). The error bars denote the two-sided 95% CI computed from 1,000 bootstrapping iterations. The ",
        "fig_number": null
      },
      {
        "paper_id": "XGT9Z257",
        "text_preview": "The features extracted from encoder are used for abnormal and normal classification. Decoder A and T are designed for th",
        "fig_number": null
      }
    ]
  },
  "prefix_variant_breakdown": {
    "Figure N": 2013,
    "Fig. N": 1826,
    "Fig N": 70,
    "Fig.N (no space)": 28,
    "Scheme N": 33,
    "Chinese 图 N": 23,
    "Figure A (letter only)": 11,
    "Figure S.N": 11,
    "Fig. S.N": 7,
    "Fig. A.N": 7,
    "Supplementary Figure": 3,
    "Figure A.N": 3,
    "Supplemental Figure": 0,
    "Suppl. Fig": 0,
    "Appendix Figure": 0,
    "Fig. A (letter only)": 0
  },
  "unclassified_sub_patterns": {
    "plain_text_no_number": 550,
    "short_label_under_5_chars": 276,
    "other_unclassified": 581,
    "schema_diagram": 61,
    "chinese_figure_图": 23,
    "fig_N_no_space": 28,
    "scheme_N": 33,
    "table_label": 13,
    "letter_subfigure_labels": 24,
    "short_trash_noise": 5
  }
}