← all runs · ← report

wi007_ui_tars_1_5_7b_native_wi006 (40 trials; ByteDance-Seed/UI-TARS-1.5-7B)

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)
live_d2_harness_pending_s400liveharness_pendingeffect_delay_ns=2000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=400validdup 0
live_d2_harness_pending_s401liveharness_pendingeffect_delay_ns=2000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=401validdup 0
live_d2_harness_pending_s402liveharness_pendingeffect_delay_ns=2000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=402validdup 0
live_d2_harness_pending_s403liveharness_pendingeffect_delay_ns=2000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=403not validdup 0
live_d2_harness_pending_s404liveharness_pendingeffect_delay_ns=2000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=404not validdup 0
live_d2_harness_pending_s405liveharness_pendingeffect_delay_ns=2000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=405validdup 0
live_d2_harness_pending_s406liveharness_pendingeffect_delay_ns=2000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=406validdup 0
live_d2_harness_pending_s407liveharness_pendingeffect_delay_ns=2000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=407not validdup 0
live_d2_harness_pending_s408liveharness_pendingeffect_delay_ns=2000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=408not validdup 0
live_d2_harness_pending_s409liveharness_pendingeffect_delay_ns=2000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=409not validdup 0
live_d2_none_s400livenoneeffect_delay_ns=2000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=400validdup 0
live_d2_none_s401livenoneeffect_delay_ns=2000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=401validdup 0
live_d2_none_s402livenoneeffect_delay_ns=2000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=402validdup 0
live_d2_none_s403livenoneeffect_delay_ns=2000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=403not validdup 0
live_d2_none_s404livenoneeffect_delay_ns=2000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=404not validdup 0
live_d2_none_s405livenoneeffect_delay_ns=2000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=405validdup 0
live_d2_none_s406livenoneeffect_delay_ns=2000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=406validdup 0
live_d2_none_s407livenoneeffect_delay_ns=2000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=407not validdup 0
live_d2_none_s408livenoneeffect_delay_ns=2000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=408not validdup 0
live_d2_none_s409livenoneeffect_delay_ns=2000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=409not validdup 0
live_d8_harness_pending_s400liveharness_pendingeffect_delay_ns=8000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=400validdup 0
live_d8_harness_pending_s401liveharness_pendingeffect_delay_ns=8000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=401validdup 0
live_d8_harness_pending_s402liveharness_pendingeffect_delay_ns=8000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=402validdup 0
live_d8_harness_pending_s403liveharness_pendingeffect_delay_ns=8000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=403not validdup 0
live_d8_harness_pending_s404liveharness_pendingeffect_delay_ns=8000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=404not validdup 0
live_d8_harness_pending_s405liveharness_pendingeffect_delay_ns=8000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=405validdup 0
live_d8_harness_pending_s406liveharness_pendingeffect_delay_ns=8000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=406validdup 0
live_d8_harness_pending_s407liveharness_pendingeffect_delay_ns=8000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=407not validdup 0
live_d8_harness_pending_s408liveharness_pendingeffect_delay_ns=8000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=408not validdup 0
live_d8_harness_pending_s409liveharness_pendingeffect_delay_ns=8000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=409not validdup 0
live_d8_none_s400livenoneeffect_delay_ns=8000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=400validdup 0
live_d8_none_s401livenoneeffect_delay_ns=8000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=401not validdup 1
live_d8_none_s402livenoneeffect_delay_ns=8000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=402not validdup 1
live_d8_none_s403livenoneeffect_delay_ns=8000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=403not validdup 0
live_d8_none_s404livenoneeffect_delay_ns=8000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=404not validdup 0
live_d8_none_s405livenoneeffect_delay_ns=8000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=405not validdup 1
live_d8_none_s406livenoneeffect_delay_ns=8000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=406validdup 0
live_d8_none_s407livenoneeffect_delay_ns=8000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=407not validdup 0
live_d8_none_s408livenoneeffect_delay_ns=8000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=408not validdup 0
live_d8_none_s409livenoneeffect_delay_ns=8000000000 irrelevant_motion=False response_window_ns=16000000000 scenario_seed=409not validdup 0