← all runs · ← report

wi007_ui_tars_1_5_7b_native_wi004 (50 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)
calib_s100pausedfrozenirrelevant_motion=False response_window_ns=16000000000 scenario_seed=100 velocity_x_px_per_s=0valid6.20
calib_s101pausedfrozenirrelevant_motion=False response_window_ns=16000000000 scenario_seed=101 velocity_x_px_per_s=0not validsemantic_error6.23
calib_s102pausedfrozenirrelevant_motion=False response_window_ns=16000000000 scenario_seed=102 velocity_x_px_per_s=0valid6.00
calib_s103pausedfrozenirrelevant_motion=False response_window_ns=16000000000 scenario_seed=103 velocity_x_px_per_s=0valid6.46
calib_s104pausedfrozenirrelevant_motion=False response_window_ns=16000000000 scenario_seed=104 velocity_x_px_per_s=0valid6.29
calib_s105pausedfrozenirrelevant_motion=False response_window_ns=16000000000 scenario_seed=105 velocity_x_px_per_s=0valid6.21
calib_s106pausedfrozenirrelevant_motion=False response_window_ns=16000000000 scenario_seed=106 velocity_x_px_per_s=0valid5.71
calib_s107pausedfrozenirrelevant_motion=False response_window_ns=16000000000 scenario_seed=107 velocity_x_px_per_s=0valid6.22
calib_s108pausedfrozenirrelevant_motion=False response_window_ns=16000000000 scenario_seed=108 velocity_x_px_per_s=0valid6.61
calib_s109pausedfrozenirrelevant_motion=False response_window_ns=16000000000 scenario_seed=109 velocity_x_px_per_s=0valid6.23
live_v0_frozen_s300livefrozenirrelevant_motion=False response_window_ns=16000000000 scenario_seed=300 velocity_x_px_per_s=0not validsemantic_error6.24
live_v0_frozen_s301livefrozenirrelevant_motion=False response_window_ns=16000000000 scenario_seed=301 velocity_x_px_per_s=0valid6.31
live_v0_frozen_s302livefrozenirrelevant_motion=False response_window_ns=16000000000 scenario_seed=302 velocity_x_px_per_s=0valid6.24
live_v0_frozen_s303livefrozenirrelevant_motion=False response_window_ns=16000000000 scenario_seed=303 velocity_x_px_per_s=0valid6.24
live_v0_frozen_s304livefrozenirrelevant_motion=False response_window_ns=16000000000 scenario_seed=304 velocity_x_px_per_s=0valid6.24
live_v0_frozen_s305livefrozenirrelevant_motion=False response_window_ns=16000000000 scenario_seed=305 velocity_x_px_per_s=0valid6.39
live_v0_frozen_s306livefrozenirrelevant_motion=False response_window_ns=16000000000 scenario_seed=306 velocity_x_px_per_s=0not validsemantic_error6.24
live_v0_frozen_s307livefrozenirrelevant_motion=False response_window_ns=16000000000 scenario_seed=307 velocity_x_px_per_s=0not validsemantic_error6.33
live_v0_frozen_s308livefrozenirrelevant_motion=False response_window_ns=16000000000 scenario_seed=308 velocity_x_px_per_s=0valid5.94
live_v0_frozen_s309livefrozenirrelevant_motion=False response_window_ns=16000000000 scenario_seed=309 velocity_x_px_per_s=0valid6.24
live_v0_late_bind_s300livelate_bindirrelevant_motion=False response_window_ns=16000000000 scenario_seed=300 velocity_x_px_per_s=0not validsemantic_error6.19
live_v0_late_bind_s301livelate_bindirrelevant_motion=False response_window_ns=16000000000 scenario_seed=301 velocity_x_px_per_s=0valid6.25
live_v0_late_bind_s302livelate_bindirrelevant_motion=False response_window_ns=16000000000 scenario_seed=302 velocity_x_px_per_s=0valid6.18
live_v0_late_bind_s303livelate_bindirrelevant_motion=False response_window_ns=16000000000 scenario_seed=303 velocity_x_px_per_s=0valid6.18
live_v0_late_bind_s304livelate_bindirrelevant_motion=False response_window_ns=16000000000 scenario_seed=304 velocity_x_px_per_s=0valid6.17
live_v0_late_bind_s305livelate_bindirrelevant_motion=False response_window_ns=16000000000 scenario_seed=305 velocity_x_px_per_s=0valid6.33
