Excluded Docling blocks

这里是差集:Docling 全量解析 text block 减去最终会进入正文的 block。优先人工检查 risk=high / medium。

layout_review.html excluded_blocks.json excluded_blocks.tsv final_body_blocks.tsv visual_assets.tsv original.pdf

Diff Summary

{
  "parsed_text_blocks": 65,
  "final_body_blocks": 23,
  "excluded_blocks": {
    "count": 42,
    "by_reason": {
      "inside_front_matter": 9,
      "outside_body_flow": 7,
      "body_heading": 6,
      "docling_page_footer": 5,
      "docling_page_header": 4,
      "non_body_heading": 3,
      "outside_body_flow_caption": 3,
      "before_body_started": 1,
      "docling_caption": 1,
      "first_page_metadata": 1,
      "front_matter_author_line": 1,
      "outside_body_flow_page_header": 1
    },
    "by_role_guess": {
      "unknown_text": 16,
      "body_heading": 8,
      "page_footer": 5,
      "page_header": 5,
      "caption": 4,
      "title_candidate": 2,
      "affiliation": 1,
      "metadata": 1
    },
    "by_risk_level": {
      "low": 26,
      "medium": 14,
      "high": 2
    },
    "high_risk_count": 2,
    "medium_risk_count": 14
  },
  "char_counts": {
    "parsed_text_chars": 2793,
    "final_body_chars": 1467,
    "excluded_chars": 1326
  }
}

Truncation

{
  "truncated": false,
  "message": "",
  "truncated_block_count": 0
}

Excluded Page Overlays

这些框显示被排除块,同时叠加真实图表资产框。青色虚线表示该 text block 被图表资产 caption 吸收;红色 STOP 是截断触发点,红色框是截断后被排除的块。

Page 1

Page 2

Page 3

Page 4

Page 5

Visual Assets

这是实际图表资产输出,不是审计层重新推断。

#typelabelpagecaption sourcesuppressedduplicate reasonrescue reasongroupconfidencebboxcaption
1figureDocling Figure 13missing_caption0.55[117.23, 280.23, 185.83, 134.34]
2figureDocling Figure 23missing_caption0.55[309.03, 278.19, 181.96, 137.67]
3figureDocling Figure 34missing_caption0.55[207.52, 107.51, 184.42, 138.46]
4figureDocling Figure 44missing_caption0.55[212.52, 282.61, 185.34, 140.19]

