{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7MWNXBARHJ7UPFAIZQTXVUNKPM","short_pith_number":"pith:7MWNXBAR","canonical_record":{"source":{"id":"2501.07721","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-13T22:14:45Z","cross_cats_sorted":[],"title_canon_sha256":"6d00bc781592326e2015c65b31dfa4d979971f620f6886b261c32769d52e637f","abstract_canon_sha256":"2ce222ec98c4d2d45a4d414bf5ac43ed67a132f059a7921f98b79e969a81bf9f"},"schema_version":"1.0"},"canonical_sha256":"fb2cdb84113a7f479408cc277ad1aa7b07a54c89c6aa9895730781c9108d3790","source":{"kind":"arxiv","id":"2501.07721","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7MWNXBARHJ7UPFAIZQTXVUNKPM","target":"record","payload":{"canonical_record":{"source":{"id":"2501.07721","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-13T22:14:45Z","cross_cats_sorted":[],"title_canon_sha256":"6d00bc781592326e2015c65b31dfa4d979971f620f6886b261c32769d52e637f","abstract_canon_sha256":"2ce222ec98c4d2d45a4d414bf5ac43ed67a132f059a7921f98b79e969a81bf9f"},"schema_version":"1.0"},"canonical_sha256":"fb2cdb84113a7f479408cc277ad1aa7b07a54c89c6aa9895730781c9108d3790","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:49.069844Z","signature_b64":"9yAITOf7gjZtFsX5EOKgMNlGsg5xeJ96VJ8/N2Lnh7gkvVq72SrH01/TQCOtuFGc2tSMt0BBKYymtcqxvQvtBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb2cdb84113a7f479408cc277ad1aa7b07a54c89c6aa9895730781c9108d3790","last_reissued_at":"2026-07-05T10:00:49.069398Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:49.069398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.07721","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:00:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HcDhLH1/utTARvMjYyYbEDgOi1b17LuQmfYKZddLYrSPZ3oE2l8+eYb7v8RPvRCCNQ2FYJ+DtBQFpC1o+taUBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:54:25.186986Z"},"content_sha256":"1a39c1ebe11e5973f9265f380157ae7b6f7b645fff4ceb1bb6ea0001d35593d4","schema_version":"1.0","event_id":"sha256:1a39c1ebe11e5973f9265f380157ae7b6f7b645fff4ceb1bb6ea0001d35593d4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7MWNXBARHJ7UPFAIZQTXVUNKPM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLMic: Romanian Foundation Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexandru Agache, Alexandru M. Gherghescu, Costin Raiciu, Mihai-Valentin Dumitru, Vlad-Andrei B\\u{a}doiu","submitted_at":"2025-01-13T22:14:45Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07721","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2501.07721/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:00:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ul45Wo/i9wxzmxbsuKiMKJOTryuly9rTBd4+A4IlDh9RdM86Nu6qMHgRzxsRvdE7XyAQcE2St1LB06mGJz0iAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:54:25.187832Z"},"content_sha256":"d3d3f628478486598f71f76ee6c6303c8307f68b29079d81d3ab999689c99de2","schema_version":"1.0","event_id":"sha256:d3d3f628478486598f71f76ee6c6303c8307f68b29079d81d3ab999689c99de2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7MWNXBARHJ7UPFAIZQTXVUNKPM/bundle.json","state_url":"https://pith.science/pith/7MWNXBARHJ7UPFAIZQTXVUNKPM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7MWNXBARHJ7UPFAIZQTXVUNKPM/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T19:54:25Z","links":{"resolver":"https://pith.science/pith/7MWNXBARHJ7UPFAIZQTXVUNKPM","bundle":"https://pith.science/pith/7MWNXBARHJ7UPFAIZQTXVUNKPM/bundle.json","state":"https://pith.science/pith/7MWNXBARHJ7UPFAIZQTXVUNKPM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7MWNXBARHJ7UPFAIZQTXVUNKPM/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EeQw9iDjt5JKp8Y7UwxPX88o5opQsk71Vn5SFCr+w22IrT5+kP6mOJdBbCS0eoz4HIW1kT3dJNwa8b+kON6cDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T19:54:25.194958Z","bundle_sha256":"ecc5204b3315f838193396db3621da4ac1345933074f1e3fd25b89fea1338917"}}