{
 "task": "extract-decision",
 "model": "meta-llama/llama-4-maverick",
 "by": "incident.models@web-summit.dinis",
 "updated": "2026-11-11T02:56:51Z",
 "about": "One model's answers to one task: the first run of each item in full (as parsed; right or wrong per field), the repeat runs as right or wrong with their cost. Raw requests and responses are in the raw store; raw_sha256 names each record.",
 "items_updated": "2026-11-11T02:53:20Z",
 "answers": {
  "d04": {
   "kind": "answered",
   "right": true,
   "fields": {
    "decider": true,
    "effect_from_utc": true,
    "effect_to_utc": true
   },
   "answer": {
    "decider": "ipma",
    "what": "Red warning for rain",
    "effect_from_utc": "2026-11-10T21:00Z",
    "effect_to_utc": "2026-11-11T06:00Z"
   },
   "model_served": "meta-llama/llama-4-maverick",
   "cost_usd": 0.0003018015,
   "latency_ms": 871,
   "tokens_in": 711,
   "tokens_out": 56,
   "at": "2026-11-11T02:25:42Z",
   "raw_sha256": "d3abd98e5b75e88d"
  },
  "d01": {
   "kind": "answered",
   "right": true,
   "fields": {
    "decider": true,
    "effect_from_utc": true,
    "effect_to_utc": true
   },
   "answer": {
    "decider": "government",
    "what": "declare a state of alert across mainland Portugal",
    "effect_from_utc": "2026-11-11T00:00Z",
    "effect_to_utc": "2026-11-11T23:59Z"
   },
   "model_served": "meta-llama/llama-4-maverick",
   "cost_usd": 0.0002819025,
   "latency_ms": 1232,
   "tokens_in": 645,
   "tokens_out": 59,
   "at": "2026-11-11T02:25:42Z",
   "raw_sha256": "05434f0ca33586f0"
  },
  "d02": {
   "kind": "answered",
   "right": true,
   "fields": {
    "decider": true,
    "effect_from_utc": true,
    "effect_to_utc": true
   },
   "answer": {
    "decider": "ipma",
    "what": "Red wind warning",
    "effect_from_utc": "2026-11-11T12:00Z",
    "effect_to_utc": "2026-11-11T21:00Z"
   },
   "model_served": "meta-llama/llama-4-maverick",
   "cost_usd": 0.0002061378,
   "latency_ms": 1269,
   "tokens_in": 734,
   "tokens_out": 55,
   "at": "2026-11-11T02:25:42Z",
   "raw_sha256": "833daf7b94a96157"
  },
  "d03": {
   "kind": "answered",
   "right": true,
   "fields": {
    "decider": true,
    "effect_from_utc": true,
    "effect_to_utc": true
   },
   "answer": {
    "decider": "ipma",
    "what": "Red warning for heavy and persistent rain",
    "effect_from_utc": "2026-11-11T09:00Z",
    "effect_to_utc": "2026-11-11T18:00Z"
   },
   "model_served": "meta-llama/llama-4-maverick",
   "cost_usd": 0.0002002374,
   "latency_ms": 1355,
   "tokens_in": 722,
   "tokens_out": 59,
   "at": "2026-11-11T02:25:42Z",
   "raw_sha256": "e810870a33ce5040"
  },
  "d05": {
   "kind": "answered",
   "right": true,
   "fields": {
    "decider": true,
    "effect_from_utc": true,
    "effect_to_utc": true
   },
   "answer": {
    "decider": "ipma",
    "what": "Red warning for rain",
    "effect_from_utc": "2026-11-10T21:00Z",
    "effect_to_utc": "2026-11-11T06:00Z"
   },
   "model_served": "meta-llama/llama-4-maverick",
   "cost_usd": 0.0003018015,
   "latency_ms": 911,
   "tokens_in": 711,
   "tokens_out": 56,
   "at": "2026-11-11T02:25:43Z",
   "raw_sha256": "8b01ed82180e0085"
  },
  "d07": {
   "kind": "answered",
   "right": true,
   "fields": {
    "decider": true,
    "effect_from_utc": true,
    "effect_to_utc": true
   },
   "answer": {
    "decider": "websummit",
    "what": "cancel Day 2",
    "effect_from_utc": null,
    "effect_to_utc": null
   },
   "model_served": "meta-llama/llama-4-maverick",
   "cost_usd": 0.0001513413,
   "latency_ms": 725,
   "tokens_in": 633,
   "tokens_out": 35,
   "at": "2026-11-11T02:25:43Z",
   "raw_sha256": "d9406b38bcfa0e88"
  },
  "d08": {
   "kind": "answered",
   "right": true,
   "fields": {
    "decider": true,
    "effect_from_utc": true,
    "effect_to_utc": true
   },
   "answer": {
    "decider": "websummit",
    "what": "proceed with Day 3 as planned",
    "effect_from_utc": null,
    "effect_to_utc": null
   },
   "model_served": "meta-llama/llama-4-maverick",
   "cost_usd": 0.0001539153,
   "latency_ms": 684,
   "tokens_in": 629,
   "tokens_out": 39,
   "at": "2026-11-11T02:25:43Z",
   "raw_sha256": "71a098aff349e118"
  },
  "d06": {
   "kind": "answered",
   "right": true,
   "fields": {
    "decider": true,
    "effect_from_utc": true,
    "effect_to_utc": true
   },
   "answer": {
    "decider": "ipma",
    "what": "issued weather warnings of RED and ORANGE level",
    "effect_from_utc": null,
    "effect_to_utc": null
   },
   "model_served": "meta-llama/llama-4-maverick",
   "cost_usd": 0.0001684683,
   "latency_ms": 1139,
   "tokens_in": 671,
   "tokens_out": 39,
   "at": "2026-11-11T02:25:43Z",
   "raw_sha256": "53daab953d327daa"
  },
  "d09": {
   "kind": "answered",
   "right": true,
   "fields": {
    "decider": true,
    "effect_from_utc": true,
    "effect_to_utc": true
   },
   "answer": {
    "decider": "aemet",
    "what": "Special warning for heavy and persistent rain, very strong gusts and rough sea",
    "effect_from_utc": null,
    "effect_to_utc": null
   },
   "model_served": "meta-llama/llama-4-maverick",
   "cost_usd": 0.0001543608,
   "latency_ms": 706,
   "tokens_in": 616,
   "tokens_out": 44,
   "at": "2026-11-11T02:25:43Z",
   "raw_sha256": "4bc43134ef9e28e1"
  },
  "d10": {
   "kind": "answered",
   "right": true,
   "fields": {
    "decider": true,
    "effect_from_utc": true,
    "effect_to_utc": true
   },
   "answer": {
    "decider": "metro",
    "what": "activate contingency plan for homeless people",
    "effect_from_utc": null,
    "effect_to_utc": null
   },
   "model_served": "meta-llama/llama-4-maverick",
   "cost_usd": 0.0001489158,
   "latency_ms": 927,
   "tokens_in": 626,
   "tokens_out": 35,
   "at": "2026-11-11T02:25:44Z",
   "raw_sha256": "9dcb231713bd2b5c"
  }
 },
 "repeats": {}
}