1
00:00:00,700 --> 00:00:04,810
Who studies alternate wetting and drying
in rice, where, and with whom?

2
00:00:05,462 --> 00:00:09,250
One request, and an agent maps
the whole field from OpenAlex.

3
00:00:10,682 --> 00:00:15,168
Then a second agent checks every
number, before anyone sees the page.

4
00:00:17,200 --> 00:00:20,447
AI for Research Efficiency.

5
00:00:20,497 --> 00:00:23,662
Episode 11:
map a research field with OpenAlex.

6
00:00:26,700 --> 00:00:30,293
Last time, an agent fetched
research data through APIs,

7
00:00:30,384 --> 00:00:33,052
starting with OpenAlex,
which needs no key.

8
00:00:33,809 --> 00:00:38,461
This time, one real run, from a
question to a checked map and a page:

9
00:00:38,893 --> 00:00:43,283
write the rules, let it estimate and
fetch, and check before you share.

10
00:00:46,100 --> 00:00:48,167
The rules go in an instruction file,

11
00:00:48,217 --> 00:00:52,209
as in episode 3: the question,
the source, and a budget.

12
00:00:53,049 --> 00:00:56,293
Without a key, OpenAlex gives
you 1,000 credits a day.

13
00:00:56,764 --> 00:01:00,419
A page of results costs 1;
a search costs 10.

14
00:01:00,870 --> 00:01:05,976
So the file says: stay under 300, and
estimate before paging through anything.

15
00:01:07,076 --> 00:01:09,059
It asks for scripts that re-run,

16
00:01:09,169 --> 00:01:12,353
and a log of every address it calls,
with what it cost.

17
00:01:13,321 --> 00:01:16,168
And it lists what to make:
works per year,

18
00:01:16,359 --> 00:01:20,730
the leading institutions and journals,
and who writes with whom in Arkansas.

19
00:01:24,500 --> 00:01:26,745
Then the request, and the run begins.

20
00:01:27,436 --> 00:01:31,725
The clock is the run's own:
7½ minutes, shown faster.

21
00:01:32,936 --> 00:01:35,522
First it reads OpenAlex's
guide for agents.

22
00:01:35,913 --> 00:01:39,230
Then it writes one small module
that every script shares:

23
00:01:39,561 --> 00:01:42,266
it logs each call,
and keeps each answer.

24
00:01:46,100 --> 00:01:50,208
Then one search defines the field:
alternate wetting and drying,

25
00:01:50,339 --> 00:01:55,588
or intermittent irrigation, or AWD,
together with rice or paddy.

26
00:01:56,746 --> 00:01:59,796
It finds 2,945 works.

27
00:02:00,268 --> 00:02:03,237
Before going on,
it reads 20 of them at random.

28
00:02:04,770 --> 00:02:07,053
All 20 are about rice and its water.

29
00:02:07,384 --> 00:02:11,639
About 13 are squarely on the practice,
and about 7 sit at the edge.

30
00:02:12,110 --> 00:02:15,114
So the search finds the field,
with a margin around it.

31
00:02:17,200 --> 00:02:20,364
Every answer states its cost,
so it counts as it goes.

32
00:02:20,834 --> 00:02:21,925
The counts by year,

33
00:02:22,036 --> 00:02:27,061
by institution and by journal are one
grouped search each: 10 credits apiece.

34
00:02:28,212 --> 00:02:30,558
A wrong field name
was refused for free.

35
00:02:30,969 --> 00:02:32,684
And to confirm each institution,

36
00:02:32,794 --> 00:02:35,480
it fetched single records,
which cost nothing.

37
00:02:38,900 --> 00:02:41,765
Works per year: 16 in 2000,

38
00:02:41,996 --> 00:02:46,283
65 in 2010, and 325 last year.

39
00:02:47,843 --> 00:02:49,765
The institutions that publish most:

40
00:02:50,156 --> 00:02:54,272
the International Rice Research Institute
leads, with 138.

41
00:02:54,723 --> 00:02:58,147
UC Davis is the only one in
the United States on the list.