Excluded Blocks

riskpageorderlabelrolereasonparser reasonproduction usage truncbody regionregionbgbboxraw textcleaned text
high114textunknown_textinside_front_matterinside_front_matter
p1:body_region:0p1:page_body:right_crossing:white[255, 255, 255]
white
[130.74, 321.89, 350.91, 6.6]Mn L 2,3 -edge X-ray absorption spectroscopic studies on charge-discharge mechanism of Li 2 MnO 3Mn L 2,3 -edge X-ray absorption spectroscopic studies on charge-discharge mechanism of Li 2 MnO 3
high116textunknown_textinside_front_matterinside_front_matter
p1:body_region:0p1:page_body:right_crossing:white[255, 255, 255]
white
[130.74, 353.26, 345.56, 4.46]Direct observation of the structural and electronic changes of Li 2 MnO 3 during electron irradiationDirect observation of the structural and electronic changes of Li 2 MnO 3 during electron irradiation
medium12textunknown_textinside_front_matterinside_front_matter
p1:body_region:0p1:page_body:left:white[255, 255, 255]
white
[120.86, 127.82, 66.02, 4.46]Shiyou Li; Dan LeiShiyou Li; Dan Lei
medium13textunknown_textinside_front_matterinside_front_matter
p1:body_region:0p1:page_body:left:white[255, 255, 255]
white
[120.86, 142.01, 114.73, 3.83]AIP Conf. Proc. 1890, 040037 (2017)AIP Conf. Proc. 1890, 040037 (2017)
medium15textunknown_textoutside_body_flowoutside_body_flow
p1:body_region:0p1:page_body:right:colored[142, 187, 232]
colored
[445.09, 185.96, 29.05, 18.96]
medium16textunknown_textoutside_body_flowoutside_body_flow
p1:body_region:0p1:page_body:right:colored[0, 102, 204]
colored
[485.76, 185.96, 29.05, 18.96]
medium17textunknown_textoutside_body_flowoutside_body_flow
p1:body_region:0p1:page_body:right:colored[229, 239, 249]
colored
[449.62, 208.91, 19.98, 5.1]ViewView
medium18textunknown_textoutside_body_flowoutside_body_flow
p1:body_region:0p1:page_body:right:gray[235, 243, 251]
gray
[486.85, 208.91, 26.87, 5.1]ExportExport
medium19textunknown_textoutside_body_flowoutside_body_flow
p1:body_region:0p1:page_body:right:gray[236, 243, 251]
gray
[446.18, 218.21, 26.87, 5.1]OnlineOnline
medium110textunknown_textoutside_body_flowoutside_body_flow
p1:body_region:0p1:page_body:right:gray[239, 245, 251]
gray
[485.76, 218.21, 31.52, 5.1]CitationCitation
medium113textunknown_textinside_front_matterinside_front_matter
p1:body_region:0p1:page_body:left:gray[238, 238, 238]
gray
[130.74, 306.45, 93.78, 3.83]AIP Conf. Proc. (August 2018)AIP Conf. Proc. (August 2018)
medium115textunknown_textinside_front_matterinside_front_matter
p1:body_region:0p1:page_body:left:gray[240, 239, 239]
gray
[130.74, 337.83, 102.7, 3.83]Appl. Phys. Lett. (February 2014)Appl. Phys. Lett. (February 2014)
medium117textunknown_textinside_front_matterinside_front_matter
p1:body_region:0p1:page_body:left:gray[244, 244, 244]
gray
[130.74, 369.2, 108.9, 3.83]Appl. Phys. Lett. (September 2014)Appl. Phys. Lett. (September 2014)
medium219textunknown_textinside_front_matterinside_front_matter
p2:page_body:right_crossing:white[255, 255, 255]
white
[264.08, 290.72, 86.39, 10.54]!" # $ %%
medium220textaffiliationfront_matter_author_linefront_matter_author_line
p2:page_body:right_crossing:white[255, 255, 255]
white
[105.14, 318.0, 404.21, 37.57]& ' ( ) * $+ , -* * .' (( /.0 / 1+ 2 3 - - ( ( ( $+ , ( /+ - ( 4& ' ( ) * $+ , -* * .' (( /.0 / 1+ 2 3 - - ( ( ( $+ , ( /+ - ( 4
medium221textunknown_textoutside_body_flowoutside_body_flow
p2:page_body:left_crossing:white[255, 255, 255]
white
[105.14, 372.42, 249.1, 9.12]! " $+ , 5 , ' 5 '! " $+ , 5 , ' 5 '
low10textunknown_textbefore_body_startedbefore_body_started
p1:body_region:0p1:page_body:left_crossing:gray[219, 218, 218]
gray
[119.7, 76.1, 179.62, 4.46]RESEARCH ARTICLE | OCTOBER 05 2017RESEARCH ARTICLE | OCTOBER 05 2017
low11section_headertitle_candidatenon_body_headingnon_body_heading
p1:body_region:0p1:page_body:right_crossing:white[255, 255, 255]
white
[120.86, 89.96, 403.77, 29.35]Synthesis and electrochemical characterization of nanosized Li 2 MnO 3 cathode material for lithium ion batteriesSynthesis and electrochemical characterization of nanosized Li 2 MnO 3 cathode material for lithium ion batteries
low14textmetadatafirst_page_metadatafirst_page_metadata
p1:body_region:0p1:page_body:left:colored[230, 239, 249]
colored
[120.86, 153.05, 104.29, 3.83]https://doi.org/10.1063/1.5005239
low111section_headertitle_candidatenon_body_headingnon_body_heading
p1:body_region:0p1:page_body:left_crossing:white[255, 255, 255]
white
[129.58, 253.99, 164.87, 5.73]Articles You May Be Interested InArticles You May Be Interested In
