Medium corpus v1 (14 470 docs / 451 072 eligible passages) summaries
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
1 changed file +54 −0
added
data/splits/medium_v1/splits_summary.json
+54 −0
@@ -0,0 +1,54 @@ | ||
| 1 | +{ | |
| 2 | + "created_at": "2026-11-09T19:16:04Z", | |
| 3 | + "git": { | |
| 4 | + "commit": "5589d0e7c4268977d5d1b68957cc1f261f05e59b", | |
| 5 | + "branch": "main", | |
| 6 | + "dirty": false | |
| 7 | + }, | |
| 8 | + "libraries": { | |
| 9 | + "python": "3.14.4", | |
| 10 | + "torch": "2.12.0", | |
| 11 | + "numpy": "2.5.4", | |
| 12 | + "anthropic": "2.3.0", | |
| 13 | + "transformers": "5.8.1", | |
| 14 | + "sentencepiece": "0.2.2", | |
| 15 | + "lxml": "6.1.3", | |
| 16 | + "pyarrow": "24.0.0", | |
| 17 | + "sacrebleu": "2.6.0", | |
| 18 | + "datasketch": "2.0.0", | |
| 19 | + "rapidfuzz": "3.14.6" | |
| 20 | + }, | |
| 21 | + "hardware": { | |
| 22 | + "platform": "macOS-27.0-arm64-arm-64bit-Mach-O", | |
| 23 | + "machine": "arm64", | |
| 24 | + "cpu_count": 18, | |
| 25 | + "chip": "Apple M5 Max", | |
| 26 | + "ram_gb": 48.0, | |
| 27 | + "torch_mps": true, | |
| 28 | + "torch_cuda": false | |
| 29 | + }, | |
| 30 | + "config": { | |
| 31 | + "seed": 20261109, | |
| 32 | + "train": 0.8, | |
| 33 | + "val": 0.1, | |
| 34 | + "test": 0.1, | |
| 35 | + "heldout_disciplines": [ | |
| 36 | + "physics", | |
| 37 | + "earth_sciences" | |
| 38 | + ], | |
| 39 | + "heldout_before_year": 1900, | |
| 40 | + "author_safe": true, | |
| 41 | + "venue_safe": false | |
| 42 | + }, | |
| 43 | + "summary": { | |
| 44 | + "heldout_domain": 253, | |
| 45 | + "heldout_period": 510, | |
| 46 | + "quarantine": 141, | |
| 47 | + "test": 1261, | |
| 48 | + "train": 11035, | |
| 49 | + "val": 1270 | |
| 50 | + }, | |
| 51 | + "n_docs": 14470, | |
| 52 | + "group_leaks": [], | |
| 53 | + "n_fixed": 13372 | |
| 54 | +} | |
| 55 | ||