live_v0_late_bind_s306livelate_bindirrelevant_motion=False response_window_ns=16000000000 scenario_seed=306 velocity_x_px_per_s=0not validsemantic_error6.17
live_v0_late_bind_s307livelate_bindirrelevant_motion=False response_window_ns=16000000000 scenario_seed=307 velocity_x_px_per_s=0not validsemantic_error6.25
live_v0_late_bind_s308livelate_bindirrelevant_motion=False response_window_ns=16000000000 scenario_seed=308 velocity_x_px_per_s=0valid5.88
live_v0_late_bind_s309livelate_bindirrelevant_motion=False response_window_ns=16000000000 scenario_seed=309 velocity_x_px_per_s=0valid6.18
live_v8_frozen_s300livefrozenirrelevant_motion=False response_window_ns=16000000000 scenario_seed=300 velocity_x_px_per_s=8not validsemantic_error6.76
live_v8_frozen_s301livefrozenirrelevant_motion=False response_window_ns=16000000000 scenario_seed=301 velocity_x_px_per_s=8not validoutdated_at_commitment6.01
live_v8_frozen_s302livefrozenirrelevant_motion=False response_window_ns=16000000000 scenario_seed=302 velocity_x_px_per_s=8not validoutdated_at_commitment6.31
live_v8_frozen_s303livefrozenirrelevant_motion=False response_window_ns=16000000000 scenario_seed=303 velocity_x_px_per_s=8not validoutdated_at_commitment6.16
live_v8_frozen_s304livefrozenirrelevant_motion=False response_window_ns=16000000000 scenario_seed=304 velocity_x_px_per_s=8not validoutdated_at_commitment6.01
live_v8_frozen_s305livefrozenirrelevant_motion=False response_window_ns=16000000000 scenario_seed=305 velocity_x_px_per_s=8not validsemantic_error6.31
live_v8_frozen_s306livefrozenirrelevant_motion=False response_window_ns=16000000000 scenario_seed=306 velocity_x_px_per_s=8not validsemantic_error6.91
live_v8_frozen_s307livefrozenirrelevant_motion=False response_window_ns=16000000000 scenario_seed=307 velocity_x_px_per_s=8not validoutdated_at_commitment6.39
live_v8_frozen_s308livefrozenirrelevant_motion=False response_window_ns=16000000000 scenario_seed=308 velocity_x_px_per_s=8not validoutdated_at_commitment6.38
live_v8_frozen_s309livefrozenirrelevant_motion=False response_window_ns=16000000000 scenario_seed=309 velocity_x_px_per_s=8not validsemantic_error6.16
live_v8_late_bind_s300livelate_bindirrelevant_motion=False response_window_ns=16000000000 scenario_seed=300 velocity_x_px_per_s=8not validsemantic_error6.70
live_v8_late_bind_s301livelate_bindirrelevant_motion=False response_window_ns=16000000000 scenario_seed=301 velocity_x_px_per_s=8valid5.95
live_v8_late_bind_s302livelate_bindirrelevant_motion=False response_window_ns=16000000000 scenario_seed=302 velocity_x_px_per_s=8valid6.25
live_v8_late_bind_s303livelate_bindirrelevant_motion=False response_window_ns=16000000000 scenario_seed=303 velocity_x_px_per_s=8valid6.10
live_v8_late_bind_s304livelate_bindirrelevant_motion=False response_window_ns=16000000000 scenario_seed=304 velocity_x_px_per_s=8valid5.95
live_v8_late_bind_s305livelate_bindirrelevant_motion=False response_window_ns=16000000000 scenario_seed=305 velocity_x_px_per_s=8not validsemantic_error6.25
live_v8_late_bind_s306livelate_bindirrelevant_motion=False response_window_ns=16000000000 scenario_seed=306 velocity_x_px_per_s=8not validsemantic_error6.85
live_v8_late_bind_s307livelate_bindirrelevant_motion=False response_window_ns=16000000000 scenario_seed=307 velocity_x_px_per_s=8valid6.32
live_v8_late_bind_s308livelate_bindirrelevant_motion=False response_window_ns=16000000000 scenario_seed=308 velocity_x_px_per_s=8valid6.32
live_v8_late_bind_s309livelate_bindirrelevant_motion=False response_window_ns=16000000000 scenario_seed=309 velocity_x_px_per_s=8not validsemantic_error6.10