{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7MWNXBARHJ7UPFAIZQTXVUNKPM","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":"2ce222ec98c4d2d45a4d414bf5ac43ed67a132f059a7921f98b79e969a81bf9f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-13T22:14:45Z","title_canon_sha256":"6d00bc781592326e2015c65b31dfa4d979971f620f6886b261c32769d52e637f"},"schema_version":"1.0","source":{"id":"2501.07721","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.07721","created_at":"2026-07-05T10:00:49Z"},{"alias_kind":"arxiv_version","alias_value":"2501.07721v1","created_at":"2026-07-05T10:00:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07721","created_at":"2026-07-05T10:00:49Z"},{"alias_kind":"pith_short_12","alias_value":"7MWNXBARHJ7U","created_at":"2026-07-05T10:00:49Z"},{"alias_kind":"pith_short_16","alias_value":"7MWNXBARHJ7UPFAI","created_at":"2026-07-05T10:00:49Z"},{"alias_kind":"pith_short_8","alias_value":"7MWNXBAR","created_at":"2026-07-05T10:00:49Z"}],"graph_snapshots":[{"event_id":"sha256:d3d3f628478486598f71f76ee6c6303c8307f68b29079d81d3ab999689c99de2","target":"graph","created_at":"2026-07-05T10:00:49Z","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/2501.07721/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks with commercial models leading the way. While open models usually operate at a smaller scale, they maintain competitiveness through specialization and fine-tuning. However, a significant challenge persists: open models often underperform in low-resource languages due to limited representation in the training corpus. In this paper, we present LLMic, a bilingual foundation language model designed specifically for the Romanian Language. We document the complete process of pretraining a f","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":"2025-01-13T22:14:45Z","title":"LLMic: Romanian Foundation Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07721","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":"sha256:1a39c1ebe11e5973f9265f380157ae7b6f7b645fff4ceb1bb6ea0001d35593d4","target":"record","created_at":"2026-07-05T10:00:49Z","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":"2ce222ec98c4d2d45a4d414bf5ac43ed67a132f059a7921f98b79e969a81bf9f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-13T22:14:45Z","title_canon_sha256":"6d00bc781592326e2015c65b31dfa4d979971f620f6886b261c32769d52e637f"},"schema_version":"1.0","source":{"id":"2501.07721","kind":"arxiv","version":1}},"canonical_sha256":"fb2cdb84113a7f479408cc277ad1aa7b07a54c89c6aa9895730781c9108d3790","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb2cdb84113a7f479408cc277ad1aa7b07a54c89c6aa9895730781c9108d3790","first_computed_at":"2026-07-05T10:00:49.069398Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:00:49.069398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9yAITOf7gjZtFsX5EOKgMNlGsg5xeJ96VJ8/N2Lnh7gkvVq72SrH01/TQCOtuFGc2tSMt0BBKYymtcqxvQvtBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:00:49.069844Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.07721","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1a39c1ebe11e5973f9265f380157ae7b6f7b645fff4ceb1bb6ea0001d35593d4","sha256:d3d3f628478486598f71f76ee6c6303c8307f68b29079d81d3ab999689c99de2"],"state_sha256":"3841de4afa4f484aaa9bb4a9c2383cc835a29939070b1b02bcee260f64e78b51"}