jev-social-research

1# Social research with Jev
2 
3Jev is the decision layer, not the social-network client and not the report writer. Use
4your normal API, fetch or browser tool to collect evidence. Jev ranks discovered posts and,
5only after a locally checked evidence floor is met, judges whether a bounded projection of
6that evidence answers the question. You read the sources and write the report.
7 
8## A preview is not evidence
9 
10Track evidence depth explicitly. One source may carry more than one level:
11 
12| level | what was actually observed | what it can support |
13|---|---|---|
14| `discovery_card` | A search result, profile tile or feed preview. | Choosing what to open. Never cite a `discovery_card` in the report. |
15| `opened_post` | The canonical post page, visible author/date and post text or caption. | Claims made by the post author. |
16| `comments_read` | The opened reply thread, with the visible sample boundary recorded. | What those observed commenters said, not what all users think. |
17| `media_observed` | The video, image, transcript or frames were actually read or played. | Only the parts observed; a thumbnail or media URL is not this level. |
18 
19An empty search page means no accessible result was observed for that query. It does not
20prove that the topic has no discussion.
21 
22## Mandatory local gate before any Jev call
23 
24Apply this gate before constructing or serializing every outbound request:
25 
261. Mark the question, every tried or candidate query and every candidate field locally. A
27…