← all runs · ← report

wi005_notification_p4 (160 trials; Qwen/Qwen3.8-27B)

One row per trial; click a trial for its frames, prompt, model responses and four-clock record. Results file: see data/.

trialconditionpolicy / memory / bindingcelloutcomelabelsB→D (s)
cal_s100_pausedpausedvlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=100valid5.28
cal_s101_pausedpausedvlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=101valid5.26
cal_s102_pausedpausedvlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=102valid5.26
cal_s103_pausedpausedvlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=103valid5.27
cal_s104_pausedpausedvlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=104valid5.26
cal_s105_pausedpausedvlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=105valid5.27
cal_s106_pausedpausedvlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=106valid5.27
cal_s107_pausedpausedvlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=107valid5.27
cal_s108_pausedpausedvlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=108valid5.27
cal_s109_pausedpausedvlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=109valid5.28
eval_w1000000000_s200_livelivevlm_directirrelevant_motion=False response_window_ns=1000000000 scenario_seed=200not validlate, outdated_at_commitment5.27
eval_w1000000000_s200_pausedpausedvlm_directirrelevant_motion=False response_window_ns=1000000000 scenario_seed=200valid5.24
eval_w1000000000_s200_replayreplayvlm_directirrelevant_motion=False response_window_ns=1000000000 scenario_seed=200valid5.24
eval_w1000000000_s201_livelivevlm_directirrelevant_motion=False response_window_ns=1000000000 scenario_seed=201not valid
eval_w1000000000_s201_pausedpausedvlm_directirrelevant_motion=False response_window_ns=1000000000 scenario_seed=201not valid
eval_w1000000000_s201_replayreplayvlm_directirrelevant_motion=False response_window_ns=1000000000 scenario_seed=201not valid
eval_w1000000000_s202_livelivevlm_directirrelevant_motion=False response_window_ns=1000000000 scenario_seed=202not validlate, outdated_at_commitment5.28
eval_w1000000000_s202_pausedpausedvlm_directirrelevant_motion=False response_window_ns=1000000000 scenario_seed=202valid5.25
eval_w1000000000_s202_replayreplayvlm_directirrelevant_motion=False response_window_ns=1000000000 scenario_seed=202valid5.25
eval_w1000000000_s203_livelivevlm_directirrelevant_motion=False response_window_ns=1000000000 scenario_seed=203not validlate, outdated_at_commitment5.28
eval_w1000000000_s203_pausedpausedvlm_directirrelevant_motion=False response_window_ns=1000000000 scenario_seed=203valid5.25
eval_w1000000000_s203_replayreplayvlm_directirrelevant_motion=False response_window_ns=1000000000 scenario_seed=203valid5.25
eval_w1000000000_s204_livelivevlm_directirrelevant_motion=False response_window_ns=1000000000 scenario_seed=204not validlate, outdated_at_commitment5.28
eval_w1000000000_s204_pausedpausedvlm_directirrelevant_motion=False response_window_ns=1000000000 scenario_seed=204valid5.25
eval_w1000000000_s204_replayreplayvlm_directirrelevant_motion=False response_window_ns=1000000000 scenario_seed=204valid5.25
eval_w1000000000_s205_livelivevlm_directirrelevant_motion=False response_window_ns=1000000000 scenario_seed=205not validlate, outdated_at_commitment5.29
eval_w1000000000_s205_pausedpausedvlm_directirrelevant_motion=False response_window_ns=1000000000 scenario_seed=205valid5.26
eval_w1000000000_s205_replayreplayvlm_directirrelevant_motion=False response_window_ns=1000000000 scenario_seed=205valid5.26
eval_w1000000000_s206_livelivevlm_directirrelevant_motion=False response_window_ns=1000000000 scenario_seed=206not valid
eval_w1000000000_s206_pausedpausedvlm_directirrelevant_motion=False response_window_ns=1000000000 scenario_seed=206not valid
eval_w1000000000_s206_replayreplayvlm_directirrelevant_motion=False response_window_ns=1000000000 scenario_seed=206not valid
