{
  "benchmark": "longmemeval",
  "selection": {
    "dataset_revision": "98d7416c24c778c2fee6e6f3006e7a073259d48f",
    "variant": "s",
    "sample_seed": 13,
    "question_limit": 150,
    "question_types": [],
    "questions_selected": 150,
    "questions_total": 500,
    "top_k": 40,
    "answer_model_id": null,
    "judge_model_id": null,
    "extraction_model_id": "anthropic:claude-sonnet-5",
    "embedding_model_id": "all-MiniLM-L6-v2",
    "context_budget_tokens": null,
    "abstraction": false,
    "consolidation": false,
    "dedup_judge": false,
    "stores_reused": true,
    "reused_from": {
      "dataset_revision": "98d7416c24c778c2fee6e6f3006e7a073259d48f",
      "variant": "s",
      "sample_seed": "13",
      "question_limit": "150",
      "question_types": "",
      "extraction_model_id": "anthropic:claude-sonnet-5",
      "embedding_model_id": "all-MiniLM-L6-v2",
      "extraction.similarity_threshold": "0.8",
      "extraction.duplicate_suppression.enabled": "True"
    },
    "answer_scaffold": 2,
    "judge_protocol": 2,
    "thresholds": {
      "extraction.similarity_threshold": 0.8,
      "confidence.uncalibrated_cap.enabled": 0.0,
      "confidence.uncalibrated_cap.cap_value": 0.7,
      "extraction.duplicate_suppression.enabled": 1.0,
      "links_suggest.auto_merge.enabled": 1.0,
      "content_age_decay.sources.CONVERSATION.half_life_days": 0.0,
      "content_age_decay.sources.CONVERSATION.floor": 1.0
    },
    "memory": "particles"
  },
  "retrieval_stage": {
    "questions": 143,
    "abstention_questions": 7,
    "mean_recall_at_k": 0.9685314685314685,
    "mean_precision_at_k": 0.3666083916083916,
    "recall_by_type": {
      "knowledge-update": 0.9761904761904762,
      "multi-session": 1.0,
      "single-session-assistant": 0.8823529411764706,
      "single-session-preference": 1.0,
      "single-session-user": 1.0,
      "temporal-reasoning": 0.9473684210526315
    },
    "per_question": [
      {
        "question_id": "01493427",
        "question_type": "knowledge-update",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.3,
        "abstention": false
      },
      {
        "question_id": "08e075c7",
        "question_type": "knowledge-update",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.075,
        "abstention": false
      },
      {
        "question_id": "0977f2af",
        "question_type": "knowledge-update",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 0.5,
        "precision_at_k": 0.15,
        "abstention": false
      },
      {
        "question_id": "10e09553",
        "question_type": "knowledge-update",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.35,
        "abstention": false
      },
      {
        "question_id": "26bdc477",
        "question_type": "knowledge-update",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.55,
        "abstention": false
      },
      {
        "question_id": "41698283",
        "question_type": "knowledge-update",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.625,
        "abstention": false
      },
      {
        "question_id": "603deb26",
        "question_type": "knowledge-update",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.225,
        "abstention": false
      },
      {
        "question_id": "6071bd76",
        "question_type": "knowledge-update",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.75,
        "abstention": false
      },
      {
        "question_id": "6a1eabeb",
        "question_type": "knowledge-update",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.275,
        "abstention": false
      },
      {
        "question_id": "6a27ffc2",
        "question_type": "knowledge-update",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.45,
        "abstention": false
      },
      {
        "question_id": "6aeb4375_abs",
        "question_type": "knowledge-update",
        "evidence_sessions": 0,
        "evidence_sessions_hit": 0,
        "particles_retrieved": 40,
        "recall_at_k": null,
        "precision_at_k": null,
        "abstention": true
      },
      {
        "question_id": "7401057b",
        "question_type": "knowledge-update",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.925,
        "abstention": false
      },
      {
        "question_id": "7a87bd0c",
        "question_type": "knowledge-update",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.25,
        "abstention": false
      },
      {
        "question_id": "852ce960",
        "question_type": "knowledge-update",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.325,
        "abstention": false
      },
      {
        "question_id": "89941a94",
        "question_type": "knowledge-update",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.85,
        "abstention": false
      },
      {
        "question_id": "8fb83627",
        "question_type": "knowledge-update",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.75,
        "abstention": false
      },
      {
        "question_id": "9ea5eabc",
        "question_type": "knowledge-update",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.15,
        "abstention": false
      },
      {
        "question_id": "b01defab",
        "question_type": "knowledge-update",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.5,
        "abstention": false
      },
      {
        "question_id": "c4ea545c",
        "question_type": "knowledge-update",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.175,
        "abstention": false
      },
      {
        "question_id": "d7c942c3",
        "question_type": "knowledge-update",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.125,
        "abstention": false
      },
      {
        "question_id": "dfde3500",
        "question_type": "knowledge-update",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.275,
        "abstention": false
      },
      {
        "question_id": "f685340e_abs",
        "question_type": "knowledge-update",
        "evidence_sessions": 0,
        "evidence_sessions_hit": 0,
        "particles_retrieved": 40,
        "recall_at_k": null,
        "precision_at_k": null,
        "abstention": true
      },
      {
