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 35 · DO #4202 · 182_Goodspeed_Bx2FF40_r

Collection
Thomas Harper Goodspeed (1887–1966) papers
Item/Folder
Sizov–Sproul, 1948–1957
Digital Object
DO #4202, page 35
Collection-level dates
1923–1963
Open PDF at page 35 ↗

Page transcription

Berkeley, California
February 7, 1955

Dr. Carl Skottsberg
c/o Dr. E. P. Reed
Valparaiso, Chile

Dear Carl:

It was good to have yours of the 18th which came last week but distressing to read of what has happened on Masatierra. What a disappointment but no one could have warned you in advance because there had been no one there for years who could have appreciated the extent to which the invaders, animal and vegetable, had transformed the island. Indeed, you are really the only botanist who knew intimately and appreciated the significance of the original endemics. I hope that Masafuera will prove to be more nearly intact and the burning less extensive than reported.

Pisano writes that he has talked with you about the paper on Chilean phyto-geography which I originally suggested as a joint project when he was a student here a good many years ago. He is a keen chap with more drive and initiative than most Chileans but not a trained botanist. He went ahead with a plant distribution map and a preliminary ms based largely on Reiche and what else was in the literature. Where he got some of the species he used I never could discover, many names were in synonymy and some species were not Chilean, indeed not even South American -- this last probably due to perpetuation of errors in the literature. He, apparently, has no idea of the amount of Chilean herbarium material in this country and abroad, most of it never commented upon in the literature.

As I saw it there were two alternatives: 1) to publish the map after a revision based on preliminary herbarium studies and evidence our South American Expeditions had obtained, with notes on the general floristic composition of each of the subdivisions shown on the map to give a picture of the unique variety of plant formations characteristic of Chile as a basis for future detailed studies by ourselves or others; 2) a thorough cataloging and critical evaluation of all available herbarium evidence followed by field work in subdivisions where such evidence is lacking of fragmentary -- there are some larger and many smaller and exceedingly interesting areas in Chile which are virtually unknown botanically, as you well know -- leading to as complete an interpretation as possible of the past and present floristic composition of either a less or more subdivided series of phytogeographic units.

I tested the importance and feasibility of this second alternative by taking one of our Senior Botanical Garden Botanists to Chile with me in 1951-52. He studied the coastal vegetation, with emphasis on cacti, from below Valparaiso to Prov. Antofagasta and got back eastward here and there. He also spent a short time in the Cord. Mahuelbuta. In advance of going to Chile he worked in most eastern U.S herbaria as well as ours on what had been collected, particularly on the northern coast. Both the field and herbarium evidence he got showed that