tempgraphrag-artifacts

Temporal-Aware GraphRAG — anonymous data archive

Anonymous double-blind artifact accompanying the EMNLP submission "The Lever Is the Prompt: Retrieval-Conditioned Prompting in Temporal-Aware GraphRAG." This is the data + trained-adapter half; the code is in the companion anonymous repository linked from the paper. See DATASHEET.md for provenance.

No author, affiliation, or identifying information is included. Please do not attempt to de-anonymize.

Contents

adapters/      LoRA adapters (inference-ready: adapter_model.safetensors +
               adapter_config.json + tokenizer + chat_template). 14 policies:
               sft-v3{,-seed1337,-seed7}        Qwen3-8B headline (3 seeds)
               sft-llama31{,-seed1337,-seed7}    Llama-3.1-8B cross-arch (3 seeds)
               sft-mistral{,-seed1337,-seed7}    Mistral-7B cross-arch (3 seeds)
               sft-multitq{,-seed1337,-seed7}    MultiTQ cross-benchmark (3 seeds)
               sft-multitq-{llama,mistral}       MultiTQ cross-arch
eval/          Per-question predictions + gold for every reported run (74 JSONs):
               TempBench 3-seed, 3-hop ablation, empty/shuffled-evidence,
               data-scale (1k/2k), full-test LLM-judge runs, MultiTQ, baselines.
benchmark/     benchmark_labelled.jsonl + labels.tsv (the benchmark of [anon-bench],
               provided as a read-only input; see PROVENANCE.txt).
sft_data/      Retrieval-conditioned SFT corpora (CoT, terse, MultiTQ).
logs/          Training / evaluation logs (negative-result evidence).

Mapping to the code repository

Place these so the code repo's scripts find them:

adapters/<name>/        ->  checkpoints/<name>/final/
eval/*.json             ->  outputs/eval/
benchmark/*             ->  outputs/benchmark/
sft_data/*.jsonl        ->  outputs/

Notes

• Adapters are inference-only (training state / optimizer checkpoints removed).
• Three contaminated judge runs (errored API calls) are excluded; all reported judge-EM numbers come from the clean full-test runs included here.

License

Mixed; the license: other tag reflects this:

• TempBench data (benchmark, labels, and their SFT corpora + eval outputs): derived from Wikidata (CC0) via TGB 2.0 — permissive, research use.
• MultiTQ / ICEWS data (MultiTQ SFT corpora and MultiTQ eval outputs): derive from the ICEWS event dataset (© 2015 Lockheed Martin Corporation and BBN-Raytheon), usable for research and educational purposes only — not for any commercial purpose. These inherit ICEWS's non-commercial, research-only restriction and are not CC0/permissive like the TempBench data above.
• LoRA adapters: derivative works of their base models and governed by those licenses — Qwen3-8B (Apache-2.0), Mistral-7B-Instruct-v0.3 (Apache-2.0), and Llama-3.1-8B-Instruct (Llama 3.1 Community License). The Llama-based adapters are Built with Llama and carry a Llama-prefixed name, as that license requires; their use is subject to the Llama 3.1 Community License.