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

5 rows where adjudicator = "confirmed"

✎ View and edit SQL

This data as json, CSV (advanced)

verifier_verdict 2

run 1

  • b 5

in_final_set 1

adjudicator 1

  • confirmed · 5 ✖
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
F2-015-B003 Pipedrive F2-015 b The system automatically transcribes calls when a user holds a call. It records and transcribes your calls so you don’t have to. https://www.pipedrive.com/en/features 01.txt passed rejected duplicate of A002   confirmed Transcription is a distinct capability from recording, now that F2-015-A002 is narrowed to recording. 1.0
F2-031-B064 Salesforce Service Cloud F2-031 b The system automatically prioritizes tickets with AI It centralizes ticket management, automates routing, and uses AI to categorize, prioritize, and resolve simple issues automatically. https://www.salesforce.com/service/support-ticketing-tools-systems/ 09.txt passed corrected Form requires an automation statement without a missing trigger; kept as the separate prioritizing capability after A053 was narrowed to categorizing. The system automatically prioritizes tickets with AI confirmed The verifier's correction is identical to the original statement, which is supported and well formed as the separate prioritizing capability. 1.0
F2-043-B032 ServiceNow IT Service Management F2-043 b The system lets an agent manage the entire life cycle of requests Agents can also manage the entire life cycle of requests. https://www.servicenow.com/docs/api/khub/maps/eH2O6EPUpf09wX0~2cZBFg/topics/IuHkukKoSrzunmpTtJoRPA/content 06.txt passed rejected duplicate of F2-043-A008   confirmed Agent-side management of the request life cycle (06.txt line 82) differs from a user requesting catalog items in A008. 1.0
F2-043-B157 ServiceNow IT Service Management F2-043 b The system lets a user associate multiple impacted configuration items with a change You can associate multiple impacted CIs with a change. https://www.servicenow.com/docs/api/khub/maps/eH2O6EPUpf09wX0~2cZBFg/topics/uXk8LEj8iwoJoS8~QkyrIA/content 21.txt passed rejected duplicate of F2-043-A125   confirmed The source lists Impacted services/CIs as a separate related list from Affected CIs (21.txt lines 158-161), so this is a different capability from A125. 1.0
F2-067-B219 Givebutter F2-067 b The system lets a user log emails to a contact activity feed with a BCC or forwarding address How to log emails to a contact activity feed with BCC or forwarding address https://help.givebutter.com/en/collections/3094625-crm-donor-management 12.txt passed rejected duplicate of F2-067-A084   confirmed Logging any email through a BCC or forwarding address is a separate user capability from A084's automatic logging when the user emails from the contact profile. 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]);