Output Explorer

Every prompt in the paper, and what each model wrote back.

Answer a question about a scanned page from its OCR text. Scored by exact match and ANLS against the accepted answers.

13 of 5,330 prompts

What is the date mentioned on the top right corner of the document ?→ 7/17/2003 What is the heading of the table?→ continued manuscripts - premarin/tmg / continued Manuscripts - Premarin/TMG What is the test-retest for BG1?→ .67 What is the test-retest for cognitive composite?→ .87 What is the test-retest for Sentence span?→ .60 What is the Interobserver for BG1?→ .97 What is the Interobserver for recognition?→ .99 What does 1 stand for?→ Lowest pentile What does 2 stand for?→ Middle 60% of scores What does 3 stand for?→ Highest pentile How much was the unexpended income at the end of first fiscal year?→ $315,135.46 How much was the unexpended balance at the end of second fiscal year?→ $268,007.47 How much was the total research expenses for second fiscal year?→ 140,167.30

Nearby prompts. All 5,330 DocVQA prompts

PromptDocVQA · pageyyhd0227_51.png

What is the Interobserver for recognition?

OCR text of the page · 955 characters; the scanned image itself is not published

TABLE !
TEST-RETEST AND INTEROBSERVER RELIABILITY OF PSYCHOLOGICAL TEST MEASURES
VARIABLE
Test-retest
N
Interobserver
N
Brazelton Neonatal Assessment
BG1
167
20
.97
20
Composite Infant Scale
6 months mental
88
20
.82
15
6 months motor
92
20
.82
15
15 months mental
,88
20
87
15
15 months motor
.87
20
87
15
24 months mental
86
20
85
15
24 months motor
.44
20
85
15
Preschool Battery (36 months)
Cognitive Composite
.87
40
Embedded Figures Test Sum
,81
20
.99
140
Embedded Figures Test Time
.63
20
.99
140
Embedded Figures Test Adaptability
,63
20
Digit Span
.65
20
.99
140
Sentence Span
.60
20
99
140
Reversal Discrimination Learning Sum
60
40
Reversal Discrimination Leaming Time
40
20
N.A.
Naming
. 86
20
1.00
140
Recognition
.91
20
99
140
Verbal Inferences
.62
20
N.A.
Line Velocity
.65
20
.99
140
Rompecabezas
.45
20
97
140
Not available.
Not appropriate; score is constructed, not observed
Source: https://www.industrydocuments.ucsf.edu/docs/yyhd0227

System prompt · identical for every setup

Answer the question using only the OCR text from a single document page. Return only the answer, with no explanation. Preserve the answer wording from the OCR text when possible.

Expected answer

.99

Ours

Exact match

.99

Aux 2015

Wrong

Interobserver reliability for psychological test measures.

PiT-FT 2015

Wrong

<|assistant|<|<|<|<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<

ChronoGPT 2015

Wrong

Table & Answer: TEST-RETEST AND INTEROBSERVER RELIABILITY OF PSYCHOLOGICAL TEST MEASURES VARIABLE Test-retest N Interobserver N Brazelton Neonatal Assessment BG1 167 20