        "question_id": "f9e8c073",
        "question_type": "knowledge-update",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.375,
        "abstention": false
      },
      {
        "question_id": "0100672e",
        "question_type": "multi-session",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.425,
        "abstention": false
      },
      {
        "question_id": "28dc39ac",
        "question_type": "multi-session",
        "evidence_sessions": 5,
        "evidence_sessions_hit": 5,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.775,
        "abstention": false
      },
      {
        "question_id": "2e6d26dc",
        "question_type": "multi-session",
        "evidence_sessions": 4,
        "evidence_sessions_hit": 4,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.525,
        "abstention": false
      },
      {
        "question_id": "37f165cf",
        "question_type": "multi-session",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.75,
        "abstention": false
      },
      {
        "question_id": "3fe836c9",
        "question_type": "multi-session",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.8,
        "abstention": false
      },
      {
        "question_id": "4adc0475",
        "question_type": "multi-session",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.375,
        "abstention": false
      },
      {
        "question_id": "55241a1f",
        "question_type": "multi-session",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.325,
        "abstention": false
      },
      {
        "question_id": "60036106",
        "question_type": "multi-session",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.6,
        "abstention": false
      },
      {
        "question_id": "60bf93ed",
        "question_type": "multi-session",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.45,
        "abstention": false
      },
      {
        "question_id": "61f8c8f8",
        "question_type": "multi-session",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.125,
        "abstention": false
      },
      {
        "question_id": "6c49646a",
        "question_type": "multi-session",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.525,
        "abstention": false
      },
      {
        "question_id": "77eafa52",
        "question_type": "multi-session",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.325,
        "abstention": false
      },
      {
        "question_id": "80ec1f4f_abs",
        "question_type": "multi-session",
        "evidence_sessions": 0,
        "evidence_sessions_hit": 0,
        "particles_retrieved": 40,
        "recall_at_k": null,
        "precision_at_k": null,
        "abstention": true
      },
      {
        "question_id": "81507db6",
        "question_type": "multi-session",
        "evidence_sessions": 5,
        "evidence_sessions_hit": 5,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.625,
        "abstention": false
      },
      {
        "question_id": "85fa3a3f",
        "question_type": "multi-session",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.425,
        "abstention": false
      },
      {
        "question_id": "87f22b4a",
        "question_type": "multi-session",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.925,
        "abstention": false
      },
      {
        "question_id": "88432d0a_abs",
        "question_type": "multi-session",
        "evidence_sessions": 0,
        "evidence_sessions_hit": 0,
        "particles_retrieved": 40,
        "recall_at_k": null,
        "precision_at_k": null,
        "abstention": true
      },
      {
        "question_id": "91b15a6e",
        "question_type": "multi-session",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.7,
        "abstention": false
      },
      {
        "question_id": "92a0aa75",
        "question_type": "multi-session",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.225,
        "abstention": false
      },
      {
        "question_id": "9aaed6a3",
        "question_type": "multi-session",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.325,
        "abstention": false
      },
      {
        "question_id": "9ee3ecd6",
        "question_type": "multi-session",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.45,
        "abstention": false
      },
      {
        "question_id": "a11281a2",
        "question_type": "multi-session",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.525,
        "abstention": false
      },
      {
        "question_id": "a1cc6108",
        "question_type": "multi-session",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.15,
        "abstention": false
      },
      {
        "question_id": "a3332713",
        "question_type": "multi-session",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.35,
        "abstention": false
      },
      {
        "question_id": "a4996e51",
        "question_type": "multi-session",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.275,
        "abstention": false
      },
      {
        "question_id": "a9f6b44c",
        "question_type": "multi-session",
        "evidence_sessions": 3,
        "evidence_sessions_hit": 3,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.675,
        "abstention": false
      },
      {
        "question_id": "bb7c3b45",
        "question_type": "multi-session",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.25,
        "abstention": false
      },
      {
        "question_id": "bc149d6b",
        "question_type": "multi-session",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.3,
        "abstention": false
      },
      {
        "question_id": "c18a7dc8",
        "question_type": "multi-session",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.475,
        "abstention": false
      },
      {
        "question_id": "d3ab962e",
        "question_type": "multi-session",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.275,
        "abstention": false
      },
      {
        "question_id": "d6062bb9",
        "question_type": "multi-session",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.2,
        "abstention": false
      },
      {
        "question_id": "d905b33f",
