f6b876fbe7
Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: XNLLLLH <XNLLLLH@users.noreply.github.com>
4 lines
495 B
JSON
4 lines
495 B
JSON
{"session": 0, "role": "user", "text": "The launch date is 2026-06-01.", "gold_fact": "2026-06-01"}
|
|
{"session": 1, "role": "user", "text": "Correction: launch moved to 2026-09-01.", "gold_fact": "2026-09-01", "contradicts_session": 0}
|
|
{"session": 2, "role": "user", "text": "What is the launch date?", "probe": "post_flip", "expects": "2026-09-01"}
|
|
{"session": 2, "role": "user", "text": "Quote the original June announcement verbatim.", "probe": "historical_verbatim", "expects": "2026-06-01"}
|