low112textbody_headinginside_front_matterinside_front_matter
p1:body_region:0p1:page_body:right_crossing:white[255, 255, 255]
white
[130.74, 277.73, 377.63, 17.25]Synthesis and electrochemical properties of low-temperature synthesized Li 2 MnO 3 /MWCNT/super P as a high capacity cathode material for lithium ion batteriesSynthesis and electrochemical properties of low-temperature synthesized Li 2 MnO 3 /MWCNT/super P as a high capacity cathode material for lithium ion batteries
low118page_headerpage_headerdocling_page_headerdocling_page_header
p1:page_body:right:white[255, 255, 255]
white
[579.66, 381.4, 4.21, 79.2]12 July 2026 14:58:2212 July 2026 14:58:22
low222section_headerbody_headingnon_body_headingnon_body_heading
p2:page_body:right_crossing:white[255, 255, 255]
white
[262.28, 398.42, 90.58, 12.16]#$% &' $ #
low223page_headerpage_headeroutside_body_flow_page_headeroutside_body_flow_page_header
p2:page_body:right:white[255, 255, 255]
white
[570.66, 356.4, 4.21, 79.2]12 July 2026 14:58:2212 July 2026 14:58:22
low226section_headerbody_headingbody_headingbody_heading
p2:page_body:right_crossing:white[255, 255, 255]
white
[261.26, 559.4, 92.47, 12.16]() % #$
low228page_footerpage_footerdocling_page_footerdocling_page_footer
p2:bottom_margin:right_crossing:white[255, 255, 255]
white
[151.71, 730.57, 308.58, 22.57]2nd International Conference on Materials Science, Resource and Environmental Engineering (MSREE 2017) AIP Conf. Proc. 1890, 040037-1-040037-4; https://doi.org/10.1063/1.5005239 Published by AIP Publishing. 978-0-7354-1568-3/$30.002nd International Conference on Materials Science, Resource and Environmental Engineering (MSREE 2017) AIP Conf. Proc. 1890, 040037-1-040037-4;
low229page_footerpage_footerdocling_page_footerdocling_page_footer
p2:bottom_margin:right_crossing:white[255, 255, 255]
white
[286.83, 761.38, 38.33, 8.25]040037-1040037-1
low330section_headerbody_headingbody_headingbody_heading
p3:body_region:0p3:page_body:right_crossing:white[255, 255, 255]
white
[267.36, 100.18, 80.66, 12.16]* *
low333section_headerbody_headingbody_headingbody_heading
p3:body_region:0p3:page_body:right_crossing:white[255, 255, 255]
white
[233.04, 253.6, 149.14, 12.16]% ' $ #& & ' #
low334captioncaptionoutside_body_flow_captionoutside_body_flow_caption
p3:body_region:0p3:page_body:left_crossing:white[255, 255, 255]
white
[136.41, 420.07, 160.11, 9.12]+ ,'% -. @ ( $ @
low335captioncaptiondocling_captiondocling_caption
p3:body_region:0p3:page_body:right_crossing:white[255, 255, 255]
white
[296.38, 420.07, 183.92, 9.12]+ ,'% 2 ( $ @+ ,'% 2 ( $ @
low336page_headerpage_headerdocling_page_headerdocling_page_header
p3:page_body:right:white[255, 255, 255]
white
[570.66, 356.4, 4.21, 79.2]12 July 2026 14:58:2212 July 2026 14:58:22
low339page_footerpage_footerdocling_page_footerdocling_page_footer
p3:body_region:0p3:bottom_margin:right_crossing:white[255, 255, 255]
white
[286.83, 761.38, 38.33, 8.25]040037-2040037-2
low440captioncaptionoutside_body_flow_captionoutside_body_flow_caption
p4:body_region:0p4:page_body:right_crossing:white[255, 255, 255]
white
[201.55, 259.19, 213.42, 9.12]+ ,'% @ ( ( $ B ! $+ ,'% @ ( ( $ B ! $
low441captioncaptionoutside_body_flow_captionoutside_body_flow_caption
p4:body_region:0p4:page_body:right_crossing:white[255, 255, 255]
white
[187.32, 430.32, 241.85, 9.12]+ ,'% . - ( $ B ! $+ ,'% . - ( $ B ! $
low442page_headerpage_headerdocling_page_headerdocling_page_header
p4:page_body:right:white[255, 255, 255]
white
[570.66, 356.4, 4.21, 79.2]12 July 2026 14:58:2212 July 2026 14:58:22
low445page_footerpage_footerdocling_page_footerdocling_page_footer
p4:body_region:0p4:bottom_margin:right_crossing:white[255, 255, 255]
white
[286.83, 761.38, 38.33, 8.25]040037-3040037-3
low546section_headerbody_headingbody_headingbody_heading
p5:page_body:right_crossing:white[255, 255, 255]
white
[268.94, 100.05, 77.25, 12.16]# ' #
low548section_headerbody_headingbody_headingbody_heading
p5:page_body:right_crossing:white[255, 255, 255]
white
[245.12, 187.2, 124.78, 12.16]# / &, #$
low550section_headerbody_headingbody_headingbody_heading
p5:page_body:right_crossing:white[255, 255, 255]
white
[269.28, 253.46, 76.56, 12.16]% + % #
low563page_headerpage_headerdocling_page_headerdocling_page_header
p5:page_body:right:white[255, 255, 255]
white
[570.66, 356.4, 4.21, 79.2]12 July 2026 14:58:2212 July 2026 14:58:22
low564page_footerpage_footerdocling_page_footerdocling_page_footer
p5:bottom_margin:right_crossing:white[255, 255, 255]
white
[286.83, 761.38, 38.33, 8.25]040037-4040037-4