eval_w1000000000_s207_livelivevlm_directirrelevant_motion=False response_window_ns=1000000000 scenario_seed=207not validlate, outdated_at_commitment5.29
eval_w1000000000_s207_pausedpausedvlm_directirrelevant_motion=False response_window_ns=1000000000 scenario_seed=207valid5.25
eval_w1000000000_s207_replayreplayvlm_directirrelevant_motion=False response_window_ns=1000000000 scenario_seed=207valid5.25
eval_w1000000000_s208_livelivevlm_directirrelevant_motion=False response_window_ns=1000000000 scenario_seed=208not validlate, outdated_at_commitment5.29
eval_w1000000000_s208_pausedpausedvlm_directirrelevant_motion=False response_window_ns=1000000000 scenario_seed=208valid5.25
eval_w1000000000_s208_replayreplayvlm_directirrelevant_motion=False response_window_ns=1000000000 scenario_seed=208valid5.25
eval_w1000000000_s209_livelivevlm_directirrelevant_motion=False response_window_ns=1000000000 scenario_seed=209not validlate, outdated_at_commitment5.29
eval_w1000000000_s209_pausedpausedvlm_directirrelevant_motion=False response_window_ns=1000000000 scenario_seed=209valid5.25
eval_w1000000000_s209_replayreplayvlm_directirrelevant_motion=False response_window_ns=1000000000 scenario_seed=209valid5.25
eval_w16000000000_s200_livelivevlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=200valid5.25
eval_w16000000000_s200_pausedpausedvlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=200valid5.25
eval_w16000000000_s200_replayreplayvlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=200valid5.25
eval_w16000000000_s201_livelivevlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=201valid5.41
eval_w16000000000_s201_pausedpausedvlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=201not valid
eval_w16000000000_s201_replayreplayvlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=201valid5.43
eval_w16000000000_s202_livelivevlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=202valid5.26
eval_w16000000000_s202_pausedpausedvlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=202valid5.25
eval_w16000000000_s202_replayreplayvlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=202valid5.27
eval_w16000000000_s203_livelivevlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=203valid5.25
eval_w16000000000_s203_pausedpausedvlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=203valid5.25
eval_w16000000000_s203_replayreplayvlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=203valid5.25
eval_w16000000000_s204_livelivevlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=204valid5.26
eval_w16000000000_s204_pausedpausedvlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=204valid5.26
eval_w16000000000_s204_replayreplayvlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=204valid5.27
eval_w16000000000_s205_livelivevlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=205valid5.26
eval_w16000000000_s205_pausedpausedvlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=205valid5.25
eval_w16000000000_s205_replayreplayvlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=205valid5.26
eval_w16000000000_s206_livelivevlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=206valid5.44
eval_w16000000000_s206_pausedpausedvlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=206not valid
eval_w16000000000_s206_replayreplayvlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=206valid5.42
eval_w16000000000_s207_livelivevlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=207valid5.28
eval_w16000000000_s207_pausedpausedvlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=207valid5.25
eval_w16000000000_s207_replayreplayvlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=207valid5.25
eval_w16000000000_s208_livelivevlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=208valid5.25
eval_w16000000000_s208_pausedpausedvlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=208valid5.25
eval_w16000000000_s208_replayreplayvlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=208valid5.25
eval_w16000000000_s209_livelivevlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=209valid5.25
