{
  "rgcn_link_prediction": {
    "validation": {
      "mean_reciprocal_rank": 0.0734197945466392,
      "hits_at_10": 0.14442630250853494,
      "hits_at_1": 0.03933501558557221
    },
    "testing": {
      "mean_reciprocal_rank": 0.07925546916450926,
      "hits_at_10": 0.15405164737310775,
      "hits_at_1": 0.04407836153161175
    },
    "split_counts": {
      "train": 121266,
      "validation": 6737,
      "test": 6738
    },
    "transe_init": true
  },
  "rollup": {
    "recorded_at": "2026-06-05",
    "phase2_targets": {
      "link_pred_mrr": 0.2,
      "source": "TODO.md Phase 2 readiness criterion"
    },
    "link_prediction_split": {
      "train": 121266,
      "validation": 6737,
      "test": 6738,
      "ratios": [
        0.9,
        0.05,
        0.05
      ],
      "seed": 42
    },
    "transe": {
      "config": "data/processed/transe_config.json",
      "artifacts": "data/processed/transe_emb.pt",
      "hyperparams": {
        "embedding_dim": 128,
        "learning_rate": 0.001,
        "batch_size": 256,
        "num_epochs": 200,
        "num_negs_per_pos": 10
      },
      "validation": {
        "mean_reciprocal_rank": 0.0688,
        "hits_at_10": 0.1718,
        "hits_at_1": 0.0056
      },
      "testing": {
        "mean_reciprocal_rank": 0.0684,
        "hits_at_10": 0.1702,
        "hits_at_1": 0.0045
      },
      "meets_mrr_target": false
    },
    "rgcn": {
      "config": "data/processed/rgcn_config.json",
      "artifacts": "checkpoints/wikimovies_rgcn.pt",
      "hyperparams": {
        "hidden_dim": 128,
        "num_layers": 2,
        "num_bases": 4,
        "learning_rate": 0.001,
        "batch_size": 1024,
        "num_epochs": 50,
        "num_negs_per_pos": 10,
        "transe_init": true,
        "frozen_after_train": true
      },
      "validation": {
        "mean_reciprocal_rank": 0.0734,
        "hits_at_10": 0.1444,
        "hits_at_1": 0.0393
      },
      "testing": {
        "mean_reciprocal_rank": 0.0793,
        "hits_at_10": 0.1541,
        "hits_at_1": 0.0441
      },
      "meets_mrr_target": false,
      "vs_transe": {
        "test_mrr_delta": 0.0109,
        "test_hits10_delta": -0.0161,
        "note": "MRR slightly up; Hits@10 down vs TransE"
      }
    },
    "hf_publish": {
      "model_name": "wikimovies-transe-rgcn",
      "version": "v1-experimental",
      "status": "staged_locally",
      "staging_dir": "models/wikimovies-transe-rgcn",
      "upload_script": "scripts/publish_encoder_hf.py",
      "note": "Experimental baseline; expect v2 after remediation. Upload requires: hf auth login && python scripts/publish_encoder_hf.py --repo-id USER/wikimovies-transe-rgcn --upload"
    },
    "encode_api": {
      "module": "graph_align/encoders/encoder.py",
      "checkpoint": "checkpoints/wikimovies_rgcn.pt",
      "benchmark": "results/encode_benchmark.json",
      "num_subgraphs": 1000,
      "split": "poc_train",
      "per_subgraph_ms": {
        "cpu_node": 2.98,
        "cpu_graph": 2.91,
        "mps_node": 40.32,
        "mps_graph": 30.86
      },
      "note": "Sequential per-subgraph forward; MPS slower than CPU on small subgraphs (kernel launch overhead). Use CPU or batched encode_subgraphs for inference."
    },
    "retrieval": {
      "config": "data/processed/config.json",
      "hop_max": 3,
      "n_max": 500,
      "train_samples": 114196,
      "answer_in_khop_rate": 1.0,
      "answer_in_retrieved_rate": 0.5623,
      "meets_retrieval_target": false,
      "note": "No formal MRR target; 56% cap coverage is QA bottleneck separate from link-pred MRR"
    },
    "gaps": [
      {
        "id": "link_pred_mrr",
        "current": 0.079,
        "target": 0.2,
        "metric": "rgcn test MRR",
        "blocks_mvp": false,
        "blocks_phase2_criterion": true
      },
      {
        "id": "retrieval_coverage",
        "current": 0.562,
        "target": null,
        "metric": "answer_in_retrieved_rate at N_max=500",
        "blocks_mvp": false,
        "note": "44% train QA: gold answer outside capped subgraph"
      }
    ],
    "remediation": {
      "link_pred_mrr": [
        {
          "priority": 1,
          "action": "Stronger KGE init: train ComplEx or RotatE (PyKEEN) on same split; use as R-GCN node init",
          "expected": "Often +0.05\u20130.15 MRR on multi-rel KGs vs TransE L1",
          "effort": "medium"
        },
        {
          "priority": 2,
          "action": "R-GCN hyperparam sweep: 100\u2013200 epochs, lr 5e-4, dropout 0.1, num_bases=9, unfreeze/finetune init",
          "expected": "Modest MRR gain; current 50-epoch run under-trained",
          "effort": "low"
        },
        {
          "priority": 3,
          "action": "Better negative sampling: type-constrained / degree-aware (PyKEEN Bernoulli or LCWA+filtered)",
          "expected": "Better ranking tail prediction",
          "effort": "medium"
        },
        {
          "priority": 4,
          "action": "Add inverse relations (+9 rels) and self-loops in message-passing graph",
          "expected": "Improves undirected reachability in conv layers",
          "effort": "medium"
        },
        {
          "priority": 5,
          "action": "Calibrate eval: run PyKEEN TransE/ComplEx baseline on identical split; verify our eval matches",
          "expected": "Rule out eval implementation gap",
          "effort": "low"
        }
      ],
      "retrieval_coverage": [
        {
          "priority": 1,
          "action": "Raise N_max budget (1000 / 2000) and rebuild subgraphs; re-measure answer_in_retrieved_rate",
          "expected": "Direct lift toward 80%+ retrieved; linear cost in subgraph size",
          "effort": "low",
          "command": "python scripts/build_subgraphs.py --n-max-budget 2000"
        },
        {
          "priority": 2,
          "action": "Smarter truncation: hop-first then degree (already); add answer-aware cap ablation for upper bound",
          "expected": "Diagnostic only \u2014 sets ceiling for retrieval",
          "effort": "low"
        }
      ],
      "mvp_path": "Proceed with frozen R-GCN (MRR 0.08) + N_max=500 (56% retrieval): link-pred MRR is init quality; QA accuracy driven mainly by retrieval + projection alignment, not global MRR>0.2."
    }
  }
}