{
  "catalog_id": 18,
  "title": "Agitated phone caller drifts into the traffic corridor",
  "source_template": "police",
  "summary": "Counterfactual proposal: an adult argues on a handheld phone while pacing on the south sidewalk. Distracted gestures become an unintentional step into the road, followed by short pacing within ego's corridor. The call continues and the caller remains partly in the corridor at 40 s, so ego never resumes.",
  "focus_xy": [
    33.6,
    -0.1
  ],
  "initial_review_time_s": 4,
  "ego_stop_x_m": 12,
  "ego_release_s": -1,
  "events": [
    {
      "time_s": -7,
      "label": "Caller paces on the south sidewalk while arguing into a phone"
    },
    {
      "time_s": -2,
      "label": "Caller turns toward the roadway without ending the call"
    },
    {
      "time_s": 0,
      "label": "An emphatic free-hand gesture accompanies an unintended step off the curb"
    },
    {
      "time_s": 4,
      "label": "Caller reaches deep into the ego corridor"
    },
    {
      "time_s": 6,
      "label": "Caller turns east while still occupying the corridor"
    },
    {
      "time_s": 11,
      "label": "Caller stops pacing and gestures emphatically again"
    },
    {
      "time_s": 14,
      "label": "Caller turns partly back toward the south curb"
    },
    {
      "time_s": 17,
      "label": "Short retreat ends before the caller clears the traffic corridor"
    },
    {
      "time_s": 40,
      "label": "Argument continues in a stable lane obstruction; ego remains stopped"
    }
  ],
  "actors": [
    {
      "id": "c018_caller",
      "label": "Agitated caller with distracted movement",
      "kind": "human",
      "role": "Phone user whose gestures and short unintentional movements create a persistent roadway hazard",
      "color": "red",
      "length_m": 0.48,
      "width_m": 0.52,
      "height_m": 1.78,
      "keys": [
        {
          "t": -7,
          "x": 29,
          "y": -5.1,
          "z": 0,
          "heading_deg": 0,
          "pose": "phone"
        },
        {
          "t": -4,
          "x": 31.4,
          "y": -5.1,
          "z": 0,
          "heading_deg": 0,
          "pose": "phone"
        },
        {
          "t": -2,
          "x": 31.4,
          "y": -5.1,
          "z": 0,
          "heading_deg": 90,
          "pose": "phone"
        },
        {
          "t": 0,
          "x": 31.4,
          "y": -2.4,
          "z": 0,
          "heading_deg": 90,
          "pose": "point"
        },
        {
          "t": 4,
          "x": 32.2,
          "y": 0.4,
          "z": 0,
          "heading_deg": 65,
          "pose": "phone"
        },
        {
          "t": 6,
          "x": 32.2,
          "y": 0.4,
          "z": 0,
          "heading_deg": 0,
          "pose": "phone"
        },
        {
          "t": 11,
          "x": 36.2,
          "y": 0.4,
          "z": 0,
          "heading_deg": 0,
          "pose": "point"
        },
        {
          "t": 14,
          "x": 36.2,
          "y": 0.4,
          "z": 0,
          "heading_deg": -130,
          "pose": "phone"
        },
        {
          "t": 17,
          "x": 35,
          "y": -1.1,
          "z": 0,
          "heading_deg": -130,
          "pose": "phone"
        },
        {
          "t": 40,
          "x": 35,
          "y": -1.1,
          "z": 0,
          "heading_deg": -130,
          "pose": "phone"
        }
      ],
      "attach_to": "",
      "attach_start_s": -7,
      "attach_end_s": 40,
      "attach_offset_xyz": [
        0,
        0,
        0
      ],
      "interaction": "The right hand keeps the phone at the right ear for the entire scene. Point poses animate only the free left arm; locomotion is layered underneath the phone gesture. Turns at -4 to -2, 4 to 6, and 11 to 14 s occur while the feet remain planted. The final retreat is incomplete, not a full crossing or clearance."