        "question_type": "multi-session",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.125,
        "abstention": false
      },
      {
        "question_id": "e6041065",
        "question_type": "multi-session",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.525,
        "abstention": false
      },
      {
        "question_id": "edced276",
        "question_type": "multi-session",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.175,
        "abstention": false
      },
      {
        "question_id": "eeda8a6d",
        "question_type": "multi-session",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.925,
        "abstention": false
      },
      {
        "question_id": "ef66a6e5",
        "question_type": "multi-session",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.5,
        "abstention": false
      },
      {
        "question_id": "gpt4_2f91af09",
        "question_type": "multi-session",
        "evidence_sessions": 3,
        "evidence_sessions_hit": 3,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.375,
        "abstention": false
      },
      {
        "question_id": "gpt4_7fce9456",
        "question_type": "multi-session",
        "evidence_sessions": 5,
        "evidence_sessions_hit": 5,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.9,
        "abstention": false
      },
      {
        "question_id": "gpt4_d12ceb0e",
        "question_type": "multi-session",
        "evidence_sessions": 3,
        "evidence_sessions_hit": 3,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.325,
        "abstention": false
      },
      {
        "question_id": "gpt4_e05b82a6",
        "question_type": "multi-session",
        "evidence_sessions": 4,
        "evidence_sessions_hit": 4,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.5,
        "abstention": false
      },
      {
        "question_id": "1d4da289",
        "question_type": "single-session-assistant",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.275,
        "abstention": false
      },
      {
        "question_id": "2bf43736",
        "question_type": "single-session-assistant",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.925,
        "abstention": false
      },
      {
        "question_id": "3249768e",
        "question_type": "single-session-assistant",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.475,
        "abstention": false
      },
      {
        "question_id": "352ab8bd",
        "question_type": "single-session-assistant",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.275,
        "abstention": false
      },
      {
        "question_id": "3e321797",
        "question_type": "single-session-assistant",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.3,
        "abstention": false
      },
      {
        "question_id": "488d3006",
        "question_type": "single-session-assistant",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.6,
        "abstention": false
      },
      {
        "question_id": "58470ed2",
        "question_type": "single-session-assistant",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.3,
        "abstention": false
      },
      {
        "question_id": "70b3e69b",
        "question_type": "single-session-assistant",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.6,
        "abstention": false
      },
      {
        "question_id": "8cf51dda",
        "question_type": "single-session-assistant",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.075,
        "abstention": false
      },
      {
        "question_id": "a40e080f",
        "question_type": "single-session-assistant",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.175,
        "abstention": false
      },
      {
        "question_id": "cc539528",
        "question_type": "single-session-assistant",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.4,
        "abstention": false
      },
      {
        "question_id": "ceb54acb",
        "question_type": "single-session-assistant",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 0,
        "particles_retrieved": 40,
        "recall_at_k": 0.0,
        "precision_at_k": 0.0,
        "abstention": false
      },
      {
        "question_id": "e3fc4d6e",
        "question_type": "single-session-assistant",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.225,
        "abstention": false
      },
      {
        "question_id": "e8a79c70",
        "question_type": "single-session-assistant",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.25,
        "abstention": false
      },
      {
        "question_id": "eaca4986",
        "question_type": "single-session-assistant",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 0,
        "particles_retrieved": 40,
        "recall_at_k": 0.0,
        "precision_at_k": 0.0,
        "abstention": false
      },
      {
        "question_id": "fca762bc",
        "question_type": "single-session-assistant",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.25,
        "abstention": false
      },
      {
        "question_id": "fea54f57",
        "question_type": "single-session-assistant",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.575,
        "abstention": false
      },
      {
        "question_id": "09d032c9",
        "question_type": "single-session-preference",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.45,
        "abstention": false
      },
      {
        "question_id": "195a1a1b",
        "question_type": "single-session-preference",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.35,
        "abstention": false
      },
      {
        "question_id": "35a27287",
        "question_type": "single-session-preference",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.325,
        "abstention": false
      },
      {
        "question_id": "505af2f5",
        "question_type": "single-session-preference",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.1,
        "abstention": false
      },
      {
        "question_id": "6b7dfb22",
        "question_type": "single-session-preference",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.3,
        "abstention": false
      },
