candidates

Every statement both blind runs produced (3,819), with its full trail: script check → verifier verdict and reason → adjudicator ruling and reason → whether it is in the final set. Most rejections are duplicates between the two runs.

Data license: Not yet licensed — internal review only · Data source: Ahmed ElBatanony, Innopolis University

8 rows where app_id = "F1-005", run = "b" and verifier_verdict = "confirmed"

✎ View and edit SQL

This data as json, CSV (advanced)

Suggested facets: source_file

verifier_verdict 1

  • confirmed · 8 ✖

run 1

in_final_set 1

app_id 1

  • DeskcommCRM · 8 ✖

adjudicator 1

candidate_id ▼ app_id run statement excerpt source_url source_file script_check verifier_verdict verifier_reason verifier_correction adjudicator adjudicator_reason in_final_set
F1-005-B045 DeskcommCRM F1-005 b The system lets a user manage follow-ups for AI agents **Follow-ups** https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 01.txt passed confirmed     (not sent: confirmed)   1.0
F1-005-B046 DeskcommCRM F1-005 b The system lets a user manage routers for AI agents **Routers** https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt passed confirmed     (not sent: confirmed)   1.0
F1-005-B048 DeskcommCRM F1-005 b The system lets a user manage the memory of AI agents **Memory** https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt passed confirmed     (not sent: confirmed)   1.0
F1-005-B049 DeskcommCRM F1-005 b The system lets a user manage skills of AI agents **Skills** https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 01.txt passed confirmed     (not sent: confirmed)   1.0
F1-005-B050 DeskcommCRM F1-005 b The system lets a user view the runs of AI agents **Runs** https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt passed confirmed     (not sent: confirmed)   1.0
F1-005-B051 DeskcommCRM F1-005 b The system lets a user view AI usage and budget **Usage & budget** https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt passed confirmed     (not sent: confirmed)   1.0
F1-005-B052 DeskcommCRM F1-005 b The system lets a user view the health of a messaging connection, reconnect it and manage templates **Connections** (QR or Meta's official channel, with health, reconnect and templates) https://raw.githubusercontent.com/melgarafael/DeskcommCRM/HEAD/README.en.md 04.txt passed confirmed     (not sent: confirmed)   1.0
F1-005-B067 DeskcommCRM F1-005 b The system automatically identifies a customer’s history, orders and prior agreements when a message arrives Before any reply, the system already knows who this is: history, orders, what was agreed last time. https://deskcomm.com.br/en 02.txt passed confirmed     (not sent: confirmed)   1.0

Advanced export

JSON shape: default, array, newline-delimited, object

CSV options: 

CREATE TABLE [candidates] ([candidate_id] TEXT PRIMARY KEY, [app_id] TEXT, [run] TEXT, [statement] TEXT, [excerpt] TEXT, [source_url] TEXT, [source_file] TEXT, [script_check] TEXT, [verifier_verdict] TEXT, [verifier_reason] TEXT, [verifier_correction] TEXT, [adjudicator] TEXT, [adjudicator_reason] TEXT, [in_final_set] REAL, FOREIGN KEY ([app_id]) REFERENCES apps(app_id));
CREATE INDEX [idx_candidates_app_id] ON [candidates]([app_id]);
CREATE INDEX [idx_candidates_run] ON [candidates]([run]);
CREATE INDEX [idx_candidates_verifier_verdict] ON [candidates]([verifier_verdict]);
CREATE INDEX [idx_candidates_adjudicator] ON [candidates]([adjudicator]);