home / pub10

features

The final dataset: one capability statement per row, each with a verbatim excerpt of the archived documentation it rests on. This is release/features.csv.

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

form
user-action = 'The system lets …'; automation = 'The system automatically …'.
found_by
Which blind run's wording was kept (the other run may also have found it), or verifier/adjudicator for added capabilities.
verification
confirmed by the verifier; corrected (reworded); or added (missed by both runs).
pipeline_id
Link to the full pipeline record of this statement.
source_sha256
sha256 of the archived plain text the excerpt was checked against.
audited
1 if the row is in the 150-row blind audit sample.
audit_correct
Blind auditor's overall verdict (1 = acceptable as is).

1 row where app_id = "F2-043" and pipeline_id = "F2-043-A085" sorted by feature_id

✎ View and edit SQL

This data as json, CSV (advanced)

verification 1

  • confirmed 1

found_by 1

  • extract-a 1

form 1

  • automation 1

app_id 1

  • ServiceNow IT Service Management · 1 ✖

audit_correct 0

feature_id ▼ app_id statement form excerpt source_url source_file source_sha256 found_by found_by_runs verification pipeline_id audited audit_correct audit_note
F2-043-S081 ServiceNow IT Service Management F2-043 The system automatically interprets user intent in virtual agent conversations with natural language understanding automation ITSM Virtual Agent uses NLU to comprehend word meanings, recognize word contexts, and infer user or system actions https://www.servicenow.com/docs/api/khub/maps/eH2O6EPUpf09wX0~2cZBFg/topics/XxZcA6SBB8BHEbUbgssXEQ/content 13.txt 72fe2a0ac23718e888eaad483442bc52afd76abc0d61551427da52935781dc2a extract-a both confirmed The system automatically interprets user intent in virtual agent conversations with natural language understanding F2-043-A085 0.0    

Advanced export

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

CSV options:

CREATE TABLE [features] ([feature_id] TEXT PRIMARY KEY, [app_id] TEXT, [statement] TEXT, [form] TEXT, [excerpt] TEXT, [source_url] TEXT, [source_file] TEXT, [source_sha256] TEXT, [found_by] TEXT, [found_by_runs] TEXT, [verification] TEXT, [pipeline_id] TEXT, [audited] REAL, [audit_correct] REAL, [audit_note] TEXT, FOREIGN KEY ([app_id]) REFERENCES apps(app_id), FOREIGN KEY ([pipeline_id]) REFERENCES candidates(candidate_id));
CREATE INDEX [idx_features_app_id] ON [features]([app_id]);
CREATE INDEX [idx_features_verification] ON [features]([verification]);
CREATE INDEX [idx_features_form] ON [features]([form]);
CREATE INDEX [idx_features_found_by] ON [features]([found_by]);
Powered by Datasette · Queries took 1042.218ms · Data license: Not yet licensed — internal review only · Data source: Ahmed ElBatanony, Innopolis University