42
00:02:59,447 --> 00:03:00,269
And the journals:

43
00:03:00,721 --> 00:03:04,450
Agricultural Water Management,
then Field Crops Research.

44
00:03:07,700 --> 00:03:10,306
For Arkansas,
it never filters by a name.

45
00:03:10,597 --> 00:03:13,654
It looks up each institution's
OpenAlex number first:

46
00:03:14,005 --> 00:03:17,673
11 records, from Fayetteville
to Stuttgart and Jonesboro.

47
00:03:18,993 --> 00:03:23,824
44 works have an author there:
1.5% of the field. 126 authors,

48
00:03:23,874 --> 00:03:27,121
and 501 pairs.

49
00:03:29,122 --> 00:03:32,784
Each dot is an author,
each line a paper written together.

50
00:03:33,174 --> 00:03:38,046
The agent sees two groups: the university
with the USDA unit in Jonesboro,

51
00:03:38,216 --> 00:03:41,937
on methane and water, and the
rice research center in Stuttgart.

52
00:03:46,000 --> 00:03:49,079
Before any check,
it writes down what looked wrong.

53
00:03:49,960 --> 00:03:53,184
Some researchers have two
or three OpenAlex profiles,

54
00:03:53,274 --> 00:03:54,726
so they appear more than once.

55
00:03:55,157 --> 00:03:57,490
One paper lists its
four authors twice,

56
00:03:57,720 --> 00:04:01,104
and the author with the Arkansas
address has no profile at all.

57
00:04:02,504 --> 00:04:04,186
And the last few years jump.

58
00:04:04,557 --> 00:04:08,371
The agent notes that more datasets
and repository records may be part of it,

59
00:04:08,542 --> 00:04:11,405
so recent years aren't comparable
with earlier ones.

60
00:04:14,900 --> 00:04:19,309
Then the checker: a second agent,
with its own script and its own calls,

61
00:04:19,360 --> 00:04:21,583
that doesn't reuse
the first one's code.

62
00:04:22,724 --> 00:04:28,007
Every count matched: 26 years,
16 institutions, 11 journals,

63
00:04:28,117 --> 00:04:33,019
the 44 works, and all 501 pairs,
rebuilt from scratch.

64
00:04:34,615 --> 00:04:39,424
It found one thing: the yearly counts
add up to 25 fewer than the total.

65
00:04:39,755 --> 00:04:44,182
Most likely, those works have no year.
The agent added that to its notes.

66
00:04:46,100 --> 00:04:49,793
Only then the page: four figures,
each with its query,

67
00:04:49,985 --> 00:04:52,673
the date of the data,
and the addresses to check it.

68
00:04:54,158 --> 00:04:55,499
It's on your computer for now.

69
00:04:55,750 --> 00:04:56,361
To share it,

70
00:04:56,411 --> 00:05:01,055
put the folder on GitHub and publish it
with Vercel, as in episodes 5 and 6.

71
00:05:05,200 --> 00:05:08,863
Read the map for what it is.
One search defines the field.

72
00:05:09,113 --> 00:05:12,746
The counts are OpenAlex's matches,
not a ranking of quality.

73
00:05:13,056 --> 00:05:14,957
And check any name you quote.

74
00:05:16,312 --> 00:05:21,319
The whole run: 7½ minutes, 47 calls,
and 112 credits of the day's 1,000.

75
00:05:21,369 --> 00:05:25,014
A free key gives 10 times as many.

76
00:05:26,800 --> 00:05:30,807
Pause here and try it: copy the
instruction file from the companion page,

77
00:05:30,938 --> 00:05:32,711
put in your own question and field,

78
00:05:32,821 --> 00:05:35,706
and read the checker's report
before you make the page.

79
00:05:38,800 --> 00:05:43,127
So: define the field with one search,
estimate before you page,

80
00:05:43,318 --> 00:05:46,663
keep the scripts, and check
every number before you share.

81
00:05:48,400 --> 00:05:51,602
Next: make a narrated
explainer of your paper.