{ "version": 4, "toy": false, "rung": null, "prepared_at": "2026-10-07T01:27:18+00:00", "dataset_dir": "dataset-v4-full", "manifest_sha256": "6792bfb740b3c7217663afdba60ae75f5ae6d79aa53ac1475971fabe51a981ac", "manifest": { "pages": 181924, "tokens": 330366386, "created_at": "2026-10-07T00:58:27+00:00" }, "manifest_shards": [ { "file": "crawl-shard-00000.jsonl", "pages": 20000, "tokens": 47840786, "bytes": 175257859, "sha256": "012bf5d772f4731eaeddcd909029d07bbe90afb2088d425cbf903b92280095e3", "source": "crawl" }, { "file": "crawl-shard-00001.jsonl", "pages": 20000, "tokens": 44063575, "bytes": 162061573, "sha256": "ead9a77cebab1660e399cb47db2adee31055847dba512dbb3ef74d03813b2b00", "source": "crawl" }, { "file": "crawl-shard-00002.jsonl", "pages": 20000, "tokens": 53181778, "bytes": 196369474, "sha256": "5ad1e712e52a266041ad1e37cf1b27fdb9c21260a228c4d072ce6b0e38bf460e", "source": "crawl" }, { "file": "crawl-shard-00003.jsonl", "pages": 20000, "tokens": 51313378, "bytes": 187276813, "sha256": "cd1b35c6649443e5e2c31ac7091045dc2a550411d12676cfda7c00918ebd9cbf", "source": "crawl" }, { "file": "crawl-shard-00004.jsonl", "pages": 20000, "tokens": 45012511, "bytes": 167024162, "sha256": "1586d5a71304ef352103f7b6e61f0189f3e63a29d887a53b0c54b70a2f848b59", "source": "crawl" }, { "file": "crawl-shard-00005.jsonl", "pages": 20000, "tokens": 42741504, "bytes": 157047166, "sha256": "4c750107a6ba28f0086af7d3b75f858b1aa76a1db8980cffa126db796c719da2", "source": "crawl" }, { "file": "crawl-shard-00006.jsonl", "pages": 16260, "tokens": 35305976, "bytes": 129501055, "sha256": "b1ad8bae8ceb4f69a291e23a82e358fef26ac1cae7ab4acf6f189ecf556e0b9f", "source": "crawl" }, { "file": "records-shard-00000.jsonl", "pages": 5000, "tokens": 1158392, "bytes": 4949845, "sha256": "c23a21d5a97448f678524a879c9e8cc4a8df3caf49a8fd52824759bb95a88d20", "source": "records" }, { "file": "records-shard-00001.jsonl", "pages": 5000, "tokens": 1096599, "bytes": 4915698, "sha256": "ec75f7ae6a88e48fcb7d1d3373fda9ce74c3a816174e87844e5760f9b95baf6d", "source": "records" }, { "file": "records-shard-00002.jsonl", "pages": 5000, "tokens": 918678, "bytes": 4308866, "sha256": "046f7198ec3f62d71aef5766ac7a11a6ca4480c045bf1e1d0b843fb32b878741", "source": "records" }, { "file": "records-shard-00003.jsonl", "pages": 5000, "tokens": 817118, "bytes": 3988989, "sha256": "a20430453ed74f27a9f121446bf5a62fa31d8377da07e499d1c8d9d1dd779e85", "source": "records" }, { "file": "records-shard-00004.jsonl", "pages": 5000, "tokens": 857884, "bytes": 4127675, "sha256": "844e7fed170a4e884aeda1f66cae789c25567b0ff3bd6cc4b2ad48f8abad62d8", "source": "records" }, { "file": "records-shard-00005.jsonl", "pages": 5000, "tokens": 883422, "bytes": 4218635, "sha256": "42c798f331a149394804573b62e74b14528fc8f8f5bc22ee1ac0a7f3e6918a2b", "source": "records" }, { "file": "records-shard-00006.jsonl", "pages": 5000, "tokens": 845402, "bytes": 4086717, "sha256": "f509992a39f656bdb263ce64f30fe360f39665fda2b8cef52f233e055d4289b0", "source": "records" }, { "file": "records-shard-00007.jsonl", "pages": 5000, "tokens": 1921725, "bytes": 6913850, "sha256": "7d2215063b7c8ea010bae86449b1a1153e22b3c32cb54d0dac711c1f306accf8", "source": "records" }, { "file": "records-shard-00008.jsonl", "pages": 5000, "tokens": 789413, "bytes": 3765224, "sha256": "7e8ea4008c2ef5d5ebf07cc53b1f45c9e0082416ef2227bb3452dcf62a574899", "source": "records" }, { "file": "records-shard-00009.jsonl", "pages": 664, "tokens": 1618245, "bytes": 5173560, "sha256": "46b0e5806746a10a607909c70b4998ff4f6a7cea5b1a783e5e35d700cdb4ecf8", "source": "records" } ], "cleaning": { "input_pages": 179924, "dup_url": 0, "dropped_url_class": { "casino": 289, "convert": 1746, "flashnews": 8345, "forecast": 48, "jobs": 1360, "price": 794, "price_prediction": 821, "zh": 669 }, "boilerplate_line_kinds": 19179, "boilerplate_lines_removed": 2698066, "wiki_tails_cut": { "pages": 17, "chars": 240631 }, "dropped_short": 45, "dropped_low_alpha": 15, "dropped_x_rewrite": 10446, "x_rewrite": { "rule": "(@handles + 'posted on X'-style phrases) per 1,000 words > 2", "handles": 55752, "phrases": 6071, "top_domains": [ [ "forum.arbitrum.foundation", 1356 ], [ "ethereum-magicians.org", 882 ], [ "gov.optimism.io", 863 ], [ "u.today", 630 ], [ "gov.uniswap.org", 389 ], [ "eips.ethereum.org", 329 ], [ "research.lido.fi", 279 ], [ "governance.aave.com", 279 ], [ "forum.balancer.fi", 250 ], [ "tapchibitcoin.io", 207 ], [ "github.com", 196 ], [ "bitcoinfoundation.org", 195 ], [ "discuss.jup.ag", 184 ], [ "coinlore.com", 132 ], [ "ethresear.ch", 117 ], [ "news.bitcoin.com", 104 ], [ "coindesk.com", 102 ], [ "coinfomania.com", 97 ], [ "cointelegraph.com", 93 ], [ "ankr.com", 90 ] ], "x_links_removed": { "pages": 2208, "links": 6130 }, "records_x_lines_removed": { "pages": 36, "lines": 39 } }, "dropped_lang": 14915, "lang": { "model": "fastText lid.176", "threshold": 0.65, "dropped_by_top_language": { "en": 6032, "vi": 1879, "pt": 731, "de": 641, "it": 532, "ar": 443, "id": 428, "nl": 423, "es": 391, "tr": 376, "pl": 371, "fr": 349, "cs": 288, "ko": 