{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UVIG4V2GPYAOVPBINIE757UCHV","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":"f5d2d411cffa9042b67789d8e731e3aa7a3ff3e5836e0a0c3263069abdaec5b4","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-07T15:13:24Z","title_canon_sha256":"51a420703827c4c8d9cad76b460372492ca2dc239b5bb7b1baec8cdd4a7d2c8e"},"schema_version":"1.0","source":{"id":"2401.03515","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.03515","created_at":"2026-07-05T07:31:09Z"},{"alias_kind":"arxiv_version","alias_value":"2401.03515v1","created_at":"2026-07-05T07:31:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.03515","created_at":"2026-07-05T07:31:09Z"},{"alias_kind":"pith_short_12","alias_value":"UVIG4V2GPYAO","created_at":"2026-07-05T07:31:09Z"},{"alias_kind":"pith_short_16","alias_value":"UVIG4V2GPYAOVPBI","created_at":"2026-07-05T07:31:09Z"},{"alias_kind":"pith_short_8","alias_value":"UVIG4V2G","created_at":"2026-07-05T07:31:09Z"}],"graph_snapshots":[{"event_id":"sha256:4d032b6ff476a031c9e18da809a1da1daf61a1226c7fbee7a5914f4b9287d0d1","target":"graph","created_at":"2026-07-05T07:31:09Z","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/2401.03515/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We pretrain RoBERTa on a Turkish corpora using BPE tokenizer. Our model outperforms BERTurk family models on the BOUN dataset for the POS task while resulting in underperformance on the IMST dataset for the same task and achieving competitive scores on the Turkish split of the XTREME dataset for the NER task - all while being pretrained on smaller data than its competitors. We release our pretrained model and tokenizer.","authors_text":"Nuri Tas","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-07T15:13:24Z","title":"RoBERTurk: Adjusting RoBERTa for Turkish"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.03515","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":"sha256:19c52e90545b8ccf7b11b687c0905182da1543e6244e4db23d885e74ec46d1e1","target":"record","created_at":"2026-07-05T07:31:09Z","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":"f5d2d411cffa9042b67789d8e731e3aa7a3ff3e5836e0a0c3263069abdaec5b4","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-07T15:13:24Z","title_canon_sha256":"51a420703827c4c8d9cad76b460372492ca2dc239b5bb7b1baec8cdd4a7d2c8e"},"schema_version":"1.0","source":{"id":"2401.03515","kind":"arxiv","version":1}},"canonical_sha256":"a5506e57467e00eabc286a09fefe823d754e14604c77ddf3cad03d864f2c2e9d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a5506e57467e00eabc286a09fefe823d754e14604c77ddf3cad03d864f2c2e9d","first_computed_at":"2026-07-05T07:31:09.977740Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:31:09.977740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VyEk1TObw9GzRvuWxW41WbXoKuP6Sts1t+BGIBeHqWkadmAIHW2IWglMVqwTkx52mxj1x2PBC2172Zvb85pUAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:31:09.978222Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.03515","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:19c52e90545b8ccf7b11b687c0905182da1543e6244e4db23d885e74ec46d1e1","sha256:4d032b6ff476a031c9e18da809a1da1daf61a1226c7fbee7a5914f4b9287d0d1"],"state_sha256":"7e56fcc652cc6faf345ad99955c0796eea76ccdd3d4aae2f8c18fdd4b864dec3"}