eval_w16000000000_s209_pausedpausedvlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=209valid5.25
eval_w16000000000_s209_replayreplayvlm_directirrelevant_motion=False response_window_ns=16000000000 scenario_seed=209valid5.25
eval_w2000000000_s200_livelivevlm_directirrelevant_motion=False response_window_ns=2000000000 scenario_seed=200not validlate, outdated_at_commitment5.25
eval_w2000000000_s200_pausedpausedvlm_directirrelevant_motion=False response_window_ns=2000000000 scenario_seed=200valid5.25
eval_w2000000000_s200_replayreplayvlm_directirrelevant_motion=False response_window_ns=2000000000 scenario_seed=200valid5.25
eval_w2000000000_s201_livelivevlm_directirrelevant_motion=False response_window_ns=2000000000 scenario_seed=201not valid
eval_w2000000000_s201_pausedpausedvlm_directirrelevant_motion=False response_window_ns=2000000000 scenario_seed=201not valid
eval_w2000000000_s201_replayreplayvlm_directirrelevant_motion=False response_window_ns=2000000000 scenario_seed=201not valid
eval_w2000000000_s202_livelivevlm_directirrelevant_motion=False response_window_ns=2000000000 scenario_seed=202not validlate, outdated_at_commitment5.25
eval_w2000000000_s202_pausedpausedvlm_directirrelevant_motion=False response_window_ns=2000000000 scenario_seed=202valid5.24
eval_w2000000000_s202_replayreplayvlm_directirrelevant_motion=False response_window_ns=2000000000 scenario_seed=202valid5.25
eval_w2000000000_s203_livelivevlm_directirrelevant_motion=False response_window_ns=2000000000 scenario_seed=203not validlate, outdated_at_commitment5.25
eval_w2000000000_s203_pausedpausedvlm_directirrelevant_motion=False response_window_ns=2000000000 scenario_seed=203valid5.25
eval_w2000000000_s203_replayreplayvlm_directirrelevant_motion=False response_window_ns=2000000000 scenario_seed=203valid5.25
eval_w2000000000_s204_livelivevlm_directirrelevant_motion=False response_window_ns=2000000000 scenario_seed=204not validlate, outdated_at_commitment5.25
eval_w2000000000_s204_pausedpausedvlm_directirrelevant_motion=False response_window_ns=2000000000 scenario_seed=204valid5.25
eval_w2000000000_s204_replayreplayvlm_directirrelevant_motion=False response_window_ns=2000000000 scenario_seed=204valid5.24
eval_w2000000000_s205_livelivevlm_directirrelevant_motion=False response_window_ns=2000000000 scenario_seed=205not validlate, outdated_at_commitment5.26
eval_w2000000000_s205_pausedpausedvlm_directirrelevant_motion=False response_window_ns=2000000000 scenario_seed=205valid5.25
eval_w2000000000_s205_replayreplayvlm_directirrelevant_motion=False response_window_ns=2000000000 scenario_seed=205valid5.25
eval_w2000000000_s206_livelivevlm_directirrelevant_motion=False response_window_ns=2000000000 scenario_seed=206not validlate, outdated_at_commitment5.41
eval_w2000000000_s206_pausedpausedvlm_directirrelevant_motion=False response_window_ns=2000000000 scenario_seed=206not valid
eval_w2000000000_s206_replayreplayvlm_directirrelevant_motion=False response_window_ns=2000000000 scenario_seed=206valid5.42
eval_w2000000000_s207_livelivevlm_directirrelevant_motion=False response_window_ns=2000000000 scenario_seed=207not validlate, outdated_at_commitment5.26
eval_w2000000000_s207_pausedpausedvlm_directirrelevant_motion=False response_window_ns=2000000000 scenario_seed=207valid5.25
eval_w2000000000_s207_replayreplayvlm_directirrelevant_motion=False response_window_ns=2000000000 scenario_seed=207valid5.25
eval_w2000000000_s208_livelivevlm_directirrelevant_motion=False response_window_ns=2000000000 scenario_seed=208not validlate, outdated_at_commitment5.25
eval_w2000000000_s208_pausedpausedvlm_directirrelevant_motion=False response_window_ns=2000000000 scenario_seed=208valid5.25
eval_w2000000000_s208_replayreplayvlm_directirrelevant_motion=False response_window_ns=2000000000 scenario_seed=208valid5.25
eval_w2000000000_s209_livelivevlm_directirrelevant_motion=False response_window_ns=2000000000 scenario_seed=209not validlate, outdated_at_commitment5.26