      {
        "question_id": "75832dbd",
        "question_type": "single-session-preference",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.075,
        "abstention": false
      },
      {
        "question_id": "afdc33df",
        "question_type": "single-session-preference",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.075,
        "abstention": false
      },
      {
        "question_id": "d6233ab6",
        "question_type": "single-session-preference",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.025,
        "abstention": false
      },
      {
        "question_id": "fca70973",
        "question_type": "single-session-preference",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.45,
        "abstention": false
      },
      {
        "question_id": "001be529",
        "question_type": "single-session-user",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.1,
        "abstention": false
      },
      {
        "question_id": "0862e8bf",
        "question_type": "single-session-user",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.475,
        "abstention": false
      },
      {
        "question_id": "0862e8bf_abs",
        "question_type": "single-session-user",
        "evidence_sessions": 0,
        "evidence_sessions_hit": 0,
        "particles_retrieved": 40,
        "recall_at_k": null,
        "precision_at_k": null,
        "abstention": true
      },
      {
        "question_id": "15745da0",
        "question_type": "single-session-user",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.075,
        "abstention": false
      },
      {
        "question_id": "19b5f2b3",
        "question_type": "single-session-user",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.8,
        "abstention": false
      },
      {
        "question_id": "29f2956b",
        "question_type": "single-session-user",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.025,
        "abstention": false
      },
      {
        "question_id": "311778f1",
        "question_type": "single-session-user",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.225,
        "abstention": false
      },
      {
        "question_id": "4fd1909e",
        "question_type": "single-session-user",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.375,
        "abstention": false
      },
      {
        "question_id": "545bd2b5",
        "question_type": "single-session-user",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.15,
        "abstention": false
      },
      {
        "question_id": "5d3d2817",
        "question_type": "single-session-user",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.125,
        "abstention": false
      },
      {
        "question_id": "66f24dbb",
        "question_type": "single-session-user",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.375,
        "abstention": false
      },
      {
        "question_id": "6b168ec8",
        "question_type": "single-session-user",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.275,
        "abstention": false
      },
      {
        "question_id": "86f00804",
        "question_type": "single-session-user",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.775,
        "abstention": false
      },
      {
        "question_id": "8a137a7f",
        "question_type": "single-session-user",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.425,
        "abstention": false
      },
      {
        "question_id": "a06e4cfe",
        "question_type": "single-session-user",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.25,
        "abstention": false
      },
      {
        "question_id": "af8d2e46",
        "question_type": "single-session-user",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.1,
        "abstention": false
      },
      {
        "question_id": "c19f7a0b",
        "question_type": "single-session-user",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.125,
        "abstention": false
      },
      {
        "question_id": "c5e8278d",
        "question_type": "single-session-user",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.35,
        "abstention": false
      },
      {
        "question_id": "d52b4f67",
        "question_type": "single-session-user",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.125,
        "abstention": false
      },
      {
        "question_id": "e47becba",
        "question_type": "single-session-user",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.05,
        "abstention": false
      },
      {
        "question_id": "f4f1d8a4",
        "question_type": "single-session-user",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.125,
        "abstention": false
      },
      {
        "question_id": "0bc8ad92",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 3,
        "evidence_sessions_hit": 3,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.25,
        "abstention": false
      },
      {
        "question_id": "2c63a862",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.325,
        "abstention": false
      },
      {
        "question_id": "2ebe6c90",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.675,
        "abstention": false
      },
      {
        "question_id": "6e984302",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 0,
        "particles_retrieved": 40,
        "recall_at_k": 0.0,
        "precision_at_k": 0.0,
        "abstention": false
      },
      {
        "question_id": "8077ef71",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.1,
        "abstention": false
      },
      {
        "question_id": "993da5e2",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.15,
        "abstention": false
      },
      {
        "question_id": "a3838d2b",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 6,
        "evidence_sessions_hit": 6,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.8,
        "abstention": false
      },
      {
        "question_id": "b29f3365",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.6,
        "abstention": false
      },
      {
        "question_id": "b46e15ee",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 4,