287, "ru": 250, "hu": 169, "uk": 159, "ja": 136, "th": 68, "ro": 62 } }, "dup_text": 3, "kept_pages": 140428, "dropped_heldout": 2000, "bad_rows": 0, "dropped_val_overlap": 0 }, "pages": { "train": 140428, "val": 2000 }, "chunks": { "train": 190867, "val": 4964, "max_chars": null, "max_tokens": 2040, "train_chunks_longer_than_context": 0 }, "chars": { "train": 790442138, "val": 15792677 }, "tokens": { "train": 183061543, "val": 3726648, "chars_per_token": 4.318 }, "tokenizer": { "trained_on": "English train pages of this dataset only (spider pages, fastText lid.176 >= 0.65)", "max_chars": 2000000000, "doc_cap": 10000, "vocab_size": 16384, "trainer": "nanochat rustbpe (GPT-4 style split pattern)", "sha256": "5782900e33bdfc9a614fd96502b9df631d90d17854ec79bff0aab9f354a64478", "glossary": { "terms": 680, "tokens": 1031, "single_token": 408, "mean_tokens": 1.516, "ref_tokens": 1106, "worse": 1, "better": 67, "same": 612, "worst": [ { "term": "Substrate", "tokens": 3, "ref": 2 } ], "passed": true, "ref": "v3" } }, "sft_headings": { "train": { "conversations": 521532, "by_kind": { "heading": 394646, "page": 75707, "faq": 51179 }, "selection": { "input": 521709, "dropped_low_edu": 0, "dropped_domain_cap": 177, "kept": 521532, "max_domain_share": 0.03, "min_edu": 2 } }, "val": { "conversations": 12012, "by_kind": { "heading": 9451, "page": 1431, "faq": 1130 }, "selection": { "input": 12042, "dropped_low_edu": 0, "dropped_domain_cap": 30, "kept": 12012, "max_domain_share": 0.03, "min_edu": 2 } } }, "chapters": { "none": 60570, "whitepapers": 564, "blogs": 2028, "docs": 14034, "solana": 5031, "forums": 12574, "evm-dex": 127, "defillama-chains": 120, "investors": 8339, "projects": 29154, "defillama-protocols": 6884, "raises": 163, "solana-mints-burns": 120, "solana-dex": 364, "defillama-stablecoins": 119, "token-facts": 230, "unlocks": 7 }, "domains": 2745, "contributors": [ { "spider_id": "queen-records", "name": "queen-records", "kind": "queen", "owner": null, "burn_tx": null, "pages": 45627, "tokens": 10830251 }, { "spider_id": "spider-05", "name": "spider-05", "kind": "queen", "owner": null, "burn_tx": null, "pages": 841, "tokens": 1692853 }, { "spider_id": "spider-04", "name": "spider-04", "kind": "queen", "owner": null, "burn_tx": null, "pages": 926, "tokens": 1668484 }, { "spider_id": "spider-03", "name": "spider-03", "kind": "queen", "owner": null, "burn_tx": null, "pages": 852, "tokens": 1662728 }, { "spider_id": "spider-02", "name": "spider-02", "kind": "queen", "owner": null, "burn_tx": null, "pages": 846, "tokens": 1615554 }, { "spider_id": "spider-01", "name": "spider-01", "kind": "queen", "owner": null, "burn_tx": null, "pages": 854, "tokens": 1587959 }, { "spider_id": "spider-13", "name": "spider-13", "kind": "queen", "owner": null, "burn_tx": null, "pages": 735, "tokens": 1536440 }, { "spider_id": "spider-07", "name": "spider-07", "kind": "queen", "owner": null, "burn_tx": null, "pages": 724, "tokens": 1517295 }, { "spider_id": "spider-06", "name": "spider-06", "kind": "queen", "owner": null, "burn_tx": null, "pages": 863, "tokens": 1482433 }, { "spider_id": "spider-24", "name": "spider-24", "kind": "queen", "owner": null, "burn_tx": null, "pages": 747, "tokens": 1474814 }, { "spider_id": "spider-32", "name": "spider-32", "kind": "queen", "owner": null, "burn_tx": null, "pages": 703, "tokens": 1458174 }, { "spider_id": "spider-33", "name": "spider-33", "kind": "queen", "owner": null, "burn_tx": null, "pages": 647, "tokens": 1442197 }, { "spider_id": "spider-08", "name": "spider-08", "kind": "queen", "owner": null, "burn_tx": null, "pages": 762, "tokens": 1440335 }, { "spider_id": "spider-69", "name": "spider-69", "kind": "queen", "owner": null, "burn_tx": null, "pages": 616, "tokens": 1426349 }, { "spider_id": "spider-58", "name": "spider-58", "kind": "queen", "owner": null, "burn_tx": null, "pages": 653, "tokens": 1397465 }, { "spider_id": "spider-57", "name": "spider-57", "kind": "queen", "owner": null, "burn_tx": null, "pages": 604, "tokens": 1394965 }, { "spider_id": "spider-41", "name": "spider-41", "kind": "queen", "owner": null, "burn_tx": null, "pages": 686, "tokens": 1378451 }, { "spider_id": "spider-12", "name": "spider-12", "kind": "queen", "owner": null, "burn_tx": null, "pages": 708, "tokens": 1373638 }, { "spider_id": "spider-46", "name": "spider-46", "kind": "queen", "owner": null, "burn_tx": null, "pages": 682, "tokens": 1359574 }, { "spider_id": "spider-23", "name": "spider-23", "kind": "queen", "owner": null, "burn_tx": null, "pages": 693, "tokens": 1338465 }, { "spider_id": "spider-26", "name": "spider-26", "kind": "queen", "owner": null, "burn_tx": null, "pages": 652, "tokens": 1335145 }, { "spider_id": "spider-31", "name": "spider-31", "kind": "queen", "owner": null, "burn_tx": null, "pages": 650, "tokens": 1322803 }, { "spider_id": "spider-11", "name": "spider-11", "kind": "queen", "owner": null, "burn_tx": null, "pages": 723, "tokens": 1313413 }, { "spider_id": "spider-52", "name": "spider-52", "kind": "queen", "owner": null, "burn_tx": null, "pages": 