Hunt Institute for Botanical Documentation
A Research Division of Carnegie Mellon University

Hunt Institute Archives Text Discovery Platform

Search a large and growing portion of our online collections, including handwritten documents.
PROTOTYPE

This prototype uses state-of-the-art artificial intelligence, including a vision-language model (VLM) capable of reading handwritten documents as well as typed and printed text, to create searchable transcriptions of digitized materials in the Hunt Institute Archives. This makes it possible to search the textual contents of individual pages, including material that may not be described in the archival catalog.

Use Keyword search for specific words, names, dates, scientific names, or phrases. Try Semantic search (experimental) to describe a topic, question, or kind of material when you do not know the exact wording used in the documents.

About the AI-generated transcriptions

The transcriptions are generated automatically from page images and may contain errors, especially with difficult handwriting, unusual names, multiple languages, image-quality problems, or complex layouts. They are intended primarily as a discovery aid rather than authoritative transcriptions.

Each result provides the generated transcription and links to the original digitized material and associated archival description so that readings can be checked against the source. The transcription workflow uses AI models run locally by the Hunt Institute.

About Keyword and Semantic search

Keyword search is the default and matches the wording in the transcriptions. Results contain all your terms. Use quotes for an exact phrase. Substring matching is supported, so aceae can find plant-family names ending in -aceae.

Semantic search (experimental) is useful when you know what kind of material you are looking for but do not know the words used in the documents. It ranks transcribed passages by similarity of meaning, so relevant results may not contain the exact words in your query.

Semantic queries can be broad research topics, descriptions of activities or relationships, or natural-language questions. For example:

Semantic search is not a chatbot: a question is used as a search query, and the system returns archival passages that appear conceptually related to it rather than generating an answer or summary. Short descriptions and ordinary research questions generally work better than lists of disconnected keywords. Quotation marks have no special meaning in Semantic mode. Cross-language matching may work in some cases, but it should not be treated as translation.

Keyword and Semantic search are complementary. Keyword search lets you require particular wording; Semantic search can surface differently worded passages about the same subject. Depending on the research question, trying both can reveal different useful material.

Open a result: use the prominent page-and-transcription link to see the metadata, PDF, and full transcription. Keyword-search terms are highlighted in the transcription.

Archives Collections Database (ArchivesSpace): the Collection, Item/Folder, and Digital Object links open the corresponding archival records. Collection-level dates describe the collection as a whole, not necessarily the specific item or page.

If a PDF does not load: on the detail page, use the Digital Object link, click “Go to file” in ArchivesSpace, and navigate to the page number shown here.

Current limitations
  • Automated transcriptions can contain missing or incorrect text or unintended repetition. Difficult handwriting, image quality, unusual layouts, and multiple languages can reduce accuracy. Always consult the original page image when an exact reading matters.
  • Semantic search remains experimental. Its rankings are an additional discovery aid, not a complete or definitive set of relevant results, and highly ranked pages can sometimes be only broadly related.
  • This is an active prototype. Search coverage, transcriptions, functionality, and the interface may continue to change as additional archival material is processed and the system is improved.

← Back to results

Page 30 · DO #4922 · 231_Rogers_Bx9FF4_r

Collection
David James Rogers (1918–2007) papers
Item/Folder
Manihot - Correspondence, 1962–1963
Digital Object
DO #4922, page 30
Collection-level dates
1948–1977
Open PDF at page 30 ↗

Page transcription

-2-

introductions that may come in, and decide whether you already have it or not.

On a separate subject, that of making collections of the plants as herbarium material. I would be very pleased to have collections from the Virgin Islands to compare with the material I have from Jamaica, Cuba and Trinidad. However, the process of making herbarium samples of cassava is quite a bit more complicated than for wild plant material, if you follow the same methods I have used, and evolved, over the years. Frankly, an ordinary herbarium specimen, with the usual type of specimen is not worth the paper it is attached to. You can decide whether it is worth it to you to follow my procedure, but I am sure that you will see the merit of the procedure, once you've been working with cassava variation. Many of the plants will not produce flowers, except under adverse conditions, and you can't wait until the flowers are produced, so you have to work the vegetative plants alone, sometimes. At any rate, I always include in my herbarium specimen a vegetative stem apex (about 6 inches long), with the young leaves attached, and preferably one leaf a bit more mature. Then, one mature vegetative leaf from farther down the stem, cutting off a section of the stem with the leaf for the specimen. Here, I always make a count of the numbers of lobes per leaf, and if there be variation on the same plant, but with one predominant number, I pick the most common representative. Then I make a long section of mature stem, about 1 foot long. I always take a long section of the root, cutting away both sides and leaving about 1/2 inch thick section of the most "typical" root, from point of attachment to the opposite end, through the center of the root. I usually tie the root section to the stem section to prevent the root from breaking, and then tag them with the same field number as the above-ground parts (the leaf, and the flower and fruit, if the latter are present). I have found it necessary to immerse the root and stem section in about 5 -10 percent formaldehyde for a couple of hours to prevent mold growth and to hasten drying.

You can see from the enclosed herbarium label the type of information I collect in the field. For color, I use the Mickerson Color Fan, put out by the Am. Hort. Council. This color fan sells for $6.00, and is really worth the money. This is the best way I know to standardize color designations though I will admit that any color comparison is liable to all sorts of interpretations. However, there may be a bit more objectivity in this technique.

I always made a black and white photograph of each cultivar that I make a specimen of--against a three-meter high backboard divided into thirds, and with a portion of the board marked off in subdivisions of meters 0.5 m., 0.1 m., etc. This is to reinforce the other information, and is quite helpful when examining the herbarium specimen. This may be eliminated if you are willing to record height, and branching pattern in detail as part of your field notes. I have found the photograph very useful, however, and invariably make an exposure to accompany any and all specimens of my own. Enclosed is a photo of one of my earlier photo-backboards. I modified this later, but don't have a spare photo to send you.

The herbarium specimen is also the document I used to keep information together concerning whatever analyses are made of the roots, or the leaves. This is, I find, an excellent way to keep your knowledge current. For example, I recently had analyses of 20 cultivars made for the amino acid content of the foliage. This work was done in hopes that the foliage may become significant as a protein-producing adjunct in tropical diets. The analysis of each of the cultivars is recorded on the specimen, as well as being the subject of paper we are at work on at the moment. I may place one reprint of this paper with the specimens, when the paper appears.

I would like to record on the specimens the time of maturation, cultural requirements where these are known, etc., but have never been able to work at a station long enough to get this type of agronomic, or horticultural, information. That's one reason why I hoped we might get together for a continuing project there in the Virgin Islands--under the aegis of the USDA, it might be possible to hold a set of experiments together long enough to gather yield data, fertilizer requirements, disease susceptibility, etc., etc.