        "evidence_sessions_hit": 4,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.275,
        "abstention": false
      },
      {
        "question_id": "b9cfe692",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 3,
        "evidence_sessions_hit": 3,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.75,
        "abstention": false
      },
      {
        "question_id": "bbf86515",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.325,
        "abstention": false
      },
      {
        "question_id": "c8090214",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.275,
        "abstention": false
      },
      {
        "question_id": "dcfa8644",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.55,
        "abstention": false
      },
      {
        "question_id": "gpt4_1a1dc16d",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.175,
        "abstention": false
      },
      {
        "question_id": "gpt4_1e4a8aeb",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.475,
        "abstention": false
      },
      {
        "question_id": "gpt4_2312f94c",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.375,
        "abstention": false
      },
      {
        "question_id": "gpt4_2487a7cb",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.65,
        "abstention": false
      },
      {
        "question_id": "gpt4_468eb063",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.125,
        "abstention": false
      },
      {
        "question_id": "gpt4_4fc4f797",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.175,
        "abstention": false
      },
      {
        "question_id": "gpt4_5438fa52",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 0.5,
        "precision_at_k": 0.175,
        "abstention": false
      },
      {
        "question_id": "gpt4_59149c78",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 0.5,
        "precision_at_k": 0.05,
        "abstention": false
      },
      {
        "question_id": "gpt4_68e94288",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.075,
        "abstention": false
      },
      {
        "question_id": "gpt4_70e84552",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.625,
        "abstention": false
      },
      {
        "question_id": "gpt4_70e84552_abs",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 0,
        "evidence_sessions_hit": 0,
        "particles_retrieved": 40,
        "recall_at_k": null,
        "precision_at_k": null,
        "abstention": true
      },
      {
        "question_id": "gpt4_76048e76",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.6,
        "abstention": false
      },
      {
        "question_id": "gpt4_7ca326fa",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 3,
        "evidence_sessions_hit": 3,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.35,
        "abstention": false
      },
      {
        "question_id": "gpt4_7ddcf75f",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.05,
        "abstention": false
      },
      {
        "question_id": "gpt4_7f6b06db",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 3,
        "evidence_sessions_hit": 3,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.3,
        "abstention": false
      },
      {
        "question_id": "gpt4_8e165409",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.15,
        "abstention": false
      },
      {
        "question_id": "gpt4_93159ced",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.25,
        "abstention": false
      },
      {
        "question_id": "gpt4_93159ced_abs",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 0,
        "evidence_sessions_hit": 0,
        "particles_retrieved": 40,
        "recall_at_k": null,
        "precision_at_k": null,
        "abstention": true
      },
      {
        "question_id": "gpt4_9a159967",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 3,
        "evidence_sessions_hit": 3,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.8,
        "abstention": false
      },
      {
        "question_id": "gpt4_af6db32f",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.5,
        "abstention": false
      },
      {
        "question_id": "gpt4_b5700ca0",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.15,
        "abstention": false
      },
      {
        "question_id": "gpt4_b5700ca9",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.15,
        "abstention": false
      },
      {
        "question_id": "gpt4_cd90e484",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.7,
        "abstention": false
      },
      {
        "question_id": "gpt4_d31cdae3",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.225,
        "abstention": false
      },
      {
        "question_id": "gpt4_e061b84g",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 3,
        "evidence_sessions_hit": 3,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.175,
        "abstention": false
      },
      {
        "question_id": "gpt4_e072b769",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 1,
        "evidence_sessions_hit": 1,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.2,
        "abstention": false
      },
      {
        "question_id": "gpt4_fa19884c",
        "question_type": "temporal-reasoning",
        "evidence_sessions": 2,
        "evidence_sessions_hit": 2,
        "particles_retrieved": 40,
        "recall_at_k": 1.0,
        "precision_at_k": 0.725,
        "abstention": false
      }
    ]
  },
  "qa_particles": null,
  "qa_full_context": null,
  "qa_no_memory": null,
  "quality_notes": [
    "Stores REUSED from a copy-on-write clone of ~/.particles/benchmark/stores/s150 — this run deposited and extracted nothing; the particle population is the one that store set was built with (extraction model anthropic:claude-sonnet-5, similarity_threshold 0.8, duplicate_suppression True).",
    "Decay is INERT for this run: content_age_decay.sources has no CONVERSATION rule, so every particle scores at recency factor 1.0. A decay on/off ablation needs a CONVERSATION entry in config before the 'on' arm means anything."
  ],
  "generated_at": "2026-09-20T19:36:33.347849Z"
}