eval_w2000000000_s209_pausedpausedvlm_directirrelevant_motion=False response_window_ns=2000000000 scenario_seed=209valid5.25
eval_w2000000000_s209_replayreplayvlm_directirrelevant_motion=False response_window_ns=2000000000 scenario_seed=209valid5.24
eval_w4000000000_s200_livelivevlm_directirrelevant_motion=False response_window_ns=4000000000 scenario_seed=200not validlate, outdated_at_commitment5.24
eval_w4000000000_s200_pausedpausedvlm_directirrelevant_motion=False response_window_ns=4000000000 scenario_seed=200valid5.26
eval_w4000000000_s200_replayreplayvlm_directirrelevant_motion=False response_window_ns=4000000000 scenario_seed=200valid5.27
eval_w4000000000_s201_livelivevlm_directirrelevant_motion=False response_window_ns=4000000000 scenario_seed=201not validlate, outdated_at_commitment5.41
eval_w4000000000_s201_pausedpausedvlm_directirrelevant_motion=False response_window_ns=4000000000 scenario_seed=201not valid
eval_w4000000000_s201_replayreplayvlm_directirrelevant_motion=False response_window_ns=4000000000 scenario_seed=201valid5.42
eval_w4000000000_s202_livelivevlm_directirrelevant_motion=False response_window_ns=4000000000 scenario_seed=202not validlate, outdated_at_commitment5.26
eval_w4000000000_s202_pausedpausedvlm_directirrelevant_motion=False response_window_ns=4000000000 scenario_seed=202valid5.24
eval_w4000000000_s202_replayreplayvlm_directirrelevant_motion=False response_window_ns=4000000000 scenario_seed=202valid5.25
eval_w4000000000_s203_livelivevlm_directirrelevant_motion=False response_window_ns=4000000000 scenario_seed=203not validlate, outdated_at_commitment5.25
eval_w4000000000_s203_pausedpausedvlm_directirrelevant_motion=False response_window_ns=4000000000 scenario_seed=203valid5.26
eval_w4000000000_s203_replayreplayvlm_directirrelevant_motion=False response_window_ns=4000000000 scenario_seed=203valid5.25
eval_w4000000000_s204_livelivevlm_directirrelevant_motion=False response_window_ns=4000000000 scenario_seed=204not validlate, outdated_at_commitment5.26
eval_w4000000000_s204_pausedpausedvlm_directirrelevant_motion=False response_window_ns=4000000000 scenario_seed=204valid5.26
eval_w4000000000_s204_replayreplayvlm_directirrelevant_motion=False response_window_ns=4000000000 scenario_seed=204valid5.25
eval_w4000000000_s205_livelivevlm_directirrelevant_motion=False response_window_ns=4000000000 scenario_seed=205not validlate, outdated_at_commitment5.26
eval_w4000000000_s205_pausedpausedvlm_directirrelevant_motion=False response_window_ns=4000000000 scenario_seed=205valid5.27
eval_w4000000000_s205_replayreplayvlm_directirrelevant_motion=False response_window_ns=4000000000 scenario_seed=205valid5.25
eval_w4000000000_s206_livelivevlm_directirrelevant_motion=False response_window_ns=4000000000 scenario_seed=206not validlate, outdated_at_commitment5.42
eval_w4000000000_s206_pausedpausedvlm_directirrelevant_motion=False response_window_ns=4000000000 scenario_seed=206not valid
eval_w4000000000_s206_replayreplayvlm_directirrelevant_motion=False response_window_ns=4000000000 scenario_seed=206not valid
eval_w4000000000_s207_livelivevlm_directirrelevant_motion=False response_window_ns=4000000000 scenario_seed=207not validlate, outdated_at_commitment5.25
eval_w4000000000_s207_pausedpausedvlm_directirrelevant_motion=False response_window_ns=4000000000 scenario_seed=207valid5.25
eval_w4000000000_s207_replayreplayvlm_directirrelevant_motion=False response_window_ns=4000000000 scenario_seed=207valid5.25
eval_w4000000000_s208_livelivevlm_directirrelevant_motion=False response_window_ns=4000000000 scenario_seed=208not validlate, outdated_at_commitment5.26
eval_w4000000000_s208_pausedpausedvlm_directirrelevant_motion=False response_window_ns=4000000000 scenario_seed=208valid5.25
eval_w4000000000_s208_replayreplayvlm_directirrelevant_motion=False response_window_ns=4000000000 scenario_seed=208valid5.25
eval_w4000000000_s209_livelivevlm_directirrelevant_motion=False response_window_ns=4000000000 scenario_seed=209not validlate, outdated_at_commitment5.25
