original.pdf docling.json layout_blocks.json layout_blocks.tsv layout_blocks.jsonl excluded_blocks.html excluded_blocks.tsv final_body_blocks.tsv visual_assets.tsv visual_assets.json
{
"blocks": 496,
"included_in_body": 61,
"gray_background_blocks": 21,
"framed_blocks": 106,
"by_role_guess": {
"page_header": 11,
"front_matter_heading": 4,
"title_candidate": 3,
"metadata": 4,
"affiliation": 23,
"front_matter_candidate": 3,
"body": 61,
"abstract_heading": 1,
"body_heading": 10,
"footnote": 2,
"page_footer": 1,
"visual_text": 75,
"unknown_text": 264,
"back_matter_heading": 2,
"body_candidate_excluded": 11,
"reference": 16,
"caption": 2,
"back_matter_text": 3
},
"by_docling_label": {
"page_header": 11,
"text": 461,
"section_header": 9,
"list_item": 6,
"footnote": 3,
"page_footer": 1,
"caption": 5
},
"by_body_decision_reason": {
"docling_page_header": 5,
"first_page_metadata": 6,
"first_page_front_matter_heading": 3,
"front_matter_author_line": 1,
"outside_body_flow_list_item": 1,
"first_page_author_or_affiliation": 1,
"front_matter_heading": 3,
"recovered_body_same_page_outside_flow": 1,
"recovered_body_outside_flow": 4,
"abstract_heading": 1,
"outside_body_flow": 1,
"first_page_summary": 1,
"body_heading": 2,
"docling_footnote": 1,
"body": 53,
"visual_text": 75,
"empty_after_cleaning": 9,
"recovered_unbound_docling_caption": 3,
"back_matter_heading": 1,
"after_back_matter_stop": 324
},
"visual_assets": {
"count": 6,
"indexable_count": 6,
"suppressed_count": 0,
"by_type": {
"figure": 6
},
"by_caption_source": {
"missing_caption": 6
},
"by_duplicate_reason": {
"": 6
},
"missing_caption_count": 6
}
}
{
"parsed_text_blocks": 496,
"final_body_blocks": 61,
"excluded_blocks": {
"count": 435,
"by_reason": {
"after_back_matter_stop": 324,
"visual_text": 75,
"empty_after_cleaning": 9,
"first_page_metadata": 6,
"docling_page_header": 5,
"first_page_front_matter_heading": 3,
"front_matter_heading": 3,
"body_heading": 2,
"abstract_heading": 1,
"back_matter_heading": 1,
"docling_footnote": 1,
"first_page_author_or_affiliation": 1,
"first_page_summary": 1,
"front_matter_author_line": 1,
"outside_body_flow": 1,
"outside_body_flow_list_item": 1
},
"by_role_guess": {
"unknown_text": 264,
"visual_text": 75,
"affiliation": 23,
"reference": 16,
"body_candidate_excluded": 11,
"page_header": 11,
"body_heading": 10,
"front_matter_heading": 4,
"metadata": 4,
"back_matter_text": 3,
"front_matter_candidate": 3,
"title_candidate": 3,
"back_matter_heading": 2,
"caption": 2,
"footnote": 2,
"abstract_heading": 1,
"page_footer": 1
},
"by_risk_level": {
"low": 414,
"medium": 21
},
"high_risk_count": 0,
"medium_risk_count": 21
},
"char_counts": {
"parsed_text_chars": 21173,
"final_body_chars": 3980,
"excluded_chars": 17193
}
}
{
"truncated": true,
"message": "Body extraction stopped at page 5 block #/texts/138: supplementary materials presents the operation voltages versus. 324 following text blocks were excluded as after_back_matter_stop.",
"stop_trigger": {
"ref": "#/texts/138",
"page": 5,
"layout_order": 171,
"role_guess": "back_matter_heading",
"body_decision_reason": "back_matter_heading",
"text_preview": "supplementary materials presents the operation voltages versus"
},
"first_truncated_block": {
"ref": "#/texts/139",
"page": 5,
"layout_order": 172,
"role_guess": "body_candidate_excluded",
"body_decision_reason": "after_back_matter_stop",
"text_preview": "speci fi c capacities of 2.0 wt% CoF2-coated sample (CF-2.0) and other four samples after 1st cycle and 100 th cycle, respectively. The initial discharge capacity of 236.0 mAh g \u0000 1 and operating potential of 3.444 V fo…"
},
"truncated_block_count": 324,
"truncated_pages": [
5,
6,
7,
8
],
"by_role_guess": {
"unknown_text": 255,
"affiliation": 21,
"reference": 16,
"body_candidate_excluded": 11,
"body_heading": 8,
"page_header": 6,
"back_matter_text": 3,
"caption": 2,
"back_matter_heading": 1,
"metadata": 1
}
}
Green = final body chunks. Orange/purple asset boxes = actual figure/table assets used by ingestion. Cyan dashed text boxes = text blocks consumed by those assets as caption continuations. Red STOP = truncation trigger. Red boxes = blocks after truncation.