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 37 · DO #4713 · 231_Rogers_Bx4FF4_r

Collection
David James Rogers (1918–2007) papers
Item/Folder
N. Y. Botanical Garden - Math & Biology, 1964
Digital Object
DO #4713, page 37
Collection-level dates
1948–1977
Open PDF at page 37 ↗

Page transcription

While the processing of a taxonomic problem is essentially complete with the development of a key, we are seldom long satisfied with the work accomplished because modifications and additions to our knowledge of plants continue to accrue from many different areas. For these reasons, the chart indicates a "feed-back" at all levels. If one uses the classification of plants or animals in studies of evolution, one frequently finds information that will affect the classification, and may cause a shift in our concepts of the taxa in the classification. Similarly, ecological studies of the environmental factors affecting the taxa will give additional insights that may or may not change our classification. The constant improvement of classifications is an important work, not liable to reach a static stage. If we are to reflect the most modern thinking about organisms, and the recent investigations of the basic hereditary materials DNA and RNA are providing much insight into the relationships of organisms, we must find new methods to cope with the ever-increasing knowledge. Only by the application of mathematical models, coupled with a large-memory capacity computer, can we hope to successfully fulfill the mission of the taxonomist. It is to these problems that we address ourselves in The New York Botanical Garden.

Dr. Maguire: I have not been attached to this program although it is of interest to me. Dr. Steere has pointed out that the herbarium of The New York Botanical Garden is a large one. It holds about three million specimens. That is a lot of plant material. There are perhaps two other institutions in the U.S. with herbaria to compare with this one in New York. One is in Washington--the National Herbarium--and the other is at Harvard University--the combined Gray Herbarium and Arnold Arboretum Herbarium. Each of these three major institutions has about three million specimens. There are other institutions, many others. Missouri Botanical Garden has about one and a half million, and the Chicago Museum has about two million specimens. Philadelphia has about one million, and many universities, with the exception of Harvard which stands well above all the others, have large and very important herbaria. Altogether then in the major herbaria of the country, there are about 14 million specimens on record that would be of interest to work of this sort. In Europe this process has gone on much longer; there are more herbaria and larger. Perhaps the largest is at Kew with some six million specimens. Paris has five million, Leningrad five million and many have one, two, or three million specimens. The total reservoir runs into the tens of millions of specimens.

The herbarium is a collection of dried, pressed specimens. It is a collection of all kinds of plants. These specimens are arranged in a very efficient system. There are several systems that have developed during the last two or three hundred years which have resulted in the two or three primary systems that apply in the world today. These systems have evolved out of the use, the study and the understanding of relationship of the plants themselves. The system now is so developed that anyone who has a little information or knowledge can put his hand on any specimen that he chooses within just a few minutes.