{ "format_version": 3, "generator": "prepare_memory_router_dataset.py", "seed": 20260909, "candidate_count": 32, "schema": { "query": "natural-language routing query", "candidates": "bounded memory records with text and provenance", "positive_indices": "one or more supporting memory records; empty means abstain", "need_memory": "1 if evidence is required and present, 0 for unknown/unsupported queries", "hop": "0 for abstention, otherwise number of supporting records clipped to router max_hops", "group_id": "conversation or QA episode identity; no group may cross train/eval" }, "files": { "train": { "path": "H:\\Memory\\V2_dpskw\\data\\_ab_mega_V2_dpskw\\train.jsonl", "episodes": 60, "sha256": "f47703450f8ab3dece5d8d0094facb745989a81b1cc4d3cd6bcc6dd450c64138" }, "eval": { "path": "H:\\Memory\\V2_dpskw\\data\\_ab_mega_V2_dpskw\\eval.jsonl", "episodes": 0, "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855" } }, "counts": { "train_groups": 80128, "eval_groups": 64, "train_episodes": 60, "eval_episodes": 0, "train_unknown": 60, "eval_unknown": 0, "train_candidates": 1920, "eval_candidates": 0 }, "local_sources": [ { "source": "H:/Memory/dynamic_memory_lab/data/benchmark_train.jsonl", "rows": 128, "kind": "benchmark", "split": "train" }, { "source": "H:/Memory/dynamic_memory_lab/data/mega_validation/memory_validation_80k_train.jsonl", "rows": 80000, "kind": "mega_validation", "split": "train" }, { "source": "H:/Memory/dynamic_memory_lab/data/benchmark_eval.jsonl", "rows": 64, "kind": "benchmark", "split": "eval" } ], "public_sources": [], "public_catalog": [ { "name": "hotpotqa_train", "dataset_id": "hotpot_qa", "config": "distractor", "split": "train", "split_kind": "train", "task": "qa", "url": "https://huggingface.co/datasets/hotpot_qa" }, { "name": "hotpotqa_validation", "dataset_id": "hotpot_qa", "config": "distractor", "split": "validation", "split_kind": "eval", "task": "qa", "url": "https://huggingface.co/datasets/hotpot_qa" }, { "name": "codesearchnet_python_train", "dataset_id": "code_search_net", "config": "python", "split": "train", "split_kind": "train", "task": "code", "url": "https://huggingface.co/datasets/code_search_net" }, { "name": "codesearchnet_python_validation", "dataset_id": "code_search_net", "config": "python", "split": "validation", "split_kind": "eval", "task": "code", "url": "https://huggingface.co/datasets/code_search_net" }, { "name": "fever_train", "dataset_id": "fever", "config": "v1.0", "split": "train", "split_kind": "train", "task": "evidence", "url": "https://huggingface.co/datasets/fever" }, { "name": "fever_validation", "dataset_id": "fever", "config": "v1.0", "split": "labelled_dev", "split_kind": "eval", "task": "evidence", "url": "https://huggingface.co/datasets/fever" } ], "split_stats": { "train": { "kept": 60, "unknown": 60, "family:benchmark_qa": 60, "written": 60 }, "eval": { "dropped": 64, "written": 0 } }, "leakage_check": { "group_overlap": 0, "passed": true }, "conflict_policy": { "enabled": true, "answerable_positive_conflicts_excluded": true, "unknown_hard_conflicts_retained": true }, "evaluation_policy": "eval.jsonl is generated and hashed before router training; the trainer refuses an optional hash mismatch.", "warnings": [ "Local generated memory-policy files are useful hard negatives but are not public-human chat data.", "Add redacted real user traces only after consent and PII removal.", "Public download failures are recorded; failed sources contribute zero rows." ] }