    },
    {
      "id": "c018_phone",
      "label": "Persistent handheld phone",
      "kind": "equipment",
      "role": "Small handset continuously held at the caller's right ear",
      "color": "silver",
      "length_m": 0.075,
      "width_m": 0.02,
      "height_m": 0.15,
      "keys": [
        {
          "t": -7,
          "x": 29.08,
          "y": -5.24,
          "z": 1.54032,
          "heading_deg": 0,
          "pose": "stand"
        },
        {
          "t": -4,
          "x": 31.48,
          "y": -5.24,
          "z": 1.54032,
          "heading_deg": 0,
          "pose": "stand"
        },
        {
          "t": -2,
          "x": 31.54,
          "y": -5.02,
          "z": 1.54179,
          "heading_deg": 90,
          "pose": "stand"
        },
        {
          "t": 0,
          "x": 31.54,
          "y": -2.32,
          "z": 1.54179,
          "heading_deg": 90,
          "pose": "stand"
        },
        {
          "t": 4,
          "x": 32.36069,
          "y": 0.41334,
          "z": 1.54176,
          "heading_deg": 65,
          "pose": "stand"
        },
        {
          "t": 6,
          "x": 32.28,
          "y": 0.26,
          "z": 1.54032,
          "heading_deg": 0,
          "pose": "stand"
        },
        {
          "t": 11,
          "x": 36.28,
          "y": 0.26,
          "z": 1.54032,
          "heading_deg": 0,
          "pose": "stand"
        },
        {
          "t": 14,
          "x": 36.04133,
          "y": 0.42871,
          "z": 1.53842,
          "heading_deg": -130,
          "pose": "stand"
        },
        {
          "t": 17,
          "x": 34.84133,
          "y": -1.07129,
          "z": 1.53842,
          "heading_deg": -130,
          "pose": "stand"
        },
        {
          "t": 40,
          "x": 34.84133,
          "y": -1.07129,
          "z": 1.53842,
          "heading_deg": -130,
          "pose": "stand"
        }
      ],
      "attach_to": "c018_caller",
      "attach_start_s": -7,
      "attach_end_s": 40,
      "attach_offset_xyz": [
        0.08,
        -0.14,
        1.54
      ],
      "interaction": "Attachment is authoritative throughout playback. Reference keys rotate the local offset with the caller and compensate the phone's ground-relative z for the supplied ground-plane slope. The right-hand grip follows the handset; there is no release, disappearance, or switch between hands."
    }
  ],
  "acceptance_checks": [
    "Verify exactly one caller and one separately identified phone persist throughout all 941 samples.",
    "Verify phone attachment, world reference positions, ear placement, and right-hand contact agree without snapping during every stationary turn.",
    "Verify left-arm gestures do not detach the phone, intersect the torso, or imply an interaction with an absent person.",
    "Verify the caller's actual walking speeds remain within 0.6–1.7 m/s apart from acceleration and braking, and stationary turns do not create lateral jumps.",
    "Verify the initial caller footprint lies on the police map's south sidewalk and the authored intrusion lies on its road polygon.",
    "Verify the caller's final footprint still intersects the buffered ego corridor; ego_release_s must remain -1 and ego must not creep past.",
    "Require human approval of the complete unresolved hazard, source-background conflicts, and the proposed 4 s review view before image generation."
  ],
  "assumptions": [
    "Image #2 supplies buildings, the overhead enclosed bridge, road, sidewalks, and parked-car context. It does not establish a phone argument; the caller, handset, and behavior are counterfactual proposals.",
    "Playback is finite and non-looping from -7 through 40 s inclusive at 20 Hz, totaling 941 samples. Use bounded C1 root motion, speed-derived walking underneath upper-body gestures, smooth braking, and stationary holds without interpolation overshoot.",
    "The south sidewalk near x=29 to 36 extends approximately from y=-6.5 to -3.4. The proposal deliberately leaves the caller on the roadway rather than inventing a successful return to that sidewalk.",
    "The supplied ground plane is interpreted as ground height a*x+b*y+c. Human z remains zero; the attached phone's listed z values are offsets above ground at its own XY, not absolute elevations.",
    "Ego is separate from this cast: length 4.5 m, width 1.9 m, y=0. It starts at x=4 at -7 s with speed 4 m/s, stops smoothly at x=12 by -3 s, and stays there through 40 s. Its buffered corridor is y=-1.5 to 1.5.",
    "Raised voice and agitation express the requested scenario, not a diagnosis or an inference from the photograph. No physical confrontation is proposed.",
    "Precise background occupancy requires human review. Approval is pending; later Image 2.5 must edit original Image #2 and use the rehearsal only for actor position and posture."
  ]
}