667, "tokens": 1304428 }, { "spider_id": "spider-81", "name": "spider-81", "kind": "queen", "owner": null, "burn_tx": null, "pages": 628, "tokens": 1300351 }, { "spider_id": "spider-17", "name": "spider-17", "kind": "queen", "owner": null, "burn_tx": null, "pages": 722, "tokens": 1295522 }, { "spider_id": "spider-28", "name": "spider-28", "kind": "queen", "owner": null, "burn_tx": null, "pages": 666, "tokens": 1274072 }, { "spider_id": "spider-20", "name": "spider-20", "kind": "queen", "owner": null, "burn_tx": null, "pages": 738, "tokens": 1263457 }, { "spider_id": "spider-19", "name": "spider-19", "kind": "queen", "owner": null, "burn_tx": null, "pages": 763, "tokens": 1262077 }, { "spider_id": "spider-48", "name": "spider-48", "kind": "queen", "owner": null, "burn_tx": null, "pages": 622, "tokens": 1253761 }, { "spider_id": "spider-29", "name": "spider-29", "kind": "queen", "owner": null, "burn_tx": null, "pages": 688, "tokens": 1244215 }, { "spider_id": "spider-25", "name": "spider-25", "kind": "queen", "owner": null, "burn_tx": null, "pages": 689, "tokens": 1241588 }, { "spider_id": "spider-65", "name": "spider-65", "kind": "queen", "owner": null, "burn_tx": null, "pages": 662, "tokens": 1236627 }, { "spider_id": "spider-45", "name": "spider-45", "kind": "queen", "owner": null, "burn_tx": null, "pages": 646, "tokens": 1227888 }, { "spider_id": "spider-38", "name": "spider-38", "kind": "queen", "owner": null, "burn_tx": null, "pages": 629, "tokens": 1223193 }, { "spider_id": "spider-14", "name": "spider-14", "kind": "queen", "owner": null, "burn_tx": null, "pages": 700, "tokens": 1218348 }, { "spider_id": "spider-40", "name": "spider-40", "kind": "queen", "owner": null, "burn_tx": null, "pages": 684, "tokens": 1205962 }, { "spider_id": "spider-21", "name": "spider-21", "kind": "queen", "owner": null, "burn_tx": null, "pages": 691, "tokens": 1205224 }, { "spider_id": "spider-66", "name": "spider-66", "kind": "queen", "owner": null, "burn_tx": null, "pages": 676, "tokens": 1199029 }, { "spider_id": "spider-22", "name": "spider-22", "kind": "queen", "owner": null, "burn_tx": null, "pages": 701, "tokens": 1196474 }, { "spider_id": "spider-15", "name": "spider-15", "kind": "queen", "owner": null, "burn_tx": null, "pages": 680, "tokens": 1187175 }, { "spider_id": "spider-10", "name": "spider-10", "kind": "queen", "owner": null, "burn_tx": null, "pages": 675, "tokens": 1181301 }, { "spider_id": "spider-70", "name": "spider-70", "kind": "queen", "owner": null, "burn_tx": null, "pages": 617, "tokens": 1169522 }, { "spider_id": "spider-49", "name": "spider-49", "kind": "queen", "owner": null, "burn_tx": null, "pages": 634, "tokens": 1159457 }, { "spider_id": "spider-39", "name": "spider-39", "kind": "queen", "owner": null, "burn_tx": null, "pages": 664, "tokens": 1137328 }, { "spider_id": "spider-34", "name": "spider-34", "kind": "queen", "owner": null, "burn_tx": null, "pages": 686, "tokens": 1136731 }, { "spider_id": "spider-42", "name": "spider-42", "kind": "queen", "owner": null, "burn_tx": null, "pages": 609, "tokens": 1136613 }, { "spider_id": "spider-73", "name": "spider-73", "kind": "queen", "owner": null, "burn_tx": null, "pages": 595, "tokens": 1132373 }, { "spider_id": "spider-64", "name": "spider-64", "kind": "queen", "owner": null, "burn_tx": null, "pages": 617, "tokens": 1117763 }, { "spider_id": "spider-82", "name": "spider-82", "kind": "queen", "owner": null, "burn_tx": null, "pages": 590, "tokens": 1117054 }, { "spider_id": "spider-09", "name": "spider-09", "kind": "queen", "owner": null, "burn_tx": null, "pages": 693, "tokens": 1113423 }, { "spider_id": "spider-75", "name": "spider-75", "kind": "queen", "owner": null, "burn_tx": null, "pages": 577, "tokens": 1104448 }, { "spider_id": "spider-101", "name": "spider-101", "kind": "queen", "owner": null, "burn_tx": null, "pages": 495, "tokens": 1090813 }, { "spider_id": "spider-67", "name": "spider-67", "kind": "queen", "owner": null, "burn_tx": null, "pages": 600, "tokens": 1085070 }, { "spider_id": "spider-36", "name": "spider-36", "kind": "queen", "owner": null, "burn_tx": null, "pages": 648, "tokens": 1082160 }, { "spider_id": "spider-27", "name": "spider-27", "kind": "queen", "owner": null, "burn_tx": null, "pages": 678, "tokens": 1075869 }, { "spider_id": "spider-18", "name": "spider-18", "kind": "queen", "owner": null, "burn_tx": null, "pages": 677, "tokens": 1066376 }, { "spider_id": "spider-71", "name": "spider-71", "kind": "queen", "owner": null, "burn_tx": null, "pages": 612, "tokens": 1059893 }, { "spider_id": "spider-30", "name": "spider-30", "kind": "queen", "owner": null, "burn_tx": null, "pages": 657, "tokens": 1056643 }, { "spider_id": "spider-44", "name": "spider-44", "kind": "queen", "owner": null, "burn_tx": null, "pages": 590, "tokens": 1048690 }, { "spider_id": "spider-43", "name": "spider-43", "kind": "queen", "owner": null, "burn_tx": null, "pages": 656, "tokens": 1048301 }, { "spider_id": "spider-35", "name": "spider-35", "kind": "queen", "owner": null, "burn_tx": null, "pages": 