Spaces:
Sleeping
Sleeping
Download results/multihop_neural_only_results.json from Angshul/Evidence-Graph-Reranker: direct link, hf CLI and curl.
- Browser
- Download file 2.03 kB
-
https://huggingface.co/spaces/Angshul/Evidence-Graph-Reranker/resolve/main/results/multihop_neural_only_results.json
- Command line
-
hf download hf://spaces/Angshul/Evidence-Graph-Reranker/results/multihop_neural_only_results.json
-
curl -L -o multihop_neural_only_results.json https://huggingface.co/spaces/Angshul/Evidence-Graph-Reranker/resolve/main/results/multihop_neural_only_results.json
2.03 kB
| { | |
| "dataset": "multihop", | |
| "questions": 300, | |
| "candidate_count_total": 6000, | |
| "candidate_pool": "Top-20 neural MiniLM retrieval from full 609-article corpus (no gold insertion)", | |
| "gold_support_count_distribution": { | |
| "3": 96, | |
| "2": 158, | |
| "4": 46 | |
| }, | |
| "gold_available_fraction": 51.67, | |
| "gold_available_count": 155, | |
| "graph_link_fraction": 4.0, | |
| "oracle_complete_coverage_pct": { | |
| "2": 35.0, | |
| "3": 48.0, | |
| "5": 51.67, | |
| "8": 51.67 | |
| }, | |
| "complete_coverage_pct": { | |
| "dense_cosine": { | |
| "2": 6.0, | |
| "3": 11.67, | |
| "5": 21.67, | |
| "8": 31.67 | |
| }, | |
| "crossencoder": { | |
| "2": 7.0, | |
| "3": 13.67, | |
| "5": 23.0, | |
| "8": 36.67 | |
| }, | |
| "dense_graph": { | |
| "2": 6.0, | |
| "3": 11.67, | |
| "5": 22.33, | |
| "8": 32.33 | |
| }, | |
| "crossencoder_graph": { | |
| "2": 7.67, | |
| "3": 13.67, | |
| "5": 26.0, | |
| "8": 36.67 | |
| } | |
| }, | |
| "crossencoder_graph_minus_crossencoder_at3_pp": 0.0, | |
| "ci95_pp": [ | |
| -1.33, | |
| 1.33 | |
| ], | |
| "paired_wins_losses_ties_at3": { | |
| "wins": 2, | |
| "losses": 2, | |
| "ties": 296 | |
| }, | |
| "timing_seconds": { | |
| "index_seconds": 8.61646041700078, | |
| "query_embedding_seconds": 2.9061220870007674, | |
| "total_prep_seconds": 11.600812000000587, | |
| "index_size": 609, | |
| "candidate_pool_size": 20, | |
| "crossencoder_scoring_seconds": 190.511, | |
| "crossencoder_scoring_ms_per_question": 635.04, | |
| "crossencoder_forward_seconds": 176.907, | |
| "graph_selection_total_s": 2.271, | |
| "graph_selection_ms_per_question": 7.57 | |
| }, | |
| "models": { | |
| "dense": "user uploaded all-MiniLM-L6-v2", | |
| "crossencoder": "user uploaded cross-encoder/ms-marco-MiniLM-L6-v2" | |
| }, | |
| "protocol": "MiniLM embeddings at max 128 WordPiece for dense. Cross-encoder truncates paired query+passage at 256 WordPiece. Both score exact same candidate pools. Fixed evidence graph .4 minmax relevance + .5 title in already-selected passage + .2 query-title score. No TF-IDF anywhere in candidate construction or scoring. Gold used solely for pool audit and evaluation." | |
| } |