{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WHSFZROQX36R6NRBM2X6VADVP7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"64caabc5b07575335389742686488642c02c33336ebe8e466bc291ea56485dcc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T16:32:48Z","title_canon_sha256":"28abc970555fe42fe66c710795f40ad90d149338114c875e67a8b2e28648f818"},"schema_version":"1.0","source":{"id":"2407.13657","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.13657","created_at":"2026-07-05T08:45:42Z"},{"alias_kind":"arxiv_version","alias_value":"2407.13657v1","created_at":"2026-07-05T08:45:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13657","created_at":"2026-07-05T08:45:42Z"},{"alias_kind":"pith_short_12","alias_value":"WHSFZROQX36R","created_at":"2026-07-05T08:45:42Z"},{"alias_kind":"pith_short_16","alias_value":"WHSFZROQX36R6NRB","created_at":"2026-07-05T08:45:42Z"},{"alias_kind":"pith_short_8","alias_value":"WHSFZROQ","created_at":"2026-07-05T08:45:42Z"}],"graph_snapshots":[{"event_id":"sha256:8a03da80bbbd2203693db191781f05498c4fa40b0cf785edd084f992912bc375","target":"graph","created_at":"2026-07-05T08:45:42Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2407.13657/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Research in the field of language models is rapidly evolving, with many open models being released to the public. Openly available pretraining corpora usually focus on only a handful of languages, with many others either missing completely or extremely underrepresented. In this report, we introduce FuLG, a hundred-fifty-billion-token Romanian corpus extracted from CommonCrawl. We present our methodology for filtering FuLG and compare it via ablation studies against existing Romanian corpora.","authors_text":"Alexandru Agache, Alexandru M. Gherghescu, Costin Raiciu, Mihai-Valentin Dumitru, Vlad-Andrei B\\u{a}doiu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T16:32:48Z","title":"FuLG: 150B Romanian Corpus for Language Model Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13657","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:33fd4b83887b8413a4ad18db88fe803ee55dadb70e029a0b812ea5cf828c4dd0","target":"record","created_at":"2026-07-05T08:45:42Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"64caabc5b07575335389742686488642c02c33336ebe8e466bc291ea56485dcc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T16:32:48Z","title_canon_sha256":"28abc970555fe42fe66c710795f40ad90d149338114c875e67a8b2e28648f818"},"schema_version":"1.0","source":{"id":"2407.13657","kind":"arxiv","version":1}},"canonical_sha256":"b1e45cc5d0befd1f362166afea80757ff750105bbe7648ae9e52f50ac77abaea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1e45cc5d0befd1f362166afea80757ff750105bbe7648ae9e52f50ac77abaea","first_computed_at":"2026-07-05T08:45:42.051745Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:42.051745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ns+zdx/FtZ99k0mD42fbtxLy5AUJIE6M7i/OL8xJtTZi2UEf/cgkh2G9ohBrve8SpZtcTY+RQ18jzwZB59peBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:42.052175Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.13657","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:33fd4b83887b8413a4ad18db88fe803ee55dadb70e029a0b812ea5cf828c4dd0","sha256:8a03da80bbbd2203693db191781f05498c4fa40b0cf785edd084f992912bc375"],"state_sha256":"0fcaed14021b00e73153585c274d8e5573804ad38fff1c9741325802174085a8"}