eval_w4000000000_s209_pausedpausedvlm_directirrelevant_motion=False response_window_ns=4000000000 scenario_seed=209valid5.25
eval_w4000000000_s209_replayreplayvlm_directirrelevant_motion=False response_window_ns=4000000000 scenario_seed=209valid5.25
eval_w8000000000_s200_livelivevlm_directirrelevant_motion=False response_window_ns=8000000000 scenario_seed=200valid5.26
eval_w8000000000_s200_pausedpausedvlm_directirrelevant_motion=False response_window_ns=8000000000 scenario_seed=200valid5.25
eval_w8000000000_s200_replayreplayvlm_directirrelevant_motion=False response_window_ns=8000000000 scenario_seed=200valid5.25
eval_w8000000000_s201_livelivevlm_directirrelevant_motion=False response_window_ns=8000000000 scenario_seed=201valid5.42
eval_w8000000000_s201_pausedpausedvlm_directirrelevant_motion=False response_window_ns=8000000000 scenario_seed=201not valid
eval_w8000000000_s201_replayreplayvlm_directirrelevant_motion=False response_window_ns=8000000000 scenario_seed=201valid5.43
eval_w8000000000_s202_livelivevlm_directirrelevant_motion=False response_window_ns=8000000000 scenario_seed=202valid5.25
eval_w8000000000_s202_pausedpausedvlm_directirrelevant_motion=False response_window_ns=8000000000 scenario_seed=202valid5.27
eval_w8000000000_s202_replayreplayvlm_directirrelevant_motion=False response_window_ns=8000000000 scenario_seed=202valid5.25
eval_w8000000000_s203_livelivevlm_directirrelevant_motion=False response_window_ns=8000000000 scenario_seed=203valid5.26
eval_w8000000000_s203_pausedpausedvlm_directirrelevant_motion=False response_window_ns=8000000000 scenario_seed=203valid5.25
eval_w8000000000_s203_replayreplayvlm_directirrelevant_motion=False response_window_ns=8000000000 scenario_seed=203valid5.25
eval_w8000000000_s204_livelivevlm_directirrelevant_motion=False response_window_ns=8000000000 scenario_seed=204valid5.26
eval_w8000000000_s204_pausedpausedvlm_directirrelevant_motion=False response_window_ns=8000000000 scenario_seed=204valid5.28
eval_w8000000000_s204_replayreplayvlm_directirrelevant_motion=False response_window_ns=8000000000 scenario_seed=204valid5.25
eval_w8000000000_s205_livelivevlm_directirrelevant_motion=False response_window_ns=8000000000 scenario_seed=205valid5.26
eval_w8000000000_s205_pausedpausedvlm_directirrelevant_motion=False response_window_ns=8000000000 scenario_seed=205valid5.25
eval_w8000000000_s205_replayreplayvlm_directirrelevant_motion=False response_window_ns=8000000000 scenario_seed=205valid5.25
eval_w8000000000_s206_livelivevlm_directirrelevant_motion=False response_window_ns=8000000000 scenario_seed=206valid5.42
eval_w8000000000_s206_pausedpausedvlm_directirrelevant_motion=False response_window_ns=8000000000 scenario_seed=206not valid
eval_w8000000000_s206_replayreplayvlm_directirrelevant_motion=False response_window_ns=8000000000 scenario_seed=206valid5.42
eval_w8000000000_s207_livelivevlm_directirrelevant_motion=False response_window_ns=8000000000 scenario_seed=207valid5.25
eval_w8000000000_s207_pausedpausedvlm_directirrelevant_motion=False response_window_ns=8000000000 scenario_seed=207valid5.27
eval_w8000000000_s207_replayreplayvlm_directirrelevant_motion=False response_window_ns=8000000000 scenario_seed=207valid5.25
eval_w8000000000_s208_livelivevlm_directirrelevant_motion=False response_window_ns=8000000000 scenario_seed=208valid5.26
eval_w8000000000_s208_pausedpausedvlm_directirrelevant_motion=False response_window_ns=8000000000 scenario_seed=208valid5.25
eval_w8000000000_s208_replayreplayvlm_directirrelevant_motion=False response_window_ns=8000000000 scenario_seed=208valid5.25
eval_w8000000000_s209_livelivevlm_directirrelevant_motion=False response_window_ns=8000000000 scenario_seed=209valid5.25
eval_w8000000000_s209_pausedpausedvlm_directirrelevant_motion=False response_window_ns=8000000000 scenario_seed=209valid5.26
eval_w8000000000_s209_replayreplayvlm_directirrelevant_motion=False response_window_ns=8000000000 scenario_seed=209valid5.26