590, "tokens": 1047010 }, { "spider_id": "spider-60", "name": "spider-60", "kind": "queen", "owner": null, "burn_tx": null, "pages": 609, "tokens": 1038729 }, { "spider_id": "spider-85", "name": "spider-85", "kind": "queen", "owner": null, "burn_tx": null, "pages": 533, "tokens": 1037504 }, { "spider_id": "spider-86", "name": "spider-86", "kind": "queen", "owner": null, "burn_tx": null, "pages": 511, "tokens": 1031582 }, { "spider_id": "spider-72", "name": "spider-72", "kind": "queen", "owner": null, "burn_tx": null, "pages": 617, "tokens": 1022998 }, { "spider_id": "spider-123", "name": "spider-123", "kind": "queen", "owner": null, "burn_tx": null, "pages": 390, "tokens": 1020861 }, { "spider_id": "spider-62", "name": "spider-62", "kind": "queen", "owner": null, "burn_tx": null, "pages": 588, "tokens": 1008813 }, { "spider_id": "spider-109", "name": "spider-109", "kind": "queen", "owner": null, "burn_tx": null, "pages": 519, "tokens": 994913 }, { "spider_id": "spider-87", "name": "spider-87", "kind": "queen", "owner": null, "burn_tx": null, "pages": 511, "tokens": 992120 }, { "spider_id": "spider-54", "name": "spider-54", "kind": "queen", "owner": null, "burn_tx": null, "pages": 651, "tokens": 991981 }, { "spider_id": "spider-97", "name": "spider-97", "kind": "queen", "owner": null, "burn_tx": null, "pages": 524, "tokens": 988073 }, { "spider_id": "spider-68", "name": "spider-68", "kind": "queen", "owner": null, "burn_tx": null, "pages": 607, "tokens": 985389 }, { "spider_id": "spider-63", "name": "spider-63", "kind": "queen", "owner": null, "burn_tx": null, "pages": 592, "tokens": 981462 }, { "spider_id": "spider-98", "name": "spider-98", "kind": "queen", "owner": null, "burn_tx": null, "pages": 568, "tokens": 977601 }, { "spider_id": "spider-61", "name": "spider-61", "kind": "queen", "owner": null, "burn_tx": null, "pages": 606, "tokens": 977574 }, { "spider_id": "spider-16", "name": "spider-16", "kind": "queen", "owner": null, "burn_tx": null, "pages": 689, "tokens": 975878 }, { "spider_id": "spider-51", "name": "spider-51", "kind": "queen", "owner": null, "burn_tx": null, "pages": 649, "tokens": 973831 }, { "spider_id": "spider-77", "name": "spider-77", "kind": "queen", "owner": null, "burn_tx": null, "pages": 528, "tokens": 973816 }, { "spider_id": "spider-83", "name": "spider-83", "kind": "queen", "owner": null, "burn_tx": null, "pages": 549, "tokens": 966853 }, { "spider_id": "spider-90", "name": "spider-90", "kind": "queen", "owner": null, "burn_tx": null, "pages": 509, "tokens": 963175 }, { "spider_id": "spider-135", "name": "spider-135", "kind": "queen", "owner": null, "burn_tx": null, "pages": 368, "tokens": 962209 }, { "spider_id": "spider-47", "name": "spider-47", "kind": "queen", "owner": null, "burn_tx": null, "pages": 614, "tokens": 960974 }, { "spider_id": "spider-93", "name": "spider-93", "kind": "queen", "owner": null, "burn_tx": null, "pages": 485, "tokens": 960061 }, { "spider_id": "spider-79", "name": "spider-79", "kind": "queen", "owner": null, "burn_tx": null, "pages": 536, "tokens": 957583 }, { "spider_id": "spider-59", "name": "spider-59", "kind": "queen", "owner": null, "burn_tx": null, "pages": 529, "tokens": 953718 }, { "spider_id": "spider-76", "name": "spider-76", "kind": "queen", "owner": null, "burn_tx": null, "pages": 575, "tokens": 953181 }, { "spider_id": "spider-92", "name": "spider-92", "kind": "queen", "owner": null, "burn_tx": null, "pages": 525, "tokens": 952317 }, { "spider_id": "spider-50", "name": "spider-50", "kind": "queen", "owner": null, "burn_tx": null, "pages": 617, "tokens": 950383 }, { "spider_id": "spider-96", "name": "spider-96", "kind": "queen", "owner": null, "burn_tx": null, "pages": 545, "tokens": 948223 }, { "spider_id": "spider-89", "name": "spider-89", "kind": "queen", "owner": null, "burn_tx": null, "pages": 517, "tokens": 937528 }, { "spider_id": "spider-108", "name": "spider-108", "kind": "queen", "owner": null, "burn_tx": null, "pages": 510, "tokens": 933970 }, { "spider_id": "spider-99", "name": "spider-99", "kind": "queen", "owner": null, "burn_tx": null, "pages": 540, "tokens": 928101 }, { "spider_id": "spider-53", "name": "spider-53", "kind": "queen", "owner": null, "burn_tx": null, "pages": 552, "tokens": 926608 }, { "spider_id": "spider-80", "name": "spider-80", "kind": "queen", "owner": null, "burn_tx": null, "pages": 530, "tokens": 923432 }, { "spider_id": "spider-84", "name": "spider-84", "kind": "queen", "owner": null, "burn_tx": null, "pages": 515, "tokens": 922461 }, { "spider_id": "spider-95", "name": "spider-95", "kind": "queen", "owner": null, "burn_tx": null, "pages": 452, "tokens": 921857 }, { "spider_id": "spider-37", "name": "spider-37", "kind": "queen", "owner": null, "burn_tx": null, "pages": 606, "tokens": 920668 }, { "spider_id": "spider-78", "name": "spider-78", "kind": "queen", "owner": null, "burn_tx": null, "pages": 536, "tokens": 912846 }, { "spider_id": "spider-144", "name": "spider-144", "kind": "queen", "owner": null, "burn_tx": null, "pages": 408, "tokens": 905626 }, { "spider_id": "spider-100", "name": "spider-100", "kind": "queen", "owner": null, "burn_tx": null, "pages": 504, "tokens": 896326 }, { "spider_id": "spider-55", "name": "spider-55", "kind": "queen", "owner": null, "burn_tx": null, "pages": 581, "tokens": 895110 }, { "spider_id": "spider-56", "name": "spider-56", "kind": "queen", "owner": null, "burn_tx": null, "pages": 593, "tokens": 881178 }, { "spider_id": "spider-114", "name": "spider-114", "kind": "queen", "owner": null, "burn_tx": null, "pages": 400, "tokens": 872805 }, { "spider_id": "spider-118", "name": "spider-118", "kind": "queen", "owner": null, "burn_tx": null, "pages": 355, "tokens": 857226 }, { "spider_id": "spider-139", "name": "spider-139", "kind": "queen", "owner": null, "burn_tx": null, "pages": 372, "tokens": 855311 }, { "spider_id": "spider-134", "name": "spider-134", "kind": "queen", "owner": null, "burn_tx": null, "pages": 406, "tokens": 854840 }, { "spider_id": "spider-104", "name": "spider-104", "kind": "queen", "owner": null, "burn_tx": null, "pages": 515, "tokens": 836639 }, { "spider_id": "spider-149", "name": "spider-149", "kind": "queen", "owner": null, "burn_tx": null, "pages": 337, "tokens": 829398 }, { "spider_id": "spider-103", "name": "spider-103", "kind": "queen", "owner": null, "burn_tx": null, "pages": 492, "tokens": 812322 }, { "spider_id": "spider-166", "name": "spider-166", "kind": "queen", "owner": null, "burn_tx": null, "pages": 349, "tokens": 807096 }, { "spider_id": "spider-91", "name": "spider-91", "kind": "queen", "owner": null, "burn_tx": null, "pages": 507, "tokens": 806440 }, { "spider_id": "spider-107", "name": "spider-107", "kind": "queen", "owner": null, "burn_tx": null, "pages": 519, "tokens": 804924 }, { "spider_id": "spider-148", "name": "spider-148", "kind": "queen", "owner": null, "burn_tx": null, "pages": 355, "tokens": 803132 }, { "spider_id": "spider-88", "name": "spider-88", "kind": "queen", "owner": null, "burn_tx": null, "pages": 500, "tokens": 798800 }, { "spider_id": "spider-106", "name": "spider-106", "kind": "queen", "owner": null, "burn_tx": null, "pages": 512, "tokens": 796260 }, { "spider_id": "spider-94", "name": "spider-94", "kind": "queen", "owner": null, "burn_tx": null, "pages": 532, "tokens": 791025 }, { "spider_id": "spider-156", "name": "spider-156", "kind": "queen", "owner": null, "burn_tx": null, "pages": 397, "tokens": 788783 }, { "spider_id": "spider-140", "name": "spider-140", "kind": "queen", "owner": null, "burn_tx": null, "pages": 339, "tokens": 783380 }, { "spider_id": "spider-119", "name": "spider-119", "kind": "queen", "owner": null, "burn_tx": null, "pages": 407, "tokens": 781758 }, { "spider_id": "spider-161", "name": "spider-161", "kind": "queen", "owner": null, "burn_tx": null, "pages": 348, "tokens": 777115 }, { "spider_id": "spider-154", "name": "spider-154", "kind": "queen", "owner": null, "burn_tx": null, "pages": 371, "tokens": 775887 }, { "spider_id": "spider-110", "name": "spider-110", "kind": "queen", "owner": null, "burn_tx": null, "pages": 465, "tokens": 766973 }, { "spider_id": "spider-102", "name": "spider-102", "kind": "queen", "owner": null, "burn_tx": null, "pages": 487, "tokens": 764842 }, { "spider_id": "spider-143", "name": "spider-143", "kind": "queen", "owner": null, "burn_tx": null, "pages": 400, "tokens": 758536 }, { "spider_id": "spider-113", "name": "spider-113", "kind": "queen", "owner": null, "burn_tx": null, "pages": 373, "tokens": 754280 }, { "spider_id": "spider-74", "name": "spider-74", "kind": "queen", "owner": null, "burn_tx": null, "pages": 557, "tokens": 748295 }, { "spider_id": "spider-167", "name": "spider-167", "kind": "queen", "owner": null, "burn_tx": null, "pages": 334, "tokens": 748128 }, { "spider_id": "spider-145", "name": "spider-145", "kind": "queen", "owner": null, "burn_tx": null, "pages": 385, "tokens": 741840 }, { "spider_id": "spider-151", "name": "spider-151", "kind": "queen", "owner": null, "burn_tx": null, "pages": 359, "tokens": 741547 }, { "spider_id": "spider-116", "name": "spider-116", "kind": "queen", "owner": null, "burn_tx": null, "pages": 391, "tokens": 738707 }, { "spider_id": "spider-132", "name": "spider-132", "kind": "queen", "owner": null, "burn_tx": null, "pages": 364, "tokens": 736976 }, { "spider_id": "spider-105", "name": "spider-105", "kind": "queen", "owner": null, "burn_tx": null, "pages": 456, "tokens": 735612 }, { "spider_id": "spider-121", "name": "spider-121", "kind": "queen", "owner": null, "burn_tx": null, "pages": 369, "tokens": 729813 }, { "spider_id": "spider-153", "name": "spider-153", "kind": "queen", "owner": null, "burn_tx": null, "pages": 397, "tokens": 720902 }, { "spider_id": "spider-138", "name": "spider-138", "kind": "queen", "owner": null, "burn_tx": null, "pages": 353, "tokens": 717669 }, { "spider_id": "spider-122", "name": "spider-122", "kind": "queen", "owner": null, "burn_tx": null, "pages": 354, "tokens": 714317 }, { "spider_id": "spider-180", "name": "spider-180", "kind": "queen", "owner": null, "burn_tx": null, "pages": 306, "tokens": 709530 }, { "spider_id": "spider-125", "name": "spider-125", "kind": "queen", "owner": null, "burn_tx": null, "pages": 374, "tokens": 699434 }, { "spider_id": "spider-150", "name": "spider-150", "kind": "queen", "owner": null, "burn_tx": null, "pages": 360, "tokens": 698648 }, { "spider_id": "spider-146", "name": "spider-146", "kind": "queen", "owner": null, "burn_tx": null, "pages": 401, "tokens": 685836 }, { "spider_id": "spider-126", "name": "spider-126", "kind": "queen", "owner": null, "burn_tx": null, "pages": 351, "tokens": 683075 }, { "spider_id": "spider-176", "name": "spider-176", "kind": "queen", "owner": null, "burn_tx": null, "pages": 312, "tokens": 680954 }, { "spider_id": "spider-129", "name": "spider-129", "kind": "queen", "owner": null, "burn_tx": null, "pages": 383, "tokens": 675353 }, { "spider_id": "spider-158", "name": "spider-158", "kind": "queen", "owner": null, "burn_tx": null, "pages": 325, "tokens": 667011 }, { "spider_id": "spider-160", "name": "spider-160", "kind": "queen", "owner": null, "burn_tx": null, "pages": 319, "tokens": 661323 }, { "spider_id": "spider-157", "name": "spider-157", "kind": "queen", "owner": null, "burn_tx": null, "pages": 380, "tokens": 648929 }, { "spider_id": "spider-127", "name": "spider-127", "kind": "queen", "owner": null, "burn_tx": null, "pages": 377, "tokens": 646950 }, { "spider_id": "spider-162", "name": "spider-162", "kind": "queen", "owner": null, "burn_tx": null, "pages": 336, "tokens": 643737 }, { "spider_id": "spider-120", "name": "spider-120", "kind": "queen", "owner": null, "burn_tx": null, "pages": 350, "tokens": 641282 }, { "spider_id": "spider-159", "name": "spider-159", "kind": "queen", "owner": null, "burn_tx": null, "pages": 372, "tokens": 639210 }, { "spider_id": "spider-128", "name": "spider-128", "kind": "queen", "owner": null, "burn_tx": null, "pages": 379, "tokens": 629538 }, { "spider_id": "spider-163", "name": "spider-163", "kind": "queen", "owner": null, "burn_tx": null, "pages": 375, "tokens": 622387 }, { "spider_id": "spider-137", "name": "spider-137", "kind": "queen", "owner": null, "burn_tx": null, "pages": 382, "tokens": 621373 }, { "spider_id": "spider-155", "name": "spider-155", "kind": "queen", "owner": null, "burn_tx": null, "pages": 361, "tokens": 616713 }, { "spider_id": "spider-136", "name": "spider-136", "kind": "queen", "owner": null, "burn_tx": null, "pages": 359, "tokens": 581199 }, { "spider_id": "spider-173", "name": "spider-173", "kind": "queen", "owner": null, "burn_tx": null, "pages": 352, "tokens": 577298 }, { "spider_id": "spider-131", "name": "spider-131", "kind": "queen", "owner": null, "burn_tx": null, "pages": 366, "tokens": 576070 }, { "spider_id": "spider-112", "name": "spider-112", "kind": "queen", "owner": null, "burn_tx": null, "pages": 355, "tokens": 574960 }, { "spider_id": "spider-111", "name": "spider-111", "kind": "queen", "owner": null, "burn_tx": null, "pages": 307, "tokens": 574400 }, { "spider_id": "spider-165", "name": "spider-165", "kind": "queen", "owner": null, "burn_tx": null, "pages": 297, "tokens": 573245 }, { "spider_id": "spider-177", "name": "spider-177", "kind": "queen", "owner": null, "burn_tx": null, "pages": 338, "tokens": 571467 }, { "spider_id": "spider-147", "name": "spider-147", "kind": "queen", "owner": null, "burn_tx": null, "pages": 305, "tokens": 569516 }, { "spider_id": "spider-171", "name": "spider-171", "kind": "queen", "owner": null, "burn_tx": null, "pages": 309, "tokens": 567054 }, { "spider_id": "spider-115", "name": "spider-115", "kind": "queen", "owner": null, "burn_tx": null, "pages": 341, "tokens": 566272 }, { "spider_id": "spider-141", "name": "spider-141", "kind": "queen", "owner": null, "burn_tx": null, "pages": 375, "tokens": 564651 }, { "spider_id": "spider-124", "name": "spider-124", "kind": "queen", "owner": null, "burn_tx": null, "pages": 324, "tokens": 561483 }, { "spider_id": "spider-130", "name": "spider-130", "kind": "queen", "owner": null, "burn_tx": null, "pages": 346, "tokens": 558800 }, { "spider_id": "spider-133", "name": "spider-133", "kind": "queen", "owner": null, "burn_tx": null, "pages": 344, "tokens": 557752 }, { "spider_id": "spider-142", "name": "spider-142", "kind": "queen", "owner": null, "burn_tx": null, "pages": 344, "tokens": 552839 }, { "spider_id": "spider-117", "name": "spider-117", "kind": "queen", "owner": null, "burn_tx": null, "pages": 361, "tokens": 525406 }, { "spider_id": "spider-183", "name": "spider-183", "kind": "queen", "owner": null, "burn_tx": null, "pages": 317, "tokens": 523941 }, { "spider_id": "spider-174", "name": "spider-174", "kind": "queen", "owner": null, "burn_tx": null, "pages": 273, "tokens": 490409 }, { "spider_id": "spider-181", "name": "spider-181", "kind": "queen", "owner": null, "burn_tx": null, "pages": 257, "tokens": 488999 }, { "spider_id": "spider-169", "name": "spider-169", "kind": "queen", "owner": null, "burn_tx": null, "pages": 284, "tokens": 487042 }, { "spider_id": "spider-152", "name": "spider-152", "kind": "queen", "owner": null, "burn_tx": null, "pages": 336, "tokens": 483309 }, { "spider_id": "spider-164", "name": "spider-164", "kind": "queen", "owner": null, "burn_tx": null, "pages": 295, "tokens": 459644 }, { "spider_id": "spider-182", "name": "spider-182", "kind": "queen", "owner": null, "burn_tx": null, "pages": 308, "tokens": 452045 }, { "spider_id": "spider-175", "name": "spider-175", "kind": "queen", "owner": null, "burn_tx": null, "pages": 244, "tokens": 436415 }, { "spider_id": "spider-168", "name": "spider-168", "kind": "queen", "owner": null, "burn_tx": null, "pages": 309, "tokens": 436316 }, { "spider_id": "spider-179", "name": "spider-179", "kind": "queen", "owner": null, "burn_tx": null, "pages": 267, "tokens": 425945 }, { "spider_id": "spider-172", "name": "spider-172", "kind": "queen", "owner": null, "burn_tx": null, "pages": 254, "tokens": 399802 }, { "spider_id": "spider-170", "name": "spider-170", "kind": "queen", "owner": null, "burn_tx": null, "pages": 246, "tokens": 385536 }, { "spider_id": "spider-178", "name": "spider-178", "kind": "queen", "owner": null, "burn_tx": null, "pages": 260, "tokens": 363115 }, { "spider_id": "spider-189", "name": "spider-189", "kind": "queen", "owner": null, "burn_tx": null, "pages": 121, "tokens": 328039 }, { "spider_id": "spider-191", "name": "spider-191", "kind": "queen", "owner": null, "burn_tx": null, "pages": 125, "tokens": 286249 }, { "spider_id": "spider-188", "name": "spider-188", "kind": "queen", "owner": null, "burn_tx": null, "pages": 145, "tokens": 267474 }, { "spider_id": "spider-185", "name": "spider-185", "kind": "queen", "owner": null, "burn_tx": null, "pages": 152, "tokens": 246111 }, { "spider_id": "spider-184", "name": "spider-184", "kind": "queen", "owner": null, "burn_tx": null, "pages": 178, "tokens": 214114 }, { "spider_id": "spider-186", "name": "spider-186", "kind": "queen", "owner": null, "burn_tx": null, "pages": 140, "tokens": 209374 }, { "spider_id": "spider-187", "name": "spider-187", "kind": "queen", "owner": null, "burn_tx": null, "pages": 113, "tokens": 158597 }, { "spider_id": "spider-193", "name": "spider-193", "kind": "queen", "owner": null, "burn_tx": null, "pages": 75, "tokens": 142691 }, { "spider_id": "spider-190", "name": "spider-190", "kind": "queen", "owner": null, "burn_tx": null, "pages": 85, "tokens": 140273 }, { "spider_id": "spider-194", "name": "spider-194", "kind": "queen", "owner": null, "burn_tx": null, "pages": 50, "tokens": 105080 }, { "spider_id": "spider-192", "name": "spider-192", "kind": "queen", "owner": null, "burn_tx": null, "pages": 48, "tokens": 65896 }, { "spider_id": "spider-195", "name": "spider-195", "kind": "queen", "owner": null, "burn_tx": null, "pages": 29, "tokens": 39995 } ], "contributors_exported_at": null, "recipe": { "lang": true, "url_filters": true, "x_filter": true, "wiki_tails": true, "token_chunks": true, "stream": true, "records_forms": true, "qa_decay": true, "source_line": true, "headings": "v31", "pass_scale": 2.0, "domain_cap": 0.05, "decay_frac": 0.2, "qa_share": 0.25, "qa_max_heading_pairs": 100000, "lid_threshold": 0.65, "headings_min_edu": 2, "headings_max_domain_share": 0.03, "recipe": "v31", "chunk_tokens": 2040, "labels": null, "shard_chars": 200000000, "row_group": 256, "bench_protocols": null, "lid_model": "lid.176.bin" }, "val": { "source": "external held-out set", "dataset": "heldout-q31", "manifest_sha256": "7efdd2af22792322c436c80449fe6153083d59a95a0605ee4eab29459657d584" }, "heldout_exclusions": { "files": [ "exclude.json" ], "urls": 2000, "sha256": 2000, "dropped": 2000 }, "records": { "parsed": { "chain": 120, "investor": 8339, "project": 29103, "protocol": 6884, "raises": 163, "stablecoin": 119, "token_facts": 230 }, "unparsed": { "project": 51 }, "forms": { "chain": 960, "investor": 25017, "project": 87270, "protocol": 54366, "raises": 1304, "stablecoin": 952, "token_facts": 1840 }, "qa_forms": 95325, "leak_audit_dropped": {} }, "stream": { "pass_scale": 2.0, "seed": 0, "passes_table": { "edu": { "0": 0, "1": 1, "2": 2, "3": 4, "4": 6, "5": 8 }, "good_min": 6, "unlabeled": { "good": 6, "none": 2, "crawl": 4, "records": 4, "form": 2 } }, "domain_cap": 0.05, "units": { "page": 144359, "records": 46508, "form": 172975 }, "unique_tokens": { "page": 172076164, "records": 10794512, "form": 10382023 }, "source_line": { "on": true, "plain_from": 0.9, "units_with_source": 363842 }, "classes": { "form": { "units": 172975, "occurrences": 691900, "tokens": 41528092, "passes_mean": 4.0 }, "good": { "units": 25214, "occurrences": 299656, "tokens": 361754490, "passes_mean": 11.885 }, "normal": { "units": 29666, "occurrences": 237328, "tokens": 277729504, "passes_mean": 8.0 }, "records": { "units": 46508, "occurrences": 372064, "tokens": 86356096, "passes_mean": 8.0 }, "weak": { "units": 89479, "occurrences": 357916, "tokens": 427320188, "passes_mean": 4.0 } }, "top_sources": [ [ "records", 0.107 ], [ "en.wikipedia.org", 0.05 ], [ "forum.arbitrum.foundation", 0.0403 ], [ "github.com", 0.0247 ], [ "ethereum-magicians.org", 0.0216 ], [ "gov.optimism.io", 0.0211 ], [ "docs.chain.link", 0.0172 ], [ "polymarket.com", 0.016 ], [ "governance.aave.com", 0.0149 ], [ "solanacompass.com", 0.0148 ], [ "galaxy.com", 0.0145 ], [ "rapidinnovation.io", 0.0134 ], [ "cryptoslate.com", 0.0119 ], [ "gov.uniswap.org", 0.0116 ], [ "research.lido.fi", 0.0111 ], [ "ethresear.ch", 0.0096 ], [ "ethereum.org", 0.0094 ], [ "bitcoin.org", 0.0091 ], [ "forum.balancer.fi", 0.0085 ], [ "eips.ethereum.org", 0.0085 ] ], "capped_domains": [ { "domain": "en.wikipedia.org", "share_before": 0.0536, "factor": 0.9284 } ], "records_share": 0.107, "forms_share": 0.0348, "occurrences": 1958864, "decay": { "frac": 0.2, "tokens_target": 254254181, "qa": { "pairs": 222270, "docs": 120947, "tokens": 54219003, "target_tokens": 63563545, "reps": 4, "formats": { "question_answer": 40240, "faq": 40316, "q_a": 40391 }, "short_of_target": true }, "qa_tokens": 54980953, "moved_tokens": 199273784, "moved_good_tokens": 199273784, "moved_documents": 481891, "qa_share": 0.2162, "documents": 602838, "shards": 6 }, "tokens": { "main": 1008433578, "decay": 254254737, "total": 1262688315 }, "documents": { "main": 1476973, "decay": 602838 }, "dirs": { "main": "nanochat/stream/main", "decay": "nanochat/stream/decay" }, "qa_pairs": { "records": 90597, "faq": 51183, "heading": 68002, "page": 12488 } }, "contamination": { "bench_files": { "arc_easy_test.json": { "sha256": "76e55faa15bce1b6ef26212c0c67a242a39952088d3b9e1a4d6071ea33c15190", "items": 2376 }, "cryptomc.json": { "sha256": "c81b3367d654f1e207d2dcbb48f490ff5feb496e2d08a049d39fb8aa8de35f87", "items": 150 }, "cryptoterms.json": { "sha256": "918b257c12deac8818cebf271187eedd88f026f875908b5a2e6987434b991f90", "items": 150 }, "ctslang.json": { "sha256": "d967e9196888027a4055592381892fca6185ee3a41b70be6a7351fa06d0bfc70", "items": 150 }, "projectid.json": { "sha256": "6feec798ea7269d2931fba111c48b33af2030a885e4c589235072ca6e488f51e", "items": 200 }, "projectid_xl.json": { "sha256": "859b5fc0d6a197bdf38e09e980d4577bd32f321e4fb3aec674725b6e4ed9a709", "items": 2593 }, "qa.json": { "sha256": "d5f699bdec9dca94e355332380adf317ef497784a56d3d9277ca6c0f993af9c1", "items": 100 } }, "skipped_files": [ "._arc_easy_test.json", "._cryptomc.json", "._cryptoterms.json", "._ctslang.json", "._fresh_pages.json", "._fresh_pages_log.json", "._grade-0.json", "._grade-1.json", "._grade-2.json", "._grade-3.json", "._grade-4.json", "._grade-key.json", "._grade2-a.json", "._grade2-b.json", "._grade2-c.json", "._grade2-grades.json", "._grade2-key.json", "._grade3-a.json", "._grade3-b.json", "._grade3-c.json", "._grade3-grades.json", "._grade3-key.json", "._models.json", "._projectid.json", "._projectid_bench_protocols.json", "._projectid_defillama_raw.json", "._projectid_meta.json", "._projectid_results.json", "._projectid_results_detail.json", "._projectid_split.json", "._projectid_xl.json", "._projectid_xl_meta.json", "._qa.json", "._qa_answers.json", "._report_q31.json", "._results.json", "._results_ctslang.json", "._results_ctslang_detail.json", "._results_detail.json", "._results_domain.json", "._results_domain_detail.json", "._smoke.json", "._web_snapshot.json", "fresh_pages.json", "fresh_pages_log.json", "grade-0.json", "grade-1.json", "grade-2.json", "grade-3.json", "grade-4.json", "grade-key.json", "grade2-a.json", "grade2-b.json", "grade2-c.json", "grade2-grades.json", "grade2-key.json", "grade3-a.json", "grade3-b.json", "grade3-c.json", "grade3-grades.json", "grade3-key.json", "models.json", "projectid_bench_protocols.json", "projectid_defillama_raw.json", "projectid_meta.json", "projectid_results.json", "projectid_results_detail.json", "projectid_split.json", "projectid_xl_meta.json", "qa_answers.json", "report_q31.json", "results.json", "results_ctslang.json", "results_ctslang_detail.json", "results_detail.json", "results_domain.json", "results_domain_detail.json", "smoke.json", "web_snapshot.json" ], "criteria": { "ngram13": 13, "ngram8": 8, "ngram8_share": 0.7, "question_min_words_in_text": 5, "answer_within_words": 100 }, "dropped": { "chunks": 0, "records_forms": 0, "qa_pairs": 753, "headings.train": 1136, "headings.val": 36 }, "checked": "on", "by_criterion": { "qa_pairs": { "question": 752, "ngram8_70": 3, "question_answer": 1, "ngram13": 1 }, "headings.train": { "question": 1132, "ngram13": 4, "ngram8_70": 4, "question_answer": 4 }, "headings.val": { "question": 36 } }, "by_bench": { "qa_pairs": { "qa.json": 751, "cryptomc.json": 8, "cryptoterms.json": 1 }, "headings.train": { "qa.json": 1129, "cryptomc.json": 16, "cryptoterms.json": 3 }, "headings.val": { "qa.json": 36 } }, "bench_fingerprint": "656b4d7aa50c7d85e43d3915aae7dce568d54be7842219a97db529bbc349c125" }, "labels": null, "bench_protocols": { "list": { "file": "projectid_bench_protocols.json", "sha256": "4e4f7eaae1e655f2ccc53de0b701ee20a0cea50be540024d6ec4cdeb6eef7471", "keys": 2222, "urls": 1922 }, "protocol_records": 6884, "bench_records": 1707, "synth_deny_list": { "file": "stream_src/synth_deny.txt", "urls": 1707, "every_protocol": false }, "qa_forms_left_out": 4725 }, "restreamed_at": "2026-10-07T01:32:05+00:00" }