Look at the following portion of a document split into blocks represented by [IDX: ...], where '...' is the block number in the document structure:
--------- Document portion -----------
{{ document_as_text }}
------- End of document portion -------

You must extract a JSON representation of the document structure, with titles and subtitles only.
Key guidelines:
1 - If there is any indication of items and sub-items in the analyzed portion, keep that in your response.
2 - This is MAYBE just an excerpt of the document whose edges (beginning and end) are unfinished parts of the same section. With that in mind, represent in the structure ONLY WHAT IS COMPLETE, leaving out the edges that look incomplete.
3 - When you include IDX in the response structure, pay CLOSE ATTENTION to indicate the correct IDX values for what is requested.
4 - Nest titles as far as they logically go. In that case, the final leaf subtitle must contain only the "idx_range" key, indicating there is no further nesting.
5 - When we show "idx_range" below, it is something like [0, 123], [540, 700], etc.

The JSON structure must be like this:
{
    "Title 1 ...": {
        "idx_range": [<start idx>, <end idx>], # This is the IDX (!!), not a page number in the text body. Pay attention!
        "Subtitle 1.1 ...": {
            "idx_range": [<start idx>, <end idx>],
            "Subtitle 1.1.1 ...": {"idx_range": [<start idx>, <end idx>]},
            "Subtitle 1.1.2 ...": {"idx_range": [<start idx>, <end idx>]}
        },
        "Subtitle 1.2 ...": {
            "idx_range": [<start idx>, <end idx>],
            "Subtitle 1.2.1 ...": {"idx_range": [<start idx>, <end idx>]},
            "Subtitle 1.2.2 ...": {"idx_range": [<start idx>, <end idx>]}
        },...etc
    },
    "Title 2 ...": {...etc},
    ...etc
}
ANSWER:
